diff options
| author | Ralph Amissah <ralph@amissah.com> | 2008-07-22 20:00:59 -0400 | 
|---|---|---|
| committer | Ralph Amissah <ralph@amissah.com> | 2008-07-22 20:00:59 -0400 | 
| commit | d29a3e5469d8468084641c385ebf16948f7c2437 (patch) | |
| tree | 1a2306de3c5c1055dbc0374b95f31c335f5da85c | |
| parent | action response query fix (diff) | |
sisu-0.68.0 proposed
* middle layer document representation changed, (accounting for substantial patch)
* texpdf multiple document sizes as specified in config
* numerous small fixes
[should on the whole be easier to maintain]
63 files changed, 5310 insertions, 4595 deletions
| @@ -9,6 +9,29 @@ Reverse Chronological:  %% STABLE MANIFEST +%% sisu_0.68.0.orig.tar.gz (2008-07-22:29/2) +http://www.jus.uio.no/sisu/pkg/src/sisu_0.68.0.orig.tar.gz +  sisu_0.68.0.orig.tar.gz +  sisu_0.68.0-1.dsc +  sisu_0.68.0-1.diff.gz + +Should simplify maintenance; numerous small fixes +Not without risk but should be easier to maintain. + +  Fixes numerous small bugs, should simplify maintenance. +  Not without risk but should be easier to maintain. + +  * Middle layer document representation changed (changes to the programs +    internal representation of text (markup)). Input unchanged; output should +    remain much the same. Changed processing markup (middle layer), affects +    internal downstream processing. Should simplify writing of downstream +    parsers and should increase both consistency and flexibility (as internal +    markup is now more easily modified). + +  * texpdf, produces pdfs in multiple document sizes as specified in config + +  * many small fixes +  %% sisu_0.67.5.orig.tar.gz (2008-07-12:27/6)  http://www.jus.uio.no/sisu/pkg/src/sisu_0.67.5.orig.tar.gz    f07a6b01c52c178c4ed57d31eb3a9162e8d59aa643b7cfb8f4250c307c0fa019 1500535 sisu_0.67.5.orig.tar.gz @@ -32,7 +55,7 @@ http://www.jus.uio.no/sisu/pkg/src/sisu_0.67.4.orig.tar.gz    * manifest minor changes to document information displayed -%% sisu_0.67.3.orig.tar.gz (2008-07-02:27/4) +%% sisu_0.67.3.orig.tar.gz (2008-07-03:26/4)  http://www.jus.uio.no/sisu/pkg/src/sisu_0.67.3.orig.tar.gz    f8c57f0e1992a5a829c321b5648dd53d31e65067d1b9464969a4e33afa9be2be 1500468 sisu_0.67.3.orig.tar.gz    c4aeb2f843980dde75611e305eb51618540f0223d5e5e969a9590c49980998de 1159 sisu_0.67.3-1.dsc @@ -4,12 +4,7 @@  raise "Please, use Ruby1.8 (1.8.4 or later), current Ruby #{RUBY_VERSION}" if RUBY_VERSION < '1.8.4' or RUBY_VERSION > '1.9'  #raise "Please, use Ruby1.8.4 or later, current Ruby #{RUBY_VERSION}" if RUBY_VERSION < '1.8.4'  $VERBOSE=nil -if RUBY_VERSION < '1.9' -  $KCODE='u' -  TS1='¡' -else -  TS1='¡'.force_encoding('utf-8') -end +$KCODE='u' if RUBY_VERSION < '1.9'  branch='v0'  SiSU_lib="sisu/#{branch}"  require "#{SiSU_lib}/hub" diff --git a/conf/sisu/sisurc.yml b/conf/sisu/sisurc.yml index d5c186e8..34629d86 100644 --- a/conf/sisu/sisurc.yml +++ b/conf/sisu/sisurc.yml @@ -61,9 +61,9 @@ flag:    iii:          '-NhwpoabxXyYv'            # includes verbose; -m run by default    iv:           '-NhwpoabxXYDyv --import'  # includes verbose; -m run by default    v:            '-NhwpoabxXYDyv --update'  # includes verbose; -m run by default -#% papersize, (LaTeX/pdf) current values A4, US_letter, book_b5, book_a5, US_legal +#% papersize, (LaTeX/pdf) available values: A4, US_letter, book_b5, book_a5, US_legal  default: -  papersize:    'A4' +  papersize:    'A4,letter'    #digest:       'sha' #sha is sha256, default is md5    #multilingual:  false    #language_file: 2 diff --git a/conf/sisu/version.yml b/conf/sisu/version.yml index fb6a31b5..ac7dd106 100644 --- a/conf/sisu/version.yml +++ b/conf/sisu/version.yml @@ -1,5 +1,5 @@  ---  -:version: 0.67.5 -:date_stamp: 2008w27/6 -:date: "2008-07-12" +:version: 0.68.0 +:date_stamp: 2008w29/2 +:date: "2008-07-22"  :project: SiSU diff --git a/data/doc/sisu/CHANGELOG b/data/doc/sisu/CHANGELOG index a99561a2..9a6f0d69 100644 --- a/data/doc/sisu/CHANGELOG +++ b/data/doc/sisu/CHANGELOG @@ -9,11 +9,31 @@ Reverse Chronological:  %% STABLE MANIFEST +%% sisu_0.68.0.orig.tar.gz (2008-07-21:29/1) +http://www.jus.uio.no/sisu/pkg/src/sisu_0.68.0.orig.tar.gz +  sisu_0.68.0.orig.tar.gz +  sisu_0.68.0-1.dsc +  sisu_0.68.0-1.diff.gz + +  Fixes numerous small bugs, should simplify maintenance. +  Not without risk but should be easier to maintain. + +  * Middle layer document representation changed (changes to the programs +    internal representation of text (markup)). Input unchanged; output should +    remain much the same. Changed processing markup (middle layer), affects +    internal downstream processing. Should simplify writing of downstream +    parsers and should increase both consistency and flexibility (as internal +    markup is now more easily modified). + +  * texpdf produces document in multiple paper sizes as specified in config + +  * many small fixes +  %% sisu_0.67.5.orig.tar.gz (2008-07-12:27/6)  http://www.jus.uio.no/sisu/pkg/src/sisu_0.67.5.orig.tar.gz -  sisu_0.67.5.orig.tar.gz -  sisu_0.67.5-1.dsc -  sisu_0.67.5-1.diff.gz +  f07a6b01c52c178c4ed57d31eb3a9162e8d59aa643b7cfb8f4250c307c0fa019 1500535 sisu_0.67.5.orig.tar.gz +  b4b01d9d3bd0b82e9c946cd2a1586b5b550912ed24f01b634f0f9c441ba72c77 1159 sisu_0.67.5-1.dsc +  c5cf3905985e8545d4b87958ed0d8bd1ed72a93051117a8c9631a4cded41da2a 146710 sisu_0.67.5-1.diff.gz    * texpdf xetex and xelatex processing commands, fix @@ -32,7 +52,7 @@ http://www.jus.uio.no/sisu/pkg/src/sisu_0.67.4.orig.tar.gz    * manifest minor changes to document information displayed -%% sisu_0.67.3.orig.tar.gz (2008-07-02:27/4) +%% sisu_0.67.3.orig.tar.gz (2008-07-03:26/4)  http://www.jus.uio.no/sisu/pkg/src/sisu_0.67.3.orig.tar.gz    f8c57f0e1992a5a829c321b5648dd53d31e65067d1b9464969a4e33afa9be2be 1500468 sisu_0.67.3.orig.tar.gz    c4aeb2f843980dde75611e305eb51618540f0223d5e5e969a9590c49980998de 1159 sisu_0.67.3-1.dsc diff --git a/data/doc/sisu/html/sisu.1.html b/data/doc/sisu/html/sisu.1.html index e7682a89..f7b70fcd 100644 --- a/data/doc/sisu/html/sisu.1.html +++ b/data/doc/sisu/html/sisu.1.html @@ -10,13 +10,13 @@  <h2><a name='sect0' href='#toc0'>Name</a></h2>  sisu - documents: markup, structuring, publishing in multiple standard -formats, and search  +formats, and search  <h2><a name='sect1' href='#toc1'>Synopsis</a></h2>  sisu [-abcDdFHhIiMmNnopqRrSsTtUuVvwXxYyZz0-9]  [filename/wildcard ]  sisu [-Ddcv] [instruction]  sisu [-CcFLSVvW] SISU - -MANUAL, RALPH AMISSAH   -<p> WHAT IS SISU?   -<p> 1. INTRODUCTION - WHAT IS SISU?  +MANUAL, RALPH AMISSAH +<p> WHAT IS SISU? +<p> 1. INTRODUCTION - WHAT IS SISU?  <p>  <b>SiSU</b> is a framework for document structuring, publishing (in multiple  open standard formats) and search, comprising of: (a) a lightweight document @@ -24,13 +24,13 @@ structure and presentation markup syntax; and (b) an accompanying engine  for generating standard document format outputs from documents prepared  in sisu markup syntax, which is able to produce multiple standard outputs  (including the population of sql databases) that (can) share a common numbering -system for the citation of text within a document.  +system for the citation of text within a document.  <p>  <b>SiSU</b> is developed under  an open source, software libre license (GPL3). Its use case for development  is to cope with medium to large document sets with evolving markup related  technologies, which should be prepared once, and for which you want multiple  output formats that can be updated and a common mechanism for cross-output-format -citation, and search.  +citation, and search.  <p>  <b>SiSU</b> both defines a markup syntax and provides an  engine that produces open standards format outputs from documents prepared  with <b>SiSU</b> markup. From a single lightly prepared document sisu custom builds @@ -42,7 +42,7 @@ of representation of the document. Significantly <b>SiSU</b> markup is more spar  than html and outputs which include html, LaTeX, landscape and portrait  pdfs, Open Document Format (ODF), all of which can be added to and updated.  <b>SiSU</b> is also able to populate SQL type databases at an object level, which -means that searches can be made with that degree of granularity.  +means that searches can be made with that degree of granularity.  <p>  Source  document preparation and output generation is a two step process: (i) document  source is prepared, that is, marked up in sisu markup syntax and (ii) the @@ -59,14 +59,14 @@ by these documents and at these locations within each document). Document  output formats share a common object numbering system for locating content.  This is particularly suitable for works (finalized texts as opposed to  works that are frequently changed or updated) for which it provides a fixed -means of reference of content.  +means of reference of content.  <p>  In preparing a <b>SiSU</b> document you optionally  provide semantic information related to the document in a document header,  and in marking up the substantive text provide information on the structure  of the document, primarily indicating heading levels and footnotes. You  also provide information on basic text attributes where used. The rest is  automatic, sisu from this information custom builds[^2] the different forms -of output requested.  +of output requested.  <p>  <b>SiSU</b> works with an abstraction of the document based  on its structure which is comprised of its structure (or frame)[^3] and  the objects[^4] it contains, which enables <b>SiSU</b> to represent the document @@ -80,7 +80,7 @@ pages; and in publishing in different formats, html, landscape and portrait  pdf etc. again page numbers are of no use to cite text in a manner that  is relevant against the different output types. Dealing with documents at  an object level together with object numbering also has implications for -search.  +search.  <p>  One of the challenges of maintaining documents is to keep them  in a format that would allow users to use them without depending on a proprietary  software popular at the time. Consider the ease of dealing with legacy proprietary @@ -104,109 +104,107 @@ and the archival of documents), and existing output to be updated (html  has evolved and the related module has been updated repeatedly over the  years, presumably when the World Wide Web Consortium (w3c) finalises html  5 which is currently under development, the html module will again be updated -allowing all existing documents to be regenerated as html 5).  +allowing all existing documents to be regenerated as html 5).  <p>  The document  formats are written to the file-system and available for indexing by independent  indexing tools, whether off the web like Google and Yahoo or on the site -like Lucene and Hyperestraier.  +like Lucene and Hyperestraier.  <p>  <b>SiSU</b> also provides other features such  as concordance files and document content certificates, and the working  against an abstraction of document structure has further possibilities  for the research and development of other document representations, the  availability of objects is useful for example for topic maps and the commercial  law thesaurus by Vikki Rogers and Al Krtizer, together with the flexibility -of <b>SiSU</b> offers great possibilities.  +of <b>SiSU</b> offers great possibilities.  <p>  <b>SiSU</b> is primarily for published works,  which can take advantage of the citation system to reliably reference its  documents. <b>SiSU</b> works well in a complementary manner with such collaborative  technologies as Wikis, which can take advantage of and be used to discuss -the substance of content prepared in <b>SiSU</b>   +the substance of content prepared in <b>SiSU</b>  <p>  <<a href='http://www.jus.uio.no/sisu'>http://www.jus.uio.no/sisu</a> ->  +>  <p> 2. -COMMANDS SUMMARY   -<p> 2.1 SYNOPSIS  +COMMANDS SUMMARY +<p> 2.1 SYNOPSIS  <p>  <b>SiSU</b> - Structured information, Serialized -Units - a document publishing system  -<p>  sisu  [  -abcDdFHhIiMmNnopqRrSsTtUuVvwXxYyZz0-9 - ]  [  filename/  -<p>  sisu  [  -Ddcv  ]  [  instruction  ]  -<p>  sisu  [  -CcFLSVvW  ]  -<p>  Note: -commands should be issued from within the directory that contains the marked -up files, cd to markup directory.  -<p> 2.2 DESCRIPTION  -<p>  <b>SiSU</b> <b>SiSU</b> is a document -publishing system, that from a simple single marked-up document, produces -multiple of output formats including: plaintext, html, LaTeX, pdf, xhtml, -XML, info, and SQL (PostgreSQL and SQLite), which share numbered text objects -( structure information. For more see: <<a href='http://www.jus.uio.no/sisu'>http://www.jus.uio.no/sisu</a> ->  -<p> 2.3 DOCUMENT - -<p>PROCESSING COMMAND FLAGS  -<p>  +Units - a document publishing system +<p>  sisu [  -abcDdFHhIiMmNnopqRrSsTtUuVvwXxYyZz0-9 + ] [  filename/  wildcard  ] +<p>  sisu [  -Ddcv  ] [  instruction  ] +<p>  sisu [  -CcFLSVvW + ] +<p>  Note: commands should be issued from within the directory that contains +the marked up files, cd to markup directory. +<p> 2.2 DESCRIPTION +<p>  <b>SiSU</b> <b>SiSU</b> +is a document publishing system, that from a simple single marked-up document, +produces multiple of output formats including: plaintext, html, LaTeX, +pdf, xhtml, XML, info, and SQL (PostgreSQL and SQLite), which share numbered +text objects ( structure information. For more see: <<a href='http://www.jus.uio.no/sisu'>http://www.jus.uio.no/sisu</a> +> + +<p> 2.3 DOCUMENT PROCESSING COMMAND FLAGS +<p>  <dl> -<dt><b> -a   [filename/wildcard]</b> </dt> -<dd>produces plaintext with -Unix linefeeds and without markup, (object numbers are omitted), has footnotes -at end of each paragraph that contains them  [ -A  for  equivalent  dos  (linefeed) - output  file]  [see  -e  for and search endnotes]. (Options include: --endnotes -for endnotes --footnotes for footnotes at the end of each paragraph --unix -for unix linefeed (default) --msdos for msdos linefeed)  +<dt><b>-a [filename/wildcard]</b> </dt> +<dd>produces plaintext +with Unix linefeeds and without markup, (object numbers are omitted), has +footnotes at end of each paragraph that contains them [  -A  for  equivalent + dos  (linefeed)  output  file] [see  -e  for (Options include: --endnotes for endnotes +--footnotes for footnotes at the end of each paragraph --unix for unix linefeed +(default) --msdos for msdos linefeed)  <p> </dd> -<dt><b> -b   [filename/wildcard]</b> -</dt> -<dd>produces xhtml/XML output for browser viewing (sax parsing).  +<dt><b>-b [filename/wildcard]</b> </dt> +<dd>produces xhtml/XML +output for browser viewing (sax parsing).  <p> </dd> -<dt><b> -C   [--init-site]</b> -</dt> -<dd>configure/initialise shared output directory files initialize shared output -directory (config files such as css and dtd files are not updated if they -already exist unless modifier is used). -C --init-site configure/initialise -site more extensive than -C on its own, shared output directory files/force -update, existing shared output config files such as css and dtd files are -updated if this modifier is used.  +<dt><b>-C [--init-site]</b> </dt> +<dd>configure/initialise +shared output directory files initialize shared output directory (config +files such as css and dtd files are not updated if they already exist unless +modifier is used). -C --init-site configure/initialise site more extensive than +-C on its own, shared output directory files/force update, existing shared +output config files such as css and dtd files are updated if this modifier +is used.  <p> </dd> -<dt><b> -CC</b> </dt> -<dd> configure/initialise  shared  output - directory  files  initialize shared  output  directory  (config  files  such  as - css  and  dtd and search is  used).  The  equivalent  of:  -C  --init-site and search -configure/initialise  site,  more  extensive  than  -C  on  its  own,  shared  output - directory  files/force  update,  existing  shared output  config  files  such - as  css  and  dtd  files  are  updated and search if  -CC  is  used. such  as  css  and - dtd  files  are  updated and search  +<dt><b>-CC</b> </dt> +<dd>configure/initialise shared output directory files initialize +shared output directory (config files such as css and dtd files are not +updated if they already exist unless modifier is used). The equivalent of: +-C --init-site configure/initialise site, more extensive than -C on its own, +shared output directory files/force update, existing shared output config +files such as css and dtd files are updated if -CC is used.  <p> </dd> -<dt><b> -c   [filename/wildcard]</b> </dt> -<dd>screen toggle ansi -screen colour on or off depending on default set (unless -c flag is used: -if sisurc colour default is set to ’true’, output to screen will be with -colour, if sisurc colour default is set to ’false’ or is undefined screen -output will be without colour).  +<dt><b>-c [filename/wildcard]</b> +</dt> +<dd>screen toggle ansi screen colour on or off depending on default set (unless +-c flag is used: if sisurc colour default is set to ’true’, output to screen +will be with colour, if sisurc colour default is set to ’false’ or is undefined +screen output will be without colour).  <p> </dd> -<dt><b> -D   [instruction]  [filename]</b> </dt> -<dd>database postgresql -( --pgsql may be used instead) possible instructions, include: --createdb; ---create; --dropall; --import  [filename]; --update  [filename]; --remove  [filename]; -see database section below.  +<dt><b>-D [instruction] [filename]</b> </dt> +<dd>database +postgresql ( --pgsql may be used instead) possible instructions, include: +--createdb; --create; --dropall; --import [filename]; --update [filename]; --remove +[filename]; see database section below.  <p> </dd> -<dt><b> -d   [--db-[database  type  (sqlite|pg)]] --[instruction] -</dt> -<dd>[filename] database type default set to sqlite, (for which --sqlite may be -used instead) or to specify another database --db-[pgsql,  sqlite] (however -see -D) possible instructions include: --createdb; --create; --dropall; --import - [filename]; --update  [filename]; --remove  [filename]; see database section -below.  +<dt><b>-d [--db-[database  type  (sqlite|pg)]] +--[instruction] [filename]</b> </dt> +<dd>database type default set to sqlite, (for which +--sqlite may be used instead) or to specify another database --db-[pgsql,  sqlite] +(however see -D) possible instructions include: --createdb; --create; --dropall; +--import [filename]; --update [filename]; --remove [filename]; see database section +below.  <p> </dd> -<dt><b> -F   [--webserv=webrick]</b> </dt> +<dt><b>-F [--webserv=webrick]</b> </dt>  <dd>generate examples of (naive) cgi search form  for sqlite and pgsql depends on your already having used sisu to populate  an sqlite and/or pgsql database, (the sqlite version scans the output directories @@ -219,137 +217,139 @@ usually 80). The samples are dumped in the present work directory which  must be writable, (with screen instructions given that they be copied to  the cgi-bin directory). -Fv (in addition to the above) provides some information -<p>on setting up hyperestraier for sisu  +<p>on setting up hyperestraier for sisu  <p> </dd> -<dt><b> -H   [filename/wildcard]</b> </dt> +<dt><b>-H [filename/wildcard]</b> </dt>  <dd>produces html  without link suffixes (.html .pdf etc.) ( an appropriately configured web -server.  [behaviour  switched  after  0.35  see  -h].  +server. [behaviour  switched  after  0.35 see  -h].  <p> </dd> -<dt><b> -h   [filename/wildcard]</b> </dt> +<dt><b>-h [filename/wildcard]</b> </dt>  <dd>produces  html (with hardlinks i.e. with name suffixes in links/local urls). html, with  internal document links that include the document suffix, i.e. whether it  is .html or .pdf (required for browsing directly off a file system, and works -with most web servers).  [behaviour  switched  after  +with most web servers). [behaviour  switched  after  0.35  see  -H].  <p> </dd> -<dt><b> -I   [filename/wildcard]</b> +<dt><b>-I [filename/wildcard]</b>  </dt> -<dd>produces texinfo and info file, (view with pinfo).  +<dd>produces texinfo and info file, (view with pinfo).  <p> </dd> -<dt><b> -i   [filename/wildcard]</b> +<dt><b>-i [filename/wildcard]</b>  </dt> -<dd>produces man page of file, not suitable for all outputs.  +<dd>produces man page of file, not suitable for all outputs.  <p> </dd> -<dt><b> -L</b> </dt> -<dd> prints  license - information.  +<dt><b>-L</b> </dt> +<dd>prints license +information.  <p> </dd> -<dt><b> -M   [filename/wildcard/url]</b> </dt> +<dt><b>-M [filename/wildcard/url]</b> </dt>  <dd>maintenance mode files created for -processing preserved and their locations indicated. (also see -V)  +processing preserved and their locations indicated. (also see -V)  <p> </dd> -<dt><b> -m   [filename/wildcard/url]</b> +<dt><b>-m [filename/wildcard/url]</b>  </dt>  <dd>assumed for most other flags, creates new meta-markup file, (the metaverse  ) that is used in all subsequent processing of other output. This step is -assumed for most processing flags. To skip it see -n  +assumed for most processing flags. To skip it see -n  <p> </dd> -<dt><b> -N   [filename/wildcard/url]</b> +<dt><b>-N [filename/wildcard/url]</b>  </dt>  <dd>document digest or document content certificate ( DCC ) as md5 digest tree  of the document: the digest for the document, and digests for each object  contained within the document (together with information on software versions -that produced it) (digest.txt). -NV for verbose digest output to screen.  +that produced it) (digest.txt). -NV for verbose digest output to screen.  <p> </dd> -<dt><b> -n -  [filename/wildcard/url]</b> </dt> +<dt><b>-n +[filename/wildcard/url]</b> </dt>  <dd>skip meta-markup (building of -m which is otherwise -assumed by most processing flags.  +assumed by most processing flags.  <p> </dd> -<dt><b> -o   [filename/wildcard/url]</b> </dt> +<dt><b>-o [filename/wildcard/url]</b> </dt>  <dd>output basic -document in opendocument file format (opendocument.odt).  +document in opendocument file format (opendocument.odt).  <p> </dd> -<dt><b> -p   [filename/wildcard]</b> +<dt><b>-p [filename/wildcard]</b>  </dt>  <dd>produces LaTeX pdf (portrait.pdf & landscape.pdf). Default paper size is set  in config file, or document header, or provided with additional command  line parameter, e.g. --papersize-a4 preset sizes include: ’A4’, U.S. ’letter’ and -’legal’ and book sizes ’A5’ and ’B5’ (system defaults to A4).  +’legal’ and book sizes ’A5’ and ’B5’ (system defaults to A4).  <p> </dd> -<dt><b> -q   [filename/wildcard]</b> +<dt><b>-q [filename/wildcard]</b>  </dt> -<dd>quiet less output to screen.  +<dd>quiet less output to screen.  <p> </dd> -<dt><b> -R   [filename/wildcard]</b> </dt> +<dt><b>-R [filename/wildcard]</b> </dt>  <dd>copies sisu output files  to remote host using rsync. This requires that sisurc.yml has been provided  with information on hostname and username, and that you have your different  if -R is used with other flags from if used alone. Alone the rsync --delete  parameter is sent, useful for cleaning the remote directory (when -R is -used together with other flags, it is not). Also see -r  +used together with other flags, it is not). Also see -r  <p> </dd> -<dt><b> -r   [filename/wildcard]</b> +<dt><b>-r [filename/wildcard]</b>  </dt>  <dd>copies sisu output files to remote host using scp. This requires that sisurc.yml  has been provided with information on hostname and username, and that you -<p>have your  +<p>have your  <p> </dd> -<dt><b> -S</b> </dt> -<dd> produces  a  sisupod  a  zipped  sisu  directory  of  markup local - configuration  file,  images  and  skins.  Note:  this  only includes  the  configuration - files  or  skins  contained  in  ./_sisu  not  those  in  ~/.sisu  -S   [filename/wildcard] -option. Note: (this option is tested only with zsh).  +<dt><b>-S</b> </dt> +<dd>produces a sisupod a zipped sisu directory of markup files +including sisu markup source files and the directories local configuration +file, images and skins. Note: this only includes the configuration files +or skins contained in  ./_sisu not those in ~/.sisu -S [filename/wildcard] +option. Note: (this<br> + option is tested only with zsh).  <p> </dd> -<dt><b> -S   [filename/wildcard]</b> -</dt> -<dd>produces a zipped file of the prepared document specified along with associated -images, by default named sisupod.zip they may alternatively be named with -the filename extension .ssp This provides a quick way of gathering the relevant -parts of a sisu document which can then for example be emailed. A sisupod -includes sisu markup source file, (along with associated documents if a -master file, or available in multilingual versions), together with related -images and skin. <b>SiSU</b> commands can be run directly against a sisupod contained -in a local directory, or provided as a url on a remote site. As there is -a security issue with skins provided by other users, they are not applied -unless the flag --trust or --trusted is added to the command instruction, it -is recommended that file that are not your own are treated as untrusted. -The directory structure of the unzipped file is understood by sisu, and -sisu commands can be run within it. Note: if you wish to send multiple files, -it quickly becomes more space efficient to zip the sisu markup directory, -rather than the individual files for sending). See the -S option without +<dt><b>-S [filename/wildcard]</b> </dt> +<dd>produces a zipped +file of the prepared document specified along with associated images, by +default named sisupod.zip they may alternatively be named with the filename +extension .ssp This provides a quick way of gathering the relevant parts +of a sisu document which can then for example be emailed. A sisupod includes +sisu markup source file, (along with associated documents if a master file, +or available in multilingual versions), together with related images and +skin. <b>SiSU</b> commands can be run directly against a sisupod contained in a +local directory, or provided as a url on a remote site. As there is a security +issue with skins provided by other users, they are not applied unless the +flag --trust or --trusted is added to the command instruction, it is recommended +that file that are not your own are treated as untrusted. The directory +structure of the unzipped file is understood by sisu, and sisu commands +can be run within it. Note: if you wish to send multiple files, it quickly +becomes more space efficient to zip the sisu markup directory, rather than +the individual files for sending). See the -S option without [filename/wildcard].  <p> </dd> -<dt><b> -s   [filename/wildcard]</b> </dt> -<dd>copies sisu markup file to output directory.  +<dt><b>-s [filename/wildcard]</b> </dt> +<dd>copies sisu markup file to output directory.  <p> </dd> -<dt><b> -t   [filename/wildcard +<dt><b>-t [filename/wildcard   (*.termsheet.rb)]</b> </dt> -<dd>standard form document builder, preprocessing feature  +<dd>standard form document builder, preprocessing feature  <p>  </dd> -<dt><b> -U   [filename/wildcard]</b> </dt> +<dt><b>-U [filename/wildcard]</b> </dt>  <dd>prints url output list/map for the available processing  flags options and resulting files that could be requested, (can be used  to get a list of processing options in relation to a file, together with @@ -357,355 +357,358 @@ information on the output that would be produced), -u provides url output  mapping for those flags requested for processing. The default assumes sisu_webrick  is running and provides webrick url mappings where appropriate, but these -<p>can be switched to file system paths in sisurc.yml  +<p>can be switched to file system paths in sisurc.yml  <p> </dd> -<dt><b> -u   [filename/wildcard]</b> +<dt><b>-u [filename/wildcard]</b>  </dt>  <dd>provides url mapping of output files for the flags requested for processing, -<p>also see -U  +<p>also see -U  <p> </dd> -<dt><b> -V</b> </dt> -<dd> on  its  own,  provides <b> SiSU</b>  version  and  environment  information - (sisu  --help  env)  +<dt><b>-V</b> </dt> +<dd>on its own, provides <b>SiSU</b> version and environment information +(sisu --help env)  <p> </dd> -<dt><b> -V   [filename/wildcard]</b> </dt> +<dt><b>-V [filename/wildcard]</b> </dt>  <dd>even more verbose than the -v flag. -(also see -M)  +(also see -M)  <p> </dd> -<dt><b> -v</b> </dt> -<dd> on  its  own,  provides <b> SiSU</b>  version  information  +<dt><b>-v</b> </dt> +<dd>on its own, provides <b>SiSU</b> version information  <p> </dd> -<dt><b> -v   [filename/wildcard]</b> +<dt><b>-v [filename/wildcard]</b>  </dt>  <dd>provides verbose output of what is being built, where it is being built  (and error messages if any), as with -u flag provides a url mapping of files -created for each of the processing flag requests. See also -V  +created for each of the processing flag requests. See also -V  <p> </dd> -<dt><b> -W</b> </dt> -<dd> starts  ruby’s - webrick  webserver  points  at  sisu  output  the  default  port  is  set  to  8081 - and  can  be   [tip:  the  so  html  output  should be  created  using  the  -h  option - rather  than  -H;  also,  note  -F  webrick  ].  +<dt><b>-W</b> </dt> +<dd>starts ruby’s +webrick webserver points at sisu output directories, the default port is +set to 8081 and can be changed in the resource configuration files. [tip: + the  webrick  server  requires  link  suffixes,  so  html  output  should  be  created + using  the  -h  option  rather  than and search -H;  also,  note  -F  webrick  ].  <p> </dd> -<dt><b> -w   [filename/wildcard]</b> </dt> -<dd>produces concordance -(wordmap) a rudimentary index of all the words in a document. (Concordance -files are not generated for documents of over 260,000 words unless this -limit is increased in the file sisurc.yml)  +<dt><b>-w +[filename/wildcard]</b> </dt> +<dd>produces concordance (wordmap) a rudimentary index +of all the words in a document. (Concordance files are not generated for +documents of over 260,000 words unless this limit is increased in the file +sisurc.yml)  <p> </dd> -<dt><b> -X   [filename/wildcard]</b> </dt> -<dd>produces -XML output with deep document structure, in the nature of dom.  +<dt><b>-X [filename/wildcard]</b> </dt> +<dd>produces XML output with deep document +structure, in the nature of dom.  <p> </dd> -<dt><b> -x   [filename/wildcard]</b> -</dt> -<dd>produces XML output shallow structure (sax parsing).  +<dt><b>-x [filename/wildcard]</b> </dt> +<dd>produces XML output +shallow structure (sax parsing).  <p> </dd> -<dt><b> -Y   [filename/wildcard]</b> -</dt> -<dd>produces a short sitemap entry for the document, based on html output and -the sisu_manifest. --sitemaps generates/updates the sitemap index of existing -sitemaps. (Experimental,  [g,y,m  announcement  this  week])  +<dt><b>-Y [filename/wildcard]</b> </dt> +<dd>produces a short +sitemap entry for the document, based on html output and the sisu_manifest. +--sitemaps generates/updates the sitemap index of existing sitemaps. (Experimental, +[g,y,m  announcement  this  week])  <p> </dd> -<dt><b> -y   [filename/wildcard]</b> -</dt> -<dd>produces an html summary of output generated (hyperlinked to content) and -document specific metadata (sisu_manifest.html). This step is assumed for -most processing flags.  +<dt><b>-y [filename/wildcard]</b> </dt> +<dd>produces an html +summary of output generated (hyperlinked to content) and document specific +metadata (sisu_manifest.html). This step is assumed for most processing flags. +  <p> </dd> -<dt><b> -Z   [filename/wildcard]</b> </dt> -<dd>Zap, if used with other processing -flags deletes output files of the type about to be processed, prior to -processing. If -Z is used as the lone processing related flag (or in conjunction -with a combination of -[mMvVq]), will remove the related document output -directory.  +<dt><b>-Z [filename/wildcard]</b> </dt> +<dd>Zap, if used with other processing flags deletes +output files of the type about to be processed, prior to processing. If +-Z is used as the lone processing related flag (or in conjunction with a +combination of -[mMvVq]), will remove the related document output directory. +  <p> </dd> -<dt><b> -z   [filename/wildcard]</b> </dt> -<dd>produces php (zend)  [this  feature  is  disabled - for  the  time being]  +<dt><b>-z [filename/wildcard]</b> </dt> +<dd>produces php (zend) [this  feature  is  disabled  for + the  time  being]  <p> </dd>  </dl> -3. COMMAND LINE MODIFIERS   -<p>  +3. COMMAND LINE MODIFIERS +<p>  <dl> -<dt><b> --no-ocn</b> </dt> -<dd>  [with  -h  -H  or  -p] switches +<dt><b>--no-ocn</b> </dt> +<dd>[with  -h  -H  or  -p] switches  off object citation numbering. Produce output without identifying numbers -in margins of html or LaTeX/pdf output.  +in margins of html or LaTeX/pdf output.  <p> </dd> -<dt><b> --no-annotate</b> </dt> -<dd> strips  output  text  of - editor  endnotes[^*1] denoted by asterisk or dagger/plus sign  +<dt><b>--no-annotate</b> </dt> +<dd>strips output text of +editor endnotes[^*1] denoted by asterisk or dagger/plus sign  <p> </dd> -<dt><b> --no-asterisk</b> +<dt><b>--no-asterisk</b>  </dt> -<dd> strips  output  text  of  editor  endnotes[^*2] denoted by asterisk sign  +<dd>strips output text of editor endnotes[^*2] denoted by asterisk sign  <p> </dd> -<dt><b> --no-dagger</b> +<dt><b>--no-dagger</b>  </dt> -<dd> strips  output  text  of  editor  endnotes[^+1] denoted by dagger/plus sign  +<dd>strips output text of editor endnotes[^+1] denoted by dagger/plus sign  <p>  </dd>  </dl> -4. DATABASE COMMANDS   -<p>  dbi - database interface  +4. DATABASE COMMANDS +<p>  dbi - database interface  <p>  -D or --pgsql set for postgresql  -d or --sqlite default set for sqlite -d is modifiable with --db=[database  type - (pgsql  or  sqlite)]  -<p>  + (pgsql  or  sqlite)] +<p>  <dl> -<dt><b> -Dv  --createall</b> </dt> -<dd> initial  step,  creates  required  relations - (tables,  indexes)  in  existing  postgresql  database  (a  database  should  be - created manually  and  given  the  same  name  as  working  directory,  as requested) - (rb.dbi)   [  -dv  --createall  sqlite  equivalent] it may be necessary to run sisu +<dt><b>-Dv --createall</b> </dt> +<dd>initial step, creates required relations +(tables, indexes) in existing postgresql database (a database should be +created manually and given the same name as working directory, as requested) +(rb.dbi) [  -dv  --createall sqlite  equivalent] it may be necessary to run sisu  -Dv --createdb initially NOTE: at the present time for postgresql it may be  necessary to manually create the database. The command would be ’createdb - [database  name]’ where database name would be SiSU_[present  working  directory - name  (without  path)]. Please use only alphanumerics and underscores.  +[database name]’ where database name would be SiSU_[present  working  directory + name  (without  path)]. Please use only alphanumerics and underscores.  <p> </dd> -<dt><b> -Dv - --import</b> </dt> -<dd>  [filename/wildcard] imports data specified to postgresql db (rb.dbi) - [  -dv  --import  sqlite  equivalent]  +<dt><b>-Dv +--import</b> </dt> +<dd>[filename/wildcard] imports data specified to postgresql db (rb.dbi) +[  -dv  --import  sqlite  equivalent]  <p> </dd> -<dt><b> -Dv  --update</b> </dt> -<dd>  [filename/wildcard] updates/imports -specified data to postgresql db (rb.dbi)  [  -dv  --update  sqlite  equivalent] +<dt><b>-Dv --update</b> </dt> +<dd>[filename/wildcard] updates/imports +specified data to postgresql db (rb.dbi) [  -dv  --update  sqlite  equivalent]  <p> </dd> -<dt><b> -D  --remove</b> </dt> -<dd>  [filename/wildcard] removes specified data to postgresql db (rb.dbi) - [  -d  --remove  sqlite  equivalent]  +<dt><b>-D --remove</b> </dt> +<dd>[filename/wildcard] removes specified data to postgresql db (rb.dbi) +[  -d  --remove  sqlite  equivalent]  <p> </dd> -<dt><b> -D  --dropall</b> </dt> -<dd> kills  data &  indexes   [  -d  --dropall - sqlite  equivalent]  -<p>  The v in e.g. -Dv is for verbose output.  +<dt><b>-D --dropall</b> </dt> +<dd>kills data --dropall  sqlite  equivalent] + +<p>  The v in e.g. -Dv is for verbose output.  <p> </dd>  </dl> -5. SHORTCUTS, -SHORTHAND FOR MULTIPLE FLAGS   -<p>  +5. SHORTCUTS, SHORTHAND FOR MULTIPLE +FLAGS +<p>  <dl> -<dt><b> --update   [filename/wildcard]</b> </dt> -<dd>Checks existing -file output and runs the flags required to update this output. This means -that if only html and pdf output was requested on previous runs, only the --hp files will be applied, and only these will be generated this time, together -with the summary. This can be very convenient, if you offer different outputs -of different files, and just want to do the same again.  +<dt><b>--update [filename/wildcard]</b> </dt> +<dd>Checks existing file output and runs +the flags required to update this output. This means that if only html and +pdf output was requested on previous runs, only the -hp files will be applied, +and only these will be generated this time, together with the summary. This +can be very convenient, if you offer different outputs of different files, +and just want to do the same again.  <p> </dd> -<dt><b> -0  to  -5   [filename - or  wildcard]</b> </dt> -<dd>Default shorthand mappings (note that the defaults can be -changed/configured in the sisurc.yml file):  +<dt><b>-0 to -5 [filename  or  wildcard]</b> </dt> +<dd>Default +shorthand mappings (note that the defaults can be changed/configured in +the sisurc.yml file):  <p> </dd> -<dt><b> -0</b> </dt> -<dd> -mNhwpAobxXyYv   [this  is  the - default  action  run  when  no  i.e.  on  ’sisu   [filename]’]  +<dt><b>-0</b> </dt> +<dd>-mNhwpAobxXyYv [this  is  the  default  action  run  when + no  i.e.  on  ’sisu  [filename]’]  <p> </dd> -<dt><b> -1</b> </dt> -<dd> -mNHwpy  give,  i.e.  on - ’sisu   [filename]’]  +<dt><b>-1</b> </dt> +<dd>-mNHwpy  <p> </dd> -<dt><b> -2</b> </dt> -<dd> -mNHwpaoy give,  i.e.  on  ’sisu   [filename]’]  +<dt><b>-2</b> </dt> +<dd>-mNHwpaoy  <p> </dd> -<dt><b> -3</b> </dt> -<dd> -mNhwpAobxXyY - i.e.  on  ’sisu   [filename]’]  +<dt><b>-3</b> </dt> +<dd>-mNhwpAobxXyY  <p> </dd> -<dt><b> -4</b> </dt> -<dd> -mNhwpAobxXDyY  --import  ’sisu   [filename]’]  +<dt><b>-4</b> </dt> +<dd>-mNhwpAobxXDyY + +<p>- +<p>- +<p>import  <p> </dd> -<dt><b> -5</b> </dt> -<dd> -mNhwpAobxXDyY - --update  ’sisu   [filename]’]  -<p>  add -v for verbose mode and -c for color, e.g. sisu --2vc  [filename  or wildcard]  -<p>  consider -u for appended url info or -v for +<dt><b>-5</b> </dt> +<dd>-mNhwpAobxXDyY --update +<p>  add -v for verbose mode and -c for color, +e.g. sisu -2vc [filename  or +<p>  consider -u for appended url info or -v for verbose -<p>verbose output  +<p>output  <p> </dd>  </dl> -5.1 COMMAND LINE WITH FLAGS - BATCH PROCESSING  -<p>  In the data -directory run sisu -mh filename or wildcard eg. cisg.sst documents.  -<p>  Running -sisu (alone without any flags, filenames or wildcards) brings up the interactive -help, as does any sisu command that is not recognised. Enter to escape.  -<p> -6. HELP   -<p> 6.1 SISU MANUAL  -<p>  The most up to date information on sisu should -be contained in the sisu_manual, available at:  +5.1 COMMAND LINE WITH FLAGS - BATCH PROCESSING +<p>  In the data directory +run sisu -mh filename or wildcard eg. cisg.sst documents. +<p>  Running sisu (alone +without any flags, filenames or wildcards) brings up the interactive help, +as does any sisu command that is not recognised. Enter to escape. +<p> 6. HELP + +<p> 6.1 SISU MANUAL +<p>  The most up to date information on sisu should be contained +in the sisu_manual, available at:  <p>    <<a href='http://sisudoc.org/sisu/sisu_manual/'>http://sisudoc.org/sisu/sisu_manual/</a>  ><br> -  +  <p>  The manual can be generated from source, found respectively, either -within the <b>SiSU</b> tarball or installed locally at:  +within the <b>SiSU</b> tarball or installed locally at:  <p>    ./data/doc/sisu/sisu_markup_samples/sisu_manual/<br> -  +  <p>    /usr/share/doc/sisu/sisu_markup_samples/sisu_manual/<br> -  -<p>  move to the respective directory and type e.g.:  + +<p>  move to the respective directory and type e.g.:  <p>    sisu sisu_manual.ssm<br> -  -<p> 6.2 SISU MAN PAGES  + +<p> 6.2 SISU MAN PAGES  <p>  If <b>SiSU</b> is installed on your system usual man commands -should be available, try:  +should be available, try:  <p>    man sisu<br> -  +  <p>    man sisu_markup<br> -  +  <p>    man sisu_commands<br> -  +  <p>  Most <b>SiSU</b> man pages are generated directly from sisu documents that  are used to prepare the sisu manual, the sources files for which are located -within the <b>SiSU</b> tarball at:  +within the <b>SiSU</b> tarball at:  <p>    ./data/doc/sisu/sisu_manual/<br> -  -<p>  Once installed, directory equivalent to:  + +<p>  Once installed, directory equivalent to:  <p>    /usr/share/doc/sisu/sisu_manual/<br> -  -<p>  Available man pages are converted back to html using man2html:  + +<p>  Available man pages are converted back to html using man2html:  <p>    /usr/share/doc/sisu/html/<br> -  +  <p>    ./data/doc/sisu/html/<br> -  -<p>  An online version of the sisu man page is available here:  + +<p>  An online version of the sisu man page is available here:  <p>  * various  sisu man pages <<a href='http://www.jus.uio.no/sisu/man/'>http://www.jus.uio.no/sisu/man/</a> ->  [^7]  +> [^7]  <p>  * sisu.1 <<a href='http://www.jus.uio.no/sisu/man/sisu.1.html'>http://www.jus.uio.no/sisu/man/sisu.1.html</a>  > - [^8]  -<p> 6.3 SISU BUILT-IN INTERACTIVE HELP  +[^8] +<p> 6.3 SISU BUILT-IN INTERACTIVE HELP  <p>  This is particularly useful for -getting the current sisu setup/environment information:  +getting the current sisu setup/environment information:  <p>    sisu --help<br> -  -<p>    sisu --help  [subject]<br> -  + +<p>    sisu --help [subject]<br> +  <p>      sisu --help commands<br> -  +  <p>      sisu --help markup<br> -  -<p>      sisu --help env  [for  feedback  on  the  way  your  system  is and search<br> + +<p>      sisu --help env [for  feedback  on  the  way  your  system  is <br>       setup  with  regard  to  sisu]<br> -  -<p>    sisu -V  [environment  information,  same  as  above  command]<br> -  + +<p>    sisu -V [environment  information,  same  as  above  command]<br> +  <p>    sisu (on its own provides version and some help information)<br> -  +  <p>  Apart from real-time information on your current configuration the <b>SiSU</b>  manual and man pages are likely to contain more up-to-date information than -the sisu interactive help (for example on commands and markup).  +the sisu interactive help (for example on commands and markup).  <p>  NOTE:  Running the command sisu (alone without any flags, filenames or wildcards)  brings up the interactive help, as does any sisu command that is not recognised. -Enter to escape.  -<p> 6.4 HELP SOURCES  +Enter to escape. +<p> 6.4 HELP SOURCES  <p>  For lists of alternative help sources, -see:  -<p>  <b>man page</b>  +see: +<p>  <b>man page</b>  <p>    man sisu_help_sources<br> -  -<p>  <b>man2html</b>  + +<p>  <b>man2html</b>  <p>    /usr/share/doc/sisu/sisu_manual/sisu_help_sources/index.html<br> -  -<p>  <b>sisu generated html</b>  + +<p>  <b>sisu generated html</b>  <p>    /usr/share/doc/sisu/html/sisu_help_sources/index.html<br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_help_sources/index.html'>http://sisudoc.org/sisu/sisu_help_sources/index.html</a>  ><br> -  -<p> 7. INTRODUCTION TO SISU MARKUP[^9]   -<p> 7.1 SUMMARY  + +<p> 7. INTRODUCTION TO SISU MARKUP[^9] +<p> 7.1 SUMMARY  <p>  <b>SiSU</b> source documents -are plaintext (UTF-8)[^10] files  +are plaintext (UTF-8)[^10] files  <p>  All paragraphs are separated by an empty -line.  -<p>  Markup is comprised of:  +line. +<p>  Markup is comprised of:  <p>  * at the top of a document, the document  header made up of semantic meta-data about the document and if desired additional  processing instructions (such an instruction to automatically number headings -from a particular level down)  +from a particular level down)  <p>  * followed by the prepared substantive  text of which the most important single characteristic is the markup of  different heading levels, which define the primary outline of the document -structure. Markup of substantive text includes:  +structure. Markup of substantive text includes:  <p>    * heading levels defines  document structure<br> -  +  <p>    * text basic attributes, italics, bold etc.<br> -  +  <p>    * grouped text (objects), which are to be treated differently, such  as code<br>     blocks or poems.<br> -  +  <p>    * footnotes/endnotes<br> -  +  <p>    * linked text and images<br> -  +  <p>    * paragraph actions, such as indent, bulleted, numbered-lists, etc.<br> -  +  <p>  Some interactive help on markup is available, by typing sisu and selecting -<p>markup or sisu --help markup  -<p>  To check the markup in a file:  +<p>markup or sisu --help markup +<p>  To check the markup in a file:  <p>    sisu --identify - [filename].sst<br> -  -<p>  For brief descriptive summary of markup history  +[filename].sst<br> + +<p>  For brief descriptive summary of markup history  <p>    sisu --query-history<br> -  -<p>  or if for a particular version:  + +<p>  or if for a particular version:  <p>    sisu --query-0.38<br> -  -<p> 7.2 MARKUP EXAMPLES  -<p> 7.2.1 ONLINE  + +<p> 7.2 MARKUP EXAMPLES +<p> 7.2.1 ONLINE  <p>  Online markup examples are available  together with the respective outputs produced from <<a href='http://www.jus.uio.no/sisu/SiSU/examples.html'>http://www.jus.uio.no/sisu/SiSU/examples.html</a>  >  or from <<a href='http://www.jus.uio.no/sisu/sisu_examples/'>http://www.jus.uio.no/sisu/sisu_examples/</a> ->  +>  <p>  There is of course this  document, which provides a cursory overview of sisu markup and the respective  output produced: <<a href='http://www.jus.uio.no/sisu/sisu_markup/'>http://www.jus.uio.no/sisu/sisu_markup/</a> ->  +>  <p>  Some example marked  up files are available as html with syntax highlighting for viewing: <<a href='http://www.jus.uio.no/sisu/sample/syntax'>http://www.jus.uio.no/sisu/sample/syntax</a>  > @@ -713,28 +716,28 @@ up files are available as html with syntax highlighting for viewing: <<a href  <p>  an alternative presentation of markup syntax: <<a href='http://www.jus.uio.no/sisu/sample/on_markup.txt'>http://www.jus.uio.no/sisu/sample/on_markup.txt</a>  > -<p> 7.2.2 INSTALLED  +<p> 7.2.2 INSTALLED  <p>  With <b>SiSU</b> installed sample skins may be found in: /usr/share/doc/sisu/sisu_markup_samples/dfsg  (or equivalent directory) and if sisu-markup-samples is installed also under: -<p>/usr/share/doc/sisu/sisu_markup_samples/non-free  -<p> 8. MARKUP OF HEADERS   +<p>/usr/share/doc/sisu/sisu_markup_samples/non-free +<p> 8. MARKUP OF HEADERS  <p>   Headers consist of semantic meta-data about a document, which can be used  by any output module of the program; and may in addition include extra -processing instructions.  +processing instructions.  <p>  Note: the first line of a document may include  information on the markup version used in the form of a comment. Comments  are a percentage mark at the start of a paragraph (and as the first character -in a line of text) followed by a space and the comment:  -<p>  +in a line of text) followed by a space and the comment: +<p>  <p> <br>  <pre>  % this would be a comment  </pre> -<p> 8.1 SAMPLE HEADER  +<p> 8.1 SAMPLE HEADER  <p>  This current document has a header similar to this -one (without the comments):  -<p>  +one (without the comments): +<p>  <p> <br>  <pre>  % SiSU 0.57    @title: SiSU @@ -772,178 +775,184 @@ documents that request them, all documents in a directory, or be site-wide.    { SiSU Download }http://www.jus.uio.no/sisu/SiSU/download.html    { SiSU Changelog }http://www.jus.uio.no/sisu/SiSU/changelog.html  </pre> -<p> 8.2 AVAILABLE HEADERS  +<p> 8.2 AVAILABLE HEADERS  <p>  Header tags appear at the beginning of a document  and provide meta information on the document (such as the Dublin Core),  or information as to how the document as a whole is to be processed. All  header instructions take either the form @headername: or 0~headername. All -<p>Dublin Core meta tags are available  +<p>Dublin Core meta tags are available  <p>  <b>@indentifier:</b> information or instructions -<p>  where the information  +<p>  where the information  <p>  Note: a header where used should only be used  once; all headers apart from @title: are optional; the @structure: header -is used to describe document structure, and can be useful to know.  +is used to describe document structure, and can be useful to know.  <p>  This -<p>is a sample header  -<p>  <b>% SiSU 0.38</b>  [declared  file-type  identifier  with  markup - version]  -<p>  <b>@title:</b>  [title  text] This is the title of the document and used -as such, this header is the only one that is <i>mandatory</i>  -<p>  <b>@subtitle:</b> The - -<p>Subtitle if any  -<p>  <b>@creator:</b>  [or  @author:] Name of Author  -<p>  <b>@subject:</b> (whatever -your subject)  -<p>  <b>@description:</b>  -<p>  <b>@publisher:</b>  -<p>  <b>@contributor:</b>  -<p>  <b>@translator:</b> - [or  @translated_by:]  -<p>  <b>@illustrator:</b>  [or  @illustrated_by:]  -<p>  <b>@prepared_by:</b> - [or  @digitized_by:]  -<p>  <b>@date: 2000-08-27</b>  [  also  @date.created:  @date.issued: - @date.available:  @date.valid:  @date.modified:  ]  -<p>  <b>@type: article</b>  -<p>  <b>@format:</b> +<p>is a sample header +<p>  <b>% SiSU 0.38</b> [declared  file-type  identifier  with  markup + version] +<p> +<p>  <b>@title:</b>   [title  text] This is the title of the document and +used as such, this header is the only one that is<br> + <i>mandatory</i> +<p>  <b>@subtitle:</b> The Subtitle if any +<p>  <b>@creator:</b> [or  @author:] Name + +<p>of Author +<p>  <b>@subject:</b> (whatever your subject) +<p>  <b>@description:</b> +<p>  <b>@publisher:</b> + +<p>  <b>@contributor:</b> +<p>  <b>@translator:</b>  [or  @translated_by:] +<p>  <b>@illustrator:</b>  [or + @illustrated_by:] +<p>  <b>@prepared_by:</b>  [or  @digitized_by:] +<p>  <b>@date: 2000-08-27</b> +[  also  @date.created:  @date.issued:  @date.available:  @date.valid:  ] +<p> +<p>  <b>@type: -<p>  <b>@identifier:</b>  -<p>  <b>@source:</b>  -<p>  <b>@language:</b>  [or  @language.document:]  [country - code  for  language  if available,  or  language,  English,  en  is  the  default - setting] (en - English, fr - French, de - German, it - Italian, es - Spanish, -pt - Portuguese, sv - Swedish, da - Danish, fi - Finnish, no - Norwegian, is -- Icelandic, nl - Dutch, et - Estonian, hu - Hungarian, pl - Polish, ro - Romanian, -ru - Russian, el - Greek, uk - Ukranian, tr - Turkish, sk - Slovak, sl - Slovenian, -hr - Croatian, cs - Czech, bg - Bul garian ) [however,  encodings  are  not  available - for  all  of  the languages  listed.]  -<p>  [@language.original:  original  language - in  which  the  work  was published]  +<p>article</b> +<p>  <b>@format:</b> +<p>  <b>@identifier:</b> +<p>  <b>@source:</b> +<p>  <b>@language:</b> [or  @language.document:] +[country  code  for  language  if  available,  or  language,  English,  en  is  the + default  setting] (en - English, fr - French, de - German, it - Italian, es +- Spanish, pt - Portuguese, sv - Swedish, da - Danish, fi - Finnish, no - Norwegian, +is - Icelandic, nl - Dutch, et - Estonian, hu - Hungarian, pl - Polish, ro - +Romanian, ru - Russian, el - Greek, uk - Ukranian, tr - Turkish, sk - Slovak, +sl - Slovenian, hr - Croatian, cs - Czech, bg - Bul garian ) [however,  encodings + are  not  available  for  all  of  the languages  listed.] +<p>  [@language.original: + original  language  in  which  the  work  was published]  <p>  <b>@papersize:</b> (A4|US_letter|book_B5|book_A5|US_legal) -<p>  <b>@relation:</b>  -<p>  <b>@coverage:</b>  +<p>  <b>@relation:</b> +<p>  <b>@coverage:</b>  <p>  <b>@rights:</b> Copyright (c) Name of Right Holder,  all rights reserved, or as granted: public domain, copyleft, creative commons -variant, etc.  -<p>  <b>@owner:</b>  +variant, etc. +<p>  <b>@owner:</b>  <p>  <b>@keywords:</b> text document generation processing -management latex pdf structured xml citation  [your  keywords  here,  used - for  example  by  rss  feeds,  and  in  sql  searches]  -<p>  <b>@abstract:</b>  [paper  abstract, - placed  after  table  of  contents]  -<p>  <b>@comment:</b>  [...]  -<p>  <b>@catalogue:</b> loc=[Library - of  Congress  classification]; dewey=[Dewey  rss  feeds, classification]; isbn=[ISBN]; -pg=[Project  Gutenberg  text  number]  -<p>  <b>@classify_loc:</b>  [Library  of  Congress - classification]  -<p>  <b>@classify_dewey:</b>  [Dewey  classification]  -<p>  <b>@classify_isbn:</b> - [ISBN]  -<p>  <b>@classify_pg:</b>  [Project  Gutenberg  text  number]  -<p>  <b>@prefix:</b>  [prefix - is  placed  just  after  table  of  contents]  -<p>  <b>@prefix_a:</b>  [prefix  is  placed - just  before  table  of  contents  -  not implemented]  -<p>  <b>@prefix_b:</b>  -<p>  <b>@rcs:</b> $Id: -sisu_markup.sst,v 1.2 2007/09/08 17:12:47 ralph Exp $  [used  by  rcs  or  cvs - to  embed  version  (revision  control)  information  into  rcs  or  cvs  can  usefully - provide  a  history  of  -<p>  <b>@structure:</b> PART; CHAPTER; SECTION; ARTICLE; none; -none; optional, document structure can be defined by words to match or -regular expression (the regular expression is assumed to start at the beginning +management latex pdf structured xml citation [your  keywords  here,  used + for  example  by  rss  feeds, +<p>  <b>@abstract:</b> [paper  abstract,  placed  after  table + of  contents] +<p>  <b>@comment:</b> [...] +<p>  <b>@catalogue:</b> loc=[Library  of  Congress  classification]; +dewey=[Dewey rss  feeds, isbn=[ISBN]; pg=[Project  Gutenberg  text  number] + +<p>  <b>@classify_loc:</b> [Library  of  Congress  classification] +<p>  <b>@classify_dewey:</b> +[Dewey  classification] +<p>  <b>@classify_isbn:</b> [ISBN] +<p>  <b>@classify_pg:</b> [Project + Gutenberg  text  number] +<p>  <b>@prefix:</b> [prefix  is  placed  just  after  table  of + contents] +<p>  <b>@prefix_a:</b> [prefix  is  placed  just  before  table  of  contents + -  not +<p>  <b>@prefix_b:</b> +<p>  <b>@rcs:</b> $Id: sisu_markup.sst,v 1.2 2007/09/08 17:12:47 +ralph Exp $ [used  by  rcs or  cvs  to  embed  version  (revision  control)  information + into document,  rcs  or  cvs  can  usefully  provide  a  history  of updates  to + a  document  ] +<p>  <b>@structure:</b> PART; CHAPTER; SECTION; ARTICLE; none; none; +optional, document structure can be defined by words to match or regular +expression (the regular expression is assumed to start at the beginning  of a line of text i.e. ^) default markers :A~ to :C~ and 1~ to 6~ can be used  within text instead, without this header tag, and may be used to supplement  the instructions provided in this header tag if provided (@structure: is -a synonym for @toc:)  -<p>  <b>@level:</b> newpage=3; breakpage=4  [paragraph  level, - used  by  latex  to  breakpages,  the  page  in  newpage]  -<p>  <b>@markup:</b> information -on the markup used, e.g. new=1,2,3; break=4; num_top=4  [or newpage=1,2,3; - breakpage=4;  num_top=4] newpage and breakpage, heading level, used by LaTeX -to breakpages. breakpage: starts on a new page in single column text and -on a new column in double column text; newpage: starts on a new page for -both single and double column texts. num_top=4  [auto-number  document,  starting - at  level  4.  the new default  is  to  provide  3  levels,  as  in  1  level  4,  1.1 - 1.1.1  level  6,  markup  to  be  merged  within  level] num_extract  [take  numbering - of  headings  provided  (manually  in   and  use  for  numbering  of  Available  where - a  clear  numbering  structure  is  without  the  repetition  of  a  number in  a - header.]  [In  0.38  notation,  you  would  map  to  the equivalent  levels,  the  examples - provided  would  map  to  the following  new=A,B,C;  break=1;  num_top=1   [or  newpage=A,B,C; -breakpage=1;  num_top=1] see headings]  -<p>  <b>@bold:</b>  [regular  expression  of  words/phrases - to  be  made  bold]  -<p>  <b>@italics:</b>  [regular  expression  of  words/phrases  to  italicise] +a synonym for @toc:) +<p>  <b>@level:</b> newpage=3; breakpage=4 [paragraph  level, + used  by  latex  to  breakpages,  the  page  is  optional  eg.  in  newpage] +<p>  <b>@markup:</b> +information on the markup used, e.g. new=1,2,3; break=4; num_top=4 [or is +newpage=1,2,3;  breakpage=4;  num_top=4] newpage and breakpage, heading level, +used by LaTeX to breakpages. breakpage: starts on a new page in single column +text and on a new column in double column text; newpage: starts on a new +page for both single and double column texts. num_top=4 [auto-number  document, + starting  at  level  4.  the a new default  is  to  provide  3  levels,  as  in  1  level + 4,  1.1  1.1.1  level  6,  markup  to  be  merged  within  level] num_extract [take + numbering  of  headings  provided  (manually  in marked  up  source  document), + and  use  for  numbering  of segments.  Available  where  a  clear  numbering  structure + is provided  within  document,  without  the  repetition  of  a  number in  a  header.] +[In  0.38  notation,  you  would  map  to  the equivalent  levels,  the  examples + provided  would  map  to  the following  new=A,B,C;  break=1;  num_top=1  [or  newpage=A,B,C; +breakpage=1;  num_top=1] see headings] +<p>  <b>@bold:</b> [regular  expression  of  words/phrases + to  be  made  bold] +<p>  <b>@italics:</b> [regular  expression  of  words/phrases  to  italicise]  <p>  <b>@vocabulary:</b> name of taxonomy/vocabulary/wordlist to use against document  <p>  <b>@skin:</b> skin_doc_[name_of_desired_document_skin] skins change default  settings related to the appearance of documents generated, such as the -urls of the home site, and the icon/logo for the document or site.  -<p>  +urls of the home site, and the icon/logo for the document or site. +<p>  <dl> -<dt><b> @man: - 8;</b> </dt> -<dd> name=sisu  -  documents:  markup,  structuring,  publishing  in multiple  standard - formats,  and  search;  synopsis=sisu  in [-abcDdFHhIiMmNnopqRrSsTtUuVvwXxYyZz0-9] - [filename/wildcard  ] sisu  [-Ddcv]  [instruction] sisu  [-CcFLSVvW] the man +<dt><b>@man: +8;</b> </dt> +<dd>name=sisu - documents: markup, structuring, publishing in multiple standard +formats, and search; synopsis=sisu [-abcDdFHhIiMmNnopqRrSsTtUuVvwXxYyZz0-9] +[filename/wildcard ] sisu [-Ddcv] [instruction] sisu [-CcFLSVvW] the man  page category number (default 1) and special tags used in preparing man -<p>page headings  +<p>page headings  <p>  <b>@links:</b> { <b>SiSU</b> }<a href='http://www.jus.uio.no/sisu/;'>http://www.jus.uio.no/sisu/;</a>   { FSF }<a href='http://www.fsf.org'>http://www.fsf.org</a> -<p>  <b>@promo:</b> sisu, ruby, search_libre_docs, open_society  [places  content  in - right  pane  in  html,  makes  use  of  commented  out  sample  in  document sample: -and  promo.yml,  commented  out  sample  in  document free_as_in_freedom.richard_stallman_crusade_for_free_software.sam_williams.sst] - +<p>  <b>@promo:</b> sisu, ruby, search_libre_docs, open_society [places  content  in + right  pane  in  html,  makes  use  of  commented  out  sample  in  document and  promo.yml, + commented  out  sample  in  document  <p> </dd>  </dl> -9. MARKUP OF SUBSTANTIVE TEXT   -<p> 9.1 HEADING LEVELS  -<p>  Heading levels are -:A~ ,:B~ ,:C~ ,1~ ,2~ ,3~ ... :A - :C being part / section headings, followed -by other heading levels, and 1 -6 being headings followed by substantive -text or sub-headings. :A~ usually the title :A~? conditional level 1 heading -(used where a stand-alone document may be imported into another)  -<p>  <b>:A~  [heading - text]</b> Top level heading  [this  usually  has  similar  content  to  the  ] NOTE: -the heading levels described here are in 0.38 notation, see heading  -<p>  <b>:B~ - [heading  text]</b> Second level heading  [this  is  a  heading  level  divider]  -<p> - <b>:C~  [heading  text]</b> Third level heading  [this  is  a  heading  level  divider] - -<p>  <b>1~  [heading  text]</b> Top level heading preceding substantive text of document -or sub-heading 2, the heading level that would normally be marked 1. or 2. -or 3. etc. in a document, and the level on which sisu by default would break -html output into named segments, names are provided automatically if none -are given (a number), otherwise takes the form 1~my_filename_for_this_segment - -<p>  <b>2~  [heading  text]</b> Second level heading preceding substantive text of -document or sub-heading 3, the heading level that would normally be marked -1.1 or 1.2 or 1.3 or 2.1 etc. in a document.  -<p>  <b>3~  [heading  text]</b> Third level -heading preceding substantive text of document, that would normally be -marked 1.1.1 or 1.1.2 or 1.2.1 or 2.1.1 etc. in a document  -<p>  +9. MARKUP OF SUBSTANTIVE TEXT +<p> 9.1 HEADING + +<p>LEVELS +<p>  Heading levels are :A~ ,:B~ ,:C~ ,1~ ,2~ ,3~ ... :A - :C being part +/ section headings, followed by other heading levels, and 1 -6 being headings +followed by substantive text or sub-headings. :A~ usually the title :A~? +conditional level 1 heading (used where a stand-alone document may be imported +into another) +<p>  <b>:A~ [heading  text]</b> Top level heading [this  usually  has + similar  content  to  the  ] NOTE: the heading levels described here are in +0.38 notation, see heading +<p>  <b>:B~ [heading  text]</b> Second level heading [this + is  a  heading  level  divider] +<p>  <b>:C~ [heading  text]</b> Third level heading [this + is  a  heading  level  divider] +<p>  <b>1~ [heading  text]</b> Top level heading preceding +substantive text of document or sub-heading 2, the heading level that would +normally be marked 1. or 2. or 3. etc. in a document, and the level on which +sisu by default would break html output into named segments, names are +provided automatically if none are given (a number), otherwise takes the + +<p>form 1~my_filename_for_this_segment +<p>  <b>2~ [heading  text]</b> Second level heading +preceding substantive text of document or sub-heading 3, the heading level +that would normally be marked 1.1 or 1.2 or 1.3 or 2.1 etc. in a document. +<p> +<b>3~ [heading  text]</b> Third level heading preceding substantive text of document, +that would normally be marked 1.1.1 or 1.1.2 or 1.2.1 or 2.1.1 etc. in a document + +<p>  <p> <br>  <pre>  1~filename level 1 heading,    % the primary division such as Chapter that is followed by substantive  text, and may be further subdivided (this is the level on which by default  html segments are made)  </pre> -<p> 9.2 FONT ATTRIBUTES  -<p>  <b>markup example:</b>  -<p>  +<p> 9.2 FONT ATTRIBUTES +<p>  <b>markup example:</b> +<p>  <p> <br>  <pre>  normal text !{emphasis}! *{bold text}* _{underscore}_ /{italics}/    normal text @@ -951,228 +960,230 @@ html segments are made)    *{bold text}*    _{underscore}_    /{italics}/ -  +    ^{superscript}^    ,{subscript},    +{inserted text}+    -{strikethrough}-  </pre> -<p>  <b>resulting output:</b>  -<p>  normal text <em>emphasis</em> <b>bold text</b> <i>underscore</i> <i>italics</i> +<p>  <b>resulting output:</b> +<p>  normal text <b>emphasis</b> <b>bold text</b> <i>underscore</i> <i>italics</i>  <cite>citation</cite> ^superscript^  [subscript] <ins>inserted text</ins> <del>strikethrough</del> -<p>  normal text  -<p>  <em>emphasis</em>  -<p>  <b>bold text</b>  -<p>  <i>underscore</i>  -<p>  <i>italics</i>  +<p>  normal text +<p> +<p>  <b>bold text</b> +<p>  <i>underscore</i> +<p>  <i>italics</i>  <p>  <cite>citation</cite> - -<p>  ^superscript^  -<p>  [subscript]  -<p>  <ins>inserted text</ins>  +<p> + ^superscript^ +<p>  [subscript] +<p>  <ins>inserted text</ins>  <p>  <del>strikethrough</del> -<p> 9.3 INDENTATION AND BULLETS  -<p>  <b>markup example:</b>  -<p>  +<p> 9.3 INDENTATION AND BULLETS +<p>  <b>markup example:</b> +<p>  <p> <br>  <pre>  ordinary paragraph    _1 indent paragraph one step    _2 indent paragraph two steps    _9 indent paragraph nine steps  </pre> -<p>  <b>resulting output:</b>  -<p>  ordinary paragraph  +<p> +<p> <b>resulting output:</b> +<p>  ordinary paragraph  <p>    indent paragraph one step<br> -  +  <p>      indent paragraph two steps<br> -  +  <p>                    indent paragraph nine steps<br> -  -<p>  <b>markup example:</b>  -<p>  + +<p>  <b>markup example:</b> +<p>  <p> <br> -<pre>  * bullet text +<pre>  _* bullet text    _1* bullet text, first indent    _2* bullet text, two step indent  </pre> -<p>  <b>resulting output:</b>  -<p>  * bullet text  +<p>  <b>resulting output:</b> +<p>  * bullet text  <p>    * bullet text, first indent<br> -  +  <p>      * bullet text, two step indent<br> -  +  <p>  Numbered List (not to be confused with headings/titles, (document structure)) -<p>  <b>markup example:</b>  -<p>  +<p>  <b>markup example:</b> +<p>  <p> <br>  <pre>  # numbered list                numbered list 1., 2., 3, etc.    _# numbered list numbered list indented a., b., c., d., etc.  </pre> -<p> 9.4 FOOTNOTES / ENDNOTES  +<p> 9.4 FOOTNOTES / ENDNOTES  <p>  Footnotes and endnotes not distinguished in  markup. They are automatically numbered. Depending on the output file format  (html, odf, pdf etc.), the document output selected will have either footnotes -or endnotes.  -<p>  <b>markup example:</b>  -<p>  +or endnotes. +<p>  <b>markup example:</b> +<p>  <p> <br>  <pre>  ~{ a footnote or endnote }~  </pre> -<p>  <b>resulting output:</b>  -<p>  [^11]  -<p>  <b>markup example:</b>  -<p>  +<p>  <b>resulting output:</b> +<p>  [^11] +<p>  <b>markup example:</b> +<p>  <p> <br>  <pre>  normal text~{ self contained endnote marker & endnote in one }~ continues  </pre> -<p>  <b>resulting output:</b>  -<p>  normal text[^12] continues  -<p>  <b>markup example:</b>  -<p>  +<p>  <b>resulting output:</b> +<p>  normal text[^12] continues +<p>  <b>markup example:</b> +<p>  <p> <br>  <pre>  normal text ~{* unnumbered asterisk footnote/endnote, insert multiple  asterisks if required }~ continues    normal text ~{** another unnumbered asterisk footnote/endnote }~ continues  </pre> -<p>  <b>resulting output:</b>  -<p>  normal text  [^*] continues  -<p>  normal text  [^**] continues +<p>  <b>resulting output:</b> +<p>  normal text [^*] continues +<p>  normal text [^**] continues -<p>  <b>markup example:</b>  -<p>  +<p> +<p>  <b>markup example:</b> +<p>  <p> <br>  <pre>  normal text ~[*  editors  notes,  numbered  asterisk  footnote/endnote  series   ]~ continues    normal text ~[+  editors  notes,  numbered  asterisk  footnote/endnote  series   ]~ continues  </pre> -<p>  <b>resulting output:</b>  -<p>  normal text  [^*3] continues  -<p>  normal text  [^+2] continues +<p>  <b>resulting output:</b> +<p>  normal text [^*3] continues +<p>  normal text [^+2] continues -<p>  <b>Alternative endnote pair notation for footnotes/endnotes:</b>  -<p>  +<p> +<p>  <b>Alternative endnote pair notation for footnotes/endnotes:</b> +<p>  <p> <br> -<pre> -  % note the endnote marker +<pre>  % note the endnote marker    normal text~^ continues    ^~ endnote text following the paragraph in which the marker occurs  </pre> -<p>  the standard and pair notation cannot be mixed in the same document  +<p>  the standard and pair notation cannot be mixed in the same document  <p> -<p>9.5 LINKS  -<p> 9.5.1 NAKED URLS WITHIN TEXT, DEALING WITH URLS  +<p>9.5 LINKS +<p> 9.5.1 NAKED URLS WITHIN TEXT, DEALING WITH URLS  <p>  urls are found  within text and marked up automatically. A url within text is automatically  hyperlinked to itself and by default decorated with angled braces, unless  they are contained within a code block (in which case they are passed as  normal text), or escaped by a preceding underscore (in which case the decoration -is omitted).  -<p>  <b>markup example:</b>  -<p>  +is omitted). +<p>  <b>markup example:</b> +<p>  <p> <br>  <pre>  normal text http://www.jus.uio.no/sisu continues  </pre> -<p>  <b>resulting output:</b>  +<p>  <b>resulting output:</b>  <p>  normal text <<a href='http://www.jus.uio.no/sisu'>http://www.jus.uio.no/sisu</a> -> continues  +> continues  <p>  An -<p>escaped url without decoration  -<p>  <b>markup example:</b>  -<p>  +<p>escaped url without decoration +<p>  <b>markup example:</b> +<p>  <p> <br>  <pre>  normal text http://www.jus.uio.no/sisu continues    deb http://www.jus.uio.no/sisu/archive unstable main non-free  </pre> -<p>  <b>resulting output:</b>  +<p>  <b>resulting output:</b>  <p>  normal text <a href='http://www.jus.uio.no/sisu'>http://www.jus.uio.no/sisu</a> - continues  + continues  <p>  deb  <p><a href='http://www.jus.uio.no/sisu/archive'>http://www.jus.uio.no/sisu/archive</a> - unstable main non-free  + unstable main non-free  <p>  where a code block  is used there is neither decoration nor hyperlinking, code blocks are discussed -<p>later in this document  -<p>  <b>resulting output:</b>  -<p>  +<p>later in this document +<p>  <b>resulting output:</b> +<p>  <p> <br>  <pre>  deb http://www.jus.uio.no/sisu/archive unstable main non-free    deb-src http://www.jus.uio.no/sisu/archive unstable main non-free  </pre> -<p>  To link text or an image to a url the markup is as follows  +<p>  To link text or an image to a url the markup is as follows  <p>  <b>markup example:</b> -<p>  +<p>  <p> <br>  <pre>  about { SiSU }http://url.org markup  </pre> -<p> 9.5.2 LINKING TEXT  -<p>  <b>resulting output:</b>  +<p> 9.5.2 LINKING TEXT +<p>  <b>resulting output:</b>  <p>  about SiSU <<a href='http://www.jus.uio.no/sisu/'>http://www.jus.uio.no/sisu/</a>  > -<p>markup  +<p>markup  <p>  A shortcut notation is available so the url link may also be provided -<p>automatically as a footnote  -<p>  <b>markup example:</b>  -<p>  +<p>automatically as a footnote +<p>  <b>markup example:</b> +<p>  <p> <br>  <pre>  about {~^ SiSU }http://url.org markup  </pre> -<p>  <b>resulting output:</b>  +<p>  <b>resulting output:</b>  <p>  about SiSU <<a href='http://www.jus.uio.no/sisu/'>http://www.jus.uio.no/sisu/</a> ->  [^13] markup  +> [^13] markup  <p> -<p>9.5.3 LINKING IMAGES  -<p>  <b>markup example:</b>  -<p>  +<p>9.5.3 LINKING IMAGES +<p>  <b>markup example:</b> +<p>  <p> <br> -<pre>     [ tux.png ] +<pre>      [ tux.png ]    % various url linked images -     [ tux.png ] -     [ GnuDebianLinuxRubyBetterWay.png ] +      [ tux.png ] +      [ GnuDebianLinuxRubyBetterWay.png ]    {~^ ruby_logo.png  </pre> -<p>  <b>resulting output:</b>  -<p>  [ tux.png ]  -<p>  tux.png 64x80  +<p>  <b>resulting output:</b> +<p>  [ tux.png ] +<p>  tux.png 64x80  <p>  [  ruby_logo  (png  missing) - ]  [^14]  -<p>  GnuDebianLinuxRubyBetterWay.png 100x101 and Ruby  + ]  [^14] +<p>  GnuDebianLinuxRubyBetterWay.png 100x101 and Ruby  <p>  <b>linked url footnote -<p>shortcut</b>  -<p>  +<p>shortcut</b> +<p>  <p> <br>  <pre>  {~^  [text  to  link] }http://url.org    % maps to: {  [text  to  link] }http://url.org ~{ http://url.org }~    % which produces hyper-linked text within a document/paragraph, with an  endnote providing the url for the text location used in the hyperlink  </pre> -<p>  +<p>  <p> <br>  <pre>  text marker *~name  </pre>  <p>  note at a heading level the same is automatically achieved by providing  names to headings 1, 2 and 3 i.e. 2~[name] and 3~[name] or in the case of -auto-heading numbering, without further intervention.  -<p> 9.6 GROUPED TEXT  +auto-heading numbering, without further intervention. +<p> 9.6 GROUPED TEXT  <p> 9.6.1 -<p>TABLES  -<p>  Tables may be prepared in two either of two forms  +<p>TABLES +<p>  Tables may be prepared in two either of two forms  <p>  <b>markup example:</b> -<p>  +<p>  <p> <br>  <pre>  table{ c3; 40; 30; 30;    This is a table @@ -1183,14 +1194,14 @@ auto-heading numbering, without further intervention.    column three of row two, and so on    }table  </pre> -<p>  <b>resulting output:</b>  +<p>  <b>resulting output:</b>  <p>   [table  omitted,  see  other  document  formats]<br> -  +  <p>  a second form may be easier to work with in cases where there is not -<p>much information in each column  -<p>  <b>markup example:</b> [^15]  -<p>  +<p>much information in each column +<p>  <b>markup example:</b> [^15] +<p>  <p> <br>  <pre>  !_ Table 3.1: Contributors to Wikipedia, January 2001 - June 2005    {table~h 24; 12; 12; 12; 12; 12; 12;} @@ -1202,38 +1213,38 @@ auto-heading numbering, without further intervention.     8,442|   16,945    Very active contributors***     |        0|       31|      190|      692|     1,639|    3,016 -  No. of English language articles|       25|   16,000|  101,000|  190,000|  +  No. of English language articles|       25|   16,000|  101,000|  190,000|  320,000|  630,000 -  No. of articles, all languages  |       25|   19,000|  138,000|  490,000|  +  No. of articles, all languages  |       25|   19,000|  138,000|  490,000|  862,000|1,600,000    \* Contributed at least ten times; \** at least 5 times in last month;  \* more than 100 times in last month.  </pre> -<p>  <b>resulting output:</b>  +<p>  <b>resulting output:</b>  <p>  <b>Table 3.1: Contributors to Wikipedia, January 2001 -- June 2005</b>  +- June 2005</b>  <p>   [table  omitted,  see  other  document  formats]<br> -  +  <p>  * Contributed at least ten times; ** at least 5 times in last month; -*** more than 100 times in last month.  -<p> 9.6.2 POEM  -<p>  <b>basic markup:</b>  -<p>  +*** more than 100 times in last month. +<p> 9.6.2 POEM +<p>  <b>basic markup:</b> +<p>  <p> <br>  <pre>  poem{      Your poem here    }poem    Each verse in a poem is given a separate object number.  </pre> -<p>  <b>markup example:</b>  -<p>  +<p>  <b>markup example:</b> +<p>  <p> <br>  <pre>  poem{                        ’Fury said to a                       mouse, That he                     met in the                   house, -  +                  both go to                    law:  I will                      prosecute @@ -1258,13 +1269,13 @@ auto-heading numbering, without further intervention.                  wasting                 our                  breath. -  +                     judge, I’ll                       be jury,                             Said                        cunning                          old Fury: -  +                          try the                             whole                              cause, @@ -1275,115 +1286,71 @@ auto-heading numbering, without further intervention.                           death.    }poem  </pre> -<p>  <b>resulting output:</b>  -<p>  +<p>  <b>resulting output:</b> +<p>  <p>                     ’Fury said to a<br> - <p> -                   mouse, That he<br> - <p> -                 met in the<br> - <p> -               house,<br> - <p> - <br> - <p> -              both go to<br> - <p> -                law:  I will<br> - <p> -                  prosecute<br> - <p> -                    YOU.  --Come,<br> - <p> -                       I’ll take no<br> - <p> -                        denial; We<br> - <p> -                     must have a<br> - <p> -                 trial:  For<br> - <p> -              really this<br> - <p> -           morning I’ve<br> - <p> -          nothing<br> - <p> -         to do.<br> - <p> -           Said the<br> - <p> -             mouse to the<br> - <p> -               cur,<br> - <p> -                 a trial,<br> - <p> -                   dear Sir,<br> - <p> -                         With<br> - <p> -                     no jury<br> - <p> -                  or judge,<br> - <p> -                would be<br> - <p> -              wasting<br> - <p> -             our<br> - <p> -              breath.<br> - <p> - <br> - <p> -                 judge, I’ll<br> - <p> -                   be jury,<br> - <p> -                         Said<br> - <p> -                    cunning<br> - <p> -                      old Fury:<br> - <p> - <br> - <p> -                      try the<br> - <p> -                         whole<br> - <p> -                          cause,<br> - <p> -                             and<br> - <p> -                        condemn<br> - <p> -                       you<br> - <p> -                      to<br> - <p> -                       death.<br> - <p> - -<p> 9.6.3 GROUP  -<p>  <b>basic markup:</b>  -<p>  +                     mouse, That he<br> +                   met in the<br> +                 house,<br> +   <br> +                both go to<br> +                  law:  I will<br> +                    prosecute<br> +                      YOU.  --Come,<br> +                         I’ll take no<br> +                          denial; We<br> +                       must have a<br> +                   trial:  For<br> +                really this<br> +             morning I’ve<br> +            nothing<br> +           to do.<br> +             Said the<br> +               mouse to the<br> +                 cur,<br> +                   a trial,<br> +                     dear Sir,<br> +                           With<br> +                       no jury<br> +                    or judge,<br> +                  would be<br> +                wasting<br> +               our<br> +                breath.<br> +   <br> +                   judge, I’ll<br> +                     be jury,<br> +                           Said<br> +                      cunning<br> +                        old Fury:<br> +   <br> +                        try the<br> +                           whole<br> +                            cause,<br> +                               and<br> +                          condemn<br> +                         you<br> +                        to<br> +                         death.<br> + +<p> 9.6.3 GROUP +<p>  <b>basic markup:</b> +<p>  <p> <br>  <pre>  group{      Your grouped text here    }group    A group is treated as an object and given a single object number.  </pre> -<p>  <b>markup example:</b>  -<p>  +<p>  <b>markup example:</b> +<p>  <p> <br>  <pre>  group{                        ’Fury said to a                       mouse, That he                     met in the                   house, -  +                  both go to                    law:  I will                      prosecute @@ -1408,13 +1375,13 @@ auto-heading numbering, without further intervention.                  wasting                 our                  breath. -  +                     judge, I’ll                       be jury,                             Said                        cunning                          old Fury: -  +                          try the                             whole                              cause, @@ -1425,115 +1392,71 @@ auto-heading numbering, without further intervention.                           death.    }group  </pre> -<p>  <b>resulting output:</b>  -<p>  +<p>  <b>resulting output:</b> +<p>  <p>                     ’Fury said to a<br> - <p> -                   mouse, That he<br> - <p> -                 met in the<br> - <p> -               house,<br> - <p> - <br> - <p> -              both go to<br> - <p> -                law:  I will<br> - <p> -                  prosecute<br> - <p> -                    YOU.  --Come,<br> - <p> -                       I’ll take no<br> - <p> -                        denial; We<br> - <p> -                     must have a<br> - <p> -                 trial:  For<br> - <p> -              really this<br> - <p> -           morning I’ve<br> - <p> -          nothing<br> - <p> -         to do.<br> - <p> -           Said the<br> - <p> -             mouse to the<br> - <p> -               cur,<br> - <p> -                 a trial,<br> - <p> -                   dear Sir,<br> - <p> -                         With<br> - <p> -                     no jury<br> - <p> -                  or judge,<br> - <p> -                would be<br> - <p> -              wasting<br> - <p> -             our<br> - <p> -              breath.<br> - <p> - <br> - <p> -                 judge, I’ll<br> - <p> -                   be jury,<br> - <p> -                         Said<br> - <p> -                    cunning<br> - <p> -                      old Fury:<br> - <p> - <br> - <p> -                      try the<br> - <p> -                         whole<br> - <p> -                          cause,<br> - <p> -                             and<br> - <p> -                        condemn<br> - <p> -                       you<br> - <p> -                      to<br> - <p> -                       death.<br> - <p> - -<p> 9.6.4 CODE  +                     mouse, That he<br> +                   met in the<br> +                 house,<br> +   <br> +                both go to<br> +                  law:  I will<br> +                    prosecute<br> +                      YOU.  --Come,<br> +                         I’ll take no<br> +                          denial; We<br> +                       must have a<br> +                   trial:  For<br> +                really this<br> +             morning I’ve<br> +            nothing<br> +           to do.<br> +             Said the<br> +               mouse to the<br> +                 cur,<br> +                   a trial,<br> +                     dear Sir,<br> +                           With<br> +                       no jury<br> +                    or judge,<br> +                  would be<br> +                wasting<br> +               our<br> +                breath.<br> +   <br> +                   judge, I’ll<br> +                     be jury,<br> +                           Said<br> +                      cunning<br> +                        old Fury:<br> +   <br> +                        try the<br> +                           whole<br> +                            cause,<br> +                               and<br> +                          condemn<br> +                         you<br> +                        to<br> +                         death.<br> + +<p> 9.6.4 CODE  <p>  Code tags are used to escape regular sisu markup, and have  been used extensively within this document to provide examples of <b>SiSU</b>  markup. You cannot however use code tags to escape code tags. They are however -used in the same way as group or poem tags.  +used in the same way as group or poem tags.  <p>  A code-block is treated as -an object and given a single object number.  [an more than 100 times in last +an object and given a single object number. [an more than 100 times in last  month. option  to  number  each  line  of  code  may  be  considered  at more than -100 times in last month. some  later  time]  +100 times in last month. some  later  time]  <p>  <b>use of code tags instead of -poem compared, resulting output:</b>  -<p>  +poem compared, resulting output:</b> +<p>  <p> <br>  <pre>                      ’Fury said to a                       mouse, That he                     met in the                   house, -  +                  both go to                    law:  I will                      prosecute @@ -1558,13 +1481,13 @@ poem compared, resulting output:</b>                  wasting                 our                  breath. -  +                     judge, I’ll                       be jury,                             Said                        cunning                          old Fury: -  +                          try the                             whole                              cause, @@ -1574,7 +1497,7 @@ poem compared, resulting output:</b>                          to                           death.  </pre> -<p> 10. COMPOSITE DOCUMENTS MARKUP   +<p> 10. COMPOSITE DOCUMENTS MARKUP  <p>  It is possible to build a document by  creating a master document that requires other documents. The documents  required may be complete documents that could be generated independently, @@ -1588,11 +1511,11 @@ within a master document <b>.sst</b> regular markup file, or <b>.ssi</b> (insert  <p>A secondary file of the composite document is built prior to processing -<p>with the same prefix and the suffix <b>._sst</b>  +<p>with the same prefix and the suffix <b>._sst</b>  <p>  basic markup for importing a -<p>document into a master document  -<p>  +<p>document into a master document +<p>  <p> <br>  <pre>  << filename1.sst    << filename2.ssi @@ -1602,83 +1525,83 @@ results in the text thus linked becoming hyperlinked to the document it  is calling in which is convenient for editing. Alternative markup for importation  of documents under consideration, and occasionally supported have been. -<p>  +<p>  <p> <br>  <pre>  << filename.ssi    <<{filename.ssi}    % using textlink alternatives    << |filename.ssi|@|^|  </pre> -<p> MARKUP SYNTAX HISTORY   +<p> MARKUP SYNTAX HISTORY  <p> 11. NOTES RELATED TO FILES-TYPES AND MARKUP SYNTAX -  +  <p>  0.38 is substantially current, depreciated 0.16 supported, though file -<p>names were changed at 0.37  -<p>  * sisu --query=[sisu  version   [0.38] or ’history] +<p>names were changed at 0.37 +<p>  * sisu --query=[sisu  version  [0.38] or ’history] -<p>  provides a short history of changes to <b>SiSU</b> markup  +<p>  provides a short history of changes to <b>SiSU</b> markup  <p>  <b>0.57</b> (2007w34/4)  <b>SiSU</b> 0.57 is the same as 0.42 with the introduction of some a shortcut to -use the headers @title and @creator in the first heading  [expanded  using - the contents  of  the  headers  @title:  and  @author:]  -<p>  +use the headers @title and @creator in the first heading [expanded  using + the  and  @author:] +<p>  <p> <br>  <pre>  :A~ @title by @author  </pre>  <p>  <b>0.52</b> (2007w14/6) declared document type identifier at start of text/document:  <p>    .B SiSU<br> - 0.52  -<p>  or, backward compatible using the comment marker:  + 0.52 +<p>  or, backward compatible using the comment marker:  <p>    %<br> - <b>SiSU</b> 0.38  -<p>  variations include ’ <b>SiSU</b> (text|master|insert)  [version]’ and ’sisu-[version]’ + <b>SiSU</b> 0.38 +<p>  variations include ’ <b>SiSU</b> (text|master|insert) [version]’ and ’sisu-[version]’ -<p>  <b>0.51</b> (2007w13/6) skins changed (simplified), markup unchanged  +<p>  <b>0.51</b> (2007w13/6) skins changed (simplified), markup unchanged  <p>  <b>0.42</b> (2006w27/4) -* (asterisk) type endnotes, used e.g. in relation to author  +* (asterisk) type endnotes, used e.g. in relation to author  <p>  <b>SiSU</b> 0.42 is  the same as 0.38 with the introduction of some additional endnote types,  <p>  Introduces some variations on endnotes, in particular the use of the -<p>asterisk  -<p>  +<p>asterisk +<p>  <p> <br>  <pre>  ~{* for example for describing an author }~ and ~{** for describing a  second author }~  </pre> -<p>  * for example for describing an author  +<p>  * for example for describing an author  <p>  ** for describing a second author -<p>  and  -<p>  +<p>  and +<p>  <p> <br>  <pre>  ~[*  my  note  ]~ or ~[+  another  note  ]~  </pre> -<p>  which numerically increments an asterisk and plus respectively  +<p>  which numerically increments an asterisk and plus respectively  <p>  *1 my -<p>note +1 another note  +<p>note +1 another note  <p>  <b>0.38</b> (2006w15/7) introduced new/alternative notation  for headers, e.g. @title: (instead of 0~title), and accompanying document -structure markup, :A,:B,:C,1,2,3 (maps to previous 1,2,3,4,5,6)  +structure markup, :A,:B,:C,1,2,3 (maps to previous 1,2,3,4,5,6)  <p>  <b>SiSU</b>  0.38 introduced alternative experimental header and heading/structure markers, -<p>  +<p>  <p> <br>  <pre>  @headername: and headers :A~ :B~ :C~ 1~ 2~ 3~  </pre> -<p>  as the equivalent of:  -<p>  +<p>  as the equivalent of: +<p>  <p> <br>  <pre>  0~headername and headers 1~ 2~ 3~ 4~ 5~ 6~  </pre>  <p>  The internal document markup of <b>SiSU</b> 0.16 remains valid and standard Though -<p>note that <b>SiSU</b> 0.37 introduced a new file naming convention  +<p>note that <b>SiSU</b> 0.37 introduced a new file naming convention  <p>  <b>SiSU</b> has in  effect two sets of levels to be considered, using 0.38 notation A-C headings/levels,  pre-ordinary paragraphs /pre-substantive text, and 1-3 headings/levels, levels @@ -1694,45 +1617,45 @@ your face and likely to be understood fairly quickly); the substantive  text follows levels 1,2,3 and it is ’nice’ to do most work in those levels  <p>  <b>0.37</b> (2006w09/7) introduced new file naming convention, .sst (text), .ssm -(master), .ssi (insert), markup syntax unchanged  +(master), .ssi (insert), markup syntax unchanged  <p>  <b>SiSU</b> 0.37 introduced new  file naming convention, using the file extensions .sst  .ssm and .ssi to replace  .s1 .s2 .s3 .r1 .r2 .r3 and .si<br> -  -<p>  this is captured by the following file ’rename’ instruction:  -<p>  + +<p>  this is captured by the following file ’rename’ instruction: +<p>  <p> <br>  <pre>  rename ’s/.s[123]$/.sst/’ *.s{1,2,3}    rename ’s/.r[123]$/.ssm/’ *.r{1,2,3}    rename ’s/.si$/.ssi/’ *.si  </pre> -<p>  The internal document markup remains unchanged, from <b>SiSU</b> 0.16  +<p>  The internal document markup remains unchanged, from <b>SiSU</b> 0.16  <p>  <b>0.35</b> (2005w52/3) -sisupod, zipped content file introduced  +sisupod, zipped content file introduced  <p>  <b>0.23</b> (2005w36/2) utf-8 for markup -<p>file  +<p>file  <p>  <b>0.22</b> (2005w35/3) image dimensions may be omitted if rmagick is available -<p>to be relied upon  -<p>  <b>0.20.4</b> (2005w33/4) header 0~links  +<p>to be relied upon +<p>  <b>0.20.4</b> (2005w33/4) header 0~links  <p>  <b>0.16</b> (2005w25/2) substantial  changes introduced to make markup cleaner, header 0~title type, and headings - [1-6]~ introduced, also percentage sign (%) at start of a text line as comment +[1-6]~ introduced, also percentage sign (%) at start of a text line as comment -<p>marker  -<p>  <b>SiSU</b> 0.16 (0.15 development branch) introduced the use of  +<p>marker +<p>  <b>SiSU</b> 0.16 (0.15 development branch) introduced the use of  <p>  the -header 0~ and headings/structure 1~ 2~ 3~ 4~ 5~ 6~  +header 0~ and headings/structure 1~ 2~ 3~ 4~ 5~ 6~  <p>  in place of the 0.1 -header, heading/structure notation  +header, heading/structure notation  <p>  <b>SiSU</b> 0.1 headers and headings structure -represented by header 0{~ and headings/structure 1{ 2{ 3{ 4{~ 5{ 6{  +represented by header 0{~ and headings/structure 1{ 2{ 3{ 4{~ 5{ 6{  <p> 12. -SISU FILETYPES   +SISU FILETYPES  <p>  <b>SiSU</b> has plaintext and binary filetypes, and can process -either type of document.  -<p> 12.1 .SST .SSM .SSI MARKED UP PLAIN TEXT  +either type of document. +<p> 12.1 .SST .SSM .SSI MARKED UP PLAIN TEXT  <p>  <b>SiSU</b> documents  are prepared as plain-text (utf-8) files with <b>SiSU</b> markup. They may make reference  to and contain images (for example), which are stored in the directory @@ -1741,264 +1664,259 @@ that may be distinguished by the file extension used: regular text .sst;  master documents, composite documents that incorporate other text, which  can be any regular text or text insert; and inserts the contents of which  are like regular text except these are marked  .ssi and are not processed.<br> -  +  <p>  <b>SiSU</b> processing can be done directly against a sisu documents; which  may be located locally or on a remote server for which a url is provided. -<p>  <b>SiSU</b> source markup can be shared with the command:  -<p>    sisu -s  [filename]<br> -  -<p> 12.1.1 SISU TEXT - REGULAR FILES (.SST)  +<p>  <b>SiSU</b> source markup can be shared with the command: +<p>    sisu -s [filename]<br> + +<p> 12.1.1 SISU TEXT - REGULAR FILES (.SST)  <p>  The most common form of document -in <b>SiSU</b> , see the section on <b>SiSU</b> markup.  +in <b>SiSU</b> , see the section on <b>SiSU</b> markup.  <p>  <<a href='http://www.jus.uio.no/sisu/sisu_markup'>http://www.jus.uio.no/sisu/sisu_markup</a>  >  <p>  <<a href='http://www.jus.uio.no/sisu/sisu_manual'>http://www.jus.uio.no/sisu/sisu_manual</a> ->  -<p> 12.1.2 SISU MASTER FILES (.SSM)  +> +<p> 12.1.2 SISU MASTER FILES (.SSM)  <p>  Composite  documents which incorporate other <b>SiSU</b> documents which may be either regular  <b>SiSU</b> text .sst which may be generated independently, or inserts prepared  solely for the purpose of being incorporated into one or more master documents.  <p>  The mechanism by which master files incorporate other documents is described -as one of the headings under under <b>SiSU</b> markup in the <b>SiSU</b> manual.  +as one of the headings under under <b>SiSU</b> markup in the <b>SiSU</b> manual.  <p>  Note:  Master documents may be prepared in a similar way to regular documents,  and processing will occur normally if a .sst file is renamed .ssm without  requiring any other documents; the .ssm marker flags that the document may -contain other documents.  +contain other documents.  <p>  Note: a secondary file of the composite document -is built prior to processing with the same prefix and the suffix ._sst  [^16] +is built prior to processing with the same prefix and the suffix ._sst [^16]  <p>  <<a href='http://www.jus.uio.no/sisu/sisu_markup'>http://www.jus.uio.no/sisu/sisu_markup</a> ->  +>  <p>  <<a href='http://www.jus.uio.no/sisu/sisu_manual'>http://www.jus.uio.no/sisu/sisu_manual</a>  > -<p> 12.1.3 SISU INSERT FILES (.SSI)  +<p> 12.1.3 SISU INSERT FILES (.SSI)  <p>  Inserts are documents prepared solely for  the purpose of being incorporated into one or more master documents. They  resemble regular <b>SiSU</b> text files except they are ignored by the <b>SiSU</b> processor.  Making a file a .ssi file is a quick and convenient way of flagging that -it is not intended that the file should be processed on its own.  +it is not intended that the file should be processed on its own.  <p> 12.2 SISUPOD, -ZIPPED BINARY CONTAINER (SISUPOD.ZIP, .SSP)  +ZIPPED BINARY CONTAINER (SISUPOD.ZIP, .SSP)  <p>  A sisupod is a zipped <b>SiSU</b>  text file or set of <b>SiSU</b> text files and any associated images that they -contain (this will be extended to include sound and multimedia-files)  -<p>  +contain (this will be extended to include sound and multimedia-files) +<p>  <b>SiSU</b> plaintext files rely on a recognised directory structure to find contents  such as images associated with documents, but all images for example for  all documents contained in a directory are located in the sub-directory  _sisu/image. Without the ability to create a sisupod it can be inconvenient  to manually identify all other files associated with a document. A sisupod  automatically bundles all associated files with the document that is turned -into a pod.  +into a pod.  <p>  The structure of the sisupod is such that it may for example  contain a single document and its associated images; a master document  and its associated documents and anything else; or the zipped contents -of a whole directory of prepared <b>SiSU</b> documents.  +of a whole directory of prepared <b>SiSU</b> documents.  <p>  The command to create -a sisupod is:  -<p>    sisu -S  [filename]<br> -  -<p>  Alternatively, make a pod of the contents of a whole directory:  -<p>    +a sisupod is: +<p>    sisu -S [filename]<br> + +<p>  Alternatively, make a pod of the contents of a whole directory: +<p>  sisu -S<br> -  +  <p>  <b>SiSU</b> processing can be done directly against a sisupod; which may be -located locally or on a remote server for which a url is provided.  +located locally or on a remote server for which a url is provided.  <p>  <<a href='http://www.jus.uio.no/sisu/sisu_commands'>http://www.jus.uio.no/sisu/sisu_commands</a>  >  <p>  <<a href='http://www.jus.uio.no/sisu/sisu_manual'>http://www.jus.uio.no/sisu/sisu_manual</a> ->  +>  <p> 13. EXPERIMENTAL ALTERNATIVE INPUT -REPRESENTATIONS   -<p> 13.1 ALTERNATIVE XML  +REPRESENTATIONS +<p> 13.1 ALTERNATIVE XML  <p>  <b>SiSU</b> offers alternative XML input  representations of documents as a proof of concept, experimental feature.  They are however not strictly maintained, and incomplete and should be -handled with care.  +handled with care.  <p>  <b>convert from sst to simple xml representations (sax, -dom and node):</b>  -<p>    sisu --to-sax  [filename/wildcard] or sisu --to-sxs node):<br> -   [filename/wildcard]<br> -  -<p>    sisu --to-dom  [filename/wildcard] or sisu --to-sxd node):<br> -   [filename/wildcard]<br> -  -<p>    sisu --to-node  [filename/wildcard] or sisu --to-sxn <br> -   [filename/wildcard]<br> -  +dom and node):</b> +<p>    sisu --to-sax [filename/wildcard] or sisu --to-sxs [filename/wildcard]<br> + +<p>    sisu --to-dom [filename/wildcard] or sisu --to-sxd [filename/wildcard]<br> + +<p>    sisu --to-node [filename/wildcard] or sisu --to-sxn [filename/wildcard]<br> + +<p>  <p>  <b>convert to sst from any sisu xml representation (sax, dom and node):</b> -<p>    sisu --from-xml2sst  [filename/wildcard   [.sxs.xml,.sxd.xml,sxn.xml]]<br> -  -<p>  or the same:  -<p>    sisu --from-sxml  [filename/wildcard   [.sxs.xml,.sxd.xml,sxn.xml]]<br> -  -<p> 13.1.1 XML SAX REPRESENTATION  +<p>    sisu --from-xml2sst [filename/wildcard  [.sxs.xml,.sxd.xml,sxn.xml]]<br> + +<p>  or the same: +<p>    sisu --from-sxml [filename/wildcard  [.sxs.xml,.sxd.xml,sxn.xml]]<br> + +<p> 13.1.1 XML SAX REPRESENTATION  <p>  To convert from sst to simple xml (sax) -representation:  -<p>    sisu --to-sax  [filename/wildcard] or sisu --to-sxs <br> -   [filename/wildcard]<br> -  -<p>  To convert from any sisu xml representation back to sst  +representation: +<p>    sisu --to-sax [filename/wildcard] or sisu --to-sxs [filename/wildcard]<br> + +<p>  To convert from any sisu xml representation back to sst  <p>    sisu --from-xml2sst - [filename/wildcard   [.sxs.xml,.sxd.xml,sxn.xml]]<br> -  -<p>  or the same:  -<p>    sisu --from-sxml  [filename/wildcard   [.sxs.xml,.sxd.xml,sxn.xml]]<br> -  -<p> 13.1.2 XML DOM REPRESENTATION  +[filename/wildcard  [.sxs.xml,.sxd.xml,sxn.xml]]<br> + +<p>  or the same: +<p>    sisu --from-sxml [filename/wildcard  [.sxs.xml,.sxd.xml,sxn.xml]]<br> + +<p> 13.1.2 XML DOM REPRESENTATION  <p>  To convert from sst to simple xml (dom) -representation:  -<p>    sisu --to-dom  [filename/wildcard] or sisu --to-sxd <br> -   [filename/wildcard]<br> -  -<p>  To convert from any sisu xml representation back to sst  +representation: +<p>    sisu --to-dom [filename/wildcard] or sisu --to-sxd [filename/wildcard]<br> + +<p>  To convert from any sisu xml representation back to sst  <p>    sisu --from-xml2sst - [filename/wildcard   [.sxs.xml,.sxd.xml,sxn.xml]]<br> -  -<p>  or the same:  -<p>    sisu --from-sxml  [filename/wildcard   [.sxs.xml,.sxd.xml,sxn.xml]]<br> -  -<p> 13.1.3 XML NODE REPRESENTATION  +[filename/wildcard  [.sxs.xml,.sxd.xml,sxn.xml]]<br> + +<p>  or the same: +<p>    sisu --from-sxml [filename/wildcard  [.sxs.xml,.sxd.xml,sxn.xml]]<br> + +<p> 13.1.3 XML NODE REPRESENTATION  <p>  To convert from sst to simple xml (node) -representation:  -<p>    sisu --to-node  [filename/wildcard] or sisu --to-sxn <br> -   [filename/wildcard]<br> -  -<p>  To convert from any sisu xml representation back to sst  +representation: +<p>    sisu --to-node [filename/wildcard] or sisu --to-sxn [filename/wildcard]<br> + +<p>  To convert from any sisu xml representation back to sst  <p>    sisu --from-xml2sst - [filename/wildcard   [.sxs.xml,.sxd.xml,sxn.xml]]<br> -  -<p>  or the same:  -<p>    sisu --from-sxml  [filename/wildcard   [.sxs.xml,.sxd.xml,sxn.xml]]<br> -  -<p> 14. CONFIGURATION   -<p> 14.1 DETERMINING THE CURRENT CONFIGURATION  +[filename/wildcard  [.sxs.xml,.sxd.xml,sxn.xml]]<br> + +<p>  or the same: +<p>    sisu --from-sxml [filename/wildcard  [.sxs.xml,.sxd.xml,sxn.xml]]<br> + +<p> 14. CONFIGURATION +<p> 14.1 DETERMINING THE CURRENT CONFIGURATION  <p>  Information  on the current configuration of <b>SiSU</b> should be available with the help -command:  +command:  <p>    sisu -v<br> -  -<p>  which is an alias for:  + +<p>  which is an alias for:  <p>    sisu --help env<br> -  +  <p>  Either of these should be executed from within a directory that contains -sisu markup source documents.  -<p> 14.2 CONFIGURATION FILES (CONFIG.YML)  +sisu markup source documents. +<p> 14.2 CONFIGURATION FILES (CONFIG.YML)  <p>  <b>SiSU</b>  configration parameters are adjusted in the configuration file, which can  be used to override the defaults set. This includes such things as which  directory interim processing should be done in and where the generated -output should be placed.  +output should be placed.  <p>  The <b>SiSU</b> configuration file is a yaml file, which -means indentation is significant.  +means indentation is significant.  <p>  <b>SiSU</b> resource configuration is determined -by looking at the following files if they exist:  +by looking at the following files if they exist:  <p>    ./_sisu/sisurc.yml<br> -  +  <p>    ~/.sisu/sisurc.yml<br> -  +  <p>    /etc/sisu/sisurc.yml<br> -  -<p>  The search is in the order listed, and the first one found is used.  + +<p>  The search is in the order listed, and the first one found is used.  <p>   In the absence of instructions in any of these it falls back to the internal -program defaults.  +program defaults.  <p>  Configuration determines the output and processing directories -and the database access details.  +and the database access details.  <p>  If <b>SiSU</b> is installed a sample sisurc.yml -<p>may be found in /etc/sisu/sisurc.yml  -<p> 15. SKINS   +<p>may be found in /etc/sisu/sisurc.yml +<p> 15. SKINS  <p>  Skins modify the default  appearance of document output on a document, directory, or site wide basis. -Skins are looked for in the following locations:  +Skins are looked for in the following locations:  <p>    ./_sisu/skin<br> -  +  <p>    ~/.sisu/skin<br> -  +  <p>    /etc/sisu/skin<br> -  +  <p>  <b>Within the skin directory</b> are the following the default sub-directories -for document skins:  +for document skins:  <p>    ./skin/doc<br> -  +  <p>    ./skin/dir<br> -  +  <p>    ./skin/site<br> -  +  <p>  A skin is placed in the appropriate directory and the file named skin_[name].rb  <p>  The skin itself is a ruby file which modifies the default appearances -set in the program.  -<p> 15.1 DOCUMENT SKIN  +set in the program. +<p> 15.1 DOCUMENT SKIN  <p>  Documents take on a document skin, -if the header of the document specifies a skin to be used.  -<p>  +if the header of the document specifies a skin to be used. +<p>  <p> <br>  <pre>  @skin: skin_united_nations  </pre> -<p> 15.2 DIRECTORY SKIN  +<p> 15.2 DIRECTORY SKIN  <p>  A directory may be mapped on to a particular skin,  so all documents within that directory take on a particular appearance.  If a skin exists in the skin/dir with the same name as the document directory,  it will automatically be used for each of the documents in that directory,  (except where a document specifies the use of another skin, in the skin/doc -directory).  +directory).  <p>  A personal habit is to place all skins within the doc directory,  and symbolic links as needed from the site, or dir directories as required. -<p> 15.3 SITE SKIN  -<p>  A site skin, modifies the program default skin.  +<p> 15.3 SITE SKIN +<p>  A site skin, modifies the program default skin.  <p> 15.4 SAMPLE -<p>SKINS  -<p>  With <b>SiSU</b> installed sample skins may be found in:  +<p>SKINS +<p>  With <b>SiSU</b> installed sample skins may be found in:  <p>    /etc/sisu/skin/doc  and<br>     /usr/share/doc/sisu/sisu_markup_samples/dfsg/_sisu/skin/doc<br> -  +  <p>  (or equivalent directory) and if sisu-markup-samples is installed also -under:  +under:  <p>    /usr/share/doc/sisu/sisu_markup_samples/non-free/_sisu/skin/doc<br> -  +  <p>  Samples of list.yml and promo.yml (which are used to create the right -column list) may be found in:  +column list) may be found in:  <p>    /usr/share/doc/sisu/sisu_markup_samples/dfsg/_sisu/skin/yml  (or equivalent<br>     directory)<br> -  -<p> 16. CSS - CASCADING STYLE SHEETS (FOR HTML, XHTML AND XML)   + +<p> 16. CSS - CASCADING STYLE SHEETS (FOR HTML, XHTML AND XML)  <p>  CSS files  to modify the appearance of <b>SiSU</b> html, XHTML or XML may be placed in the  configuration directory:  ./_sisu/css; ~/.sisu/css or; /etc/sisu/css and  these will be copied to the<br> - output directories with the command sisu -CC.  + output directories with the command sisu -CC.  <p>  The basic CSS file for html  output is html.css, placing a file of that name in directory _sisu/css or  equivalent will result in the default file of that name being overwritten. -<p>  HTML: html.css  -<p>  XML DOM: dom.css  -<p>  XML SAX: sax.css  -<p>  XHTML: xhtml.css  +<p>  HTML: html.css +<p>  XML DOM: dom.css +<p>  XML SAX: sax.css +<p>  XHTML: xhtml.css  <p> - The default homepage may use homepage.css or html.css  + The default homepage may use homepage.css or html.css  <p>  Under consideration  is to permit the placement of a CSS file with a different name in directory  _sisu/css directory or equivalent, and change the default CSS file that -is looked for in a skin.[^17]  -<p> 17. ORGANISING CONTENT   +is looked for in a skin.[^17] +<p> 17. ORGANISING CONTENT  <p> 17.1 DIRECTORY STRUCTURE -<p>AND MAPPING  +<p>AND MAPPING  <p>  The output directory root can be set in the sisurc.yml file.  Under the root, subdirectories are made for each directory in which a document  set resides. If you have a directory named poems or conventions, that directory @@ -2006,7 +1924,7 @@ will be created under the output directory root and the output for all  documents contained in the directory of a particular name will be generated  to subdirectories beneath that directory (poem or conventions). A document  will be placed in a subdirectory of the same name as the document with -the filetype identifier stripped (.sst .ssm)  +the filetype identifier stripped (.sst .ssm)  <p>  The last part of a directory  path, representing the sub-directory in which a document set resides, is  the directory name that will be used for the output directory. This has @@ -2022,45 +1940,45 @@ named after each institution, and these would be output to the same output  directory. Skins could be associated with each institution on a directory  basis and resulting documents will take on the appropriate different appearance. -<p> 17.2 ORGANISING CONTENT  -<p> 18. HOMEPAGES   +<p> 17.2 ORGANISING CONTENT +<p> 18. HOMEPAGES  <p>  <b>SiSU</b> is about the ability to auto-generate  documents. Home pages are regarded as custom built items, and are not created  by <b>SiSU</b>  <b>SiSU</b> has a default home page, which will not be appropriate for  use with other sites, and the means to provide your own home page instead -in one of two ways as part of a site’s configuration, these being:  +in one of two ways as part of a site’s configuration, these being:  <p>  1. through  placing your home page and other custom built documents in the subdirectory  _sisu/home/ (this probably being the easier and more convenient option) -<p>  2. through providing what you want as the home page in a skin,  +<p>  2. through providing what you want as the home page in a skin,  <p>  Document  sets are contained in directories, usually organised by site or subject.  Each directory can/should have its own homepage. See the section on directory -structure and organisation of content.  +structure and organisation of content.  <p> 18.1 HOME PAGE AND OTHER CUSTOM BUILT -<p>PAGES IN A SUB-DIRECTORY  +<p>PAGES IN A SUB-DIRECTORY  <p>  Custom built pages, including the home page index.html  may be placed within the configuration directory _sisu/home/ in any of  the locations that is searched for the configuration directory, namely  ./_sisu; ~/_sisu; /etc/sisu From there they are copied to the root of the -output directory with the command:  +output directory with the command:  <p>    sisu -CC<br> -  -<p> 18.2 HOME PAGE WITHIN A SKIN  + +<p> 18.2 HOME PAGE WITHIN A SKIN  <p>  Skins are described in a separate section,  but basically are a file written in the programming language <b>Ruby</b> that  may be provided to change the defaults that are provided with sisu with -respect to individual documents, a directories contents or for a site.  +respect to individual documents, a directories contents or for a site.  <p>   If you wish to provide a homepage within a skin the skin should be in  the directory _sisu/skin/dir and have the name of the directory for which  it is to become the home page. Documents in the directory commercial_law  would have the homepage modified in skin_commercial law.rb; or the directory -<p>poems in skin_poems.rb  -<p>  +<p>poems in skin_poems.rb +<p>  <p> <br>  <pre>    class Home        def homepage @@ -2076,20 +1994,20 @@ index.html        end      end  </pre> -<p> 19. MARKUP AND OUTPUT EXAMPLES   -<p> 19.1 MARKUP EXAMPLES  +<p> 19. MARKUP AND OUTPUT EXAMPLES +<p> 19.1 MARKUP EXAMPLES  <p>  Current markup examples  and document output samples are provided at <<a href='http://www.jus.uio.no/sisu/SiSU/examples.html'>http://www.jus.uio.no/sisu/SiSU/examples.html</a>  >  <p>  Some markup with syntax highlighting may be found under <<a href='http://www.jus.uio.no/sisu/sample/syntax'>http://www.jus.uio.no/sisu/sample/syntax</a>  > -but is not as up to date.  +but is not as up to date.  <p>  For some documents hardly any markup at all  is required at all, other than a header, and an indication that the levels -to be taken into account by the program in generating its output are.  +to be taken into account by the program in generating its output are.  <p> 20. -SISU SEARCH - INTRODUCTION   +SISU SEARCH - INTRODUCTION  <p>  <b>SiSU</b> output can easily and conveniently be  indexed by a number of standalone indexing tools, such as Lucene, Hyperestraier. @@ -2097,28 +2015,28 @@ indexed by a number of standalone indexing tools, such as Lucene, Hyperestraier.  the text object citation system is available hypothetically at least, for  all forms of output, it is possible to search the sql database, and either  read results from that database, or just as simply map the results to the -html output, which has richer text markup.  +html output, which has richer text markup.  <p>  In addition to this <b>SiSU</b> has  the ability to populate a relational sql type database with documents at  an object level, with objects numbers that are shared across different  output types, which make them searchable with that degree of granularity.  Basically, your match criteria is met by these documents and at these locations  within each document, which can be viewed within the database directly -or in various output formats.  -<p> 21. SQL   +or in various output formats. +<p> 21. SQL  <p> 21.1 POPULATING SQL TYPE DATABASES  <p>  <b>SiSU</b> feeds sisu markupd documents into sql type databases PostgreSQL[^18]  and/or SQLite[^19] database together with information related to document -structure.  +structure.  <p>  This is one of the more interesting output forms, as all the  structural data of the documents are retained (though can be ignored by  the user of the database should they so choose). All site texts/documents -are (currently) streamed to four tables:  +are (currently) streamed to four tables:  <p>    * one containing semantic  (and other) headers, including, title, author,<br>     subject, (the Dublin Core...);<br> -  +  <p>    * another the substantive texts by individual<br>     along with structural information, each paragraph being identifiable  by its<br> @@ -2126,25 +2044,25 @@ by its<br>     substantive text of each paragraph quite naturally being searchable  (both in<br>     formatted and clean text versions for searching); and<br> -  +  <p>    * a third containing endnotes cross-referenced back to the paragraph  from<br>     which they are referenced (both in formatted and clean text versions  for<br>     searching).<br> -  +  <p>    * a fourth table with a one to one relation with the headers table  contains<br>     full text versions of output, eg. pdf, html, xml, and ascii.<br> -  -<p>  There is of course the possibility to add further structures.  + +<p>  There is of course the possibility to add further structures.  <p>  At this  level <b>SiSU</b> loads a relational database with documents chunked into objects,  their smallest logical structurally constituent parts, as text objects,  with their object citation number and all other structural information  needed to construct the document. Text is stored (at this text object level)  with and without elementary markup tagging, the stripped version being -so as to facilitate ease of searching.  +so as to facilitate ease of searching.  <p>  Being able to search a relational  database at an object level with the <b>SiSU</b> citation system is an effective  way of locating content generated by <b>SiSU</b>  object numbers, and all versions @@ -2154,203 +2072,202 @@ output formats, with live links to the precise locations in the database  or in html/xml documents; or, the structural information provided makes  it possible to search the full contents of the database and have headings  in which search content appears, or to search only headings etc. (as the -Dublin Core is incorporated it is easy to make use of that as well).  +Dublin Core is incorporated it is easy to make use of that as well).  <p> 22. -POSTGRESQL   -<p> 22.1 NAME  +POSTGRESQL +<p> 22.1 NAME  <p>  <b>SiSU</b> - Structured information, Serialized Units -- a document publishing system, postgresql dependency package  +- a document publishing system, postgresql dependency package  <p> 22.2 DESCRIPTION  <p>  Information related to using postgresql with sisu (and related to the  sisu_postgresql dependency package, which is a dummy package to install  dependencies needed for <b>SiSU</b> to populate a postgresql database, this being -part of <b>SiSU</b> - man sisu).  -<p> 22.3 SYNOPSIS  -<p>    sisu -D  [instruction]  [filename/wildcard +part of <b>SiSU</b> - man sisu). +<p> 22.3 SYNOPSIS +<p>    sisu -D [instruction] [filename/wildcard   if  required]<br> -  -<p>    sisu -D --pg --[instruction]  [filename/wildcard  if  required]<br> -  -<p> 22.4 COMMANDS  + +<p>    sisu -D --pg --[instruction] [filename/wildcard  if  required]<br> + +<p> 22.4 COMMANDS  <p>  Mappings to two databases are provided by default, postgresql  and sqlite, the same commands are used within sisu to construct and populate  databases however -d (lowercase) denotes sqlite and -D (uppercase) denotes -postgresql, alternatively --sqlite or --pgsql may be used  +postgresql, alternatively --sqlite or --pgsql may be used  <p>  <b>-D or --pgsql</b> may -be used interchangeably.  -<p> 22.4.1 CREATE AND DESTROY DATABASE  -<p>  +be used interchangeably. +<p> 22.4.1 CREATE AND DESTROY DATABASE +<p>  <dl> -<dt><b> --pgsql  --createall</b> +<dt><b>--pgsql --createall</b>  </dt> -<dd> initial  step,  creates  required  relations  (tables,  indexes)  in  existing - (postgresql)  database  (a  database  should  be  created manually  and  given - the  same  name  as  working  directory,  as requested)  (rb.dbi) the  same  name - as  working  directory,  as  +<dd>initial step, creates required relations (tables, indexes) in existing +(postgresql) database (a database should be created manually and given +the same name as working directory, as requested) (rb.dbi)  <p> </dd> -<dt><b> sisu  -D  --createdb</b> </dt> -<dd> creates  database  where  no  database - existed  before  as  +<dt><b>sisu -D --createdb</b> +</dt> +<dd> +<p>creates database where no database existed before  <p> </dd> -<dt><b> sisu  -D  --create</b> </dt> -<dd> creates  database  tables  where  no  database - tables  existed before  database  tables  where  no  database  tables  existed +<dt><b>sisu -D --create</b> </dt> +<dd>creates +<p>database tables where no database tables existed before  <p> </dd> -<dt><b> sisu  -D  --Dropall</b> </dt> -<dd> destroys  database  (including  all  its  content)!  kills  data -and  drops  tables,  indexes  and  database  associated  with  a given  directory - (and  directories  of  the  same  name).  a  +<dt><b>sisu -D --Dropall</b> +</dt> +<dd>destroys database (including all its content)! kills data and drops tables, +indexes and database associated with a given directory (and directories +of the same name).  <p> </dd> -<dt><b> sisu  -D  --recreate</b> </dt> -<dd> destroys  existing +<dt><b>sisu -D --recreate</b> </dt> +<dd>destroys existing database and builds -<p> database  and  builds  a  new  empty  database  structure  +<p>a new empty database structure  <p> </dd>  </dl> -22.4.2 IMPORT AND REMOVE - -<p>DOCUMENTS  -<p>  +22.4.2 IMPORT AND REMOVE DOCUMENTS +<p>  <dl> -<dt><b> sisu  -D  --import  -v   [filename/wildcard]</b> </dt> -<dd>populates database with -the contents of the file. Imports documents(s) specified to a postgresql -database (at an object level).  +<dt><b>sisu +-D --import -v [filename/wildcard]</b> </dt> +<dd>populates database with the contents of +the file. Imports documents(s) specified to a postgresql database (at an +object level).  <p> </dd> -<dt><b> sisu  -D  --update  -v   [filename/wildcard]</b> </dt> -<dd>updates +<dt><b>sisu -D --update -v [filename/wildcard]</b> </dt> +<dd>updates file contents -<p>file contents in database  +<p>in database  <p> </dd> -<dt><b> sisu  -D  --remove  -v   [filename/wildcard]</b> </dt> -<dd>removes -specified document from postgresql database.  +<dt><b>sisu -D --remove -v [filename/wildcard]</b> </dt> +<dd>removes specified document +from postgresql database.  <p> </dd>  </dl> -23. SQLITE   -<p> 23.1 NAME  -<p>  <b>SiSU</b> -- Structured information, Serialized Units - a document publishing system. - -<p> 23.2 DESCRIPTION  -<p>  Information related to using sqlite with sisu (and related -to the sisu_sqlite dependency package, which is a dummy package to install -dependencies needed for <b>SiSU</b> to populate an sqlite database, this being -part of <b>SiSU</b> - man sisu).  -<p> 23.3 SYNOPSIS  -<p>    sisu -d  [instruction]  [filename/wildcard - if  required]<br> -  -<p>    sisu -d --(sqlite|pg) --[instruction]  [filename/wildcard  if <br> +23. SQLITE +<p> 23.1 NAME +<p>  <b>SiSU</b> - Structured information, +Serialized Units - a document publishing system. +<p> 23.2 DESCRIPTION +<p>  Information +related to using sqlite with sisu (and related to the sisu_sqlite dependency +package, which is a dummy package to install dependencies needed for <b>SiSU</b> +to populate an sqlite database, this being part of <b>SiSU</b> - man sisu). +<p> 23.3 + +<p>SYNOPSIS +<p>    sisu -d [instruction] [filename/wildcard  if  required]<br> + +<p>    sisu -d --(sqlite|pg) --[instruction] [filename/wildcard  if <br>     required]<br> -  -<p> 23.4 COMMANDS  + +<p> 23.4 COMMANDS  <p>  Mappings to two databases are provided by default, postgresql  and sqlite, the same commands are used within sisu to construct and populate  databases however -d (lowercase) denotes sqlite and -D (uppercase) denotes -postgresql, alternatively --sqlite or --pgsql may be used  +postgresql, alternatively --sqlite or --pgsql may be used  <p>  <b>-d or --sqlite</b> may -be used interchangeably.  -<p> 23.4.1 CREATE AND DESTROY DATABASE  -<p>  +be used interchangeably. +<p> 23.4.1 CREATE AND DESTROY DATABASE +<p>  <dl> -<dt><b> --sqlite  --createall</b> +<dt><b>--sqlite --createall</b>  </dt> -<dd> initial  step,  creates  required  relations  (tables,  indexes)  in  existing - (sqlite)  database  (a  database  should  be  created  as requested)  (rb.dbi) the - same  name  as  working  directory,  as  +<dd>initial step, creates required relations (tables, indexes) in existing +(sqlite) database (a database should be created manually and given the +same name as working directory, as requested) (rb.dbi)  <p> </dd> -<dt><b> sisu  -d  --createdb</b> </dt> -<dd> creates  database  where - no  database  existed  before  as  +<dt><b>sisu -d --createdb</b> +</dt> +<dd> +<p>creates database where no database existed before  <p> </dd> -<dt><b> sisu  -d  --create</b> </dt> -<dd> creates  database  tables  where - no  database  tables  existed before  database  tables  where  no  database  tables - existed  +<dt><b>sisu -d --create</b> </dt> +<dd>creates + +<p>database tables where no database tables existed before  <p> </dd> -<dt><b> sisu  -d  --dropall</b> </dt> -<dd> destroys  database  (including  all  its  content)! - kills  data and  drops  tables,  indexes  and  database  associated  with  a given - directory  (and  directories  of  the  same  name).  a  +<dt><b>sisu -d --dropall</b> +</dt> +<dd>destroys database (including all its content)! kills data and drops tables, +indexes and database associated with a given directory (and directories +of the same name).  <p> </dd> -<dt><b> sisu  -d  --recreate</b> </dt> -<dd> destroys +<dt><b>sisu -d --recreate</b> </dt> +<dd>destroys existing database and builds -<p> existing  database  and  builds  a  new  empty  database  structure  +<p>a new empty database structure  <p> </dd>  </dl> -23.4.2 IMPORT - -<p>AND REMOVE DOCUMENTS  -<p>  +23.4.2 IMPORT AND REMOVE DOCUMENTS +<p>  <dl> -<dt><b> sisu  -d  --import  -v   [filename/wildcard]</b> </dt> -<dd>populates database -with the contents of the file. Imports documents(s) specified to an sqlite -database (at an object level).  +<dt><b>sisu +-d --import -v [filename/wildcard]</b> </dt> +<dd>populates database with the contents of +the file. Imports documents(s) specified to an sqlite database (at an object +level).  <p> </dd> -<dt><b> sisu  -d  --update  -v   [filename/wildcard]</b> </dt> -<dd>updates +<dt><b>sisu -d --update -v [filename/wildcard]</b> </dt> +<dd>updates file contents in database -<p>file contents in database   <p> </dd> -<dt><b> sisu  -d  --remove  -v   [filename/wildcard]</b> </dt> -<dd>removes -specified document from sqlite database.  +<dt><b>sisu -d --remove -v [filename/wildcard]</b> </dt> +<dd>removes specified document from sqlite +database.  <p> </dd>  </dl> -24. INTRODUCTION   -<p> 24.1 SEARCH - -DATABASE FRONTEND SAMPLE, UTILISING DATABASE AND SISU FEATURES, INCLUDING -OBJECT CITATION NUMBERING (BACKEND CURRENTLY POSTGRESQL)  -<p>  Sample search -frontend <<a href='http://search.sisudoc.org'>http://search.sisudoc.org</a> ->  [^20] A small database and sample query -front-end (search from) that makes use of the citation system, <i>object</i> citation -numbering to demonstrates functionality.[^21]  -<p>  <b>SiSU</b> can provide information -on which documents are matched and at what locations within each document -the matches are found. These results are relevant across all outputs using -object citation numbering, which includes html, XML, LaTeX, PDF and indeed -the SQL database. You can then refer to one of the other outputs or in the -SQL database expand the text within the matched objects (paragraphs) in -the documents matched.  -<p>  Note you may set results either for documents matched -and object number locations within each matched document meeting the search -criteria; or display the names of the documents matched along with the -objects (paragraphs) that meet the search criteria.[^22]  -<p>  +24. INTRODUCTION +<p> 24.1 SEARCH - DATABASE FRONTEND SAMPLE, UTILISING +DATABASE AND SISU FEATURES, INCLUDING OBJECT CITATION NUMBERING (BACKEND +CURRENTLY POSTGRESQL) +<p>  Sample search frontend <<a href='http://search.sisudoc.org'>http://search.sisudoc.org</a> +> +[^20] A small database and sample query front-end (search from) that makes +use of the citation system, <i>object</i> citation numbering to demonstrates functionality.[^21] + +<p>  <b>SiSU</b> can provide information on which documents are matched and at what +locations within each document the matches are found. These results are +relevant across all outputs using object citation numbering, which includes +html, XML, LaTeX, PDF and indeed the SQL database. You can then refer to +one of the other outputs or in the SQL database expand the text within +the matched objects (paragraphs) in the documents matched. +<p>  Note you may +set results either for documents matched and object number locations within +each matched document meeting the search criteria; or display the names +of the documents matched along with the objects (paragraphs) that meet +the search criteria.[^22] +<p>  <dl> -<dt><b> sisu  -F  --webserv-webrick</b> -</dt> -<dd> -<p> builds  a  cgi  web  search  frontend  for  the  database  created  -<p>  The following -is feedback on the setup on a machine provided by the help command:  -<p>   - sisu --help sql<br> -  -<p>  +<dt><b>sisu -F --webserv-webrick</b> </dt> +<dd>builds a cgi web search + +<p>frontend for the database created +<p>  The following is feedback on the setup +on a machine provided by the help command: +<p>    sisu --help sql<br> + +<p>  <p> <br>  <pre>  Postgresql      user:             ralph @@ -2361,289 +2278,292 @@ is feedback on the setup on a machine provided by the help command:      current db set:   /home/ralph/sisu_www/sisu/sisu_sqlite.db      dbi connect       DBI:SQLite:/home/ralph/sisu_www/sisu/sisu_sqlite.db  </pre> -<p>  Note on databases built  -<p>  By default,  [unless  otherwise  specified] databases +<p>  Note on databases built +<p>  By default, [unless  otherwise  specified] databases  are built on a directory basis, from collections of documents within that  directory. The name of the directory you choose to work from is used as  the database name, i.e. if you are working in a directory called /home/ralph/ebook -the database SiSU_ebook is used.  [otherwise  a  manual  mapping  for  the  collection - is  +the database SiSU_ebook is used. [otherwise  a  manual  mapping  for  the  collection + is  <p> </dd>  </dl> -24.2 SEARCH FORM  -<p>  +24.2 SEARCH FORM +<p>  <dl> -<dt><b> sisu  -F</b> </dt> -<dd> generates  a  sample  search  form,  which  must - be  copied  to  which  must  be  copied  to  +<dt><b>sisu -F</b> </dt> +<dd>generates a sample search form, which must + +<p>be copied to the web-server cgi directory  <p> </dd> -<dt><b> sisu  -F  --webserv-webrick</b> </dt> -<dd> generates  a - sample  search  form  for  use  with  the  webrick  which  must  be  copied  to  the - web-server  cgi  directory  which  must  be  copied  to  the  web-server  cgi  directory +<dt><b>sisu -F --webserv-webrick</b> </dt> +<dd>generates +a sample search form for use with the webrick server, which must be copied +<p>to the web-server cgi directory  <p> </dd> -<dt><b> sisu  -Fv</b> </dt> -<dd> as  above,  and  provides  some  information  on  setting  up  +<dt><b>sisu -Fv</b> </dt> +<dd>as above, and provides some information + +<p>on setting up hyperestraier  <p> </dd> -<dt><b> sisu  -W</b> -</dt> -<dd> -<p> starts  the  webrick  server  which  should  be  available  +<dt><b>sisu -W</b> </dt> +<dd>starts the webrick server which should + +<p>be available wherever sisu is properly installed  <p>  The generated search -<p>form must be copied manually to the webserver directory as instructed  +<p>form must be copied manually to the webserver directory as instructed  <p>  </dd>  </dl> -25. HYPERESTRAIER   -<p>  See the documentation for hyperestraier:  +25. HYPERESTRAIER +<p>  See the documentation for hyperestraier:  <p>    <<a href='http://hyperestraier.sourceforge.net/'>http://hyperestraier.sourceforge.net/</a>  ><br> -  +  <p>    /usr/share/doc/hyperestraier/index.html<br> -  +  <p>    man estcmd<br> -  -<p>  on sisu_hyperestraier:  + +<p>  on sisu_hyperestraier:  <p>    man sisu_hyperestraier<br> -  +  <p>    /usr/share/doc/sisu/sisu_markup/sisu_hyperestraier/index.html<br> -  +  <p>  NOTE: the examples that follow assume that sisu output is placed in -<p>the directory /home/ralph/sisu_www  +<p>the directory /home/ralph/sisu_www  <p>  (A) to generate the index within the -webserver directory to be indexed:  -<p>    estcmd gather -sd  [index  name]  [directory +webserver directory to be indexed: +<p>    estcmd gather -sd [index  name] [directory   path  to  index]<br> -  +  <p>  the following are examples that will need to be tailored according to -your needs:  +your needs:  <p>    cd /home/ralph/sisu_www<br> -  +  <p>    estcmd gather -sd casket /home/ralph/sisu_www<br> -  +  <p>  you may use the ’find’ command together with ’egrep’ to limit indexing to  particular document collection directories within the web server directory:  <p>    find /home/ralph/sisu_www -type f | egrep<br>     ’/home/ralph/sisu_www/sisu/.+?.html$’ |estcmd gather -sd casket -<br> -  +  <p>  Check which directories in the webserver/output directory (~/sisu_www  or elsewhere depending on configuration) you wish to include in the search -index.  +index.  <p>  As sisu duplicates output in multiple file formats, it it is probably  preferable to limit the estraier index to html output, and as it may also  be desirable to exclude files ’plain.txt’, ’toc.html’ and ’concordance.html’, as -these duplicate information held in other html output e.g.  +these duplicate information held in other html output e.g.  <p>    find /home/ralph/sisu_www  -type f | egrep<br>     ’/sisu_www/(sisu|bookmarks)/.+?.html$’ | egrep -v<br>     ’(doc|concordance).html$’ |estcmd gather -sd casket -<br> -  +  <p>  from your current document preparation/markup directory, you would construct -a rune along the following lines:  +a rune along the following lines:  <p>    find /home/ralph/sisu_www -type f  | egrep ’/home/ralph/sisu_www/([specify <br>     first  directory  for  inclusion]|[specify  second  directory  for <br>     inclusion]|[another  directory  for  inclusion?  ...])/.+?.html$’ |<br>     egrep -v ’(doc|concordance).html$’ |estcmd gather -sd<br>     /home/ralph/sisu_www/casket -<br> -  -<p>  (B) to set up the search form  + +<p>  (B) to set up the search form  <p>  (i) copy estseek.cgi to your cgi directory -and set file permissions to 755:  +and set file permissions to 755:  <p>    sudo cp -vi /usr/lib/estraier/estseek.cgi  /usr/lib/cgi-bin<br> -  +  <p>    sudo chmod -v 755 /usr/lib/cgi-bin/estseek.cgi<br> -  +  <p>    sudo cp -v /usr/share/hyperestraier/estseek.* /usr/lib/cgi-bin<br> -  -<p>     [see  estraier  documentation  for  paths]<br> -  + +<p>    [see  estraier  documentation  for  paths]<br> +  <p>  (ii) edit estseek.conf, with attention to the lines starting ’indexname:’ -and ’replace:’:  +and ’replace:’:  <p>    indexname: /home/ralph/sisu_www/casket<br> -  +  <p>    replace: ^file:///home/ralph/sisu_www{{!}}<a href='http://localhost'>http://localhost</a>  <br> -  +  <p>    replace: /index.html?${{!}}/<br> -  -<p>  (C) to test using webrick, start webrick:  + +<p>  (C) to test using webrick, start webrick:  <p>    sisu -W<br> -  +  <p>  and try open the url: <<a href='http://localhost:8081/cgi-bin/estseek.cgi'>http://localhost:8081/cgi-bin/estseek.cgi</a> ->  +>  <p> 26. SISU_WEBRICK -  -<p> 26.1 NAME  + +<p> 26.1 NAME  <p>  <b>SiSU</b> - Structured information, Serialized Units - a document -<p>publishing system  -<p> 26.2 SYNOPSIS  -<p>  sisu_webrick  [port]  -<p>  or  -<p>  sisu -W  [port] +<p>publishing system +<p> 26.2 SYNOPSIS +<p>  sisu_webrick [port] +<p>  or +<p>  sisu -W [port] -<p> 26.3 DESCRIPTION  +<p> 26.3 DESCRIPTION  <p>  sisu_webrick is part of <b>SiSU</b> (man sisu) sisu_webrick  starts <b>Ruby</b> ’s Webrick web-server and points it to the directories to which  <b>SiSU</b> output is written, providing a list of these directories (assuming -<b>SiSU</b> is in use and they exist).  +<b>SiSU</b> is in use and they exist).  <p>  The default port for sisu_webrick is set  to 8081, this may be modified in the yaml file: ~/.sisu/sisurc.yml a sample  of which is provided as /etc/sisu/sisurc.yml (or in the equivalent directory -on your system).  -<p> 26.4 SUMMARY OF MAN PAGE  +on your system). +<p> 26.4 SUMMARY OF MAN PAGE  <p>  sisu_webrick, may be started -on it’s own with the command: sisu_webrick or using the sisu command with -the -W flag: sisu -W  [port]  -<p>  where no port is given and settings are unchanged +on it’s own with the command: sisu_webrick [port] or using the sisu command +with the -W flag: sisu -W [port] +<p>  where no port is given and settings are -<p>the default port is 8081  -<p> 26.5 DOCUMENT PROCESSING COMMAND FLAGS  -<p>  sisu --W  [port] starts <b>Ruby</b> Webrick web-server, serving <b>SiSU</b> output directories, +<p>unchanged the default port is 8081 +<p> 26.5 DOCUMENT PROCESSING COMMAND FLAGS + +<p>  sisu -W [port] starts <b>Ruby</b> Webrick web-server, serving <b>SiSU</b> output directories,  on the port provided, or if no port is provided and the defaults have not -<p>been changed in ~/.sisu/sisurc.yaml then on port 8081  +<p>been changed in ~/.sisu/sisurc.yaml then on port 8081  <p> 26.6 FURTHER INFORMATION  <p>  For more information on <b>SiSU</b> see: <<a href='http://www.jus.uio.no/sisu'>http://www.jus.uio.no/sisu</a> ->  +>  <p>  or man sisu -<p> 26.7 AUTHOR  -<p>  Ralph Amissah ralph@amissah.com or ralph.amissah@gmail.com  +<p> 26.7 AUTHOR +<p>  Ralph Amissah ralph@amissah.com or ralph.amissah@gmail.com  <p> -<p>26.8 SEE ALSO  +<p>26.8 SEE ALSO  <p>    <a href='http:~/bin/man2html?sisu:1'>sisu(1)</a>  <br> -  +  <p>    <a href='http:~/bin/man2html?sisu_vim:7'>sisu_vim(7)</a>  <br> -  +  <p>    <a href='http:~/bin/man2html?sisu:8'>sisu(8)</a>  <br> -  -<p> 27. REMOTE SOURCE DOCUMENTS   + +<p> 27. REMOTE SOURCE DOCUMENTS  <p>  <b>SiSU</b> processing instructions can be run  against remote source documents by providing the url of the documents against  which the processing instructions are to be carried out. The remote <b>SiSU</b>  documents can either be sisu marked up files in plaintext .sst or .ssm or; -zipped sisu files, sisupod.zip or filename.ssp  +zipped sisu files, sisupod.zip or filename.ssp  <p>  <b>.sst / .ssm - sisu text files</b>  <p>  <b>SiSU</b> can be run against source text files on a remote machine, provide  the processing instruction and the url. The source file and any associated -parts (such as images) will be downloaded and generated locally.  -<p>  +parts (such as images) will be downloaded and generated locally. +<p>  <p> <br>  <pre>  sisu -3 http://[provide  url  to  valid  .sst  or  .ssm  file]  </pre>  <p>  Any of the source documents in the sisu examples page can be used in  this way, see <<a href='http://www.jus.uio.no/sisu/SiSU/examples.html'>http://www.jus.uio.no/sisu/SiSU/examples.html</a>  > and use the url -for the desired document.  +for the desired document.  <p>  NOTE: to set up a remote machine to serve <b>SiSU</b>  documents in this way, images should be in the directory relative to the -<p>document source ../_sisu/image  -<p>  <b>sisupod - zipped sisu files</b>  +<p>document source ../_sisu/image +<p>  <b>sisupod - zipped sisu files</b>  <p>  A sisupod is  the zipped content of a sisu marked up text or texts and any other associated -parts to the document such as images.  +parts to the document such as images.  <p>  <b>SiSU</b> can be run against a sisupod  on a (local or) remote machine, provide the processing instruction and  the url, the sisupod will be downloaded and the documents it contains generated -locally.  -<p>  +locally. +<p>  <p> <br>  <pre>  sisu -3 http://[provide  url  to  valid  sisupod.zip  or  .ssp  file]  </pre>  <p>  Any of the source documents in the sisu examples page can be used in  this way, see <<a href='http://www.jus.uio.no/sisu/SiSU/examples.html'>http://www.jus.uio.no/sisu/SiSU/examples.html</a>  > and use the url -for the desired document.  -<p> REMOTE DOCUMENT OUTPUT   -<p> 28. REMOTE OUTPUT   -<p>  +for the desired document. +<p> REMOTE DOCUMENT OUTPUT +<p> 28. REMOTE OUTPUT +<p>  Once properly configured <b>SiSU</b> output can be automatically posted once generated -to a designated remote machine using either rsync, or scp.  +to a designated remote machine using either rsync, or scp.  <p>  In order to  do this some ssh authentication agent and keychain or similar tool will  need to be configured. Once that is done the placement on a remote host  can be done seamlessly with the -r (for scp) or -R (for rsync) flag, which -may be used in conjunction with other processing flags, e.g.  -<p>  +may be used in conjunction with other processing flags, e.g. +<p>  <p> <br>  <pre>  sisu -3R sisu_remote.sst  </pre> -<p> 28.1 COMMANDS  -<p>  +<p> 28.1 COMMANDS +<p>  <dl> -<dt><b> -R   [filename/wildcard]</b> </dt> +<dt><b>-R [filename/wildcard]</b> </dt>  <dd>copies sisu output files to remote  host using rsync. This requires that sisurc.yml has been provided with information  on hostname and username, and that you have your different if -R is used  with other flags from if used alone. Alone the rsync --delete parameter is  sent, useful for cleaning the remote directory (when -R is used together -with other flags, it is not). Also see -r  +with other flags, it is not). Also see -r  <p> </dd> -<dt><b> -r   [filename/wildcard]</b> </dt> +<dt><b>-r [filename/wildcard]</b> </dt>  <dd>copies sisu  output files to remote host using scp. This requires that sisurc.yml has  been provided with information on hostname and username, and that you have -<p>your  +<p>your  <p> </dd>  </dl> -28.2 CONFIGURATION  +28.2 CONFIGURATION  <p>  [expand  on  the  setting  up  of  an  ssh-agent  /  keychain] -<p> 29. REMOTE SERVERS   +<p> 29. REMOTE SERVERS  <p>  As <b>SiSU</b> is generally operated using the command line,  and works within a Unix type environment, <b>SiSU</b> the program and all documents  can just as easily be on a remote server, to which you are logged on using  a terminal, and commands and operations would be pretty much the same as -they would be on your local machine.  +they would be on your local machine.  <p> 30. QUICKSTART - GETTING STARTED HOWTO -  -<p> 30.1 INSTALLATION  + +<p> 30.1 INSTALLATION  <p>  Installation is currently most straightforward and  tested on the <b>Debian</b> platform, as there are packages for the installation -of sisu and all requirements for what it does.  +of sisu and all requirements for what it does.  <p> 30.1.1 DEBIAN INSTALLATION  <p>  <b>SiSU</b> is available directly from the <b>Debian</b> Sid and testing archives (and  possibly Ubuntu), assuming your /etc/apt/sources.list is set accordingly: -<p>  +<p>  <p> <br>  <pre>    aptitude update      aptitude install sisu-complete  </pre>  <p>  The following /etc/apt/sources.list setting permits the download of additional -markup samples:  -<p>  +markup samples: +<p>  <p> <br>  <pre>  #/etc/apt/sources.list      deb http://ftp.fi.debian.org/debian/ unstable main non-free contrib      deb-src http://ftp.fi.debian.org/debian/ unstable main non-free contrib    d  </pre> -<p>  The aptitude commands become:  -<p>  +<p>  The aptitude commands become: +<p>  <p> <br>  <pre>    aptitude update      aptitude install sisu-complete sisu-markup-samples @@ -2652,308 +2572,308 @@ markup samples:  <p>they will be available by adding the following to your /etc/apt/sources.list -<p>  +<p>  <p> <br>  <pre>  #/etc/apt/sources.list      deb http://www.jus.uio.no/sisu/archive unstable main non-free      deb-src http://www.jus.uio.no/sisu/archive unstable main non-free  </pre> -<p>  repeat the aptitude commands  -<p>  +<p>  repeat the aptitude commands +<p>  <p> <br>  <pre>    aptitude update      aptitude install sisu-complete sisu-markup-samples  </pre>  <p>  Note however that it is not necessary to install sisu-complete if not  all components of sisu are to be used. Installing just the package sisu -will provide basic functionality.  -<p> 30.1.2 RPM INSTALLATION  +will provide basic functionality. +<p> 30.1.2 RPM INSTALLATION  <p>  RPMs are provided  though untested, they are prepared by running alien against the source -package, and against the debs.  -<p>  They may be downloaded from:  +package, and against the debs. +<p>  They may be downloaded from:  <p>    <<a href='http://www.jus.uio.no/sisu/SiSU/download.html#rpm'>http://www.jus.uio.no/sisu/SiSU/download.html#rpm</a>  ><br> -  -<p>  as root type:  -<p>    rpm -i  [rpm  package  name]<br> -  -<p> 30.1.3 INSTALLATION FROM SOURCE  + +<p>  as root type: +<p>    rpm -i [rpm  package  name]<br> + +<p> 30.1.3 INSTALLATION FROM SOURCE  <p>  To install <b>SiSU</b> from source check information -at:  +at:  <p>    <<a href='http://www.jus.uio.no/sisu/SiSU/download.html#current'>http://www.jus.uio.no/sisu/SiSU/download.html#current</a>  ><br> -  -<p>  * download the source package  -<p>  * Unpack the source  + +<p>  * download the source package +<p>  * Unpack the source  <p>  Two alternative  modes of installation from source are provided, setup.rb (by Minero Aoki)  and a rant(by Stefan Lang) built install file, in either case: the first -steps are the same, download and unpack the source file:  +steps are the same, download and unpack the source file:  <p>  For basic use  <b>SiSU</b> is only dependent on the programming language in which it is written  <b>Ruby</b> , and <b>SiSU</b> will be able to generate html, various XMLs, including  ODF (and will also produce LaTeX). Dependencies required for further actions,  though it relies on the installation of additional dependencies which the  source tarball does not take care of, for things like using a database -(postgresql or sqlite)[^23] or converting LaTeX to pdf.  -<p>  <b>setup.rb</b>  +(postgresql or sqlite)[^23] or converting LaTeX to pdf. +<p>  <b>setup.rb</b>  <p>  This  is a standard ruby installer, using setup.rb is a three step process. In -the root directory of the unpacked <b>SiSU</b> as root type:  -<p>  +the root directory of the unpacked <b>SiSU</b> as root type: +<p>  <p> <br>  <pre>      ruby setup.rb config        ruby setup.rb setup        #[and  as  root:]        ruby setup.rb install  </pre> -<p>  further information on setup.rb is available from:  +<p>  further information on setup.rb is available from:  <p>    <<a href='http://i.loveruby.net/en/projects/setup/'>http://i.loveruby.net/en/projects/setup/</a>  ><br> -  +  <p>    <<a href='http://i.loveruby.net/en/projects/setup/doc/usage.html'>http://i.loveruby.net/en/projects/setup/doc/usage.html</a>  ><br> -  -<p>  <b></b>  -<p>  The root directory of the unpacked <b>SiSU</b> as root type:  + +<p>  <b></b> +<p>  The root directory of the unpacked <b>SiSU</b> as root type:  <p>    ruby install  base<br> -  -<p>  or for a more complete installation:  + +<p>  or for a more complete installation:  <p>    ruby install<br> -  -<p>  or  + +<p>  or  <p>    ruby install base<br> -  +  <p>  This makes use of Rant (by Stefan Lang) and the provided Rantfile. It  has been configured to do post installation setup setup configuration and  generation of first test file. Note however, that additional external package -dependencies, such as tetex-extra are not taken care of for you.  +dependencies, such as tetex-extra are not taken care of for you.  <p>  Further -<p>information on  +<p>information on  <p>    <<a href='http://make.rubyforge.org/'>http://make.rubyforge.org/</a>  ><br> -  +  <p>    <<a href='http://rubyforge.org/frs/?group_id=615'>http://rubyforge.org/frs/?group_id=615</a>  ><br> -  -<p>  For a list of alternative actions you may type:  + +<p>  For a list of alternative actions you may type:  <p>    ruby install help<br> -  +  <p>    ruby install -T<br> -  -<p> 30.2 TESTING SISU, GENERATING OUTPUT  + +<p> 30.2 TESTING SISU, GENERATING OUTPUT  <p>  To check which version of sisu -is installed:  -<p>  sisu -v  +is installed: +<p>  sisu -v  <p>  Depending on your mode of installation one or -a number of markup sample files may be found either in the directory:  +a number of markup sample files may be found either in the directory:  <p> -   -<p>  or  -<p>    -<p>  change directory to the appropriate one:  + +<p>  or +<p> +<p>  change directory to the appropriate one:  <p>  cd /usr/share/doc/sisu/sisu_markup_samples/dfsg -<p> 30.2.1 BASIC TEXT, PLAINTEXT, HTML, XML, ODF  +<p> 30.2.1 BASIC TEXT, PLAINTEXT, HTML, XML, ODF  <p>  Having moved to the directory  that contains the markup samples (see instructions above if necessary), -<p>choose a file and run sisu against it  +<p>choose a file and run sisu against it  <p>  sisu -NhwoabxXyv free_as_in_freedom.rms_and_free_software.sam_williams.sst  <p>  this will generate html including a concordance file, opendocument text  format, plaintext, XHTML and various forms of XML, and OpenDocument text -<p> 30.2.2 LATEX / PDF  +<p> 30.2.2 LATEX / PDF  <p>  Assuming a LaTeX engine such as tetex or texlive is  installed with the required modules (done automatically on selection of -sisu-pdf in <b>Debian</b> )  +sisu-pdf in <b>Debian</b> )  <p>  Having moved to the directory that contains the markup  samples (see instructions above if necessary), choose a file and run sisu -<p>against it  +<p>against it  <p>  sisu -pv free_as_in_freedom.rms_and_free_software.sam_williams.sst -<p>  sisu -3 free_as_in_freedom.rms_and_free_software.sam_williams.sst  +<p>  sisu -3 free_as_in_freedom.rms_and_free_software.sam_williams.sst  <p>  should  generate most available output formats: html including a concordance file,  opendocument text format, plaintext, XHTML and various forms of XML, and -<p>OpenDocument text and pdf  +<p>OpenDocument text and pdf  <p> 30.2.3 RELATIONAL DATABASE - POSTGRESQL, SQLITE  <p>  Relational databases need some setting up - you must have permission to -create the database and write to it when you run sisu.  +create the database and write to it when you run sisu.  <p>  Assuming you have -<p>the database installed and the requisite permissions  +<p>the database installed and the requisite permissions  <p>  sisu --sqlite --recreate  <p>  sisu --sqlite -v --import free_as_in_freedom.rms_and_free_software.sam_williams.sst -<p>  sisu --pgsql --recreate  +<p>  sisu --pgsql --recreate  <p>  sisu --pgsql -v --import free_as_in_freedom.rms_and_free_software.sam_williams.sst -<p> 30.3 GETTING HELP  -<p> 30.3.1 THE MAN PAGES  -<p>  Type:  +<p> 30.3 GETTING HELP +<p> 30.3.1 THE MAN PAGES +<p>  Type:  <p>    man sisu<br> -  +  <p>  The man pages are also available online, though not always kept as up -to date as within the package itself:  +to date as within the package itself:  <p>  * sisu.1 <<a href='http://www.jus.uio.no/sisu/man/sisu.1'>http://www.jus.uio.no/sisu/man/sisu.1</a>  > - [^24]  +[^24]  <p>  * sisu.8 <<a href='http://www.jus.uio.no/sisu/man/sisu.8'>http://www.jus.uio.no/sisu/man/sisu.8</a> ->  [^25]  +> [^25]  <p>  * man directory  <<a href='http://www.jus.uio.no/sisu/man'>http://www.jus.uio.no/sisu/man</a> ->  [^26]  -<p> 30.3.2 BUILT IN HELP  -<p>  sisu --help  +> [^26] +<p> 30.3.2 BUILT IN HELP +<p>  sisu --help  <p>  sisu  <p>-  <p>- -<p>help --env  -<p>  sisu --help --commands  -<p>  sisu --help --markup  -<p> 30.3.3 THE HOME PAGE  -<p>  +<p>help --env +<p>  sisu --help --commands +<p>  sisu --help --markup +<p> 30.3.3 THE HOME PAGE +<p>  <<a href='http://www.jus.uio.no/sisu'>http://www.jus.uio.no/sisu</a> ->  +>  <p>  <<a href='http://www.jus.uio.no/sisu/SiSU'>http://www.jus.uio.no/sisu/SiSU</a> ->  +>  <p> 30.4 MARKUP SAMPLES -<p>  A number of markup samples (along with output) are available off:  +<p>  A number of markup samples (along with output) are available off:  <p>  <<a href='http://www.jus.uio.no/sisu/SiSU/examples.html'>http://www.jus.uio.no/sisu/SiSU/examples.html</a>  > -<p>  Additional markup samples are packaged separately in the file:  -<p>  <b>*</b>  -<p>  +<p>  Additional markup samples are packaged separately in the file: +<p>  <b>*</b> +<p>  On <b>Debian</b> they are available in non-free[^27] to include them it is necessary  to include non-free in your /etc/apt/source.list or obtain them from the -sisu home site.  -<p> 31. EDITOR FILES, SYNTAX HIGHLIGHTING   +sisu home site. +<p> 31. EDITOR FILES, SYNTAX HIGHLIGHTING  <p>  The directory:  <p>    ./data/sisu/conf/editor-syntax-etc/<br> -  +  <p>    /usr/share/sisu/conf/editor-syntax-etc<br> -  -<p>  contains rudimentary sisu syntax highlighting files for:  + +<p>  contains rudimentary sisu syntax highlighting files for:  <p>  * (g)vim  <<a href='http://www.vim.org'>http://www.vim.org</a> ->  +>  <p>    package: sisu-vim<br> -  -<p>  status: largely done  + +<p>  status: largely done  <p>    there is a vim syntax highlighting and folds  component<br> -  +  <p>  * gedit <<a href='http://www.gnome.org/projects/gedit'>http://www.gnome.org/projects/gedit</a> ->  +>  <p>  * gobby <<a href='http://gobby.0x539.de/'>http://gobby.0x539.de/</a>  >  <p>    file: sisu.lang<br> -  -<p>  place in:  + +<p>  place in:  <p>    /usr/share/gtksourceview-1.0/language-specs<br> -  -<p>  or  + +<p>  or  <p>    ~/.gnome2/gtksourceview-1.0/language-specs<br> -  +  <p>    status: very basic syntax highlighting<br> -  +  <p>    comments: this editor features display line wrap and is used by Goby!<br> -  +  <p>  * nano <<a href='http://www.nano-editor.org'>http://www.nano-editor.org</a> ->  +>  <p>    file: nanorc<br> -  -<p>  save as:  + +<p>  save as:  <p>    ~/.nanorc<br> -  +  <p>    status: basic syntax highlighting<br> -  +  <p>    comments: assumes dark background; no display line-wrap; does line  breaks<br> -  +  <p>  * diakonos (an editor written in ruby) <<a href='http://purepistos.net/diakonos'>http://purepistos.net/diakonos</a>  > -<p>  file: diakonos.conf  -<p>  save as:  +<p>  file: diakonos.conf +<p>  save as:  <p>    ~/.diakonos/diakonos.conf<br> -  -<p>  includes:  + +<p>  includes:  <p>    status: basic syntax highlighting<br> -  -<p>  comments: assumes dark background; no display line-wrap  + +<p>  comments: assumes dark background; no display line-wrap  <p>  * kate & kwrite  <<a href='http://kate.kde.org'>http://kate.kde.org</a> ->  +>  <p>    file: sisu.xml<br> -  +  <p>    place in:<br> -  +  <p>      /usr/share/apps/katepart/syntax<br> -  +  <p>    or<br> -  +  <p>      ~/.kde/share/apps/katepart/syntax<br> -  -<p>     [settings::configure  kate::{highlighting,filetypes}]<br> -  -<p>     [tools::highlighting::{markup,scripts}::<br> - <b> SiSU</b> ]  + +<p>    [settings::configure  kate::{highlighting,filetypes}]<br> + +<p>    [tools::highlighting::{markup,scripts}::  .B  SiSU  ]<br> +  <p>  * nedit <<a href='http://www.nedit.org'>http://www.nedit.org</a> ->  +>  <p>    file: sisu_nedit.pats<br> -  +  <p>    nedit -import sisu_nedit.pats<br> -  -<p>    status: a very clumsy first attempt  [not  really  done]<br> -  + +<p>    status: a very clumsy first attempt [not  really  done]<br> +  <p>    comments: this editor features display line wrap<br> -  +  <p>  * emacs <<a href='http://www.gnu.org/software/emacs/emacs.html'>http://www.gnu.org/software/emacs/emacs.html</a> ->  +>  <p>    files: sisu-mode.el<br> -  +  <p>    to file ~/.emacs add the following 2 lines:<br> -  +  <p>      (add-to-list ’load-path<br> -  +  <p>      (require ’sisu-mode.el)<br> -  -<p>     [not  done  /  not  yet  included]<br> -  + +<p>    [not  done  /  not  yet  included]<br> +  <p>  * vim & gvim <<a href='http://www.vim.org'>http://www.vim.org</a> ->  +>  <p>    files:<br> -  +  <p>    package is the most comprehensive sisu syntax highlighting and editor<br>     environment provided to date (is for vim/ gvim, and is separate from  the<br>     contents of this directory)<br> -  +  <p>    status: this includes: syntax highlighting; vim folds; some error  checking<br> -  +  <p>    comments: this editor features display line wrap<br> -  -<p>  NOTE:  -<p>  [ <b> SiSU</b>  parses  files  with  long  lines  or  line  breaks,  but,  display - linewrap  (without  line-breaks)  is  a  convenient  editor  feature  to  have  for - sisu  markup]  -<p> 32. HOW DOES SISU WORK?   + +<p>  NOTE: +<p>  [  .B  SiSU  parses  files  with  long  lines  or  line  breaks, but,  display + linewrap  (without  line-breaks)  is  a  convenient editor  feature  to  have  for + sisu  markup] +<p> 32. HOW DOES SISU WORK?  <p>  <b>SiSU</b> markup is fairly minimalistic,  it consists of: a (largely optional) document header, made up of information  about the document (such as when it was published, who authored it, and @@ -2971,15 +2891,15 @@ considerable flexibility in representing documents different ways and for  different purposes (e.g. search, document layout, publishing, content certification,  concordance etc.), and makes it possible to take advantage of some of the  strengths of established ways of representing documents, (or indeed to -create new ones).  -<p> 33. SUMMARY OF FEATURES   +create new ones). +<p> 33. SUMMARY OF FEATURES  <p>  * sparse/minimal markup (clean  utf-8 source texts). Documents are prepared in a single UTF-8 file using a  minimalistic mnemonic syntax. Typical literature, documents like headers -are optional.  +are optional.  <p>  * markup is easily readable/parsable by the human eye, (basic -markup is simpler and more sparse than the most basic HTML),  [this  may - also  be simpler converted  to  XML  representations  of  the  same  input/source +markup is simpler and more sparse than the most basic HTML), [this  may + also  be  converted  to  XML  representations  of  the  same  input/source  document].  <p>  * markup defines document structure (this may be done once in a header  pattern-match description, or for heading levels individually); basic text @@ -2989,38 +2909,37 @@ beyond the Dublin core and easily further extended as required); the headers  may also contain processing instructions. <b>SiSU</b> markup is primarily an abstraction  of document structure and document metadata to permit taking advantage  of the basic strengths of existing alternative practical standard ways -of representing documents  [be  that browser  viewing,  paper  publication, - sql  search  etc.] (html, xml, odf, latex, pdf, sql)  -<p>  * for output produces -reasonably elegant output of established industry and institutionally accepted -open standard formats.[3] takes advantage of the different strengths of -various standard formats for representing documents, amongst the output -formats currently supported are:  -<p>    * html - both as a single scrollable -text and a segmented document<br> -  +of representing documents [be  that  paper  publication,  sql  search  etc.] (html, +xml, odf, latex, pdf, sql) +<p>  * for output produces reasonably elegant output +of established industry and institutionally accepted open standard formats.[3] +takes advantage of the different strengths of various standard formats +for representing documents, amongst the output formats currently supported +are: +<p>    * html - both as a single scrollable text and a segmented document<br> +  <p>    * xhtml<br> -  +  <p>    * XML - both in sax and dom style xml structures for further development  as<br>     required<br> -  +  <p>    * ODF - open document format, the iso standard for document storage<br> -  +  <p>    * LaTeX - used to generate pdf<br> -  +  <p>    * pdf (via LaTeX)<br> -  +  <p>    * sql - population of an sql database, (at the same object level that  is<br>     used to cite text within a document)<br> -  +  <p>  Also produces: concordance files; document content certificates (md5  or sha256 digests of headings, paragraphs, images etc.) and html manifests  (and sitemaps of content). (b) takes advantage of the strengths implicit  in these very different output types, (e.g. PDFs produced using typesetting  of LaTeX, databases populated with documents at an individual object/paragraph -level, making possible granular search (and related possibilities))  +level, making possible granular search (and related possibilities))  <p>  *  ensuring content can be cited in a meaningful way regardless of selected  output format. Online publishing (and publishing in multiple document formats) @@ -3031,23 +2950,23 @@ the text within a document, (which can be utilized for citation and by  search engines). The outputs share a common numbering system that is meaningful  (to man and machine) across all digital outputs whether paper, screen,  or database oriented, (pdf, HTML, xml, sqlite, postgresql), this numbering -system can be used to reference content.  +system can be used to reference content.  <p>  * Granular search within documents.  SQL databases are populated at an object level (roughly headings, paragraphs,  verse, tables) and become searchable with that degree of granularity, the  output information provides the object/paragraph numbers which are relevant  across all generated outputs; it is also possible to look at just the matching -paragraphs of the documents in the database;  [output  indexing  also  work - well  with  search  indexing  tools  like  hyperestraier].  +paragraphs of the documents in the database; [output  indexing  also  work + well  with  search  indexing tools  like  hyperestraier].  <p>  * long term maintainability  of document collections in a world of changing formats, having a very sparsely  marked-up source document base. there is a considerable degree of future-proofing,  output representations are upgradeable (open document text) module in 2006  and in future html5 output sometime in future, without modification of -<p>existing prepared texts  +<p>existing prepared texts  <p>  * SQL search aside, documents are generated as -required and static once generated.  +required and static once generated.  <p>  * documents produced are static files,  and may be batch processed, this needs to be done only once but may be  repeated for various reasons as desired (updated content, addition of new @@ -3055,7 +2974,7 @@ output formats, updated technology document presentations/representations)  <p>  * document source (plaintext utf-8) if shared on the net may be used as -<p>input and processed locally to produce the different document outputs  +<p>input and processed locally to produce the different document outputs  <p>   * document source may be bundled together (automatically) with associated  documents (multiple language versions or master document with inclusions) @@ -3068,232 +2987,232 @@ and images and sent as a zip file called a sisupod, if shared on the net  <p>  * for basic document generation, the only software dependency is <b>Ruby</b>  , and a few standard Unix tools (this covers plaintext, HTML, XML, ODF,  LaTeX). To use a database you of course need that, and to convert the LaTeX -generated to pdf, a latex processor like tetex or texlive.  +generated to pdf, a latex processor like tetex or texlive.  <p>  * as a developers -<p>tool it is flexible and extensible  +<p>tool it is flexible and extensible  <p>  Syntax highlighting for <b>SiSU</b> markup -is available for a number of text editors.  +is available for a number of text editors.  <p>  <b>SiSU</b> is less about document  layout than about finding a way with little markup to be able to construct  an abstract representation of a document that makes it possible to produce  multiple representations of it which may be rather different from each  other and used for different purposes, whether layout and publishing, or -<p>search of content  +<p>search of content  <p>  i.e. to be able to take advantage from this minimal preparation  starting point of some of the strengths of rather different established  ways of representing documents for different purposes, whether for search  (relational database, or indexed flat files generated for that purpose  whether of complete documents, or say of files made up of objects), online -viewing (e.g. html, xml, pdf), or paper publication (e.g. pdf)...  +viewing (e.g. html, xml, pdf), or paper publication (e.g. pdf)...  <p>  the solution  arrived at is by extracting structural information about the document (about  headings within the document) and by tracking objects (which are serialized  and also given hash values) in the manner described. It makes possible representations  that are quite different from those offered at present. For example objects  could be saved individually and identified by their hashes, with an index -of how the objects relate to each other to form a document.  +of how the objects relate to each other to form a document.  <p> 34. HELP SOURCES -  +  <p>  For a summary of alternative ways to get help on <b>SiSU</b> try one of the -following:  -<p>  <b>man page</b>  +following: +<p>  <b>man page</b>  <p>    man sisu_help<br> -  -<p>  <b>man2html</b>  + +<p>  <b>man2html</b>  <p>    <<a href='http://www.jus.uio.no/sisu/man/sisu_help.1.html'>http://www.jus.uio.no/sisu/man/sisu_help.1.html</a>  ><br> -  -<p>  <b>sisu generated output - links to html</b>  + +<p>  <b>sisu generated output - links to html</b>  <p>    <<a href='http://sisudoc.org/sisu/sisu_help/index.html'>http://sisudoc.org/sisu/sisu_help/index.html</a>  ><br> -  -<p>  <b>help sources lists</b>  + +<p>  <b>help sources lists</b>  <p>  Alternative sources for this help sources page -listed here:  +listed here:  <p>    man sisu_help_sources<br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_help_sources/index.html'>http://sisudoc.org/sisu/sisu_help_sources/index.html</a>  ><br> -  -<p> 34.1 MAN PAGES  -<p> 34.1.1 MAN  + +<p> 34.1 MAN PAGES +<p> 34.1.1 MAN  <p>    man sisu<br> -  +  <p>    man 7 sisu_complete<br> -  +  <p>    man 7 sisu_pdf<br> -  +  <p>    man 7 sisu_postgresql<br> -  +  <p>    man 7 sisu_sqlite<br> -  +  <p>    man sisu_termsheet<br> -  +  <p>    man sisu_webrick<br> -  -<p> 34.2 SISU GENERATED OUTPUT - LINKS TO HTML  + +<p> 34.2 SISU GENERATED OUTPUT - LINKS TO HTML  <p>  Note <b>SiSU</b> documentation is  prepared in <b>SiSU</b> and output is available in multiple formats including  amongst others html, pdf, and odf which may be also be accessed via the -html pages[^28]  -<p> 34.2.1 WWW.SISUDOC.ORG  +html pages[^28] +<p> 34.2.1 WWW.SISUDOC.ORG  <p>  <<a href='http://sisudoc.org/sisu/sisu_manual/index.html'>http://sisudoc.org/sisu/sisu_manual/index.html</a>  >  <p>    <<a href='http://sisudoc.org/sisu/sisu_manual/index.html'>http://sisudoc.org/sisu/sisu_manual/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_commands/index.html'>http://sisudoc.org/sisu/sisu_commands/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_complete/index.html'>http://sisudoc.org/sisu/sisu_complete/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_configuration/index.html'>http://sisudoc.org/sisu/sisu_configuration/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_description/index.html'>http://sisudoc.org/sisu/sisu_description/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_examples/index.html'>http://sisudoc.org/sisu/sisu_examples/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_faq/index.html'>http://sisudoc.org/sisu/sisu_faq/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_filetypes/index.html'>http://sisudoc.org/sisu/sisu_filetypes/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_help/index.html'>http://sisudoc.org/sisu/sisu_help/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_help_sources/index.html'>http://sisudoc.org/sisu/sisu_help_sources/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_howto/index.html'>http://sisudoc.org/sisu/sisu_howto/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_introduction/index.html'>http://sisudoc.org/sisu/sisu_introduction/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_manual/index.html'>http://sisudoc.org/sisu/sisu_manual/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_markup/index.html'>http://sisudoc.org/sisu/sisu_markup/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_output_overview/index.html'>http://sisudoc.org/sisu/sisu_output_overview/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_pdf/index.html'>http://sisudoc.org/sisu/sisu_pdf/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_postgresql/index.html'>http://sisudoc.org/sisu/sisu_postgresql/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_quickstart/index.html'>http://sisudoc.org/sisu/sisu_quickstart/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_remote/index.html'>http://sisudoc.org/sisu/sisu_remote/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_search/index.html'>http://sisudoc.org/sisu/sisu_search/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_skin/index.html'>http://sisudoc.org/sisu/sisu_skin/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_sqlite/index.html'>http://sisudoc.org/sisu/sisu_sqlite/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_syntax_highlighting/index.html'>http://sisudoc.org/sisu/sisu_syntax_highlighting/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_vim/index.html'>http://sisudoc.org/sisu/sisu_vim/index.html</a>  ><br> -  +  <p>    <<a href='http://sisudoc.org/sisu/sisu_webrick/index.html'>http://sisudoc.org/sisu/sisu_webrick/index.html</a>  ><br> -  -<p> 34.3 MAN2HTML  -<p> 34.3.1 LOCALLY INSTALLED  + +<p> 34.3 MAN2HTML +<p> 34.3.1 LOCALLY INSTALLED  <p>  <file:///usr/share/doc/sisu/html/sisu.1.html> -<p>  <file:///usr/share/doc/sisu/html/sisu_help.1.html>  +<p>  <file:///usr/share/doc/sisu/html/sisu_help.1.html>  <p>  <file:///usr/share/doc/sisu/html/sisu_help_sources.1.html>  <p>    /usr/share/doc/sisu/html/sisu.1.html<br> -  +  <p>    /usr/share/doc/sisu/html/sisu_pdf.7.html<br> -  +  <p>    /usr/share/doc/sisu/html/sisu_postgresql.7.html<br> -  +  <p>    /usr/share/doc/sisu/html/sisu_sqlite.7.html<br> -  +  <p>    /usr/share/doc/sisu/html/sisu_webrick.1.html<br> -  -<p> 34.3.2 WWW.JUS.UIO.NO/SISU  + +<p> 34.3.2 WWW.JUS.UIO.NO/SISU  <p>  <<a href='http://www.jus.uio.no/sisu/man/sisu.1.html'>http://www.jus.uio.no/sisu/man/sisu.1.html</a> ->  +>  <p>    <<a href='http://www.jus.uio.no/sisu/man/sisu.1.html'>http://www.jus.uio.no/sisu/man/sisu.1.html</a>  ><br> -  +  <p>    <<a href='http://www.jus.uio.no/sisu/man/sisu_complete.7.html'>http://www.jus.uio.no/sisu/man/sisu_complete.7.html</a>  ><br> -  +  <p>    <<a href='http://www.jus.uio.no/sisu/man/sisu_pdf.7.html'>http://www.jus.uio.no/sisu/man/sisu_pdf.7.html</a>  ><br> -  +  <p>    <<a href='http://www.jus.uio.no/sisu/man/sisu_postgresql.7.html'>http://www.jus.uio.no/sisu/man/sisu_postgresql.7.html</a>  ><br> -  +  <p>    <<a href='http://www.jus.uio.no/sisu/man/sisu_sqlite.7.html'>http://www.jus.uio.no/sisu/man/sisu_sqlite.7.html</a>  ><br> -  +  <p>    <<a href='http://www.jus.uio.no/sisu/man/sisu_webrick.1.html'>http://www.jus.uio.no/sisu/man/sisu_webrick.1.html</a>  ><br> -  -<p> DOCUMENT INFORMATION (METADATA)   -<p> METADATA   + +<p> DOCUMENT INFORMATION (METADATA) +<p> METADATA  <p>  Document Manifest @ <<a href='http://sisudoc.org/sisu_manual/sisu/sisu_manifest.html'>http://sisudoc.org/sisu_manual/sisu/sisu_manifest.html</a>  > -<p>  <b>Dublin Core</b> (DC)  +<p>  <b>Dublin Core</b> (DC)  <p>  <i>DC</i> tags included with this document are provided here. -<p>  DC Title: <i>SiSU</i> - Manual  -<p>  DC Creator: <i>Ralph</i> Amissah  -<p>  DC Rights: <i>Copyright</i> -(C) Ralph Amissah 2008, part of SiSU documentation, License GPL 3  -<p>  DC -Type: <i>information</i>  -<p>  DC Date created: <i>2002-08-28</i>  -<p>  DC Date issued: <i>2002-08-28</i> +<p> DC Title: <i>SiSU</i> - Manual +<p> DC Creator: <i>Ralph</i> Amissah +<p> DC Rights: 3 +<p>  DC Type: -<p>  DC Date available: <i>2002-08-28</i>  -<p>  DC Date modified: <i>2008-05-22</i>  +<p><i>information</i> +<p>  DC Date created: <i>2002-08-28</i> +<p>  DC Date issued: <i>2002-08-28</i> +<p>  DC +Date available: <i>2002-08-28</i> +<p>  DC Date modified: <i>2008-05-22</i>  <p>  DC Date: <i>2008-05-22</i> -<p>  <b>Version Information</b>  -<p>  Sourcefile: <i>sisu.ssm.sst</i>  +<p>  <b>Version Information</b> +<p>  Sourcefile: <i>sisu.ssm.sst</i>  <p>  Filetype: <i>SiSU</i> text insert -<p>0.67  -<p>  Sourcefile Digest, MD5(sisu.ssm.sst)= <i>7568e6bc171256672e0820a333b37459</i> +<p>0.67 +<p>  Sourcefile Digest, MD5(sisu.ssm.sst)= <i>7fbab3b7c0fd0ed2e128585c2982c5c8</i>  <p>  Skin_Digest: MD5(skin_sisu_manual.rb)= <i>072b2584bedea82ea8a416587b9fa244</i> -<p>  <b>Generated</b>  -<p>  Document (metaverse) last generated: <i>Thu</i> May 22 20:03:01 +<p>  <b>Generated</b> +<p>  Document (metaverse) last generated: <i>Mon</i> Jul 21 02:54:34  <p>- -<p>0400 2008  -<p>  Generated by: <i>SiSU</i> <i>0.66.3</i> of 2008w18/0 (2008-05-11)  +<p>0400 2008 +<p>  Generated by: <i>SiSU</i> <i>0.68.0</i> of 2008w29/1 (2008-07-21)  <p>  Ruby version: -<i>ruby</i> 1.8.6 (2008-03-03 patchlevel 114)  [i486-linux]  -<p>  +<i>ruby</i> 1.8.7 (2008-06-20 patchlevel 22)  [i486-linux] +<p>  <ol>  <b>.</b><li>objects include: headings,  paragraphs, verse, tables, images, but not footnotes/endnotes which are @@ -3303,9 +3222,9 @@ for that form of presentation, rather than for example the html being a  saved version of the odf, or the pdf being a saved version of the html.  </li><b>.</b><li>the different heading levels </li><b>.</b><li>units of text, primarily paragraphs and headings,  also any tables, poems, code-blocks </li><b>.</b><li>Specification submitted by Adobe to -ISO to become a full open ISO specification  <<a href='http://www.linux-watch.com/news/NS7542722606.html'>http://www.linux-watch.com/news/NS7542722606.html</a> -><br> - </li><b>.</b><li>ISO/IEC 26300:2006 </dd> +ISO to become a full open ISO specification <<a href='http://www.linux-watch.com/news/NS7542722606.html'>http://www.linux-watch.com/news/NS7542722606.html</a> +> +</li><b>.</b><li>ISO/IEC 26300:2006 </dd>  <dt><b>*1.</b> </dt>  <dd>square brackets </dd> @@ -3340,44 +3259,43 @@ notes, numbered asterisk footnote/endnote series </li><b>.</b><li><<a href='h  >  </li><b>.</b><li><<a href='http://www.ruby-lang.org/en/'>http://www.ruby-lang.org/en/</a>  > </li><b>.</b><li>Table from the Wealth of Networks by Yochai Benkler - <<a href='http://www.jus.uio.no/sisu/the_wealth_of_networks.yochai_benkler'>http://www.jus.uio.no/sisu/the_wealth_of_networks.yochai_benkler</a> -><br> - </li><b>.</b><li>.ssc (for composite) is under consideration but ._sst makes clear that this -is not a regular file to be worked on, and thus less likely that people -will have processing. It may be however that when the resulting file is -shared .ssc is an appropriate suffix to use. </li><b>.</b><li>.B SiSU has worked this way in -the past, though this was dropped as it was thought the complexity outweighed -the flexibility, however, the balance was rather fine and this behaviour -could be reinstated. </li><b>.</b><li><<a href='http://www.postgresql.org/'>http://www.postgresql.org/</a> ->  <<a href='http://advocacy.postgresql.org/'>http://advocacy.postgresql.org/</a> -><br> -  <<a href='http://en.wikipedia.org/wiki/Postgresql'>http://en.wikipedia.org/wiki/Postgresql</a> -><br> - </li><b>.</b><li><<a href='http://www.hwaci.com/sw/sqlite/'>http://www.hwaci.com/sw/sqlite/</a> ->  <<a href='http://en.wikipedia.org/wiki/Sqlite'>http://en.wikipedia.org/wiki/Sqlite</a> -><br> - </li><b>.</b><li><<a href='http://search.sisudoc.org'>http://search.sisudoc.org</a> -> </li><b>.</b><li>(which could be extended further with current -back-end). As regards scaling of the database, it is as scalable as the database -(here Postgresql) and hardware allow. </li><b>.</b><li>of this feature when demonstrated -to an IBM software innovations evaluator in 2004 he said to paraphrase: -this could be of interest to us. We have large document management systems, -you can search hundreds of thousands of documents and we can tell you which -documents meet your search criteria, but there is no way we can tell you -without opening each document where within each your matches are found. -</li><b>.</b><li>There is nothing to stop MySQL support being added in future. </li><b>.</b><li><<a href='http://www.jus.uio.no/sisu/man/sisu.1'>http://www.jus.uio.no/sisu/man/sisu.1</a> +<<a href='http://www.jus.uio.no/sisu/the_wealth_of_networks.yochai_benkler'>http://www.jus.uio.no/sisu/the_wealth_of_networks.yochai_benkler</a> +> </li><b>.</b><li>.ssc (for composite) +is under consideration but ._sst makes clear that this is not a regular +file to be worked on, and thus less likely that people will have processing. +It may be however that when the resulting file is shared .ssc is an appropriate +suffix to use. </li><b>.</b><li>.B SiSU has worked this way in the past, though this was dropped +as it was thought the complexity outweighed the flexibility, however, the +balance was rather fine and this behaviour could be reinstated. </li><b>.</b><li><<a href='http://www.postgresql.org/'>http://www.postgresql.org/</a>  > -</li><b>.</b><li><<a href='http://www.jus.uio.no/sisu/man/sisu.8'>http://www.jus.uio.no/sisu/man/sisu.8</a> -> </li><b>.</b><li><<a href='http://www.jus.uio.no/sisu/man'>http://www.jus.uio.no/sisu/man</a> -> </li><b>.</b><li>the  .B Debian -Free Software guidelines require that everything distributed within  .B -Debian can be changed - and the documents are authors’ works that while freely -distributable are not freely changeable. </li><b>.</b><li>named index.html or more extensively - -<p>through sisu_manifest.html  +<<a href='http://advocacy.postgresql.org/'>http://advocacy.postgresql.org/</a> +> <<a href='http://en.wikipedia.org/wiki/Postgresql'>http://en.wikipedia.org/wiki/Postgresql</a> +> </li><b>.</b><li><<a href='http://www.hwaci.com/sw/sqlite/'>http://www.hwaci.com/sw/sqlite/</a> +> +<<a href='http://en.wikipedia.org/wiki/Sqlite'>http://en.wikipedia.org/wiki/Sqlite</a> +> </li><b>.</b><li><<a href='http://search.sisudoc.org'>http://search.sisudoc.org</a> +> </li><b>.</b><li>(which could +be extended further with current back-end). As regards scaling of the database, +it is as scalable as the database (here Postgresql) and hardware allow. +</li><b>.</b><li>of this feature when demonstrated to an IBM software innovations evaluator +in 2004 he said to paraphrase: this could be of interest to us. We have +large document management systems, you can search hundreds of thousands +of documents and we can tell you which documents meet your search criteria, +but there is no way we can tell you without opening each document where +within each your matches are found. </li><b>.</b><li>There is nothing to stop MySQL support +being added in future. </li><b>.</b><li><<a href='http://www.jus.uio.no/sisu/man/sisu.1'>http://www.jus.uio.no/sisu/man/sisu.1</a> +> </li><b>.</b><li><<a href='http://www.jus.uio.no/sisu/man/sisu.8'>http://www.jus.uio.no/sisu/man/sisu.8</a> +> +</li><b>.</b><li><<a href='http://www.jus.uio.no/sisu/man'>http://www.jus.uio.no/sisu/man</a> +> </li><b>.</b><li>the <b>Debian</b> Free Software guidelines require +that everything distributed within <b>Debian</b> can be changed - and the documents +are authors’ works that while freely distributable are not freely changeable. +</li><b>.</b><li> +<p>named index.html or more extensively through sisu_manifest.html  <p> </dd> -<dt>Other versions of this document: </dt> +<dt>Other versions +of this document: </dt>  <dd></dd>  <dt>manifest: <<a href='http://www.jus.uio.no/sisu/sisu/sisu_manifest.html'><a href='http://www.jus.uio.no/sisu/sisu/sisu_manifest.html'>http://www.jus.uio.no/sisu/sisu/sisu_manifest.html</a> @@ -3408,15 +3326,15 @@ distributable are not freely changeable. </li><b>.</b><li>named index.html or mo  </dt>  <dd></dd> -<dt>* Generated by: SiSU 0.66.3 of 2008w18/0 (2008-05-11) </dt> +<dt>* Generated by: SiSU 0.68.0 of 2008w29/1 (2008-07-21) </dt>  <dd></dd>  <dt>* Ruby version: ruby -1.8.6 (2008-03-03 patchlevel 114) [i486-linux] </dt> +1.8.7 (2008-06-20 patchlevel 22) [i486-linux] </dt>  <dd></dd> -<dt>* Last Generated on: Thu May -22 20:03:01 -0400 2008 </dt> +<dt>* Last Generated on: Mon Jul 21 +02:54:35 -0400 2008 </dt>  <dd></dd>  <dt>* SiSU <a href='http://www.jus.uio.no/sisu'>http://www.jus.uio.no/sisu</a> diff --git a/data/doc/sisu/sisu_markup_samples/sisu_manual/_sisu/sisurc.yml b/data/doc/sisu/sisu_markup_samples/sisu_manual/_sisu/sisurc.yml index ab6d99d0..908992ee 100644 --- a/data/doc/sisu/sisu_markup_samples/sisu_manual/_sisu/sisurc.yml +++ b/data/doc/sisu/sisu_markup_samples/sisu_manual/_sisu/sisurc.yml @@ -67,7 +67,7 @@ flag:    v:            '-NhwpoabxXYDyv --update'  # includes verbose; -m run by default  #% papersize, (LaTeX/pdf) current values A4, US_letter, book_b5, book_a5, US_legal  default: -  papersize:    'A4' +  papersize:    'A4,letter'    language_file: 2    #digest:       'sha' #sha is sha256, default is md5    #multilingual:  false diff --git a/data/doc/sisu/sisu_markup_samples/sisu_manual/sisu_download.ssi b/data/doc/sisu/sisu_markup_samples/sisu_manual/sisu_download.ssi index 69e51f28..864bd303 100644 --- a/data/doc/sisu/sisu_markup_samples/sisu_manual/sisu_download.ssi +++ b/data/doc/sisu/sisu_markup_samples/sisu_manual/sisu_download.ssi @@ -18,9 +18,9 @@  @date.available: 2007-08-28 -@date.modified: 2008-05-22 +@date.modified: 2008-07-21 -@date: 2008-05-22 +@date: 2008-07-21  @level: new=C; break=1; num_top=1 @@ -55,7 +55,7 @@  Download the latest version of SiSU (and SiSU markup samples):~{ Breakage and Fixes Report<br> http://www.jus.uio.no/sisu/SiSU/breakage_and_fixes.html }~ -_* {~^ sisu_0.67.0.orig.tar.gz (of 2008-05-22:20/4) }http://www.jus.uio.no/sisu/pkg/src/sisu_0.67.0.orig.tar.gz +_* {~^ sisu_0.68.0.orig.tar.gz (of 2008-07-21:29/1) }http://www.jus.uio.no/sisu/pkg/src/sisu_0.68.0.orig.tar.gz  _* {~^ sisu-markup-samples_1.0.8.orig.tar.gz (of 2007-08-19:33/7 ) }http://www.jus.uio.no/sisu/pkg/src/sisu-markup-samples_1.0.8.orig.tar.gz *~sisu-markup-samples @@ -90,23 +90,23 @@ deb-src http://www.jus.uio.no/sisu/archive unstable main non-free  !_ Source -_* {~^ sisu_0.67.0.orig.tar.gz }http://www.jus.uio.no/sisu/pkg/src/sisu_0.67.0.orig.tar.gz +_* {~^ sisu_0.68.0.orig.tar.gz }http://www.jus.uio.no/sisu/pkg/src/sisu_0.68.0.orig.tar.gz -_* {~^ sisu_0.67.0-1.diff.gz }http://www.jus.uio.no/sisu/pkg/src/sisu_0.67.0-1.diff.gz +_* {~^ sisu_0.68.0-1.diff.gz }http://www.jus.uio.no/sisu/pkg/src/sisu_0.68.0-1.diff.gz -_* {~^ sisu_0.67.0-1.dsc }http://www.jus.uio.no/sisu/pkg/src/sisu_0.67.0-1.dsc +_* {~^ sisu_0.68.0-1.dsc }http://www.jus.uio.no/sisu/pkg/src/sisu_0.68.0-1.dsc  !_ Debs -_* {~^ sisu_0.67.0-1_all.deb }http://www.jus.uio.no/sisu/archive/pool/main/s/sisu/sisu_0.67.0-1_all.deb ~{ <br>sisu, the base code, (the main package on which the others depend), without any dependencies other than ruby (and for convenience the ruby webrick web server), this generates a number of types of output on its own, other packages provide additional functionality, and have their dependencies <br>Depends: ruby (>=1.8.2), libwebrick-ruby<br>Recommends: sisu-pdf, sisu-sqlite, sisu-postgresql, sisu-examples, vim-sisu, librmagick-ruby, trang, tidy, libtidy, librexml-ruby, zip, unzip, openssl }~ +_* {~^ sisu_0.68.0-1_all.deb }http://www.jus.uio.no/sisu/archive/pool/main/s/sisu/sisu_0.68.0-1_all.deb ~{ <br>sisu, the base code, (the main package on which the others depend), without any dependencies other than ruby (and for convenience the ruby webrick web server), this generates a number of types of output on its own, other packages provide additional functionality, and have their dependencies <br>Depends: ruby (>=1.8.2), libwebrick-ruby<br>Recommends: sisu-pdf, sisu-sqlite, sisu-postgresql, sisu-examples, vim-sisu, librmagick-ruby, trang, tidy, libtidy, librexml-ruby, zip, unzip, openssl }~ -_* {~^ sisu-complete_0.67.0-1_all.deb }http://www.jus.uio.no/sisu/archive/pool/main/s/sisu/sisu-complete_0.67.0-1_all.deb ~{ <br>a package that pulls in other packages to build the whole of sisu (excluding sisu-examples) <br>Depends: ruby (>=1.8.2), sisu, sisu-pdf, sisu-postgresql, sisu-remote, sisu-sqlite, vim-sisu<br>Recommends: sisu-examples }~ +_* {~^ sisu-complete_0.68.0-1_all.deb }http://www.jus.uio.no/sisu/archive/pool/main/s/sisu/sisu-complete_0.68.0-1_all.deb ~{ <br>a package that pulls in other packages to build the whole of sisu (excluding sisu-examples) <br>Depends: ruby (>=1.8.2), sisu, sisu-pdf, sisu-postgresql, sisu-remote, sisu-sqlite, vim-sisu<br>Recommends: sisu-examples }~ -_* {~^ sisu-pdf_0.67.0-1_all.deb }http://www.jus.uio.no/sisu/archive/pool/main/s/sisu/sisu-pdf_0.67.0-1_all.deb ~{ <br>dependencies used by sisu to produce pdf from LaTeX generated <br>Depends: sisu, tetex-bin, tetex-extra, latex-ucs<br>Suggests: evince, xpdf }~ +_* {~^ sisu-pdf_0.68.0-1_all.deb }http://www.jus.uio.no/sisu/archive/pool/main/s/sisu/sisu-pdf_0.68.0-1_all.deb ~{ <br>dependencies used by sisu to produce pdf from LaTeX generated <br>Depends: sisu, tetex-bin, tetex-extra, latex-ucs<br>Suggests: evince, xpdf }~ -_* {~^ sisu-postgresql_0.67.0-1_all.deb }http://www.jus.uio.no/sisu/archive/pool/main/s/sisu/sisu-postgresql_0.67.0-1_all.deb ~{ <br>dependencies used by sisu to populate postgresql database (further configuration is necessary) <br>Depends: sisu, postgresql-8.1, libdbi-ruby, libdbm-ruby, libdbd-pg-ruby<br>Suggests: pgaccess, libdbd-pgsql, postgresql-contrib-8.1 }~ +_* {~^ sisu-postgresql_0.68.0-1_all.deb }http://www.jus.uio.no/sisu/archive/pool/main/s/sisu/sisu-postgresql_0.68.0-1_all.deb ~{ <br>dependencies used by sisu to populate postgresql database (further configuration is necessary) <br>Depends: sisu, postgresql-8.1, libdbi-ruby, libdbm-ruby, libdbd-pg-ruby<br>Suggests: pgaccess, libdbd-pgsql, postgresql-contrib-8.1 }~ -_* {~^ sisu-sqlite_0.67.0-1_all.deb }http://www.jus.uio.no/sisu/archive/pool/main/s/sisu/sisu-sqlite_0.67.0-1_all.deb ~{ <br>dependencies used by sisu to populate sqlite database <br>Depends: sisu, sqlite, libdbi-ruby, libdbm-ruby, libdbd-sqlite-ruby<br>Suggests: libdbd-sqlite }~ +_* {~^ sisu-sqlite_0.68.0-1_all.deb }http://www.jus.uio.no/sisu/archive/pool/main/s/sisu/sisu-sqlite_0.68.0-1_all.deb ~{ <br>dependencies used by sisu to populate sqlite database <br>Depends: sisu, sqlite, libdbi-ruby, libdbm-ruby, libdbd-sqlite-ruby<br>Suggests: libdbd-sqlite }~  For changelogs see: @@ -132,7 +132,7 @@ _1 http://www.jus.uio.no/sisu/sisu_markup_samples_changelog/changelog_markup_sam  The RPM is generated Alien~{ http://www.kitenet.net/programs/alien/ }~ from two deb packages (sisu and sisu-doc). Dependencies are not handled, not even that of the essential Ruby. -_* {~^ sisu-0.67.0-2.noarch.rpm }http://www.jus.uio.no/sisu/pkg/rpm/sisu-0.67.0-2.noarch.rpm ~{ untested, created using: alien -r sisu_0.67.0-1_all.deb }~ +_* {~^ sisu-0.68.0-2.noarch.rpm }http://www.jus.uio.no/sisu/pkg/rpm/sisu-0.68.0-2.noarch.rpm ~{ untested, created using: alien -r sisu_0.68.0-1_all.deb }~  _* {~^ sisu-markup-samples_1.0.8.orig-2.noarch.rpm }http://www.jus.uio.no/sisu/pkg/rpm/sisu-markup-samples_1.0.6.orig-2.noarch.rpm ~{ <br> untested, created using alien }~ diff --git a/data/doc/sisu/sisu_markup_samples/sisu_manual/sisu_manual.ssm b/data/doc/sisu/sisu_markup_samples/sisu_manual/sisu_manual.ssm index 19324618..41fd724b 100644 --- a/data/doc/sisu/sisu_markup_samples/sisu_manual/sisu_manual.ssm +++ b/data/doc/sisu/sisu_markup_samples/sisu_manual/sisu_manual.ssm @@ -18,9 +18,9 @@  @date.available: 2002-08-28 -@date.modified: 2008-05-22 +@date.modified: 2008-07-21 -@date: 2008-05-22 +@date: 2008-07-21  @level: new=C; break=1; num_top=1 diff --git a/data/doc/sisu/sisu_markup_samples/sisu_manual/sisu_markup.sst b/data/doc/sisu/sisu_markup_samples/sisu_manual/sisu_markup.sst index 3b83eee7..32659adf 100644 --- a/data/doc/sisu/sisu_markup_samples/sisu_manual/sisu_markup.sst +++ b/data/doc/sisu/sisu_markup_samples/sisu_manual/sisu_markup.sst @@ -529,8 +529,6 @@ normal text ~[+ editors notes, numbered asterisk footnote/endnote series ]~ cont  code{ -code{ -  % note the endnote marker "~^"  normal text~^ continues diff --git a/lib/sisu/v0/concordance.rb b/lib/sisu/v0/concordance.rb index 1b777bb5..f62b20ac 100644 --- a/lib/sisu/v0/concordance.rb +++ b/lib/sisu/v0/concordance.rb @@ -183,18 +183,18 @@ WOK            @path="#{@env.path.output}/#{@md.fnb}"            @freq=Hash.new(0)            @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -          @rxp_to=Regexp.new("<~(\\d+);(?:[oh]|[0-6]:)\\d+;\\w\\d+><#@dp:#@dp>$") -          @rxp_lv1=Regexp.new('^1~') #line start markers removed, ('^1~') for exceptions <!pn!>\n\n4{{{ -          @rxp_lv2=Regexp.new('^2~') -          @rxp_lv3=Regexp.new('^3~') -          @rxp_seg=Regexp.new('^4~(.+?)\s+') -          @rxp_title=Regexp.new('^0~title\s*(.+?)\s*$') +          @rxp_to=Regexp.new("#{Mx[:id_o]}~(\\d+);(?:[oh]|[0-6]:)\\d+;\\w\\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}|#{Mx[:id_o]}\S+?#{Mx[:id_c]}$") +          @rxp_lv1=/^#{Mx[:lv_o]}1:/ +          @rxp_lv2=/^#{Mx[:lv_o]}2:/ +          @rxp_lv3=/^#{Mx[:lv_o]}3:/ +          @rxp_seg=/^#{Mx[:lv_o]}4:(\S+?)#{Mx[:lv_c]}/ +          @rxp_title=Regexp.new("^#{Mx[:meta_o]}title#{Mx[:meta_c]}\s*(.+?)\s*$")            @rxp_t1=Regexp.new('^T1')            @rxp_t2=Regexp.new('^T2')            @rxp_t3=Regexp.new('^T3') -          @rxp_excluded1=/(?:https?|file|ftp):\/\/\S+/mi -          @rxp_excluded0=/^(?:to\d+|\d+| |EOF|thumb_\S+|snap_\S+|_+|-+|ii+|iv|vi+|ix|xi+|xiv|xv|xvi+|xix|xx|\S+?_\S+|[\d_]+\w\S+|[\w\d]{1,2}|\d{1,3}\w?|#@dp|[0-9a-f]{16,64}|\d{2,3}x\d{2,3}|\S{0,2}sha\d|\S{0,3}\d{4}w\d\d|\b\w\d+|\d_all\b|e\.?g\.?)$/mi #this regex causes and cures a stack dump in ruby 1.9 !!! -          @rgx_scanlist=%r{(?:<i>(?:[a-zA-Z0-9"\s]){2,7}</i>|<b>(?:[a-zA-Z0-9"\s]){2,7}</b>|(?:https?|file)://\S+)|code\{.+?\}code|<\S+?>|\w+}mi +          @rxp_excluded1=/(?:https?|file|ftp):\/\/\S+/ +          @rxp_excluded0=/^(?:#{Mx[:fa_bold_o]}|#{Mx[:fa_italics_o]})?(?:to\d+|\d+| |#{Mx[:br_endnotes]}|EOF|#{Mx[:br_eof]}|thumb_\S+|snap_\S+|_+|-+|[(]?(?:ii+|iv|vi+|ix|xi+|xiv|xv|xvi+|xix|xx)[).]?|\S+?_\S+|[\d_]+\w\S+|[\w\d]{1,2}|\d{1,3}\w?|#@dp|[0-9a-f]{16,64}|\d{2,3}x\d{2,3}|\S{0,2}sha\d|\S{0,3}\d{4}w\d\d|\b\w\d+|\d_all\b|e\.?g\.?)(?:#{Mx[:fa_bold_c]}|#{Mx[:fa_italics_c]})?$/mi #this regex causes and cures a stack dump in ruby 1.9 !!! +          @rgx_scanlist=%r{#{Mx[:fa_italics_o]}[a-zA-Z0-9"\s]{2,12}#{Mx[:fa_italics_c]}|#{Mx[:fa_bold_o]}[a-zA-Z0-9"\s]{2,12}#{Mx[:fa_bold_c]}|(?:https?|file)://\S+|#{Mx[:gr_o]}code#{Mx[:gr_o]}.+?#{Mx[:gr_o]}code-end#{Mx[:gr_o]}|<\S+?>|#{Mx[:id_o]}\S+?#{Mx[:id_c]}|\w+|[a-zA-Z]+}mi          rescue; SiSU_Errors::Info_error.new($!,$@,@md.cmd,@md.fns).error          end        end @@ -231,20 +231,39 @@ WOK          @seg,toy=nil,nil          @word_map={}          @dal_array.each do |line| -          if line !~/<~(\d+);[um]\d+;\w\d+><#@dp:#@dp>$/ # lines to ignore: # are added but not part of authors substantive text; 0 are mostly machine generated -            if line =~@rxp_seg;   @seg=line[@rxp_seg,1] +          if line !~/#{Mx[:id_o]}~(\d+);[um]\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ #lines to ignore: # are added but not part of authors substantive text; 0 are mostly machine generated +            if line =~@rxp_seg; @seg=line[@rxp_seg,1]              end -            if line =~@rxp_to;    toy=line[@rxp_to,1] +            if line =~@rxp_to;  toy=line[@rxp_to,1]              end              if toy =~/\d+/ \              and toy !~/^0$/                for word in line.scan(@rgx_scanlist) #%take in word or other match +                #word.gsub!(@rxp_clean,'') +                word.gsub!(/#{Mx[:fa_o]}\S+?#{Mx[:fa_o_c]}/,'') +                word.gsub!(/#{Mx[:fa_c_o]}\S+?#{Mx[:fa_c]}/,'') +                word.gsub!(/#{Mx[:gl_o]}#[a-z]+#{Mx[:gl_c]}/,'') +                word.gsub!(/#{Mx[:gl_o]}#[0-9]+#{Mx[:gl_c]}/,'') +                word.gsub!(/^\S$/,'') +                word=nil if word.empty?                  word=nil if word =~@rxp_excluded0 #watch                  word=nil if word =~@rxp_excluded1 #watch +                word=nil if word =~/^\S$/                  if word -                  #word.gsub!(/<\/?[i]>/,'') +                  word.gsub!(/#{Mx[:br_nl]}|#{Mx[:br_line]}/,' ') +                  word.gsub!(/#{Mx[:lv_o]}\d:\S*?#{Mx[:lv_c]}/,'') +                  word.gsub!(/#{Mx[:pa_o]}:i\d#{Mx[:pa_c]}/,'') +                  word.gsub!(/#{Mx[:id_o]}~\d+;\S+?#{Mx[:id_c]}/,'') +                  word.gsub!(/#{Mx[:fa_o]}[a-z]{1,7}#{Mx[:fa_o_c]}|#{Mx[:fa_c_o]}[a-z]{1,7}#{Mx[:fa_c]}/,'') +                  word.gsub!(/#{Mx[:mk_o]}(?:[0-9a-f]{32}:[0-9a-f]{32}|[0-9a-f]{64}:[0-9a-f]{64})#{Mx[:mk_c]}/,'') +                  word.gsub!(/#{Mx[:mk_o]}(?:[0-9a-f]{32}|[0-9a-f]{64})#{Mx[:mk_c]}/,'') +                  word.gsub!(/#{Mx[:en_a_o]}(?:\d|[*+])*|#{Mx[:en_b_o]}(?:\d|[*+])*|#{Mx[:en_a_c]}|#{Mx[:en_b_c]}/mi,'') +                  word.gsub!(/#{Mx[:fa_o]}\S+?#{Mx[:fa_o_c]}/,''); word.gsub!(/#{Mx[:fa_c_o]}\S+?#{Mx[:fa_c]}/,'') +                  #word.gsub!(/#{Mx[:fa_o]}\S+?#{Mx[:fa_c]}/,'') #watch                    word.gsub!(/<\/?\S+?>/,'') +                  word.gsub!(/^\@+/,'')                    word.strip! +                  word.gsub!(/#{Mx[:tc_p]}.+/,'')                    word.gsub!(/[\.,;:"]$/,'')                    word.gsub!(/["]/,'')                    word.gsub!(/^\s*[\(]/,'') @@ -252,8 +271,12 @@ WOK                    word.gsub!(/^(?:See|e\.?g\.?).+/,'')                    word.gsub!(/^\s*[.,;:]\s*/,'')                    word.strip! +                  word.gsub!(/^\(?[a-zA-Z]\)$/,'')                    word.gsub!(/^\d+(st|nd|rd|th)$/,'')                    word.gsub!(/^(\d+\.?)+$/, '') +                  word.gsub(/#{Mx[:mk_o]}|#{Mx[:mk_c]}/,'') +                  word.gsub!(/^\S$/,'') +                  word=nil if word =~/^\S$/                    word=nil if word =~/^\s*$/ #watch                    if word                      unless word =~/[A-Z][A-Z]/ \ diff --git a/lib/sisu/v0/conf.rb b/lib/sisu/v0/conf.rb index 639847ab..5fc9343c 100644 --- a/lib/sisu/v0/conf.rb +++ b/lib/sisu/v0/conf.rb @@ -111,6 +111,7 @@ module SiSU_Initialize        tell=SiSU_Screen::Ansi.new(@opt.cmd,'invert','Copy images','')        tell.colorize unless @opt.cmd =~/q/        SiSU_Env::Create_site.new(@opt.cmd).cp_local_images +      SiSU_Env::Create_site.new(@opt.cmd).cp_webserver_images_local #this should not have been necessary        SiSU_Env::Create_site.new(@opt.cmd).cp_base_images #base images (nav etc.) used by all html      end      def cp_external_images diff --git a/lib/sisu/v0/constants.rb b/lib/sisu/v0/constants.rb index 1fa40fb1..68093673 100644 --- a/lib/sisu/v0/constants.rb +++ b/lib/sisu/v0/constants.rb @@ -1,9 +1,10 @@ +# coding:utf-7  =begin   * Name: SiSU   * Description: a framework for document structuring, publishing and search -   #___# +   constants   * Author: Ralph Amissah @@ -59,6 +60,110 @@   ** Description: system environment, resource control and configuration details  =end - +Mx,Rx={},{} +Mx[:meta_o],Mx[:meta_c]='〔@','〕' +Mx[:lv_o_1],Mx[:lv_o_2],Mx[:lv_o_3],Mx[:lv_o_4],Mx[:lv_o_5],Mx[:lv_o_6],Mx[:lv_o_7],Mx[:lv_o_8],Mx[:lv_o_9]= +  '〔1:','〔2:','〔3:','〔4:','〔5:','〔6:','〔7:','〔8:','〔9:'; +Mx[:lv_o],Mx[:lv_c]='〔','〕' +#  '1~','2~','3~','4~','5~','6~','7~','8~','9~'; Mx[:lv_c]='' +Mx[:en_a_o]='【'; Mx[:en_a_c]='】' #Mx[:en_a_o]='~{'; Mx[:en_a_c]='}~' +Mx[:en_b_o]='〖'; Mx[:en_b_c]='〗' #Mx[:en_b_o]='~['; Mx[:en_b_c]=']~' +Mx[:br_line]="#{Mx[:mk_o]}br#{Mx[:mk_c]}" +Mx[:gr_o]='〔';                                         Mx[:gr_c]='〕' #group text mark +Mx[:id_o]='〔';                                         Mx[:id_c]='〕' #object id mark +Mx[:tc_o]='『';                                         Mx[:tc_c]='』' #table column mark +Mx[:tc_p]='┆'                                                          #table row/misc mark +Mx[:pa_o]='〔';                                         Mx[:pa_c]='〕' #affects paragraph mark +Mx[:mk_o]='〔';                                         Mx[:mk_c]='〕' #generic mark +Mx[:gl_o]='〔';                                         Mx[:gl_c]='〕' #glyph +Mx[:fa_o]='〔'; Mx[:fa_o_c]='¤';                        Mx[:fa_c_o]='¤'; Mx[:fa_c]='〕' +Mx[:fa_bold_o]=       "#{Mx[:fa_o]}b#{Mx[:fa_o_c]}";    Mx[:fa_bold_c]=       "#{Mx[:fa_c_o]}b#{Mx[:fa_c]}" +Mx[:fa_italics_o]=    "#{Mx[:fa_o]}i#{Mx[:fa_o_c]}";    Mx[:fa_italics_c]=    "#{Mx[:fa_c_o]}i#{Mx[:fa_c]}" +Mx[:fa_underscore_o]= "#{Mx[:fa_o]}u#{Mx[:fa_o_c]}";    Mx[:fa_underscore_c]= "#{Mx[:fa_c_o]}u#{Mx[:fa_c]}" +Mx[:fa_cite_o]=       "#{Mx[:fa_o]}cite#{Mx[:fa_o_c]}"; Mx[:fa_cite_c]=       "#{Mx[:fa_c_o]}cite#{Mx[:fa_c]}" +Mx[:fa_insert_o]=     "#{Mx[:fa_o]}ins#{Mx[:fa_o_c]}";  Mx[:fa_insert_c]=     "#{Mx[:fa_c_o]}ins#{Mx[:fa_c]}" +Mx[:fa_strike_o]=     "#{Mx[:fa_o]}del#{Mx[:fa_o_c]}";  Mx[:fa_strike_c]=     "#{Mx[:fa_c_o]}del#{Mx[:fa_c]}" +Mx[:fa_superscript_o]="#{Mx[:fa_o]}sup#{Mx[:fa_o_c]}";  Mx[:fa_superscript_c]="#{Mx[:fa_c_o]}sup#{Mx[:fa_c]}" +Mx[:fa_subscript_o]=   "#{Mx[:fa_o]}sub#{Mx[:fa_o_c]}"; Mx[:fa_subscript_c]=  "#{Mx[:fa_c_o]}sub#{Mx[:fa_c]}" +Mx[:fa_hilite_o]=     "#{Mx[:fa_o]}hi#{Mx[:fa_o_c]}";   Mx[:fa_hilite_c]=     "#{Mx[:fa_c_o]}hi#{Mx[:fa_c]}" +Mx[:gl_bullet]=       "#{Mx[:gl_o]}●#{Mx[:gl_c]}" +#non substantive text sort: <-#> <~#> +  Mx[:pa_non_object_dummy_heading]="#{Mx[:pa_o]}-##{Mx[:pa_c]}" #unnumbered paragraph, delete when not required [used in dummy headings, eg. for segmented html] (place marker at end of paragraph) +  Mx[:pa_non_object_no_heading]="#{Mx[:pa_o]}~##{Mx[:pa_c]}" #unnumbered paragraph (place marker at end of paragraph) +Mx[:br_line]=         "#{Mx[:mk_o]}br#{Mx[:mk_c]}" +Mx[:br_paragraph]=    "#{Mx[:mk_o]}br#{Mx[:mk_c]}" +Mx[:br_nl]=           "#{Mx[:mk_o]}nl#{Mx[:mk_c]}" +Mx[:br_page]=         "#{Mx[:mk_o]}pb#{Mx[:mk_c]}" +Mx[:br_page_new]=     "#{Mx[:mk_o]}pn#{Mx[:mk_c]}" +Mx[:br_endnotes]=     "#{Mx[:mk_o]}ENDNOTES#{Mx[:mk_c]}" +Mx[:br_eof]=          "#{Mx[:mk_o]}EOF#{Mx[:mk_c]}" +Mx[:lnk_o]='「'; Mx[:lnk_c]='」' +Mx[:sm_set_o]='《'; Mx[:sm_set_c]='》' +Mx[:sm_subset_o]='《 '; Mx[:sm_subset_c]='》' +#Mx[:sm_set_o]='∈ '; Mx[:sm_set_c]='∋ ' +#Mx[:sm_subset_o]='∈ '; Mx[:sm_subset_c]='∋ ' +Rx[:mx_fa_clean]=     /#{Mx[:fa_o]}.+?#{Mx[:fa_c]}|#{Mx[:pa_o]}.+?#{Mx[:pa_c]}|#{Mx[:mk_o]}.+?#{Mx[:mk_c]}/ +Rx[:lv],Rx[:lv_1],Rx[:lv_2],Rx[:lv_3],Rx[:lv_4],Rx[:lv_5],Rx[:lv_6],Rx[:lv_7],Rx[:lv_8],Rx[:lv_9]= +  /〔([1-9]):(\S*?)〕/,/#{Mx[:lv_o_1]}(\S*?)#{Mx[:lv_c]}/,/#{Mx[:lv_o_2]}(\S*?)#{Mx[:lv_c]}/,/#{Mx[:lv_o_3]}(\S*?)#{Mx[:lv_c]}/,/#{Mx[:lv_o_4]}(\S*?)#{Mx[:lv_c]}/,/#{Mx[:lv_o_5]}(\S*?)#{Mx[:lv_c]}/,/#{Mx[:lv_o_6]}(\S*?)#{Mx[:lv_c]}/,/#{Mx[:lv_o_7]}(\S*?)#{Mx[:lv_c]}/,/#{Mx[:lv_o_8]}(\S*?)#{Mx[:lv_c]}/,/#{Mx[:lv_o_9]}(\S*?)#{Mx[:lv_c]}/ +Rx[:meta]=/#{Mx[:meta_o]}(\S+?)#{Mx[:meta_c]}/ +unless RUBY_VERSION < '1.9' +  Mx[:meta_o].force_encoding('utf-8');                      Mx[:meta_c].force_encoding('utf-8') +  Mx[:lv_o_1].force_encoding('utf-8'); Mx[:lv_o_2].force_encoding('utf-8'); Mx[:lv_o_3].force_encoding('utf-8'); Mx[:lv_o_4].force_encoding('utf-8'); Mx[:lv_o_5].force_encoding('utf-8'); Mx[:lv_o_6].force_encoding('utf-8'); Mx[:lv_o_7].force_encoding('utf-8'); Mx[:lv_o_8].force_encoding('utf-8'); Mx[:lv_o_9].force_encoding('utf-8') +  Mx[:lv_o].force_encoding('utf-8');                        Mx[:lv_c].force_encoding('utf-8') +  Mx[:gr_o].force_encoding('utf-8');                        Mx[:gr_c].force_encoding('utf-8') +  Mx[:id_o].force_encoding('utf-8');                        Mx[:id_c].force_encoding('utf-8') +  Mx[:tc_p].force_encoding('utf-8') +  Mx[:tc_o].force_encoding('utf-8');                        Mx[:tc_c].force_encoding('utf-8') +  Mx[:pa_o].force_encoding('utf-8');                        Mx[:pa_c].force_encoding('utf-8') +  Mx[:mk_o].force_encoding('utf-8');                        Mx[:mk_c].force_encoding('utf-8') +  Mx[:gl_o].force_encoding('utf-8');                        Mx[:gl_c].force_encoding('utf-8') +  Mx[:fa_o].force_encoding('utf-8');                        Mx[:fa_c].force_encoding('utf-8') +  Mx[:fa_o_c].force_encoding('utf-8');                      Mx[:fa_c_o].force_encoding('utf-8') +  Mx[:fa_bold_o].force_encoding('utf-8');                   Mx[:fa_bold_c].force_encoding('utf-8') +  Mx[:fa_italics_o].force_encoding('utf-8');                Mx[:fa_italics_c].force_encoding('utf-8') +  Mx[:fa_underscore_o].force_encoding('utf-8');             Mx[:fa_underscore_c].force_encoding('utf-8') +  Mx[:fa_cite_o].force_encoding('utf-8');                   Mx[:fa_cite_c].force_encoding('utf-8') +  Mx[:fa_insert_o].force_encoding('utf-8');                 Mx[:fa_insert_c].force_encoding('utf-8') +  Mx[:fa_strike_o].force_encoding('utf-8');                 Mx[:fa_strike_c].force_encoding('utf-8') +  Mx[:fa_superscript_o].force_encoding('utf-8');            Mx[:fa_superscript_c].force_encoding('utf-8') +  Mx[:fa_subscript_o].force_encoding('utf-8');              Mx[:fa_subscript_c].force_encoding('utf-8') +  Mx[:fa_hilite_o].force_encoding('utf-8');                 Mx[:fa_hilite_c].force_encoding('utf-8') +  Mx[:gl_bullet].force_encoding('utf-8') +  Mx[:pa_non_object_dummy_heading].force_encoding('utf-8'); Mx[:pa_non_object_no_heading].force_encoding('utf-8') +  Mx[:br_line].force_encoding('utf-8');                     Mx[:br_nl].force_encoding('utf-8') +  Mx[:br_paragraph].force_encoding('utf-8') +  Mx[:br_page].force_encoding('utf-8');                     Mx[:br_page_new].force_encoding('utf-8') +  Mx[:br_endnotes].force_encoding('utf-8') +  Mx[:br_eof].force_encoding('utf-8') +  Mx[:lnk_o].force_encoding('utf-8');                       Mx[:lnk_c].force_encoding('utf-8') +  Mx[:sm_set_o].force_encoding('utf-8');                    Mx[:sm_set_c].force_encoding('utf-8') +  Mx[:sm_subset_o].force_encoding('utf-8');                 Mx[:sm_subset_c].force_encoding('utf-8') +# +  Rx[:mx_fa_clean].force_encoding('utf-8') +  Rx[:lv].force_encoding('utf-8');Rx[:lv_1].force_encoding('utf-8');Rx[:lv_2].force_encoding('utf-8');Rx[:lv_3].force_encoding('utf-8');Rx[:lv_4].force_encoding('utf-8');Rx[:lv_5].force_encoding('utf-8');Rx[:lv_6].force_encoding('utf-8');Rx[:lv_7].force_encoding('utf-8');Rx[:lv_8].force_encoding('utf-8');Rx[:lv_9].force_encoding('utf-8') +  Rx[:meta].force_encoding('utf-8') +end  __END__ +consider: +  〔comment〕 +  〔links?????〕 +   import document? +check: +  bold line + +┆┆⋮┇┊┋ +『』 +「」 +〔〕 +【】 + +· +¤ + #˝ " λ Ω  β   α π  Ѫ Ж  Я Ѳ  ѳ   Ф ㈣ + Ѳ  ѳ   Ф + ♩ ♭   ✠   ▭  ▬   ▪ +【】〖〗《》「」 + ‹ › ∗  +'〔lv1〕','〔lv2〕','〔lv3〕','〔lv4〕','〔lv5〕','〔lv6〕','〔lv7〕','〔lv8〕','〔lv9〕' +'〔 Ѳ1〕','〔 Ѳ2〕','〔 Ѳ3〕','〔 Ѳ4〕','〔 Ѳ5〕','〔Ѳ6〕','〔Ѳ7〕','〔Ѳ8〕','〔Ѳ9〕' diff --git a/lib/sisu/v0/css.rb b/lib/sisu/v0/css.rb index d1798a77..cdd05528 100644 --- a/lib/sisu/v0/css.rb +++ b/lib/sisu/v0/css.rb @@ -581,7 +581,9 @@ WOK      color: #000077;    }    li.doc { -    background: url(../image/bullet_doc.png) no-repeat 0 0; +    background: url(../image/bullet_09.png) no-repeat 0px 6px; +    /* background: url(../image/bullet_doc.png) no-repeat 0 0; */ +    /* background: url(../../_sisu/image/bullet_09.png) no-repeat 0px 6px; */      padding-left: 16px;      margin-left: 10px;      margin-top: 0px; @@ -603,6 +605,7 @@ WOK      text-align: left;    }    li.refcenter { +    background: url(../image/bullet_09.png) no-repeat 0px 6px;      /* background: url(../image/bullet_doc.png) no-repeat 0 0; */      background: none;      padding-left: 20px; @@ -614,7 +617,8 @@ WOK      text-align: center;    }    li.refbold { -    background: url(../image/bullet_doc.png) no-repeat 0 0; +    background: url(../image/bullet_09.png) no-repeat 0px 6px; +    /* background: url(../image/bullet_doc.png) no-repeat 0 0; */      /* padding-left: 0px; */      padding-left: 16px;      margin-left: 0; diff --git a/lib/sisu/v0/dal.rb b/lib/sisu/v0/dal.rb index 3e5e11ac..cb6d70f8 100644 --- a/lib/sisu/v0/dal.rb +++ b/lib/sisu/v0/dal.rb @@ -70,7 +70,7 @@ module SiSU_DAL    include SiSU_Env    include SiSU_Param    include SiSU_Viz -  include Syntax +  include SiSU_Syntax    class Instantiate < SiSU_Param::Parameters::Instructions      def initialize        @@flag_vocab=0 @@ -199,6 +199,7 @@ module SiSU_DAL        data=data.join.split("\n\n")        data=expand_insertions?(data)        data=SiSU_document_structure::Code.new(@md,data).code +      data=substitutions_and_insertions?(data)        data_new=[]        data.each do |x|          data_new << if x =~ /\n\n/m; x.split(/\n\n+/) @@ -206,8 +207,7 @@ module SiSU_DAL          end        end        data=data_new.flatten -      data=substitutions_and_insertions?(data) -      data=Syntax::Markup.new(@md,data).songsheet +      data=SiSU_Syntax::Markup.new(@md,data).songsheet        data=character_check(data)        data=images(data)        data=SiSU_document_structure::Tables.new(@md,data).tables @@ -234,12 +234,12 @@ module SiSU_DAL          para.gsub!(/^([12])~\?\s+/,'\1~ ')                                    #conditional header for incorporated document 2004w12          para.gsub!(/^[{~}]\s*$/,'')          para.gsub!(/^#{@@comment}.*/,'')                                       #remove comment and divider #% -        para.gsub!(/<~#>|~#\s*/,'<~#>') -        para.gsub!(/-#\s*/,'<-#><~#>') +        para.gsub!(/<~#>|~#\s*/,"#{Mx[:fa_o]}~##{Mx[:fa_c]}") +        para.gsub!(/-#\s*/,"#{Mx[:fa_o]}-##{Mx[:fa_c]}#{Mx[:fa_o]}~##{Mx[:fa_c]}")          #para.gsub!(/(#\{{3} arch-tag:|0\{{3}~cvs)\s+/, "0{{~rcs ") #KEEP ... ENABLE WIDER USE OF REVISION CONTROL -        para.gsub!(/(~\{ )\s+/,'\1') -        para.gsub!(/ \/\//,'<br />')                                           #added 2004w29 -        para.gsub!(/<br>/,'<br />')                                            #needed by xml, xhtml etc. +        para.gsub!(/(#{Mx[:en_a_o]} )\s+/,'\1'); para.gsub!(/(~\{ )\s+/,'\1') +        para.gsub!(/ \/\//,"#{Mx[:br_line]}")                                           #added 2004w29 +        para.gsub!(/<br>/,"#{Mx[:br_line]}")                                            #needed by xml, xhtml etc.          #para.gsub!(/<p>/,'<p />')                                             #consider          para.gsub!(/`/,"'")          para.gsub!(/\t/,' ') @@ -252,12 +252,12 @@ module SiSU_DAL          para.gsub!(/\\trademark\b|\\tm\b/,'®')          #non_utf8(para)          para=para + "\n" -        unless para =~/^<:code>/ +        unless para =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/            case para            when /\^~/ # endnotes                                                                                   #% Note must do this first (earlier loop) and then enter gathered data into ~^\d+              sub_para=para.dup -            @@endnote_array << sub_para.gsub!(/\n/,'').gsub!(/\^~\s+(.+)\s*/, %{~\{#{endnote_no} \\1 \}~}).strip +            @@endnote_array << sub_para.gsub!(/\n/,'').gsub!(/\^~\s+(.+)\s*/, %{#{Mx[:en_a_o]}#{endnote_no} \\1 #{Mx[:en_a_c]}}).strip               endnote_no+=1              para=nil if para =~/\^~ .+/ #removes 'binary' endnote now in endnote array for later insertion            end @@ -383,7 +383,7 @@ module SiSU_DAL              manifest="#{pre}{#{txt} }#{@u.remote}/#{url_dir}/toc.html#{note}\n\n"            else              puts "error, does currently support relative paths (reltive paths were removed, as had problems for citation, and was not suited to all output types should possibly reconsider) #{__FILE__} #{__LINE__}" -            if para =~/\{(?:~\^\s+)?(.+?)\s\[(\d[sS]*)\]\}\.\.\/(\S+?)\/(\s+~\{.+?\}~)?/ +            if para =~/\{(?:~\^\s+)?(.+?)\s\[(\d[sS]*)\]\}\.\.\/(\S+?)\/(\s+#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]})?/                txt,cmd,url_dir,note=$1,$2,$3,$4                manifest="{ #{txt} }../#{url_dir}/toc.html#{note}\n\n"              end @@ -452,7 +452,7 @@ module SiSU_DAL        tuned_file      end      def substitutions_and_insertions?(data) -      tuned_file=[] +      data_expand=[]        if data[0] =~ /^#!\s*(?:\/usr\/bin\/env sisu|\/usr\/bin\/sisu)/ # remove bang from top #! (however file is stripped, so will be removed provided no content preceeds it)          data[0].gsub!(/^#!\s*\/usr\/bin\/sisu/,'')          data[0].gsub!(/^#!\s*\/usr\/bin\/env sisu/,'') @@ -462,16 +462,6 @@ module SiSU_DAL          data[0].gsub!(/^(sisu-[\d.]+)$/,'% \1')        end        data.each do |para| -        para=if @md.markup_version.to_f >= 0.38 -          SiSU_document_structure::Structure.new(@md,para).structure_markup_normalize -        else para -        end -        #para.gsub!(/<url:(\S+?)>/,'\1') #consider, would permit use of text hyperlinks if desired, dal_syntax more appropriate? -        para.gsub!(/^((?:[1-9]|:?[A-C])~\S*)\s*$/,'\1~ [Note: heading marker::required title missing]~#')                                    #conditional header for incorporated document 2004w12 -        if para =~/^@\S+?:/ -          para.gsub!(/^@(\S+?):\s+/,'0~\1 ') -          para.gsub!(/^@(\S+?):([+-])\s+/,'0~\1\2 ') -        end          if para =~/<:insert\d+!?>/ \          and para !~/^%\s+/            @skin.select @@ -501,13 +491,25 @@ module SiSU_DAL              para=[]              ins.insert7.split(/\n\n/).each{|x| para << x << "\n"}            end -          para.each{|x| tuned_file << x } -        else tuned_file << para +          para.each{|x| data_expand << x } +        else data_expand << para +        end +        data_expand.flatten! +        data_expand.compact! +      end +      data_expand.each do |para| +        para=if @md.markup_version.to_f >= 0.38 +          SiSU_document_structure::Structure.new(@md,para).structure_markup_normalize +        else +          SiSU_document_structure::Structure.new(@md,para).structure_marks +        end +        #para.gsub!(/<url:(\S+?)>/,'\1') #consider, would permit use of text hyperlinks if desired, dal_syntax more appropriate? +        para.gsub!(/^((?:[1-9]|:?[A-C])~\S*)\s*$/,'\1~ [Note: heading marker::required title missing]~#')                                    #conditional header for incorporated document 2004w12 +        if para =~/^@\S+?:/ +          para.gsub!(/^@(\S+?):\s+/,"#{Mx[:meta_o]}\\1#{Mx[:meta_c]}") +          para.gsub!(/^@(\S+?):([+-])\s+/,"#{Mx[:meta_o]}\\1\\2#{Mx[:meta_c]}")          end -        tuned_file.flatten! -        tuned_file.compact!        end -      tuned_file      end      def numbering_song(data)        data=number_plaintext_para(data) @@ -524,8 +526,10 @@ module SiSU_DAL      def number_plaintext_para(data)        @tuned_file=[]        data.each do |para| -        para.gsub!(/(^|[^<][^v][^>])\n/,'\1 ') #messy, but idea is that tables should retain breaks -        para.gsub!(/^/,"\n") unless para =~/¡/u +        if para !~/#{Mx[:gr_o]}(?:code|group|alt|poem|verse)#{Mx[:gr_c]}|#{Mx[:gr_o]}Th|#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}/ +          para.gsub!(/(.+)\n/,'\1 ') #messy, but idea is that tables should retain breaks +        end +        para.gsub!(/^/,"\n") unless para =~/#{Mx[:tc_p]}/u          para.gsub!(/^\s+|\s$/,"\n")          @tuned_file << para        end @@ -557,27 +561,27 @@ module SiSU_DAL        # debug 2003w46 adding revision control info        if @md.flag_auto_endnotes \        and @md.flag_separate_endnotes_make -        @tuned_file << "\n4~endnotes Endnotes <-#> <~0;0:0;u0>" +        @tuned_file << "\n#{Mx[:lv_o]}4:endnotes#{Mx[:lv_c]}Endnotes #{Mx[:gl_o]}-##{Mx[:gl_c]} #{Mx[:id_o]}~0;0:0;u0#{Mx[:id_c]}"        end -      @tuned_file << "\n<ENDNOTES>" +      @tuned_file << "\n#{Mx[:br_endnotes]}" #DECIDE ON        @tuned_file=@tuned_file.flatten      end      def owner_details_seg -      data << '4~owner.details Owner Details' +      data << "#{Mx[:lv_o]}4:owner.details#{Mx[:lv_c]}Owner Details"      end      def number_sub_heading(para,num,title_no)        case para -      when /#{num}~- /;    para.gsub!(/#{num}~- /,"#{title_no} ") -      when /^#{num}~#\s*/; para.gsub!(/^#{num}~#\s*/,"#{title_no} ") -      when /^#{num}~[a-z_\.]+ / -        para.gsub!(/^#{num}~([a-z_\.]+)\s+(.+)/i,%{#{num}~\\1 #{title_no} \\2  <:name##{title_no}>}) -      when /^#{num}~\s+#{title_no}/ -        para.gsub!(/^#{num}~ /,"#{num}~#{title_no} ")                #where title contains title number -      else para.gsub!(/^#{num}~ /,"#{num}~#{title_no} #{title_no} ") #main, where title number is to be provided +      when /#{Mx[:lv_o]}#{num}:-#{Mx[:lv_c]}/;  para.gsub!(/#{Mx[:lv_o]}#{num}:-#{Mx[:lv_c]}/,"#{title_no} ") +      when /^#{Mx[:lv_o]}#{num}:##{Mx[:lv_c]}/; para.gsub!(/^#{Mx[:lv_o]}#{num}:##{Mx[:lv_c]}/,"#{title_no} ") +      when /^#{Mx[:lv_o]}#{num}:[a-z_\.]+#{Mx[:lv_c]}/ +        para.gsub!(/^#{Mx[:lv_o]}#{num}:([a-z_\.]+)#{Mx[:lv_c]}\s*(.+)/i,%{#{Mx[:lv_o]}#{num}:\\1#{Mx[:lv_c]} #{title_no} \\2  #{Mx[:fa_o]}:name##{title_no}#{Mx[:fa_c]}}) +      when /^#{Mx[:lv_o]}#{num}:#{Mx[:lv_c]}\s*#{title_no}/ +        para.gsub!(/^#{Mx[:lv_o]}#{num}:#{Mx[:lv_c]}/,"#{Mx[:lv_o]}#{num}:#{title_no}#{Mx[:lv_c]}")                #where title contains title number +      else para.gsub!(/^#{Mx[:lv_o]}#{num}:#{Mx[:lv_c]}/,"#{Mx[:lv_o]}#{num}:#{title_no}#{Mx[:lv_c]} #{title_no} ") #main, where title number is to be provided        end        if @md.toc_lev_limit \        and @md.toc_lev_limit < num -        para.gsub!(/^[5-8]~(?:~\S+)?\s*/,'!_ ') +        para.gsub!(/^#{Mx[:lv_o]}[5-9]:\S*?#{Mx[:lv_c]}/,'!_ ') #bold line, watch        end        para      end @@ -596,61 +600,61 @@ module SiSU_DAL          if (@md.markup =~/num_top/ \          or (@md.num_top \          and @md.num_top !~/^$/)) \ -        and para !~/^0~/ +        and para !~/^#{Rx[:meta]}/            if (para =~/^(?:#{no1}|^#{no2}|^#{no3}#{no4})~#/ \ -          and para !~/^4~endnotes?/) +          and para !~/^#{Mx[:lv_o]}4:endnotes#{Mx[:lv_c]}/)              t_not+=1 #; t_no2=0; t_no3=0 -            para.gsub!(/^(#{no1})~#\s*/,"\\1~ps#{t_not} ") -            para.gsub!(/^(#{no2})~#\s*/,"\\1~ps#{t_not} ") -            para.gsub!(/^(#{no3})~#\s*/,"\\1~ps#{t_not} ") -            para.gsub!(/^(#{no4})~#\s*/,"\\1~ps#{t_not} ") +            para.gsub!(/^(#{Mx[:lv_o]}#{no1}):#(#{Mx[:lv_c]})/,"\\1:ps#{t_not}\\2") +            para.gsub!(/^(#{Mx[:lv_o]}#{no2}):#(#{Mx[:lv_c]})/,"\\1:ps#{t_not}\\2") +            para.gsub!(/^(#{Mx[:lv_o]}#{no3}):#(#{Mx[:lv_c]})/,"\\1:ps#{t_not}\\2") +            para.gsub!(/^(#{Mx[:lv_o]}#{no4}):#(#{Mx[:lv_c]})/,"\\1:ps#{t_not}\\2")            end -          if para =~/#{no1}~/ +          if para =~/#{Mx[:lv_o]}#{no1}:/              @subnumber=1 -            @subnumber=0 if para =~/#{no1}~/ +            @subnumber=0 if para =~/#{Mx[:lv_o]}#{no1}:/            end -          if para =~/^[0-6]~[ \w-]/ \ -          and para !~ /(?:[0-6]~[\w-]+-|4~endnotes|^[0-6]~([a-z_\.]+)\s+[\d.]+)\s/ \ -          and para !~/<~#>|<-#>/ -            if para =~/^#{no1}~/ +          if para =~/^#{Mx[:lv_o]}[1-6]:[\w-]*#{Mx[:lv_c]}/ \ +          and para !~ /(?:#{Mx[:lv_o]}[1-6]:[\w-]+-#{Mx[:lv_c]}|#{Mx[:lv_o]}4:endnotes#{Mx[:lv_c]}|^#{Mx[:lv_o]}[1-6]:[a-z_\.]+#{Mx[:lv_c]}\s+[\d.]+)\s/ \ +          and para !~/#{Mx[:fa_o]}(?:~#|-#)#{Mx[:fa_c]}/ +            if para =~/^#{Mx[:lv_o]}#{no1}:/                t_no1+=1; t_no2=0; t_no3=0                title_no="#{t_no1}"                if not @md.seg_names.nil? \                and not @md.seg_names.include?(title_no) -                para.gsub!(/^#{no1}~\s+(\S+)#/,"#{no1}~#{title_no} \\1 #{title_no} ") #shift placement of auto-number to after first word, e.g. Article # not # Article, added on occasion of ABF (20040329) +                para.gsub!(/^#{Mx[:lv_o]}#{no1}:#{Mx[:lv_c]}\s*(\S+)#/,"#{Mx[:lv_o]}#{no1}:#{title_no}#{Mx[:lv_c]} \\1 #{title_no} ") #shift placement of auto-number to after first word, e.g. Article # not # Article, added on occasion of ABF (20040329)                  para.gsub!(/^#{no1}\{\s+(Article|Clause|Section)\s+#/i,%{#{no1}~#{title_no} \\1 #{title_no}. }) -                unless para =~/^#{no1}~\s+[\d.]+\s/ #fix -> if the title starts with a numbering scheme, do not auto-number, review -                  para.gsub!(/^#{no1}~\s+/,"#{no1}~#{title_no} #{title_no}. ") +                unless para =~/^#{Mx[:lv_o]}#{no1}:#{Mx[:lv_c]}\s*[\d.]+\s/ #fix -> if the title starts with a numbering scheme, do not auto-number, review +                  para.gsub!(/^#{Mx[:lv_o]}#{no1}:#{Mx[:lv_c]}/,"#{Mx[:lv_o]}#{no1}:#{title_no}#{Mx[:lv_c]}#{title_no}. ")                  end                  @md.seg_names << title_no                #else puts "warning segment name #{title_no} already exists"                end -              unless para =~/^#{no1}~([a-z_\.]+)\s+[A-Z]\.?\s/ #bug -> tmp fix, excludes A. B. C. lettering, but not roman numerals, is arbitrary, review required -                para.gsub!(/^#{no1}~([a-z_\.]+)\s+(.+)/i,%{#{no1}~\\1 #{title_no}. \\2 <:name##{title_no}>}) +              unless para =~/^#{Mx[:lv_o]}#{no1}:([a-z_\.]+)#{Mx[:lv_c]}\s*[A-Z]\.?\s/ #bug -> tmp fix, excludes A. B. C. lettering, but not roman numerals, is arbitrary, review required +                para.gsub!(/^#{Mx[:lv_o]}#{no1}:([a-z_\.]+)#{Mx[:lv_c]}\s*(.+)/i, +                  %{#{Mx[:lv_o]}#{no1}:\\1#{Mx[:lv_c]}#{title_no}. \\2 #{Mx[:fa_o]}:name##{title_no}#{Mx[:fa_c]}})                end +              para.gsub!(/^#{Mx[:lv_o]}#{no1}:##{Mx[:lv_c]}/,"#{title_no}. ") #watch                para.gsub!(/^#{no1}~#\s*/,"#{title_no}. ")              end -            if para =~/^#{no2}~/ +            if para =~/^#{Mx[:lv_o]}#{no2}:\S*?#{Mx[:lv_c]}/                t_no2+=1; t_no3=0                title_no="#{t_no1}.#{t_no2}"                para=number_sub_heading(para,no2,title_no)              end -            if para =~/^#{no3}~/ +            if para =~/^#{Mx[:lv_o]}#{no3}:\S*?#{Mx[:lv_c]}/                t_no3+=1                title_no="#{t_no1}.#{t_no2}.#{t_no3}"                para=number_sub_heading(para,no3,title_no)              end -          elsif para =~ /^[0-6]~[\w-]+-/ # endnotes, watch2005 -            para.gsub!(/^#{no1}~([a-z_\.]+)- /,"#{no1}~\\1 ") -            para.gsub!(/^#{no2}~([a-z_\.]+)- /,"#{no2}~\\1 ") -            para.gsub!(/^#{no3}~([a-z_\.]+)- /,"#{no3}~\\1 ") +          elsif para =~/^#{Mx[:lv_o]}[1-6]:[\w-]+-#{Mx[:lv_c]}/ # endnotes, watch2005 +            para.gsub!(/^#{Mx[:lv_o]}#{no1}:([a-z_\.]+)-#{Mx[:lv_c]}/,"#{Mx[:lv_o]}#{no1}:\\1#{Mx[:lv_c]}") #"#{no1}~\\1 ") +            para.gsub!(/^#{Mx[:lv_o]}#{no2}:([a-z_\.]+)-#{Mx[:lv_c]}/,"#{Mx[:lv_o]}#{no2}:\\1#{Mx[:lv_c]}") +            para.gsub!(/^#{Mx[:lv_o]}#{no3}:([a-z_\.]+)-#{Mx[:lv_c]}/,"#{Mx[:lv_o]}#{no3}:\\1#{Mx[:lv_c]}")            end          elsif @md.markup =~/num_extract/ #AS DANGEROUS force enable with document, note already does this type of numbering for cisg, locate and coordinate logic, is currently misplaced in code, chengwei inspired 2004w23/4 -          unless para =~ /^[0-6]~\S+/ #endnotes watch? -            if para =~/^[1-6]~\s+([\d\.]+)/ #risky (must be unique) consider output to 4~~\d instead of 4~\d -              name_num=$1 -              para.gsub!(/^([1-6]~)\s+/,"\\1#{name_num} ") -            end +          if para =~/^#{Mx[:lv_o]}[1-9]:#{Mx[:lv_c]}([\d\.]+)/ #risky (must be unique) consider output to 4~~\d instead of 4~\d +            name_num=$1 +            para.gsub!(/^#{Mx[:lv_o]}([1-9]:)#{Mx[:lv_c]}/,"#{Mx[:lv_o]}\\1#{name_num}#{Mx[:lv_c]}")            end            if @md.toc_lev_limit            end @@ -663,7 +667,7 @@ module SiSU_DAL        @tuned_file=[]        object_array=SiSU_document_structure::OCN.new(@md,data).ocn        object_array.each do |o| -        @tuned_file <<= if o.ocn; "#{o.txt} <~#{o.ocn};#{o.lv};#{o.type}>" #main ocn descriptor +        @tuned_file <<= if o.ocn; "#{o.txt} #{Mx[:id_o]}~#{o.ocn};#{o.lv};#{o.type}#{Mx[:id_c]}" #main ocn descriptor          else o.txt          end        end @@ -675,8 +679,8 @@ module SiSU_DAL        letter=%w( a b c d e f g h i j k l m n o p q r s t u v w x y z )        data.each do |para|          if para =~/\w|\S|<|\(/ -          if para !~/^%% |^0~|^4~endnotes|^<\/center>|<:ee>|<:e[:_]>|^\^~ |<:e[:_]\d+?>|^<:p[bn]>|^<:\#|<:- |<[:!]!4|^(?:alt|code|group|poem|table)\{|^\}(?:alt|code|group|poem|table)|^\}table$|<table|<\/table>|<td|<\/td>|<th|<\/th>|<tr>|<\/tr>|<hr width|<:4-endnotes>|\[endnotes\]|<:zz>|<:isbn-|<:journal-|<:conference-|<ENDNOTES?>/i #ocn here #  added with Tune.code #¡ -            if para=~/^[1-8]~/; number_small,letter_small=0,0                    #% sub-number system, (baby numbering) reset with any change of major number (more obviously should be placed in number titles, but that is conditionally executed, check and move later) +          if para !~/^%% |#{Rx[:meta]}|^0~|^#{Mx[:lv_o]}endnotes:|^4~endnotes|^<\/center>|<:ee>|<:e[:_]>|^\^~ |<:e[:_]\d+?>|^#{Mx[:fa_o]}:p[bn]#{Mx[:fa_c]}|^<:\#|<:- |<[:!]!4|#{Mx[:gr_o]}(?:alt|code|group|poem|table)#{Mx[:gr_c]}|^(?:alt|code|group|poem|table)\{|^\}(?:alt|code|group|poem|table)|^\}table$|<table|<\/table>|<td|<\/td>|<th|<\/th>|<tr>|<\/tr>|<hr width|<:4-endnotes>|\[endnotes\]|<:zz>|<:isbn-|<:journal-|<:conference-|#{Mx[:br_endnotes]}/i #ocn here #  added with Tune.code #¡ +            if para=~/^#{Mx[:lv_o]}[1-9]:\S*?#{Mx[:lv_c]}/; number_small,letter_small=0,0                    #% sub-number system, (baby numbering) reset with any change of major number (more obviously should be placed in number titles, but that is conditionally executed, check and move later)              end              if para =~/^#[ 1]/                letter_small=0 @@ -685,7 +689,7 @@ module SiSU_DAL                para.gsub!(/^#[ 1]/,"#{number_small}. ") #change 2004              end              if para =~/^_# / -              para.gsub!(/^_# /,"<:i1> #{letter[letter_small]}. ") #change 2004 +              para.gsub!(/^_# /,"#{Mx[:fa_o]}:i1#{Mx[:fa_c]} #{letter[letter_small]}. ") #change 2004                letter_small+=1              end            end @@ -717,53 +721,51 @@ module SiSU_DAL        end        data.each do |para|          para=SiSU_document_structure::Structure.new(@md,para).structure_markup -        if para =~/^[456]~ / -          if para=~/^4/ \ +        if para =~/^#{Mx[:lv_o]}[456]:#{Mx[:lv_c]}/ +          if para=~/^#{Mx[:lv_o]}[4]:#{Mx[:lv_c]}/ \            and not @md.set_heading_seg              @md.set_heading_seg=true            end -          if para =~/^[456]~(?:\s\S+)?\s+([\d.,:-]+)/m #heading starts with a recognised numeric or word followed by a recognised numerical construct, use that as name +          if para =~/^#{Mx[:lv_o]}[456]:#{Mx[:lv_c]}(?:\s*\S+)?\s+([\d.,:-]+)/m #heading starts with a recognised numeric or word followed by a recognised numerical construct, use that as name              pattern=$1              pattern.gsub!(/(?:[:,-]|\W)/,'.')              pattern.gsub!(/\.$/,'')              if not @md.seg_names.nil? \              and not @md.seg_names.include?(pattern) -              para.gsub!(/^([456])~\s*/,"\\1~#{pattern} ") +              para.gsub!(/^#{Mx[:lv_o]}([456]):#{Mx[:lv_c]}/,"#{Mx[:lv_o]}\\1:#{pattern}#{Mx[:lv_c]}")                @md.seg_names << pattern              else puts 'warn, there may be a conflicting numbering scheme' if @md.cmd =~/[VM]/              end            end -          if para =~/^4~\s.+?;4:(\d+);/m #extract segment name from embedded document structure info +          if para =~/^#{Mx[:lv_o]}4:#{Mx[:lv_c]}.+?;4:(\d+);/m #extract segment name from embedded document structure info              pattern=$1              pattern.gsub!(/(?:[:,-]|\W)/,'.')              pattern.gsub!(/\.$/,'')              if not @md.seg_names.nil? \              and not @md.seg_names.include?(pattern) -              para.gsub!(/^(4)~\s*/,"\\1~#{pattern} ") +              para.gsub!(/^#{Mx[:lv_o]}(4:)#{Mx[:lv_c]}/,"#{Mx[:lv_o]}\\1#{pattern}#{Mx[:lv_c]}")                @md.seg_names << pattern              else -              para.gsub!(/^(4)~\s*/,"\\1~~#{pattern} ") +              para.gsub!(/^#{Mx[:lv_o]}(4:)#{Mx[:lv_c]}/,"#{Mx[:lv_o]}\\1~#{pattern}#{Mx[:lv_c]}")                @md.seg_names << "~#{pattern}"              end            end -          if para =~/^4~\s+/ #if still not segment name, provide a numerical one +          if para =~/^#{Mx[:lv_o]}4:#{Mx[:lv_c]}/ #if still not segment name, provide a numerical one              if not @md.seg_names.nil? \              and not @md.seg_names.include?(art_filename_auto) -              para.gsub!(/^4~\s+/,%{4~_#{art_filename_auto} }) +              para.gsub!(/^#{Mx[:lv_o]}(4:)#{Mx[:lv_c]}/,%{#{Mx[:lv_o]}\\1~#{art_filename_auto}#{Mx[:lv_c]}})                @md.seg_names << art_filename_auto              else puts 'segment name (numbering) error'              end              art_filename_auto+=1            end          end -        @tuned_file << if para =~/^([1-6])~/m \ -        and (@md.pagenew \ -        or @md.pagebreak) +        @tuned_file << if para =~/^#{Mx[:lv_o]}([1-6]):\S*?#{Mx[:lv_c]}/m \ +        and (@md.pagenew or @md.pagebreak)            m=$1 #watch ref~            para_tmp=[] -          if @md.pagenew.inspect =~/#{m}/;           para_tmp << "<:pn>\n" << para -          end -          if @md.pagebreak.inspect =~/#{m}/;         para_tmp << "<:pb>\n" << para +          if @md.pagenew.inspect =~/#{m}/;           para_tmp << "#{Mx[:br_page_new]}\n" << para +          elsif @md.pagebreak.inspect =~/#{m}/;         para_tmp << "#{Mx[:br_page]}\n" << para            end            para_result=unless para_tmp.length > 0; para            else                       para_tmp @@ -782,11 +784,11 @@ module SiSU_DAL          @tuned_file=[]          data.each do |para|            unless @md.set_heading_top -            if para !~/^(?:@\S+:|0~\S+)\s/m \ +            if para !~/^(?:#{Rx[:meta]}|@\S+:|0~\S+)\s/m \              and para !~/\A\s*\Z/m                @md.set_heading_top=true -              head=if @md.title ; "1~ #{@md.title}" -              else                '1~ [no title provided]' +              head=if @md.title ; "#{Mx[:lv_o]}1:#{Mx[:lv_c]} #{@md.title}" +              else                "#{Mx[:lv_o]}1:#{Mx[:lv_c]} [no title provided]"                end                @tuned_file << head              end @@ -802,12 +804,12 @@ module SiSU_DAL          @tuned_file=[]          data.each do |para|            unless @md.set_heading_seg -            if para !~/^(?:@\S+:|0~\S+|[123]~)/m \ +            if para !~/^(?:#{Rx[:meta]}|#{Mx[:lv_o]}[123]:\S*?#{Mx[:lv_c]})/m \              and para !~/\A\s*\Z/m \ -            and para !~/<:p[bn]>/ +            and para !~/#{Mx[:br_page]}|#{Mx[:br_page_new]}/                @md.set_heading_seg=true -              head=if @md.title ; "4~seg [#{@md.title}]" -              else                '4~seg [segment]' +              head=if @md.title ; "#{Mx[:lv_o]}4:seg#{Mx[:lv_c]} [#{@md.title}]" +              else                "#{Mx[:lv_o]}4:seg#{Mx[:lv_c]} [segment]"                end                @tuned_file << head              end @@ -825,7 +827,7 @@ module SiSU_DAL            unless @md.set_header_title              if para !~/^%{1,2}\s/m \              and para !~/\A\s*\Z/m -              @tuned_file << "0~title #{@md.heading_seg_first}" +              @tuned_file << "#{Mx[:meta_o]}title#{Mx[:meta_c]} #{@md.heading_seg_first}"                @md.title=@md.heading_seg_first                @md.set_header_title=true              end @@ -842,23 +844,23 @@ module SiSU_DAL        data.each do |para|                                                                                   # manually numbered endnotes <!e(\d)!> <!e_(\d)!> -->          if @md.mod.inspect =~/--no-asterisk|--no-annotate/ -          para.gsub!(/~\[[*]\s.+?\]~/,'') +          para.gsub!(/#{Mx[:en_b_o]}\s.+?#{Mx[:en_b_c]}/,'')          end          if @md.mod.inspect =~/--no-dagger|--no-annotate/ -          para.gsub!(/~\[[+]\s.+?\]~/,'') +          para.gsub!(/#{Mx[:en_b_o]}[+]\s.+?#{Mx[:en_b_c]}/,'')          end -        unless para =~/^<:code>/ +        unless para =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/            case para                                                                                   # auto-numbered endnotes <!e!> <!e_!> --> -          when /~\{\s+.+?\}~|~\[[*+]\s+.+?\]~/ -            para.gsub!(/\s*(\}~|\]~)/,' \1')                                     # required 2003w31 -            word_mode=para.scan(/<:group>\n|\n<:group-end>|\S+/m) +          when /#{Mx[:en_a_o]}\s+.+?#{Mx[:en_a_c]}|#{Mx[:en_b_o]}[*+]\s+.+?#{Mx[:en_b_c]}/ +            para.gsub!(/\s*(#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/,' \1')                                     # required 2003w31 +            word_mode=para.scan(/#{Mx[:gr_o]}group#{Mx[:gr_c]}\n|\n#{Mx[:gr_o]}group-end#{Mx[:gr_c]}|\S+/m)              word_mode=endnote_call_number(word_mode)              para=word_mode.join(' ')              endnote_ref+=1            when /~\^(?:\s|$)|<:e>/                                                                                   #%Note inserts endnotes previously gathered from /^(<!e[:_]!>|[-~]\{{3})/ (in earlier loop) -            word_mode=para.scan(/<:group>\n|\n<:group-end>|\S+/m) +            word_mode=para.scan(/#{Mx[:gr_o]}group#{Mx[:gr_c]}\n|\n#{Mx[:gr_o]}group-end#{Mx[:gr_c]}|\S+/m)              word_mode=endnote_call_number(word_mode)              para=word_mode.join(' ')              endnote_ref+=1 @@ -870,19 +872,19 @@ module SiSU_DAL      end      def endnote_call_number(data)        data.each do |word| -        unless data =~/^<:code>/ +        unless data =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/            case word -          when /~\{/ -            unless word =~/~\{[*+]+/ -              word.gsub!(/~\{/,"~\{#{@@endnote_counter} ") +          when /#{Mx[:en_a_o]}/ +            unless word =~/#{Mx[:en_a_o]}[*+]+/ +              word.gsub!(/#{Mx[:en_a_o]}/,"#{Mx[:en_a_o]}#{@@endnote_counter} ")                @@endnote_counter+=1              end -          when /~\[/ -            if word =~/~\[[+]/ -              word.gsub!(/~\[[+]/,"~\[\+#{@@endnote_counter_dag} ") +          when /#{Mx[:en_b_o]}/ +            if word =~/#{Mx[:en_b_o]}[+]/ +              word.gsub!(/#{Mx[:en_b_o]}[+]/,"#{Mx[:en_b_o]}\+#{@@endnote_counter_dag} ")                @@endnote_counter_dag+=1              else -              word.gsub!(/~\[[*]?/,"~\[\*#{@@endnote_counter_asterisk} ") +              word.gsub!(/#{Mx[:en_b_o]}[*]?/,"#{Mx[:en_b_o]}\*#{@@endnote_counter_asterisk} ")                @@endnote_counter_asterisk+=1              end            when /~\^|<:e>/ @@ -898,106 +900,105 @@ module SiSU_DAL        base_html="#{dir.url.root}/#{@md.fnb}"        ocnm=ocnd=ocnv=0        ocnm+=1 -      header0='<:pn>' -      header1="\n1~meta Document Information (metadata) <~0;0:0;m#{ocnm}>" +      header1="\n#{Mx[:lv_o_1]}meta#{Mx[:lv_c]}Document Information (metadata) #{Mx[:id_o]}~0;0:0;m#{ocnm}#{Mx[:id_c]}"        ocnm+=1 -      header4="\n4~metadata Metadata <~0;m#{ocnm};m#{ocnm}>" +      header4="\n#{Mx[:lv_o_4]}metadata#{Mx[:lv_c]}Metadata #{Mx[:id_o]}~0;m#{ocnm};m#{ocnm}#{Mx[:id_c]}"        ocnm+=1; ocnd+=1 -      head_no_dc="<~0;m#{ocnm};d#{ocnd}>" +      head_no_dc="#{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}"        ocnm+=1; ocnd+=1 -      head_no_dc_tag="<~0;m#{ocnm};d#{ocnd}>" +      head_no_dc_tag="#{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}"        data.each do |para|          case para -        when /^0~(title|creator|author|translator|translated_by|illustrator|illustrated_by|prepared_by|digitized_by|description|publisher|contributor|date\.created|date\.issued|date\.available|date\.valid|date\.modified|date|type|format|rights|identifier|source|language)/i +        when /^#{Mx[:meta_o]}(title|creator|author|translator|translated_by|illustrator|illustrated_by|prepared_by|digitized_by|description|publisher|contributor|date\.created|date\.issued|date\.available|date\.valid|date\.modified|date|type|format|rights|identifier|source|language)#{Mx[:meta_c]}/i            m=$1            ocnm+=1; ocnd+=1            @dc << case para -          when /^0~title/ -            "\n#{@tr.dc_title}: <u>#{@md.dc_title}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~(?:creator|author)/ -            "\n#{@tr.creator}: <u>#{@md.dc_creator}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /0~(?:translator|translated_by)/ -            "\n#{@tr.translator}: <u>#{@md.translator}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~(?:illustrator|illustrated_by)/ -            "\n#{@tr.illustrator}: <u>#{@md.illustrator}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~prepared_by/ -            "\n#{@tr.prepared_by}: <u>#{@md.prepared_by}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~digitized_by/ -            "\n#{@tr.digitized_by}: <u>#{@md.digitized_by}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~description/ -            "\n#{@tr.description}: <u>#{@md.dc_description}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~subject/ -            "\n#{@tr.subject}: <u>#{@md.dc_subject}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~abstract/ -            "\n#{@tr.abstract}: <u>#{@md.dc_abstract}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~publisher/ -            "\n#{@tr.publisher}: <u>#{@md.dc_publisher}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~contributor/ -            "\n#{@tr.contributor}: <u>#{@md.dc_contributor}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~date.created/ -            "\n#{@tr.date_created}: <u>#{@md.dc_date_created}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~date.issued/ -            "\n#{@tr.date_issued}: <u>#{@md.dc_date_issued}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~date.available/ -            "\n#{@tr.date_available}: <u>#{@md.dc_date_available}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~date.modified/ -            "\n#{@tr.date_modified}: <u>#{@md.dc_date_modified}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~date.valid/ -            "\n#{@tr.date_valid}: <u>#{@md.dc_date_valid}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~date/ -            "\n#{@tr.date}: <u>#{@md.dc_date}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~type/ -            "\n#{@tr.type}: <u>#{@md.dc_type}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~format/ -            "\n#{@tr.format}: <u>#{@md.dc_format}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~rights/ -            "\n#{@tr.rights}: <u>#{@md.dc_rights}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~identifier/ -            "\n#{@tr.identifier}: <u>#{@md.dc_identifier}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~source/ -            "\n#{@tr.source}: <u>#{@md.dc_source}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~language/ -            "\n#{@tr.language}: <u>#{@md.dc_language}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~language.original/ -            "\n#{@tr.language_original}: <u>#{@md.language_original}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~relation/ -            "\n#{@tr.relation}: <u>#{@md.dc_relation}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~coverage/ -            "\n#{@tr.coverage}: <u>#{@md.dc_coverage}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~keywords/ -            "\n#{@tr.keywords}: <u>#{@md.keywords}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~comments/ -            "\n#{@tr.comments}: <u>#{@md.comments}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~cls_loc/ -            "\n#{@cls_dewey}: <u>#{@md.cls_dewey}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~cls_dewey/ -            "\n#{@tr.cls_dewey}: <u>#{@md.cls_dewey}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~cls_gutenberg|0~cls_pg/ -            "\n#{@tr.cls_gutenberg}: <u>#{@md.cls_gutenberg}</u> <~0;m#{ocnm};d#{ocnd}>" -            #"\n#{@tr.cls_gutenberg}: <u>#{@md.cls_pg}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~cls_isbn/ -            "\n#{@tr.cls_isbn}: <u>#{@md.cls_isbn}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~prefix(?:_a)?/ -            "\n#{@tr.prefix_a}: <u>#{@md.prefix_a}</u> <~0;m#{ocnm};d#{ocnd}>" -          when /^0~prefix_b/ -            "\n#{@tr.prefix_b}: <u>#{@md.prefix_b}</u> <~0;m#{ocnm};d#{ocnd}>" -          else para.gsub(/^0~(#{m})\s+(.+)/m,"\n#{m.capitalize}: <u>\\2</u> <~0;m#{ocnm};d#{ocnd}>") +          when /^#{Mx[:meta_o]}title#{Mx[:meta_c]}/ +            "\n#{@tr.dc_title}: #{Mx[:fa_underscore_o]}#{@md.dc_title}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}(?:creator|author)#{Mx[:meta_c]}/ +            "\n#{@tr.creator}: #{Mx[:fa_underscore_o]}#{@md.dc_creator}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /#{Mx[:meta_o]}(?:translator|translated_by)#{Mx[:meta_c]}/ +            "\n#{@tr.translator}: #{Mx[:fa_underscore_o]}#{@md.translator}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}(?:illustrator|illustrated_by)#{Mx[:meta_c]}/ +            "\n#{@tr.illustrator}: #{Mx[:fa_underscore_o]}#{@md.illustrator}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}prepared_by#{Mx[:meta_c]}/ +            "\n#{@tr.prepared_by}: #{Mx[:fa_underscore_o]}#{@md.prepared_by}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}digitized_by#{Mx[:meta_c]}/ +            "\n#{@tr.digitized_by}: #{Mx[:fa_underscore_o]}#{@md.digitized_by}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}description#{Mx[:meta_c]}/ +            "\n#{@tr.description}: #{Mx[:fa_underscore_o]}#{@md.dc_description}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}subject#{Mx[:meta_c]}/ +            "\n#{@tr.subject}: #{Mx[:fa_underscore_o]}#{@md.dc_subject}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}abstract#{Mx[:meta_c]}/ +            "\n#{@tr.abstract}: #{Mx[:fa_underscore_o]}#{@md.dc_abstract}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}publisher#{Mx[:meta_c]}/ +            "\n#{@tr.publisher}: #{Mx[:fa_underscore_o]}#{@md.dc_publisher}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}contributor#{Mx[:meta_c]}/ +            "\n#{@tr.contributor}: #{Mx[:fa_underscore_o]}#{@md.dc_contributor}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}date.created#{Mx[:meta_c]}/ +            "\n#{@tr.date_created}: #{Mx[:fa_underscore_o]}#{@md.dc_date_created}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}date.issued#{Mx[:meta_c]}/ +            "\n#{@tr.date_issued}: #{Mx[:fa_underscore_o]}#{@md.dc_date_issued}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}date.available#{Mx[:meta_c]}/ +            "\n#{@tr.date_available}: #{Mx[:fa_underscore_o]}#{@md.dc_date_available}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}date.modified#{Mx[:meta_c]}/ +            "\n#{@tr.date_modified}: #{Mx[:fa_underscore_o]}#{@md.dc_date_modified}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}date.valid#{Mx[:meta_c]}/ +            "\n#{@tr.date_valid}: #{Mx[:fa_underscore_o]}#{@md.dc_date_valid}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}date#{Mx[:meta_c]}/ +            "\n#{@tr.date}: #{Mx[:fa_underscore_o]}#{@md.dc_date}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}type#{Mx[:meta_c]}/ +            "\n#{@tr.type}: #{Mx[:fa_underscore_o]}#{@md.dc_type}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}format#{Mx[:meta_c]}/ +            "\n#{@tr.format}: #{Mx[:fa_underscore_o]}#{@md.dc_format}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}rights#{Mx[:meta_c]}/ +            "\n#{@tr.rights}: #{Mx[:fa_underscore_o]}#{@md.dc_rights}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}identifier#{Mx[:meta_c]}/ +            "\n#{@tr.identifier}: #{Mx[:fa_underscore_o]}#{@md.dc_identifier}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}source#{Mx[:meta_c]}/ +            "\n#{@tr.source}: #{Mx[:fa_underscore_o]}#{@md.dc_source}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}language#{Mx[:meta_c]}/ +            "\n#{@tr.language}: #{Mx[:fa_underscore_o]}#{@md.dc_language}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}language.original#{Mx[:meta_c]}/ +            "\n#{@tr.language_original}: #{Mx[:fa_underscore_o]}#{@md.language_original}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}relation#{Mx[:meta_c]}/ +            "\n#{@tr.relation}: #{Mx[:fa_underscore_o]}#{@md.dc_relation}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}coverage#{Mx[:meta_c]}/ +            "\n#{@tr.coverage}: #{Mx[:fa_underscore_o]}#{@md.dc_coverage}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}keywords#{Mx[:meta_c]}/ +            "\n#{@tr.keywords}: #{Mx[:fa_underscore_o]}#{@md.keywords}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}comments#{Mx[:meta_c]}/ +            "\n#{@tr.comments}: #{Mx[:fa_underscore_o]}#{@md.comments}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}cls_loc#{Mx[:meta_c]}/ +            "\n#{@cls_dewey}: #{Mx[:fa_underscore_o]}#{@md.cls_dewey}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}cls_dewey#{Mx[:meta_c]}/ +            "\n#{@tr.cls_dewey}: #{Mx[:fa_underscore_o]}#{@md.cls_dewey}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}(?:cls_gutenberg|cls_pg)#{Mx[:meta_c]}/ +            "\n#{@tr.cls_gutenberg}: #{Mx[:fa_underscore_o]}#{@md.cls_gutenberg}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +            #"\n#{@tr.cls_gutenberg}: <u>#{@md.cls_pg}</u> #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}cls_isbn#{Mx[:meta_c]}/ +            "\n#{@tr.cls_isbn}: #{Mx[:fa_underscore_o]}#{@md.cls_isbn}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}prefix(?:_a)?#{Mx[:meta_c]}/ +            "\n#{@tr.prefix_a}: #{Mx[:fa_underscore_o]}#{@md.prefix_a}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          when /^#{Mx[:meta_o]}prefix_b#{Mx[:meta_c]}/ +            "\n#{@tr.prefix_b}: #{Mx[:fa_underscore_o]}#{@md.prefix_b}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" +          else para.gsub(/^#{Mx[:meta_o]}(#{m})\s+(.+)/m,"\n#{m.capitalize}: #{Mx[:fa_underscore_o]}\\2#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}")            end          end        end        ocnm+=1; ocnv+=1 -      head_no_rc="<~0;m#{ocnm};v#{ocnv}>" +      head_no_rc="#{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"        ocnm+=1; ocnv+=1 -      head_no_rc_tag="<~0;m#{ocnm};v#{ocnv}>" +      head_no_rc_tag="#{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"        data.each do |para|          case para          when /^0~(?:cvs|rcs)\+\s+/ #note the + sign to turn on use of cvs id            ocnm+=1; ocnv+=1 -          @cvs << "#{@tr.sc_number}: <u>#{@md.sc_number}</u> <~0;m#{ocnm};v#{ocnv}>" +          @cvs << "#{@tr.sc_number}: #{Mx[:fa_underscore_o]}#{@md.sc_number}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"            ocnm+=1; ocnv+=1 -          @cvs << "#{@tr.sc_date}: <u>#{@md.sc_date}</u> <~0;m#{ocnm};v#{ocnv}>" +          @cvs << "#{@tr.sc_date}: #{Mx[:fa_underscore_o]}#{@md.sc_date}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"            ocnm+=1; ocnv+=1 -          @cvs << "CVS/RCS time: <u>#{@md.sc_time}</u> <~0;m#{ocnm};v#{ocnv}>" +          @cvs << "CVS/RCS time: #{Mx[:fa_underscore_o]}#{@md.sc_time}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"            ocnm+=1; ocnv+=1          when /^0~cvs[+\s]/ #enable pattern above instead if you wish the default to be to include cvs tags from all documents KEEP          when /^0~cvs\s+/ #enable pattern above instead if you wish the default to be to include cvs tags from all documents KEEP @@ -1007,47 +1008,45 @@ module SiSU_DAL          ocnm+=1; ocnv+=1          if @md.sc_filename \          and @md.sc_filename.length > 3 -          @rc << "#{@tr.sourcefile}: <u>#{@md.sc_filename}</u> <~0;m#{ocnm};v#{ocnv}>" -        else @rc << "#{@tr.sourcefile}: <u>#{@md.fns}</u> <~0;m#{ocnm};v#{ocnv}>" +          @rc << "#{@tr.sourcefile}: #{Mx[:fa_underscore_o]}#{@md.sc_filename}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" +        else @rc << "#{@tr.sourcefile}: #{Mx[:fa_underscore_o]}#{@md.fns}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"          end          ocnm+=1; ocnv+=1          if @md.file_encoding \          and @md.file_encoding.length > 3  #translate -          @rc << "Filetype: <u>#{@md.file_encoding}</u> <~0;m#{ocnm};v#{ocnv}>" +          @rc << "Filetype: #{Mx[:fa_underscore_o]}#{@md.file_encoding}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"          end          ocnm+=1; ocnv+=1          if @md.dgst #change. enable by default -          @rc << "#{@tr.sourcefile_digest}, #{@md.dgst[0]} <u>#{@md.dgst[1]}</u> <~0;m#{ocnm};v#{ocnv}>" +          @rc << "#{@tr.sourcefile_digest}, #{@md.dgst[0]} #{Mx[:fa_underscore_o]}#{@md.dgst[1]}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"            ocnm+=1; ocnv+=1          end          if @md.dgst_skin #change. enable by default -          @rc << "Skin_Digest: #{@md.dgst_skin[0]} <u>#{@md.dgst_skin[1]}</u> <~0;m#{ocnm};v#{ocnv}>" +          @rc << "Skin_Digest: #{@md.dgst_skin[0]} #{Mx[:fa_underscore_o]}#{@md.dgst_skin[1]}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"            ocnm+=1; ocnv+=1          end -        @rc << "<b>Generated</b> #{head_no_rc}" if @rc.length > 0 -        @rc << "#{@tr.last_generated}: <u>#{Time.now}</u> <~0;m#{ocnm};v#{ocnv}>" +        @rc << "#{Mx[:fa_bold_o]}Generated#{Mx[:fa_bold_c]} #{head_no_rc}" if @rc.length > 0 +        @rc << "#{@tr.last_generated}: #{Mx[:fa_underscore_o]}#{Time.now}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"          ocnm+=1; ocnv+=1          if @md.sisu_version[:version] -          @rc << "#{@tr.sisu_version}: <u>#{@md.sisu_version[:project]}</u>  <u>#{@md.sisu_version[:version]}</u> of #{@md.sisu_version[:date_stamp]} (#{@md.sisu_version[:date]}) <~0;m#{ocnm};v#{ocnv}>" +          @rc << "#{@tr.sisu_version}: #{Mx[:fa_underscore_o]}#{@md.sisu_version[:project]}#{Mx[:fa_underscore_c]}  #{Mx[:fa_underscore_o]}#{@md.sisu_version[:version]}#{Mx[:fa_underscore_c]} of #{@md.sisu_version[:date_stamp]} (#{@md.sisu_version[:date]}) #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"            ocnm+=1; ocnv+=1          end -        @rc << "#{@tr.ruby_version}: <u> #{@md.ruby_version}</u> <~0;m#{ocnm};v#{ocnv}>" +        @rc << "#{@tr.ruby_version}: #{Mx[:fa_underscore_o]} #{@md.ruby_version}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"        end -      meta << header0 -      meta << header1 -      meta << header4 -      meta << "Document Manifest @\n #{base_html}/#{@md.fn[:manifest]} <~0;m#{ocnm};m#{ocnm}>" -      meta << "<b>Dublin Core</b> (DC) #{head_no_dc}" if @dc.length > 0 -      meta << "<i>DC tags included with this document are provided here.</i> #{head_no_dc_tag}" if @dc.length > 0 +      meta << Mx[:br_page_new] << header1 << header4 +      meta << "Document Manifest @\n #{base_html}/#{@md.fn[:manifest]} #{Mx[:id_o]}~0;m#{ocnm};m#{ocnm}#{Mx[:id_c]}" +      meta << "#{Mx[:fa_bold_o]}Dublin Core#{Mx[:fa_bold_c]} (DC) #{head_no_dc}" if @dc.length > 0 +      meta << "#{Mx[:fa_italics_o]}DC tags included with this document are provided here.#{Mx[:fa_italics_c]} #{head_no_dc_tag}" if @dc.length > 0        @dc.each { |x| meta << x } -      meta << "<b>Version Information</b> #{head_no_rc}" if @rc.length > 0 +      meta << "#{Mx[:fa_bold_o]}Version Information#{Mx[:fa_bold_c]} #{head_no_rc}" if @rc.length > 0        if @cvs.length > 0 -        meta << "<i>Note the version information provided here, is specific to the host site.</i> #{head_no_rc_tag}" +        meta << "#{Mx[:fa_italics_o]}Note the version information provided here, is specific to the host site.#{Mx[:fa_italics_c]} #{head_no_rc_tag}"          @cvs.each { |x| meta << x }        end        @rc.each { |x| meta << x }        ## ENDNOTE RELATED endnote related -      meta << "\n<EOF>" +      meta << "\n#{Mx[:br_eof]}"        meta=object_digest(meta)      end      def stamped(para,hash_class) @@ -1056,23 +1055,23 @@ module SiSU_DAL        digest_all=hash_class.hexdigest(para) # print "#{hash_class.name}: "; puts digest_all #length==32 or 64        stripped=strip_clean_of_markup(para)        digest_strip=hash_class.hexdigest(stripped) -      unless para =~/<:code>/ +      unless para =~/#{Mx[:fa_o]}code#{Mx[:fa_c]}/          case para -        when /~\{[\d*+]+\s+.+?\}~|~\[[*+]\d+\s+.+?\]~/m +        when /#{Mx[:en_a_o]}[\d*+]+\s+.+?#{Mx[:en_a_c]}|#{Mx[:en_b_o]}[*+]\d+\s+.+?#{Mx[:en_b_c]}/m            en_and_para,en_and_para_digest=[],[] -          para.gsub!(/\s*(\}~|\]~)/m,' \1') #watch -          para_plus_en=para.scan(/.*?~\{.+?\}~|.*?~\[.+?\]~/m) -          para_tail=if para =~/(?:.*?~\{.+?\}~|.*?~\[.+?\]~)+([\s\S]+)/m -            /(?:.*?~\{.+?\}~|.*?~\[.+?\]~)+(.+?<~\d+;(?:\w|[0-6]:)\d+;\w\d+>)/m.match(para)[1] +          para.gsub!(/\s*(#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/m,' \1') #watch +          para_plus_en=para.scan(/.*?#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}|.*?#{Mx[:en_b_o]}.+?#{Mx[:en_b_c]}/m) +          para_tail=if para =~/(?:.*?#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}|.*?#{Mx[:en_b_o]}.+?#{Mx[:en_b_c]})+([\s\S]+)/m +            /(?:.*?#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}|.*?#{Mx[:en_b_o]}.+?#{Mx[:en_b_c]})+(.+?#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]})/m.match(para)[1]            else ''            end            para_plus_en << para_tail            en_and_para_digest << endnote_digest(para_plus_en)            para_new=en_and_para_digest.join(' ') -          @tuned << para_new + '<' + digest_strip + ':' + digest_all + '>' unless para.nil? -        else @tuned << para + '<' + digest_strip + ':' + digest_all + '>' unless para.nil? +          @tuned << para_new + Mx[:id_o] + digest_strip + ':' + digest_all + Mx[:id_c] unless para.nil? +        else @tuned << para + Mx[:id_o] + digest_strip + ':' + digest_all + Mx[:id_c] unless para.nil?          end -      else @tuned << para + '<' + digest_strip + ':' + digest_all + '>' unless para.nil? +      else @tuned << para + Mx[:id_o] + digest_strip + ':' + digest_all + Mx[:id_c] unless para.nil?        end        @tuned.join      end @@ -1088,7 +1087,8 @@ module SiSU_DAL        data.compact!        data.each do |para|          para.strip! -        if para=~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+>/ +        if para=~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}/ \ +        and para !~/#{Rx[:meta]}/ #test should not be necessary remove            if @env.digest.type =~/sha256/              for hash_class in [ Digest::SHA256 ]                @tuned_file << stamped(para,hash_class) @@ -1108,16 +1108,16 @@ module SiSU_DAL        para_bit=[]        data.each do |en_plus|          para_bit <<= case en_plus -        when /~\{|~\[/ -          if en_plus =~/~\{.+?\}~|~\[.+?\]~/ -            para_txt,en_open,en_txt,en_close=/(.*?)(~\{|~\[)(.+?)(\}~|\]~)/m.match(en_plus)[1..4] +        when /#{Mx[:en_a_o]}|#{Mx[:en_b_o]}/ +          if en_plus =~/#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}|#{Mx[:en_b_o]}.+?#{Mx[:en_b_c]}/ +            para_txt,en_open,en_txt,en_close=/(.*?)(#{Mx[:en_a_o]}|#{Mx[:en_b_o]})(.+?)(#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/m.match(en_plus)[1..4]              stripped_en=strip_clean_of_markup(en_txt)              digest_en_strip=if @env.digest.type =~/sha256/                Digest::SHA256.hexdigest(stripped_en)              else                Digest::MD5.hexdigest(stripped_en)              end -            para_txt + en_open + en_txt + '<' + digest_en_strip + '>' + en_close +            para_txt + en_open + en_txt + Mx[:id_o] + digest_en_strip + Mx[:id_c] + en_close            else puts "Error Exception - problem encountered with:\n#{en_plus}" #arbitrary exception, tidy up            end          else en_plus @@ -1131,12 +1131,13 @@ module SiSU_DAL        s=s.gsub(/ [ ]+/,' ')        s=s.gsub(/^ [ ]+/,'')        s=s.gsub(/ [ ]+$/,'') -      s=s.gsub(/(<\/[bi]>')[ ]+(s )/,'\1\2') +      s=s.gsub(/((?:#{Mx[:fa_bold_c]}|#{Mx[:fa_italics_c]})')[ ]+(s )/,'\1\2') +      s=s.gsub(/((?:#{Mx[:fa_bold_c]}|#{Mx[:fa_italics_c]})')[ ]+(s )/,'\1\2')      end      def strip_clean_of_markup(s)                                                 # used for digest, define rules, make same as in db clean        #consider: <\/?[ib]>|<(?:\/ )?br>|<del>(.+?)<\/del>        s=s.dup -      s=s.gsub(/(?:<\/?[ib]>|<~\d+;(?:\w|[0-6]:)\d+;\w\d+>|<#@dp:#@dp>|^[1-6]~\S+|~\{\d+\s.+?\}~)/m,'') # markup and endnotes removed +      s=s.gsub(/(?:<\/?[ib]>|#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}|#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}|^#{Mx[:lv_o]}[1-6]:\S+?#{Mx[:lv_c]}|#{Mx[:en_a_o]}\d+\s.+?#{Mx[:en_a_c]})/m,'') # markup and endnotes removed                                                                                   #% same as db clean -->        s=s.gsub(/<del>(.+?)<\/del>/,'DELETED(\1)')                             # deletions        s=s.gsub(/<sup>(\d+)<\/sup>/,'[\1]') diff --git a/lib/sisu/v0/dal_doc_str.rb b/lib/sisu/v0/dal_doc_str.rb index ebaa8625..37e9be3c 100644 --- a/lib/sisu/v0/dal_doc_str.rb +++ b/lib/sisu/v0/dal_doc_str.rb @@ -71,14 +71,14 @@ module SiSU_document_structure        @para      end      def structure_markup -      @para=unless @para =~/[0-6]~/ +      @para=unless @para =~/#{Mx[:lv_o]}[1-9]:\S*?#{Mx[:lv_c]}/          @para=case @para -        when /^\s*#{@md.lv1}/; @para.sub!(/(?:<[:!]1!?>\s*)?(.+)/,'1~ \1') if @para !~/^1~/ -        when /^\s*#{@md.lv2}/; @para.sub!(/(?:<[:!]2!?>\s*)?(.+)/,'2~ \1') if @para !~/^2~/ -        when /^\s*#{@md.lv3}/; @para.sub!(/(?:<[:!]3!?>\s*)?(.+)/,'3~ \1') if @para !~/^3~/ -        when /^\s*#{@md.lv4}/; @para.sub!(/(?:<[:!]4!?>\s*)?(.+)/,'4~ \1') if @para !~/^4~/ -        when /^\s*#{@md.lv5}/; @para.sub!(/(?:<[:!]5!?>\s*)?(.+)/,'5~ \1') if @para !~/^5~/ -        when /^\s*#{@md.lv6}/; @para.sub!(/(?:<[:!]6!?>\s*)?(.+)/,'6~ \1') if @para !~/^6~/ +        when /^\s*#{@md.lv1}/; @para.sub!(/(?:<[:!]1!?>\s*)?(.+)/,"#{Mx[:lv_o]}1:#{Mx[:lv_c]} \\1") if @para !~/^#{Mx[:lv_o]}1:\S*?#{Mx[:lv_c]}/ +        when /^\s*#{@md.lv2}/; @para.sub!(/(?:<[:!]2!?>\s*)?(.+)/,"#{Mx[:lv_o]}2:#{Mx[:lv_c]} \\1") if @para !~/^#{Mx[:lv_o]}2:\S*?#{Mx[:lv_c]}/ +        when /^\s*#{@md.lv3}/; @para.sub!(/(?:<[:!]3!?>\s*)?(.+)/,"#{Mx[:lv_o]}3:#{Mx[:lv_c]} \\1") if @para !~/^#{Mx[:lv_o]}3:\S*?#{Mx[:lv_c]}/ +        when /^\s*#{@md.lv4}/; @para.sub!(/(?:<[:!]4!?>\s*)?(.+)/,"#{Mx[:lv_o]}4:#{Mx[:lv_c]} \\1") if @para !~/^#{Mx[:lv_o]}4:\S*?#{Mx[:lv_c]}/ +        when /^\s*#{@md.lv5}/; @para.sub!(/(?:<[:!]5!?>\s*)?(.+)/,"#{Mx[:lv_o]}5:#{Mx[:lv_c]} \\1") if @para !~/^#{Mx[:lv_o]}5:\S*?#{Mx[:lv_c]}/ +        when /^\s*#{@md.lv6}/; @para.sub!(/(?:<[:!]6!?>\s*)?(.+)/,"#{Mx[:lv_o]}6:#{Mx[:lv_c]} \\1") if @para !~/^#{Mx[:lv_o]}6:\S*?#{Mx[:lv_c]}/          else @para          end        else @para @@ -91,12 +91,18 @@ module SiSU_document_structure            #@para.gsub!(/^5~/,'8~')            #@para.gsub!(/^4~/,'7~')          @para.gsub!(/^[456]~/,'!_') -        @para.gsub!(/^3~/,'6~') -        @para.gsub!(/^2~/,'5~') -        @para.gsub!(/^1~/,'4~') -        @para.gsub!(/^:?C~/,'3~') -        @para.gsub!(/^:?B~/,'2~') -        @para.gsub!(/^:?A~/,'1~') +        @para.gsub!(/^3~(\S+)/,"#{Mx[:lv_o]}6:\\1#{Mx[:lv_c]}") +        @para.gsub!(/^3~\s+/,"#{Mx[:lv_o]}6:#{Mx[:lv_c]}") +        @para.gsub!(/^2~(\S+)/,"#{Mx[:lv_o]}5:\\1#{Mx[:lv_c]}") +        @para.gsub!(/^2~\s+/,"#{Mx[:lv_o]}5:#{Mx[:lv_c]}") +        @para.gsub!(/^1~(\S+)/,"#{Mx[:lv_o]}4:\\1#{Mx[:lv_c]}") +        @para.gsub!(/^1~\s+/,"#{Mx[:lv_o]}4:#{Mx[:lv_c]}") +        @para.gsub!(/^:?C~(\S+)/,"#{Mx[:lv_o]}3:\\1#{Mx[:lv_c]}") +        @para.gsub!(/^:?C~\s+/,"#{Mx[:lv_o]}3:#{Mx[:lv_c]}") +        @para.gsub!(/^:?B~(\S+)/,"#{Mx[:lv_o]}2:\\1#{Mx[:lv_c]}") +        @para.gsub!(/^:?B~\s+/,"#{Mx[:lv_o]}2:#{Mx[:lv_c]}") +        @para.gsub!(/^:?A~(\S+)/,"#{Mx[:lv_o]}1:\\1#{Mx[:lv_c]}") +        @para.gsub!(/^:?A~\s+/,"#{Mx[:lv_o]}1:#{Mx[:lv_c]}")          @para=if @para =~/^@(?:level|markup):\s/            @para.gsub!(/3/,'6')            @para.gsub!(/2/,'5') @@ -110,6 +116,25 @@ module SiSU_document_structure        else @para        end      end +    def structure_marks +      para=if @md.markup_version.to_f < 0.38 +        @para.gsub!(/^1~(\S+)/,"#{Mx[:lv_o]}1:\\1#{Mx[:lv_c]}") +        @para.gsub!(/^1~\s+/,"#{Mx[:lv_o]}1:#{Mx[:lv_c]}") +        @para.gsub!(/^2~(\S+)/,"#{Mx[:lv_o]}2:\\1#{Mx[:lv_c]}") +        @para.gsub!(/^2~\s+/,"#{Mx[:lv_o]}2:#{Mx[:lv_c]}") +        @para.gsub!(/^3~(\S+)/,"#{Mx[:lv_o]}3:\\1#{Mx[:lv_c]}") +        @para.gsub!(/^3~\s+/,"#{Mx[:lv_o]}3:#{Mx[:lv_c]}") +        @para.gsub!(/^4~(\S+)/,"#{Mx[:lv_o]}4:\\1#{Mx[:lv_c]}") +        @para.gsub!(/^4~\s+/,"#{Mx[:lv_o]}4:#{Mx[:lv_c]}") +        @para.gsub!(/^5~(\S+)/,"#{Mx[:lv_o]}5:\\1#{Mx[:lv_c]}") +        @para.gsub!(/^5~\s+/,"#{Mx[:lv_o]}5:#{Mx[:lv_c]}") +        @para.gsub!(/^6~(\S+)/,"#{Mx[:lv_o]}6:\\1#{Mx[:lv_c]}") +        @para.gsub!(/^6~\s+/,"#{Mx[:lv_o]}6:#{Mx[:lv_c]}") +        @para.gsub!(/^[789]~/,'!_') +        @para +      else @para +      end +    end    end    class Struct      def initialize(o) @@ -147,21 +172,21 @@ module SiSU_document_structure        #headings=if @md.ocn.inspect =~/skip=headings/; '^(?:[A-C]|[1-9])~\S* |'        #else ''        #end -      regex_exclude_ocn_and_node = /#{headings}^%{1,4}\s|^@\S+?:\s|^0~|^4~endnotes|^<\/center>|<:ee>|<:e[:_]>|^\^~ |<:e[:_]\d+?>|^<:p[bn]>|^<:\#|<:- |<[:!]!4|<table|<\/table>|<td|<\/td>|<th|<\/th>|<tr>|<\/tr>|<hr width|<:4-endnotes>|\[endnotes\]|<:zz>|<:isbn-|<:journal-|<:conference-|<ENDNOTES?>/i #ocn here #  added with Tune.code #¡ +      regex_exclude_ocn_and_node = /#{headings}^%{1,4}\s|#{Rx[:meta]}|^@\S+?:\s|^0~|^4~endnotes|^#{Mx[:lv_o]}4:endnotes#{Mx[:lv_c]}|^<\/center>|<:ee>|<:e[:_]>|^\^~ |<:e[:_]\d+?>|^#{Mx[:fa_o]}p[bn]#{Mx[:fa_c]}|^<:\#|<:- |<[:!]!4|<table|<\/table>|<td|<\/td>|<th|<\/th>|<tr>|<\/tr>|<hr width|<:4-endnotes>|\[endnotes\]|<:zz>|<:isbn-|<:journal-|<:conference-|#{Mx[:br_endnotes]}/i #ocn here #  added with Tune.code #¡        regex_exclude_ocn = /^(?:alt|code|group|poem|table)\{|^\}(?:alt|code|group|poem|table)|^\}table$/ #ocn here #  added with Tune.code #¡        data.each do |para|          o={}          if para =~/\w|\S|<|\(/            if para !~ regex_exclude_ocn_and_node              if node_count_flag \ -            or para=~/^1~/ +            or para=~/^#{Mx[:lv_o]}1:/                node_count_flag=true              end              node+=1 if node_count_flag              if para !~ regex_exclude_ocn # regex_exclude_large previously excluded                unless para=~/<:#>|~#|-#/ # |^\s*\*\s*\*\s*\*\s*$ <-consider leaving un-numbered                  ocn+=1 -                if para=~/^[1-8]~(?:\s+|\S)/ \ +                if para=~/^#{Mx[:lv_o]}[1-9]:\S*?#{Mx[:lv_c]}/ \                  or para =~@md.lv1 \                  or para =~@md.lv2 \                  or para =~@md.lv3 \ @@ -169,33 +194,33 @@ module SiSU_document_structure                  or para =~@md.lv5 \                  or para =~@md.lv6                    ocnh+=1 -                  if    para=~/^1~(?:\s+|\S)/ \ +                  if    para=~/^#{Mx[:lv_o]}1:(\S*?)#{Mx[:lv_c]}/ \                    or para =~@md.lv1                      ocnh1+=1                                             #heading                      ocn_dv,ocn_sp="1:#{ocnh1}","h#{ocnh}" -                  elsif para=~/^2~(?:\s+|\S)/ \ +                  elsif para=~/^#{Mx[:lv_o]}2:(\S*?)#{Mx[:lv_c]}/ \                    or para =~@md.lv2; ocnh2+=1                      ocn_dv,ocn_sp="2:#{ocnh2}","h#{ocnh}" -                  elsif para=~/^3~(?:\s+|\S)/ \ +                  elsif para=~/^#{Mx[:lv_o]}3:(\S*?)#{Mx[:lv_c]}/ \                    or para =~@md.lv3; ocnh3+=1                      ocn_dv,ocn_sp="3:#{ocnh3}","h#{ocnh}" -                  elsif para=~/^4~(?:\s+|\S)/ \ +                  elsif para=~/^#{Mx[:lv_o]}4:(\S*?)#{Mx[:lv_c]}/ \                    or para =~@md.lv4; ocnh4+=1                      ocn_dv,ocn_sp="4:#{ocnh4}","h#{ocnh}" -                  elsif para=~/^5~(?:\s+|\S)/ \ +                  elsif para=~/^#{Mx[:lv_o]}5:(\S*?)#{Mx[:lv_c]}/ \                    or para =~@md.lv5; ocnh5+=1                      ocn_dv,ocn_sp="5:#{ocnh5}","h#{ocnh}" -                  elsif para=~/^6~(?:\s+|\S)/ \ +                  elsif para=~/^#{Mx[:lv_o]}6:(\S*?)#{Mx[:lv_c]}/ \                    or para =~@md.lv6; ocnh6+=1                      ocn_dv,ocn_sp="6:#{ocnh6}","h#{ocnh}"                    end                  else                    ocno+=1 -                  if para=~/<!TZ!>/;                             ocnt+=1 #table +                  if para=~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/;                             ocnt+=1 #table                      ocn_dv,ocn_sp="o#{ocno}","t#{ocnt}" -                  elsif para=~/^<:code>/;                        ocnc+=1 #code block +                  elsif para=~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/;                        ocnc+=1 #code block                      ocn_dv,ocn_sp="o#{ocno}","c#{ocnc}" -                  elsif para=~/^<:(?:group|alt|verse)>/;         ocng+=1 #group, poem +                  elsif para=~/^#{Mx[:gr_o]}(?:group|alt|verse)#{Mx[:gr_c]}/;         ocng+=1 #group, poem                      ocn_dv,ocn_sp="o#{ocno}","g#{ocng}"                    elsif para=~/\{\S+?\.(?:png|jpg|gif)\s+/m;     ocni+=1 #image                      ocn_dv,ocn_sp="o#{ocno}","i#{ocni}" @@ -212,7 +237,7 @@ module SiSU_document_structure                  #  ocn_dv,ocn_sp="u#{ocnu}","u#{ocnu}"                  #end                  #para.gsub!(/<~#>|<-#>/,'') if para              #get rid of need -                para.gsub!(/<~#>/,'') if para +                para.gsub!(/#{Mx[:fa_o]}~##{Mx[:fa_c]}/,'') if para                  ocn_dv,ocn_sp="u#{ocnu}","u#{ocnu}"                  o[:txt],o[:node],o[:ocn],o[:lv],o[:type]=para,node,0,ocn_dv,ocn_sp                end @@ -225,9 +250,9 @@ module SiSU_document_structure              end            end          end -        para.gsub!(/\n\n/,"\n") if para =~/<:(?:code|verse|alt|group)>/ #newlines taken out -        para.gsub!(/(<:(?:code-end)>)/,"\n\\1") if para =~/<:(?:code-end)>/ #newlines added check -        if para =~/<!Th?¡/u; para.gsub!(/(<!Th?¡.+?!)>/u,"\\1~#{o[:ocn]};#{o[:lv]};#{o[:type]}>") +        para.gsub!(/\n\n/,"\n") if para =~/#{Mx[:gr_o]}(?:code|verse|alt|group)#{Mx[:gr_c]}/ #newlines taken out +        para.gsub!(/(#{Mx[:gr_o]}(?:code-end)#{Mx[:gr_c]})/,"\n\\1") if para =~/#{Mx[:gr_o]}(?:code-end)#{Mx[:gr_c]}/ #newlines added check +        if para =~/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}/u; para.gsub!(/(#{Mx[:gr_o]}Th?#{Mx[:tc_p]}.+?)#{Mx[:gr_c]}/u,"\\1#{Mx[:tc_p]}~#{o[:ocn]};#{o[:lv]};#{o[:type]}#{Mx[:gr_c]}")          end          @o_array << Struct.new(o).structure if o        end diff --git a/lib/sisu/v0/dal_doc_str_code.rb b/lib/sisu/v0/dal_doc_str_code.rb index 9596bb69..82ada040 100644 --- a/lib/sisu/v0/dal_doc_str_code.rb +++ b/lib/sisu/v0/dal_doc_str_code.rb @@ -80,30 +80,30 @@ module SiSU_document_structure_code        @@counter=0        @verse_count=0        data.each do |para| -        para.gsub!(/(<:(?:code|verse|alt|group)>)\s/,'\1') #double check +        para.gsub!(/(#{Mx[:gr_o]}(?:code|verse|alt|group)#{Mx[:gr_c]})\s/,'\1') #double check          para.gsub!(/(?:\n\s*\n)+/m,"\n") unless @@flag['code'] -        if para =~/^code\{/ +        if para =~/^code\{/ and not @@flag['code']            @@flag['code']=true            @@counter=1 -          para.gsub!(/^code\{.*/,'<:code>') +          para.gsub!(/^code\{.*/,"#{Mx[:gr_o]}code#{Mx[:gr_c]}")          elsif para =~/^(?:poem)\{/ \          and not @@flag['code']            @@flag['poem']=true -          para.gsub!(/^(poem)\{.*/,'<:verse>') +          para.gsub!(/^(poem)\{.*/,"#{Mx[:gr_o]}verse#{Mx[:gr_c]}")          elsif para =~/^(?:alt|group)\{/ \          and not @@flag['code'] #group not tested, stub 2005            @@flag['group']=true -          para.gsub!(/^(alt|group)\{.*/,'<:\1>') +          para.gsub!(/^(alt|group)\{.*/,"#{Mx[:gr_o]}\\1#{Mx[:gr_c]}")          end          if @@flag['code']            if @@flag['code'] \            and para =~/^\}code/ -            para.gsub!(/^\}code.*/,'<:code-end>') +            para.gsub!(/^\}code.*/,"#{Mx[:gr_o]}code-end#{Mx[:gr_c]}")              @@flag['code']=false            end            if @@flag['code'] \ -          or para =~/<:code-end>/ #and para =~/\S/ -            sub_array=if para !~/<:code(?:-end)?>/; para.dup + '<:br>' +          or para =~/#{Mx[:gr_o]}code-end#{Mx[:gr_c]}/ #and para =~/\S/ +            sub_array=if para !~/#{Mx[:gr_o]}code(?:-end)?#{Mx[:gr_c]}/; para.dup + "#{Mx[:br_nl]}"              else para.dup              end              @line_mode=sub_array.scan(/.+/) @@ -117,18 +117,18 @@ module SiSU_document_structure_code          and not @@flag['code']            if @@flag['poem'] \            and para =~/^\}(?:poem)/ -            para.gsub!(/^\}(poem).*/,"\n<:verse-end>") +            para.gsub!(/^\}(poem).*/,"\n#{Mx[:gr_o]}verse-end#{Mx[:gr_c]}")              @@flag['poem']=false            elsif ( @@flag['group'] \            and para =~/^\}(?:alt|group)/ ) \            and not @@flag['code'] -            para.gsub!(/^\}(alt|group).*/,'<:\1-end>') +            para.gsub!(/^\}(alt|group).*/,"#{Mx[:gr_o]}\\1-end#{Mx[:gr_c]}")              @@flag['group']=false            end            if @@flag['poem'] \            or @@flag['group'] \            and para =~/\S/ \ -          and para !~/<:(verse|code|alt|group)(-end)?>/ \ +          and para !~/#{Mx[:gr_o]}(verse|code|alt|group)(-end)?#{Mx[:gr_c]}/ \            and not @@flag['code']              sub_array=para.dup              @line_mode=sub_array.scan(/.+/) @@ -138,7 +138,7 @@ module SiSU_document_structure_code              SiSU_document_structure_code::Code.new(@md,@line_mode).code_lines(type)              div=if @@flag['poem'] \              and @verse_count > 0 -              "\n" + '<:verse-end>' + "\n\n" + '<:verse>' +              "\n" + "#{Mx[:gr_o]}verse-end#{Mx[:gr_c]}" + "\n\n" + "#{Mx[:gr_o]}verse#{Mx[:gr_c]}"              else ''              end              @verse_count+=1 if @@flag['poem'] @@ -150,13 +150,13 @@ module SiSU_document_structure_code          or @@flag['poem'] \          or  @@flag['group']            @tuned_group << para if para =~/\S+/ -        elsif para =~/<:(?:code|alt|group|verse)-end>/ +        elsif para =~/#{Mx[:gr_o]}(?:code|alt|group|verse)-end#{Mx[:gr_c]}/            @verse_count=0            @tuned_group << para -          tuned_file <<= if para =~/<:group-end>/ +          tuned_file <<= if para =~/#{Mx[:gr_o]}group-end#{Mx[:gr_c]}/              @tuned_group.join("\n")            else @tuned_group=@tuned_group.join -            @tuned_group.gsub!(/<:br><:br>(<:code-end>)/,'\1') +            @tuned_group.gsub!(/#{Mx[:br_nl]}#{Mx[:br_nl]}(#{Mx[:gr_o]}code-end#{Mx[:gr_c]})/,'\1')              @tuned_group            end            @tuned_group=[] @@ -169,18 +169,18 @@ module SiSU_document_structure_code        data=@data        data.each do |line|          if line =~/\S/ \ -        and line !~/^code\{|^\}code|<:code.+/ +        and line !~/^code\{|^\}code|#{Mx[:gr_o]}code.+/            line.gsub!(/\s\s/,'  ') -          line.gsub!(/^/,'<:codeline>') if type=='code' # try sort for texpdf special case +          line.gsub!(/^/,"#{Mx[:gr_o]}codeline#{Mx[:gr_c]}") if type=='code' # try sort for texpdf special case            if line =~/(?:https?|file|ftp):\/\/\S+$/ -            line.gsub!(/$/,' <:br>') -          else line.gsub!(/$/,'<:br>') #unless type=='code' +            line.gsub!(/$/," #{Mx[:br_nl]}") +          else line.gsub!(/$/,"#{Mx[:br_nl]}") #unless type=='code'            end            if @@flag['code']; @@counter+=1            else            end          elsif line =~/^\s*$/ -          line.gsub!(/$/,' <:br>') +          line.gsub!(/$/,"#{Mx[:br_nl]}")          end        end      end diff --git a/lib/sisu/v0/dal_doc_str_tables.rb b/lib/sisu/v0/dal_doc_str_tables.rb index a17eb63f..5b636dfa 100644 --- a/lib/sisu/v0/dal_doc_str_tables.rb +++ b/lib/sisu/v0/dal_doc_str_tables.rb @@ -97,29 +97,29 @@ module SiSU_document_structure_tables        w=widths.split(/;/)        tuned_file=[]        tuned_file << if para =~/\{(?:t|table)~h(?:\sc\d+;)?[\d; ]*\}/ -        "<!Th#{TS1} c#{@row[2].length}; #{widths}!>" +        "#{Mx[:gr_o]}Th#{Mx[:tc_p]} c#{@row[2].length}; #{widths}#{Mx[:gr_c]}"        elsif para =~/\{(?:t|table)(?:\sc\d+;)?[\d; ]*\}/ -        "<!T#{TS1} c#{@row[2].length}; #{widths}!>" +        "#{Mx[:gr_o]}T#{Mx[:tc_p]} c#{@row[2].length}; #{widths}#{Mx[:gr_c]}"        end        @row.each do |l|          l << '' if l.length == (@row[1].length - 1)          table=[]          if l.length == @row[1].length -          table << '<!'                                                                  #'<tr>' +          table << Mx[:tc_o]                                                                  #'<tr>'            n= -1            l.each do |c|              n +=1                                                                      #'<td>' + c + '</td>'              table << if c =~/\A(?:\n)?\s*\Z/ -              "#{TS1}#{TS1}#{w[n]}#{TS1}" + ' ' +              "#{Mx[:tc_p]}#{Mx[:tc_p]}#{w[n]}#{Mx[:tc_p]}" + ' '              else -              "#{TS1}#{TS1}#{w[n]}#{TS1}" + c.strip +              "#{Mx[:tc_p]}#{Mx[:tc_p]}#{w[n]}#{Mx[:tc_p]}" + c.strip              end            end -          table << '!>'                                                                  #'</tr>' +          table << Mx[:tc_c]            tuned_file << table.join          end        end -      tuned_file << '<!TZ!>'                                                            #'</table>' +      tuned_file << "#{Mx[:gr_o]}TZ#{Mx[:gr_c]}"                                                            #'</table>'        tuned_file=tuned_file.compact.join("\n")      end      def tables @@ -141,13 +141,13 @@ module SiSU_document_structure_tables              instructions=$1              @@column=instructions.split(/;\s*/)              @@columns=@@column[0] -            para.gsub!(/^table\{~h\s+(c\d+?;.+?)$/,"<!Th#{TS1} \\1!>") -            para.gsub!(/^table\{\s+(c\d+?;.+?)$/,"<!T#{TS1} \\1!>") +            para.gsub!(/^table\{~h\s+(c\d+?;.+?)$/,"#{Mx[:gr_o]}Th#{Mx[:tc_p]} \\1#{Mx[:gr_c]}") +            para.gsub!(/^table\{\s+(c\d+?;.+?)$/,"#{Mx[:gr_o]}T#{Mx[:tc_p]} \\1#{Mx[:gr_c]}")              @@flag['table_to']=true            end            if @@flag['table_to'] \            and para =~/\}table/ -            para.gsub!(/^\}table\s*$/,"<!TZ!>\n") +            para.gsub!(/^\}table\s*$/,"#{Mx[:gr_o]}TZ#{Mx[:gr_c]}\n")              para.gsub!(/\n/,' ') #newlines taken out              para.strip!              @tuned_table << para @@ -164,13 +164,13 @@ module SiSU_document_structure_tables              @@line_mode=sub_array.scan(/.+/u)              Tables.new(@md,@@line_mode).tr_td              para=@@line_mode.join -            para.gsub!(/(.*\S+.*)\Z/m,'<!\1!>') unless para =~/<!Th?#{TS1}/u +            para.gsub!(/(.*\S+.*)\Z/m,"#{Mx[:tc_o]}\\1#{Mx[:tc_c]}") unless para =~/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}/u            end            para.gsub!(/\n/,' ')            para.strip!            @tuned_table << para          else -          para.gsub!(/\n/,' ') unless para =~/<:(?:code|verse|alt|group)>/ +          para.gsub!(/\n/,' ') unless para =~/#{Mx[:gr_o]}(?:code|verse|alt|group)#{Mx[:gr_c]}/            para.strip!            @tuned_file << para          end @@ -182,11 +182,11 @@ module SiSU_document_structure_tables        data=@data        data.each do |line|          if @@counter <= @@columns.to_i \ -        and line !~/(\}T\s*$|<:table[-_](close|end)>|<!TZ!>)/ +        and line !~/(\}T\s*$|#{Mx[:gr_o]}:table[-_](close|end)#{Mx[:gr_c]}|#{Mx[:gr_o]}TZ#{Mx[:gr_c]})/            #if line.encoding.inspect =~/Encoding:ASCII-8BIT/            #  line=line.force_encoding('utf-8')            #end -          line.gsub!(/(.+)/,"#{TS1}#{TS1}#{@@column[@@counter]}#{TS1}\\1") unless line =~/<!Th?#{TS1}/u +          line.gsub!(/(.+)/,"#{Mx[:tc_p]}#{Mx[:tc_p]}#{@@column[@@counter]}#{Mx[:tc_p]}\\1") unless line =~/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}/u            @@counter+=1          end        end diff --git a/lib/sisu/v0/dal_syntax.rb b/lib/sisu/v0/dal_syntax.rb index 22ec72b0..c3bd8a7d 100644 --- a/lib/sisu/v0/dal_syntax.rb +++ b/lib/sisu/v0/dal_syntax.rb @@ -58,7 +58,7 @@   ** Description: Syntax for markup, input markup syntaxes, determined here  =end -module Syntax +module SiSU_Syntax    class Words      def initialize(line,md,mkp)        @line,@md,@mkp=line,md,mkp @@ -71,11 +71,11 @@ module Syntax        @data_new=[]        url_and_stub=SiSU_Env::Info_env.new.url        @output_url="#{url_and_stub.remote}" -      @http_m='\{.+?\}(?:https?|file)://\S+|(?:https?|file):\S+|\.\.\/\S+|\S+?\.png\b|[*]~\S+|^0~.+|<:(?:code|group|alt|verse)(?:-end)?>|<:br>' +      @http_m=%r{\{.+?\}(?:https?|file)://\S+|(?:https?|file):\S+|\.\.\/\S+|\S+?\.png\b|[*]~\S+|^#{Mx[:meta_o]}.+|#{Mx[:gr_o]}(?:code|group|alt|verse)(?:-end)?#{Mx[:gr_c]}|#{Mx[:fa_o]}:br#{Mx[:fa_c]}}        @manmkp_ital='[i/]\\{.+?\\}[i/]'        tail_m_ital=%q{(?:\s|[.,;:?!'")]|~\^|~\\\{\s|$)} -      tail_m_bold=%q{(?:(?:<\/i>)?(?:\s|[.,;:?!'")]|~\^|~\\\{\s|$))?} -      bold_line=%q{^!_\s.+?(?:<br>|\n|$)} +      tail_m_bold=%{(?:(?:#{Mx[:fa_italics_c]})?(?:\s|[.,;:?!'")]|~\^|~\\\{\s|$))?} +      bold_line=%{^!_\s.+?(?:#{Mx[:br_line]}|\n|$)}        @line_scan_ital=if defined? @md.make_italic[:str] \        and defined? @vz.markup_make_italic[:str]          /#@http_m|#{bold_line}|#@manmkp_ital#{tail_m_ital}|(?:#{@md.make_italic[:str]}|#{@vz.markup_make_italic[:str]})#{tail_m_ital}|\S+|\n/ @@ -114,6 +114,8 @@ module Syntax      end      def pre(line)        line=line.dup +      line.gsub!(/^0~(\S+)/,"#{Mx[:lv_o]}@\\1#{Mx[:lv_c]}") +      line.gsub!(/^@(\S+?):/,"#{Mx[:lv_o]}@\\1#{Mx[:lv_c]}")        if line =~/\{(?:t|table)(?:~h)?\s*c?[\d; ]*\}/; line.gsub!(/(\n)/,';;\1') #markup for alternative tables        end        line @@ -124,7 +126,7 @@ module Syntax        and @md.make_italic[:str]) \        or (defined? @vz.markup_make_italic[:str] \        and @vz.markup_make_italic[:str]) -        line= if line !~/^(?:0~|%{1,4}\s|<:code)/  #!~/^(?:[0-6]~|!_|%+\s)/ +        line= if line !~/^(?:#{Rx[:meta]}|#{Mx[:gr_o]}code)/  #!~/^(?:[0-6]~|!_|%+\s)/            word=line.scan(@line_scan_ital)            word.flatten!            word.compact! #reinstated @@ -133,10 +135,10 @@ module Syntax              unless /#@manmkp_ital|#@http_m/.match(w)                if defined? @md.make_italic[:regx] \                and @md.make_italic[:regx] -                w.gsub!(@md.make_italic[:regx],'<i>\1</i>') +                w.gsub!(@md.make_italic[:regx],"#{Mx[:fa_italics_o]}\\1#{Mx[:fa_italics_c]}")                elsif defined? @vz.markup_make_italic \                and @vz.markup_make_italic -                w.gsub!(@vz.markup_make_italic,'<i>\1</i>') +                w.gsub!(@vz.markup_make_italic,"#{Mx[:fa_italics_o]}\\1#{Mx[:fa_italics_c]}")                end              end              line_array << w @@ -148,10 +150,10 @@ module Syntax        line      end      def embolden(given) -      given.gsub!(/(?:^!_|^[7-9]~)\s+(.+?)(<br>)/,'<b>\1</b>\2') -      given.gsub!(/(?:^!_|^[7-9]~)\s+(.+?)\s+((?:[*]~\S+\s*)+)/,'<b>\1</b> \2') -      given.gsub!(/(?:^!_|^[7-9]~)\s+(.+?)\s*([~-]#)$/,'<b>\1</b> \2') -      given.gsub!(/(?:^!_\s+|^[7-9]~\s+)(.*)?\s*$/,'<b>\1</b>') +      given.gsub!(/(?:^!_|^#{Mx[:lv_o]}[7-9]:\S*?#{Mx[:lv_c]})\s*(.+?)(<br>)/,"#{Mx[:fa_bold_o]}\\1#{Mx[:fa_bold_c]}\\2") +      given.gsub!(/(?:^!_|^#{Mx[:lv_o]}[7-9]:\S*?#{Mx[:lv_c]})\s*(.+?)\s+((?:[*]~\S+\s*)+)/,"#{Mx[:fa_bold_o]}\\1#{Mx[:fa_bold_c]}\\2") +      given.gsub!(/(?:^!_|^#{Mx[:lv_o]}[7-9]:\S*?#{Mx[:lv_c]})\s*(.+?)\s*([~-]#)$/,"#{Mx[:fa_bold_o]}\\1#{Mx[:fa_bold_c]}\\2") +      given.gsub!(/(?:^!_\s+|^#{Mx[:lv_o]}[7-9]:\S*?#{Mx[:lv_c]}\s*)(.*)?\s*$/,"#{Mx[:fa_bold_o]}\\1#{Mx[:fa_bold_c]}")      end      def wordlist_bold(line)        line=line.dup @@ -159,7 +161,7 @@ module Syntax        and @md.make_bold[:str]) \        or (defined? @vz.markup_make_bold[:str] \        and @vz.markup_make_bold[:str]) -        line=if line !~/^(?:[0-9]~|%+\s|<:code)/ +        line=if line !~/^(?:#{Rx[:meta]}|#{Mx[:lv_o]}[1-9]:\S*?#{Mx[:lv_c]}|%+\s|#{Mx[:gr_o]}code)/            line_array=[]            word=line.scan(@line_scan_bold)            word.flatten! @@ -168,13 +170,13 @@ module Syntax              unless /#@manmkp_bold|#@http_m/.match(w)                if defined? @md.make_bold[:regx] \                and @md.make_bold[:regx]   #document header: 0~bold [bold word list] -                w.gsub!(@md.make_bold[:regx],'<b>\1</b>') +                w.gsub!(@md.make_bold[:regx],"#{Mx[:fa_bold_o]}\\1#{Mx[:fa_bold_c]}")                elsif defined? @vz.markup_make_bold \                and @vz.markup_make_bold               #defaults and skin adjusted bold word list -                w.gsub!(@vz.markup_make_bold,'<b>\1</b>') +                w.gsub!(@vz.markup_make_bold,"#{Mx[:fa_bold_o]}\\1#{Mx[:fa_bold_c]}")                end              else -              if w =~ /(?:^!_|^[7-9]~)\s+/; embolden(w) #bold paragraph/emphasize #may wish to remove think about 7{ 8{ conversion not satisfactory, as information is lost! +              if w =~ /(?:^!_|^#{Mx[:lv_o]}[7-9]:\S*?#{Mx[:lv_c]})\s+/; embolden(w) #bold paragraph/emphasize #may wish to remove think about 7{ 8{ conversion not satisfactory, as information is lost!                end              end              line_array << w @@ -183,8 +185,8 @@ module Syntax          else line          end        else -        if line !~/^(?:[0-9]~|%+\s)/ \ -        and line =~ /(?:^!_|^[7-9]~)\s+/ +        if line !~/^(?:#{Mx[:lv_o]}[0-9]:\S*?#{Mx[:lv_c]}|%+\s)/ \ +        and line =~ /(?:^!_|^#{Mx[:lv_o]}[7-9]:\S*?#{Mx[:lv_c]})\s+/            embolden(line)          end        end @@ -218,107 +220,126 @@ module Syntax        # #                                     #numbered (list) level 1        # _#                                    #numbered (list) level 2        line=line.dup -      if line !~/^0~|<:codeline>|<:code-end>/ +      if line !~/^#{Mx[:meta_o]}|#{Mx[:gr_o]}codeline#{Mx[:gr_c]}|#{Mx[:gr_o]}code-end#{Mx[:gr_c]}/          #special characters: ~ { } < > - _ / also used : ^ ! #          line_array=[]          line.gsub!(/^%{1,4} .+/mi,'') #remove comments -        word=line.scan(/\S+|\n/) unless line =~/^(?:0~\S|%+\s)/ +        word=line.scan(/\S+|\n/) unless line =~/^(?:#{Mx[:meta_o]}|%+\s)/ #visit          if word            word.each do |w| # _ - / # | : ! ^ ~ -            unless w =~/^[0-9]~|~\{|\}~|~\[|\]~|^\^~|~\^|\*~\S+|~#|\{t?~|\{table/ -              w.gsub!(/\\~/,'~')                                              #escaped special character -              w.gsub!(/~/,'~') +            unless w =~/^#{Mx[:lv_o]}[0-9]:\S*?#{Mx[:lv_c]}|~\{|\}~|~\[|\]~|^\^~|~\^|\*~\S+|~#|\{t?~|\{table/ +              w.gsub!(/\\?~/,"#{Mx[:gl_o]}#126#{Mx[:gl_c]}")                                              #escaped special character +              #w.gsub!(/~/,"#{Mx[:gl_o]}#126#{Mx[:gl_c]}")              end -            w.gsub!(/^\<$/,'<')                                                 #escaped special character -            w.gsub!(/^\>$/,'>')                                                 #escaped special character +            w.gsub!(/^\<$/,"#{Mx[:gl_o]}#lt#{Mx[:gl_c]}")                                                 #escaped special character +            w.gsub!(/^\>$/,"#{Mx[:gl_o]}#gt#{Mx[:gl_c]}")                                                 #escaped special character              line_array << w            end            line=line_array.join(' ')            line=line.strip          end -        line.gsub!(/^(1~\??) @title\s+(?:(by\s+)?(?:@creator|@author))\s*$/,"\\1 #{@md.title} - #{@md.subtitle},<br />\\2#{@md.dc_creator}") +        line.gsub!(/~\{(.+?)\}~/m,"#{Mx[:en_a_o]}\\1#{Mx[:en_a_c]}") +        line.gsub!(/~\[(.+?)\]~/m,"#{Mx[:en_b_o]}\\1#{Mx[:en_b_c]}") +        line.gsub!(/^(#{Mx[:lv_o]}1:\??#{Mx[:lv_c]})\s*@title\s+(?:(by\s+)?(?:@creator|@author))\s*$/,"\\1 #{@md.title} - #{@md.subtitle},<br />\\2#{@md.dc_creator}")          line.gsub!(/^(1~\??) @title\s*$/,"\\1 #{@md.title} - #{@md.subtitle}")                    # -        line.gsub!(/^([23]~\??) (?:(by\s+)?(?:@creator|@author))\s*$/,"\\1 \\2#{@md.dc_creator}")                    # -        line.gsub!(/<((?:https?|file):\/\/\S+?)>/,'< \1 >')                             #catch problem markup -        line.gsub!(/\}\.\.\/(\S+)/,"\}#@output_url/\\1")                             #means you are not supporting relative links (only relevant in html), converted to static here +        line.gsub!(/^(#{Mx[:lv_o]}[23]:\??#{Mx[:lv_c]}) (?:(by\s+)?(?:@creator|@author))\s*$/,"\\1 \\2#{@md.dc_creator}")                    # +        line.gsub!(/<((?:https?|file):\/\/\S+?)>/,'< \1 >')                    #catch problem markup +        line.gsub!(/\}\.\.\/(\S+)/,"\}#@output_url/\\1")                       #means you are not supporting relative links (only relevant in html), converted to static here          line.gsub!(/<:=(\S+?)>/,'{ c_\1.png 14x14 }http://www.jus.uio.no/sisu')                                                    #adjustment 2005w30          line.gsub!(/<!(\S+)!>/,'<:\1>')                                        #escaped special character -        line.gsub!(/\\~/,'~')                                             #escaped special character -        line.gsub!(/\\\{/,'{')                                            #escaped special character -        line.gsub!(/\\\}/,'}')                                            #escaped special character -        line.gsub!(/\\\<</,'<<')                                         #escaped special character -        line.gsub!(/\\\>>/,'>>')                                         #escaped special character -        line.gsub!(/\\\</,'<')                                              #escaped special character -        line.gsub!(/\\\>/,'>')                                              #escaped special character -        line.gsub!(/\\\_/,'_')                                            #escaped special character -        line.gsub!(/\\\-/,'-')                                            #escaped special character -        line.gsub!(/\\\+/,'+')                                            #escaped special character -        line.gsub!(/\\\//,'/')                                            #escaped special character -        line.gsub!(/\\\#/,'#')                                            #escaped special character -        line.gsub!(/\\\&/,'&')                                    #&  #escaped special character -        line.gsub!(/\\\|/,'|')                                            #not really a sisu special character but made available as possibility -        line.gsub!(/\\\:/,':')                                            #not really a sisu special character but made available as possibility -        line.gsub!(/\\\!/,'!')                                            #not really a sisu special character but made available as possibility -        line.gsub!(/\\\^/,'^')                                            #not really a sisu special character but made available as possibility -        line.gsub!(/\\\,/,',')                                            #not really a sisu special character but made available as possibility +        line.gsub!(/\\~/,"#{Mx[:gl_o]}#126#{Mx[:gl_c]}")                                             #escaped special character +        line.gsub!(/\\\{/,"#{Mx[:gl_o]}#123#{Mx[:gl_c]}")                                            #escaped special character +        line.gsub!(/\\\}/,"#{Mx[:gl_o]}#125#{Mx[:gl_c]}")                                            #escaped special character +        line.gsub!(/\\\<</,"#{Mx[:gl_o]}#lt#{Mx[:gl_c]}#{Mx[:gl_o]}#lt#{Mx[:gl_c]}")                 #escaped special character +        line.gsub!(/\\\>>/,"#{Mx[:gl_o]}#gt#{Mx[:gl_c]}#{Mx[:gl_o]}#gt#{Mx[:gl_c]}")                 #escaped special character +        line.gsub!(/\\\</,"#{Mx[:gl_o]}#lt#{Mx[:gl_c]}")                                             #escaped special character +        line.gsub!(/\\\>/,"#{Mx[:gl_o]}#gt#{Mx[:gl_c]}")                                             #escaped special character +        line.gsub!(/\\\_/,"#{Mx[:gl_o]}#095#{Mx[:gl_c]}")                                            #escaped special character +        line.gsub!(/\\\-/,"#{Mx[:gl_o]}#045#{Mx[:gl_c]}")                                            #escaped special character +        line.gsub!(/\\\+/,"#{Mx[:gl_o]}#043#{Mx[:gl_c]}")                                            #escaped special character +        line.gsub!(/\\\//,"#{Mx[:gl_o]}#047#{Mx[:gl_c]}")                                            #escaped special character +        line.gsub!(/\\\#/,"#{Mx[:gl_o]}#035#{Mx[:gl_c]}")                                            #escaped special character +        line.gsub!(/\\\&/,"#{Mx[:gl_o]}#038#{Mx[:gl_c]}")                                            #& #escaped special character +        line.gsub!(/\\\|/,"#{Mx[:gl_o]}#124#{Mx[:gl_c]}")                                            #not really a sisu special character but made available as possibility +        line.gsub!(/\\\:/,"#{Mx[:gl_o]}#058#{Mx[:gl_c]}")                                            #not really a sisu special character but made available as possibility +        line.gsub!(/\\\!/,"#{Mx[:gl_o]}#033#{Mx[:gl_c]}")                                            #not really a sisu special character but made available as possibility +        line.gsub!(/\\\^/,"#{Mx[:gl_o]}#094#{Mx[:gl_c]}")                                            #not really a sisu special character but made available as possibility +        line.gsub!(/\\\,/,"#{Mx[:gl_o]}#044#{Mx[:gl_c]}")                                            #not really a sisu special character but made available as possibility          #ADD --> -        line.gsub!(/\\\\/,'\')                                            #escaped special character -        line.gsub!(/\\\*/,'*')                                            #escaped special character -        line.gsub!(/\\\!/,'!')                                            #escaped special character -        line.gsub!(/(?:^| )\*~([a-z0-9._-]+)/i,' <:name#\1>')                  #html name marker <a name="\\1"></a> -        line.gsub!(/^([56]~)(\S+)(.+)/,'\1\2 \3 <:name#\2>')                   #html name marker <a name="\\1"></a>, however at present takes you to correct position within sub-toc, will nneed to clean from sub-toc leaving in main body only -        line.gsub!(/(^| )\{~\^ (.+?)\s*\}((?:https?|file|ftp):\S+?)([;,.]?(?=\s[^~]|$))/,'\1{ \2 }\3\4 ~{ \3 }~ ') #text url endnote url shortcut {~^ [text] }http://url is { [text] }http://url ~{ http://url }~ [plus adjustment for commas] #means for this class, non-object, un-numbered ~# will not work # shortcut should not be used in conjunction with rebgular matches #reversed order, and addition of no-tilde.. -        line.gsub!(/(^| )\{~\^ (.+?)\s*\}((?:https?|file|ftp):\S+)\s+~\{(.+?)\}~/,'\1{ \2 }\3 ~{ \3 \4 }~') # watch -        line.gsub!(/<:?br>/,'<br />')                                              #xml requires -      # depreciated --> -        line.gsub!(/(^|\s+|['"]| |[\(\[\{]|\>)e\{(.+?)\}e/,'\1<b>\2</b>')     #emphasis -        line.gsub!(/(^|\s+|['"]| |[\(\[\{]|\>)b\{(.+?)\}b/,'\1<b>\2</b>')     #bold -        line.gsub!(/(^|\s+|['"]| |[\(\[\{]|\>)u\{(.+?)\}u/,'\1<u>\2</u>')     #underscore -        line.gsub!(/(^|\s+|['"]| |[\(\[\{]|\>)c\{(.+?)\}c/,'\1<cite>\2</cite>') #cite /blockquote? -        line.gsub!(/(^|\s+|['"]| |[\(\[\{]|\>)i\{(.+?)\}i/,'\1<i>\2</i>')     #italics +        line.gsub!(/\\\\/,"#{Mx[:gl_o]}#092#{Mx[:gl_c]}")                                            #escaped special character +        line.gsub!(/\\\*/,"#{Mx[:gl_o]}#042#{Mx[:gl_c]}")                                            #escaped special character +        line.gsub!(/\\\!/,"#{Mx[:gl_o]}#033#{Mx[:gl_c]}")                                            #escaped special character +        line.gsub!(/(?:^| )\*~([a-z0-9._-]+)/i," #{Mx[:mk_o]}:name#\\1#{Mx[:mk_c]}")                 #html name marker <a name="\\1"></a> +        line.gsub!(/^(#{Mx[:lv_o]}[56]:(\S+?)#{Mx[:lv_c]})\s*(.+)/,"\\1 \\3 #{Mx[:mk_o]}:name#\\2#{Mx[:mk_c]}")   #html name marker <a name="\\1"></a>, however at present takes you to correct position within sub-toc, will nneed to clean from sub-toc leaving in main body only +        line.gsub!(/(?:<:?br>|<br \/>)/,"#{Mx[:br_line]}")                     #indent used in endnotes, not implemented, replace when ready with: line.gsub!(/(?:<br>|<br \/>)\s*_([12])\s+/,'<br><:i\1> ') +        if line=~/(^|#{Mx[:gl_c]}| )\{~\^ (.+?)\s*\}((?:https?|file|ftp):\S+)\s*#{Mx[:en_a_o]}(.+?)#{Mx[:en_a_c]}/m +          line.gsub!(/(^|#{Mx[:gl_c]}| )\{~\^ ([^}]+?)\s*\}((?:https?|file|ftp):\S+)\s*#{Mx[:en_a_o]}(.+?)#{Mx[:en_a_c]}/m,"\\1{ \\2 }\\3 #{Mx[:en_a_o]} \\3 \\4 #{Mx[:en_a_c]}") # watch +        end +        if line=~/(^|#{Mx[:gl_c]}| )\{~\^ (.+?)\s*\}((?:https?|file|ftp):\S+?)([;,.]?(?=\s|$))/m +          line.gsub!(/(^|#{Mx[:gl_c]}| )\{~\^ (.+?)\s*\}((?:https?|file|ftp):\S+?)([;,.]?(?=\s|$))/m,"\\1{ \\2 }\\3\\4 #{Mx[:en_a_o]} \\3 #{Mx[:en_a_c]} ") +           #text url endnote url shortcut {~^ [text] }http://url is { [text] }http://url #{Mx[:en_a_o]} http://url #{Mx[:en_a_c]} [plus adjustment for commas] +           #means for this class, non-object, un-numbered ~# will not work # shortcut should not be used in conjunction with rebgular matches #reversed order, and addition of no-tilde.. +        end +        #line.gsub!(/(^| )\{~\^ (.+?)\s*\}((?:https?|file|ftp):\S+)\s+~\{(.+?)\}~/,'\1{ \2 }\3 ~{ \3 \4 }~') # watch +        line.gsub!(/<:?p([nb])>/,"#{Mx[:fa_o]}p\\1#{Mx[:fa_c]}")               #indent used in endnotes, not implemented, replace when ready with: line.gsub!(/(?:<br>|<br \/>)\s*_([12])\s+/,'<br><:i\1> ') +      # depreciated -->#{Mx[:fa_c]} +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[\{]|\>)e\{(.+?)\}e/,"\\1#{Mx[:fa_bold_o]}\\2#{Mx[:fa_bold_c]}")              #emphasis +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[\{]|\>)b\{(.+?)\}b/,"\\1#{Mx[:fa_bold_o]}\\2#{Mx[:fa_bold_c]}")              #bold +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[\{]|\>)u\{(.+?)\}u/,"\\1#{Mx[:fa_underscore_o]}\\2#{Mx[:fa_underscore_c]}")  #underscore +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[\{]|\>)c\{(.+?)\}c/,"\\1#{Mx[:fa_cite_o]}\\2#{Mx[:fa_c_o]}cite#{Mx[:fa_c]}") #cite /blockquote? +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[\{]|\>)i\{(.+?)\}i/,"\\1#{Mx[:fa_italics_o]}\\2#{Mx[:fa_italics_c]}")        #italics        # depreciated ^ -        line.gsub!(/(^|\s+|['"]| |[\(\[\{]|\>)!\{(.+?)\}!/,'\1<em>\2</em>')   #emphasis -        line.gsub!(/(^|\s+|['"]| |[\(\[\{]|\>)\*\{(.+?)\}\*/,'\1<b>\2</b>')   #bold -        line.gsub!(/(^|\s+|['"]| |[\(\[\{]|\>)_\{(.+?)\}_/,'\1<u>\2</u>')     #underscore -        line.gsub!(/(^|\s+|['"]| |[\(\[]|\(|\>)\/\{(.+?)\}\//,'\1<i>\2</i>')  #italics -        line.gsub!(/(^|\s+|['"]| |\(|\>)\"\{(.+?)\}\"/,'\1<cite>\2</cite>')   #cite /blockquote? -        line.gsub!(/(^|[^\\])\^\{(.+?)\}\^/,'\1<sup>\2</sup>')                     #superscript -        line.gsub!(/(^|\s+|['"]| |\(|\>|\S)9\{(.+?)\}9/,'\1<sup>\2</sup>')    #superscript -        line.gsub!(/(^|[^\\]),\{(.+?)\},/,'\1<sub>\2</sub>')                       #subscript -        line.gsub!(/(^|\s+|['"]| |\(|\>)6\{(.+?)\}6/,'\1<sub>\2</sub>')       #subscript -        line.gsub!(/(^|\s+|['"]| |\(|\>)\+\{(.+?)\}\+/,'\1<ins>\2</ins>')     #inserted text -        line.gsub!(/(^|\s+|['"]| |\(|\>)v\{(.+?)\}v/,'\1<ins>\2</ins>')       #inserted text -        line.gsub!(/(^|\s+|['"]| |\(|\>)-\{(.+?)\}-/,'\1<del>\2</del>')       #strikethrough - deleted text -        line.gsub!(/(^|\s+|['"]| |\(|\>)x\{(.+?)\}x/,'\1<del>\2</del>')       #deleted text -        line.gsub!(/(^|\s+|['"]| |\(|\>)\*(\S+?)\*/,'\1<b>\2</b>')            #bold single word, watch -        line.gsub!(/(^|\s+|['"]| |\(|\>)\!(\S+?)\!/,'\1<b>\2</b>')            #bold single word, watch -        line.gsub!(/(^|\s+|['"]| |\(|\>)\/([\(\)a-zA-Z0-9']+?)\/([^a-zA-Z0-9]|[ ,.;:'"~$]|$)/,'\1<i>\2</i>\3')     #italics single word, watch -        line.gsub!(/(^|\s+|['"]| |\(|\>)_(\S+?)_([.,!'")]?(?:\s|$))/,'\1<u>\2</u>\3')  #underscore single word, watch (made more complicated by url decoration escape tag (_url)) -        line.gsub!(/(^|\s+)-([^{]\S+?)-( |$)/,'\1<del>\2</del>\3')                 #underscore single word, watch -        line.gsub!(/(^|\s+|['"]| |\(|\>|\d+)\^(\S+?)\^/,'\1<sup>\2</sup>')    #superscript single word, watch digit added -        line.gsub!(/<[:e]\s+(.+?)!?>/,'~{ \1 }~')                                  # not tested -        line.gsub!(/^\s*_([1-9])(\*+)\s*/,'<:i\1> _* ')                             #bullets, shortcut -        line.gsub!(/^\s*_([1-9])\s+/,'<:i\1> ')                                     #indent -        line.gsub!(/(?:<br>|<br \/>)\s*_[12]\s+/,'<br> ')                          #indent used in endnotes, not implemented, replace when ready with: line.gsub!(/(?:<br>|<br \/>)\s*_([12])\s+/,'<br><:i\1> ') -        line.gsub!(/<:?br>/,'<br />')                                              #adjustment 2004w41, from # line.gsub!(/<br>/,'<br />') +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[\{]|\>)!\{(.+?)\}!/,"\\1#{Mx[:fa_bold_o]}\\2#{Mx[:fa_bold_c]}")              #emphasis +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[\{]|\>)\*\{(.+?)\}\*/,"\\1#{Mx[:fa_bold_o]}\\2#{Mx[:fa_bold_c]}")            #bold +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[\{]|\>)_\{(.+?)\}_/,"\\1#{Mx[:fa_underscore_o]}\\2#{Mx[:fa_underscore_c]}")  #underscore +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[]|\(|\>)\/\{(.+?)\}\//,"\\1#{Mx[:fa_italics_o]}\\2#{Mx[:fa_italics_c]}")     #italics +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)\"\{(.+?)\}\"/,"\\1#{Mx[:fa_cite_o]}\\2#{Mx[:fa_c_o]}cite#{Mx[:fa_c]}")     #cite /blockquote? +        line.gsub!(/(^|[^\\])\^\{(.+?)\}\^/,"\\1#{Mx[:fa_superscript_o]}\\2#{Mx[:fa_superscript_c]}")                                 #superscript +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |\(|\>|\S)9\{(.+?)\}9/,"\\1#{Mx[:fa_superscript_o]}\\2#{Mx[:fa_superscript_c]}")           #superscript +        line.gsub!(/(^|[^\\]),\{(.+?)\},/,"\\1#{Mx[:fa_subscript_o]}\\2#{Mx[:fa_subscript_c]}")                                 #subscript +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)6\{(.+?)\}6/,"\\1#{Mx[:fa_subscript_o]}\\2#{Mx[:fa_subscript_c]}")   #subscript +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)\+\{(.+?)\}\+/,"\\1#{Mx[:fa_insert_o]}\\2#{Mx[:fa_insert_c]}")              #inserted text +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)v\{(.+?)\}v/,"\\1#{Mx[:fa_insert_o]}\\2#{Mx[:fa_insert_c]}")                #inserted text +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)-\{(.+?)\}-/,"\\1#{Mx[:fa_strike_o]}\\2#{Mx[:fa_strike_c]}")                #strikethrough - deleted text +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)x\{(.+?)\}x/,"\\1#{Mx[:fa_strike_o]}\\2#{Mx[:fa_strike_c]}")                #deleted text +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)\*(\S+?)\*/,"\\1#{Mx[:fa_bold_o]}\\2#{Mx[:fa_bold_c]}")                     #bold single word, watch +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)\!(\S+?)\!/,"\\1#{Mx[:fa_bold_o]}\\2#{Mx[:fa_bold_c]}")                     #bold single word, watch +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)\/([\(\)a-zA-Z0-9']+?)\/([^a-zA-Z0-9]|[ ,.;:'"~$]|$)/,"\\1#{Mx[:fa_italics_o]}\\2#{Mx[:fa_italics_c]}\\3") #italics single word, watch +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)_(\S+?)_([.,!'")]?(?:\s|$))/,"\\1#{Mx[:fa_underscore_o]}\\2#{Mx[:fa_underscore_c]}\\3") #underscore single word, watch (made more complicated by url decoration escape tag (_url)) +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+)-([^{]\S+?)-( |$)/,"\\1#{Mx[:fa_strike_o]}\\2#{Mx[:fa_strike_c]}\\3")                                        #underscore single word, watch +        line.gsub!(/(^|#{Mx[:gl_c]}|\s+|['"]| |#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>|\d+)\^(\S+?)\^/,"\\1#{Mx[:fa_superscript_o]}\\2#{Mx[:fa_superscript_c]}") #superscript single word, watch digit added +        line.gsub!(/<[:e]\s+(.+?)!?>/,"#{Mx[:en_a_o]} \\1 #{Mx[:en_a_c]}")                                                                                     #not tested +        line.gsub!(/^\s*_\*\s*/,"#{Mx[:gl_bullet]}")                               #bullets, shortcut +        #line.gsub!(/^\s*_(\*+)\s*/,"#{Mx[:gl_bullet]}")                               #bullets, shortcut +        line.gsub!(/^\s*_([1-9])\*\s*/,"#{Mx[:pa_o]}:i\\1#{Mx[:pa_c]}#{Mx[:gl_bullet]}")                               #bullets, shortcut +        #line.gsub!(/^\s*_([1-9])(\*+)\s*/,"#{Mx[:fa_o]}:i\\1#{Mx[:fa_c]}#{Mx[:fa_o]}\\2#{Mx[:fa_c_o]}")                               #bullets, shortcut +        line.gsub!(/^\s*_([1-9])\s+/,"#{Mx[:pa_o]}:i\\1#{Mx[:pa_c]}")                                                                 #indent +        line.gsub!(/(?:<:?br>|<br \/>)/,"#{Mx[:br_line]}")                        #indent used in endnotes, not implemented, replace when ready with: line.gsub!(/(?:<br>|<br \/>)\s*_([12])\s+/,'<br><:i\1> ')          ##added          #line.gsub!(/(?:^!_\s+|^[7-9]~\s+|<:b>)(.*)?([~-]#)$/i,'<b>\1</b> \2')    #bold paragraph/emphasize #may wish to remove think about 7{ 8{ conversion not satisfactory, as information is lost! -        #line.gsub!(/(?:^!_\s+|^[7-9]~\s+|<:b>)(.*)?\s*$/i,'<b>\1</b>')            #bold paragraph/emphasize #may wish to remove think about 7{ 8{ conversion not satisfactory, as information is lost! -        #line.gsub!(/(?:(?:^| )!_ |^[7-9]~ |<:b>)(.*)\n/mi,'<b>\1</b> ')           #bold paragraph/emphasize #may wish to remove think about 7{ 8{ conversion not satisfactory, as information is lost! +        #line.gsub!(/(?:^!_\s+|^[7-9]~\s+|<:b>)(.*)?\s*$/i,'<b>\1</b>')           #bold paragraph/emphasize #may wish to remove think about 7{ 8{ conversion not satisfactory, as information is lost! +        #line.gsub!(/(?:(?:^| )!_ |^[7-9]~ |<:b>)(.*)\n/mi,'<b>\1</b> ')          #bold paragraph/emphasize #may wish to remove think about 7{ 8{ conversion not satisfactory, as information is lost!          #line.gsub!(/^_" (.*)\n/i,'<blockquote>\1</blockquote> ')                 #blockquotes #introduce KEEP -        line.gsub!(/<:hi>/,'<span style="background-color: rgb(255,240,196)">')    # bright yellow rgb(255,255,0) pale yellow rgb(255,255,200) -        line.gsub!(/<:\/hi>/,'</span>') -        line.gsub!(/(<:verse>.+)/m,"\\1\n") +        line.gsub!(/<:hi>/,"#{Mx[:fa_hilite_o]}") #'<span style="background-color: rgb(255,240,196)">')   # bright yellow rgb(255,255,0) pale yellow rgb(255,255,200) +        line.gsub!(/<:\/hi>/,"#{Mx[:fa_hilite_c]}") #'</span>') +        #line.gsub!(/<:hi>/, +        #line.gsub!(/<:\/hi>/,'</span>') +        line.gsub!(/(#{Mx[:gr_o]}verse#{Mx[:gr_c]}.+)/m,"\\1\n")          line.gsub!(/[ ]+($)/,'\1') -        if line =~/(<:(?:verse|group)>)/; line.gsub!(/(<:(?:verse|group)>)/i,"\\1\n") #cosmetic -        else line.gsub!(/(<br \/>)/i,"\\1\n") +        #line.gsub!(/\{(.+?)\}(https?:\S+)/,"#{Mx[:lnk_o]}\\1#{Mx[:lnk_c]}\\2") #linked (text or image) +        #line.gsub!(/\{(.+?)\}(image)/,"#{Mx[:lnk_o]}\\1#{Mx[:lnk_c]}\\2")      #linked image +        ##semantic +        #line.gsub!(/([a-z](?:[a-z_:.]+?[a-z])?)+(?::\{(.+?)\}:\1)/m,"\\1#{Mx[:sm_set_o]}\\2#{Mx[:sm_set_c]}\\1") +        #line.gsub!(/;\{\s*(.+?)\s*\};([a-z]+(?:[_:.][a-z]+)*)/,"#{Mx[:sm_subset_o]}\\1#{Mx[:sm_subset_c]}\\2") +        if line =~/(#{Mx[:gr_o]}(?:verse|group)#{Mx[:gr_c]})/; line.gsub!(/(#{Mx[:gr_o]}(?:verse|group)#{Mx[:gr_c]})/i,"\\1\n") #cosmetic +        else line.gsub!(/<br \/>/i,"#{Mx[:br_line]}\n")          end -      elsif line =~/^<:code(?:-end)?>|<:codeline>/ # /^<:code>/ #should be enough # underscore used as escape for angle brackets +      elsif line =~/^#{Mx[:gr_o]}code(?:-end)?#{Mx[:gr_c]}|#{Mx[:gr_o]}codeline#{Mx[:gr_c]}/ # /^<:code>/ #should be enough # underscore used as escape for angle brackets          line.gsub!(/([<>])/,'_\1')          line.gsub!(/_<:(\S+?)_>/,'<:\1>') #convert <:\S+> back, clumsy          line.gsub!(/_<(br(?: \/)?)_>/,'<\1>') #convert <br> <br /> back, clumsy -        line.gsub!(/(^|\s)<(br(?: \/)?)>([\s,.]|$)/,'\1<\2>\3') #convert <br> <br /> back, clumsy -        line.gsub!(/<:codeline>/,"\n  ") #temporary fix, prefer: #line.gsub!(/<:codeline>/,"\n") +        line.gsub!(/(^|#{Mx[:gl_c]}|\s)<(br(?: \/)?)>([\s,.]|$)/,'\1<\2>\3') #convert <br> <br /> back, clumsy +        line.gsub!(/#{Mx[:gr_o]}codeline#{Mx[:gr_c]}/,"\n  ") #temporary fix, prefer: #line.gsub!(/<:codeline>/,"\n")        else # 0~        end        line @@ -341,32 +362,32 @@ module Syntax        # +2                  <!i2!>        puts 'tech'        @data.each do |line| -        line.gsub!(/(^|\s+|['"]|[\(\[]|\>)e\{(.+?)\}e/,'\1<b>\2</b>')          #emphasis -        line.gsub!(/(^|\s+|['"]|[\(\[]|\>)b\{(.+?)\}b/,'\1<b>\2</b>')          #bold -        line.gsub!(/(^|\s+|['"]|[\(\[]|\>)u\{(.+?)\}u/,'\1<u>\2</u>')          #underscore -        line.gsub!(/(^|\s+|['"]|[\(\[]|\>)c\{(.+?)\}c/,'\1<cite>\2</cite>')    #cite -        line.gsub!(/(^|\s+|['"]|[\(\[]|\>)i\{(.+?)\}i/,'\1<i>\2</i>')          #italics -        line.gsub!(/(^|\s+|['"]|[\(\[]|\>)!\{(.+?)\}!/,'\1<em>\2</em>')        #emphasis -        line.gsub!(/(^|\s+|['"]|[\(\[]|\>)\*\{(.+?)\}\*/,'\1<b>\2</b>')        #bold -        line.gsub!(/(^|\s+|['"]|[\(\[]|\>)_\{(.+?)\}_/,'\1<u>\2</u>')          #underscore -        line.gsub!(/(^|\s+|['"]|[\(\[]|\(|\>)\/\{(.+?)\}\//,'\1<i>\2</i>')     #italics -        line.gsub!(/(^|\s+|['"]|\(|\>)\"\{(.+?)\}\"/,'\1<cite>\2</cite>') -        line.gsub!(/(^|\s+|['"]|\(|\>|\S)\^\{(.+?)\}\^/,'\1<sup>\2</sup>') -        line.gsub!(/(^|\s+|['"]|\(|\>|\S)9\{(.+?)\}9/,'\1<sup>\2</sup>') -        line.gsub!(/(^|\s+|['"]|\(|\>),\{(.+?)\},/,'\1<sub>\2</sub>') -        line.gsub!(/(^|\s+|['"]|\(|\>)6\{(.+?)\}6/,'\1<sub>\2</sub>') -        line.gsub!(/(^|\s+|['"]|\(|\>)\+\{(.+?)\}\+/,'\1<ins>\2</ins>') -        line.gsub!(/(^|\s+|['"]|\(|\>)v\{(.+?)\}v/,'\1<ins>\2</ins>') -        line.gsub!(/(^|\s+|['"]|\(|\>)-\{(.+?)\}-/,'\1<del>\2</del>') -        line.gsub!(/(^|\s+|['"]|\(|\>)x\{(.+?)\}x/,'\1<del>\2</del>') -        line.gsub!(/(^|\s+|['"]|\(|\>)\*(\S+?)\*/,'\1<b>\2</b>')               #bold single word, watch -        line.gsub!(/(^|\s+|['"]|\(|\>)\!(\S+?)\!/,'\1<b>\2</b>')               #bold single word, watch -        line.gsub!(/(^|\s+|['"]|\(|\>)\/([\(\)a-zA-Z0-9']+?)\/([ ,.;:'"~$]|[^a-zA-Z0-9])/,'\1<i>\2</i>\3')     #italics single word, watch -        line.gsub!(/(^|\s+|['"]|\(|\>)_(\S+?)_/,'\1<u>\2</u>')                 #underscore single word, watch -        line.gsub!(/(^|\s+|['"]|\(|\>|\d+)\^(\S+?)\^/,'\1<sup>\2</sup>')       #superscript single word, watch digit added -        line.gsub!(/^\s*_([1-9])(\*+)\s*/,'<:i\1> _* ') # bullets, shortcut -        line.gsub!(/^\s*_([1-9])\s+/,'<:i\1> ') -        line.gsub!(/<:?br>/,'<br />') +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[]|\>)e\{(.+?)\}e/,"\\1#{Mx[:fa_bold_o]}\\2#{Mx[:fa_bold_c]}")              #emphasis +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[]|\>)b\{(.+?)\}b/,"\\1#{Mx[:fa_bold_o]}\\2#{Mx[:fa_bold_c]}")              #bold +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[]|\>)u\{(.+?)\}u/,"\\1#{Mx[:fa_underscore_o]}\\2#{Mx[:fa_underscore_c]}")  #underscore +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[]|\>)c\{(.+?)\}c/,"\\1#{Mx[:fa_cite_o]}\\2#{Mx[:fa_c_o]}cite#{Mx[:fa_c]}") #cite +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[]|\>)i\{(.+?)\}i/,"\\1#{Mx[:fa_italics_o]}\\2#{Mx[:fa_italics_c]}")        #italics +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[]|\>)!\{(.+?)\}!/,"\\1#{Mx[:fa_bold_o]}\\2#{Mx[:fa_bold_c]}")              #emphasis +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[]|\>)\*\{(.+?)\}\*/,"\\1#{Mx[:fa_bold_o]}\\2#{Mx[:fa_bold_c]}")            #bold +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[]|\>)_\{(.+?)\}_/,"\\1#{Mx[:fa_underscore_o]}\\2#{Mx[:fa_underscore_c]}")  #underscore +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|[\(\[]|\(|\>)\/\{(.+?)\}\//,"\\1#{Mx[:fa_italics_o]}\\2#{Mx[:fa_italics_c]}")   #italics +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)\"\{(.+?)\}\"/,"\\1#{Mx[:fa_cite_o]}\\2#{Mx[:fa_c_o]}cite#{Mx[:fa_c]}") +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)\^\{(.+?)\}\^/,"\\1#{Mx[:fa_superscript_o]}\\2#{Mx[:fa_superscript_c]}") +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)9\{(.+?)\}9/,"\\1#{Mx[:fa_superscript_o]}\\2#{Mx[:fa_superscript_c]}") +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>),\{(.+?)\},/,"\\1#{Mx[:fa_subscript_o]}\\2#{Mx[:fa_subscript_c]}") +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)6\{(.+?)\}6/,"\\1#{Mx[:fa_subscript_o]}\\2#{Mx[:fa_subscript_c]}") +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)\+\{(.+?)\}\+/,"\\1#{Mx[:fa_insert_o]}\\2#{Mx[:fa_insert_c]}") +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)v\{(.+?)\}v/,"\\1#{Mx[:fa_insert_o]}\\2#{Mx[:fa_insert_c]}") +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)-\{(.+?)\}-/,"\\1#{Mx[:fa_strike_o]}\\2#{Mx[:fa_strike_c]}") +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)x\{(.+?)\}x/,"\\1#{Mx[:fa_strike_o]}\\2#{Mx[:fa_strike_c]}") +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)\*(\S+?)\*/,"\\1#{Mx[:fa_bold_o]}\\2#{Mx[:fa_bold_c]}")               #bold single word, watch +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)\!(\S+?)\!/,"\\1#{Mx[:fa_bold_o]}\\2#{Mx[:fa_bold_c]}")               #bold single word, watch +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)\/([\(\)a-zA-Z0-9']+?)\/([ ,.;:'"~$]|[^a-zA-Z0-9])/,"\\1#{Mx[:fa_italics_o]}\\2#{Mx[:fa_italics_c]}\\3")     #italics single word, watch +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)_(\S+?)_/,"\\1#{Mx[:fa_underscore_o]}\\2#{Mx[:fa_underscore_c]}")                 #underscore single word, watch +        line.gsub!(/(^|\s+|['"]|#{Mx[:fa_o_c]}|#{Mx[:fa_c]}|\(|\>)\^(\S+?)\^/,"\\1#{Mx[:fa_superscript_o]}\\2#{Mx[:fa_superscript_c]}")     #check  #superscript single word, watch digit added +        line.gsub!(/^\s*_\([1-9]\)\(\*\+\)\s*/,"#{Mx[:pa_o]}:i\\1#{Mx[:pa_c]}#{Mx[:fa_o]}\\2#{Mx[:fa_c_o]}") # bullets, shortcut +        line.gsub!(/^\s*_\([1-9]\)\s+/,"#{Mx[:pa_o]}:i\\1#{Mx[:pa_c]}") +        line.gsub!(/(?:<:?br>|<br \/>)\s*_[12]\s+/,"#{Mx[:br_line]} ")                          #indent used in endnotes, not implemented, replace when ready with: line.gsub!(/(?:<br>|<br \/>)\s*_([12])\s+/,'<br><:i\1> ')        end        @data      end diff --git a/lib/sisu/v0/db_import.rb b/lib/sisu/v0/db_import.rb index cb68ffd6..1e788f8e 100644 --- a/lib/sisu/v0/db_import.rb +++ b/lib/sisu/v0/db_import.rb @@ -138,20 +138,20 @@ module SiSU_DB_import      end      def special_character_escape(string)        string.gsub!(/'/,"''") #string.gsub!(/'/,"\047") #string.gsub!(/'/,"\\'") -      string.gsub!(/<:br>/,"<br />\n") -      string.gsub!(/<:(?:code|alt|group|verse)(?:-end)?>/,'') -      string.gsub!(/<:name#\S+?>/,'') +      string.gsub!(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,"<br />\n") +      string.gsub!(/#{Mx[:gr_o]}(?:code|alt|group|verse)(?:-end)?#{Mx[:gr_c]}/,'') +      string.gsub!(/#{Mx[:mk_o]}:name#\S+?#{Mx[:mk_c]}/,'')        string.gsub!(/\{\s*(\S+?\.(?:png|jpg))(?:\s+\d+x\d+)?(.+?)\}\S+/,'[image: \1] \2')        string.gsub!(/\{\s*(.+?)\s*\}(?:https?|file|ftp):\/\/\S+?([.,!?]?(?:\s|$))/,'\1\2')      end      def strip_markup(string) #define rules, make same as in dal clean -      string.gsub!(/<sup>(\d+)<\/sup>/,'[\1]') -      string.gsub!(/<:i[12]>/,'') +      string.gsub!(/#{Mx[:fa_superscript_o]}(\d+)#{Mx[:fa_superscript_c]}/,'[\1]') +      string.gsub!(/#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]}/,'')        string.gsub!(/(?: \\;)+/,' ') -      string.gsub!(/<!T[h]?¡.+?!>/u,"[TABLE]\n")                                 #tables -      string.gsub!(/<!¡¡\d+(.+?)!>/u,'\1')                                       #tables -      string.gsub!(/¡¡\d+¡/u,' ')                                                #tables -      string.gsub!(/¡/u,' ')                                                     #tables tidy later +      string.gsub!(/#{Mx[:gr_o]}T[h]?#{Mx[:tc_p]}.+?#{Mx[:gr_c]}/u,"[TABLE]\n")             #tables #CHECK should take whole table +      string.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}\d+(.+)#{Mx[:tc_c]}/u,'\1')         #tables +      string.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}\d+#{Mx[:tc_p]}/u,' ')                          #tables +      string.gsub!(/#{Mx[:tc_p]}/u,' ')                                                     #tables tidy later        string.gsub!(/<.+?>/,'')        string.gsub!(/\{.+?\.(?:png|jpg|gif).+?\}(?:https?|file|ftp)\\\:\S+ /,' [image] ') # else image names found in search        string.gsub!(/\s\s+/,' ') @@ -375,23 +375,30 @@ module SiSU_DB_import          @col[:en_z]=nil          dal_array.each do |data|            #data.gsub!(/<[biu]>(.+?)<\/[biu]>/,'\1')                    # remove bold, italics, underscore -          data.gsub!(/<b>(.+?)<\/b>/,'\1')                             # remove bold, italics, underscore -          data.gsub!(/<i>(.+?)<\/i>/,'\1')                             # remove bold, italics, underscore -          data.gsub!(/<u>(.+?)<\/u>/,'\1')                             # remove bold, italics, underscore -          #data.gsub!(/<:name#\S+?>/,'') +          data.gsub!(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'\1') +          #data.gsub!(/#{Mx[:fa_emphasis_o]}(.+?)#{Mx[:fa_emphaisis_c]}/,'\1') +          data.gsub!(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'\1') +          data.gsub!(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'\1') +          data.gsub!(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,'\1') +          data.gsub!(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,'\1') +          data.gsub!(/#{Mx[:fa_insert_o]}(.+?)#{Mx[:fa_insert_c]}/,'\1') +          data.gsub!(/#{Mx[:fa_cite_o]}(.+?)#{Mx[:fa_cite_c]}/,'\1') +          data.gsub!(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'\1') +          data.gsub!(/#{Mx[:gl_o]}(●)#{Mx[:gl_c]}\s*/,'\1 ') +          data.gsub!(/#{Mx[:mk_o]}:name#\S+?#{Mx[:mk_c]}/,'')            @col[:seg]=@@seg -          if data =~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}>/m                                                    # regular text +          if data =~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}#{Mx[:id_c]}/m      # regular text              notedata=data.dup -            if data[/^([123])~\s+(.+?)<~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)><([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})>/] +            if data[/^#{Mx[:lv_o]}([123]):\S*?#{Mx[:lv_c]}\s*(.+?)#{Mx[:id_o]}~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)#{Mx[:id_c]}#{Mx[:id_o]}([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})#{Mx[:id_c]}/m]                @col[:lev],txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:digest_clean],@col[:digest_all]=$1,$2,$3,$4,$5,$6,$7                @col[:lid]+=1 -              if txt =~/~[{\[][*+]?(\d+)\s+.+?[}\]]~/ +              if txt =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[*+]?(\d+)\s+.+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/                  endnotes(txt).range -                if txt =~/~\{.+?\}~/;   @en << endnotes(txt).standard +                if txt =~/#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/;   @en << endnotes(txt).standard                  end -                if txt =~/~\[\*.+?\]~/; @en_ast << endnotes(txt).asterisk +                if txt =~/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/; @en_ast << endnotes(txt).asterisk                  end -                if txt =~/~\[\+.+?\]~/; @en_pls << endnotes(txt).plus +                if txt =~/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_o]}/; @en_pls << endnotes(txt).plus                  end                  txt=endnotes(txt).clean_text                end @@ -413,7 +420,7 @@ module SiSU_DB_import                when /3/; @col[:lv3]+=1                end                @col[:lev]=@col[:plaintext]=@col[:body]='' -            elsif data[/^4~(.+?)\s+(.+?)<~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)><([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})>/] +            elsif data[/^#{Mx[:lv_o]}4:(\S*?)#{Mx[:lv_c]}\s*(.+?)#{Mx[:id_o]}~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)#{Mx[:id_c]}#{Mx[:id_o]}([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})#{Mx[:id_c]}/]                @@seg,txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:digest_clean],@col[:digest_all]=$1,$2,$3,$4,$5,$6,$7                @col[:seg]=@@seg                @col[:lv4]+=1 @@ -426,13 +433,13 @@ module SiSU_DB_import                end                @env=SiSU_Env::Info_env.new(@md.fns)                @base_url="#{@env.url.root}/#{@md.fnb}/#@hname.html" -              if txt =~/~[{\[][*+]?(\d+)\s+.+?[}\]]~/ +              if txt =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[*+]?(\d+)\s+.+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/                  endnotes(txt).range -                if txt =~ /~\{.+?\}~/;  @en << endnotes(txt).standard +                if txt =~ /#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/;  @en << endnotes(txt).standard                  end -                if txt =~/~\[\*.+?\]~/; @en_ast << endnotes(txt).asterisk +                if txt =~/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/; @en_ast << endnotes(txt).asterisk                  end -                if txt =~/~\[\+.+?\]~/; @en_pls << endnotes(txt).plus +                if txt =~/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_c]}/; @en_pls << endnotes(txt).plus                  end                  txt=endnotes(txt).clean_text(@base_url)                end @@ -449,9 +456,9 @@ module SiSU_DB_import                t=SiSU_DB_tuple::Load_documents.new(@conn,@col,@opt,@file)                t.tuple                @col[:lev]=@col[:plaintext]=@col[:body]='' -            elsif data[/^5~(?:~\S+)?(.+?)<~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)><([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})>/]                             # header lev5 seg level +            elsif data[/^#{Mx[:lv_o]}5:\S*?#{Mx[:lv_c]}\s*(.+?)#{Mx[:id_o]}~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)#{Mx[:id_c]}#{Mx[:id_o]}([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})#{Mx[:id_c]}/]                             # header lev5 seg level                txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:digest_clean],@col[:digest_all]=$1,$2,$3,$4,$5,$6 -              re=/^5~(.+?)\s+/ +              re=/^#{Mx[:lv_o]}5:(\S*?)#{Mx[:lv_c]}/                @@seg_full=re.match(data)[1] if data=~re #create?                @@seg ||='' #nil # watch                @col[:seg]=@@seg @@ -465,13 +472,13 @@ module SiSU_DB_import                end                @env=SiSU_Env::Info_env.new(@md.fns)                @base_url="#{@env.url.root}/#{@md.fnb}/#@hname.html" -              if txt =~/~[{\[][*+]?(\d+)\s+.+?[}\]]~/ +              if txt =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[*+]?(\d+)\s+.+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/                  endnotes(txt).range -                if txt =~ /~\{.+?\}~/;  @en << endnotes(txt).standard +                if txt =~ /#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/;  @en << endnotes(txt).standard                  end -                if txt =~/~\[\*.+?\]~/; @en_ast << endnotes(txt).asterisk +                if txt =~/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/; @en_ast << endnotes(txt).asterisk                  end -                if txt =~/~\[\+.+?\]~/; @en_pls << endnotes(txt).plus +                if txt =~/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_c]}/; @en_pls << endnotes(txt).plus                  end                  txt=endnotes(txt).clean_text(@base_url)                end @@ -488,9 +495,9 @@ module SiSU_DB_import                t=SiSU_DB_tuple::Load_documents.new(@conn,@col,@opt,@file)                t.tuple                @col[:lev]=@col[:plaintext]=@col[:body]='' -            elsif data[/^6~(?:~\S+)?(.+?)<~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)><([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})>/] # header lev6 seg level +            elsif data[/^#{Mx[:lv_o]}6:\S*?#{Mx[:lv_c]}\s*(.+?)#{Mx[:id_o]}~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)#{Mx[:id_c]}#{Mx[:id_o]}([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})#{Mx[:id_c]}/] # header lev6 seg level                txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:digest_clean],@col[:digest_all]=$1,$2,$3,$4,$5,$6 -              re=/^6~(.+?)\s+/ +              re=/^#{Mx[:lv_o]}6:(\S*?)#{Mx[:lv_c]}/                @@seg_full=re.match(data)[1] if data=~re #create?                @@seg ||='' #nil # watch                @col[:seg]=@@seg @@ -504,13 +511,13 @@ module SiSU_DB_import                end                @env=SiSU_Env::Info_env.new(@md.fns)                @base_url="#{@env.url.root}/#{@md.fnb}/#@hname.html" -              if txt =~/~[{\[][*+]?(\d+)\s+.+?[}\]]~/ +              if txt =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[*+]?(\d+)\s+.+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/                  endnotes(txt).range -                if txt =~ /~\{.+?\}~/;  @en << endnotes(txt).standard +                if txt =~ /#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/;  @en << endnotes(txt).standard                  end -                if txt =~/~\[\*.+?\]~/; @en_ast << endnotes(txt).asterisk +                if txt =~/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/; @en_ast << endnotes(txt).asterisk                  end -                if txt =~/~\[\+.+?\]~/; @en_pls << endnotes(txt).plus +                if txt =~/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_c]}/; @en_pls << endnotes(txt).plus                  end                  txt=endnotes(txt).clean_text(@base_url)                end @@ -530,21 +537,21 @@ module SiSU_DB_import              else                                                               #% regular text                @col[:lid]+=1                txt='' -              txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:digest_clean],@col[:digest_all]=(/(.+?)<~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)><([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})>/m).match(data).captures +              txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:digest_clean],@col[:digest_all]=(/(.+?)#{Mx[:id_o]}~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)#{Mx[:id_c]}#{Mx[:id_o]}([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})#{Mx[:id_c]}/m).match(data).captures                @hname=if @col[:seg] \                and not @col[:seg].to_s.empty? -                 @@hname=@col[:seg].to_s +                @@hname=@col[:seg].to_s                else @@hname                end                @env=SiSU_Env::Info_env.new(@md.fns)                @base_url="#{@env.url.root}/#{@md.fnb}/#@hname.html" -              if txt =~/~[{\[][*+]?(\d+)\s+.+?[}\]]~/ +              if txt =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[*+]?(\d+)\s+.+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/                  endnotes(txt).range -                if txt =~ /~\{.+?\}~/;  @en << endnotes(txt).standard +                if txt =~ /#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/;  @en << endnotes(txt).standard                  end -                if txt =~/~\[\*.+?\]~/; @en_ast << endnotes(txt).asterisk +                if txt =~/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/; @en_ast << endnotes(txt).asterisk                  end -                if txt =~/~\[\+.+?\]~/; @en_pls << endnotes(txt).plus +                if txt =~/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_c]}/; @en_pls << endnotes(txt).plus                  end                  txt=endnotes(txt).clean_text(@base_url)                end @@ -562,12 +569,10 @@ module SiSU_DB_import                end                if @en_pls[0]; @en_a_plus,@en_z_plus=@en_pls[0].first,@en_pls[0].last                end -              @col[:body]=if txt=~/<!T[h]?¡.+?!~\d+;\w\d+;\w\d+>/ #watch +              @col[:body]=if txt=~/#{Mx[:gr_o]}T[h]?#{Mx[:tc_p]}.+?#{Mx[:tc_p]}~\d+;\w\d+;\w\d+#{Mx[:gr_c]}/ #watch                  SiSU_Format_Shared::CSS_Format.new(@md,txt,@col).html_table -              elsif txt=~/<:i1>/ -                SiSU_Format_Shared::CSS_Format.new(@md,txt,@col).indent1 -              elsif txt=~/<:i2>/ -                SiSU_Format_Shared::CSS_Format.new(@md,txt,@col).indent2 +              elsif txt=~/^#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]}/ +                SiSU_Format_Shared::CSS_Format.new(@md,txt,@col).indent($1)                else                  SiSU_Format_Shared::CSS_Format.new(@md,txt,@col).norm                end @@ -580,11 +585,11 @@ module SiSU_DB_import                @col[:en_a]=@col[:en_z]=nil                @col[:lev]=@col[:plaintext]=@col[:body]=''              end -            if notedata =~ /~\{.+?\}~/                                         #% import into database endnotes tables -              endnote_array=notedata.scan(/~\{.+?\}~/) +            if notedata =~/#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/                                         #% import into database endnotes tables +              endnote_array=notedata.scan(/#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/)                endnote_array.each do |inf| -                if inf[/~\{\d+.+?<[0-9a-f]{#{@@dl}}>\}~/]                      # dal new endnotes 2003w31/1 -                  if inf[/~\{(\d+)(.+?)<([0-9a-f]{#{@@dl}})>\}~/]              # dal new endnotes 2003w31/1 +                if inf[/#{Mx[:en_a_o]}\d+.+?#{Mx[:id_o]}[0-9a-f]{#{@@dl}}#{Mx[:id_c]}#{Mx[:en_a_c]}/]                      # dal new endnotes 2003w31/1 +                  if inf[/#{Mx[:en_a_o]}(\d+)(.+?)#{Mx[:id_o]}([0-9a-f]{#{@@dl}})#{Mx[:id_c]}#{Mx[:en_a_c]}/]              # dal new endnotes 2003w31/1                      nr,txt,digest_clean=$1,$2,$3                    end                    @id_n+=1 @@ -620,11 +625,11 @@ module SiSU_DB_import                end                word_mode=notedata.scan(/\S+/)              end -            if notedata =~ /~\[\*.+?\]~/                                       #% import into database endnotes tables -              endnote_array=notedata.scan(/~\[\*.+?\]~/) +            if notedata =~/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/                                       #% import into database endnotes tables +              endnote_array=notedata.scan(/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/)                endnote_array.each do |inf| -                if inf[/~\[\*\d+.+?<[0-9a-f]{#{@@dl}}>\]~/]                    # dal new endnotes 2003w31/1 -                  if inf[/~\[[*](\d+)(.+?)<([0-9a-f]{#{@@dl}})>\]~/]           # dal new endnotes 2003w31/1 +                if inf[/#{Mx[:en_b_o]}\*\d+.+?#{Mx[:id_o]}[0-9a-f]{#{@@dl}}#{Mx[:id_c]}#{Mx[:en_b_c]}/]                    # dal new endnotes 2003w31/1 +                  if inf[/#{Mx[:en_b_o]}[*](\d+)(.+?)#{Mx[:id_o]}([0-9a-f]{#{@@dl}})#{Mx[:id_c]}#{Mx[:en_b_c]}/]           # dal new endnotes 2003w31/1                      nr,txt,digest_clean=$1,$2,$3                    end                    @id_n+=1 @@ -661,11 +666,11 @@ module SiSU_DB_import                end                word_mode=notedata.scan(/\S+/)              end -            if notedata =~ /~\[\+.+?\]~/                                           #% import into database endnotes tables -              endnote_array=notedata.scan(/~\[\+.+?\]~/) +            if notedata =~/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_c]}/                                           #% import into database endnotes tables +              endnote_array=notedata.scan(/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_c]}/)                endnote_array.each do |inf| -                if inf[/~\[\+\d+.+?<[0-9a-f]{#{@@dl}}>\]~/]                        # dal new endnotes 2003w31/1 -                  if inf[/~\[[+](\d+)(.+?)<([0-9a-f]{#{@@dl}})>\]~/]               # dal new endnotes 2003w31/1 +                if inf[/#{Mx[:en_b_o]}\+\d+.+?#{Mx[:id_o]}[0-9a-f]{#{@@dl}}#{Mx[:id_c]}#{Mx[:en_b_c]}/]                        # dal new endnotes 2003w31/1 +                  if inf[/#{Mx[:en_b_o]}[+](\d+)(.+?)#{Mx[:id_o]}([0-9a-f]{#{@@dl}})#{Mx[:id_c]}#{Mx[:en_b_c]}/]               # dal new endnotes 2003w31/1                      nr,txt,digest_clean=$1,$2,$3                    end                    @id_n+=1 @@ -710,38 +715,38 @@ module SiSU_DB_import      def endnotes(txt)        @txt=txt        def standard -        x=if @txt =~ /~\{.+?\}~/; @txt.scan(/~\{(\d+).+?\}~/) +        x=if @txt =~/#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/; @txt.scan(/#{Mx[:en_a_o]}(\d+).+?#{Mx[:en_a_c]}/)          else nil          end        end        def asterisk -        x=if @txt =~/~\[\*.+?\]~/; @txt.scan(/~\[[*](\d+).+?\]~/) +        x=if @txt =~/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/; @txt.scan(/#{Mx[:en_b_o]}[*](\d+).+?#{Mx[:en_b_c]}/)          else nil          end        end        def plus -        x=if @txt =~/~\[\+.+?\]~/; @txt.scan(/~\[[+](\d+).+?\]~/) +        x=if @txt =~/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_c]}/; @txt.scan(/#{Mx[:en_b_o]}[+](\d+).+?#{Mx[:en_b_c]}/)          else nil          end        end        def clean_text(base_url=nil)          if base_url -          @txt.gsub!(/~\{(\d+).+?\}~/,%{<sup><a href="#{base_url}#_\\1" name="-\\1">\\1</a></sup>}) -          @txt.gsub!(/~\[([*]\d+).+?\]~/,%{<sup><a href="#{base_url}#_\\1" name="-\\1">\\1</a></sup>}) -          @txt.gsub!(/~\[([+]\d+).+?\]~/,%{<sup><a href="#{base_url}#_\\1" name="-\\1">\\1</a></sup>}) +          @txt.gsub!(/#{Mx[:en_a_o]}(\d+).+?#{Mx[:en_a_c]}/,%{<sup><a href="#{base_url}#_\\1" name="-\\1">\\1</a></sup>}) +          @txt.gsub!(/#{Mx[:en_b_o]}([*]\d+).+?#{Mx[:en_b_c]}/,%{<sup><a href="#{base_url}#_\\1" name="-\\1">\\1</a></sup>}) +          @txt.gsub!(/#{Mx[:en_b_o]}([+]\d+).+?#{Mx[:en_b_c]}/,%{<sup><a href="#{base_url}#_\\1" name="-\\1">\\1</a></sup>})          else -          @txt.gsub!(/~\{(\d+).+?\}~/,'<sup>\1</sup>') -          @txt.gsub!(/~\[([*]\d+).+?\]~/,'<sup>\1</sup>') -          @txt.gsub!(/~\[([+]\d+).+?\]~/,'<sup>\1</sup>') +          @txt.gsub!(/#{Mx[:en_a_o]}(\d+).+?#{Mx[:en_a_c]}/,'<sup>\1</sup>') +          @txt.gsub!(/#{Mx[:en_b_o]}([*]\d+).+?#{Mx[:en_b_c]}/,'<sup>\1</sup>') +          @txt.gsub!(/#{Mx[:en_b_o]}([+]\d+).+?#{Mx[:en_b_c]}/,'<sup>\1</sup>')          end          @txt        end        def range          @col[:en_a]=@col[:en_z]=nil -        if @txt =~ /~\{.+?\}~|~\[([*]\d+).+?\]~|~\[([+]\d+).+?\]~/ +        if @txt =~/#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}|#{Mx[:en_b_o]}([*]\d+).+?#{Mx[:en_b_c]}|#{Mx[:en_b_o]}([+]\d+).+?#{Mx[:en_b_c]}/            word_array=@txt.scan(/\S+/)            word_array.each do |w| -            if w[/~[{\[][*+]?(\d+)\s+.+?[}\]]~/]                                                # not tested since change 2003w31 +            if w[/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[*+]?(\d+)\s+.+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/]                                                # not tested since change 2003w31                @col[:en_a]=$1 unless @col[:en_a]                @col[:en_z]=@col[:en_a].dup unless @col[:en_a]                @col[:en_z]=$1 if @col[:en_a] diff --git a/lib/sisu/v0/defaults.rb b/lib/sisu/v0/defaults.rb index 5ea3de65..4129893a 100644 --- a/lib/sisu/v0/defaults.rb +++ b/lib/sisu/v0/defaults.rb @@ -151,6 +151,193 @@ module SiSU_Viz      end      def js_old      end +    def semantic_tags +      def default +          #:f =>       'firstname', +          #:m =>       'middlename', +          #:l =>       'lastname', +          #:ed =>      'editor', #editor? +          #:v =>       'version', #edition +        { +          :pub =>     'publication', +          :conv =>    'convention', +          :vol =>     'volume', +          :pg =>      'page', +          :cty =>     'city', +          :org =>     'organization', +          :uni =>     'university', +          :dept =>    'department', +          :fac =>     'faculty', +          :inst =>    'institute', +          :co =>      'company', +          :com =>     'company', +          :conv =>    'convention', +          :dt =>      'date', +          :y =>       'year', +          :m =>       'month', +          :d =>       'day', +          :ti =>      'title', +          :au =>      'author', +          :ed =>      'editor', #editor? +          :v =>       'version', #edition +          :n =>       'name', +          :fn =>      'firstname', +          :mn =>      'middlename', +          :ln =>      'lastname', +          :in =>      'initials', +          :qt =>      'quote', +          :ct =>      'cite', +          :ref =>     'reference', +          :ab =>      'abreviation', +          :def =>     'define', +          :desc =>    'description', +          :trans =>   'translate', +        } +      end +      self +    end +    #% decorate +    def decorate_italics +      'title|article|book|journal' +    end +    def decorate_bold +    end +    def decorate_uppercase +      'surname' +    end +    #% semantic +    def sem_title #dc 1 +      'title' +    end +    def sem_article +      'article' +    end +    def sem_book +      'book' +    end +    def sem_journal +      'journal' +    end +    def sem_fullname # (contains: firstname, surname) #issues arise as contains surname etc. +      'fullname' +    end +    def sem_first +      'first' +    end +    def sem_surname +      'surname' +    end +    def sem_middle +      'middle' +    end +    def sem_creator #dc 2 # == fullname (contains: firstname, surname) +      'creator' +    end +    def sem_author # == fullname (contains: firstname, surname) +      'author' +    end +    def sem_editor # == fullname (contains: firstname, surname) +      'editor' +    end +    def sem_illustrator # == fullname (contains: firstname, surname) +      'illustrator' +    end +    def sem_translator # == fullname (contains: firstname, surname) +      'translator' +    end +    def sem_isbn # 10 or 13 +      'isbn' +    end +    def sem_isbn_10 +      'isbn10' +    end +    def sem_isbn_13 +      'isbn13' +    end +    def sem_loc # library of congress +      'loc' +    end +    def sem_dewey +      'dewey' +    end +    def sem_pg # project gutenberg number +      'pg' +    end +    def sem_subject #dc 3 +      'subject' +    end +    def sem_date #dc 7 +      'date' +    end +    def sem_date_created +      'date_created' +    end +    def sem_date_issued +      'date_issued' +    end +    def sem_date_available +      'date_available' +    end +    def sem_date_valid +      'date_valid' +    end +    def sem_date_modified +      'date_modified' +    end +    def sem_type #dc 8 +      'type' +    end +    def sem_description #dc 4 +      'description' +    end +    def sem_publisher #dc 5 +      'publisher' +    end +    def sem_contributor #dc 6 +      'contributor' +    end +    def sem_format #dc 9 +      'format' +    end +    def sem_identifier #dc 10 +      'identifier' +    end +    def sem_source #dc 11 +      'source' +    end +    def sem_language #dc 12 +      'language' +    end +    def sem_relation #dc 13 +      'source' +    end +    def sem_coverage #dc 14 +      'coverage' +    end +    def sem_rights #dc 15 +      'rights' +    end +    def sem_copyright +      'copyright' +    end +    def sem_license +      'license' +    end +    def sem_prepared_by +      'prepared_by' +    end +    def sem_digitized_by +      'digitized_by' +    end +    def sem_keywords +      'keywords' +    end +    def sem_comments +      'comments' +    end +    def sem_abstract +      'abstract' +    end      #% path      def path_stylesheet_home        %{  <link rel="stylesheet" href="./#{@dir.path.style}/homepage.css" type="text/css" />} diff --git a/lib/sisu/v0/digests.rb b/lib/sisu/v0/digests.rb index 0c859010..9510a12a 100644 --- a/lib/sisu/v0/digests.rb +++ b/lib/sisu/v0/digests.rb @@ -150,11 +150,14 @@ module SiSU_Digest_view          data.each do |para|            x=nil            y,para_endnotes=[],[] -          if para =~/<~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)><([0-9a-f]{#@dl}):([0-9a-f]{#@dl})>/ +          if para =~/#{Mx[:id_o]}~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)#{Mx[:id_c]}#{Mx[:id_o]}([0-9a-f]{#@dl}):([0-9a-f]{#@dl})#{Mx[:id_c]}/              ocn,h1,h2,d_clean,d_all=$1,$2,$3,$4,$5              @ocn=ocn unless ocn.to_i == 0 -            if para=~/~\{[\d*+]+.+?<[0-9a-f]{#@dl}>\}~/ -              para_endnotes << para.scan(/~[{\[]([\d*+]+).+?<([0-9a-f]{#@dl})>[}\]]~/) +            para.gsub!(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'<b>\1</b>') +            para.gsub!(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'<i>\1</i>') +            para.gsub!(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'<u>\1</u>') +            if para=~/#{Mx[:en_a_o]}[\d*+]+.+?#{Mx[:id_o]}[0-9a-f]{#@dl}#{Mx[:id_c]}#{Mx[:en_a_c]}/ +              para_endnotes << para.scan(/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})([\d*+]+).+?#{Mx[:id_o]}([0-9a-f]{#@dl})#{Mx[:id_c]}(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/)              end              ima=[]              if para !~/^%+\s/ \ @@ -163,21 +166,21 @@ module SiSU_Digest_view              else image=nil              end              x=case para -            when /^0~title/ +            when /^#{Mx[:meta_o]}title#{Mx[:meta_c]}/                "\n" + '  '*0 +'@' + '  '*9 -            when /^0~subtitle/ +            when /^#{Mx[:meta_o]}subtitle#{Mx[:meta_c]}/                "\n" + '  '*1 +'@' + '  '*8 -            when /^1~/ +            when /^#{Mx[:lv_o]}1:/                "\n" + '  '*2 +':A ' + '  '*6 +'- ' + ocn + ' '*(10-ocn.length) + d_clean + ' ' + d_all -            when /^2~/ +            when /^#{Mx[:lv_o]}2:/                "\n" + '  '*3 +':B ' + '  '*5 +'- ' + ocn + ' '*(10-ocn.length) + d_clean + ' ' + d_all -            when /^3~/ +            when /^#{Mx[:lv_o]}3:/                "\n" + '  '*4 +':C ' + '  '*4 +'- ' + ocn + ' '*(10-ocn.length) + d_clean + ' ' + d_all -            when /^4~/ +            when /^#{Mx[:lv_o]}4:/                "\n" + '  '*5 +'1' + '  '*4 +'- ' + ocn + ' '*(10-ocn.length) + d_clean + ' ' + d_all -            when /^5~/ +            when /^#{Mx[:lv_o]}5:/                "\n" + '  '*6 +'2' + '  '*3 +'- ' + ocn + ' '*(10-ocn.length) + d_clean + ' ' + d_all -            when /^6~/ +            when /^#{Mx[:lv_o]}6:/                "\n" + '  '*7 +'3' + '  '*2 +'- ' + ocn + ' '*(10-ocn.length) + d_clean + ' ' + d_all              else                if para =~/MD5\(\S+?\.sst\)=\s*<u>([0-9a-f]{#@dl})<\/u>/                                        #watch @@ -248,20 +251,20 @@ module SiSU_Digest_view                  m_ruby_version=rgx_txt(@tr.ruby_version)                  case para                  when /#{m_dc_title}: / -                  @t=/#{m_dc_title}: (.+?)<~\d;(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#@dl}:[0-9a-f]{#@dl}>/.match(para)[1].gsub(/<\/?u>/,'').strip +                  @t=/#{m_dc_title}: (.+?)#{Mx[:id_o]}~\d;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#@dl}:[0-9a-f]{#@dl}#{Mx[:id_c]}/.match(para)[1].gsub(/<\/?u>/,'').strip                  when /#{m_creator}: / -                  @c=/#{m_creator}: (.+?)<~\d;(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#@dl}:[0-9a-f]{#@dl}>/.match(para)[1].gsub(/<\/?u>/,'').strip +                  @c=/#{m_creator}: (.+?)#{Mx[:id_o]}~\d;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#@dl}:[0-9a-f]{#@dl}#{Mx[:id_c]}/.match(para)[1].gsub(/<\/?u>/,'').strip                  when /#{m_sourcefile_digest}.+?<u>/                                        #watch                    dgst_extra="\n" + ' '*21 +'source' +' '*4 + @md.dgst[1] + ' '*34 + @md.fns                  when /Skin_Digest: /                    dgst_extra="\n" + ' '*21 + 'skin' +' '*6 + @md.dgst_skin[1] + ' '*34 + /(skin_\S+?\.rb)/.match(@md.dgst_skin[0])[1]                  when /#{m_sisu_version}: / -                  @v=/#{m_sisu_version}: (.+?)<~\d;(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#@dl}:[0-9a-f]{#@dl}>/.match(para)[1].gsub(/<\/?u>/,'').strip +                  @v=/#{m_sisu_version}: (.+?)#{Mx[:id_o]}~\d;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#@dl}:[0-9a-f]{#@dl}#{Mx[:id_c]}/.match(para)[1].gsub(/<\/?u>/,'').strip                  when /#{m_last_generated}: / -                  @g=/#{m_last_generated}: (.+?)<~\d;(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#@dl}:[0-9a-f]{#@dl}>/.match(para)[1].gsub(/<\/?u>/,'').strip +                  @g=/#{m_last_generated}: (.+?)#{Mx[:id_o]}~\d;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#@dl}:[0-9a-f]{#@dl}#{Mx[:id_c]}/.match(para)[1].gsub(/<\/?u>/,'').strip   #                                                   'doc last generated'                  when /#{m_ruby_version}: / -                  @r=/#{m_ruby_version}: (.+?)<~\d;(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#@dl}:[0-9a-f]{#@dl}>/.match(para)[1].gsub(/<\/?u>/,'').strip +                  @r=/#{m_ruby_version}: (.+?)#{Mx[:id_o]}~\d;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#@dl}:[0-9a-f]{#@dl}#{Mx[:id_c]}/.match(para)[1].gsub(/<\/?u>/,'').strip                  end                  dgst_extra ||=''                  "\n" + prefix +' - ' + ocn + ' '*(10-ocn.length) + d_clean + ' ' + d_all + dgst_extra + "\n" @@ -306,27 +309,27 @@ module SiSU_Digest_view          ocn,endnotes=nil,nil          data.each do |para|            x=case para -          when /^0~/; l[0] +=1 -            if para =~/^0~title/; '' #'  '*0 +'@ == headers' + "\n" + '  '*0 +'headings:' +          when /^#{Mx[:meta_o]}/; l[0] +=1 +            if para =~/^#{Mx[:meta_o]}title#{Mx[:meta_c]}/; '' #'  '*0 +'@ == headers' + "\n" + '  '*0 +'headings:'              end -          when /^1~/; l[1] +=1 +          when /^#{Mx[:lv_o]}1:/; l[1] +=1              '  '*0 +':A' -          when /^2~/; l[2] +=1 +          when /^#{Mx[:lv_o]}2:/; l[2] +=1              '  '*1 +':B' -          when /^3~/; l[3] +=1 +          when /^#{Mx[:lv_o]}3:/; l[3] +=1              '  '*2 +':C' -          when /^4~/; l[4] +=1 +          when /^#{Mx[:lv_o]}4:/; l[4] +=1              '  '*3 +'1' -          when /^5~/; l[5] +=1 +          when /^#{Mx[:lv_o]}5:/; l[5] +=1              '  '*4 +'2' -          when /^6~/; l[6] +=1 +          when /^#{Mx[:lv_o]}6:/; l[6] +=1              '  '*5 +'3'            else nil            end -          if para =~/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#@dl}:[0-9a-f]{#@dl}>/ +          if para =~/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#@dl}:[0-9a-f]{#@dl}#{Mx[:id_c]}/              ocn=$1 unless $1.to_i == 0            end -          if para =~/~[{\[]([\d*+]+).+?<[0-9a-f]{#@dl}>[}\]]~/ +          if para =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})([\d*+]+).+?#{Mx[:id_o]}[0-9a-f]{#@dl}#{Mx[:id_c]}(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/              endnotes=$1 unless $1.to_i == 0            end            dal_structure_tree("#{x}\n") if x and not x.empty? diff --git a/lib/sisu/v0/help.rb b/lib/sisu/v0/help.rb index acbae57b..22736aac 100644 --- a/lib/sisu/v0/help.rb +++ b/lib/sisu/v0/help.rb @@ -1425,7 +1425,7 @@ WOK        sudo ruby ./sisu-install setup      if rant is installed on your system you may instead run:        sudo rant base -  +      for further options:        ./sisu-install -T diff --git a/lib/sisu/v0/html.rb b/lib/sisu/v0/html.rb index 208b7409..5b9639dd 100644 --- a/lib/sisu/v0/html.rb +++ b/lib/sisu/v0/html.rb @@ -75,6 +75,7 @@ module SiSU_HTML    require "#{SiSU_lib}/html_tune"    include SiSU_Tune    require "#{SiSU_lib}/shared_xml" +  require "#{SiSU_lib}/shared_structure"    class Source      def initialize(opt)        @opt=opt @@ -180,52 +181,7 @@ module SiSU_HTML          @tuned_file_array        end      end -    class Split_text_object -      include SiSU_Viz -      include SiSU_HTML_Format_type -      @@dp=nil -      attr_reader :format,:text,:ocn,:scroll_lev_para_ocn,:seg_lev_para_ocn -      def initialize(md,para) -        @md,@para=md,para -        @format,@ocn='null','null' -        #@format,@ocn=nil,nil -        @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -      end -      def lev_segname_para_ocn                                                   #needs work 2003w29 -        if @para =~/^\d~.+?<~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ -          if @para[/^([1-6])~(\S+)\s+(\S.+?)<~(\d+);(?:[ohmu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m] -            @format,segname,@text,@ocn=$1,$2,$3,$4 -            @format="#@format~#{segname}" # -          elsif @para[/^([1-6]~)\s+(\S.+?)<~(\d+);(?:[ohmu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m] -            @format,@text,@ocn=$1,$2,$3 -          end -        else -          if @para[/^(?:<:i([1-9])>\s*_\*)\s+(.+?)<~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m] -            @format,@text,@ocn="_#{$1}\*",$2,$3,$4 -          elsif @para[/^(_\*)\s+(.+?)<~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m] -            @format,@text,@ocn=$1,$2,$3 -          elsif  @para[/<:(i[1-9])>\s*(.+?)<~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m] -            @format,@text,@ocn=$1,$2,$3 -          elsif @para[/<:(code|alt|verse|group)>(.+?)<~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m] -            @format,@text,@ocn=$1,$2,$3 -          elsif @para[/(.+?)<~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m] -            @text,@ocn=$1,$2 #,$3 -          end -          if @para !~/<~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$|^$/ #added 2002w06 -            @text=@para[/(.+?)/m,1] -          end -          if @para[/^(\d)~\S*\s+(.+)/m] -            @format,@text=$1,$2 -          end -        end -        @seg_lev_para_ocn=if @para[/.+<~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/] -          SiSU_HTML_Format_type::Format_seg.new(@md,@format,@text,@ocn) -        end -        @scroll_lev_para_ocn=if @para[/.+<~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/] -          SiSU_HTML_Format_type::Format_scroll.new(@md,@format,@text,@ocn) -        end -        self -      end +    class Split_text_object <SiSU_Structure::Split_text_object      end      class Links_guide        @links_guide_toc=[] @@ -266,18 +222,18 @@ module SiSU_HTML          @scr_endnotes << format_head_scroll.title_endnote          @data.each do |para|            pg=para.dup -          unless pg =~/^<:code>/ -            if pg =~/~[{\[][\d*+]+ <a name="_[\d*+]+"/ \ -            and not pg =~/^<:code>/ -              endnote_array=[] -              if pg=~/~\{[\d*+].+?\}\~/m -                endnote_array << pg.scan(/~\{[\d*+]+(.+?)\}\~/m) +          unless pg =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/ +            if pg =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[\d*+]+ <a name="_[\d*+]+"/ \ +            and not pg =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/ +              endnote_array=[] #(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]}) +              if pg=~/#{Mx[:en_a_o]}[\d*+].+?#{Mx[:en_a_c]}/m +                endnote_array << pg.scan(/#{Mx[:en_a_o]}[\d*+]+(.+?)#{Mx[:en_a_c]}/m)                end -              if pg=~/~\[[\d*]+\s.+?\]\~/m -                endnote_array << pg.scan(/~\[[\d*]+(.+?)\]\~/m) +              if pg=~/#{Mx[:en_b_o]}[\d*]+\s.+?#{Mx[:en_b_c]}/m +                endnote_array << pg.scan(/#{Mx[:en_b_o]}[\d*]+(.+?)#{Mx[:en_b_c]}/m)                end -              if pg=~/~\[[\d+]+\s.+?\]\~/m -                endnote_array << pg.scan(/~\[[\d+]+(.+?)\]\~/m) +              if pg=~/#{Mx[:en_b_o]}[\d+]+\s.+?#{Mx[:en_b_c]}/m +                endnote_array << pg.scan(/#{Mx[:en_b_o]}[\d+]+(.+?)#{Mx[:en_b_c]}/m)                end                endnote_array.flatten.each do |note|                  format_scroll=SiSU_HTML_Format_type::Format_scroll.new(@md,note) @@ -297,7 +253,7 @@ module SiSU_HTML          @data,@md=data,md          @vz=SiSU_Env::Get_init.instance.skin          @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -        @pat_heading=/^(?:[1-6]~\S*)?(.*)<~(\d+);(?:[hm]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +        @pat_heading=/^(?:#{Mx[:lv_o]}[1-6]:\S*?#{Mx[:lv_c]}\s*)?(.*)#{Mx[:id_o]}~(\d+);(?:[hm]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/          @pat_strip_heading_name=/<a name="h?\d.*?">(.+?)<\/a>/          @tell=SiSU_Screen::Ansi.new(@md.cmd)        end @@ -306,22 +262,22 @@ module SiSU_HTML          toc=nil          @@firstseg=nil          @data.each do |para| -          if para =~/^([1-6]~|4~!)/ +          if para =~/^(?:#{Mx[:lv_o]}[1-6]:|4~!)/              para_toc=para.dup -            para_toc.gsub!(/ <a name="-[\d*+]+" href="#_[\d*+]+"> <sup>[\d*+]+<\/sup> <\/a>\s+~[{\[].+?[}\]]~/m,'') #remove endnotes from toc +            para_toc.gsub!(/ <a name="-[\d*+]+" href="#_[\d*+]+"> <sup>[\d*+]+<\/sup> <\/a>\s*(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]}).+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/m,'') #remove endnotes from toc              toc=case para_toc -            when /^\s*1~(\S+)?/; Toc.new(para_toc,@md).level_1 -            when /^\s*2~(\S+)?/; Toc.new(para_toc,@md).level_2 -            when /^\s*3~(\S+)?/; Toc.new(para_toc,@md).level_3 -            when /^\s*4~(\S+)?/; Toc.new(para_toc,@md).level_4 -            when /^\s*5~(\S+)?/; Toc.new(para_toc,@md).level_5 -            when /^\s*6~(\S+)?/; Toc.new(para_toc,@md).level_6 +            when /^\s*#{Mx[:lv_o]}1:\S*/; Toc.new(para_toc,@md).level_1 +            when /^\s*#{Mx[:lv_o]}2:\S*/; Toc.new(para_toc,@md).level_2 +            when /^\s*#{Mx[:lv_o]}3:\S*/; Toc.new(para_toc,@md).level_3 +            when /^\s*#{Mx[:lv_o]}4:\S+/; Toc.new(para_toc,@md).level_4 +            when /^\s*#{Mx[:lv_o]}5:\S*/; Toc.new(para_toc,@md).level_5 +            when /^\s*#{Mx[:lv_o]}6:\S*/; Toc.new(para_toc,@md).level_6              when /^\s*4~!/;      Toc.new(para_toc).level_crosslink              else              end              if @@firstseg.nil? \ -            and para=~/^4~\S+?/ -              @@firstseg=/^4~(\S+)?/.match(para)[1] +            and para=~/^#{Mx[:lv_o]}4:\S+?#{Mx[:lv_c]}/ +              @@firstseg=/^#{Mx[:lv_o]}4:(\S+?)#{Mx[:lv_c]}/.match(para)[1]              end              if toc                begin @@ -374,11 +330,11 @@ WOK        end        def level_1          para=@data -        unless para =~/<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +        unless para =~/#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/            para.gsub!(@pat_strip_heading_name,'\1')          end          para[@pat_heading] -        linkname,link=$1,$2 if $& +        linkname,link=$1.strip,$2 if $&            if link \            and link !~/#/ #% keep eye on link              p_num=SiSU_HTML_Format_type::Paragraph_number.new(@md,link) @@ -390,26 +346,26 @@ WOK          end          toc={}          format_toc=SiSU_HTML_Format_type::Format_toc.new(@md,title) -        toc[:seg]=if para =~/^\d~meta\s+Document Information/ +        toc[:seg]=if para =~/^#{Mx[:lv_o]}\d:meta^#{Mx[:lv_c]}\s*Document Information/            format_toc.lev0          else format_toc.lev1          end -        title=if para =~/(<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)$/ +        title=if para =~/(#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]})$/            m=/#{$1}/            para.gsub!(m,'') -          if para=~/^\d~meta\s+Document Information/ +          if para=~/^#{Mx[:lv_o]}\d:meta#{Mx[:lv_c]}\s*Document Information/              %{<a href="#docinfo">#{linkname}</a>}            else linkname            end          else            @@toc[:scr] <<  '<br />' -          link=if para =~/<~[1-9];([0-6]):\d+;\w\d+><#@dp:#@dp>$/; $1 +          link=if para =~/#{Mx[:id_o]}~[1-9];([0-6]):\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/; $1            else ''            end            %{<b><a href="##{link}">#{linkname}</a></b>}          end          format_toc=SiSU_HTML_Format_type::Format_toc.new(@md,title) -        toc[:scr]=if para =~/^\d~meta\s+Document Information/ +        toc[:scr]=if para =~/^#{Mx[:lv_o]}\d:meta^#{Mx[:lv_c]}\s*Document Information/            format_toc.lev0          else format_toc.lev1          end @@ -417,11 +373,11 @@ WOK        end        def level_2          para=@data -        unless para =~/<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +        unless para =~/#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/            para.gsub!(@pat_strip_heading_name,'\1')          end          para[@pat_heading] -        linkname,link=$1,$2 if $& +        linkname,link=$1.strip,$2 if $&          if link \          and link !~/#/            p_num=SiSU_HTML_Format_type::Paragraph_number.new(@md,link) @@ -429,7 +385,7 @@ WOK          format_toc=SiSU_HTML_Format_type::Format_toc.new(@md,linkname)          toc={}          toc[:seg]=format_toc.lev2 -        if para =~/(<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)$/ +        if para =~/(#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]})$/            m=/#{$1}/            para.gsub!(m,'')            title=linkname @@ -444,7 +400,7 @@ WOK          para.gsub!(@pat_strip_heading_name,'\1')          para.gsub(/(.*?)<a name="(\d+)"><\/a>(.*)/,'\1') #2002w42 altered gsub! - problematic? - suspect          para[@pat_heading] -        linkname,link=$1,$2 if $& +        linkname,link=$1.strip,$2 if $&          if link \          and link !~/#/            p_num=SiSU_HTML_Format_type::Paragraph_number.new(@md,link) @@ -452,7 +408,7 @@ WOK          format_toc=SiSU_HTML_Format_type::Format_toc.new(@md,linkname)          toc={}          toc[:seg]=format_toc.lev3 -        if para =~/(<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)$/ +        if para =~/(#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]})$/            m=/#{$1}/            para.gsub!(m,'')            title=linkname @@ -465,19 +421,19 @@ WOK        def level_4          para=@data          unless para =~/~metadata/ -          unless para =~/<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +          unless para =~/#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/              para.gsub!(@pat_strip_heading_name,'\1')              para[@pat_heading] -            linkname,link=$1,$2 if $& +            linkname,link=$1.strip,$2 if $&              p_num=SiSU_HTML_Format_type::Paragraph_number.new(@md,link) if link            end -          para.gsub!(/<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/,'') -          if para =~/^4~/ -            seg_link=para.gsub(/^\s*4~(\S+)\s+(.+?)$/, +          para.gsub!(/#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/,'') +          if para =~/^#{Mx[:lv_o]}4:/ +            seg_link=para.gsub(/^\s*#{Mx[:lv_o]}4:(\S+?)#{Mx[:lv_c]}\s*(.+?)$/,                %{  <a href="#{@md.fnl[:pre]}\\1#{@md.fnl[:mid]}#{@md.sfx}#{@md.fnl[:post]}" target="_top">      \\2    </a> }) -            @@seg_url=para[/^4~(\S+).+?$/,1] +            @@seg_url=para[/^#{Mx[:lv_o]}4:(\S+?)#{Mx[:lv_c]}.+?$/,1]            elsif para =~/\d+.\d+.\d+.\d+|\d+.\d+.\d+|\d+.\d+|\d+/              seg_link=para.gsub(/^\s*(#{@md.lv4}\s+)\s*(\d+.\d+.\d+.\d+|\d+.\d+.\d+|\d+.\d+|\d+)(.*)/,                %{<a href="#{@md.fnl[:pre]}\\2#{@md.fnl[:mid]}#{@md.sfx}#{@md.fnl[:post]}" } + @@ -487,7 +443,7 @@ WOK            format_toc=SiSU_HTML_Format_type::Format_toc.new(@md,seg_link)            toc={}            toc[:seg]=format_toc.lev4 -          if para =~/<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +          if para =~/#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/              m=/#{$1}/              para.gsub!(m,'')              title=linkname @@ -500,17 +456,17 @@ WOK        end        def level_5          para=@data -        if para !~/<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +        if para !~/#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/            para.gsub!(@pat_strip_heading_name,'\1')          end          para[@pat_heading] -        linkname,link=$1,$2 if $& +        linkname,link=$1.strip,$2 if $&          if link \          and link !~/#/            p_num=SiSU_HTML_Format_type::Paragraph_number.new(@md,link)          end          toc={} -        if para =~/<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +        if para =~/#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/            m=/#{$1}/            para.gsub!(m,'')            title=linkname @@ -528,17 +484,17 @@ WOK        end        def level_6          para=@data -        if para !~/<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +        if para !~/#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/            para.gsub!(@pat_strip_heading_name,'\1')          end          para[@pat_heading] -        linkname,link=$1,$2 if $& +        linkname,link=$1.strip,$2 if $&          if link \          and link !~/#/            p_num=SiSU_HTML_Format_type::Paragraph_number.new(@md,link)          end          toc={} -        if para =~/<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +        if para =~/#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/            m=/#{$1}/            para.gsub!(m,'')            title=linkname @@ -671,7 +627,7 @@ WOK        def publish          scroll=[]          hr='<center><hr width=90% /></center>' -        scroll << @scr_toc << hr << @scr_body << hr << @scr_endnotes << hr << @scr_metadata << @scr_owner_details << @scr_tails +        scroll << @scr_toc << hr << @scr_body << @scr_endnotes << hr << @scr_metadata << @scr_owner_details << @scr_tails          scroll.flatten!.compact!        end      end @@ -690,6 +646,7 @@ WOK            @data.each do |para|              para.strip!              para.gsub!(/<:.+?>/,'') +            para.gsub!(/#{Rx[:mx_fa_clean]}/,'')              unless para =~/\A\s*\Z/                @filename_html_scroll.puts para,"\n"              end @@ -703,7 +660,7 @@ WOK            @filename_html_index=@my_make.file_html_index(@md)            @data.each do |para|              para.strip! -            para.gsub!(/<!.+?!>|<~\d+;(?:[ohm]|[0-6]:)\d+;\w\d+><#@dp:#@dp>/,'') +            para.gsub!(/<!.+?!>|#{Mx[:gr_o]}.*?#{Mx[:gr_c]}|#{Mx[:id_o]}~\d+;(?:[ohm]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}/,'')              unless para =~/\A\s*\Z/                @filename_html_segtoc.puts para,"\n"                @filename_html_index.puts para,"\n" diff --git a/lib/sisu/v0/html_format.rb b/lib/sisu/v0/html_format.rb index 525ef50d..03d97a8d 100644 --- a/lib/sisu/v0/html_format.rb +++ b/lib/sisu/v0/html_format.rb @@ -960,7 +960,8 @@ WOK      end      def endnote_mark  %{<p class="center" id="endnotes"> -<a href="#top"><hr></a></p>} #revisit +<a href="#top"><hr width=90% /></a> +</p>} #revisit      end    end    class Format_text_object @@ -969,10 +970,10 @@ WOK      attr_accessor :md,:one,:two,:three,:parablock,:table,:link,:linkname,:format,:paranum,:p_num,:para_id,:headname,:margin,:paragraph,:table,:banner,:url,:icon,:font,:one_stripped      def initialize(md='',*txt)        @md,@one,@two,@three=md,txt[0],txt[1],txt[2] -      rgx=/^[1-6-]~/ +      rgx=/^#{Mx[:lv_o]}\d:\S*?#{Mx[:lv_c]}/        @one_stripped=@one.gsub(rgx,'') if @one =~rgx        @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -      rgx=/~[{\[][\d*+]+\s+(.+?)<#@dp>[}\]]~/ #problem introduced +      rgx=/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[\d*+]+\s+(.+?)#{Mx[:id_o]}#@dp#{Mx[:id_c]}(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/ #problem introduced        @one_stripped=@one.gsub(rgx,'\1') if @one =~rgx #problem introduced        @link,@linkname=txt[0],txt[1]        @format,parablock=txt[0],txt[1] @@ -989,7 +990,7 @@ WOK          @para_id=Paragraph_id_ocn.new(@md,@paranum) #used by table version        end        @headname='' -      if @format =~ /\d~(\S+)/ +      if @format=~/^\d:(\S+)/ #need more reliable marker #if @format =~ /#{Rx[:lv]}/          headname=$1 #format[/\d~(\S+)/m,1]          @headname=if headname =~/^[a-zA-Z]/; %{<a name="#{headname}" id="#{headname}"></a>} #consider: h_#{headname}          else %{<a name="h#{headname}" id="h#{headname}"></a>} @@ -1045,12 +1046,12 @@ WOK      end      def gsub_body        case @one -      when /^(?:<:i[1-9]>\s*)?\((i+|iv|v|vi+|ix|x|xi+)\)/ +      when /^(?:#{Mx[:pa_o]}i[1-9]#{Mx[:pa_c]}\s*)?\((i+|iv|v|vi+|ix|x|xi+)\)/          @one.gsub!(/^\((i+|iv|v|vi+|ix|x|xi+)\)/,'<b>(\1)</b>') -        @one.gsub!(/^(<:i[1-9]>)\s*\((i+|iv|v|vi+|ix|x|xi+)\)/,'\1<b>(\2)</b>') -      when /^(?:<:i[1-9]>\s*)?\(?(\d|[a-z])+\)/ +        @one.gsub!(/^(#{Mx[:pa_o]}i[1-9]#{Mx[:pa_c]})\s*\((i+|iv|v|vi+|ix|x|xi+)\)/,'\1<b>(\2)</b>') +      when /^(?:#{Mx[:pa_o]}i[1-9]#{Mx[:pa_c]}\s*)?\(?(\d|[a-z])+\)/          @one.gsub!(/^\((\d+|[a-z])+\)/,'<b>(\1)</b>') -        @one.gsub!(/^(<:i[1-9]>)\s*\((\d+|[a-z])+\)/,'\1<b>(\2)</b>') +        @one.gsub!(/^(#{Mx[:pa_o]}i[1-9]#{Mx[:pa_c]})\s*\((\d+|[a-z])+\)/,'\1<b>(\2)</b>')        when /^\s*\d{1,3}\.\s/          @one.gsub!(/^\s*(\d+\.)/,'<b>\1</b>')        when /^\s*[A-Z]\.\s/ @@ -1069,7 +1070,7 @@ WOK      def bold_header        @one.gsub!(/[1-9]~(\S+)/,'<a name="\1"></a>')        @one.gsub!(/[1-9]~/,'') -      @one.gsub!(/<~0;[um]\d+;[um]\d+><#@dp:#@dp>\s*$/i,'') #watch & do differently +      @one.gsub!(/#{Mx[:id_o]}~0;[um]\d+;[um]\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}\s*$/i,'') #watch & do differently        %{<p class="bold">      #@one    </p> diff --git a/lib/sisu/v0/html_format_css.rb b/lib/sisu/v0/html_format_css.rb index db381e63..ace6983b 100644 --- a/lib/sisu/v0/html_format_css.rb +++ b/lib/sisu/v0/html_format_css.rb @@ -352,10 +352,10 @@ module SiSU_HTML_Format_type        else @one        end        note='' -      if one =~/(~[{\[].+?[}\]]~\s*)/m #this is a clumsy fix, revisit and address upstream +      if one =~/((?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]}).+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})\s*)/m #this is a clumsy fix, revisit and address upstream          note=$1          note.gsub!(/[\n\s]+/m,' ') -        one.gsub!(/~[{\[].+?[}\]]~\s*/m,' ') +        one.gsub!(/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]}).+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})\s*/m,' ')          one.gsub!(/<a[\n\s]+name="-\d+"[\n\s]+href="#_\d+"> <sup>\d+<\/sup> /m,'')        end        %{<#@tag class="#@class"> @@ -384,7 +384,7 @@ module SiSU_HTML_Format_type  #{@vz.table_close}}      end      def header_sub -      @parablock.gsub!(/~[{\[].+?[}\]]~\s*/m,' ') +      @parablock.gsub!(/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]}).+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})\s*/m,' ')        %{#{@vz.margin_css}  #{@headname}    <#@tag class="#@class" #{@p_num.id}>#{@p_num.name} diff --git a/lib/sisu/v0/html_scroll.rb b/lib/sisu/v0/html_scroll.rb index 97a1a02e..0bbac4fa 100644 --- a/lib/sisu/v0/html_scroll.rb +++ b/lib/sisu/v0/html_scroll.rb @@ -84,39 +84,39 @@ module SiSU_HTML_scroll        @rcdc=false        @scr={ :body=>[],:metadata=>[],:owner_details=>[] }        data.each do |para| -        if para =~/^\d~endnotes\s+Endnotes/ -          para.gsub!(/Endnotes.+/,'') -        end -        if para =~/^\d~meta\s+Document Information/ +        #if para =~/^#{Mx[:lv_o]}\d:endnotes#{Mx[:lv_c]}\s*Endnotes/ +        ##  para.gsub!(/Endnotes.+/,'') +        #end +        if para =~/^#{Mx[:lv_o]}\d:meta#{Mx[:lv_c]}\s*Document Information/            para.gsub!(/(Document Information(?: \(metadata\))?)/,'\1<a name="docinfo"></a>')          end -        if para =~/^\d~metadata\s+Metadata/ +        if para =~/^#{Mx[:lv_o]}\d:metadata#{Mx[:lv_c]}\s*Metadata/            para.gsub!(/(Metadata)/,'\1<a name="metadata"></a>')          end          if @rcdc==false \ -        and (para =~/^\d~metadata/ or para =~/^1~meta\s+Document Information/) +        and (para =~/^#{Mx[:lv_o]}:metadata#{Mx[:lv_c]}/ or para =~/^#{Mx[:lv_o]}1:meta#{Mx[:lv_c]}\s*Document Information/)            @rcdc=true          end -        if para !~/(^0~|<ENDNOTES>|<EOF>)/ -          unless para =~/^<:code>/; para.gsub!(/~[{\[].+?[}\]]~\s+/m,' ') +        if para !~/(^#{Rx[:meta]}|#{Mx[:br_endnotes]}|#{Mx[:br_eof]})/ +          unless para =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/; para.gsub!(/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]}).+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})\s*/m,' ')            end -          if para =~/.+?<~\d+;(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ -            paranum=para[/.+?<~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/,1] +          if para =~/.+?#{Mx[:id_o]}~\d+;(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ +            paranum=para[/.+?#{Mx[:id_o]}~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/,1]              @p_num=SiSU_HTML_Format_type::Paragraph_number.new(@md,paranum)            end -          @sto=SiSU_HTML::Source::Split_text_object.new(@md,para).lev_segname_para_ocn -          m=/<~\d+;(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +          @sto=SiSU_HTML::Source::Split_text_object.new(@md,para).html_scroll +          m=/#{Mx[:id_o]}~\d+;(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/            if para =~m -            format_txt_obj=SiSU_HTML_Format_type::Format_text_object.new(@md,@sto.text) if @sto.format =~/i[1-9]|_[1-9]?\*|<:i[1-9]>\s*_\*|null/ +            format_txt_obj=SiSU_HTML_Format_type::Format_text_object.new(@md,@sto.text) if @sto.format =~/i[1-9]|null/ #watch              case @sto.format -            when /^1~\S*/; para=@sto.scroll_lev_para_ocn.heading_body1 -            when /^2~\S*/; para=@sto.scroll_lev_para_ocn.heading_body2 -            when /^3~\S*/; para=@sto.scroll_lev_para_ocn.heading_body3 -            when /^4~\S+/; para=@sto.scroll_lev_para_ocn.heading_body4 # work on see Split_text_object4 -            when /^5~\S*/; para=@sto.scroll_lev_para_ocn.heading_body5 -            when /^6~\S*/; para=@sto.scroll_lev_para_ocn.heading_body6 -            when /^_\*$/;  para=@sto.scroll_lev_para_ocn.bullet -            when /^_([1-9])\*$/ #indent with bullet +            when /^1:\S*?/; para=@sto.scroll_lev_para_ocn.heading_body1 +            when /^2:\S*?/; para=@sto.scroll_lev_para_ocn.heading_body2 +            when /^3:\S*?/; para=@sto.scroll_lev_para_ocn.heading_body3 +            when /^4:\S+?/; para=@sto.scroll_lev_para_ocn.heading_body4 # work on see Split_text_object4 +            when /^5:\S*?/; para=@sto.scroll_lev_para_ocn.heading_body5 +            when /^6:\S*?/; para=@sto.scroll_lev_para_ocn.heading_body6 +            when /^#{Mx[:gl_bullet]}/;  para=@sto.scroll_lev_para_ocn.bullet +            when /^#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]}#{Mx[:gl_bullet]}/ #indent with bullet                format_txt_obj.gsub_body                para=@sto.scroll_lev_para_ocn.format('li',"i#{$1}")              when /^i([1-9])$/ #indent @@ -130,26 +130,26 @@ module SiSU_HTML_scroll                if para !~/#{@vz.margin_txt_0}|#{@vz.margin_txt_1}|#{@vz.margin_txt_2}/                  format_txt_obj.gsub_body                  para=@sto.scroll_lev_para_ocn.para -                if para =~/<!Th?.+/ # tables come as single block +                if para =~/#{Mx[:gr_o]}Th?.+/ # tables come as single block                    table=SiSU_HTML_shared::Table.new(para)                    para=table.table_split                  end                end              end -          elsif para =~/^[1-9]~\S*/ \ -          and para !~/<~\d+;(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +          elsif para =~/^#{Mx[:lv_o]}[1-9]:/ \ +          and para !~/#{Mx[:id_o]}~\d+;(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_c]}#@dp:#@dp#{Mx[:id_c]}$/              format_txt_obj=SiSU_HTML_Format_type::Format_text_object.new(@md,para)              para=format_txt_obj.bold_header            elsif para =~/Endnotes?/ \ -          and para !~/<~\d+;(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +          and para !~/#{Mx[:id_o]}~\d+;(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/              format_txt_obj=SiSU_HTML_Format_type::Format_text_object.new(@md,'<br /><a name="notes">Note</a>')              para=format_txt_obj.bold_para            elsif para =~/Owner Details/ \ -          and para !~/<~\d+;(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +          and para !~/#{Mx[:id_o]}~\d+;(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/              format_txt_obj=SiSU_HTML_Format_type::Format_text_object.new(@md,'<br /><a name="owner.details">Owner Details</a>')              @scr[:owner_details]=format_txt_obj.bold_para              para='' -          elsif para =~/(.*)<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>(.*)/ #watch +          elsif para =~/(.*)#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}(.*)/ #watch              one,two=$1,$2              format_seg=SiSU_HTML_Format_type::Format_seg.new(@md,one,two)              para=format_seg.no_paranum @@ -162,9 +162,8 @@ module SiSU_HTML_scroll              one,two=/(.*)<:center>(.*)/.match(para).captures              format_scroll=SiSU_HTML_Format_type::Format_scroll.new(@md,one,two)            end -          para.gsub!(/<!.+!>/,' ') -          para.gsub!(/^<:\S?>/,'') -          para.gsub!(/<:\S?>/,' ') +          para.gsub!(/^#{Rx[:mx_fa_clean]}/,' '); para.gsub!(/^<:\S?>/,'') +          para.gsub!(/#{Rx[:mx_fa_clean]}/,' '); para.gsub!(/<:\S?>/,' '); para.gsub!(/<!.+!>/,' ')            para.strip!            unless @rcdc; @scr[:body] << para unless para =~/\A\s*\Z/            else          @scr[:metadata] << para diff --git a/lib/sisu/v0/html_segments.rb b/lib/sisu/v0/html_segments.rb index a2d06ed9..a15c302e 100644 --- a/lib/sisu/v0/html_segments.rb +++ b/lib/sisu/v0/html_segments.rb @@ -103,9 +103,9 @@ module SiSU_HTML_seg        @h_sfx=@md.sfx if @md.file_type =~/html/        @h_sfx='.html' if @md.file_type =~/html/ #used in creating file, not to be omitted.        data.each do |para| -        if para =~/^4~/ -          @@seg_name << para[/^4~(\S+)/,1] -          seg_name=para[/^4~(\S+)/,1] +        if para =~/^#{Mx[:lv_o]}4:/ +          @@seg_name << para[/^#{Mx[:lv_o]}4:(\S+?)#{Mx[:lv_c]}/,1] +          seg_name=para[/^#{Mx[:lv_o]}4:(\S+?)#{Mx[:lv_c]}/,1]            @@seg_ad[seg_name]=para[/.+?<:\d\s+(.+)\s*?>/,1] #watch          end        end @@ -116,36 +116,36 @@ module SiSU_HTML_seg        tell.segmented unless @md.cmd =~/q/        flagend='y'        data.each do |para| -        if para =~/^4~.+/ #watch -          if para =~/<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ -            @@header4=para.to_s[/^4~(?:\S+\s+)?(.+?)<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/,1] -          else @@header4=para.to_s[/^4~(?:\S+\s+)?(.+)/,1] +        if para =~/^#{Mx[:lv_o]}4:/ #watch +          if para =~/#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ +            @@header4=para.to_s[/^#{Mx[:lv_o]}4:\S+?#{Mx[:lv_c]}(.+?)#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/,1] +          else @@header4=para.to_s[/^#{Mx[:lv_o]}4:\S+?#{Mx[:lv_c]}(.+)/,1]            end            @@is4=newfile=1          end -        if para =~/^3~.+/ -          @@header3=para.to_s[/^3~(?:~\S+\s+)?(.+)/,1] +        if para =~/^#{Mx[:lv_o]}3:\S*?#{Mx[:lv_c]}/ +          @@header3=para.to_s[/^#{Mx[:lv_o]}3:\S*?#{Mx[:lv_c]}\s*?(.+)/,1]            @@is4,@@is3=0,1          end -        if para =~/^2~.+/ -          @@header2=para.to_s[/^2~(?:~\S+\s+)?(.+)/,1] +        if para =~/^#{Mx[:lv_o]}2:\S*?#{Mx[:lv_c]}/ +          @@header2=para.to_s[/^#{Mx[:lv_o]}2:\S*?#{Mx[:lv_c]}\s*?(.+)/,1]            @@is4,@@is3,@@is2=0,0,1          end -        if para =~/^1~.+/ -          @@header1=para.to_s[/^1~(?:~\S+\s+)?(.+)/,1] +        if para =~/^#{Mx[:lv_o]}1:\S*?#{Mx[:lv_c]}/ +          @@header1=para.to_s[/^#{Mx[:lv_o]}1:\S*?#{Mx[:lv_c]}\s*?(.+)/,1]            @@is4,@@is3,@@is2,@@is1=0,0,0,1          end          if (@@is1 && !@@is2 && !@@is3 && !@@is4) -          unless para =~/^1~/; head1=$_ #; +          unless para =~/^#{Mx[:lv_o]}1:/; head1=$_ #;            end          end          if @@is4 == 1 \ -        or para =~/^<ENDNOTES>|^<EOF>/ +        or para =~/^#{Mx[:br_endnotes]}|^#{Mx[:br_eof]}/            if newfile == 1 \ -          or para =~/^<ENDNOTES>|^<EOF>/ +          or para =~/^#{Mx[:br_endnotes]}|^#{Mx[:br_eof]}/              newfile=0 -            if para =~/^4~\S+/ \ -            or para =~/^<ENDNOTES>|^<EOF>/ # @@level4 +            if para =~/^#{Mx[:lv_o]}4:\S+?#{Mx[:lv_c]}/ \ +            or para =~/^#{Mx[:br_endnotes]}|^#{Mx[:br_eof]}/ # @@level4                if tracking != 0                  mkdir_p(@md.dir_out) unless FileTest.directory?(@md.dir_out) #bug - added specifically for nav! not needed by regular seg, check !!!                  Seg.new('',@md).tail @@ -174,8 +174,8 @@ module SiSU_HTML_seg              tracking=tracking + 1            end            m=para[/.+?<a name="(\d+)">.*/]; @@get_hash_to=$1 if m              # changed 2002w42, again w44 ! & again 2003w16 -          m=para[/^4~(\S+)/]; @@get_hash_fn=$1 if m -          para=if para =~/<!Th?¡\s+c|<:(?:code|alt|verse|group)>/um; para.split(/\n/) +          m=para[/^#{Mx[:lv_o]}4:(\S+?)#{Mx[:lv_c]}/]; @@get_hash_fn=$1 if m +          para=if para =~/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s*c|#{Mx[:gr_o]}(?:code|alt|verse|group)#{Mx[:gr_c]}/um; para.split(/\n/)            else para            end            if para.class == String @@ -195,7 +195,7 @@ module SiSU_HTML_seg      end      def header_art(para)        format_head_seg=SiSU_HTML_Format_type::Head_seg.new(@md) -      if para =~/^[0-6]~/ #2004w27/5 +      if para =~/^#{Mx[:lv_o]}[1-6]:/ #2004w27/5          if @@tracker < @@seg_total-1; @@seg[:dot_nav]=format_head_seg.dot_control_pre_next          else                          @@seg[:dot_nav]=format_head_seg.dot_control_pre          end @@ -204,7 +204,7 @@ module SiSU_HTML_seg        @@seg[:title]=format_head_seg.head << ads.div.major      end      def head(para) -      clean=/<!.*?!>|<:.*?>|<~\d+;(?:[ohum]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +      clean=/<!.*?!>|#{Mx[:gr_o]}:.*?#{Mx[:gr_c]}|<:.*?>|#{Mx[:id_o]}~\d+;(?:[ohum]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/        format_head_seg=SiSU_HTML_Format_type::Head_seg.new(@md)        if @@tracker < @@seg_total-1          if @@tracker == 0; @@segtocband=format_head_seg.toc_next2 #if format_head_seg.toc_next2 @@ -218,7 +218,7 @@ module SiSU_HTML_seg          @@seg[:tocband] << format_head_seg.navigation_band(@@segtocband,@@seg[:dot_nav])          @@seg[:headers] << format_head_seg.seg_head_escript if SiSU_HTML_Format_type::Head_seg.method_defined? :seg_head_escript #debug PHP move up in text #bug          @@seg[:headers] << format_head_seg.title_banner(@md.title,@md.subtitle,@dc_creator).gsub(clean,'') -        paranum=if @@header1[/.+?<~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/]; $1 +        paranum=if @@header1[/.+?#{Mx[:id_o]}~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/]; $1          else ''          end          @p_num=SiSU_HTML_Format_type::Paragraph_number.new(@md,paranum) @@ -228,7 +228,7 @@ module SiSU_HTML_seg        end        if @@is2 == 1          header2=@@header2 -        paranum=if header2[/.+?<~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/]; $1 +        paranum=if header2[/.+?#{Mx[:id_o]}~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/]; $1          else ''          end          @p_num=SiSU_HTML_Format_type::Paragraph_number.new(@md,paranum) @@ -238,7 +238,7 @@ module SiSU_HTML_seg        end        if @@is3 == 1          header3=@@header3 -        paranum=if header3[/.+?<~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/]; $1 +        paranum=if header3[/.+?#{Mx[:id_o]}~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/]; $1          else ''          end          @p_num=SiSU_HTML_Format_type::Paragraph_number.new(@md,paranum) @@ -248,7 +248,7 @@ module SiSU_HTML_seg        end        if @@is4 == 1          header4=@@header4 -        paranum=if header4[/.+?<~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/]; $1 +        paranum=if header4[/.+?#{Mx[:id_o]}~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/]; $1          else ''          end          @p_num=SiSU_HTML_Format_type::Paragraph_number.new(@md,paranum) @@ -261,47 +261,48 @@ module SiSU_HTML_seg      def markup(para)        @debug=[]        format_head_seg=SiSU_HTML_Format_type::Head_seg.new(@md) -      if para !~/^0~/ -        m=para[/.+?<~(\d+);(?:[ohm]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/] +      if para !~/^#{Rx[:meta]}/ +        m=para[/.+?#{Mx[:id_o]}~(\d+);(?:[ohm]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/]          if m            paranum=m[1].to_s            @p_num=SiSU_HTML_Format_type::Paragraph_number.new(@md,paranum)          end -        if para =~/<:(?:code|alt|verse|group)>/m \ +        if para =~/#{Mx[:gr_o]}(?:code|alt|verse|group)#{Mx[:gr_c]}/m \          or @@flag_alt==true -          if para =~/<:(?:code|alt|verse|group)>/m +          if para =~/#{Mx[:gr_o]}(?:code|alt|verse|group)#{Mx[:gr_c]}/m              @group_collect=[] #unless @group_collect.class == Array -            @group_collect << @vz.margin_txt_0 + para.gsub(/<:(?:code|alt|verse|group)-end>/m,'') #watch ! +            @group_collect << @vz.margin_txt_0 + para.gsub(/#{Mx[:gr_o]}(?:code|alt|verse|group)-end#{Mx[:gr_c]}/m,'') #watch !              @@flag_alt=true            elsif @@flag_alt==true -            @group_collect << if para !~/<:(?:code|alt|verse|group)-end>/m                  # neither ideal nor necessary sort later +            @group_collect << if para !~/#{Mx[:gr_o]}(?:code|alt|verse|group)-end#{Mx[:gr_c]}/m                  # neither ideal nor necessary sort later                para              else -              para.gsub(/<:(?:code|alt|verse|group)-end>/m,'') +              para.gsub(/#{Mx[:gr_o]}(?:code|alt|verse|group)-end#{Mx[:gr_c]}/m,'')              end            end -          if para =~/<:(?:code|alt|verse|group)-end>/m +          if para =~/#{Mx[:gr_o]}(?:code|alt|verse|group)-end#{Mx[:gr_c]}/m              para=@group_collect.flatten.join              @@flag_alt=false              @group_collect=[]            end          end -        if para !~/^[0-9]~/ -          if para =~/(.*)<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>(.*)/ +        if para !~/^#{Mx[:lv_o]}[1-9]:|#{Rx[:meta]}/ +          if para =~/(.*)#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}(.*)/              one,two=$1,$2              format_seg=SiSU_HTML_Format_type::Format_seg.new(@md,one,two)              para=format_seg.no_paranum            end          end -        if para[/<~(\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+><#@dp:#@dp)>$/] -          @sto=SiSU_HTML::Source::Split_text_object.new(@md,para).lev_segname_para_ocn -          format_txt_obj=SiSU_HTML_Format_type::Format_text_object.new(@md,@sto.text) if @sto.format =~/i[1-9]|_[1-9]?\*|<:i[1-9]>\s*_\*|null/ +        if para[/#{Mx[:id_o]}~(\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp)#{Mx[:id_c]}$/] +          @sto=SiSU_HTML::Source::Split_text_object.new(@md,para).html_seg +          format_txt_obj=SiSU_HTML_Format_type::Format_text_object.new(@md,@sto.text) if @sto.format =~/i[1-9]|null/ #watch            para=case @sto.format # work area 2003w29 ||@|def lev_segname_para_ocn| -          when /^4~\S+/;       @sto.seg_lev_para_ocn.header4 # work on see Split_text_object -          when /^5~(?:~\S+)?/; @sto.seg_lev_para_ocn.header5 -          when /^6~(?:~\S+)?/; @sto.seg_lev_para_ocn.header6 -          when /^_\*$/;        @sto.seg_lev_para_ocn.bullet -          when /^_([1-9])\*$/  #indent levels 1-9 with bullet +          when /^4:/; @sto.seg_lev_para_ocn.header4 # work on see Split_text_object +          when /^5:/; @sto.seg_lev_para_ocn.header5 +          when /^6:/; @sto.seg_lev_para_ocn.header6 +          when /^#{Mx[:gl_bullet]}/ +            @sto.seg_lev_para_ocn.bullet +          when /^#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]}#{Mx[:gl_bullet]}/  #indent levels 1-9 with bullet              format_txt_obj.gsub_body              para=@sto.seg_lev_para_ocn.format('li',"i#{$1}")            when /^i([1-9])$/    #indent levels 1-9 @@ -313,18 +314,18 @@ module SiSU_HTML_seg              @sto.seg_lev_para_ocn.code            when /null/              if para !~/#{@vz.margin_txt_0}|#{@vz.margin_txt_1}|#{@vz.margin_txt_2}/ \ -            and para !~/^<!TZ!>/ +            and para !~/^#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/                format_txt_obj.gsub_body                @sto.seg_lev_para_ocn.para              elsif para !~/#{@vz.margin_txt_0}|#{@vz.margin_txt_1}|#{@vz.margin_txt_2}/ \ -            and para =~/^<!TZ!>/ +            and para =~/^#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/                format_txt_obj.gsub_body                @sto.seg_lev_para_ocn.table_end              else para              end            else para            end -        elsif para =~/¡|<!T[hZ]?/u +        elsif para =~/#{Mx[:tc_p]}|#{Mx[:gr_o]}T[hZ]?/u            table=SiSU_HTML_shared::Table.new(para)            para=table.table          end @@ -332,10 +333,11 @@ module SiSU_HTML_seg            para.gsub!(/"\s+href="#_(\d+)">/,%{" href=\"endnotes#{@md.sfx}#_\\1">})       #endnote- twice #removed file type          end          if para !~/#{@vz.margin_txt_w1}|#{@vz.margin_txt_w2}/ -          if para[/(.*)<~0;(?:u|[0-6]:)\d+;\w\d+><#@dp:#@dp>(.*)/] #% watch u & m? +          if para[/(.*)#{Mx[:id_o]}~0;(?:u|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}(.*)/] #% watch u & m?              one,two=$1,$2              format_seg=SiSU_HTML_Format_type::Format_seg.new(@md,one,two) -            para=format_seg.seg_no_paranum                                   #% undefined +#FIX --> not that undefined, rather is not needed, should not be visited, and remove +            #para=format_seg.seg_no_paranum                                   #% undefined            end            para.gsub!(/\s*(-\{{2}~\d+|<:e[:_]\d+>).*/,'')                   #potentially dagerous - removes all paragraphs with <!e_!> #?? workpoint            if para =~/<a name="_\d+" href="#-\d+"> <sup>/                #endnote- note- @@ -343,8 +345,8 @@ module SiSU_HTML_seg              para=format_seg.no_paranum            end          end -        if para =~/^4~\S+|4~!/ -          para.gsub!(/4~\S+|<:[-_\w\d]?(-.+?-)?>|4~!.+/,'')              #sort seg headers +        if @sto.format=~/4:\S+/ +          para.gsub!(/^\s*4:\S+\s*|<:[-_\w\d]?(-.+?-)?>|4~!.+/m,'')              #sort seg headers            @@seg[:main] << para            @@seg[:main] << @@seg_subtoc[@@get_hash_fn]                       #% insertion of sub-toc          else @@ -398,39 +400,39 @@ module SiSU_HTML_seg        data.each do |para|          para.gsub!(/<a name=\"h\d.*?\">(.+?)<\/a>/mi,'\1')          if @md.flag_auto_endnotes -          if para =~/^[1234]~/ \ +          if para =~/^#{Mx[:lv_o]}[1234]:/ \            and not @@fn.empty?              @@seg_endnotes[@@fn]=[]              @@seg_endnotes[@@fn] << @@seg_endnotes_array -            @@seg_endnotes_array=[] if para=~/^4~/ -            @@fns_previous=@md.fns if para=~/^1~meta/ +            @@seg_endnotes_array=[] if para=~/^#{Mx[:lv_o]}4:/ +            @@fns_previous=@md.fns if para=~/^#{Mx[:lv_o]}1:meta#{Mx[:lv_c]}/            end -          if para =~/^4~/                                              #% EXTRACTION OF SUB-TOCs +          if para =~/^#{Mx[:lv_o]}4:/                                              #% EXTRACTION OF SUB-TOCs              @@seg_subtoc[@@fn]=@@seg_subtoc_array              @@seg_subtoc_array=[]            end -          if para =~/^4~/                                              #% SEGMENT NAME, after EXTRACTION OF ENDNOTES & SUB-TOCs -            if para !~/^4~metadata/ -              m=para[/^4~(\S+).+?<~(\d+);(?:[oh]|4:)\d+;\w\d+><#@dp:#@dp>$/] +          if para =~/^#{Mx[:lv_o]}4:/                                              #% SEGMENT NAME, after EXTRACTION OF ENDNOTES & SUB-TOCs +            if para !~/^#{Mx[:lv_o]}4:metadata#{Mx[:lv_c]}/ +              m=para[/^#{Mx[:lv_o]}4:(\S+?)#{Mx[:lv_c]}.+?#{Mx[:id_o]}~(\d+);(?:[oh]|4:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/]              end              if m;  @@fn,@@to_lev4=$1,$2 if m # changed 2004w07          #endnotes and sub-tocs              else -              if para !~/^4~metadata/ -                m=para[/^4~(\S+)/] +              if para !~/^#{Mx[:lv_o]}4:metadata#{Mx[:lv_c]}/ +                m=para[/^#{Mx[:lv_o]}4:(\S+?)#{Mx[:lv_c]}/]                  @@fn,@@to_lev4=$1,'nonum' if m # changed 2005w13                else @@fn=''                end              end            end          end -        if para =~/^[56]~\S*\s+(.+)?<~(\d+);(?:h|[56]:)\d+;\w\d+><#@dp:#@dp>$/ +        if para =~/^#{Mx[:lv_o]}[56]:\S*?#{Mx[:lv_c]}\s*(.+)?#{Mx[:id_o]}~(\d+);(?:h|[56]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/            para.gsub!(/ <\/a>/,' ')            case para # series changed 2002w42 -          when /^5~\S*\s+(.+)?<~(\d+);(?:h|[56]:)\d+;\w\d+><#@dp:#@dp>$/ #remove [u]? req by pg texts, revist +          when /^#{Mx[:lv_o]}5:\S*?#{Mx[:lv_c]}\s*(.+)?#{Mx[:id_o]}~(\d+);(?:h|[56]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ #remove [u]? req by pg texts, revist              one,two=$1,$2              format_seg=SiSU_HTML_Format_type::Format_seg.new(@md,one,two)              para=format_seg.subtoc_lev5 -          when /^6~\S*\s+(.+)?<~(\d+);(?:h|[56]:)\d+;\w\d+><#@dp:#@dp>$/ +          when /^#{Mx[:lv_o]}6:\S*?#{Mx[:lv_c]}\s*(.+)?#{Mx[:id_o]}~(\d+);(?:h|[56]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/              one,two=$1,$2              format_seg=SiSU_HTML_Format_type::Format_seg.new(@md,one,two)              para=format_seg.subtoc_lev6 @@ -438,27 +440,27 @@ module SiSU_HTML_seg            @@seg_subtoc_array << para          end          if @md.flag_auto_endnotes -          if para =~/~[{\[][\d*+]+ <a name="_[\d*+]+"/ \ -          and not para =~/^<:code>/ # endnote- +          if para =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[\d*+]+ <a name="_[\d*+]+"/ \ +          and not para =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/ # endnote-              endnote_array=[] -            if para=~/~\{.+?\}\~/m -              endnote_array << para.scan(/~\{.+?\}\~/m) +            if para=~/#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/m +              endnote_array << para.scan(/#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/m)              end -            if para=~/~\[[*]\d+\s.+?\]\~/m -              endnote_array << para.scan(/~\[[*]\d+\s.+?\]\~/m) +            if para=~/#{Mx[:en_b_o]}[*]\d+\s.+?#{Mx[:en_b_c]}/m +              endnote_array << para.scan(/#{Mx[:en_b_o]}[*]\d+\s.+?#{Mx[:en_b_c]}/m)              end -            if para=~/~\[[+]\d+\s.+?\]\~/m -              endnote_array << para.scan(/~\[[+]\d+\s.+?\]\~/m) +            if para=~/#{Mx[:en_b_o]}[+]\d+\s.+?#{Mx[:en_b_c]}/m +              endnote_array << para.scan(/#{Mx[:en_b_o]}[+]\d+\s.+?#{Mx[:en_b_c]}/m)              end              endnote_array.flatten!.compact! #check compacting              endnote_array.each do |note|                note_match=note.dup                note_match_seg=note.dup -              e_n=note_match_seg[/(?:~\{[\d*+]+|~\[[*+]\d+)\s+(.+?)[}\]]~/m,1] +              e_n=note_match_seg[/(?:#{Mx[:en_a_o]}[\d*+]+|#{Mx[:en_b_o]}[*+]\d+)\s+(.+?)(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/m,1]                try=e_n.split(/<br \/>/)                try.each do |e|                  format_seg=SiSU_HTML_Format_type::Format_seg.new(@md,e) -                note_match=if e =~/<:i[1-9]>/ +                note_match=if e =~/#{Mx[:pa_o]}i[1-9]#{Mx[:pa_c]}/                    format_seg.endnote_body_seg_tail_indent                  else format_seg.endnote_body_seg_tail                  end @@ -466,14 +468,14 @@ module SiSU_HTML_seg                end                try.join('<br \/>')                #% creation of separate end segment/page of all endnotes referenced back to reference segment -              m=/(?:~\{[\d*+]+|~\[[*+]\d+)\s+(.+?href=")(#-[\d*+]+".+)[}\]]~/mi +              m=/(?:#{Mx[:en_a_o]}[\d*+]+|#{Mx[:en_b_o]}[*+]\d+)\s+(.+?href=")(#-[\d*+]+".+)(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/mi                one=note_match_seg[m,1] #note~ [a name]                two=note_match_seg[m,2] #note-                format_seg=SiSU_HTML_Format_type::Format_seg.new(@md,one,two)                note_match_all_seg=format_seg.endnote_seg_body(@@fn) #BUG WATCH 200408                @@seg[:endnote_all] << note_match_all_seg              end -            para.gsub!(/~[{\[].+?[}\]]~\s*/m,' ') +            para.gsub!(/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]}).+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})\s*/m,' ')            end          end        end diff --git a/lib/sisu/v0/html_table.rb b/lib/sisu/v0/html_table.rb index 556c46be..1aed4f5d 100644 --- a/lib/sisu/v0/html_table.rb +++ b/lib/sisu/v0/html_table.rb @@ -102,39 +102,39 @@ module SiSU_HTML_table        m=@parablock[/<!f(.+?)!>/,1]        @@tablefoot << m if m        @parablock.gsub!(/<!f.+?!>/,'') -      @@tablehead=1 if @parablock =~/<!Th¡/u -      if @parablock =~/<!Th?¡.+?!~(\d+);\w\d+;\w\d+>/u; @parablock=table_head($1) +      @@tablehead=1 if @parablock =~/#{Mx[:gr_o]}Th#{Mx[:tc_p]}/u +      if @parablock =~/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}.+?#{Mx[:tc_p]}~(\d+);\w\d+;\w\d+#{Mx[:gr_c]}/u; @parablock=table_head($1)        end -      if @parablock =~/<!TZ!>/ +      if @parablock =~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/          tablefoot=[]          @@tablefoot.each {|x| tablefoot << ''}          @@tablefoot=[] -        if @parablock =~/<!TZ!>/; @parablock=table_end +        if @parablock =~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/; @parablock=table_end          end        end        if @@tablehead == 1 -        if @parablock =~/¡¡/u -          if @parablock =~/<!¡¡(\d+?)¡/u -            @parablock.gsub!(/<!¡¡(\d+?)¡/u,table_row($1,true)) +        if @parablock =~/#{Mx[:tc_p]}#{Mx[:tc_p]}/u +          if @parablock =~/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u +            @parablock.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,table_row($1,true))            end -          if @parablock =~/¡¡(\d+?)¡/u -            @parablock.gsub!(/¡¡(\d+?)¡/u,table_cell($1,true)) +          if @parablock =~/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u +            @parablock.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,table_cell($1,true))            end -          if @parablock =~/!>/ -            @parablock.gsub!(/!>/,table_row_close(true)) +          if @parablock =~/#{Mx[:tc_c]}/ +            @parablock.gsub!(/#{Mx[:tc_c]}/,table_row_close(true))            end            @@tablehead=0          end          @parablock        else -        if @parablock =~/<!¡¡(\d+?)¡/u -          @parablock.gsub!(/<!¡¡(\d+?)¡/u,table_row($1)) +        if @parablock =~/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u +          @parablock.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,table_row($1))          end -        if @parablock =~/¡¡(\d+?)¡/u -          @parablock.gsub!(/¡¡(\d+?)¡/u,table_cell($1)) +        if @parablock =~/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u +          @parablock.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,table_cell($1))          end -        if @parablock =~/!>/ -          @parablock.gsub!(/!>/,table_row_close) +        if @parablock =~/#{Mx[:tc_c]}/ +          @parablock.gsub!(/#{Mx[:tc_c]}/,table_row_close)          end          @parablock        end diff --git a/lib/sisu/v0/html_tune.rb b/lib/sisu/v0/html_tune.rb index 8cd8841e..11976af9 100644 --- a/lib/sisu/v0/html_tune.rb +++ b/lib/sisu/v0/html_tune.rb @@ -101,6 +101,8 @@ module SiSU_Tune        @html=html      end      def clean +      @html.gsub!(/#{Mx[:gl_o]}(#[0-9]+)#{Mx[:gl_c]}/u,'&\1;') +      @html.gsub!(/#{Mx[:gl_o]}#([a-z]{2,4})#{Mx[:gl_c]}/u,'&\1;')        @html.gsub!(/¢/u,'¢')    # ¢        @html.gsub!(/£/u,'£')   # £        @html.gsub!(/¥/u,'¥')     # ¥ @@ -208,9 +210,7 @@ module SiSU_Tune          tell.txt_grey unless @md.cmd =~/q/          data=Tune.new(@data,@md).endnotes_html          data=Tune.new(data,@md).url_markup -        if @sys.locale =~/utf-?8/i -          data=Tune.new(data,@md).utf8_markup -        end +        data=Tune.new(data,@md).markup          if @md.cmd =~/M/  #Hard Output Tune Optional on/off here            data=Output.new(data,@md).hard_output            Output.new(data,@md).marshal @@ -224,22 +224,30 @@ module SiSU_Tune        data=@data        @tuned_file=[]        data.each do |para| -        para.gsub!(/(\d~(\S+))/,'\1<a name="H#\2">#\2.</a> ') +        para.gsub!(/#{Mx[:lv_o]}\d:(\S?)#{Mx[:lv_c]}/,'\0<a name="H#\1">#\1.</a> ')          @tuned_file << para        end      end -    def utf8_markup +    def markup        @tuned_file=[]        @data.each do |para|          #@utf8.new(para).html          #@utf8.html(@para) -        if @sys.locale =~/utf-?8/i # instead ucs for utf8 #require 'iconv' ? Iñtërnâtiônàlizætiøn -          #¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûü -          #¢£¥§©ª«®°±²³µ¶¹º»¼½¾×÷ -          ##para.gsub!(//, '&#;') -          ##para.gsub!(//, '&;') -          para=SiSU_Tune::Clean_html.new(para).clean -        end +        para.gsub!(/#{Mx[:mk_o]}#([a-zA-Z]+)#{Mx[:mk_c]}/,'&\1;') +        para.gsub!(/#{Mx[:mk_o]}(#[0-9]+)#{Mx[:mk_c]}/,'&\1;') +        para.gsub!(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,'<br />') +        para.gsub!(/(?:\s*#{Mx[:br_page]}\s*|\s*#{Mx[:br_page_new]}\s*)+/m,'<p><hr width=90% /></p>') # else clean '' +        para.gsub!(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'<b>\1</b>') +        para.gsub!(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'<i>\1</i>') +        para.gsub!(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'<u>\1</u>') +        para.gsub!(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,'<sup>\1</sup>') +        para.gsub!(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,'<sub>\1</sub>') +        para.gsub!(/#{Mx[:fa_insert_o]}(.+?)#{Mx[:fa_insert_c]}/,'<ins>\1</ins>') +        para.gsub!(/#{Mx[:fa_cite_o]}(.+?)#{Mx[:fa_cite_c]}/,'<cite>\1</cite>') +        para.gsub!(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'<del>\1</del>') +        para.gsub!(/#{Mx[:mk_o]}:name#(\S+?)#{Mx[:mk_c]}/,'<a name="\1"></a>') +        para.gsub!(/<(p|br)>/,'<\1 />') +        para=SiSU_Tune::Clean_html.new(para).clean          @tuned_file << para        end      end @@ -287,12 +295,10 @@ module SiSU_Tune        data=@data        @tuned_file=[]        data.each do |para| -        para.gsub!(/<:name\#(\S+?)>/,'<a name="\1"></a>') +        #para.gsub!(/#{Mx[:mk_o]}name#(\S+?)#{Mx[:mk_c]}/,'<a name="\1"></a>')          para.gsub!(/<-#>/,'') -        para.gsub!(/<:p[bn]>/,'') -        para.gsub!(/<(p|br)>/,'<\1 />') -        para.gsub!(/<:br>/,'<br />') -        unless para =~/^<:code>/ +        #para.gsub!(/<(p|br)>/,'<\1 />') +        unless para =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/            if para =~/<::\s+/ #watch              para.gsub!(/<::\s+(\S+?)\s+!>/,                %{<img src="#{@env.url.images}/c_\\1.png" alt="\\1" width="14" height="14" align="bottom" border="0">}) @@ -308,11 +314,11 @@ module SiSU_Tune                %{<img src="#{@env.url.images_local}/\\1" naturalsizeflag="0" align="bottom" border="0">})            end            if para =~/\{.+?\}((?:https?|file|ftp)\S+|image)/ -            @word_mode=para.scan(/\{.+?\}(?:(?:https?|file|ftp)\S+|image)|\S+/) +            @word_mode=para.scan(/\{.+?\}(?:(?:https?|file|ftp)\S+|image)|(?:#{Mx[:gl_o]}\S+?#{Mx[:gl_c]})+|\S+/u)              words=urls(@word_mode)              para.gsub!(/.+/m,words)            end -          if (para !~/^0~|^<:code>/) +          if (para !~/^#{Mx[:meta_o]}|^#{Mx[:gr_o]}code#{Mx[:gr_c]}/)              para.gsub!(/\\copyright/i,%{<sup>©</sup>})              if (para !~/\<:ad\s+\.\.\//)                para.gsub!(/\<:ad\s+(\S+)?\s+(\S+\.png)\s+(.+)?\;\s+(.+)?\;\s*!\>/, @@ -327,11 +333,11 @@ module SiSU_Tune              para.gsub!(/<:to(\d{1,7}?)>/,'<a href="#to\1">to { \1 }</a> ')              if para =~/\b\S+\@\S+?\.\S+/ \              and para !~/(\"\S+\@\S+?\.\S+\"|>\S+\@\S+?\.\S+?<)/ -              para.gsub!(/\b(\S+\@\S+?\.\S+)(\s)/,'<<a href="mailto:\1">\1</a>>\2') +              para.gsub!(/([a-zA-Z0-9._-]+\@\S+?\.[a-zA-Z0-9._-]+)/,'<<a href="mailto:\1">\1</a>>')              end              para.gsub!(/\b[_\\]((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'<a href="\1" target="_top">\1</a>\2') #http ftp matches escaped, no decoration              para.gsub!(/((?:^|\s)[}])((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'\1<a href="\2" target="_top">\2</a>\3') #special case \{ e.g. \}http://url -            para.gsub!(/(^|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/,%{\\1#{@url_brace.xml_open}<a href="\\2" target="_top">\\2</a>#{@url_brace.xml_close}\\3}) #http ftp matches with decoration +            para.gsub!(/(^|#{Mx[:gl_c]}|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/,%{\\1#{@url_brace.xml_open}<a href="\\2" target="_top">\\2</a>#{@url_brace.xml_close}\\3}) #http ftp matches with decoration              if para =~/..\/\S+/ \              and para !~/(\"..\/\S+?\"|>\s*..\/\S+<)/                para.gsub!(/(\.\.\/\S+)/,'<a href="\1">\1</a>') @@ -349,14 +355,14 @@ module SiSU_Tune        data=@data        @tuned_file=[]        data.each do |para| -        unless para =~/^<:code>/ -          para.gsub!(/(~[{])(\d+) (.+?) <#@dp>([}]~)/, +        unless para =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/ +          para.gsub!(/(#{Mx[:en_a_o]}|#{Mx[:en_b_o]})(\d+)\s+(.+?) #{Mx[:id_o]}#@dp#{Mx[:id_c]}(#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/,              ' <a name="-\2" href="#_\2"> <sup>\2</sup> </a> ' +  #note- endnote-              '\1\2 <a name="_\2" href="#-\2"> <sup>\2.</sup></a> \3 \4') #endnote- note- (careful may have switched) -          para.gsub!(/(~\[)([*+]\d+) (.+?) <#@dp>(\]~)/, +          para.gsub!(/(#{Mx[:en_b_o]})([*+]\d+)\s+(.+?) #{Mx[:id_o]}#@dp#{Mx[:id_c]}(#{Mx[:en_b_c]})/,              ' <a name="-\2" href="#_\2"> <sup>\2</sup> </a> ' +  #note- endnote-              '\1\2 <a name="_\2" href="#-\2"> <sup>\2.</sup></a> \3 \4') #endnote- note- (careful may have switched) -          para.gsub!(/(~\{)([*+]+) (.+?) <#@dp>(\}~)/, +          para.gsub!(/(#{Mx[:en_a_o]})([*+]+)\s+(.+?) #{Mx[:id_o]}#@dp#{Mx[:id_c]}(#{Mx[:en_a_c]})/,              ' <a name="-\2" href="#_\2"> <sup>\2</sup> </a> ' +  #note- endnote-              '\1\2 <a name="_\2" href="#-\2"> <sup>\2</sup></a> \3 \4') #endnote- note- (careful may have switched)          end diff --git a/lib/sisu/v0/hub.rb b/lib/sisu/v0/hub.rb index af93c736..b3815828 100644 --- a/lib/sisu/v0/hub.rb +++ b/lib/sisu/v0/hub.rb @@ -419,8 +419,8 @@ p "here #{__FILE__} #{__LINE__}" if @opt =~/M/          end          if @opt.cmd =~/[hHz]/; op('html','html')               #% -h -H -z html css          end -        if @opt.cmd =~/A/; op('air','air')         #% #-A -        end +        #if @opt.cmd =~/A/; op('air','air')         #% #-A +        #end          if @opt.cmd =~/a/; op('plaintext','plaintext')         #% -a #-A -f -e -E plaintext -a creates ms-dos type; -A creates unix type, plaintext file          end          if @opt.cmd =~/g/; op('wikispeak','wikispeak')         #% -g wiki diff --git a/lib/sisu/v0/manifest.rb b/lib/sisu/v0/manifest.rb index 4861097e..6bdfdae4 100644 --- a/lib/sisu/v0/manifest.rb +++ b/lib/sisu/v0/manifest.rb @@ -182,14 +182,64 @@ module SiSU_Manifest            id,file='HTML, full length document',@md.fn[:doc]            summarize(id,file,img)          end -        if FileTest.file?("#@base_path/#{@md.fn[:pdf_p]}")==true +        #if FileTest.file?("#@base_path/#{@md.fn[:pdf_p]}")==true +        #  img='<img border="0" height="18" width="15" src="../_sisu/image_sys/b_pdf.png" alt="PDF portrait" /> ' +        #  id,file="full length document (PDF portrait / vertical - recommended for printing), size #{@md.papersize_array[0]}",@md.fn[:pdf_p] +        #  summarize(id,file,img) +        #end +        #if FileTest.file?("#@base_path/#{@md.fn[:pdf_l]}")==true +        #  img='<img border="0" height="15" width="18" src="../_sisu/image_sys/b_pdf.png" alt="PDF landscape" /> ' +        #  id,file="full length document (PDF landscape / horizontal - recommended for screen viewing), size #{@md.papersize_array[0]}",@md.fn[:pdf_l] +        #  summarize(id,file,img) +        #end +        if FileTest.file?("#@base_path/#{@md.fn[:pdf_p_letter]}")==true            img='<img border="0" height="18" width="15" src="../_sisu/image_sys/b_pdf.png" alt="PDF portrait" /> ' -          id,file='PDF document portrait/vertical (recommended for printing)',@md.fn[:pdf_p] +          id,file="PDF, U.S. letter size, portrait/vertical document (recommended for printing)",@md.fn[:pdf_p_letter]            summarize(id,file,img)          end -        if FileTest.file?("#@base_path/#{@md.fn[:pdf_l]}")==true +        if FileTest.file?("#@base_path/#{@md.fn[:pdf_l_letter]}")==true            img='<img border="0" height="15" width="18" src="../_sisu/image_sys/b_pdf.png" alt="PDF landscape" /> ' -          id,file='PDF document landscape/horizontal (recommended for screen viewing)',@md.fn[:pdf_l] +          id,file="PDF, U.S. letter size, landscape/horizontal document (recommended for screen viewing)",@md.fn[:pdf_l_letter] +          summarize(id,file,img) +        end +        if FileTest.file?("#@base_path/#{@md.fn[:pdf_p_a4]}")==true +          img='<img border="0" height="18" width="15" src="../_sisu/image_sys/b_pdf.png" alt="PDF portrait" /> ' +          id,file="PDF, A4 size, portrait/vertical document (recommended for printing)",@md.fn[:pdf_p_a4] +          summarize(id,file,img) +        end +        if FileTest.file?("#@base_path/#{@md.fn[:pdf_l_a4]}")==true +          img='<img border="0" height="15" width="18" src="../_sisu/image_sys/b_pdf.png" alt="PDF landscape" /> ' +          id,file="PDF, A4 size, landscape/horizontal document (recommended for screen viewing)",@md.fn[:pdf_l_a4] +          summarize(id,file,img) +        end +        if FileTest.file?("#@base_path/#{@md.fn[:pdf_p_a5]}")==true +          img='<img border="0" height="18" width="15" src="../_sisu/image_sys/b_pdf.png" alt="PDF portrait" /> ' +          id,file="PDF, A5 (book) size, portrait/vertical document (recommended for printing)",@md.fn[:pdf_p_a5] +          summarize(id,file,img) +        end +        if FileTest.file?("#@base_path/#{@md.fn[:pdf_l_a5]}")==true +          img='<img border="0" height="15" width="18" src="../_sisu/image_sys/b_pdf.png" alt="PDF landscape" /> ' +          id,file="PDF, A5 (book) size, landscape/horizontal document (recommended for screen viewing)",@md.fn[:pdf_l_a5] +          summarize(id,file,img) +        end +        if FileTest.file?("#@base_path/#{@md.fn[:pdf_p_b5]}")==true +          img='<img border="0" height="18" width="15" src="../_sisu/image_sys/b_pdf.png" alt="PDF portrait" /> ' +          id,file="PDF, B5 (book) size, portrait/vertical document (recommended for printing)",@md.fn[:pdf_p_b5] +          summarize(id,file,img) +        end +        if FileTest.file?("#@base_path/#{@md.fn[:pdf_l_b5]}")==true +          img='<img border="0" height="15" width="18" src="../_sisu/image_sys/b_pdf.png" alt="PDF landscape" /> ' +          id,file="PDF, B5 (book) size, landscape/horizontal document (recommended for screen viewing)",@md.fn[:pdf_l_b5] +          summarize(id,file,img) +        end +        if FileTest.file?("#@base_path/#{@md.fn[:pdf_p_legal]}")==true +          img='<img border="0" height="18" width="15" src="../_sisu/image_sys/b_pdf.png" alt="PDF portrait" /> ' +          id,file="PDF, U.S. legal size, portrait/vertical document (recommended for printing)",@md.fn[:pdf_p_legal] +          summarize(id,file,img) +        end +        if FileTest.file?("#@base_path/#{@md.fn[:pdf_l_legal]}")==true +          img='<img border="0" height="15" width="18" src="../_sisu/image_sys/b_pdf.png" alt="PDF landscape" /> ' +          id,file="PDF, U.S. legal size, landscape/horizontal document (recommended for screen viewing)",@md.fn[:pdf_l_legal]            summarize(id,file,img)          end          if FileTest.file?("#@base_path/#{@md.fn[:odf]}")==true diff --git a/lib/sisu/v0/manpage.rb b/lib/sisu/v0/manpage.rb index e267de48..06878094 100644 --- a/lib/sisu/v0/manpage.rb +++ b/lib/sisu/v0/manpage.rb @@ -68,6 +68,7 @@ module SiSU_manpage    require "#{SiSU_lib}/manpage_format"    include Format    require "#{SiSU_lib}/shared_txt" +  require "#{SiSU_lib}/shared_structure"    pwd=Dir.pwd    @@alt_id_count,@@alt_id_count,@@tablehead,@@number_of_cols=0,0,0,0    @@tablefoot='' @@ -100,54 +101,6 @@ module SiSU_manpage        end      end      private -    class Split_text_object <Source -      require "#{SiSU_lib}/manpage_format" -      include SiSU_Viz -      include Format -      @@alt_id_count=0 -      @@dp=nil -      attr_reader :format,:lev,:text,:ocn,:lev_para_ocn -      def initialize(para) -        @para=para -        @format,@ocn='null','null' -        @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -      end -      def lev_segname_para_ocn -        @text=nil -        if @para =~/^(\d~|<:.+?>).+?<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ -          if /^(([1-6])~(\S+))\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @format,@lev,segname,@text,@ocn=$1,$2,$3,$4,$5 -          elsif  /^(([1-6])~)\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @format,@lev,@text,@ocn=$1,$2,$3,$4 -          elsif /<:(.+?)>\s*(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @format,@text,@ocn=$1,$2,$3 -          elsif /^(([1-6])~(\S+))\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;[um]\d+><#@dp:#@dp>$/m.match(@para) -            @@alt_id_count+=1 -            @format,@lev,segname,@text,@ocn=$1,$2,$3,$4,"x#{@@alt_id_count}" -          elsif  /^(([1-6])~)\s+(\S.+?)<~(\d+);[um]\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @@alt_id_count+=1 -            @format,@lev,@text,@ocn=$1,$2,$3,"x#{@@alt_id_count}" -          end -        else -          if /(.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @text,@ocn=$1,$2 -          end -          if @para !~/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$|^$/ #added 2002w06 -            @text=/(.+?)/m.match(@para)[1] -          end -          if /^((\d)~(?:~\S+)?)\s+(.+)/m.match(@para) -            @format,@lev,@text=$1,$2,$3 -          end -        end -        format=@format.dup -        @lev_para_ocn=if @para =~/.+<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ -          Format::Format_text_object.new(format,@text,@ocn) -        else -          Format::Format_text_object.new(format,@text,"<~(\d+);[um]\d+;\w\d+><#@dp:#@dp>") -        end -        self -      end -    end      class Scroll <Source        require "#{SiSU_lib}/defaults"        require "#{SiSU_lib}/shared_txt" @@ -159,7 +112,7 @@ module SiSU_manpage          @url_brace=SiSU_Viz::Skin.new.url_decoration          @vz=SiSU_Env::Get_init.instance.skin          @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -        @regx=/^(?:(?:<:p[bn]>\s*)?\d~(?:(\S+))?\s+)?(.+?)\s*<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m # 2004w18 pb pn removal added +        @regx=/^(?:(?:#{Mx[:br_page]}\s*|#{Mx[:br_page_new]}\s*)?#{Mx[:lv_o]}\d:(\S*?)#{Mx[:lv_c]})?\s*(.+?)\s*#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m # 2004w18 pb pn removal added          @tab="\t"          @br="\n"          @@dostype='unix endnotes' @@ -171,12 +124,12 @@ module SiSU_manpage        end        # Used for extraction of endnotes from paragraphs        def extract_endnotes(para='') -        notes=para.scan(/~[{\[]([\d*+]+\s+.+?)\s*<#@dp>[}\]]~/) +        notes=para.scan(/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})([\d*+]+\s+.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/m)          @n=[]          notes.each do |n| #high cost to deal with <br> appropriately within manpage, consider            n=n.dup.to_s -          if n =~/<br(?: \/)?>/ -            fix = n.split(/<br(?: \/)?>/) #watch #added +          if n =~/#{Mx[:br_line]}/ +            fix = n.split(/\s*#{Mx[:br_line]}+\s*/) #watch #added              fix.each do |x|                unless x.empty?; @n << x                end @@ -201,7 +154,7 @@ module SiSU_manpage  GSUB                        )            else -            wrap.gsub!(/^(.+)\Z/m, <<GSUB +            wrap.gsub!(/^\s*(.+)\Z/m, <<GSUB  \\1  GSUB                        ) @@ -267,9 +220,9 @@ WOK          lv=nil if lv == 0          wrapped=if para[@regx]            paragraph=para[@regx,2] -          if paragraph =~/<:i([1-9])>/ +          if paragraph =~/#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]}/              m=$1.to_i -            paragraph.gsub!(/<:i#{m}>/,'') +            paragraph.gsub!(/#{Mx[:pa_o]}:i#{m}#{Mx[:pa_c]}/,'')              util=SiSU_text_utils::Wrap.new(paragraph,78,m*2)            else util=SiSU_text_utils::Wrap.new(paragraph,78,0)            end @@ -277,6 +230,7 @@ WOK            w.gsub!(/^(\\\.)/,' \1')            w          end +        #wrapped.gsub!(/(?:#{Mx[:br_line]}|#{Mx[:br_nl]})\s*/m,"\n\n") if wrapped          if lv            times=wrapped.length            times=78 if times > 78 @@ -312,106 +266,107 @@ WOK          table_message='[table omitted, see other document formats]'          fix=[]          data.each do |para| -          para.gsub!(/<!Th?¡.+/um,"#@br#{table_message}") +          para.gsub!(/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}.+/um,"#@br#{table_message}")            para.gsub!(/.+?<-#>/,'')                                           # remove dummy headings (used by html) #check -          para.gsub!(/_\*\s+/,'* ')                                          # bullet markup, marked down -          para.gsub!(/<sup>(.+?)<\/sup>/,'^\1^') -          para.gsub!(/<sub>(.+?)<\/sub>/,'[\1]') -          para.gsub!(/<i>(.+?)<\/i>/,'<:br>.I \1<:br>') -          para.gsub!(/\A<b>(.+?)<\/b><br \/>/m,'<:br>.BI \1<:br>') -          para.gsub!(/<b>(.+?)<\/b>/,'<:br>.B \1<:br>') -          para.gsub!(/<u>(.+?)<\/u>/,'<:br>.I \1<:br>') -          unless para =~/<:code>/ +          para.gsub!(/#{Mx[:gl_bullet]}\s*/,'* ')                                          # bullet markup, marked down +          para.gsub!(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,'^\1^') +          para.gsub!(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,'[\1]') +          para.gsub!(/\A\s*#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}#{Mx[:br_line]}/m,"#{Mx[:br_line]}.I \\1#{Mx[:br_line]}") +          para.gsub!(/\s*#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/m,"#{Mx[:br_line]}.I \\1#{Mx[:br_line]}") +          para.gsub!(/\A\s*#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}#{Mx[:br_line]}/m,"#{Mx[:br_line]}.BI \\1#{Mx[:br_line]}") +          para.gsub!(/\s*#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,"#{Mx[:br_line]}.B \\1#{Mx[:br_line]}") +          para.gsub!(/\s*#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,"#{Mx[:br_line]}.I \\1#{Mx[:br_line]}") +          unless para =~/#{Mx[:gr_o]}code#{Mx[:gr_c]}/              para.gsub!(/(?:^|\s)\{(.+?)\}((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([.,]?(?:\s|$))/,"\\1 #{@url_brace.txt_open}\\2#{@url_brace.txt_close}\\3") -            para.gsub!(/(^|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([.,]?(?:\s|$))/,"\\1#{@url_brace.txt_open}\\2#{@url_brace.txt_close}\\3") +            para.gsub!(/(^|#{Mx[:gl_c]}|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([.,]?(?:\s|$))/,"\\1#{@url_brace.txt_open}\\2#{@url_brace.txt_close}\\3")              @manpage[:endnotes]=extract_endnotes(para) -            para.gsub!(/~[{\[]([\d*+]+)\s+(?:.+?)[}\]]~/,'[^\1]') # endnote marker marked up -            para.gsub!(/&/,'&') -            para.gsub!(/!/,'!') -            para.gsub!(/#/,'#') -            para.gsub!(/*/,'*') -            para.gsub!(/-/,'-') -            para.gsub!(///,'/') -            para.gsub!(/_/,'_') -            para.gsub!(/{/,'{') -            para.gsub!(/}/,'}') -            para.gsub!(/~/,'~') -            para.gsub!(/©/,'©') +            para.gsub!(/#{Mx[:en_a_o]}([\d*+]+)\s*(?:.+?)#{Mx[:en_a_c]}/m,'[^\1]') # endnote marker marked up +            para.gsub!(/#{Mx[:en_b_o]}([\d*+]+)\s*(?:.+?)#{Mx[:en_b_c]}/m,'[^\1]') # endnote marker marked up +            #para.gsub!(/~[{\[]([\d*+]+)\s+(?:.+?)[}\]]~/,'[^\1]') # endnote marker marked up +            para.gsub!(/#{Mx[:gl_o]}#amp#{Mx[:gl_c]}/,'&') ##{Mx[:gl_o]}#095#{Mx[:gl_c]} +            para.gsub!(/#{Mx[:gl_o]}#033#{Mx[:gl_c]}/,'!') +            para.gsub!(/#{Mx[:gl_o]}#035#{Mx[:gl_c]}/,'#') +            para.gsub!(/#{Mx[:gl_o]}#042#{Mx[:gl_c]}/,'*') +            para.gsub!(/#{Mx[:gl_o]}#045#{Mx[:gl_c]}/,'-') +            para.gsub!(/#{Mx[:gl_o]}#047#{Mx[:gl_c]}/,'/') +            para.gsub!(/#{Mx[:gl_o]}#095#{Mx[:gl_c]}/,'_') +            para.gsub!(/#{Mx[:gl_o]}#123#{Mx[:gl_c]}/,'{') +            para.gsub!(/#{Mx[:gl_o]}#125#{Mx[:gl_c]}/,'}') +            para.gsub!(/#{Mx[:gl_o]}#126#{Mx[:gl_c]}/,'~') +            para.gsub!(/#{Mx[:gl_o]}#169#{Mx[:gl_c]}/,'©')            end            para.gsub!(/(^| |\s|\*)\\\*/,'\1\\\\\*') #man page requires            para.gsub!(/\s\.(\S+)/,' \\.\1')            para.gsub!(/(\n\.)(\S\S\S+)/m,'\1\\.\2')            para.gsub!(/-/,'\-') #manpages use this            para.gsub!(/~/,'~') if para #manpages use this -          if para =~/<:(?:group|verse|alt|code)(?:-end)?>(?:\s+<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)?/ -            if para =~/<:code>/ #code-block: angle brackets special characters +          if para =~/#{Mx[:gr_o]}(?:group|verse|alt|code)(?:-end)?#{Mx[:gr_c]}(?:\s*#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_c]}#@dp:#@dp#{Mx[:id_c]})?/ +            if para =~/#{Mx[:gr_o]}code#{Mx[:gr_c]}/ #code-block: angle brackets special characters                para.gsub!(/(^|[^}])_([<>])/m,'\1\2') # _> _<                para.gsub!(/(^|[^}])_([<>])/m,'\1\2') # _<_<                #para.gsub!(/(?![}])_([<>])/m,'\1') # _> _<                        }_<              end -            para.gsub!(/<br(?: \/)?>/,"\n\n.P\n\n")                                   # watch -            para.gsub!(/<:(?:group|verse|alt)(?:\\-end)?>(?:\s+<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)?/,'') -            para.gsub!(/<:code>(?:\s+<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)?/,"\n\n.nf\n\n") -            para.gsub!(/<:code\\-end>(?:\s+<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)?/,"\n\n.fi\n\n") +            para.gsub!(/(?:#{Mx[:br_line]}|#{Mx[:br_nl]})+\s*/,"\n\n.BR\n\n")                                   # watch +            para.gsub!(/#{Mx[:gr_o]}(?:group|verse|alt)(?:\\-end)?#{Mx[:gr_c]}(?:\s+#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]})?/,'') +            para.gsub!(/#{Mx[:gr_o]}code#{Mx[:gr_c]}(?:\s*#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]})?/,"\n\n.nf\n\n") +            para.gsub!(/#{Mx[:gr_o]}code\\-end#{Mx[:gr_c]}(?:\s*#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]})?/,"\n\n.fi\n\n")            else -            para.gsub!(/<br(?: \/)?>/,"\n\n")                                   #watch introduces a bug +            para.gsub!(/(?:#{Mx[:br_line]}|#{Mx[:br_nl]})\s*/,"\n\n") #unless para =~/#{Mx[:lv_o]}\d:/                                   #watch introduces a bug            end            blit=para.scan(/\[[^\]]+\]|[^\[]+/)            blit_array=[]            blit.each do |x|              if x =~/^\[/                x.gsub!(/\s+/,' \ ') #manpages use this -            elsif x =~/\.(?:TP|BI)\s/ -              x.gsub!(/\s+/,' \ ') #manpages use this              else x              end              blit_array << x            end -          para = blit_array.join -          para.gsub!(/\s\\\s+(<:br>|<br(?: \/)?>)/,'\1') #a messy solution -          para.gsub!(/\s(\[)/,' \ \1') #manpages use this -          para.gsub!(/<:p[bn]>/,'')                                         # remove page breaks -          para.gsub!(/^\s*<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/,'') # remove empty lines - check -          para.gsub!(/(^|\s)[_\\]((?:https?|ftp):\/\/\S+?\.[^'"><\s]+?)([.,]?(?:\s|$))/,'\1\2\3') +          para=blit_array.join +          para.gsub!(/#{Mx[:gl_o]}:name#\S+?#{Mx[:gl_c]}/mi,'') #added +          para.gsub!(/\s\\\s+(#{Mx[:br_line]}|#{Mx[:br_nl]})/,'\1') #a messy solution +          para.gsub!(/#{Mx[:br_page]}\s*|#{Mx[:br_page_new]}/,'')                                         # remove page breaks +          para.gsub!(/^\s*#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/,'') # remove empty lines - check +          para.gsub!(/(^|#{Mx[:gl_c]}|\s)[_\\]((?:https?|ftp):\/\/\S+?\.[^'"><\s]+?)([.,]?(?:\s|$))/,'\1\2\3')            para.gsub!(/<a href=".+?">(.+?)<\/a>/m,'\1') -          para.gsub!(/<:name#\S+?>/,'')                                     # remove name links +          para.gsub!(/#{Mx[:mk_o]}name#\S+?#{Mx[:mk_c]}/,'')                                     # remove name links            para.gsub!(/ /,' ')                                          # decide on            para.gsub!(/(["''])/,"\\\\\\1")                                   # quotation marks need escape            para.gsub!(/(?:^|[^_\\])\{(\S+?\.(?:png|jpg|gif)) .+?\}(?:(?:https?|file|ftp):\/\/\S+|image)/,'    [ \1 ]') #"[ #{dir.url.images_local}\/\\1 ]")            para.gsub!(/^(?:^|[^_\\])\{\S+?\.(?:png|jpg|gif)\s+.+?"(.*?)"\s*\}\S+/,'[image: "\1"]')            wordlist=para.scan(/\S+/) -          if para =~/^0~(\S+)\s+(.+?)\Z/m # for headers +          if para =~/^#{Rx[:meta]}\s*(.+?)\Z/m # for headers              d_meta=SiSU_text_utils::Header_scan.new(@md,para).meta              if d_meta; manpage_metadata(d_meta)             end            end -          if para !~/(^0~|<ENDNOTES>|<EOF>)/ +          if para !~/(^#{Rx[:meta]}|#{Mx[:br_eof]}|#{Mx[:br_endnotes]})/              if para =~@regx #/.+?<~\d+;\w\d+;\w\d+>.*/ #watch change                paranum=para[@regx,3]                @p_num=Format::Paragraph_number.new(paranum)              end -            @sto=Split_text_object.new(para).lev_segname_para_ocn +            @sto=SiSU_Structure::Split_text_object.new(@md,para).txt              ### problem in scroll, it appears tables are getting paragraph numbers -            m=/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +            m=/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/              if para =~m \              and para=~/\S+/                para=case @sto.format -              when /^(1)~(?:(\S+))?/ +              when /^(1):(\S*)/                  manpage_structure(para,$1,@sto.ocn,$2)                  @sto.lev_para_ocn.heading_body1 -              when /^(2)~(?:(\S+))?/ +              when /^(2):(\S*)/                  manpage_structure(para,$1,@sto.ocn,$2)                  @sto.lev_para_ocn.heading_body2 -              when /^(3)~(?:(\S+))?/ +              when /^(3):(\S*)/                  manpage_structure(para,$1,@sto.ocn,$2)                  @sto.lev_para_ocn.heading_body3 -              when /^(4)~(\S+)/ # work on see SiSU_text_parts::Split_text_object +              when /^(4):(\S+)/ # work on see SiSU_text_parts::Split_text_object                  manpage_structure(para,$1,@sto.ocn,$2)                  @sto.lev_para_ocn.heading_body4 -              when /^(5)~(?:(\S+))?/ +              when /^(5):(\S*)/                  manpage_structure(para,$1,@sto.ocn,$2)                  @sto.lev_para_ocn.heading_body5 -              when /^(6)~(?:(\S+))?/ +              when /^(6):(\S*)/                  manpage_structure(para,$1,@sto.ocn,$2)                  @sto.lev_para_ocn.heading_body6                #when /^(i1)$/ @@ -440,17 +395,17 @@ WOK              elsif para =~/#{table_message}/                @manpage[:body] << para << @br              elsif para =~/(Note|Endnotes?)/ \ -            and para !~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +            and para !~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/              elsif para =~/(MetaData)/ \ -            and para =~/<~(\d+);[um]\d+;\w\d+><#@dp:#@dp>$/ #debug 2003w46 add rc info ####suspect visit +            and para =~/#{Mx[:id_o]}~(\d+);[um]\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ #debug 2003w46 add rc info ####suspect visit                #formatMono=MonoSiSU.new('<br /><a name="metadata">MetaData</a>')                #para=formatMono.bold_para              elsif para.include? 'Owner Details' \ -            and para !~/<~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +            and para !~/#{Mx[:id_o]}~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                #formatMono=MonoSiSU.new('<br /><a name="owner.details">Owner Details</a>')                #@@manpage[:owner_details]=formatMono.bold_para                #para='' -            elsif para =~/(¡|<!Th?)/u #tables ! +            elsif para =~/(#{Mx[:tc_p]}|#{Mx[:gr_o]}Th?)/u #tables !              elsif para =~/(.*)<!#!>(.*)/                one,two=$1,$2                format_text=Format_text_object.new(one,two) @@ -461,7 +416,7 @@ WOK                para=''              end              case para -            when /<:i[1-9]>/ +            when /#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]}/                if para =~/.*<:#>.*$/m                  format_text=Format_text_object.new(para,'')                  para=format_text.scr_indent_one_no_paranum @@ -475,10 +430,14 @@ WOK                format_text=Format_text_object.new(one,two)                para=format_text.center              end -            para.gsub!(/~/,'~') if para #manpages use this -            para.gsub!(/{/,'{') if para #manpages use this +            para.gsub!(/\s(\[)/m,' \ \1') if para #manpages use this +            para.gsub!(/(?:#{Mx[:br_line]}|#{Mx[:br_nl]})/,"\n\n") if para +            para.gsub!(/#{Mx[:gl_o]}#126#{Mx[:gl_c]}/,'~') if para #manpages use this +            para.gsub!(/#{Mx[:gl_o]}#123#{Mx[:gl_c]}/,'{') if para #manpages use this +            para.gsub!(/#{Mx[:pa_o]}\S+#{Mx[:pa_c]}/,' ') if para ## Clean Prepared Text              para.gsub!(/<!.+!>/,' ') if para ## Clean Prepared Text              para.gsub!(/<:\S+>/,' ') if para ## Clean Prepared Text +            para            end          end          @manpage diff --git a/lib/sisu/v0/manpage_format.rb b/lib/sisu/v0/manpage_format.rb index 978cc6b4..02fbf216 100644 --- a/lib/sisu/v0/manpage_format.rb +++ b/lib/sisu/v0/manpage_format.rb @@ -81,10 +81,10 @@ module Format      def initialize(one,two,three)        one.gsub!(/\.(html|pdf|php)/,'') if one =~/\.\.\/\S+/        @one,@two,@three=one,two,three -      rgx=/^[1-6-]~/ +      rgx=/^#{Mx[:lv_o]}[1-6-]:/        @one.gsub!(rgx,'') if @one =~rgx        @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -      rgx=/~\{[\d*+]+\s+(.+?)<#@dp>\}~/ +      rgx=/#{Mx[:en_a_o]}[\d*+]+\s+(.+?)#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/        @one.gsub!(rgx,'\1') if @one =~rgx        @link,@linkname=one,two        @vz=SiSU_Env::Get_init.instance.skin diff --git a/lib/sisu/v0/odf.rb b/lib/sisu/v0/odf.rb index 1883bdba..09c67ff6 100644 --- a/lib/sisu/v0/odf.rb +++ b/lib/sisu/v0/odf.rb @@ -68,6 +68,7 @@ module SiSU_ODF    require "#{SiSU_lib}/odf_format"    include SiSU_ODF_format    require "#{SiSU_lib}/shared_txt" +  require "#{SiSU_lib}/shared_structure"    @@alt_id_count,@@alt_id_count,@@tablehead,@@number_of_cols=0,0,0,0    class Source      require 'zlib' @@ -100,55 +101,6 @@ module SiSU_ODF        end      end      private -    class Split_text_object <Source -      require "#{SiSU_lib}/odf_format" -      include SiSU_Viz -      include SiSU_ODF_format -      @@dp=nil -      @@alt_id_count=0 -      attr_reader :format,:lev,:text,:ocn,:lev_para_ocn -      def initialize(para) -        @para=para -        @format,@ocn='null','null' -        #@format,@ocn=nil,nil -        @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -      end -      def lev_segname_para_ocn -        @text=nil -        if @para =~/^(\d~|<:.+?>).+?<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ -          if /^(([1-6])~(\S+))\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @format,@lev,segname,@text,@ocn=$1,$2,$3,$4,$5 -          elsif  /^(([1-6])~)\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @format,@lev,@text,@ocn=$1,$2,$3,$4 -          elsif /<:(.+?)>\s*(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @format,@text,@ocn=$1,$2,$3 -          elsif /^(([1-6])~(\S+))\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;[um]\d+><#@dp:#@dp>$/m.match(@para) -            @@alt_id_count+=1 -            @format,@lev,segname,@text,@ocn=$1,$2,$3,$4,"x#{@@alt_id_count}" -          elsif  /^(([1-6])~)\s+(\S.+?)<~(\d+);[um]\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @@alt_id_count+=1 -            @format,@lev,@text,@ocn=$1,$2,$3,"x#{@@alt_id_count}" -          end -        else -          if /(.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @text,@ocn=$1,$2 -          end -          if @para !~/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$|^$/ -            @text=/(.+?)/im.match(@para)[1] -          end -          if /^((\d)~(?:~\S+)?)\s+(.+)/m.match(@para) -            @format,@lev,@text=$1,$2,$3 -          end -        end -        format=@format.dup -        @lev_para_ocn=if @para =~/.+<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ -          SiSU_ODF_format::Format_text_object.new(format,@text,@ocn) -        else -          SiSU_ODF_format::Format_text_object.new(format,@text,"<~(\d+);[um]\d+;\w\d+><#@dp:#@dp>") -        end -        self -      end -    end      class Scroll <Source        require "#{SiSU_lib}/defaults"        require "#{SiSU_lib}/shared_txt" @@ -160,8 +112,8 @@ module SiSU_ODF          @env,@md,@dal_array=particulars.env,particulars.md,particulars.dal_array          @vz=SiSU_Env::Get_init.instance.skin          @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -        @regx=/^(?:(?:<:p[bn]>\s*)?\d~(?:(\S+))?\s+)?(.+?)\s*<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ -        @serial=/\s*<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>\s*/ +        @regx=/^(?:(?:#{Mx[:br_page]}\s*|#{Mx[:br_page_new]}\s*)?#{Mx[:lv_o]}\d:(\S*?)#{Mx[:lv_c]})?\s*(.+?)\s*#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ +        @serial=/\s*#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}\s*/          @tab="\t"          @url_brace=SiSU_Viz::Skin.new.url_decoration          @br=if @md.cmd =~/M/; "\n" @@ -176,12 +128,12 @@ module SiSU_ODF        end        # Used for extraction of endnotes from paragraphs        def extract_endnotes(para='') -        notes=para.scan(/~\{(\d+\s+.+?)\s*<#@dp>\}~/) +        notes=para.scan(/#{Mx[:en_a_o]}(\d+\s+.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/)          @n=[]          notes.each do |n| #high cost to deal with <br> appropriately within odf, consider            n=n.dup.to_s -          if n =~/<:?br(?: \/)?>/ -            fix=n.split(/<:?br(?: \/)?>/) #watch #added +          if n =~/#{Mx[:br_line]}/ +            fix=n.split(/#{Mx[:br_line]}/) #watch #added              fix.each do |x|                if x =~/\S+/; @n << x                end @@ -210,8 +162,8 @@ module SiSU_ODF        end        def heading(para,no)          para.gsub!(@serial,'') -        para.gsub!(/<:name#\S+?>/,'') -        para.gsub!(/^([1-6])~\S*\s/,'') +        para.gsub!(/#{Mx[:mk_o]}:name#\S+?#{Mx[:mk_c]}/,'') +        para.gsub!(/^#{Mx[:lv_o]}(\d):\S*?#{Mx[:lv_c]}\s*/,'')          m=/#{$1}/          breakpage=''          if @md.fns \ @@ -307,19 +259,19 @@ module SiSU_ODF        def normal(para)                                                           #P1 - P3          para.gsub!(@serial,'')          para.gsub!(/\b[_\\]((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/, -          %{<text:a xlink:type="simple" xlink:href="\\1">\\1</text:a>\\2}) #http ftp matches escaped, no decoration +          '<text:a xlink:type="simple" xlink:href="\1">\1</text:a>\2') #http ftp matches escaped, no decoration          para.gsub!(/((?:^|\s)[}])((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/,            '\1<text:a xlink:type="simple" xlink:href="\2">\2</text:a>\3') #special case \{ e.g. \}http://url -        para.gsub!(/(^|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/, +        para.gsub!(/(^|#{Mx[:gl_c]}|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/,            %{\\1#{@url_brace.xml_open}<text:a xlink:type="simple" xlink:href="\\2">\\2</text:a>#{@url_brace.xml_close}\\3}) #http ftp matches with decoration          #para.gsub!(/\b((?:https?|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/, also works            #%{#{@url_brace.xml_open}<text:a xlink:type="simple" xlink:href="\\1">\\1</text:a>#{@url_brace.xml_close}\\2}) #http ftp matches with decoration          para.gsub!(/([a-zA-Z0-9._-]+@[a-zA-Z0-9._-]+)/,            %{#{@url_brace.xml_open}<text:a xlink:type="simple" xlink:href="mailto:\\1">\\1</text:a>#{@url_brace.xml_close}})          para=case para -        when /^<:i([1-9])>\s/m +        when /^#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]}/m            m=$1 -          para.gsub!(/^<:i#{m}>\s/m,'') +          para.gsub!(/^#{Mx[:pa_o]}:i#{m}#{Mx[:pa_c]}/m,'')            %{<text:p text:style-name="P1#{m}">#{para}</text:p>}          else %{<text:p text:style-name="P1">#{para}</text:p>}          end @@ -331,24 +283,24 @@ module SiSU_ODF        end        def footnote(para)          @astx||=10000 -        para.gsub!(/<#@dp>([}\]]~)/,'\1') +        para.gsub!(/#{Mx[:id_o]}#@dp#{Mx[:id_c]}(#{Mx[:en_a_c]}|#{Mx[:en_a_c]})/,'\1')          #para.gsub!(/<br \/><:i[1-9]>/,'<br />') -       if para =~/~\{\d+\s+/ -          para=para.gsub(/~\{(\d+)\s+(.+?)\}~/,'<text:note text:id="ftn\1" text:note-class="footnote"><text:note-citation>\1</text:note-citation><text:note-body><text:p text:style-name="Footnote"> \2</text:p><text:p text:style-name="Footnote"/></text:note-body></text:note>') +       if para =~/#{Mx[:en_a_o]}\d+\s+/ +          para=para.gsub(/#{Mx[:en_a_o]}(\d+)\s+(.+?)#{Mx[:en_a_c]}/,'<text:note text:id="ftn\1" text:note-class="footnote"><text:note-citation>\1</text:note-citation><text:note-body><text:p text:style-name="Footnote"> \2</text:p><text:p text:style-name="Footnote"/></text:note-body></text:note>')          end -        if para=~/~\[[*+]\d+\s/ #editor notes, squre bracket series -          asterisk=para.scan(/~\[([*+]\d+)\s+(.+?)\]~/) +        if para=~/#{Mx[:en_b_o]}[*+]\d+\s/ #editor notes, squre bracket series +          asterisk=para.scan(/#{Mx[:en_b_o]}([*+]\d+)\s+(.+?)#{Mx[:en_b_c]}/)            asterisk.each do |x|              a=x[0].gsub(/([*+])/,"\\\\\\1") -            para=para.gsub(/~\[(#{a})\s+(.+?)\]~/,%{<text:note text:id="ftn#{@astx.to_s}" text:note-class="footnote"><text:note-citation text:label="\\1">\\1</text:note-citation><text:note-body><text:p text:style-name="Footnote"> \\2</text:p><text:p text:style-name="Footnote"/></text:note-body></text:note>}) +            para=para.gsub(/#{Mx[:en_b_o]}(#{a})\s+(.+?)#{Mx[:en_b_c]}/,%{<text:note text:id="ftn#{@astx.to_s}" text:note-class="footnote"><text:note-citation text:label="\\1">\\1</text:note-citation><text:note-body><text:p text:style-name="Footnote"> \\2</text:p><text:p text:style-name="Footnote"/></text:note-body></text:note>})              @astx+=1            end          end -        if para=~/~\{[*+]+\s/ -          asterisk=para.scan(/~\{([*+]+)\s+(.+?)\}~/) +        if para=~/#{Mx[:en_a_o]}[*+]+\s/ +          asterisk=para.scan(/#{Mx[:en_a_o]}([*+]+)\s+(.+?)#{Mx[:en_a_c]}/)            asterisk.each do |x|              a=x[0].gsub(/([*+])/,"\\\\\\1") -            para=para.gsub(/~\{(#{a})\s+(.+?)\}~/,%{<text:note text:id="ftn#{@astx.to_s}" text:note-class="footnote"><text:note-citation text:label="\\1">\\1</text:note-citation><text:note-body><text:p text:style-name="Footnote"> \\2</text:p><text:p text:style-name="Footnote"/></text:note-body></text:note>}) +            para=para.gsub(/#{Mx[:en_a_o]}(#{a})\s+(.+?)#{Mx[:en_a_c]}/,%{<text:note text:id="ftn#{@astx.to_s}" text:note-class="footnote"><text:note-citation text:label="\\1">\\1</text:note-citation><text:note-body><text:p text:style-name="Footnote"> \\2</text:p><text:p text:style-name="Footnote"/></text:note-body></text:note>})              @astx+=1            end          end @@ -358,15 +310,16 @@ module SiSU_ODF          para.gsub!(/&nbsp;| /,' ')          para.gsub!(/</,'<'); para.gsub!(/>/,'>')          para.gsub!(/<(text:span text:style-name="T[1-5]"|\/text:span)>/,'<\1>') #works, not ideal +        para.gsub!(/#{Mx[:br_line]}/,'<br />')          para.gsub!(/<br(?:\s+\/)?>/,'<br />')          #para.gsub!(/\s\s/,'  ')          para        end        def poem(para)                                                             #P4 #same as group          para.gsub!(@serial,'') -        para.gsub!(/<:verse(?:-end)?>\s*/m,'') +        para.gsub!(/#{Mx[:gr_o]}verse(?:-end)?#{Mx[:gr_c]}\s*/m,'')          parray=[] -        para.split(/<:?br(?: \/)?>/).each do |parablock| +        para.split(/#{Mx[:br_line]}|#{Mx[:br_nl]}/).each do |parablock|            parablock=group_clean(parablock)            parray << %{<text:p text:style-name="P4">#{parablock}</text:p>} if parablock =~/\S+/          end @@ -374,9 +327,9 @@ module SiSU_ODF        end        def group(para)                                                            #P4 #same as verse          para.gsub!(@serial,'') -        para.gsub!(/<:group(?:-end)?>\s*/m,'') +        para.gsub!(/#{Mx[:gr_o]}group(?:-end)?#{Mx[:gr_c]}\s*/m,'')          parray=[] -        para.split(/<:?br(?: \/)?>/).each do |parablock| +        para.split(/#{Mx[:br_line]}|#{Mx[:br_nl]}/).each do |parablock|            parablock=group_clean(parablock)            parablock.gsub!(/<text:a xlink:type="simple" xlink:href="(.+?)">/m,'<text:a xlink:type="simple" xlink:href="\1">')            parablock.gsub!(/<(\/text:a)>/,'<\1>') @@ -390,21 +343,21 @@ module SiSU_ODF        end        def code(para)                                                             #P5          para.gsub!(@serial,'') -        para.gsub!(/<:code(?:-end)?>\s*/m,'') +        para.gsub!(/#{Mx[:gr_o]}code(?:-end)?#{Mx[:gr_c]}\s*/m,'')          para.gsub!(/\s\s/,'  ')          parray=[] -        para.split(/<:?br(?: \/)?>/).each do |parablock| +        para.split(/#{Mx[:br_line]}|#{Mx[:br_nl]}/).each do |parablock|            parablock=group_clean(parablock)            parablock.gsub!(/^\s*$/,'<br />')            parablock.gsub!(/\b[_\\]((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/, -            %{<text:a xlink:type="simple" xlink:href="\\1">\\1</text:a>\\2}) #http ftp matches escaped, no decoration +            '<text:a xlink:type="simple" xlink:href="\1">\1</text:a>\2') #http ftp matches escaped, no decoration            parray << %{<text:p text:style-name="P5">#{parablock}</text:p>} if parablock =~/\S+/          end          para=parray.join + '<text:p text:style-name="Standard"/>'          para        end        def table(para)                                                            # -        if para =~/<!Th?.+/ # tables come as single block +        if para =~/#{Mx[:gr_o]}Th?.+/ # tables come as single block            table=SiSU_ODF_format::Table.new(@md,para)            para=table.table_split          end @@ -414,7 +367,7 @@ module SiSU_ODF          n=lv - 1          n3=lv + 2          lv=nil if lv == 0 -        para=unless para=~/^<:code>/ +        para=unless para=~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/            para=if para =~/\{\s*\S+?\.(?:png|jpg|gif)\s.+?\}(?:(?:https?|file|ftp):\S+|image)/; image(para)            elsif para =~/\{.+?\}(?:(?:https?|file|ftp):\S+|image)/; text_link(para)            else para @@ -431,16 +384,16 @@ module SiSU_ODF            when 5; heading(para,'5') << @br*2            when 6; heading(para,'6') << @br*2            end -        elsif para =~ /<:verse(?:-end)?>/ +        elsif para =~ /#{Mx[:gr_o]}verse(?:-end)?#{Mx[:gr_c]}/            @@odf[:body] << poem(para)            @@odf[:body] << @br*2 -        elsif para =~ /<:group(?:-end)?>/ +        elsif para =~ /#{Mx[:gr_o]}group(?:-end)?#{Mx[:gr_c]}/            @@odf[:body] << group(para)            @@odf[:body] << @br*2 -        elsif para =~ /<:code(?:-end)?>/ +        elsif para =~ /#{Mx[:gr_o]}code(?:-end)?#{Mx[:gr_c]}/            @@odf[:body] << code(para)            @@odf[:body] << @br*2 -        elsif para =~ /<!Th?/ #elsif para =~ /<!Th?¡/u +        elsif para =~ /#{Mx[:gr_o]}Th?/ #elsif para =~ /<!Th?¡/u            @@odf[:body] << table(para)            @@odf[:body] << @br*2          else @@ -457,7 +410,7 @@ module SiSU_ODF          wordlist        end        def markup(data)                                                                 # Used for major markup instructions -        safe_characters=/[^a-zA-Z0-9}{\/?,."';:)(><\-_&!@%~#\]\[*=$| \n+`¡]/u +        safe_characters=/[^a-zA-Z0-9}{\/?,."';:)(><\-_&!@%~#\]\[*=$| \n+`#{Mx[:tc_p]}]/u          dir=SiSU_Env::Info_env.new(@md.fns)          @data_mod,@endnotes,@level,@cont,@copen,@odf_contents_close=Array.new(6){[]}          @rcdc=false @@ -474,10 +427,10 @@ module SiSU_ODF            word=para.scan(/\S+|\n/)            if word              word.each do |w| # _ - / # | : ! ^ ~ -              unless w =~/<~\S+?;\S+?;\S+?><#@dp:#@dp>|<[:!][^<>]+?>|^<\/?(?:del|ins|sub|sup|cite)>$/ +              unless w =~/#{Mx[:id_o]}~\S+?;\S+?;\S+?#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}|#{Mx[:gr_o]}.+?#{Mx[:gr_c]}|<[:!][^<>]+?>/                  w.gsub!(/^<([^<>][^<>][^<>][^<>]+?)>$/,'<\1>') #refix                end -              unless para =~/^(?:0~|%+ )/m +              unless para =~/^(?:#{Rx[:meta]}|%+ )/m                  w.gsub!(/&#(?:126|152);/,'~') #126 usual                  if w !~/&\S{1,7};/ \                  or w =~/ / @@ -489,24 +442,32 @@ module SiSU_ODF              para=para_array.join(' ')              para=para.strip            end -          if para =~/<:code>/ #code-block: angle brackets special characters +          if para =~/#{Mx[:gr_o]}code#{Mx[:gr_c]}/ #code-block: angle brackets special characters              para.gsub!(/(^|[^}])_</m,'\1<'); para.gsub!(/(^|[^}])_>/m,'\1>')              para.gsub!(/(^|[^}])_</m,'\1<'); para.gsub!(/(^|[^}])_>/m,'\1>')            end -          para.gsub!(/^(<:i[1-9]>\s+)?_\*\s+/,'\1<draw:frame draw:style-name="gr1" text:anchor-type="as-char" svg:width="0.22cm" svg:height="0.22cm" draw:z-index="2"><draw:image xlink:href="Pictures/bullet_09.png" xlink:type="simple" xlink:show="embed" xlink:actuate="onLoad"/></draw:frame> ') # bullet_09.png +          para.gsub!(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'<del>\1</del>') +          para.gsub!(/#{Mx[:fa_insert_o]}(.+?)#{Mx[:fa_insert_c]}/,'<ins>\1</ins>') +          para.gsub!(/#{Mx[:fa_cite_o]}(.+?)#{Mx[:fa_cite_c]}/,'<cite>\1</cite>') +          para.gsub!(/#{Mx[:mk_o]}:name#\S+?#{Mx[:mk_c]}/,'') +          para.gsub!(/#{Mx[:mk_o]}#([a-zA-Z]+)#{Mx[:mk_c]}/,'&\1;') +          para.gsub!(/#{Mx[:mk_o]}(#[0-9]+)#{Mx[:mk_c]}/,'&\1;') +          para.gsub!(/#{Mx[:mk_o]}[~-]##{Mx[:mk_c]}/,'') +          para.gsub!(/^(#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]}\s*)?#{Mx[:gl_bullet]}/,'\1<draw:frame draw:style-name="gr1" text:anchor-type="as-char" svg:width="0.22cm" svg:height="0.22cm" draw:z-index="2"><draw:image xlink:href="Pictures/bullet_09.png" xlink:type="simple" xlink:show="embed" xlink:actuate="onLoad"/></draw:frame> ') # bullet_09.png            #para.gsub!(/^(<:i[1-9]>\s+)?_\*\s+/,'\1<text:span text:style-name="T6">●</text:span> ')     #bullet            #para.gsub!(/^(<:i[1-9]>\s+)?_\*\s+/,'\1● ') # bullet utf8, make smaller if used            #para.gsub!(/^_\*\s+/,'<text:span text:style-name="T6">●</text:span> ')     #bullet -          para.gsub!(/^(<:i[1-9]>)\s+_\*\s+/,'\1 <text:span text:style-name="T6">·</text:span> ') #bullet -          para.gsub!(/<:?br>/,'<br />') -          para.gsub!(/<:p[bn]>/,'<text:p text:style-name="P8"> </text:p>') +          para.gsub!(/^(#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]})\s*#{Mx[:gl_bullet]}/,'\1 <text:span text:style-name="T6">·</text:span> ') #bullet +          para.gsub!(/^#{Mx[:gl_bullet]}/,'<text:span text:style-name="T6">·</text:span> ') #bullet +          para.gsub!(/#{Mx[:br_line]}/,'<br />') +          para.gsub!(/#{Mx[:br_page]}|#{Mx[:br_page_new]}/,'<text:p text:style-name="P8"> </text:p>')            para.gsub!(/©/,'©') #too arbitrary            para.gsub!(/.+?<-#>/,'')                                           # remove dummy headings (used by html) #check -          para.gsub!(/<b>(.+?)<\/b>/,'<text:span text:style-name="T1">\1</text:span>') -          para.gsub!(/<i>(.+?)<\/i>/,'<text:span text:style-name="T2">\1</text:span>') -          para.gsub!(/<u>(.+?)<\/u>/,'<text:span text:style-name="T3">\1</text:span>') -          para.gsub!(/<sup>(.+?)<\/sup>/,'<text:span text:style-name="T4">\1</text:span>') -          para.gsub!(/<sub>(.+?)<\/sub>/,'<text:span text:style-name="T5">\1</text:span>') +          para.gsub!(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'<text:span text:style-name="T1">\1</text:span>') +          para.gsub!(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'<text:span text:style-name="T2">\1</text:span>') +          para.gsub!(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'<text:span text:style-name="T3">\1</text:span>') +          para.gsub!(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,'<text:span text:style-name="T4">\1</text:span>') +          para.gsub!(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,'<text:span text:style-name="T5">\1</text:span>')            para.gsub!(/`/,"'")            para.gsub!(//u,'-')            para.gsub!(/·/u,'*') @@ -520,10 +481,10 @@ module SiSU_ODF            para.gsub!(/\44/,'$') #$ watch            #para.gsub!(/^·/,'_*') #$ watch            #para.gsub!(/·/,'*') #$ watch -          para.gsub!(/<:p[bn]>/,'')                                         # remove page breaks -          para.gsub!(/^\s*<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>/,'') # remove empty lines +          para.gsub!(/#{Mx[:br_page]}|#{Mx[:br_page_new]}/,'')                                         # remove page breaks +          para.gsub!(/^\s*#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}/,'') # remove empty lines            para.gsub!(/<a href=".+?">(.+?)<\/a>/,'\1') -          para.gsub!(/<:name#\S+?>/,'')                                       # remove name links +          para.gsub!(/#{Mx[:mk_o]}name#\S+?#{Mx[:mk_c]}/,'')                                       # remove name links  #          para.gsub!(/<a href=".+?">(.+?)<\/a>/im,'\1')            #para.gsub!(/ /,' ')                                            # decide on            #para.gsub!(/\{(\S+?\.(?:png|jpg)) .+?\}(?:http:\/\/\S+|image)/,"    [ \\1 ]") #"[ #{@env.url.images_local}\/\\1 ]") @@ -533,38 +494,44 @@ module SiSU_ODF            #para.gsub!(/^(\{\S+?\.(?:png|jpg)\s+.+?"(.*?)"\s*\}\S+)/,"\\1 \n [image: \"\\2\"]")            wordlist=para.scan(/\S+/)            para=tidywords(wordlist).join(' ').strip -          if para =~/^0~(\S+)\s+(.+?)\Z/m # for headers +          if para =~/^#{Rx[:meta]}(\S+)\s+(.+?)\Z/m # for headers              d_meta=SiSU_text_utils::Header_scan.new(@md,para).meta              if d_meta; odf_metadata(d_meta)              end            end            @rcdc=true if @rcdc==false \ -          and (para =~/~metadata/ or para =~/1~meta\s+Document Information/) -          if para !~/(^0~|<ENDNOTES>|<EOF>)/ +          and (para =~/~metadata/ or para =~/#{Mx[:lv_o]}1:meta#{Mx[:lv_x]}\s*Document Information/) +          if para !~/(^#{Rx[:meta]}|#{Mx[:br_eof]}|#{Mx[:br_endnotes]})/              if para =~@regx #/.+?<~\d+;\w\d+;\w\d+>.*/ #watch change                paranum=para[@regx,3]                @p_num=SiSU_ODF_format::Paragraph_number.new(paranum)              end -            @sto=Split_text_object.new(para).lev_segname_para_ocn +            @sto=SiSU_Structure::Split_text_object.new(@md,para).odt              #<office:annotation><dc:date>yyyy-mm-ddT00:00:00</dc:date><text:p>#{ocn}</text:p></office:annotation> #followed immediately by paragraph closure              ### problem in scroll, it appears tables are getting paragraph numbers              unless @rcdc -              m=/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +              m=/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                if para =~m \                and para=~/\S+/                  para=case @sto.format -                when /^(1)~(?:(\S+))?/; odf_structure(para,$1,@sto.ocn,$2) +                when /^(1):(\S*)/ +                  odf_structure(para,$1,@sto.ocn,$2)                    para -                when /^(2)~(?:(\S+))?/; odf_structure(para,$1,@sto.ocn,$2) +                when /^(2):(\S*)/ +                  odf_structure(para,$1,@sto.ocn,$2)                    para -                when /^(3)~(?:(\S+))?/; odf_structure(para,$1,@sto.ocn,$2) +                when /^(3):(\S*)/ +                  odf_structure(para,$1,@sto.ocn,$2)                    para -                when /^(4)~(\S+)/;      odf_structure(para,$1,@sto.ocn,$2) +                when /^(4):(\S+)/ # work on see Split_text_object +                  odf_structure(para,$1,@sto.ocn,$2)                    # work on see SiSU_text_parts::Split_text_object                    para -                when /^(5)~(?:(\S+))?/; odf_structure(para,$1,@sto.ocn,$2) +                when /^(5):(\S*)/ +                  odf_structure(para,$1,@sto.ocn,$2)                    para -                when /^(6)~(?:(\S+))?/; odf_structure(para,$1,@sto.ocn,$2) +                when /^(6):(\S*)/ +                  odf_structure(para,$1,@sto.ocn,$2)                    para                    #@sto.lev_para_ocn.heading_body6                  #when /^(i1)$/ @@ -610,12 +577,14 @@ module SiSU_ODF                if para =~ /^(4)~(\S+)/                  odf_structure(para,$1,@sto.ocn,$2)                  para -              elsif para =~/<~(\d+);m\d+;[mdv]\d+><#@dp:#@dp>$/ +              elsif para =~/#{Mx[:id_o]}~(\d+);m\d+;[mdv]\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                  odf_structure(para,nil,nil,nil) #watch may be problematic                  para                end              end              para.gsub!(/<!.+!>/,' ') if para ## Clean Prepared Text +            para.gsub!(/#{Mx[:gr_o]}.+?#{Mx[:gr_c]}/,' ') if para ## CHECK Clean Prepared Text +            para.gsub!(/#{Mx[:tc_o]}.+?#{Mx[:tc_c]}/,' ') if para ## CHECK Clean Prepared Text              para.gsub!(/<:\S+>/,' ') if para ## Clean Prepared Text            end          end @@ -668,7 +637,6 @@ module SiSU_ODF            %{<style:style style:name="P8" style:family="paragraph" style:parent-style-name="Standard"><style:paragraph-properties fo:break-before="page"/></style:style>#@br} +            %{<style:style style:name="P9" style:family="paragraph" style:parent-style-name="Standard"><style:paragraph-properties fo:break-after="page"/></style:style>#@br} +            %{<style:style style:name="P10" style:family="paragraph" style:parent-style-name="Standard"><style:paragraph-properties  fo:margin-top="0.199cm" fo:margin-bottom="0.199cm" fo:line-height="150%" fo:text-align="justify" style:justify-single-word="false"/></style:style>#@br} + # P1 -            %{<style:style style:name="P11" style:family="paragraph" style:parent-style-name="Standard"><style:paragraph-properties  fo:margin-top="0.199cm" fo:margin-bottom="0.199cm" fo:line-height="150%" fo:margin-left="1cm" fo:margin-right="0cm" fo:text-align="justify" style:justify-single-word="false" fo:text-indent="0cm" style:auto-text-indent="false"/></style:style>#@br} +            %{<style:style style:name="P12" style:family="paragraph" style:parent-style-name="Standard"><style:paragraph-properties  fo:margin-top="0.199cm" fo:margin-bottom="0.199cm" fo:line-height="150%" fo:margin-left="2cm" fo:margin-right="0cm" fo:text-align="justify" style:justify-single-word="false" fo:text-indent="0cm" style:auto-text-indent="false"/></style:style>#@br} +            %{<style:style style:name="P13" style:family="paragraph" style:parent-style-name="Standard"><style:paragraph-properties  fo:margin-top="0.199cm" fo:margin-bottom="0.199cm" fo:line-height="150%" fo:margin-left="3cm" fo:margin-right="0cm" fo:text-align="justify" style:justify-single-word="false" fo:text-indent="0cm" style:auto-text-indent="false"/></style:style>#@br} + diff --git a/lib/sisu/v0/odf_format.rb b/lib/sisu/v0/odf_format.rb index 3a6d0d94..05e4a918 100644 --- a/lib/sisu/v0/odf_format.rb +++ b/lib/sisu/v0/odf_format.rb @@ -81,10 +81,10 @@ module SiSU_ODF_format      def initialize(one,two,three)        one.gsub!(/\.(html|pdf|php)/,'') if one =~/\.\.\/\S+/        @one,@two,@three=one,two,three -      rgx=/^[1-6-]~/ +      rgx=/^#{Mx[:lv_o]}[1-6-]:/        @one.gsub!(rgx,'') if @one =~rgx        @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -      rgx=/~\{\d+\s+(.+?)<#@dp>\}~/ +      rgx=/#{Mx[:en_a_o]}\d+\s+(.+?)#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/        @one.gsub!(rgx,'\1') if @one =~rgx        @link,@linkname=one,two        @vz=SiSU_Env::Get_init.instance.skin @@ -178,45 +178,45 @@ module SiSU_ODF_format      end      def table        @parablock='' if @parablock =~/^<!$/ -      @parablock.gsub!(/<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>/,'') +      @parablock.gsub!(/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}/,'')        m=@parablock[/<!f(.+?)!>/,1]        @@tablefoot << m if m        @parablock.gsub!(/<!f.+?!>/,'') -      @@tablehead=1 if @parablock =~/<!Th¡/u -      @@table_counter+=1  if @parablock =~/<!Th?¡/u -      if @parablock =~/<!Th¡\s+c(\d+).+?!~\d+;\w\d+;\w\d+>/u; @parablock=table_head(@@table_counter,$1,true) -      elsif @parablock =~/<!T¡\s+c(\d+).+?!~\d+;\w\d+;\w\d+>/u; @parablock=table_head(@@table_counter,$1) +      @@tablehead=1 if @parablock =~/#{Mx[:gr_o]}Th#{Mx[:tc_p]}/u +      @@table_counter+=1  if @parablock =~/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}/u +      if @parablock =~/#{Mx[:gr_o]}Th#{Mx[:tc_p]}\s+c(\d+).+?#{Mx[:tc_p]}~\d+;\w\d+;\w\d+#{Mx[:gr_c]}/u; @parablock=table_head(@@table_counter,$1,true) +      elsif @parablock =~/#{Mx[:gr_o]}T#{Mx[:tc_p]}\s+c(\d+).+?#{Mx[:tc_p]}~\d+;\w\d+;\w\d+#{Mx[:gr_c]}/u; @parablock=table_head(@@table_counter,$1)        end -      if @parablock =~/<!TZ!>/ +      if @parablock =~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/          tablefoot=[]          @@tablefoot.each {|x| tablefoot << ''}          @@tablefoot=[] -        if @parablock =~/<!TZ!>/; @parablock=table_end +        if @parablock =~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/; @parablock=table_end          end        end        if @@tablehead == 1 -        if @parablock =~/¡¡/u -          if @parablock =~/<!¡¡(\d+?)¡/u -            @parablock.gsub!(/<!¡¡(\d+?)¡/u,table_row($1,true)) +        if @parablock =~/#{Mx[:tc_p]}#{Mx[:tc_p]}/u +          if @parablock =~/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u +            @parablock.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,table_row($1,true))            end -          if @parablock =~/¡¡(\d+?)¡/u -            @parablock.gsub!(/¡¡(\d+?)¡/u,table_cell($1,true)) +          if @parablock =~/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u +            @parablock.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,table_cell($1,true))            end -          if @parablock =~/!>/ -            @parablock.gsub!(/!>/,table_row_close(true)) +          if @parablock =~/#{Mx[:tc_c]}/ +            @parablock.gsub!(/#{Mx[:tc_c]}/,table_row_close(true))            end            @@tablehead=0          end          @parablock        else -        if @parablock =~/<!¡¡(\d+?)¡/u -          @parablock.gsub!(/<!¡¡(\d+?)¡/u,table_row($1)) +        if @parablock =~/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u +          @parablock.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,table_row($1))          end -        if @parablock =~/¡¡(\d+?)¡/u -          @parablock.gsub!(/¡¡(\d+?)¡/u,table_cell($1)) +        if @parablock =~/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u +          @parablock.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,table_cell($1))          end -        if @parablock =~/!>/ -          @parablock.gsub!(/!>/,table_row_close) +        if @parablock =~/#{Mx[:tc_c]}/ +          @parablock.gsub!(/#{Mx[:tc_c]}/,table_row_close)          end          @parablock        end @@ -224,8 +224,12 @@ module SiSU_ODF_format      end      def table_split        @new_content=[] -      @one.split(/\s*<!/).each do |parablock| -        table=Table.new(@md,"<!#{parablock}") +      @one.split(/\s*#{Mx[:tc_o]}/).each do |parablock| +        table=if parablock =~/#{Mx[:gr_o]}/ +          Table.new(@md,"#{parablock}") +        else +          Table.new(@md,"#{Mx[:tc_o]}#{parablock}") +        end          @new_content << table.table        end        @new_content.join diff --git a/lib/sisu/v0/param.rb b/lib/sisu/v0/param.rb index f9d15a22..43b2d862 100644 --- a/lib/sisu/v0/param.rb +++ b/lib/sisu/v0/param.rb @@ -119,7 +119,7 @@ module SiSU_Param        @doc={ :lv=>[] }        @doc[:fns],@doc[:fnb],@doc[:scr_suffix]='','',''        @@publisher='SiSU scribe' -      attr_accessor :cmd,:mod,:env,:fn,:fns,:fnb,:fnn,:fnt,:fnl,:flv,:fnz,:fnstex,:ocn,:sfx_src,:sfx,:pdf,:file_type,:dir_out,:dir_tex,:dir_lout,:txt_path,:site_skin,:sisu,:sisu_version,:ruby_version,:title,:dc_title,:html_title,:subtitle,:subtitle_tex,:creator_home,:dc_creator,:translator,:illustrator,:prepared_by,:digitized_by,:dc_subject,:dc_description,:dc_publisher,:dc_contributor,:dc_date,:dc_date_created,:dc_date_issued,:dc_date_available,:dc_date_valid,:dc_date_modified,:date_scheme,:date_created_scheme,:date_issued_scheme,:date_available_scheme,:date_valid_scheme,:date_modified_scheme,:dc_type,:dc_format,:dc_identifier,:dc_source,:dc_language,:language_original,:dc_relation,:dc_coverage,:dc_rights,:keywords,:comments,:abstract,:cls_loc,:cls_dewey,:cls_pg,:cls_isbn,:papersize,:toc,:lv1,:lv2,:lv3,:lv4,:lv5,:lv6,:pagenew,:pagebreak,:num_top,:toc_lev_limit,:flag_endnotes,:flag_auto_endnotes,:flag_separate_endnotes,:flag_separate_endnotes_make,:flag_auto_heading_num,:markup,:markup_instruction,:markup_version,:markup_declared,:make_bold,:make_italic,:flag_tables,:vocabulary,:doc_skin,:doc_css,:yaml,:lnk,:prefix_a,:prefix_b,:suffix,:information,:contact,:icon,:image,:ad_url,:ad_png,:ad_alt,:ad_began,:flag_promo,:promo,:ad_home,:stmp,:stmpd,:sc_filename,:sc_number,:sc_date,:sc_time,:sc_info,:yamladdr,:locale,:wc_lines,:wc_words,:wc_bytes,:file_encoding,:file_size,:user,:home,:hostname,:pwd,:firstseg,:programs,:creator_copymark,:lang,:en,:dgst,:dgst_skin,:generated,:tags,:tag_array,:concord_make,:seg_names,:seg_autoname_safe,:set_header_title,:set_heading_top,:set_heading_seg,:heading_seg_first,:heading_seg_first_flag,:base_program,:man_section,:man_name,:man_synopsis,:ec,:opt,:sem_tag +      attr_accessor :cmd,:mod,:env,:fn,:fns,:fnb,:fnn,:fnt,:fnl,:flv,:fnz,:fnstex,:ocn,:sfx_src,:sfx,:pdf,:file_type,:dir_out,:dir_tex,:dir_lout,:txt_path,:site_skin,:sisu,:sisu_version,:ruby_version,:title,:dc_title,:html_title,:subtitle,:subtitle_tex,:creator_home,:dc_creator,:translator,:illustrator,:prepared_by,:digitized_by,:dc_subject,:dc_description,:dc_publisher,:dc_contributor,:dc_date,:dc_date_created,:dc_date_issued,:dc_date_available,:dc_date_valid,:dc_date_modified,:date_scheme,:date_created_scheme,:date_issued_scheme,:date_available_scheme,:date_valid_scheme,:date_modified_scheme,:dc_type,:dc_format,:dc_identifier,:dc_source,:dc_language,:language_original,:dc_relation,:dc_coverage,:dc_rights,:keywords,:comments,:abstract,:cls_loc,:cls_dewey,:cls_pg,:cls_isbn,:papersize,:papersize_array,:toc,:lv1,:lv2,:lv3,:lv4,:lv5,:lv6,:pagenew,:pagebreak,:num_top,:toc_lev_limit,:flag_endnotes,:flag_auto_endnotes,:flag_separate_endnotes,:flag_separate_endnotes_make,:flag_auto_heading_num,:markup,:markup_instruction,:markup_version,:markup_declared,:make_bold,:make_italic,:flag_tables,:vocabulary,:doc_skin,:doc_css,:yaml,:lnk,:prefix_a,:prefix_b,:suffix,:information,:contact,:icon,:image,:ad_url,:ad_png,:ad_alt,:ad_began,:flag_promo,:promo,:ad_home,:stmp,:stmpd,:sc_filename,:sc_number,:sc_date,:sc_time,:sc_info,:yamladdr,:locale,:wc_lines,:wc_words,:wc_bytes,:file_encoding,:file_size,:user,:home,:hostname,:pwd,:firstseg,:programs,:creator_copymark,:lang,:en,:dgst,:dgst_skin,:generated,:tags,:tag_array,:concord_make,:seg_names,:seg_autoname_safe,:set_header_title,:set_heading_top,:set_heading_seg,:heading_seg_first,:heading_seg_first_flag,:base_program,:man_section,:man_name,:man_synopsis,:ec,:opt,:sem_tag        def initialize(fns_array,opt)          @env=@fn=@fns=@fnb=@fnn=@fnt=@fnl=@flv=@fnz=@fnstex=@ocn=@sfx_src=@sfx=@pdf=@file_type=@dir_out=@dir_tex=@dir_lout=@txt_path=@flag_endnotes=@flag_auto_endnotes=@flag_separate_endnotes=@flag_separate_endnotes_make=@site_skin=@sisu=@sisu_version=@ruby_version=@title=@dc_title=@html_title=@subtitle=@subtitle_tex=@creator_home=@dc_creator=@translator=@illustrator=@prepared_by=@digitized_by=@dc_subject=@dc_description=@dc_publisher=@dc_contributor=@dc_date=@dc_date_created=@dc_date_issued=@dc_date_available=@dc_date_valid=@dc_date_modified=@date_scheme=@date_created_scheme=@date_issued_scheme=@date_available_scheme=@date_valid_scheme=@date_modified_scheme=@dc_type=@dc_format=@dc_identifier=@dc_source=@dc_language=@language_original=@dc_relation=@dc_coverage=@dc_rights=@keywords=@comments=@abstract=@cls_loc=@cls_dewey=@cls_pg=@cls_isbn=@papersize=@toc=@lv1=@lv2=@lv3=@lv4=@lv5=@lv6=@pagenew=@pagebreak=@num_top=@toc_lev_limit=@flag_auto_heading_num=@make_bold=@make_italic=@flag_tables=@vocabulary=@doc_skin=@doc_css=@yaml=@lnk=@prefix_a=@prefix_b=@suffix=@information=@contact=@icon=@ad_url=@ad_png=@ad_alt=@ad_began=@promo=@ad_home=@stmp=@stmpd=@sc_filename=@sc_number=@sc_date=@sc_time=@sc_info=@yamladdr=@locale=@wc_lines=@wc_words=@wc_bytes=@file_encoding=@file_size=@firstseg=@programs=@creator_copymark=@lang=@en=@dgst=@dgst_skin=@generated=@heading_seg_first=@base_program=@man_synopsis=nil          @man_section=1 @@ -132,6 +132,7 @@ module SiSU_Param          @markup=@markup_instruction #use @markup_instruction          @doc,@fn,@make_italic,@make_bold,@tag_hash,@ec={},{},{},{},{},{},{}          @flv,@lang,@seg_names,@tags,@tag_array,@tag_a,@ec[:image],@ec[:audio],@ec[:multimedia]=Array.new(9){[]} +        @papersize_array=[]          @rgx_image=/(?:^|[^_\\])\{\s*(\S+?\.(?:png|jpg|gif))/          @rgx_audio=/\{\s*(\S+?\.(?:mp3|ogg))/          @rgx_mm=/\{\s*(\S+?\.(?:ogg|mpeg))/ #expand and distinguish ogg @@ -419,17 +420,17 @@ module SiSU_Param                @toc=[ @toc ] if @toc == String                #@toc.each {|x| x.gsub!(/\{/,'\{') } #FIX~                lv1=@toc[0] ||='1~ '                                        #some arbitrary changes made -              @lv1=/^#{lv1}\b/ +              @lv1=/^#{lv1}/                lv2=@toc[1] ||='2~ ' -              @lv2=/^#{lv2}\b/ +              @lv2=/^#{lv2}/                lv3=@toc[2] ||='3~ ' -              @lv3=/^#{lv3}\b/ +              @lv3=/^#{lv3}/                lv4=@toc[3] ||='4~ ' -              @lv4=/^#{lv4}\b/ +              @lv4=/^#{lv4}/                lv5=@toc[4] ||='5~ ' -              @lv5=/^#{lv5}\b/ +              @lv5=/^#{lv5}/                lv6=@toc[5] ||='6~ ' -              @lv6=/^#{lv6}\b/ +              @lv6=/^#{lv6}/              when /^(?:0~(?:level|page|markup)|@(?:level|page|markup):)\s+(.+?)$/m                   #% processing revisit..., use syntax 0~level new=1,2,3; break=4                if para =~/(?:0~|@)(?:markup|level|page):?\s+(.+?)\Z/m                  page_break_str=$1 @@ -548,12 +549,12 @@ module SiSU_Param                  @man_synopsis= x[/synopsis=(.+)/m,1] if x =~/synopsis=.+/                end              end -            @lv1 ||=/^1~/ -            @lv2 ||=/^2~/ -            @lv3 ||=/^3~/ -            @lv4 ||=/^4~/ -            @lv5 ||=/^5~/ -            @lv6 ||=/^6~/ +            @lv1 ||=/^#{Mx[:lv_o]}1:/ +            @lv2 ||=/^#{Mx[:lv_o]}2:/ +            @lv3 ||=/^#{Mx[:lv_o]}3:/ +            @lv4 ||=/^#{Mx[:lv_o]}4:/ +            @lv5 ||=/^#{Mx[:lv_o]}5:/ +            @lv6 ||=/^#{Mx[:lv_o]}6:/            else                                                                   #%              if para =~ /^(?:1|:?A)~/                                                                      #% processing                if para=~/^:?A~/ @@ -696,6 +697,7 @@ module SiSU_Param          or  @mod.inspect =~/--(?:a4|letter|legal|book|a5|b5)\b/i #command line config/header override            @papersize=determine_papersize(@mod.inspect)          end +        @papersize_array=@papersize.scan(/(?:a4|letter|legal|book|a5|b5)/i)          if @sys.openssl !=false            skin=if @doc_skin; SiSU_Env::Info_skin.new(@opt,@doc_skin).select            else               SiSU_Env::Info_skin.new(@opt).select @@ -836,12 +838,12 @@ module SiSU_Param            end          end          @lnk=@lnk.compact if @lnk -        @lv1 ||=/^1~/ -        @lv2 ||=/^2~/ -        @lv3 ||=/^3~/ -        @lv4 ||=/^4~/ -        @lv5 ||=/^5~/ -        @lv6 ||=/^6~/ +        @lv1 ||=/^#{Mx[:lv_o]}1:/ +        @lv2 ||=/^#{Mx[:lv_o]}2:/ +        @lv3 ||=/^#{Mx[:lv_o]}3:/ +        @lv4 ||=/^#{Mx[:lv_o]}4:/ +        @lv5 ||=/^#{Mx[:lv_o]}5:/ +        @lv6 ||=/^#{Mx[:lv_o]}6:/          if @doc_skin            tell=SiSU_Screen::Ansi.new(@cmd,"doc_skin <- #@doc_skin")            tell.txt_grey if @cmd =~/v/ diff --git a/lib/sisu/v0/particulars.rb b/lib/sisu/v0/particulars.rb index ce12fc31..8ae4f66e 100644 --- a/lib/sisu/v0/particulars.rb +++ b/lib/sisu/v0/particulars.rb @@ -1,9 +1,10 @@ +# coding:utf-8  =begin   * Name: SiSU   * Description: a framework for document structuring, publishing and search -   #___# +   particulars, composite information about document being processed   * Author: Ralph Amissah diff --git a/lib/sisu/v0/plaintext.rb b/lib/sisu/v0/plaintext.rb index 2cf26b93..b89a6252 100644 --- a/lib/sisu/v0/plaintext.rb +++ b/lib/sisu/v0/plaintext.rb @@ -68,6 +68,7 @@ module SiSU_Plaintext    require "#{SiSU_lib}/plaintext_format"    include Format    require "#{SiSU_lib}/shared_txt" +  require "#{SiSU_lib}/shared_structure"    pwd=Dir.pwd    @@alt_id_count,@@alt_id_count,@@tablehead,@@number_of_cols=0,0,0,0    @@tablefoot='' @@ -111,54 +112,6 @@ module SiSU_Plaintext        end      end      private -    class Split_text_object <Source -      require "#{SiSU_lib}/plaintext_format" -      include SiSU_Viz -      include Format -      @@alt_id_count=0 -      @@dp=nil -      attr_reader :format,:lev,:text,:ocn,:lev_para_ocn -      def initialize(para) -        @para=para -        @format,@ocn='null','null' -        @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -      end -      def lev_segname_para_ocn -        @text=nil -        if @para =~/^(\d~|<:.+?>).+?<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ -          if /^(([1-6])~(\S+))\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @format,@lev,segname,@text,@ocn=$1,$2,$3,$4,$5 -          elsif  /^(([1-6])~)\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @format,@lev,@text,@ocn=$1,$2,$3,$4 -          elsif /<:(.+?)>\s*(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @format,@text,@ocn=$1,$2,$3 -          elsif /^(([1-6])~(\S+))\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;[um]\d+><#@dp:#@dp>$/m.match(@para) -            @@alt_id_count+=1 -            @format,@lev,segname,@text,@ocn=$1,$2,$3,$4,"x#{@@alt_id_count}" -          elsif  /^(([1-6])~)\s+(\S.+?)<~(\d+);[um]\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @@alt_id_count+=1 -            @format,@lev,@text,@ocn=$1,$2,$3,"x#{@@alt_id_count}" -          end -        else -          if /(.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -            @text,@ocn=$1,$2 -          end -          if @para !~/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$|^$/ #added 2002w06 -            @text=/(.+?)/m.match(@para)[1] -          end -          if /^((\d)~(?:~\S+)?)\s+(.+)/m.match(@para) -            @format,@lev,@text=$1,$2,$3 -          end -        end -        format=@format.dup -        @lev_para_ocn=if @para =~/.+<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ -          Format::Format_text_object.new(format,@text,@ocn) -        else -          Format::Format_text_object.new(format,@text,"<~(\d+);[um]\d+;\w\d+><#@dp:#@dp>") -        end -        self -      end -    end      class Scroll <Source        require "#{SiSU_lib}/defaults"        require "#{SiSU_lib}/shared_txt" @@ -170,7 +123,7 @@ module SiSU_Plaintext          @url_brace=SiSU_Viz::Skin.new.url_decoration          @vz=SiSU_Env::Get_init.instance.skin          @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -        @regx=/^(?:(?:<:p[bn]>\s*)?\d~(?:(\S+))?\s+)?(.+?)\s*<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m # 2004w18 pb pn removal added +        @regx=/^(?:(?:#{Mx[:br_page]}\s*|#{Mx[:br_page_new]}\s*)?#{Mx[:lv_o]}\d:(\S*?)#{Mx[:lv_c]})?\s*(.+?)\s*#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m # 2004w18 pb pn removal added          @tab="\t"          @br=if md.mod.inspect =~ /--footnote/ \          and md.mod.inspect =~ /--dos/ @@ -198,12 +151,12 @@ module SiSU_Plaintext        end        # Used for extraction of endnotes from paragraphs        def extract_endnotes(para='') -        notes=para.scan(/~[{\[]([\d*+]+\s+.+?)\s*<#@dp>[}\]]~/) +        notes=para.scan(/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})([\d*+]+\s+.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/)          @n=[]          notes.flatten.each do |n| #high cost to deal with <br> appropriately within plaintext, consider            n=n.dup.to_s -          if n =~/<br(?: \/)?>/ -            fix = n.split(/<br(?: \/)?>/) #watch #added +          if n =~/#{Mx[:br_line]}|#{Mx[:br_nl]}/ +            fix = n.split(/#{Mx[:br_line]}|#{Mx[:br_nl]}/) #watch #added              fix.each do |x|                unless x.empty?; @n << x                end @@ -283,11 +236,11 @@ WOK          lv=nil if lv == 0          wrapped=if para[@regx]            paragraph=para[@regx,2] -          if paragraph =~/<:i([1-9])>/ +          if paragraph =~/#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]}/              m=$1.to_i -            paragraph.gsub!(/<:i#{m}>/,'') +            paragraph.gsub!(/#{Mx[:pa_o]}:i#{m}#{Mx[:pa_c]}/,'')              util=SiSU_text_utils::Wrap.new(paragraph,78,m*2) -          else util=SiSU_text_utils::Wrap.new(paragraph,78,0) +          else util=SiSU_text_utils::Wrap.new(paragraph.gsub(/#{Mx[:lv_o]}[1-9]:\S*?#{Mx[:lv_c]}/,''),78,0)            end            util.line_wrap          end @@ -322,83 +275,89 @@ WOK          table_message='[table omitted, see other document formats]'          fix=[]          data.each do |para| -          para.gsub!(/<!Th?¡.+/um,"#@br#{table_message}") -          para.gsub!(/.+?<-#>/,'')                                           # remove dummy headings (used by html) #check -          para.gsub!(/_\*\s+/,'* ')                                          # bullet markup, marked down -          para.gsub!(/<sup>(.+?)<\/sup>/,'^\1^') -          para.gsub!(/<sub>(.+?)<\/sub>/,'[\1]') -          para.gsub!(/<i>(.+?)<\/i>/,'/\1/') -          para.gsub!(/<b>(.+?)<\/b>/,'*\1*') -          para.gsub!(/<u>(.+?)<\/u>/,'_\1_') -          unless para =~/<:code>/ +          para.gsub!(/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}.+/um,"#@br#{table_message}") +          para.gsub!(/.+?#{Mx[:gl_o]}-##{Mx[:gl_c]}/,'')                                           # remove dummy headings (used by html) #check +          para.gsub!(/#{Mx[:gl_bullet]}\s*/,'* ')                                          # bullet markup, marked down +          para.gsub!(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'*\1*') +          para.gsub!(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'/\1/') +          para.gsub!(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,'[\1]') +          para.gsub!(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'_\1_') +          para.gsub!(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,'^\1^') +          para.gsub!(/#{Mx[:fa_insert_o]}(.+?)#{Mx[:fa_insert_c]}/,'+\1+') +          para.gsub!(/#{Mx[:fa_cite_o]}(.+?)#{Mx[:fa_cite_c]}/,'"\1"') +          para.gsub!(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'-\1-') +          unless para =~/#{Mx[:gr_o]}code#{Mx[:gr_c]}/              para.gsub!(/\{(.+?)\}((?:https?|file|ftp):\/\/\S+|image)/,'\1 [link:] \2') -            para.gsub!(/(^|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([.,]?(?:\s|$))/,"\\1#{@url_brace.txt_open}\\2#{@url_brace.txt_close}\\3") +            para.gsub!(/(^|#{Mx[:gl_c]}|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([.,]?(?:\s|$))/,"\\1#{@url_brace.txt_open}\\2#{@url_brace.txt_close}\\3")              para.gsub!(/_((?:https?|file|ftp):\/\/\S+)/,'\1')              extract_endnotes(para) -            para.gsub!(/~[{\[]([\d*+]+)\s+(?:.+?)[}\]]~/,'[^\1]') # endnote marker marked up -            para.gsub!(/&/,'&') -            para.gsub!(/!/,'!') -            para.gsub!(/#/,'#') -            para.gsub!(/*/,'*') -            para.gsub!(/-/,'-') -            para.gsub!(///,'/') -            para.gsub!(/_/,'_') -            para.gsub!(/{/,'{') -            para.gsub!(/}/,'}') -            para.gsub!(/~/,'~') -            para.gsub!(/©/,'©') +            para.gsub!(/#{Mx[:en_a_o]}([\d*+]+)\s+(?:.+?)#{Mx[:en_a_c]}/,'[^\1]') # endnote marker marked up +            para.gsub!(/#{Mx[:en_b_o]}([\d*+]+)\s+(?:.+?)#{Mx[:en_b_c]}/,'[^\1]') # endnote marker marked up +            para.gsub!(/#{Mx[:gl_o]}(?:#lt|#060)#{Mx[:gl_c]}/,'<') +            para.gsub!(/#{Mx[:gl_o]}(?:#gt|#062)#{Mx[:gl_c]}/,'>') +            para.gsub!(/#{Mx[:gl_o]}#(?:038|amp)#{Mx[:gl_c]}/,'&') +            para.gsub!(/#{Mx[:gl_o]}#033#{Mx[:gl_c]}/,'!') +            para.gsub!(/#{Mx[:gl_o]}#035#{Mx[:gl_c]}/,'#') +            para.gsub!(/#{Mx[:gl_o]}#042#{Mx[:gl_c]}/,'*') +            para.gsub!(/#{Mx[:gl_o]}#045#{Mx[:gl_c]}/,'-') +            para.gsub!(/#{Mx[:gl_o]}#047#{Mx[:gl_c]}/,'/') +            para.gsub!(/#{Mx[:gl_o]}#095#{Mx[:gl_c]}/,'_') +            para.gsub!(/#{Mx[:gl_o]}#123#{Mx[:gl_c]}/,'{') +            para.gsub!(/#{Mx[:gl_o]}#125#{Mx[:gl_c]}/,'}') +            para.gsub!(/#{Mx[:gl_o]}#126#{Mx[:gl_c]}/,'~') +            para.gsub!(/#{Mx[:gl_o]}#169#{Mx[:gl_c]}/,'©')            end -          if para =~/<:(?:group|verse|alt|code)(?:-end)?>(?:\s+<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)?/ -            if para =~/<:code>/ #code-block: angle brackets special characters +          if para =~/#{Mx[:gr_o]}(?:group|verse|alt|code)(?:-end)?#{Mx[:gr_c]}(?:\s+#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]})?/ ##{Mx[:gr_o]}codeline#{Mx[:gr_c]} +            if para =~/#{Mx[:gr_o]}code#{Mx[:gr_c]}/ #code-block: angle brackets special characters                para.gsub!(/(^|[^}])_([<>])/m,'\1\2') # _> _<                para.gsub!(/(^|[^}])_([<>])/m,'\1\2') # _<_<              end -            para.gsub!(/<br(?: \/)?>/,"\n")                                   # watch -            para.gsub!(/<:(?:group|verse|alt|code)(?:-end)?>(?:\s+<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)?/,'') -          else para.gsub!(/<br(?: \/)?>/,"\n\n")                                   # watch introduces a bug +            para.gsub!(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,"\n")                                   # watch +            para.gsub!(/#{Mx[:gr_o]}(?:group|verse|alt|code)(?:-end)?#{Mx[:gr_c]}(?:\s+#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]})?/,'') +          else para.gsub!(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,"\n\n")                                   # watch introduces a bug            end -          para.gsub!(/<:p[bn]>/,'')                                         # remove page breaks -          para.gsub!(/^\s*<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/,'') # remove empty lines - check -          para.gsub!(/(^|\s)[_\\]((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([.,]?(?:\s|$))/,'\1\2\3') +          para.gsub!(/#{Mx[:br_page]}\s*|#{Mx[:br_page_new]}/,'')                                         # remove page breaks +          para.gsub!(/^\s*#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/,'') # remove empty lines - check +          para.gsub!(/(^|#{Mx[:gl_c]}|\s)[_\\]((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([.,]?(?:\s|$))/,'\1\2\3')            para.gsub!(/<a href=".+?">(.+?)<\/a>/m,'\1') -          para.gsub!(/<:name#\S+?>/,'')                                       # remove name links +          para.gsub!(/#{Mx[:mk_o]}:name#(\S+?)#{Mx[:mk_c]}/,'')                                       # remove name links            para.gsub!(/ /,' ')                                            # decide on            para.gsub!(/(?:^|[^_\\])\{(\S+?\.(?:png|jpg|gif)) .+?\}(?:(?:https?|file|ftp):\/\/\S+|image)/,'    [ \1 ]') #"[ #{dir.url.images_local}\/\\1 ]")            para.gsub!(/(?:^|[^_\\])\{\s*\S+?\.(?:png|jpg|gif)\s+.+?"(.*?)"\s*\}\S+/,'[image: "\1"]')            #para.gsub!(/^\{\S+?\.(?:png|jpg|gif)\s+.+?"(.*?)"\s*\}\S+/,'[image: "\1"]')            wordlist=para.scan(/\S+/) -          if para =~/^0~(\S+)\s+(.+?)\Z/m # for headers +          if para =~/^#{Rx[:meta]}\s*(.+?)\Z/m # for headers              d_meta=SiSU_text_utils::Header_scan.new(@md,para).meta              if d_meta; plaintext_metadata(d_meta)             end            end -          if para !~/(^0~|<ENDNOTES>|<EOF>)/ +          if para !~/(^#{Rx[:meta]}|#{Mx[:br_eof]}|#{Mx[:br_endnotes]})/              if para =~@regx #/.+?<~\d+;\w\d+;\w\d+>.*/ #watch change                paranum=para[@regx,3]                @p_num=Format::Paragraph_number.new(paranum)              end -            @sto=Split_text_object.new(para).lev_segname_para_ocn +            @sto=SiSU_Structure::Split_text_object.new(@md,para).txt              ### problem in scroll, it appears tables are getting paragraph numbers -            m=/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +            m=/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/              if para =~m \              and para=~/\S+/                para=case @sto.format -              when /^(1)~(?:(\S+))?/ +              when /^(1):(\S*?)/                  plaintext_structure(para,$1,@sto.ocn,$2)                  @sto.lev_para_ocn.heading_body1 -              when /^(2)~(?:(\S+))?/ +              when /^(2):(\S*?)/                  plaintext_structure(para,$1,@sto.ocn,$2)                  @sto.lev_para_ocn.heading_body2 -              when /^(3)~(?:(\S+))?/ +              when /^(3):(\S*?)/                  plaintext_structure(para,$1,@sto.ocn,$2)                  @sto.lev_para_ocn.heading_body3 -              when /^(4)~(\S+)/ # work on see SiSU_text_parts::Split_text_object +              when /^(4):(\S+?)/ # work on see SiSU_text_parts::Split_text_object                  plaintext_structure(para,$1,@sto.ocn,$2)                  @sto.lev_para_ocn.heading_body4 -              when /^(5)~(?:(\S+))?/ +              when /^(5):(\S*?)/                  plaintext_structure(para,$1,@sto.ocn,$2)                  @sto.lev_para_ocn.heading_body5 -              when /^(6)~(?:(\S+))?/ +              when /^(6):(\S*?)/                  plaintext_structure(para,$1,@sto.ocn,$2)                  @sto.lev_para_ocn.heading_body6                #when /^(i1)$/ @@ -427,17 +386,17 @@ WOK              elsif para =~/#{table_message}/                @plaintext[:body] << para << @br              elsif para =~/(Note|Endnotes?)/ \ -            and para !~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +            and para !~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/              elsif para =~/(MetaData)/ \ -            and para =~/<~(\d+);[um]\d+;\w\d+><#@dp:#@dp>$/ #debug 2003w46 add rc info ####suspect visit +            and para =~/#{Mx[:id_o]}~(\d+);[um]\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ #debug 2003w46 add rc info ####suspect visit                #formatMono=MonoSiSU.new('<br /><a name="metadata">MetaData</a>')                #para=formatMono.bold_para              elsif para.include? 'Owner Details' \ -            and para !~/<~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +            and para !~/#{Mx[:id_o]}~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                #formatMono=MonoSiSU.new('<br /><a name="owner.details">Owner Details</a>')                #@plaintext[:owner_details]=formatMono.bold_para                #para='' -            elsif para =~/(¡|<!Th?)/u #tables ! +            elsif para =~/(#{Mx[:tc_p]}|#{Mx[:gr_o]}Th?)/u #tables ! check              elsif para =~/(.*)<!#!>(.*)/                one,two=$1,$2                format_text=Format_text_object.new(one,two) @@ -446,7 +405,7 @@ WOK              para='' if (para =~/<a name="n\d+">/ \              and para =~/^(-\{{2}~\d+|<!e[:_]\d+!>)/) # -endnote              case para -            when /<:i[1-9]>/ +            when /#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]}/                if para =~/.*<:#>.*$/m                  format_text=Format_text_object.new(para,'')                  para=format_text.scr_indent_one_no_paranum @@ -460,6 +419,7 @@ WOK                format_text=Format_text_object.new(one,two)                para=format_text.center              end +            para.gsub!(/#{Mx[:id_o]}.+?#{Mx[:id_c]}/,' ') if para ## Clean Prepared Text              para.gsub!(/<!.+!>/,' ') if para ## Clean Prepared Text              para.gsub!(/<:\S+>/,' ') if para ## Clean Prepared Text            end diff --git a/lib/sisu/v0/plaintext_format.rb b/lib/sisu/v0/plaintext_format.rb index 1840daa6..e957d3a3 100644 --- a/lib/sisu/v0/plaintext_format.rb +++ b/lib/sisu/v0/plaintext_format.rb @@ -81,10 +81,10 @@ module Format      def initialize(one,two,three)        one.gsub!(/\.(html|pdf|php)/,'') if one =~/\.\.\/\S+/        @one,@two,@three=one,two,three -      rgx=/^[1-6-]~/ +      rgx=/^#{Rx[:lv]}/        @one.gsub!(rgx,'') if @one =~rgx        @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -      rgx=/~\{[\d*+]+\s+(.+?)<#@dp>\}~/ +      rgx=/#{Mx[:en_a_o]}[\d*+]+\s+(.+?)#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/        @one.gsub!(rgx,'\1') if @one =~rgx        @link,@linkname=one,two        @vz=SiSU_Env::Get_init.instance.skin diff --git a/lib/sisu/v0/shared_html_lite.rb b/lib/sisu/v0/shared_html_lite.rb index 106a56af..a930821e 100644 --- a/lib/sisu/v0/shared_html_lite.rb +++ b/lib/sisu/v0/shared_html_lite.rb @@ -130,15 +130,16 @@ module SiSU_Format_Shared        @words=@words.join(' ')      end      def markup(para) -      if para !~/^<:code>/ +      if para !~/^#{Mx[:gr_o]}:code#{Mx[:gr_c]}/          if para =~/\{.+?\}((?:https?|file|ftp)\S+|image)/            wm=para.scan(/\{.+?\}(?:(?:https?|file|ftp)\S+|image)|\S+/)            words=urls(wm)            para.gsub!(/.+/m,words)          end +        para.gsub!(/#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]}/m,'')          para.gsub!(/\b[_\\]((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'<a href="\1" target="_top">\1</a>\2') #http ftp matches escaped, no decoration          para.gsub!(/((?:^|\s)[}])((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'\1<a href="\2" target="_top">\2</a>\3') #special case \{ e.g. \}http://url -        para.gsub!(/(^|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/,%{\\1#{@url_brace.xml_open}<a href="\\2" target="_top">\\2</a>#{@url_brace.xml_close}\\3}) #http ftp matches with decoration +        para.gsub!(/(^|#{Mx[:gl_c]}|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/,%{\\1#{@url_brace.xml_open}<a href="\\2" target="_top">\\2</a>#{@url_brace.xml_close}\\3}) #http ftp matches with decoration        else          para.gsub!(/(^|[^}])_</m,'\1<'); para.gsub!(/(^|[^}])_>/m,'\1>') #code-block: angle brackets special characters          para.gsub!(/(^|[^}])_</m,'\1<'); para.gsub!(/(^|[^}])_>/m,'\1>') @@ -175,13 +176,9 @@ GSUB        @content=markup(@content)        %{#{@tab*1}<p class="norm" id="#@ocn" type="substantive">\n#{@tab*2}#@content\n#{@tab*1}</p>\n}      end -    def indent1 +    def indent(t)        @content=markup(@content) -      %{#{@tab*1}<p class="indent1" id="#@ocn" type="substantive">\n#{@tab*2}#@content\n#{@tab*1}</p>\n} -    end -    def indent2 -      @content=markup(@content) -      %{#{@tab*1}<p class="indent2" id="#@ocn" type="substantive">\n#{@tab*2}#@content\n#{@tab*1}</p>\n} +      %{#{@tab*1}<p class="indent#{t}" id="#@ocn" type="substantive">\n#{@tab*2}#@content\n#{@tab*1}</p>\n}      end      def para_table        %{<p class="norm" align="left"><font #{@vz.font_small} #{@vz.font_color} #{@vz.font_face}>} @@ -195,40 +192,40 @@ GSUB          m=parablock[/<!f(.+?)!>/,1]          @@tablefoot<<m if m          parablock.gsub!(/<!f.+?!>/,'') -        @@tablehead=1 if parablock =~/<!Th¡/u -        parablock.gsub!(/<!Th?¡.+?!~(\d+)>/, +        @@tablehead=1 if parablock =~/#{Mx[:gr_o]}Th#{Mx[:tc_p]}/u +        parablock.gsub!(/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}.+?#{Mx[:tc_p]}~(\d+)#{Mx[:gr_c]}/,             #%{<table summary="normal text css" width="100%" border="0" bgcolor="white" cellpadding="2" align="center"><tr><td valign="top" align="justify"><p class="norm" id="\\1">  </p> </td><td>\n} +             %{<table summary="normal text css" width="100%" border="0" bgcolor="white" cellpadding="2" align="center">}) -        if parablock =~/<!TZ!>/ +        if parablock =~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/            tablefoot=[]            @@tablefoot.each {|x| tablefoot << %{<p align="center"><font size=2><i>#{x}</i></font></p>\n}}            @@tablefoot=[] -          parablock.gsub!(/<!TZ!>/, +          parablock.gsub!(/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/,              %{#{@vz.table_close}\n}) # +              #%{#{tablefoot}})          end          if @@tablehead == 1 -          if parablock =~/¡¡/u -            parablock.gsub!(/<!¡¡(\d+?)¡/u, +          if parablock =~/#{Mx[:tc_p]}#{Mx[:tc_p]}/u +            parablock.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,                %{\n<tr>} +                %{\n<td width="\\1%" valign="top">} +                %{#{para_table}<b>}) -            parablock.gsub!(/¡¡(\d+?)¡/u, +            parablock.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,                %{</b></td><td width="\\1%" valign="top">} +                %{#{para_table}<b>}) -            parablock.gsub!(/!>/, '</b></td></tr>') -            @@tablehead=0 #if parablock =~/!>/ +            parablock.gsub!(/#{Mx[:tc_c]}/, '</b></td></tr>') +            @@tablehead=0            end            parablock          else -          parablock.gsub!(/<!¡¡(\d+?)¡/u, +          parablock.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,              %{\n<tr>} +              %{\n<td width="\\1%" valign="top">} +              %{#{para_table}}) -          parablock.gsub!(/¡¡(\d+?)¡/u, +          parablock.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,              %{</td><td width="\\1%" valign="top">} +              %{#{para_table}}) -          parablock.gsub!(/!>/, '</td></tr>') +          parablock.gsub!(/#{Mx[:tc_c]}/, '</td></tr>')            parablock          end          @new_content << parablock diff --git a/lib/sisu/v0/shared_structure.rb b/lib/sisu/v0/shared_structure.rb new file mode 100644 index 00000000..f7b78e0e --- /dev/null +++ b/lib/sisu/v0/shared_structure.rb @@ -0,0 +1,151 @@ +# coding:utf-8 +=begin + + * Name: SiSU + + * Description: a framework for document structuring, publishing and search +   shared document structure + + * Author: Ralph Amissah + + * Copyright: (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, +   2007, +   2008 Ralph Amissah All Rights Reserved. + + * License: GPL 3 or later: + +   SiSU, a framework for document structuring, publishing and search + +   Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, +   2007 Ralph Amissah + +   This program is free software: you can redistribute it and/or modify it +   under the terms of the GNU General Public License as published by the Free +   Software Foundation, either version 3 of the License, or (at your option) +   any later version. + +   This program is distributed in the hope that it will be useful, but WITHOUT +   ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +   FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for +   more details. + +   You should have received a copy of the GNU General Public License along with +   this program. If not, see <http://www.gnu.org/licenses/>. + +   If you have Internet connection, the latest version of the GPL should be +   available at these locations: +   <http://www.fsf.org/licensing/licenses/gpl.html> +   <http://www.gnu.org/copyleft/gpl.html> + +   <http://www.jus.uio.no/sisu/gpl.fsf/toc.html> +   <http://www.jus.uio.no/sisu/gpl.fsf/doc.html> +   <http://www.jus.uio.no/sisu/gpl.fsf/plain.txt> + + * SiSU uses: +   * Standard SiSU markup syntax, +   * Standard SiSU meta-markup syntax, and the +   * Standard SiSU object citation numbering and system + + * Hompages: +   <http://www.jus.uio.no/sisu> +   <http://www.sisudoc.org> + + * Download: +   <http://www.jus.uio.no/sisu/SiSU/download.html> + + * Ralph Amissah +   <ralph@amissah.com> +   <ralph.amissah@gmail.com> + + ** Description: system environment, resource control and configuration details + +=end +module SiSU_Structure +  class Split_text_object +    include SiSU_Viz +    #include SiSU_HTML_Format_type +    @@dp=nil +    attr_reader :format,:text,:ocn,:scroll_lev_para_ocn,:seg_lev_para_ocn,:lev_para_ocn +    def initialize(md,para) +      @md,@para=md,para +      @format,@ocn='null','null' +      #@format,@ocn=nil,nil +      @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern +    end +    def lev_segname_para_ocn +      if @para =~/^#{Mx[:lv_o]}\d:.+?#{Mx[:id_o]}~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ +        if @para[/^#{Mx[:lv_o]}([1-6]):(\S+?)#{Mx[:lv_c]}\s*(\S.+?)#{Mx[:id_o]}~(\d+);(?:[ohmu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m] +          @format,segname,@text,@ocn=$1,$2,$3,$4 +          #@format="#@format:#{segname}" # +        elsif @para[/^#{Mx[:lv_o]}([1-6]):#{Mx[:lv_c]}\s*(\S.+?)#{Mx[:id_o]}~(\d+);(?:[ohmu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m] +          @format,@text,@ocn=$1,$2,$3 +        end +      else +        if @para[/^(#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]}#{Mx[:gl_bullet]})\s*(.+?)#{Mx[:id_o]}~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m] +          @format,@text,@ocn=$1,$2,$3,$4 #watch and work on +        elsif @para[/^(#{Mx[:gl_bullet]})\s*(.+?)#{Mx[:id_o]}~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m] +          @format,@text,@ocn=$1,$2,$3 +        elsif  @para[/#{Mx[:pa_o]}:(i[1-9])#{Mx[:pa_c]}\s*(.+?)#{Mx[:id_o]}~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m] +          @format,@text,@ocn=$1,$2,$3 #consider +        elsif @para[/#{Mx[:gr_o]}(code|alt|verse|group)#{Mx[:gr_c]}(.+?)#{Mx[:id_o]}~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m] +          @format,@text,@ocn=$1,$2,$3 +        elsif @para[/(.+?)#{Mx[:id_o]}~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m] +          @text,@ocn=$1,$2 #,$3 +        end +        if @para !~/#{Mx[:id_o]}~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$|^$/ #added 2002w06 +          @text=@para[/(.+?)/m,1] +        end +        if @para[/^#{Mx[:lv_o]}(\d):\S*?#{Mx[:lv_c]}\s+(.+)/m] +          @format,@text=$1,$2 +        end +      end +      @format="#@format:#{segname}" if @format =~/^[1-6]$/ +      self +    end +    def html_seg +      lev_segname_para_ocn +      @seg_lev_para_ocn=if @para[/.+#{Mx[:id_o]}~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/] +        SiSU_HTML_Format_type::Format_seg.new(@md,@format,@text,@ocn) +      end +      self +    end +    def html_scroll +      lev_segname_para_ocn +      @scroll_lev_para_ocn=if @para[/.+#{Mx[:id_o]}~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/] +        SiSU_HTML_Format_type::Format_scroll.new(@md,@format,@text,@ocn) +      end +      self +    end +    def xml +      require "#{SiSU_lib}/shared_xml" +      lev_segname_para_ocn +      @lev_para_ocn=if @para =~/.+#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ +        SiSU_XML_format::Format_scroll.new(@md,@format,@text,"x#@ocn") +      else +        SiSU_XML_format::Format_scroll.new(@md,@format,@text,"#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}") +      end +      self +    end +    def odt +      lev_segname_para_ocn +      @lev_para_ocn=if @para =~/.+#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ +        SiSU_ODF_format::Format_text_object.new(format,@text,@ocn) +      else +        SiSU_ODF_format::Format_text_object.new(format,@text,"#{Mx[:id_o]}~(\d+);[um]\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}") +      end +      self + +    end +    def txt +      lev_segname_para_ocn +      #format=@format.dup +      @lev_para_ocn=if @para =~/.+#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ +        Format::Format_text_object.new(@format,@text,@ocn) +      else +        Format::Format_text_object.new(@format,@text,"#{Mx[:id_o]}~(\d+);[um]\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}") +      end +      self +    end +  end +end +__END__ diff --git a/lib/sisu/v0/shared_txt.rb b/lib/sisu/v0/shared_txt.rb index aaa2d4d7..484a5f05 100644 --- a/lib/sisu/v0/shared_txt.rb +++ b/lib/sisu/v0/shared_txt.rb @@ -74,7 +74,7 @@ module SiSU_text_utils        line=0        out=[]        out[line]='' -      @para.gsub!(/<:br>/,"\n\n") +      @para.gsub!(/#{Mx[:br_nl]}/,"\n\n")        words=@para.scan(/\n\n|\S+/m)        while words != ''          word=words.shift @@ -116,7 +116,7 @@ module SiSU_text_utils    end    class Header_scan      def initialize(md,para) -      @regxcl=/<~\d+;\w\d+;\w\d+><(?:[0-9a-f]{32}|[0-9a-f]{64}):(?:[0-9a-f]{32}|[0-9a-f]{64})>/ +      @regxcl=/#{Mx[:id_o]}~\d+;\w\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}(?:[0-9a-f]{32}|[0-9a-f]{64}):(?:[0-9a-f]{32}|[0-9a-f]{64})#{Mx[:id_c]}/        para=para.gsub(@regxcl,'').dup        @md,@p=md,para      end @@ -155,122 +155,68 @@ module SiSU_text_utils        end        self      end -    def start_is_zero +    def start_is_match        meta=case @p -      when /^0~(title)\s+(.+?)$/;               header($1,@md.dc_title,'meta','dc') #dc 1 -      #when /^0~(subtitle)\s+(.+?)$/;            header($1,$2) -      when /^0~(creator|author)\s+(.+?)$/;      header('creator',$2,'meta','dc')    #dc 2 -      when /^0~(subject)\s+(.+?)$/;             header($1,$2,'meta','dc')           #dc 3 -      when /^0~(description)\s+(.+?)$/;         header($1,$2,'meta','dc')           #dc 4 -      when /^0~(publisher)\s+(.+?)$/;           header($1,$2,'meta','dc')           #dc 5 -      when /^0~(contributor)\s+(.+?)$/;         header($1,$2,'meta','dc')           #dc 6 -      when /^0~(date)\s+(.+?)$/;                header($1,$2,'meta','dc')           #dc 7 -      when /^0~(date\.created)\s+(.+?)$/;       header($1,$2,'meta','extra') -      when /^0~(date\.issued)\s+(.+?)$/;        header($1,$2,'meta','extra') -      when /^0~(date\.available)\s+(.+?)$/;     header($1,$2,'meta','extra') -      when /^0~(date\.valid)\s+(.+?)$/;         header($1,$2,'meta','extra') -      when /^0~(date\.modified)\s+(.+?)$/;      header($1,$2,'meta','extra') -      when /^0~(type)\s+(.+?)$/;                header($1,$2,'meta','dc')           #dc 8 -      when /^0~(format)\s+(.+?)$/;              header($1,$2,'meta','dc')           #dc 9 -      when /^0~(identifier)\s+(.+?)$/;          header($1,$2,'meta','dc')           #dc 10 -      when /^0~(source)\s+(.+?)$/;              header($1,$2,'meta','dc')           #dc 11 -      when /^0~(language)\s+(.+?)$/;            header($1,$2,'meta','dc')           #dc 12 -      when /^0~(relation)\s+(.+?)$/;            header($1,$2,'meta','dc')           #dc 13 -      when /^0~(coverage)\s+(.+?)$/;            header($1,$2,'meta','dc')           #dc 14 -      when /^0~(rights)\s+(.+?)$/;              header($1,$2,'meta','dc')           #dc 15 -      when /^0~(keywords)\s+(.+?)$/;            header($1,$2,'meta','extra') -      when /^0~(copyright)\s+(.+?)$/;           header($1,$2,'meta','extra') -      when /^0~(translator|translated_by)\s+(.+?)$/;   header('translator',$2,'meta','extra') -      when /^0~(illustrator|illustrated_by)\s+(.+?)$/; header('illustrator',$2,'meta','extra') -      when /^0~(prepared_by)\s+(.+?)$/;         header($1,$2,'meta','extra') -      when /^0~(digitized_by)\s+(.+?)$/;        header($1,$2,'meta','extra') -      when /^0~(comments?)\s+(.+?)$/;           header($1,$2,'meta','extra') -      when /^0~(abstract)\s+(.+?)$/;            header($1,$2,'meta','extra') -      when /^0~(tags?)\s+(.+?)$/;               header($1,$2,'meta','extra') -      when /^0~(catalogue)\s+(.+?)$/;           header($1,$2,'meta','extra') -      when /^0~(class(?:ify)?_loc)\s+(.+?)$/;   header('classify_loc',$2,'meta','extra') -      when /^0~(class(?:ify)?_dewey)\s+(.+?)$/; header('classify_dewey',$2,'meta','extra') -      when /^0~(class(?:ify)?_pg)\s+(.+?)$/;    header('classify_pg',$2,'meta','extra') -      when /^0~(class(?:ify)?_isbn)\s+(.+?)$/;  header('classify_isbn',$2,'meta','extra') -      when /^0~(toc|structure)\s+(.+?)$/;       header('structure',$2,'meta','extra') -      when /^0~(toc|structure)\s+(.+?)$/;       header('structure',$2,'proc','instruct') -      when /^0~(level|page|markup)\s+(.+?)$/;   header('markup',$2,'process','instruct') -      when /^0~(bold)\s+(.+?)$/;                header($1,$2,'process','instruct') -      when /^0~(italics|itali[sz]e)\s+(.+?)$/;  header('italicize',$2,'process','instruct') -      when /^0~(vocabulary|wordlist)\s+(.+?)$/; header('vocabulary',$2,'process','instruct') -      when /^0~(skin)\s+(.+?)$/;                header($1,$2,'process','instruct') -      when /^0~(css|stylesheet)\s+(.+?)$/;      header('css',$2,'process','instruct') -      when /^0~(links)\s+(.+?)$/;               header($1,$2,'process','instruct') -      when /^0~(prefix)\s+(.+?)$/;              header($1,$2,'process','instruct') -      when /^0~(suffix)\s+(.+?)$/;              header($1,$2,'process','instruct') -      when /^0~(information)\s+(.+?)$/;         header($1,$2,'process','instruct') -      when /^0~(contact)\s+(.+?)$/;             header($1,$2,'process','instruct') -      when /^0~(rcs|cvs)\s+(.+?)$/;             header('version',$2,'process','instruct') -      else nil -      end -    end -    def start_is_at -      meta=case @p -      when /^@(title):\s+(.+?)$/;               header($1,@md.dc_title,'meta','dc') #dc 1 +      when /^#{Mx[:meta_o]}(title)#{Mx[:meta_c]}\s*(.+?)$/;               header($1,@md.dc_title,'meta','dc') #dc 1        #when /^@(subtitle):\s+(.+?)$/;            header($1,$2,'meta','extra') -      when /^@(creator|author):\s+(.+?)$/;      header('creator',$2,'meta','dc')    #dc 2 -      when /^@(subject):\s+(.+?)$/;             header($1,$2,'meta','dc')           #dc 3 -      when /^@(description):\s+(.+?)$/;         header($1,$2,'meta','dc')           #dc 4 -      when /^@(publisher):\s+(.+?)$/;           header($1,$2,'meta','dc')           #dc 5 -      when /^@(contributor):\s+(.+?)$/;         header($1,$2,'meta','dc')           #dc 6 -      when /^@(date):\s+(.+?)$/;                header($1,$2,'meta','dc')           #dc 7 -      when /^@(date\.created):\s+(.+?)$/;       header($1,$2,'meta','extra') -      when /^@(date\.issued):\s+(.+?)$/;        header($1,$2,'meta','extra') -      when /^@(date\.available):\s+(.+?)$/;     header($1,$2,'meta','extra') -      when /^@(date\.valid):\s+(.+?)$/;         header($1,$2,'meta','extra') -      when /^@(date\.modified):\s+(.+?)$/;      header($1,$2,'meta','extra') -      when /^@(type):\s+(.+?)$/;                header($1,$2,'meta','dc')           #dc 8 -      when /^@(format):\s+(.+?)$/;              header($1,$2,'meta','dc')           #dc 9 -      when /^@(identifier):\s+(.+?)$/;          header($1,$2,'meta','dc')           #dc 10 -      when /^@(source):\s+(.+?)$/;              header($1,$2,'meta','dc')           #dc 11 -      when /^@(language):\s+(.+?)$/;            header($1,$2,'meta','dc')           #dc 12 -      when /^@(relation):\s+(.+?)$/;            header($1,$2,'meta','dc')           #dc 13 -      when /^@(coverage):\s+(.+?)$/;            header($1,$2,'meta','dc')           #dc 14 -      when /^@(rights):\s+(.+?)$/;              header($1,$2,'meta','dc')           #dc 15 -      when /^@(keywords):\s+(.+?)$/;            header($1,$2,'meta','extra') -      when /^@(copyright):\s+(.+?)$/;           header($1,$2,'meta','extra') -      when /^@(translator|translated_by):\s+(.+?)$/;   header('translator',$2) -      when /^@(illustrator|illustrated_by):\s+(.+?)$/; header('illustrator',$2) -      when /^@(prepared_by):\s+(.+?)$/;         header($1,$2,'meta','extra') -      when /^@(digitized_by):\s+(.+?)$/;        header($1,$2,'meta','extra') -      when /^@(comments?):\s+(.+?)$/;           header($1,$2,'meta','extra') -      when /^@(abstract):\s+(.+?)$/;            header($1,$2,'meta','extra') -      when /^@(tags?):\s+(.+?)$/;               header($1,$2,'meta','extra') -      when /^@(catalogue):\s+(.+?)$/;           header($1,$2,'meta','extra') -      when /^@(class(?:ify)?_loc):\s+(.+?)$/;   header('classify_loc',$2,'meta','extra') -      when /^@(class(?:ify)?_dewey):\s+(.+?)$/; header('classify_dewey',$2,'meta','extra') -      when /^@(class(?:ify)?_pg):\s+(.+?)$/;    header('classify_pg',$2,'meta','extra') -      when /^@(class(?:ify)?_isbn):\s+(.+?)$/;  header('classify_isbn',$2,'meta','extra') -      when /^@(toc|structure):\s+(.+?)$/;       header('structure',$2,'process','instruct') -      when /^@(level|page|markup):\s+(.+?)$/;   header('markup',$2,'process','instruct') -      when /^@(bold):\s+(.+?)$/;                header($1,$2,'process','instruct') -      when /^@(italics|itali[sz]e):\s+(.+?)$/;  header('italicize',$2,'process','instruct') -      when /^@(vocabulary|wordlist):\s+(.+?)$/; header('vocabulary',$2,'process','instruct') -      when /^@(skin):\s+(.+?)$/;                header($1,$2,'process','instruct') -      when /^@(css|stylesheet):\s+(.+?)$/;      header('css',$2,'process','instruct') -      when /^@(links):\s+(.+?)$/;               header($1,$2,'process','instruct') -      when /^@(prefix):\s+(.+?)$/;              header($1,$2,'process','instruct') #add a & b -      when /^@(suffix):\s+(.+?)$/;              header($1,$2,'process','instruct') -      when /^@(information):\s+(.+?)$/;         header($1,$2,'process','instruct') -      when /^@(contact):\s+(.+?)$/;             header($1,$2,'process','instruct') -      when /^@(rcs|cvs):\s+(.+?)$/;             header('version',$2,'process','instruct') +      when /^#{Mx[:meta_o]}(creator|author)#{Mx[:meta_c]}\s*(.+?)$/;      header('creator',$2,'meta','dc')    #dc 2 +      when /^#{Mx[:meta_o]}(subject)#{Mx[:meta_c]}\s*(.+?)$/;             header($1,$2,'meta','dc')           #dc 3 +      when /^#{Mx[:meta_o]}(description)#{Mx[:meta_c]}\s*(.+?)$/;         header($1,$2,'meta','dc')           #dc 4 +      when /^#{Mx[:meta_o]}(publisher)#{Mx[:meta_c]}\s*(.+?)$/;           header($1,$2,'meta','dc')           #dc 5 +      when /^#{Mx[:meta_o]}(contributor)#{Mx[:meta_c]}\s*(.+?)$/;         header($1,$2,'meta','dc')           #dc 6 +      when /^#{Mx[:meta_o]}(date)#{Mx[:meta_c]}\s*(.+?)$/;                header($1,$2,'meta','dc')           #dc 7 +      when /^#{Mx[:meta_o]}(date\.created)#{Mx[:meta_c]}\s*(.+?)$/;       header($1,$2,'meta','extra') +      when /^#{Mx[:meta_o]}(date\.issued)#{Mx[:meta_c]}\s*(.+?)$/;        header($1,$2,'meta','extra') +      when /^#{Mx[:meta_o]}(date\.available)#{Mx[:meta_c]}\s*(.+?)$/;     header($1,$2,'meta','extra') +      when /^#{Mx[:meta_o]}(date\.valid)#{Mx[:meta_c]}\s*(.+?)$/;         header($1,$2,'meta','extra') +      when /^#{Mx[:meta_o]}(date\.modified)#{Mx[:meta_c]}\s*(.+?)$/;      header($1,$2,'meta','extra') +      when /^#{Mx[:meta_o]}(type)#{Mx[:meta_c]}\s*(.+?)$/;                header($1,$2,'meta','dc')           #dc 8 +      when /^#{Mx[:meta_o]}(format)#{Mx[:meta_c]}\s*(.+?)$/;              header($1,$2,'meta','dc')           #dc 9 +      when /^#{Mx[:meta_o]}(identifier)#{Mx[:meta_c]}\s*(.+?)$/;          header($1,$2,'meta','dc')           #dc 10 +      when /^#{Mx[:meta_o]}(source)#{Mx[:meta_c]}\s*(.+?)$/;              header($1,$2,'meta','dc')           #dc 11 +      when /^#{Mx[:meta_o]}(language)#{Mx[:meta_c]}\s*(.+?)$/;            header($1,$2,'meta','dc')           #dc 12 +      when /^#{Mx[:meta_o]}(relation)#{Mx[:meta_c]}\s*(.+?)$/;            header($1,$2,'meta','dc')           #dc 13 +      when /^#{Mx[:meta_o]}(coverage)#{Mx[:meta_c]}\s*(.+?)$/;            header($1,$2,'meta','dc')           #dc 14 +      when /^#{Mx[:meta_o]}(rights)#{Mx[:meta_c]}\s*(.+?)$/;              header($1,$2,'meta','dc')           #dc 15 +      when /^#{Mx[:meta_o]}(keywords)#{Mx[:meta_c]}\s*(.+?)$/;            header($1,$2,'meta','extra') +      when /^#{Mx[:meta_o]}(copyright)#{Mx[:meta_c]}\s*(.+?)$/;           header($1,$2,'meta','extra') +      when /^#{Mx[:meta_o]}(translator|translated_by)#{Mx[:meta_c]}\s*(.+?)$/;   header('translator',$2) +      when /^#{Mx[:meta_o]}(illustrator|illustrated_by)#{Mx[:meta_c]}\s*(.+?)$/; header('illustrator',$2) +      when /^#{Mx[:meta_o]}(prepared_by)#{Mx[:meta_c]}\s*(.+?)$/;         header($1,$2,'meta','extra') +      when /^#{Mx[:meta_o]}(digitized_by)#{Mx[:meta_c]}\s*(.+?)$/;        header($1,$2,'meta','extra') +      when /^#{Mx[:meta_o]}(comments?)#{Mx[:meta_c]}\s*(.+?)$/;           header($1,$2,'meta','extra') +      when /^#{Mx[:meta_o]}(abstract)#{Mx[:meta_c]}\s*(.+?)$/;            header($1,$2,'meta','extra') +      when /^#{Mx[:meta_o]}(tags?)#{Mx[:meta_c]}\s*(.+?)$/;               header($1,$2,'meta','extra') +      when /^#{Mx[:meta_o]}(catalogue)#{Mx[:meta_c]}\s*(.+?)$/;           header($1,$2,'meta','extra') +      when /^#{Mx[:meta_o]}(class(?:ify)?_loc)#{Mx[:meta_c]}\s*(.+?)$/;   header('classify_loc',$2,'meta','extra') +      when /^#{Mx[:meta_o]}(class(?:ify)?_dewey)#{Mx[:meta_c]}\s*(.+?)$/; header('classify_dewey',$2,'meta','extra') +      when /^#{Mx[:meta_o]}(class(?:ify)?_pg)#{Mx[:meta_c]}\s*(.+?)$/;    header('classify_pg',$2,'meta','extra') +      when /^#{Mx[:meta_o]}(class(?:ify)?_isbn)#{Mx[:meta_c]}\s*(.+?)$/;  header('classify_isbn',$2,'meta','extra') +      when /^#{Mx[:meta_o]}(toc|structure)#{Mx[:meta_c]}\s*(.+?)$/;       header('structure',$2,'process','instruct') +      when /^#{Mx[:meta_o]}(level|page|markup)#{Mx[:meta_c]}\s*(.+?)$/;   header('markup',$2,'process','instruct') +      when /^#{Mx[:meta_o]}(bold)#{Mx[:meta_c]}\s*(.+?)$/;                header($1,$2,'process','instruct') +      when /^#{Mx[:meta_o]}(italics|itali[sz]e)#{Mx[:meta_c]}\s*(.+?)$/;  header('italicize',$2,'process','instruct') +      when /^#{Mx[:meta_o]}(vocabulary|wordlist)#{Mx[:meta_c]}\s*(.+?)$/; header('vocabulary',$2,'process','instruct') +      when /^#{Mx[:meta_o]}(skin)#{Mx[:meta_c]}\s*(.+?)$/;                header($1,$2,'process','instruct') +      when /^#{Mx[:meta_o]}(css|stylesheet)#{Mx[:meta_c]}\s*(.+?)$/;      header('css',$2,'process','instruct') +      when /^#{Mx[:meta_o]}(links)#{Mx[:meta_c]}\s*(.+?)$/;               header($1,$2,'process','instruct') +      when /^#{Mx[:meta_o]}(prefix)#{Mx[:meta_c]}\s*(.+?)$/;              header($1,$2,'process','instruct') #add a & b +      when /^#{Mx[:meta_o]}(suffix)#{Mx[:meta_c]}\s*(.+?)$/;              header($1,$2,'process','instruct') +      when /^#{Mx[:meta_o]}(information)#{Mx[:meta_c]}\s*(.+?)$/;         header($1,$2,'process','instruct') +      when /^#{Mx[:meta_o]}(contact)#{Mx[:meta_c]}\s*(.+?)$/;             header($1,$2,'process','instruct') +      when /^#{Mx[:meta_o]}(rcs|cvs)#{Mx[:meta_c]}\s*(.+?)$/;             header('version',$2,'process','instruct')        else nil        end      end      def dublin -      out=if @p =~/^0~\S+\s/;                  start_is_zero -      elsif @p =~/^@\S+:[+-]?\s/;              start_is_at +      out=if @p =~/^#{Mx[:meta_o]}\S+?#{Mx[:meta_c]}/ +        start_is_match        else nil        end      end      def meta -      out=if @p =~/^0~\S+\s/;                  start_is_zero -      elsif @p =~/^@\S+:[+-]?\s/;              start_is_at +      out=if @p =~/^#{Mx[:meta_o]}\S+?#{Mx[:meta_c]}/ +        start_is_match        else nil        end      end @@ -287,30 +233,30 @@ module SiSU_text_parts_flatfile        @@dl ||=SiSU_Env::Info_env.new.digest.length      end      def lev_segname_para_ocn -      if @para =~/^(\d~|<:.+?>).+?<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}>.*/ -        if /^([1-6])~(\S+)\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}>/m.match(@para) +      if @para =~/^(?:#{Mx[:lv_o]}[1-9]:\S*?#{Mx[:lv_c]}|<:.+?>).+?#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}#{Mx[:id_c]}.*/ +        if /^(#{Mx[:lv_o]}([1-6]):(\S+?)#{Mx[:lv_c]})\s*(\S.+?)#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}#{Mx[:id_c]}/m.match(@para)            @format,segname,@text,@ocn=$1,$2,$3,$4            @format="#@format~#{segname}" # -        elsif  /^([1-6]~)\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}>/m.match(@para) +        elsif  /^(#{Mx[:lv_o]}([1-6]):#{Mx[:lv_c]})\s*(\S.+?)#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}#{Mx[:id_c]}/m.match(@para)            @format,@text,@ocn=$1,$2,$3 -        elsif /<:(.+?)>\s*(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}>/m.match(@para) +        elsif /<:(.+?)>\s*(\S.+?)#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}#{Mx[:id_c]}/m.match(@para)            @format,@text,@ocn=$1,$2,$3 -        elsif /^([1-6])~(\S+)\s+(\S.+?)<~(0);(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}>/m.match(@para) +        elsif /^(#{Mx[:lv_o]}([1-6]):(\S+?)#{Mx[:lv_c]})\s*(\S.+?)#{Mx[:id_o]}~(0);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}#{Mx[:id_c]}/m.match(@para)            @@alt_id_count+=1            @format,segname,@text,@ocn=$1,$2,$3,"x#{@@alt_id_count}"            @format="#@format~#{segname}" # -        elsif /^([1-6]~)\s+(\S.+?)<~(0);(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}>/m.match(@para) +        elsif /^(#{Mx[:lv_o]}([1-6]):#{Mx[:lv_c]})\s*(\S.+?)#{Mx[:id_o]}~(0);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}#{Mx[:id_c]}/m.match(@para)            @@alt_id_count+=1            @format,@text,@ocn=$1,$2,"x#{@@alt_id_count}"          end        else -        if /(.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}>/m.match(@para) +        if /(.+?)#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}#{Mx[:id_c]}/m.match(@para)            @text,@ocn=$1,$2          end -        if @para !~/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}>|^$/ #added 2002w06 +        if @para !~/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}#{Mx[:id_c]}|^$/ #added 2002w06            @text=/(.+?)/m.match(@para)[1]          end -        if /^(\d)~\S*\s+(.+)/m.match(@para) +        if /^(#{Mx[:lv_o]}([1-9]):\S*?#{Mx[:lv_c]})\s*(.+)/m.match(@para)            @format,@text=$1,$2          end        end diff --git a/lib/sisu/v0/shared_xml.rb b/lib/sisu/v0/shared_xml.rb index c93eff5b..3c34e67f 100644 --- a/lib/sisu/v0/shared_xml.rb +++ b/lib/sisu/v0/shared_xml.rb @@ -59,75 +59,27 @@  =end  module SiSU_text_parts -  class Split_text_object +  require "#{SiSU_lib}/shared_structure" +  class Split_text_object < SiSU_Structure::Split_text_object      require "#{SiSU_lib}/param"      require "#{SiSU_lib}/xml_format"      include SiSU_Viz      include SiSU_XML_format      @@alt_id_count=0      @@dp=nil -    attr_reader :format,:text,:ocn,:lev_para_ocn -    def initialize(md,para) -      @md,@para=md,para -      @format,@ocn='null','null' -      #@format,@ocn=nil,nil -      @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -    end -    def lev_segname_para_ocn #using shared_txt instead, watch #% watch closely -      if @para =~/^(\d~|<:.+?>).+?<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ -        if /^([1-6])~(\S+)\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -          @format,segname,@text,@ocn=$1,$2,$3,$4 -          @format="#@format~#{segname}" # -        elsif  /^([1-6]~)\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -          @format,@text,@ocn=$1,$2,$3 -        elsif /<:(.+?)>\s*(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -          @format,@text,@ocn=$1,$2,$3 -        elsif /^([1-6])~(\S+)\s+(\S.+?)<~(0);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -          @@alt_id_count+=1 -          @format,segname,@text,@ocn=$1,$2,$3,"x#{@@alt_id_count}" -          @format="#@format~#{segname}" # -        elsif  /^([1-6]~)\s+(\S.+?)<~(0);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -          @@alt_id_count+=1 -          @format,@text,@ocn=$1,$2,"x#{@@alt_id_count}" -        elsif /^(?:<:i([1-9])>\s*_\*)\s+(.+?)<~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -          @format,@text,@ocn="_#{$1}\*",$2,$3,$4 -        elsif /^(_\*)\s+(.+?)<~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -          @format,@text,@ocn=$1,$2,$3 -        elsif  /<:(i[1-9])>\s*(.+?)<~(\d+);(?:[ohu]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -          @format,@text,@ocn=$1,$2,$3 -        end -      else -        if /(.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) -          @text,@ocn=$1,$2 -        end -        if @para !~/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$|^$/ #added 2002w06 -          @text=/(.+?)/m.match(@para)[1] -        end -        if /^(\d)~\S*\s+(.+)/m.match(@para) -          @format,@text=$1,$2 -        end -      end -      @lev_para_ocn=if @para =~/.+<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ -        SiSU_XML_format::Format_scroll.new(@md,@format,@text,@ocn) -      else -        SiSU_XML_format::Format_scroll.new(@md,@format,@text,"<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>") -      end -      self -    end      def lev_segname_para -      if @para =~/^(\d~|<:.+?>).+/ -        if /^([1-6])~(\S+)\s+(\S.+)/m.match(@para) +      if @para =~/^#{Mx[:lv_o]}(?:\d:|<:.+?>).+/ +        if /^#{Mx[:lv_o]}([1-6]):(\S+?)#{Mx[:lv_c]}\s*(\S.+)/m.match(@para)            @format,segname,@text=$1,$2,$3 -          @format="#@format~#{segname}" # -        elsif /^([1-6]~)\s+(\S.+)/m.match(@para) +        elsif /^#{Mx[:lv_o]}([1-6]):#{Mx[:lv_c]}\s*(\S.+)/m.match(@para)            @format,@text=$1,$2          elsif /<:(.+?)>\s*(\S.+?)/m.match(@para)            @format,@text=$1,$2 -        elsif /^([1-6])~(\S+)\s+(\S.+?)/m.match(@para) +        elsif /^#{Mx[:lv_o]}([1-6]):(\S+?)#{Mx[:lv_c]}\s*(\S.+?)/m.match(@para)            @@alt_id_count+=1            @format,segname,@text=$1,$2,$3 -          @format="#@format~#{segname}" # -        elsif /^([1-6]~)\s+(\S.+?)/m.match(@para) +          #@format="#@format:#{segname}" # +        elsif /^#{Mx[:lv_o]}([1-6]):#{Mx[:lv_c]}\s*(\S.+?)/m.match(@para)            @@alt_id_count+=1            @format,@text=$1,$2          end @@ -135,17 +87,19 @@ module SiSU_text_parts          if /(.+?)/m.match(@para)            @text=$1          end -        if @para !~/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$|^$/ #added 2002w06 +        if @para !~/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$|^$/ #added 2002w06            @text=/(.+?)/m.match(@para)[1]          end          if /^(\d)~\S*\s+(.+)/m.match(@para)            @format,@text=$1,$2          end        end -      @lev_para_ocn=if @para =~/.+<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +      @format="#@format:#{segname}" # +#follow this search beneath for heading_body1-6 +      @lev_para_ocn=if @para =~/.+#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/          SiSU_XML_format::Format_scroll.new(@md,@format,@text,@ocn)        else -        SiSU_XML_format::Format_scroll.new(@md,@format,@text,"<~0;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>") +        SiSU_XML_format::Format_scroll.new(@md,@format,@text,"#{Mx[:id_o]}~0;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}")        end        self      end @@ -396,19 +350,40 @@ module SiSU_XML_munge      def markup(para='')        wordlist=para.scan(/\S+|\n/) #\n needed for tables, check though added 2005w17        para=tidywords(wordlist).join(' ').strip -      para.gsub!(/(^|\s+)<\s+/,'\1< '); para.gsub!(/\s+>(\s+|$)/,' >\1') -      para.gsub!(/<:pb>\s*/,'') +      para.gsub!(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,'<br />') +      para.gsub!(/#{Mx[:mk_o]}:name#\S+?#{Mx[:mk_c]}/,'') +      para.gsub!(/#{Mx[:mk_o]}#([a-zA-Z]+)#{Mx[:mk_c]}/,'&\1;') +      para.gsub!(/#{Mx[:mk_o]}(#[0-9]+)#{Mx[:mk_c]}/,'&\1;') +      para.gsub!(/(^|#{Mx[:gl_c]}|\s+)<\s+/,'\1< '); para.gsub!(/\s+>(\s+|$)/,' >\1') +      #para.gsub!(/#{Mx[:fa_emphasis_o]}(.+?)#{Mx[:fa_emphasis_c]}/,'<em>\1</em>') #reinstate +      para.gsub!(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'<b>\1</b>') +      para.gsub!(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'<i>\1</i>') +      para.gsub!(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'<u>\1</u>') +      para.gsub!(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,'<sup>\1</sup>') +      para.gsub!(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,'<sub>\1</sub>') +      para.gsub!(/#{Mx[:fa_insert_o]}(.+?)#{Mx[:fa_insert_c]}/,'<ins>\1</ins>') +      para.gsub!(/#{Mx[:fa_cite_o]}(.+?)#{Mx[:fa_cite_c]}/,'<cite>\1</cite>') +      para.gsub!(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'<del>\1</del>') +      para.gsub!(/<:pb>\s*/,'') #Fix        para.gsub!(/<+[-~]#>+/,'') -      para.gsub!(/<0;\w\d+;[um]\d+><#@dp:#@dp>/,'') -      if para !~/^<:code>/ +      para.gsub!(/#{Mx[:id_o]}0;\w\d+;[um]\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}/,'') +      if para !~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/          #embeds a red-bullet image --> +        para.gsub!(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'<b>\1</b>') +        para.gsub!(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'<i>\1</i>') +        para.gsub!(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'<u>\1</u>') +        para.gsub!(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'<del>\1</del>') +        para.gsub!(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,'<br />') +        para.gsub!(/#{Mx[:br_page]}\s*/,'') +        para.gsub!(/#{Mx[:br_page_new]}\s*/,'') +        para.gsub!(/#{Mx[:pa_non_object_no_heading]}|#{Mx[:pa_non_object_dummy_heading]}/,''); para.gsub!(/<[-~]#>/,'')          para.gsub!(/(?:^|[^_\\])\{\s*(\S+?\.(?:jpg|png|gif))\s+(\d+)x(\d+)(\s+[^}]+)?\}(https?:\/\/\S+)/,  	  %{<image xmlns:xlink="http://www.w3.org/1999/xlink" xlink:type="simple" xlink:actuate="onLoad" xlink:show="embed" xlink:href="#{@dir.url.images_local}/\\1" width="\\2" height="\\3" />[\\1] \\4})          para.gsub!(/(?:^|[^_\\])\{\s*(\S+?\.(?:jpg|png|gif))(\s+[^}]+)?\}(https?:\/\/\S+)/,  	  %{<image xmlns:xlink="http://www.w3.org/1999/xlink" xlink:type="simple" xlink:actuate="onLoad" xlink:show="embed" xlink:href="#{@dir.url.images_local}/\\1"/>\\1}) -        para.gsub!(/(^|\s)\{([^}]+)\}(https?:\/\/[^"><]+?)([,.:;"><]?(?=\s|$))/, +        para.gsub!(/(^|#{Mx[:gl_c]}|\s)\{([^}]+)\}(https?:\/\/[^"><]+?)([,.:;"><]?(?=\s|$))/,            '\1<link xmlns:xlink="http://www.w3.org/1999/xlink" xlink:type="simple" xlink:href="\3">\2</link>\4') #watch, compare html_tune -        para.gsub!(/(^|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/, +        para.gsub!(/(^|#{Mx[:gl_c]}|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/,            %{\\1#{@url_brace.xml_open}<link xmlns:xlink="http://www.w3.org/1999/xlink" xlink:type="simple" xlink:href="\\2">\\2</link>#{@url_brace.xml_close}\\3})          para.gsub!(/\b[_\\]((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,  	  '<link xmlns:xlink="http://www.w3.org/1999/xlink" xlink:type="simple" xlink:href="\1">\1</link>\2') #escaped urls not linked, deal with later @@ -429,7 +404,7 @@ module SiSU_XML_munge        para.gsub!(/<br(\s*\/)?>/,'<br />')        para.gsub!(/<:pb>\s*/,'')        para.gsub!(/<[-~]#>/,'') -      para.gsub!(/(^|\s)&\s+/,'\1& ') #sort +      para.gsub!(/(^|#{Mx[:gl_c]}|\s)&\s+/,'\1& ') #sort        para.gsub!(/&([^;]{1,5})/,'&\1') #sort, rough estimate, revisit #WATCH found in node not sax        para.gsub!(/(?:^|[^_\\])\{(\S+?\.(?:png|jpg|gif)) .+?\}(?:(?:https?|file|ftp):\/\/\S+|image)/,          "<image.path>#{@dir.url.images_local}\/\\1</image.path>") @@ -452,7 +427,7 @@ module SiSU_XML_munge        para.gsub!(/<:\S+?>/,'')        #<-- temporary        para.gsub!(/<[-~]#>/,'') -      para.gsub!(/(^|\s)&\s+/,'\1& ') #sort +      para.gsub!(/(^|#{Mx[:gl_c]}|\s)&\s+/,'\1& ') #sort        para.gsub!(/&([^;]{1,5})/,'&\1') #sort, rough estimate, revisit #WATCH found in node not sax        para.gsub!(/(?:^|[^_\\])\{(\S+?\.(?:png|jpg|gif)) .+?\}(?:(?:https?|file|ftp):\/\/\S+|image)/,          "<image.path>#{@dir.url.images_local}\/\\1</image.path>") @@ -728,4 +703,3 @@ module SiSU_Tables    require "#{SiSU_lib}/xml_tables"  end  __END__ - diff --git a/lib/sisu/v0/sst_do_inline_footnotes.rb b/lib/sisu/v0/sst_do_inline_footnotes.rb index 3ee301f2..5cfd38da 100644 --- a/lib/sisu/v0/sst_do_inline_footnotes.rb +++ b/lib/sisu/v0/sst_do_inline_footnotes.rb @@ -68,7 +68,7 @@ module SiSU_Convert_footnotes    include SiSU_Env    include SiSU_Param    include SiSU_Viz -  include Syntax +  include SiSU_Syntax    class Instantiate < SiSU_Param::Parameters::Instructions       @@flag={} #Beware!!      def initialize @@ -337,7 +337,7 @@ module SiSU_Convert_footnotes        # debug 2003w46 adding revision control info        if @md.flag_auto_endnotes \        and @md.flag_separate_endnotes_make -        @tuned_file << "\n1~endnotes Endnotes <~0;0:0;u0>" #prob numbering, revisit +        @tuned_file << "\n1~endnotes Endnotes #{Mx[:id_o]}~0;0:0;u0#{Mx[:id_c]}" #prob numbering, revisit        end        @tuned_file << "\n<ENDNOTES>"        @tuned_file @@ -469,7 +469,7 @@ module SiSU_Convert_footnotes      end      def strip_clean_of_markup(s)                                               # used for digest, define rules, make same as in db clean        s=s.dup -      s=s.gsub(/(?:<\/?[ib]>|<~\d+;(?:\w|[0-6]:)\d+;\w\d+>|<#@dp:#@dp>|^:[A-C]~\S+|^[1-6]~\S+|~\{\d+\s.+?\}~)/,'') # markup and endnotes removed +      s=s.gsub(/(?:<\/?[ib]>|#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}|#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}|^:[A-C]~\S+|^[1-6]~\S+|~\{\d+\s.+?\}~)/,'') # markup and endnotes removed                                                                                 #% same as db clean -->        s=s.gsub(/<del>(.+?)<\/del>/,'DELETED(\1)')                           # deletions        s=s.gsub(/<sup>(\d+)<\/sup>/,'[\1]') diff --git a/lib/sisu/v0/sst_to_s_xml_dom.rb b/lib/sisu/v0/sst_to_s_xml_dom.rb index 1bf9a561..23143ed8 100644 --- a/lib/sisu/v0/sst_to_s_xml_dom.rb +++ b/lib/sisu/v0/sst_to_s_xml_dom.rb @@ -135,7 +135,7 @@ module SiSU_simple_xml_model_dom        def initialize(data='',particulars='')          @data,@env,@md=data,particulars.env,particulars.md          @vz=SiSU_Env::Get_init.instance.skin -        @regx=/^(?:(?:<:p[bn]>\s*)?(?::?[A-C]|\d~)(?:(\S+))?\s+)?(.+)/ +        @regx=/^(?:#{Mx[:mk_o]}:p[bn]#{Mx[:mk_c]}\s*)?(?:#{Mx[:lv_o]}[1-9]:(\S*)#{Mx[:lv_c]})?(.+)/          @tab="\t"          if @md            @trans=SiSU_XML_munge::Trans.new(@md) @@ -155,13 +155,14 @@ module SiSU_simple_xml_model_dom          para.gsub!(/~\[([*+])\s+(.+?)\]~/,            '<endnote><symbol>\1</symbol><note>\2</note></endnote> ')        end -      def xml_markup(para='') +      def xml_clean(para='')          para.gsub!(/~\[([*+])\s+(.+?)\]~/,            '<endnote><symbol>\1</symbol><note>\2</note></endnote> ')          para.gsub!(/~\{([*+]+)\s+(.+?)\}~/,            '<endnote><symbol>\1</symbol><note>\2</note></endnote> ')          para.gsub!(/~\{(.+?)\}~/,            '<endnote><note>\1</note></endnote> ') +        para.gsub!(/#{Mx[:lv_o]}[1-9]:\S*?#{Mx[:lv_c]}/,'') #Danger, watch        end        def xml_head(meta)          txt=meta.text @@ -367,11 +368,14 @@ WOK            para.gsub!(/ /,' ')            para=SiSU_document_structure::Structure.new(@md,para).structure            @trans.char_enc.utf8(para) if @sys.locale =~/utf-?8/i #% utf8 -          if para =~/\A(?:@|0~)(\S+?):?\s+(.+?)\Z/m +          para.gsub!(/^0~(\S+)/,"#{Mx[:lv_o]}@\\1#{Mx[:lv_c]}") +          para.gsub!(/^@(\S+?):/,"#{Mx[:lv_o]}@\\1#{Mx[:lv_c]}") +          if para =~/\A#{Mx[:lv_o]}@(\S+?)#{Mx[:lv_c]}\s*(.+?)\Z/m # for headers              d_meta=SiSU_text_utils::Header_scan.new(@md,para).meta              if d_meta; xml_head(d_meta)              end            end +          para='' if para=~/#{Mx[:lv_o]}@\S+?#{Mx[:lv_c]}/            if @rcdc==false \            and (para =~/~metadata/ or para =~/^1~meta\s+Document Information/)              @rcdc=true @@ -382,28 +386,28 @@ WOK                if para !~/^(?:%\s|0~|@\S+?:)/                  format_scroll=SiSU_XML_format::Format_scroll.new(@md,@sto.text) if @sto.format =~/i[12]|null/                  case @sto.format -                when /^(1)~(\S+)?/ -                  xml_markup(para) +                when /^(1):(\S*)/ +                  xml_clean(para)                    xml_structure($1,para,$2)                    para=@sto.lev_para_ocn.heading_body1 -                when /^(2)~(\S+)?/ -                  xml_markup(para) +                when /^(2):(\S*)/ +                  xml_clean(para)                    xml_structure($1,para,$2)                    para=@sto.lev_para_ocn.heading_body2 -                when /^(3)~(\S+)?/ -                  xml_markup(para) +                when /^(3):(\S*)/ +                  xml_clean(para)                    xml_structure($1,para,$2)                    para=@sto.lev_para_ocn.heading_body3 -                when /^(4)~(\S+)?/ -                  xml_markup(para) +                when /^(4):(\S*)/ +                  xml_clean(para)                    xml_structure($1,para,$2)                    para=@sto.lev_para_ocn.heading_body4 -                when /^(5)~(\S+)?/ -                  xml_markup(para) +                when /^(5):(\S*)/ +                  xml_clean(para)                    xml_structure($1,para,$2)                    para=@sto.lev_para_ocn.heading_body5 -                when /^(6)~(\S+)?/ -                  xml_markup(para) +                when /^(6):(\S*)?/ +                  xml_clean(para)                    xml_structure($1,para,$2)                    para=@sto.lev_para_ocn.heading_body6                  #when /^(i1)$/i @@ -427,19 +431,20 @@ WOK                  #    end                  else                    if para =~ /<:verse>/ -                    poem_structure(para) +                    para=poem_structure(para)                    elsif para =~ /<:group>/ -                    group_structure(para) +                    para=group_structure(para)                    elsif para =~ /<:code>/                      para.gsub!(/</,'<')                      para.gsub!(/>/,'>') -                    code_structure(para) +                    para=code_structure(para)                    elsif para =~/<!Th?.+/ # tables come as single block #work area 2005w13 +                  #elsif para =~/#{Mx[:gr_o]}Th?.+/ # tables come as single block #work area 2005w13                      table=SiSU_Tables::Table_xml.new(para)                      para=table.table_split                      @@xml[:body] << table_structure(para)                    else #xml_structure -                    xml_markup(para) +                    xml_clean(para)                      if para[@regx] \                      and para[@regx,2]                        @@xml[:body] << %{#{@tab*6}<object>} << "\n" @@ -450,11 +455,11 @@ WOK                  end                elsif para =~/(Note|Endnotes?)/                elsif para =~/(MetaData)/ \ -              and para =~/<~\d+;[m]\d+;\w\d+><#{@@dp}:#{@@dp}>$/ #debug 2003w46 add rc info +              and para =~/#{Mx[:id_o]}~\d+;[m]\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#{@@dp}:#{@@dp}#{Mx[:id_c]}$/ #debug 2003w46 add rc info                  format_scroll=Format_scroll.new(@md,'<br /><a name="metadata">MetaData</a>')                  para=format_scroll.bold_para                elsif para =~/(Owner Details)/ \ -              and para !~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#{@@dp}:#{@@dp}>$/ +              and para !~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#{@@dp}:#{@@dp}#{Mx[:id_c]}$/                  format_scroll=Format_scroll.new(@md,'<br /><a name="owner.details">Owner Details</a>')                  @@xml[:owner_details]=format_scroll.bold_para                  para='' @@ -484,10 +489,10 @@ WOK                  format_text=Format_text_object.new(one,two)                  para=format_text.center                end -            else              end              para.gsub!(/<:\S+?>/,'')              para.gsub!(/<!.+!>/,' ') +            para            end          end          @content_flag=true @@ -563,6 +568,7 @@ WOK            para.gsub!(/_\{(.+?)\}_/,'<underscore>\1</underscore>')            para.gsub!(/-\{(.+?)\}-/,'<strike>\1</strike>')            # do { links }http://url +          #para.gsub!(/#{Mx[:gl_o]}\S+?#{Mx[:gl_c]}/,'') #Danger, watch            para.gsub!(/<:\S+?>/,'')            para.gsub!(/<!.+?!>/,'')            para="#{para}\n" unless para.empty? diff --git a/lib/sisu/v0/sst_to_s_xml_node.rb b/lib/sisu/v0/sst_to_s_xml_node.rb index 697a7a77..ed7f4b10 100644 --- a/lib/sisu/v0/sst_to_s_xml_node.rb +++ b/lib/sisu/v0/sst_to_s_xml_node.rb @@ -142,7 +142,7 @@ module SiSU_simple_xml_model_node        def initialize(data='',particulars='')          @data,@env,@md=data,particulars.env,particulars.md          @vz=SiSU_Env::Get_init.instance.skin -        @regx=/^(?:(?:<:p[bn]>\s*)?(?::?[A-C]~|\d~)(?:(\S+))?\s+)?(.+)/ +        @regx=/^(?:#{Mx[:mk_o]}:p[bn]#{Mx[:mk_c]}\s*)?(?:#{Mx[:lv_o]}[1-9]:(\S*)#{Mx[:lv_c]})?(.+)/          @tab="\t"          if @md            @trans=SiSU_XML_munge::Trans.new(@md) @@ -159,16 +159,16 @@ module SiSU_simple_xml_model_node        end      protected        def embedded_endnotes(para='') -        para.gsub!(/~\{(.+?)\}~/,'<endnote symbol="norm">\1</endnote> ') -        para.gsub!(/~\[([*+])\s+(.+?)\]~/,'<endnote symbol="\1">\2</endnote> ') +        para.gsub!(/#{Mx[:en_a_o]}(.+?)#{Mx[:en_a_c]}/,'<endnote symbol="norm">\1</endnote> ') +        para.gsub!(/#{Mx[:en_b_o]}([*+])\s+(.+?)#{Mx[:en_b_c]}/,'<endnote symbol="\1">\2</endnote> ')        end        def xml_head(meta)          txt=meta.text -        txt.gsub!(/\/{(.+?)}\//,'<i>\1</i>') -        txt.gsub!(/[*!]{(.+?)}[*!]/,'<b>\1</b>') -        txt.gsub!(/_{(.+?)}_/,'<u>\1</u>') -        txt.gsub!(/-{(.+?)}-/,'<del>\1</del>') -        txt.gsub!(/<br(?: \/)?>/,'<br />') +        txt.gsub!(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'<i>\1</i>') +        txt.gsub!(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'<b>\1</b>') +        txt.gsub!(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'<u>\1</u>') +        txt.gsub!(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'<del>\1</del>') +        txt.gsub!(/#{Mx[:br_line]}|#{Mx[:br_paragraph]}/,'<br />')          txt.gsub!(/ & /,' and ')          @@xml[:head] <<<<WOK  #{@tab}<header class="#{meta.attrib}"> @@ -273,13 +273,13 @@ WOK          else puts 'error'          end        end -      def node_structure(o='',para='',lv='',hname='') #extracted endnotes -        if o.ocn -          lv=lv.to_i -          lv=nil if lv == 0 -          build_relationships(o,lv) -        end -      end +      #def node_structure(o='',para='',lv='',hname='') #extracted endnotes +      #  if o.ocn +      #    lv=lv.to_i +      #    lv=nil if lv == 0 +      #    build_relationships(o,lv) +      #  end +      #end        def xml_structure(o='',para='',lv='',hname='') #extracted endnotes          if o.ocn            puts para if lv and @md.cmd =~/M/ @@ -397,6 +397,10 @@ WOK          @@xml[:body] << "#{@tab*0}</object>" << "\n" #if para[@regx]          @endnotes=[]        end +      def xml_clean(para) +        para.gsub!(/#{Mx[:lv_o]}[1-9]:\S*?#{Mx[:lv_c]}/,'') +        para +      end        def markup          data=[]          @data=@data.join.split("\n\n") @@ -404,7 +408,7 @@ WOK          @data.each do |para|            data << SiSU_document_structure::Structure.new(@md,para).structure          end -        data=Syntax::Markup.new(@md,data).songsheet +        data=SiSU_Syntax::Markup.new(@md,data).songsheet          data=SiSU_document_structure::Tables.new(@md,data).tables          obj=SiSU_document_structure::OCN.new(@md,data).ocn          obj.compact! @@ -429,58 +433,69 @@ WOK              para=SiSU_sem::Tags.new(para,@md).rm.all              para=@trans.markup_light(para)              @trans.char_enc.utf8(para) if @sys.locale =~/utf-?8/i #% utf8 -            if para =~/\A(?:@|0~)(\S+?):?\s+(.+?)\Z/m # for headers +            if para =~/\A#{Mx[:lv_o]}@(\S+?)#{Mx[:lv_c]}\s*(.+?)\Z/m # for headers                d_meta=SiSU_text_utils::Header_scan.new(@md,para).meta                if d_meta; xml_head(d_meta)                end              end            end          end +        #obj.each do |o| +        #  para=o.txt unless o.txt =~/^%% / #comments are lost, consider +        #  if para +        #    para.gsub!(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'<i>\1</i>') +        #    para.gsub!(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'<b>\1</b>') +        #    para.gsub!(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'<u>\1</u>') +        #    para.gsub!(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'<del>\1</del>') +        #    para.gsub!(/#{Mx[:br_line]}|#{Mx[:br_paragraph]}/,'<br />') +        #    if @rcdc==false \ +        #    and (para =~/~metadata/ or para =~/^1~meta\s+Document Information/) +        #      if para !~/(^0~|^@\S+?:|^\s*$|<ENDNOTES>|<EOF>)/ +        #        @rcdc=true +        #      end +        #      @sto=SiSU_text_parts::Split_text_object.new(@md,para).lev_segname_para +        #      unless @rcdc +        #        format_scroll=SiSU_XML_format::Format_scroll.new(@md,@sto.text) if @sto.format =~/i[12]|null/ +        #        case @sto.format +        #        when /^(1):(\S*)/ +        #          node_structure(o,para,$1,$2) +        #        when /^(2):(\S*)/ +        #          node_structure(o,para,$1,$2) +        #        when /^(3):(\S*)/ +        #          node_structure(o,para,$1,$2) +        #        when /^(4):(\S*)/ # work on see Split_text_object +        #          node_structure(o,para,$1,$2) +        #        when /^(5):(\S*)/ +        #          node_structure(o,para,$1,$2) +        #        when /^(6):(\S*)/ +        #          node_structure(o,para,$1,$2) +        #        else +        #          if para =~ /<:verse>/ +        #            node_structure(o,para) +        #          elsif para =~ /<:group>/ +        #            node_structure(o,para) +        #          elsif para =~ /<:code>/ +        #            node_structure(o,para) +        #          elsif para =~/<!Th?.+/ # tables come as single block #work area 2005w13 +        #          #elsif para =~/#{Mx[:gr_o]}Th?.+/ # tables come as single block #work area 2005w13 +        #            table=SiSU_Tables::Table_xml.new(para) +        #            para=table.table_split +        #            node_structure(o,para) +        #          else node_structure(o,para,nil,nil) +        #          end +        #        end +        #      end +        #    end +        #  end +        #end          obj.each do |o|            para=o.txt unless o.txt =~/^%% / #comments are lost, consider            if para -            if @rcdc==false \ -            and (para =~/~metadata/ or para =~/^1~meta\s+Document Information/) -              if para !~/(^0~|^@\S+?:|^\s*$|<ENDNOTES>|<EOF>)/ -                @rcdc=true -              end -              @sto=SiSU_text_parts::Split_text_object.new(@md,para).lev_segname_para -              unless @rcdc -                format_scroll=SiSU_XML_format::Format_scroll.new(@md,@sto.text) if @sto.format =~/i[12]|null/ -                case @sto.format -                when /^(1)~(\S+)?/ -                  node_structure(o,para,$1,$2) -                when /^(2)~(\S+)?/ -                  node_structure(o,para,$1,$2) -                when /^(3)~(\S+)?/ -                  node_structure(o,para,$1,$2) -                when /^(4)~(\S+)?/ # work on see Split_text_object -                  node_structure(o,para,$1,$2) -                when /^(5)~(\S+)?/ -                  node_structure(o,para,$1,$2) -                when /^(6)~(\S+)?/ -                  node_structure(o,para,$1,$2) -                else -                  if para =~ /<:verse>/ -                    node_structure(o,para) -                  elsif para =~ /<:group>/ -                    node_structure(o,para) -                  elsif para =~ /<:code>/ -                    node_structure(o,para) -                  elsif para =~/<!Th?.+/ # tables come as single block #work area 2005w13 -                    table=SiSU_Tables::Table_xml.new(para) -                    para=table.table_split -                    node_structure(o,para) -                  else node_structure(o,para,nil,nil) -                  end -                end -              end -            end -          end -        end -        obj.each do |o| -          para=o.txt unless o.txt =~/^%% / #comments are lost, consider -          if para +            para.gsub!(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'<i>\1</i>') +            para.gsub!(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'<b>\1</b>') +            para.gsub!(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'<u>\1</u>') +            para.gsub!(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'<del>\1</del>') +            para.gsub!(/#{Mx[:br_line]}|#{Mx[:br_paragraph]}/,'<br />')              if @rcdc==false \              and (para =~/~metadata/ \              or para =~/^1~meta\s+Document Information/) @@ -491,22 +506,28 @@ WOK                unless @rcdc                  format_scroll=SiSU_XML_format::Format_scroll.new(@md,@sto.text) if @sto.format =~/i[12]|null/                  case @sto.format -                when /^(1)~(\S+)?/ +                when /^(1):(\S*)/ +                  xml_clean(para)                    xml_structure(o,para,$1,$2)                    para=@sto.lev_para_ocn.heading_body1 -                when /^(2)~(\S+)?/ +                when /^(2):(\S*)/ +                  xml_clean(para)                    xml_structure(o,para,$1,$2)                    para=@sto.lev_para_ocn.heading_body2 -                when /^(3)~(\S+)?/ +                when /^(3):(\S*)/ +                  xml_clean(para)                    xml_structure(o,para,$1,$2)                    para=@sto.lev_para_ocn.heading_body3 -                when /^(4)~(\S+)?/ # work on see Split_text_object +                when /^(4):(\S*)/ # work on see Split_text_object +                  xml_clean(para)                    xml_structure(o,para,$1,$2)                    para=@sto.lev_para_ocn.heading_body4 -                when /^(5)~(\S+)?/ +                when /^(5):(\S*)/ +                  xml_clean(para)                    xml_structure(o,para,$1,$2)                    para=@sto.lev_para_ocn.heading_body5 -                when /^(6)~(\S+)?/ +                when /^(6):(\S*)/ +                  xml_clean(para)                    xml_structure(o,para,$1,$2)                    para=@sto.lev_para_ocn.heading_body6                  else @@ -519,6 +540,7 @@ WOK                      para.gsub!(/>/,'>')                      code_structure(o,para)                    elsif para =~/<!Th?.+/ # tables come as single block #work area 2005w13 +                  #elsif para =~/#{Mx[:gr_o]}Th?.+/ # tables come as single block #work area 2005w13                      table=SiSU_Tables::Table_xml.new(para)                      para=table.table_split                      table_structure(o,para) @@ -603,6 +625,7 @@ WOK        def xml          @sisu=[]          @data.each do |para| +          #para.gsub!(/#{Mx[:gl_o]}\S+?#{Mx[:gl_c]}/,'') #Danger, watch            para.gsub!(/<:\S+?>/,'')            para.gsub!(/<!.+?!>/,'')            para="#{para}\n" unless para.empty? diff --git a/lib/sisu/v0/sst_to_s_xml_sax.rb b/lib/sisu/v0/sst_to_s_xml_sax.rb index e7765d33..4b3ca7c8 100644 --- a/lib/sisu/v0/sst_to_s_xml_sax.rb +++ b/lib/sisu/v0/sst_to_s_xml_sax.rb @@ -137,7 +137,7 @@ module SiSU_simple_xml_model_sax        def initialize(data='',particulars='')          @data,@env,@md=data,particulars.env,particulars.md          @vz=SiSU_Env::Get_init.instance.skin -        @regx=/^(?:(?:<:p[bn]>\s*)?(?::?[A-C]~|\d~)(?:(\S+))?\s+)?(.+)/ +        @regx=/^(?:#{Mx[:mk_o]}:p[bn]#{Mx[:mk_c]}\s*)?(?:#{Mx[:lv_o]}[1-9]:(\S*)#{Mx[:lv_c]})?(.+)/          @tab="\t"          if @md            @trans=SiSU_XML_munge::Trans.new(@md) @@ -206,7 +206,7 @@ WOK          @@xml[:body] << "#{@tab*1}" << "\n" if para[@regx]          @@xml[:body] << if lv; %{#{@tab*1}<text class="h#{lv}">\n#{@tab*2}#{wrapped}\n#{@tab*1}</text>\n} << "\n"          elsif wrapped =~/\A%%?\s+/; %{<!--\n#{@tab*1}<text class="comment">\n#{@tab*2}#{wrapped}\n#{@tab*1}</text>\n-->\n} # comments -        else                   %{#{@tab*1}<text class="norm">\n#{@tab*2}#{wrapped}\n#{@tab*1}</text>\n} # main text, contents, body KEEP +        else                        %{#{@tab*1}<text class="norm">\n#{@tab*2}#{wrapped}\n#{@tab*1}</text>\n} # main text, contents, body KEEP          end          #@@xml[:body] << "#{@tab*1}<text>\n#{@tab*2}#{wrapped}\n#{@tab*1}</text>\n" # main text, contents, body KEEP          @@xml[:body] << "#{@endnotes}" if @endnotes # main text, endnotes KEEP @@ -252,9 +252,12 @@ WOK            x.gsub!(/&/,'&') unless x =~/&\S+;/          end        end +      def xml_clean(para) +        para.gsub!(/#{Mx[:gl_o]}[1-9]:\S*?#{Mx[:gl_c]}/,'') #Danger, watch +        para +      end        def markup          data=[] -        #@data=@data.join.split("\n\n")          dir=SiSU_Env::Info_env.new(@md.fns)          xml_sc(@md)          @endnotes,@level,@cont,@copen,@xml_contents_close=[],[],[],[],[] @@ -262,7 +265,7 @@ WOK          (0..6).each { |x| @cont[x]=@level[x]=false }          (4..6).each { |x| @xml_contents_close[x]='' }          @data.each do |para| -          data << SiSU_document_structure::Structure.new(@md,para).structure +          data << SiSU_document_structure::Structure.new(@md,para).structure #takes on Mx marks          end          data.each do |para|            if para !~/^\s*(?:%+ |<:code>)/ @@ -275,11 +278,14 @@ WOK            end            para=@trans.markup_light(para)            @trans.char_enc.utf8(para) if @sys.locale =~/utf-?8/i #% utf8 -          if para =~/\A(?:@|0~)(\S+?):?\s+(.+?)\Z/m # for headers +          para.gsub!(/^0~(\S+)/,"#{Mx[:lv_o]}@\\1#{Mx[:lv_c]}") +          para.gsub!(/^@(\S+?):/,"#{Mx[:lv_o]}@\\1#{Mx[:lv_c]}") +          if para =~/\A#{Mx[:lv_o]}@(\S+?)#{Mx[:lv_c]}\s*(.+?)\Z/m # for headers              d_meta=SiSU_text_utils::Header_scan.new(@md,para).meta              if d_meta; xml_head(d_meta)              end            end +          para='' if para=~/#{Mx[:lv_o]}@\S+?#{Mx[:lv_c]}/            if @rcdc==false \            and (para =~/~metadata/ or para =~/^1~meta\s+Document Information/)              @rcdc=true @@ -287,24 +293,30 @@ WOK            if para !~/(^0~|^@\S+?:|^\s*$|<ENDNOTES>|<EOF>)/              @sto=SiSU_text_parts::Split_text_object.new(@md,para).lev_segname_para              unless @rcdc -              format_scroll=SiSU_XML_format::Format_scroll.new(@md,@sto.text) if @sto.format =~/i[12]|null/ +              format_scroll=SiSU_XML_format::Format_scroll.new(@md,@sto.text) if @sto.format =~/i[1-9]|null/                case @sto.format -              when /^(1)~(\S+)?/ +              when /^(1):(\S*)/ +                xml_clean(para)                  xml_structure(para,$1,$2)                  para=@sto.lev_para_ocn.heading_body1 -              when /^(2)~(\S+)?/ +              when /^(2):(\S*)/ +                xml_clean(para)                  xml_structure(para,$1,$2)                  para=@sto.lev_para_ocn.heading_body2 -              when /^(3)~(\S+)?/ +              when /^(3):(\S*)/ +                xml_clean(para)                  xml_structure(para,$1,$2)                  para=@sto.lev_para_ocn.heading_body3 -              when /^(4)~(\S+)?/ # work on see Split_text_object +              when /^(4):(\S*)/ # work on see Split_text_object +                xml_clean(para)                  xml_structure(para,$1,$2)                  para=@sto.lev_para_ocn.heading_body4 -              when /^(5)~(\S+)?/ +              when /^(5):(\S*)/ +                xml_clean(para)                  xml_structure(para,$1,$2)                  para=@sto.lev_para_ocn.heading_body5 -              when /^(6)~(\S+)?/ +              when /^(6):(\S*)/ +                xml_clean(para)                  xml_structure(para,$1,$2)                  para=@sto.lev_para_ocn.heading_body6                #when /^(i1)$/i @@ -328,17 +340,18 @@ WOK                #    end                else                  if para =~ /<:verse>/ -                  poem_structure(para) +                  para=poem_structure(para)                  elsif para =~ /<:group>/ -                  group_structure(para) +                  para=group_structure(para)                  elsif para =~ /<:code>/                    para.gsub!(/</,'<')                    para.gsub!(/>/,'>') -                  code_structure(para) +                  para=code_structure(para) +                #elsif para =~/#{Mx[:gr_o]}Th?.+/ # tables come as single block #work area 2005w13                  elsif para =~/<!Th?.+/ # tables come as single block #work area 2005w13                    table=SiSU_Tables::Table_xml.new(para)                    para=table.table_split -                  table_structure(para) +                  para=table_structure(para)                  else xml_structure(para,nil,nil)                  end                end @@ -367,7 +380,9 @@ WOK              end              para.gsub!(/<:\S+?>/,'')              para.gsub!(/<!.+!>/,'') ## Clean Prepared Text #bugwatch reinstate +            para            end +          para          end          6.downto(4) do |x|            y=x - 1; v=x - 3 @@ -419,6 +434,7 @@ WOK        def xml          @sisu=[]          @data.each do |para| +          #para.gsub!(/#{Mx[:gl_o]}\S+?#{Mx[:gl_c]}/,'') #Danger, watch            para.gsub!(/<:\S+?>/,'')            para.gsub!(/<!.+?!>/,'')            para="#{para}\n" unless para.empty? diff --git a/lib/sisu/v0/sysenv.rb b/lib/sisu/v0/sysenv.rb index 3d01729e..a259d991 100644 --- a/lib/sisu/v0/sysenv.rb +++ b/lib/sisu/v0/sysenv.rb @@ -380,7 +380,8 @@ module SiSU_Env            @@flv ||=document_language_versions_found[:f]            unless @@fns =~/\S+?\.zip/              @@fnz ||=if @@fns =~/(?:\~\S{2,3})?\.(?:ssm\.sst|ssm)$/; @@fnb + '.ssm.zip' -            else @@fnb + '.sst.zip' +            elsif @fnb; @@fnb + '.sst.zip' +            else '' # e.g. termsheet              end            end          else m=/(.+?)\.((?:-|ssm\.)?sst|ssm)$/ @@ -491,6 +492,16 @@ module SiSU_Env          :xhtml           => filename(code,'scroll','.xhtml'),          :pdf_l           => filename(code,'landscape','.pdf'),          :pdf_p           => filename(code,'portrait','.pdf'), +        :pdf_l_a4        => filename(code,'landscape.a4','.pdf'), +        :pdf_p_a4        => filename(code,'portrait.a4','.pdf'), +        :pdf_l_a5        => filename(code,'landscape.a5','.pdf'), +        :pdf_p_a5        => filename(code,'portrait.a5','.pdf'), +        :pdf_l_b5        => filename(code,'landscape.b5','.pdf'), +        :pdf_p_b5        => filename(code,'portrait.b5','.pdf'), +        :pdf_l_letter    => filename(code,'landscape.letter','.pdf'), +        :pdf_p_letter    => filename(code,'portrait.letter','.pdf'), +        :pdf_l_legal     => filename(code,'landscape.legal','.pdf'), +        :pdf_p_legal     => filename(code,'portrait.legal','.pdf'),          :toc             => filename(code,'toc','.html'),          :doc             => filename(code,'doc','.html'),          :index           => filename(code,'index','.html'), @@ -665,14 +676,8 @@ module SiSU_Env        end        @texpdf      end -    def latex2pdf(md=nil)                                                              #convert from latex to pdf +    def latex2pdf(md,papersize='a4')                                                              #convert from latex to pdf        tell=((@cmd =~/[MVv]/) ? '' : '> /dev/null' ) -      papersize='a4' -      papersize=if md and defined? md.papersize and not md.papersize.empty? \ -      and md.papersize =~/(?:a4|letter|legal|book|a5|b5)\b/ -        md.papersize -      else papersize -      end        mode='batchmode'        #mode='nonstopmode'        program_ref="\n\t\tSee http://www.tug.org/applications/pdftex/\n\t\tOn Debian this is is included in tetex-extra" @@ -2045,8 +2050,8 @@ WOK        is      end      def papersize                                                              # paper settings, default overidden in param if set within document -      if defined? @rc['default']['papersize'];   @rc['default']['papersize'].downcase -      else                                       defaults[:papersize].downcase +      if defined? @rc['default']['papersize']; @rc['default']['papersize'].downcase +      else                                     defaults[:papersize].downcase        end      end      def odf_structure @@ -3130,6 +3135,11 @@ WOK        dest="#{@env.path.webserv}/_sisu/image"        cp_images(src,dest)      end +    def cp_webserver_images_local #this should not have been necessary +      src=@env.path.image_source +      dest="#{@env.path.webserv}/#{@env.path.stub_pwd}/_sisu/image" +      cp_images(src,dest) +    end      def cp_base_images #fix images        src="#{@env.path.share}/image"        dest="#{@env.path.webserv}/_sisu/image_sys" diff --git a/lib/sisu/v0/texinfo.rb b/lib/sisu/v0/texinfo.rb index 2b10c04c..adcba123 100644 --- a/lib/sisu/v0/texinfo.rb +++ b/lib/sisu/v0/texinfo.rb @@ -160,11 +160,11 @@ module SiSU_TexInfo        data.each do |para|          # DEBUG 2003w16 this is a kludge, because i could not get parameters          # from param, Sort out ... revert to more elegant solution -        if para =~ /<!Th?¡\s+c/u +        if para =~ /#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s+c/u            @@flag['tables']='y' # KLUDGE get from param          end          para.gsub!(/<:p[bn]>/,'') -        para.gsub!(/(^|\s)\{(.+?)\}((?:https?|file):\/\/\S+)/,'\1(\2 [linked to:] \3)') +        para.gsub!(/(^|#{Mx[:gl_c]}|\s)\{(.+?)\}((?:https?|file):\/\/\S+)/,'\1(\2 [linked to:] \3)')          do_mono=TexInfoFormat::Texinfo.new(para,@md)          @tex_file << do_mono.spec_char        end @@ -176,10 +176,10 @@ module SiSU_TexInfo        @tex_file=[]        data.each do |para|          # BUG bug -> have problems with endnotes in headers -        if para =~ /\\~@\{\d+\s+/ #if para =~ /<!e\s+/ # watch -          para.gsub!(/\s*\\~@\{(?:\d+)\s+(.+?)<#@dp>@\}\\~/m,' @footnote{ \1} ') -        elsif para =~ /\\~@\{\*+\s+/ #if para =~ /<!e\s+/ # watch -          para.gsub!(/\s*\\~@\{(\*+)\s+(?:.+?)<#@dp>@\}\\~/m,' @footnote{ \1} ') +        if para =~ /#{Mx[:en_a_o]}\d+\s+/ #if para =~ /<!e\s+/ # watch +          para.gsub!(/\s*#{Mx[:en_a_o]}(?:\d+)\s+(.+?)#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/m,' @footnote{ \1} ') +        elsif para =~ /#{Mx[:en_a_o]}\*+\s+/ #if para =~ /<!e\s+/ # watch +          para.gsub!(/\s*#{Mx[:en_a_o]}(\*+)\s+(?:.+?)#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/m,' @footnote{ \1} ')          end          @tex_file << para        end @@ -190,16 +190,16 @@ module SiSU_TexInfo        @tex_file=[]        @@counting=0        data.each do |para| -        if para =~ /<:code>/ +        if para =~ /#{Mx[:gr_o]}code#{Mx[:gr_c]}/            @@flag['code']=true            @@counting=1          end -        if para =~ /<:verse>/ +        if para =~ /#{Mx[:gr_o]}verse#{Mx[:gr_c]}/            @@flag['poem']=1          end          if @@flag['code']            if @@flag['code'] \ -          and para =~ /<:code[-_](?:end|close)>/ #watch change not tested 200501 +          and para =~ /#{Mx[:gr_o]}code[-_](?:end|close)#{Mx[:gr_c]}/ #watch change not tested 200501              @@flag['code']=false            end            if @@flag['code'] \ @@ -211,7 +211,7 @@ module SiSU_TexInfo            end          elsif @@flag['poem']==1            if @@flag['poem']==1 \ -          and para =~ /<:verse[-_](?:end|close)>/ #watch change not tested 200501 +          and para =~ /#{Mx[:gr_o]}verse[-_](?:end|close)#{Mx[:gr_c]}/ #watch change not tested 200501              @@flag['poem']=0            end            if @@flag['poem']==1 \ @@ -229,7 +229,7 @@ module SiSU_TexInfo        data=@data        data.each do |line|          if line =~ /\S/ \ -        and line !~ /<:(code|verse).+/ +        and line !~ /#{Mx[:gr_o]}(code|verse).+/            if @@flag['code']              line.gsub!(/^\s*(.+)/m, "\\noindent \\marginpar\[left-text\]{\\begin{tiny}#{@@counting}\\end{tiny}}\\1\\")              @@counting+=1 if @@flag['code'] @@ -243,7 +243,7 @@ module SiSU_TexInfo        @tex_file=[]        @@tableheader=0        data.each do |para| -        if para =~ /¡|<!T/ui +        if para =~ /#{Mx[:tc_p]}|#{Mx[:gr_o]}T/ui            do_mono=TexInfoFormat::Texinfo.new(para,@md)            para=do_mono.longtable # using longtable latex package          end @@ -264,21 +264,21 @@ module SiSU_TexInfo        @submenu,@subsubmenu={},{}        data.each do |para|          para.gsub!(/\s*<:name#example>\s*/,' ') -        if para =~ /^[1-3]\\+~\S*(.+?)\s*$/ +        if para =~ /^#{Mx[:lv_o]}[1-3]:\S*?#{Mx[:lv_c]}\s*(.+?)\s*$/            toc=TexInfoFormat::Texinfo.new($1,@md)            texinfo_menu << toc.menu -        elsif para =~ /^[4-6]\\+~(?:\S+)?\s+(.+?)\s*$/ +        elsif para =~ /^#{Mx[:lv_o]}[4-6]:\S*?#{Mx[:lv_c]}\s*(.+?)\s*$/            toc=TexInfoFormat::Texinfo.new($1,@md)            texinfo_menu << toc.menu            case para -          when /^[4]\\+~\S+\s+(.+?)\s*$/ +          when /^#{Mx[:lv_o]}4:\S+?#{Mx[:lv_c]}\s*(.+?)\s*$/              n_menu+=1              @submenu[n_menu]=[] -          when /^[5]\\+~\S+\s+(.+?)\s*$/ +          when /^#{Mx[:lv_o]}5:\S+?#{Mx[:lv_c]}\s*(.+?)\s*$/              n_submenu+=1              @subsubmenu[n_menu]=[]              @submenu[n_menu] << toc.menu -          when /^[6]\\+~\S+\s+(.+?)\s*$/ +          when /^#{Mx[:lv_o]}6:\S+?#{Mx[:lv_c]}\s*(.+?)\s*$/              n_submenu+=1              @subsubmenu[n_submenu]=[]              @subsubmenu[n_submenu] << toc.menu @@ -299,14 +299,14 @@ module SiSU_TexInfo        data.each do |para|          mono=TexInfoFormat::Texinfo.new(para,@md)          case para -        when /^1\\+/; mono.level1 -        when /^2\\+/; mono.level2 -        when /^3\\+/; mono.level3 -        when /^4\\+~/ +        when /^#{Mx[:lv_o]}1:/; mono.level1 +        when /^#{Mx[:lv_o]}2:/; mono.level2 +        when /^#{Mx[:lv_o]}3:/; mono.level3 +        when /^#{Mx[:lv_o]}4:/;            mono.level4            n_menu+=1            @@do_submenu,@@do_subsubmenu=1,1 -        when /^5\\+/ +        when /^#{Mx[:lv_o]}5:/;            n_submenu+=1            @@do_subsubmenu=1            if @@do_submenu==1 @@ -315,7 +315,7 @@ module SiSU_TexInfo              @@do_submenu=0            else mono.level5            end -        when /^6\\+/ +        when /^#{Mx[:lv_o]}6:/;            if @@do_submenu==1              menu=TexInfoFormat::Texinfo.new(@subsubmenu[n_menu],@md)              para="#{menu.subsubmenu}#{mono.level6}" @@ -339,9 +339,7 @@ module SiSU_TexInfo            if para !~/\S/              para=nil            else -            para.gsub!(/<\\~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/,'<\1>') -            #para.gsub!(/<\\~(\d+);\w\d+;\w\d+><#@dp:#@dp>/,'<\1>') -            #para.gsub!(/<\\~(\d+);\w\d+;\w\d+><#@dp:#@dp>/,'<\1>') +            para.gsub!(/#{Mx[:id_o]}\\~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/,'<\1>')              para            end          end @@ -369,7 +367,7 @@ module SiSU_TexInfo        no1=num_top; no2=(num_top + 1); no3=(num_top + 2);  no4=(num_top + 3);        data.each do |para|          if @md.markup =~ /num_top/i \ -        and para !~ /0\\+/ +        and para !~ /#{Rx[:meta]}/            if para =~ /^[1-6]\\+(?:~\S+)?\s*<!h-.+?-!>/ \            and para !~ /<:\d-endnotes>/              header=para[/<!h-(.+?)-!>/m, 1].gsub!(/-/m,'.') @@ -390,9 +388,9 @@ module SiSU_TexInfo        @tex_file=[]        paranumber=0        data.each do |para| -        if para =~/<\\~(\d+);\w\d+;\w\d+><#@dp:#@dp>/ \ -        and para !~ /<EOF>/ -          parablock,paranum=/(.+?)<\\~(\d+);\w\d+;\w\d+><#@dp:#@dp>/im.match(para)[1,2] +        if para =~/#{Mx[:id_o]}\\~(\d+);\w\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}/ \ +        and para !~ /#{Mx[:br_eof]}/ +          parablock,paranum=/(.+?)#{Mx[:id_o]}\\~(\d+);\w\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}/im.match(para)[1,2]            do_duo=TexInfoFormat::DuoTex.new(parablock,paranum) ###is BUG            para=do_duo.paraNum if parablock          end diff --git a/lib/sisu/v0/texinfo_format.rb b/lib/sisu/v0/texinfo_format.rb index 5bcdf04d..42d62960 100644 --- a/lib/sisu/v0/texinfo_format.rb +++ b/lib/sisu/v0/texinfo_format.rb @@ -237,7 +237,7 @@ WOK        "@bye"      end      def clean(para) -      para.gsub!(/<\\~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/,'<\1>') +      para.gsub!(/#{Mx[:id_o]}\\~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/,'<\1>')        para.gsub!(/\s*[,:]\s*/,' - ')        para.gsub!(/<:#>/,'')        para.strip! @@ -249,21 +249,21 @@ WOK        "* #{para}::"      end      def level1 -      @para.gsub!(/[1]\\+~/,'') +      @para.gsub!(/#{Mx[:lv_o]}1:\S*?#{Mx[:lv_c]}\s*/,'')        para=clean(@para)        nd=para.gsub(/@footnote\{.+?\}\s+/,'')        para="@node #{nd}\n@unnumbered #{para}\n@cindex chapter, #{nd}\n"        @para.gsub!(/.+/,"#{para}")      end      def level2 -      @para.gsub!(/[2]\\+~/,'') +      @para.gsub!(/#{Mx[:lv_o]}2:\S*?#{Mx[:lv_c]}\s*/,'')        para=clean(@para)        nd=para.gsub(/@footnote\{.+?\}\s+/,'')        para="@node #{nd}\n@unnumbered #{para}\n@cindex chapter, #{nd}\n"        @para.gsub!(/.+/,"#{para}")      end      def level3 -      @para.gsub!(/[3]\\+\~/,'') +      @para.gsub!(/#{Mx[:lv_o]}3:\S*?#{Mx[:lv_c]}\s*/,'')        para=clean(@para)        nd=para.gsub(/@footnote\{.+?\}\s+/,'')        #para=para.gsub(/(.+?)\s*(@footnote\{.+?\})\s*(.+)$/,"\\1 \\3\n\\2") @@ -272,21 +272,21 @@ WOK        @para.gsub!(/.+/,"#{para}")      end      def level4 -      @para.gsub!(/[4]\\+~\S+/,'') +      @para.gsub!(/#{Mx[:lv_o]}4:\S+?#{Mx[:lv_c]}\s*/,'')        para=clean(@para)        nd=para.gsub(/@footnote\{.+?\}\s+/,'')        para="@node #{nd}\n@unnumbered #{para}\n@cindex chapter, #{nd}\n"        @para.gsub!(/.+/,"#{para}")      end      def level5 -      @para.gsub!(/[5]\\+~\S+/,'') +      @para.gsub!(/#{Mx[:lv_o]}5:\S*?#{Mx[:lv_c]}\s*/,'')        para=clean(@para)        nd=para.gsub(/@footnote\{.+?\}\s+/,'')        para="@node #{nd}\n@unnumbered #{para}\n@cindex chapter, #{nd}\n"        @para.gsub!(/.+/,"#{para}")      end      def level6 -      @para.gsub!(/[6]\\+~\S+/,'') +      @para.gsub!(/#{Mx[:lv_o]}6:\S*?#{Mx[:lv_c]}\s*/,'')        para=clean(@para)        nd=para.gsub(/@footnote\{.+?\}\s+/,'')        para="@node #{nd}\n@unnumbered #{para}\n@cindex chapter, #{nd}\n" @@ -313,16 +313,16 @@ WOK        @para.gsub!(/<:i2>(.*)/,'\1')      end      def spec_char # special characters -      @para.gsub!(/<EOF>/i,'') -      @para.gsub!(/©/,'(c)') -      @para.gsub!(/&(lt|#060);/,'<'); @para.gsub!(/&(gt|#062);/,'>') -      @para.gsub!(/{/,'{'); @para.gsub!(/}/,'}') -      @para.gsub!(/&#(126|152);/i,'~') -      @para.gsub!(/!/,'!') -      @para.gsub!(/#/,'#') -      @para.gsub!(/*/,'*') -      @para.gsub!(///,'/') -      @para.gsub!(/_/,'_') +      @para.gsub!(/#{Mx[:br_eof]}/i,'') +      @para.gsub!(/#{Mx[:gl_o]}#169#{Mx[:gl_c]}/,'(c)') +      @para.gsub!(/#{Mx[:gl_o]}#(?:lt|060)#{Mx[:gl_c]}/,'<'); @para.gsub!(/#{Mx[:gl_o]}(gt|#062)#{Mx[:gl_c]}/,'>') +      @para.gsub!(/#{Mx[:gl_o]}#123#{Mx[:gl_c]}/,'{'); @para.gsub!(/#{Mx[:gl_o]}#125#{Mx[:gl_c]}/,'}') +      @para.gsub!(/#{Mx[:gl_o]}#(?:126|152)#{Mx[:gl_c]}/i,'~') +      @para.gsub!(/#{Mx[:gl_o]}#033#{Mx[:gl_c]}/,'!') +      @para.gsub!(/#{Mx[:gl_o]}#035#{Mx[:gl_c]}/,'#') +      @para.gsub!(/#{Mx[:gl_o]}#042#{Mx[:gl_c]}/,'*') +      @para.gsub!(/#{Mx[:gl_o]}#047#{Mx[:gl_c]}/,'/') +      @para.gsub!(/#{Mx[:gl_o]}#095#{Mx[:gl_c]}/,'_')        @para.gsub!(/<sup><font face=symbol>&atild;<\/font><\/sup>/,' ')        @para.gsub!(/\\/,'\\backslash ')        @para.gsub!(/<:pb>/,'\\newpage') @@ -375,9 +375,9 @@ WOK      def longtable        @end_table="\\end{longtable}"        @row_break='\\\\\\' -      if @para[/<!Th?¡\s+c(\d+);(.+?)!>/ui] +      if @para[/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s+c(\d+);(.+?)#{Mx[:gr_c]}/ui] #CHECK !> closure          no_of_cols,cols_width=$1,$2 -        @@tableheader=1 if @para =~ /<!Th/i +        @@tableheader=1 if @para =~ /#{Mx[:gr_o]}Th/i          @w=cols_width.split(/;\s+/)          @@number_of_cols=no_of_cols          @colW=[] @@ -390,17 +390,17 @@ WOK          @colW=@colW.join          @@start_table="\\setlength{\\LTleft}{0pt}\n\\setlength{\\LTright}{\\fill}\n" +            "\\begin{longtable}[hb]#@colW\n" -        @para.gsub!(/<!Th?¡\s+c\d+?;.+!>/u,"#{@@start_table}") +        @para.gsub!(/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s+c\d+?;.+#{Mx[:gr_c]}/u,"#{@@start_table}")        end -      if @para =~/<!TZ!>/ -        @para.gsub!(/<!TZ!>/," #@end_table") +      if @para =~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/ +        @para.gsub!(/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/," #@end_table")        end -      @para.gsub!(/<!¡/u,'') +      @para.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}/u,'')        if @@tableheader==1 -        if @para =~/¡\d+?¡(.+?)(?:¡|!)/u +        if @para =~/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|!)/u            tablefoot=para[/\<!f(.+?)!\>/,1]            @para.gsub!(/\<!f(.+?)!\>/,'') -          @para.gsub!(/¡\d+?¡(.+?)(?:¡|!)/u, +          @para.gsub!(/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|!)/u,            "{\\begin{tiny} {\\bfseries \\1}\\end{tiny}}&")            @para.gsub!(/&>\s*$/,            " #@row_break \\hline\\endhead #@row_break") @@ -409,8 +409,8 @@ WOK            @@number_of_cols=0          end        else -        if @para =~/¡\d+?¡(.+?)(?:¡|!)/u -          @para.gsub!(/¡\d+?¡(.+?)(?:¡|!)/u,"\\begin{tiny}\\1\\end{tiny}&") +        if @para =~/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|!)/u +          @para.gsub!(/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|!)/u,"\\begin{tiny}\\1\\end{tiny}&")            @para.gsub!(/&>\s*$/," #@row_break")          end        end @@ -423,7 +423,7 @@ WOK        @end_table="\\end{tabular}"        @row_break='\\\\\\\\'        @break_page="#@row_break\n#@row_break \n" -      if @para[/<!Th?¡\s+c(\d+);(.+?)!>/ui] +      if @para[/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s+c(\d+);(.+?)#{Mx[:gr_c]}/ui]          no_of_cols,cols_width=$1,$2          @w=cols_width.split(/;\s+/)          @colW=[] @@ -432,13 +432,13 @@ WOK            @colW << "p{#{col_w}cm}" if col_w          end          @@start_table="\\begin{tabular}{#@colW}\n" -        @para.gsub!(/<!Th?¡\s+c\d+?;.+!>/u,"#{@@start_table}") +        @para.gsub!(/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s+c\d+?;.+#{Mx[:gr_c]}/u,"#{@@start_table}")        end -      if @para =~/<!TZ!>/ -        @para.gsub!(/<!TZ!>/,"#@end_table") +      if @para =~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/ +        @para.gsub!(/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/,"#@end_table")          @@table_pg_break_counter=1        end -      if @para =~/<!¡/u +      if @para =~/#{Mx[:tc_o]}#{Mx[:tc_p]}/u          if @@table_pg_break_counter==28 # taken from 34 ideal for portrait to 28 which suits landscape            @para =              "\n\n#@end_table \n" + @@ -446,14 +446,14 @@ WOK              "#{@@start_table}\n"            @@table_pg_break_counter=1          else -          @para.gsub!(/<!¡/u,'') +          @para.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}/u,'')            @@table_pg_break_counter+=1            tablefoot=@para[/\<!f(.+?)!\>/]            @para.gsub!(/\<!f(.+?)!\>/,'')          end        end -      if @para =~/¡\d+?¡(.+?)(?:¡|!)/u -      @para.gsub!(/¡\d+?¡(.+?)(?:¡|!)/u,"\\begin{tiny}\\1\\end{tiny}&") +      if @para =~/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|!)/u +      @para.gsub!(/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|!)/u,"\\begin{tiny}\\1\\end{tiny}&")        @para.gsub!(/&>\s*$/,"#@row_break")        end        @para diff --git a/lib/sisu/v0/texpdf.rb b/lib/sisu/v0/texpdf.rb index 1d37b588..8d951dfb 100644 --- a/lib/sisu/v0/texpdf.rb +++ b/lib/sisu/v0/texpdf.rb @@ -72,7 +72,7 @@ module SiSU_TeX    @@tabular="{tabular}"    @@column_instruct=@@squigle_close=@@tex_line_mode=@@tex_word_mode=@@line_mode=''    @@tex_debug_counter=@@table_pagebreak_counter=@@tex_footnote_call_counter=@@tex_table_flag=@@tex_counter=@@tex_column=@@tex_columns=@@tex_columns=@@counting=0 -  @@tex_pattern_margin_number="\\\\begin\\\{tiny\\\}~\\\\end\\\{tiny\\\}\\\{\\\\marginpar.+?\s+" +  @@tex_pattern_margin_number=/\\\\begin\\\{tiny\\\}~\\\\end\\\{tiny\\\}\\\{\\\\marginpar.+?\s+/    #@@tex_pattern_margin_number="\\\\marginpar.+?\s+"    @@n=@@tableheader=@@rights=nil    @@date ||=SiSU_Env::Info_date.new @@ -116,12 +116,10 @@ module SiSU_TeX          tell=SiSU_Screen::Ansi.new(@opt.cmd,@opt.fns,"#{@env.program.pdf_viewer} #{path}/#{@md.fnb}/#{@md.fn[:pdf_p]}")          tell.flow if @opt.cmd =~/[MVv]/          @md=@particulars.md -        my_make=SiSU_Env::Create_file.new(@opt.cmd,@opt.fns) +        SiSU_Env::Create_file.new(@opt.cmd,@opt.fns)          $flag=@md.cmd                                                         #introduced to pass 0 for no object citation numbers... to texpdf_format          @dir_o="#{@env.path.output}/#{@opt.fnb}"          directories -        filename_index="#{@md.txt_path}/pdf" -        newfilename=filename_index                                                                               #% needed needs to be reprogrammed !!!          SiSU_Env::Info_skin.new(@md).select          dal_array=SiSU_DAL::Source.new(@opt).get # dal file drawn here @@ -160,33 +158,49 @@ module SiSU_TeX        def initialize(md,env)          @md,@env=md,env        end -      def latex_do(texfilename) +      def latex_do(texfilename,papersize)          @texfilename=texfilename          @@n_lpdf=@@n_lpdf+1 -        tell=SiSU_Screen::Ansi.new(@md.cmd,'portrait ->') +        tell=SiSU_Screen::Ansi.new(@md.cmd,"#{papersize} portrait ->")          tell.dark_grey_title_hi if @md.cmd =~/[MVv]/          tex_fn_base=@texfilename.gsub(/\.tex$/,'')          cmd=SiSU_Env::System_call.new("#{tex_fn_base}.tex",'',@md.cmd)          tell=SiSU_Screen::Ansi.new(@md.cmd)          tell.grey_open unless @md.cmd =~/q/ -        2.times { |i| cmd.latex2pdf(@md) unless ("#{tex_fn_base}.tex" !~/\w+/) } +        if "#{tex_fn_base}" =~/\w+/ \ +        and "#{papersize}" =~/\w+/ +          2.times { |i| cmd.latex2pdf(@md,papersize) } +        end          tell.p_off unless @md.cmd =~/q/ -        tell=SiSU_Screen::Ansi.new(@md.cmd,'landscape ->') +        tell=SiSU_Screen::Ansi.new(@md.cmd,"#{papersize} landscape ->")          tell.dark_grey_title_hi if @md.cmd =~/[MVv]/          cmd=SiSU_Env::System_call.new("#{tex_fn_base}.landscape.tex",'',@md.cmd)          tell.grey_open -        2.times { |i| cmd.latex2pdf(@md) unless ("#{tex_fn_base}.landscape.tex" !~/\w+/) } +        if "#{tex_fn_base}" =~/\w+/ \ +        and "#{papersize}" =~/\w+/ +          2.times { |i| cmd.latex2pdf(@md,papersize) } +        end          tell.p_off unless @md.cmd =~/q/          pwd=Dir.pwd          portrait_pdf="#{pwd}/#{tex_fn_base}.pdf"          landscape_pdf="#{pwd}/#{tex_fn_base}.landscape.pdf" +        case papersize +        when /a4/;     pdf_p=@md.fn[:pdf_p_a4];     pdf_l=@md.fn[:pdf_l_a4] +        when /a5/;     pdf_p=@md.fn[:pdf_p_a5];     pdf_l=@md.fn[:pdf_l_a5] +        when /b5/;     pdf_p=@md.fn[:pdf_p_b5];     pdf_l=@md.fn[:pdf_l_b5] +        when /letter/; pdf_p=@md.fn[:pdf_p_letter]; pdf_l=@md.fn[:pdf_l_letter] +        when /legal/;  pdf_p=@md.fn[:pdf_p_legal];  pdf_l=@md.fn[:pdf_l_legal] +        else           pdf_p=@md.fn[:pdf_p_a4];     pdf_l=@md.fn[:pdf_l_a4] +        end          if FileTest.file?(portrait_pdf) -          cp(portrait_pdf,"#@dir_sisu/#{@md.fnb}/#{@md.fn[:pdf_p]}") +          cp(portrait_pdf,"#@dir_sisu/#{@md.fnb}/#{pdf_p}")            rm(portrait_pdf) +        else p "here #{__FILE__} #{__LINE__} NOT FOUND: #{portrait_pdf}" if @md.cmd.inspect =~/M/          end          if FileTest.file?(landscape_pdf) -          cp(landscape_pdf,"#@dir_sisu/#{@md.fnb}/#{@md.fn[:pdf_l]}") +          cp(landscape_pdf,"#@dir_sisu/#{@md.fnb}/#{pdf_l}")            rm(landscape_pdf) +        else p "here #{__FILE__} #{__LINE__}  NOT FOUND: #{landscape_pdf}" if @md.cmd.inspect =~/M/          end          tell=SiSU_Screen::Ansi.new(@md.cmd,@@n_lpdf,'processed (SiSU LaTeX to pdf - using pdfetex aka. pdftex or pdflatex)')          tell.generic_number unless @md.cmd =~/q/ @@ -198,25 +212,50 @@ module SiSU_TeX            @tex_f_no=0            info={}            if FileTest.file?(@env.source_file_with_path) -            if @md.fns =~/\.(?:-|ssm\.)?sst$/ -              @dirout=SiSU_Env::Info_env.new(@md.fns) -              case @md.fns -              when /\.(?:-|ssm\.)?sst$/ -                if FileTest.directory?(@env.path.tex)==true -                  Dir.chdir(@env.path.tex) -                  @dir_sisu=@dirout.path.output -                  texfile=@md.fns.gsub(/$/,'.tex') -                  texfile=texfile.gsub(/~/,'-') -                  if File.exist?(texfile) \ -                  and File.size(texfile) > 0 -                    @tex_f_no+=1 -                    latex_do(texfile) -                  else -                    puts "\tzero file size #{@env.path.tex}/#{@md.fns}" +            @md.papersize_array.each do |ps| +              if @md.fns =~/\.(?:-|ssm\.)?sst$/ +                @dirout=SiSU_Env::Info_env.new(@md.fns) +                case @md.fns +                when /\.(?:-|ssm\.)?sst$/ +                  if FileTest.directory?(@env.path.tex)==true +                    Dir.chdir(@env.path.tex) +                    @dir_sisu=@dirout.path.output +                    texfile=@md.fns.gsub(/$/,".#{ps}.tex") +                    texfile=texfile.gsub(/~/,'-') +                    if File.exist?(texfile) \ +                    and File.size(texfile) > 0 +                      @tex_f_no+=1 +                      latex_do(texfile,ps) +                    else +                      puts "\tzero file size #{@env.path.tex}/#{texfile}" +                    end                    end                  end                end              end +            outputdir="#@dir_sisu/#{@md.fnb}" +            case @md.papersize_array[0] #default pdf +            when /a4/;     pdf_p=@md.fn[:pdf_p_a4];     pdf_l=@md.fn[:pdf_l_a4] +            when /a5/;     pdf_p=@md.fn[:pdf_p_a5];     pdf_l=@md.fn[:pdf_l_a5] +            when /b5/;     pdf_p=@md.fn[:pdf_p_b5];     pdf_l=@md.fn[:pdf_l_b5] +            when /letter/; pdf_p=@md.fn[:pdf_p_letter]; pdf_l=@md.fn[:pdf_l_letter] +            when /legal/;  pdf_p=@md.fn[:pdf_p_legal];  pdf_l=@md.fn[:pdf_l_legal] +            else           pdf_p=@md.fn[:pdf_p_a4];     pdf_l=@md.fn[:pdf_l_a4] +            end +            if FileTest.file?("#{outputdir}/#{pdf_p}") +              system(" +                cd #{outputdir} +                rm portrait.pdf +                ln -s #{pdf_p} portrait.pdf +              ") +            end +            if FileTest.file?("#{outputdir}/#{pdf_l}") +              system(" +                cd #{outputdir} +                rm landscape.pdf +                ln -s #{pdf_l} landscape.pdf +              ") +            end            else              tell=SiSU_Screen::Ansi.new(@md.cmd,"FILE NOT FOUND: << #{@md.fns} >> - requested latex system processing skipped")              tell.warn @@ -232,7 +271,14 @@ module SiSU_TeX        #include SiSU_Param        @@tex_backslash ||="\\\\"        @@tilde='\\\\\\~' #?? debug crazy -      @@tex_head={ :p => nil, :l => nil } +      @@tex_head={ +        'a4'=>{:p => nil, :l => nil}, +        'a5'=>{:p => nil, :l => nil}, +        'b5'=>{:p => nil, :l => nil}, +        'letter'=>{:p => nil, :l => nil}, +        'legal'=>{:p => nil, :l => nil}, +        'book'=>{:p => nil, :l => nil} +      }        @@flag_alt,@@flag_group,@@flag_code=false,false,false        @@dp,@@prefix_b=nil,nil        def initialize(particulars) @@ -260,30 +306,30 @@ module SiSU_TeX            tell.txt_grey unless @md.cmd =~/q/            if @md.dc_rights              use=@md.dc_rights.dup #dup is necessary, else contents of :rights changed -            do_mono=SiSU_TeX_Pdf::Format_text_object.new(@md,use) +            sp_char=SiSU_TeX_Pdf::Special_characters.new(@md,use)              copymark=if @md.creator_copymark; '{\\begin{small}\\raisebox{1ex}{\\copyright}\\end{small}} '              else ''              end              copymark='Copyright {\\begin{small}\\raisebox{1ex}{\\copyright}\\end{small}} ' -            copyright=do_mono.special_characters_safe.gsub(/^\s*Copyright \(C\)/, copymark) +            copyright=sp_char.special_characters_safe.gsub(/^\s*Copyright \(C\)/, copymark)              @@rights||="\n #{@@tex_backslash*2}[3]\\ \\linebreak #{copyright}"            end            if @md.prefix_b -            do_mono=SiSU_TeX_Pdf::Format_text_object.new(@md,@md.prefix_b) -            prefix_b=do_mono.special_characters_safe +            sp_char=SiSU_TeX_Pdf::Special_characters.new(@md,@md.prefix_b) +            prefix_b=sp_char.special_characters_safe              @@prefix_b="\n #{@@tex_backslash*2}[3]\\ \\linebreak \\ #{prefix_b}\n" unless @@prefix_b            end            data=pre(data)            data=footnote(data)            if @md.flag_tables -           data=tables(data) +            data=tables(data)            end            ocn=if @md.markup.inspect =~/no_ocn/ \            or @md.mod.inspect =~/--no-ocn/ \            or @skin_no_ocn              false -           else true -           end +          else true +          end            data=number_paras(data,ocn)            data=markup(data)            output(data) @@ -298,22 +344,22 @@ module SiSU_TeX            # DEBUG 2003w16 this is a kludge, because i could not get parameters            # from param, Sort out ... revert to more elegant solution            # even more of a kludge as had to insert newlines where code is used not satisfactory, think about -          para=if para =~/<:br>|\n/; para.split(/<:br>|\n/) +          para=if para =~/#{Mx[:br_nl]}|\n/; para.split(/#{Mx[:br_nl]}|\n/)            else para            end            if para.class == String -            @md.flag_tables=true if para =~/<!Th?¡\s+c/u -            do_mono=SiSU_TeX_Pdf::Format_text_object.new(@md,para) -            @tex_file << do_mono.special_characters +            @md.flag_tables=true if para =~/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s+c/u +            sp_char=SiSU_TeX_Pdf::Special_characters.new(@md,para) +            @tex_file << sp_char.special_characters            elsif para.class == Array              para.each do |grp| -              @md.flag_tables=true if grp =~/<!Th?¡\s+c/u -              do_mono=SiSU_TeX_Pdf::Format_text_object.new(@md,grp) -              @tex_file << do_mono.special_characters +              @md.flag_tables=true if grp =~/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s+c/u +              sp_char=SiSU_TeX_Pdf::Special_characters.new(@md,grp) +              @tex_file << sp_char.special_characters              end            end          end -        data=@tex_file.delete_if {|x| x =~/^\s*0#{@@tilde}/} +        data=@tex_file.delete_if {|x| x =~/^\s*#{Rx[:meta]}/}          @tex_file        end        def footnote(data) @@ -321,29 +367,34 @@ module SiSU_TeX          data.each do |para|            # EMBEDDED FOOTNOTES / ENDNOTES should be straightforward but not quite a synch.            footnote=[] -          if para =~/~\\\{[\d*+]+\s|\\\~\[([*+]\d+)\s/                                                # note escape not necessary in front of ~ has implications for many other matches #debug note -            para.gsub!(/\\~\\\{(\d+)\s+(.+?)<#@dp>\\\}\\~/m,"\\footnote[\\1]{%\n \\2} ") #removed space before \\footnote 2004w21, watch -            para.gsub!(/\\~\[([*+]\d+)\s+(.+?)<#@dp>\]\\~/m,"\\FootnoteA{\\1}{%\n \\2} ") #work on asterisk footnotes -            para.gsub!(/\\~\\\{([*+]+)\s+(.+?)<#@dp>\\\}\\~/m,"\\FootnoteA{\\1}{%\n \\2} ") #work on asterisk footnotes +          if para =~/#{Mx[:en_a_o]}[\d*+]+\s|#{Mx[:en_b_o]}([*+]\d+)\s/                                                # note escape not necessary in front of ~ has implications for many other matches #debug note +            para.gsub!(/#{Mx[:en_a_o]}(\d+)\s+(.+?)#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/m,"\\footnote[\\1]{%\n \\2} ") #removed space before \\footnote 2004w21, watch +            para.gsub!(/#{Mx[:en_b_o]}([*+]\d+)\s+(.+?)#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_b_c]}/m,"\\FootnoteA{\\1}{%\n \\2} ") #work on asterisk footnotes +            para.gsub!(/#{Mx[:en_a_o]}([*+]+)\s+(.+?)#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/m,"\\FootnoteA{\\1}{%\n \\2} ") #work on asterisk footnotes            end            @tex_file << para          end          @tex_file        end        def tables_hash(md,para) -        para_p=para.dup #visit -        do_mono_l=SiSU_TeX_Pdf::Format_text_object.new(md,para) -        do_mono_p=SiSU_TeX_Pdf::Format_text_object.new(md,para_p) -        block={ -          :l => do_mono_l.longtable_landscape, -          :p => do_mono_p.longtable_portrait -        } +        @block={} +        @para=para +        @md.papersize_array.each do |ps| +          @@tableheader={ ps => { :p => 0, :l => 0 }} +          para,para_p=@para.dup,@para.dup #visit +          format_l=SiSU_TeX_Pdf::Format_text_object.new(md,para,ps) +          format_p=SiSU_TeX_Pdf::Format_text_object.new(md,para_p,ps) +          @block[ps]={ +            :l => format_l.longtable_landscape, +            :p => format_p.longtable_portrait +          } +        end +        @block        end        def tables(data) -        @@tableheader={ :p => 0, :l => 0 }          @tex_file=[]          data.each do |para| -          @tex_file << if para =~/¡|<!T/u +          @tex_file << if para =~/#{Mx[:tc_p]}|#{Mx[:gr_o]}T/u              tables_hash(@md,para) #Hash result            else para            end @@ -361,31 +412,31 @@ module SiSU_TeX        def markup_common(para)          tex_f=nil          mono=SiSU_TeX_Pdf::Format_text_object.new(@md,para) -        if para =~/<:(?:code|alt|verse|group)>/ \ +        if para =~/#{Mx[:gr_o]}(?:code|alt|verse|group)#{Mx[:gr_c]}/ \          or @@flag_alt -          if para =~/<:(?:code|alt|verse|group)>/ +          if para =~/#{Mx[:gr_o]}(?:code|alt|verse|group)#{Mx[:gr_c]}/              @lineone=case para -            when /<:(?:alt|verse|group)>/; para -            when /<:code>/; "#{@tex.paraskip_small} \\begin{scriptsize} " + para +            when /#{Mx[:gr_o]}(?:alt|verse|group)#{Mx[:gr_c]}/; para +            when /#{Mx[:gr_o]}code#{Mx[:gr_c]}/; "#{@tex.paraskip_small} \\begin{scriptsize} " + para              else 'error' #should never occur              end            end            if para =~/<=curly/ #takes care of escaped curly braces, expand -            do_mono=SiSU_TeX_Pdf::Format_text_object.new(@md,para) -            para=do_mono.special_characters_curly(para) +            sp_char=SiSU_TeX_Pdf::Special_characters.new(@md,para) +            para=sp_char.special_characters_curly(para)            end -          regx=/<:((?:code|alt|verse|group)(?:-end)?)>/m +          regx=/#{Mx[:gr_o]}((?:code|alt|verse|group)(?:-end)?)#{Mx[:gr_c]}/m +          x=nil            x=regx.match(para)[1] if para =~regx -          x=$1 -          para.gsub!(/\n<:(?:code|alt|verse|group)>\n/m,'') +          para.gsub!(/\n#{Mx[:gr_o]}(?:code|alt|verse|group)#{Mx[:gr_c]}\n/m,'')            para=enclose(para,'code') unless para =~/^$/            if x =~/(?:alt|verse|group)/; @@flag_alt=true              if x =~/group/; @@flag_group=true              end            elsif x =~/code/; @@flag_alt,@@flag_code=true,true -          elsif @@flag_alt; +          elsif @@flag_alt              if para =~ /\}(?:https?|file|ftp)/m -              para=mono.http #(@orientation) +              para=SiSU_TeX_Pdf::Format_text_object.new(@md,para,'a4').http              end              @group_collect << para #<< "\n\n"            end @@ -400,67 +451,84 @@ module SiSU_TeX              group_collect=[]              group_collect << '\begin{footnotesize} ' unless @@flag_code              @group_collect.each do |x| -              x.gsub!(/(<:\S+>|<!.*?!>|<!>)/,' ') +              x.gsub!(/(<:\S+>|#{Mx[:id_o]}.*?#{Mx[:id_c]}|#{Mx[:tc_o]}.*?#{Mx[:tc_c]}|#{Mx[:gr_o]}.*?#{Mx[:gr_c]}|<!.*?!>|<!>)/,' ') #Mx fix                x=x.split(/ \\\\ /)                group_collect << x              end              group_collect << ' \end{footnotesize} ' unless @@flag_code              @group_collect=group_collect.flatten -            @lineone.gsub!(/(<:\S+>|<!.*?!>|<!>)/,' ') +            @lineone.gsub!(/(<:\S+>|#{Mx[:fa_o]}.*?#{Mx[:fa_c]}|#{Mx[:gr_o]}.*?#{Mx[:gr_c]}|<!.*?!>|<!>)/,' ')              #@group_collect.each{ |x| x.gsub!(/(.#{@@tilde}\S*\s*|<:\S+>|<!.*?!>|<!>)/,' ') } -            #@lineone.gsub!(/(.#{@@tilde}\S*\s*|<:\S+>|<!.*?!>|<!>)/,' ')              insert=[] -            if para =~/<:code-end>/m +            insert=if para =~/#{Mx[:gr_o]}code-end#{Mx[:gr_c]}/m                insert << y + @lineone << @group_collect << ' \end{scriptsize}' << " #{@tex.paraskip_normal}"              else insert << y + @lineone << @group_collect              end +            para.gsub!(/(<:\S+>|#{Mx[:fa_o]}.*?#{Mx[:fa_c]}|#{Mx[:gr_o]}.*?#{Mx[:gr_c]}|<!.*?!>|<!>)/,' ')              @@flag_alt,@@flag_group,@@flag_code=false,false,false              @group_collect=[] -            para.gsub!(/(<:\S+>|<!.*?!>|<!>)/,' ') -            #para.gsub!(/(.#{@@tilde}\S*\s*|<:\S+>|<!.*?!>|<!>)/,' ')              #@tex_file << insert.flatten -            tex_f = insert.flatten +            tex_f=insert.flatten            end +          para=tex_f          else -          if para =~ /\}(?:https?|file|ftp)/ -            para=mono.http #(@orientation) -          end +          #if para =~ /\}(?:https?|file|ftp)/ +          #  para=mono.http #(@orientation) +          #end            case para -          when /^1#{@@tilde}/;       mono.level1 -          when /^2#{@@tilde}/;       mono.level2 -          when /^3#{@@tilde}/;       mono.level3 -          when /^4#{@@tilde}/;       mono.level4 -          when /^5#{@@tilde}/;       mono.level5 -          when /^6#{@@tilde}/;       mono.level6 -          when /^<:i([1-9])>/;       mono.indent($1) -          when /<:=/;                mono.symbol_graphic #watch -          when /^\s*<:image\s+/;     mono.image -          when /\}image/;            mono.png +          when /^#{Mx[:lv_o_1]}/;                    mono.level1 +          when /^#{Mx[:lv_o_2]}/;                    mono.level2 +          when /^#{Mx[:lv_o_3]}/;                    mono.level3 +          when /^#{Mx[:lv_o_4]}/;                    mono.level4 +          when /^#{Mx[:lv_o_5]}/;                    mono.level5 +          when /^#{Mx[:lv_o_6]}/;                    mono.level6 +          when /^#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]}/; mono.indent($1) +          when /<:=/;                                mono.symbol_graphic #watch +          when /^\s*<:image\s+/;                     mono.image +          when /\}image/;                            mono.png            else              para.strip!              para=enclose(para) unless para =~/^$/            end -          para.gsub!(/(\.#{@@tilde}\S*\s*|<:\S+>|<!.*?!>|<!>)/,' ')   #% tread with care +          para.gsub!(/\s*(?:#{Mx[:br_line]}|#{Mx[:br_nl]})\s*/,' \\\\\\\\ ')   #% tread with care +          para.gsub!(/(\.#{@@tilde}\S*\s*|<:\S+>|#{Mx[:fa_o]}.*?#{Mx[:fa_c]}|#{Mx[:gr_o]}.*?#{Mx[:gr_c]}|<!.*?!>|<!>)/,' ')   #% tread with care            #para.gsub!(/(.#{@@tilde}(?:\\~\S+)?\s*|<:\S+>|<!.*?!>|<!>)/,' ')  #KEEP reference, problem escaping open curly braces \{            if para =~/<=curly/ #takes care of escaped curly braces, expand -            do_mono=SiSU_TeX_Pdf::Format_text_object.new(@md,para) -            para=do_mono.special_characters_curly(para) +            sp_char=SiSU_TeX_Pdf::Special_characters.new(@md,para) +            para=sp_char.special_characters_curly(para) +          end +          para +        end +        if para =~ /\}(?:https?|file|ftp)/ +          para=if para !~/\.(?:png|jpg|gif)/ +            SiSU_TeX_Pdf::Format_text_object.new(@md,para,'a4').http +          else +            @block={} +            @md.papersize_array.each do |ps| +              image=SiSU_TeX_Pdf::Format_text_object.new(@md,para,ps).http +              @block[ps]={ +                :l => image, +                :p => image +              } +            end +            @block            end -          tex_f = para          end -        tex_f +        para        end        def markup(data)          @tex_file=[]          md={}          #% document headers watch special characters in title & subtitle: glark "\{\{~(sub)?title.+?[$&%#_\{\}]" *.(lm|er)?? -        home=@vz.txt_home.gsub(/<(br|p)>|<\/\s*(br|p)>|<(br|p)\s*\/>|\\\\/,' - ') #no line splitting in heading neither html nor latex -        title=@md.title.gsub(/<(br|p)>|<\/\s*(br|p)>|<(br|p)\s*\/>|\\\\/,' - ') #no line splitting in heading neither html nor latex -        subtitle=@md.subtitle.gsub(/<(br|p)>|<\/\s*(br|p)>|<(br|p)\s*\/>|\\\\/,' - ') if @md.subtitle #no line splitting in heading neither html nor latex -        orient_portrait=SiSU_TeX_Pdf::Format_text_object.new(@md,'portrait',"#{home}: - #{title} #{subtitle}") -        orient_landscape=SiSU_TeX_Pdf::Format_text_object.new(@md,'landscape',"#{home}: - #{title} #{subtitle}") -        @@tex_head[:p]=orient_portrait.document_head_with_orientation -        @@tex_head[:l]=orient_landscape.document_head_with_orientation +        home=@vz.txt_home.gsub(/#{Mx[:br_line]}|#{Mx[:br_nl]}|#{Mx[:br_paragraph]}|\\\\/,' - ') #no line splitting in heading neither html nor latex +        title=@md.title.gsub(/#{Mx[:br_line]}|#{Mx[:br_nl]}|#{Mx[:br_paragraph]}|\\\\/,' - ') #no line splitting in heading neither html nor latex +        subtitle=@md.subtitle.gsub(/#{Mx[:br_line]}|#{Mx[:br_nl]}|#{Mx[:br_paragraph]}|\\\\/,' - ') if @md.subtitle #no line splitting in heading neither html nor latex +        @md.papersize_array.each do |ps| +          orient_portrait=SiSU_TeX_Pdf::Format_head.new(@md,ps,'portrait',"#{home}: - #{title} #{subtitle}") +          orient_landscape=SiSU_TeX_Pdf::Format_head.new(@md,ps,'landscape',"#{home}: - #{title} #{subtitle}") +          @@tex_head[ps][:p]=orient_portrait.document_head_with_orientation +          @@tex_head[ps][:l]=orient_landscape.document_head_with_orientation +        end          @tex_file <<<<WOK  #{@tex.header}#{@tex.footer}  \\tolerance=500 @@ -481,8 +549,8 @@ WOK          @tex_file << x          x=nil          if @md.dc_creator -          do_mono=SiSU_TeX_Pdf::Format_text_object.new(@md,@md.dc_creator) -          creator=do_mono.special_characters +          sp_char=SiSU_TeX_Pdf::Special_characters.new(@md,@md.dc_creator) +          creator=sp_char.special_characters            @tex_file << if @md.creator_home              <<WOK @@ -533,10 +601,26 @@ WOK            if para.class == String              para=markup_common(para)            elsif para.class == Hash -            para={  -              :p => markup_common(para[:p]), -              :l => markup_common(para[:l]) -            } +            if ( para['a4'] or para['a5'] or para['b5'] \ +            or para['letter'] or para['legal']) +              @md.papersize_array.each do |ps| +                if para[ps] +                  if (para[ps][:p] and para[ps][:l]) +                    para[ps]={ +                      :p => markup_common(para[ps][:p]), +                      :l => markup_common(para[ps][:l]) +                    } +                  else p "here #{__FILE__} #{__LINE__}" if @md.cmd.inspect =~/M/ +                  end +                end +              end +            elsif (para[:p] and para[:l]) +              para = { +                :p => markup_common(para[:p]), +                :l => markup_common(para[:l]) +              } +            else p "here #{__FILE__} #{__LINE__}" if @md.cmd.inspect =~/M/ +            end            end            @tex_file << para          end @@ -553,7 +637,7 @@ WOK                url=%<#{l[:url]}>                url.gsub!(/(?:\\)*([$&~%_#}{^])/,"\\\\\\1")                         #latex special chars                s_lnk=l[:say] -              s_lnk.gsub!(/(<br>|<br \/>|<p>|<p \/>)/,'') +              s_lnk.gsub!(/\s*(#{Mx[:br_line]}|#{Mx[:br_nl]}|#{Mx[:br_paragraph]})\s*/,' \\\\\\\\ ')                s_lnk.gsub!(/(?:\\)*([$&~%_#}{^])/,"\\\\\\1")                       #latex special chars                if url !~/^\.(\.)?\//                  s_lnk_url=%<\\begin{scriptsize}\\href{#{url}}{#{url}}\\end{scriptsize}>  # note this bit of dereferencing magic @@ -589,77 +673,116 @@ WOK          @tex_file << "\n\\end{document}"        end        def number_paras_numbering(para,ocn) -        if para =~/<\\~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ \ -        and para !~/\\end\{longtable\}|<EOF>/ #catch <!TZ!> -          m=/(.+?)<\\~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m +        if para =~/#{Mx[:id_o]}\\~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ \ +        and para !~/\\end\{longtable\}|#{Mx[:br_eof]}/ #catch <!TZ!> +          m=/(.+?)#{Mx[:id_o]}\\~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m            parablock=para[m,1]            paranum=if ocn; para[m,2]            else ''            end            do_duo=SiSU_TeX_Pdf::Format_text_object.new(@md,parablock,paranum)            para=do_duo.para_num if parablock -        elsif para =~/^<~\d+;(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ #2005 this is added for tables, rationalise -          m=/<~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m +        elsif para =~/^#{Mx[:id_o]}~\d+;(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ #2005 this is added for tables, rationalise +          m=/#{Mx[:id_o]}~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m            paranum=para[m,1] -          para.gsub!(/<~\d+;(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>/,'') +          para.gsub!(/#{Mx[:id_o]}~\d+;(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}/,'')            para="\\marginpar{\\begin{tiny}#{paranum}\\end{tiny}}" + para -        elsif para =~/^<~\d+;(?:[oh]|[0-6]:)\d+;\w\d+>/ #extra 2005 this is added for tables, rationalise -          m=/<~(\d+);[oh]\d+;\w\d+>/m +        elsif para =~/^#{Mx[:id_o]}~\d+;(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}/ #extra 2005 this is added for tables, rationalise +          m=/#{Mx[:id_o]}~(\d+);[oh]\d+;\w\d+#{Mx[:id_c]}/m            paranum=para[m,1] -          para.gsub!(/<~\d+;(?:[oh]|[0-6]:)\d+;\w\d+>/,'') +          para.gsub!(/#{Mx[:id_o]}~\d+;(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}/,'')            para="\\marginpar{\\begin{tiny}#{paranum}\\end{tiny}}" + para          elsif para =~/\\end\{longtable\}/ #catch <!TZ!> -          para.gsub!(/<\\~\d+>|<\\~(\d+);(?:[ohm]|[0-6]:)\d+;\w\d+><#@dp:#@dp>/,'') -          para.gsub!(/<\\~\d+>|<\\~(\d+);(?:[ohm]|[0-6]:)\d+;\w\d+>/,'') #extra +          para.gsub!(/#{Mx[:id_o]}\\~\d+#{Mx[:id_c]}|#{Mx[:id_o]}\\~(\d+);(?:[ohm]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}/,'') +          para.gsub!(/#{Mx[:id_o]}\\~\d+#{Mx[:id_c]}|#{Mx[:id_o]}\\~(\d+);(?:[ohm]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}/,'') #extra          end          para        end        def number_paras(data,ocn)          tex_file=[]          data.each do |para| -          para=if para.class == Hash \ -          and (para[:p] and para[:l]) -            para = { -              :p => number_paras_numbering(para[:p],ocn), -              :l => number_paras_numbering(para[:l],ocn) -            } +          para=if para.class == Hash +            if ( para['a4'] or para['a5'] or para['b5'] \ +            or para['letter'] or para['legal']) +              @para={} +              @md.papersize_array.each do |ps| +                if para[ps] +                  if (para[ps][:p] and para[ps][:l]) +                    @para[ps]={ +                        :p => number_paras_numbering(para[ps][:p],ocn), +                        :l => number_paras_numbering(para[ps][:l],ocn) +                    } +                  else p "here #{__FILE__} #{__LINE__}" if @md.cmd.inspect =~/M/ +                  end +                end +              end +            elsif (para[:p] and para[:l]) +              @para = { +                :p => number_paras_numbering(para[:p],ocn), +                :l => number_paras_numbering(para[:l],ocn) +              } +            else p "here #{__FILE__} #{__LINE__}" if @md.cmd.inspect =~/M/ +            end            else #elsif para.class == String -            number_paras_numbering(para,ocn) +            @para=number_paras_numbering(para,ocn)            end -          tex_file << para +          tex_file << @para          end          tex_file        end        def output(array)          array.flatten!          array.compact! +        @array=array          fns_l=@md.fns.gsub(/~/,'-') #this is a sorry fix, but necessary as it appears latex programs like not ~ -        filename_tex_landscape=File.new("#{@env.path.tex}/#{fns_l}.landscape.tex",'w+') -        filename_tex_portrait=File.new("#{@env.path.tex}/#{fns_l}.tex",'w+') -        filename_tex_portrait << @@tex_head[:p] -        filename_tex_landscape << @@tex_head[:l] -        array.each do |para| -          case para -          when String -            para.gsub!(/^\s+/,'') -            if para !~/\A\s*\Z/ -              filename_tex_portrait.puts para,"\n" -              filename_tex_landscape.puts para,"\n" -            end -          when Hash -            para[:p].gsub!(/^\s+/,'') -            para[:l].gsub!(/^\s+/,'') -            if para[:p] !~/\A\s*\Z/ -              filename_tex_portrait.puts para[:p],"\n" -            end -            if para[:l] !~/\A\s*\Z/ -              filename_tex_landscape.puts para[:l],"\n" +        @md.papersize_array.each do |ps| +          filename_tex_landscape=File.new("#{@env.path.tex}/#{fns_l}.#{ps}.landscape.tex",'w+') +          filename_tex_portrait=File.new("#{@env.path.tex}/#{fns_l}.#{ps}.tex",'w+') +          filename_tex_portrait << @@tex_head[ps][:p] +          filename_tex_landscape << @@tex_head[ps][:l] +          array.each do |para| +            case para +            when String +              para.gsub!(/^\s+/,'') +              if para !~/\A\s*\Z/ +                filename_tex_portrait.puts para,"\n" +                filename_tex_landscape.puts para,"\n" +              end +            when Hash +              if para[ps] and (para[ps][:p] and para[ps][:l]) +                para[ps][:p].gsub!(/^\s+/,'') if para[ps][:p] +                para[ps][:l].gsub!(/^\s+/,'') if para[ps][:l] +                if para[ps][:p] !~/\A\s*\Z/ +                  filename_tex_portrait.puts para[ps][:p],"\n" +                end +                if para[ps][:l] !~/\A\s*\Z/ +                  filename_tex_landscape.puts para[ps][:l],"\n" +                end +              elsif (para[:p] and para[:l]) +                para[:p].gsub!(/^\s+/,'') if para[:p] +                para[:l].gsub!(/^\s+/,'') if para[:l] +                if para[:p] !~/\A\s*\Z/ +                  filename_tex_portrait.puts para[:p],"\n" +                end +                if para[:l] !~/\A\s*\Z/ +                  filename_tex_landscape.puts para[:l],"\n" +                end +              else p "here #{__FILE__} #{__LINE__}" if @md.cmd.inspect =~/M/ +              end              end            end +          array=@array +          filename_tex_portrait.close +          filename_tex_landscape.close          end -        filename_tex_portrait.close -        filename_tex_landscape.close -        @@tex_head={} #@@tex_head={ :p => nil, :l => nil } +        @@tex_head={ +          'a4'=>{:p => nil, :l => nil}, +          'a5'=>{:p => nil, :l => nil}, +          'b5'=>{:p => nil, :l => nil}, +          'letter'=>{:p => nil, :l => nil}, +          'legal'=>{:p => nil, :l => nil}, +          'book'=>{:p => nil, :l => nil} +        }          array=[]        end      end diff --git a/lib/sisu/v0/texpdf_format.rb b/lib/sisu/v0/texpdf_format.rb index ab4c7fe2..0fa439f0 100644 --- a/lib/sisu/v0/texpdf_format.rb +++ b/lib/sisu/v0/texpdf_format.rb @@ -61,215 +61,22 @@  module SiSU_TeX_Pdf    @@table_pg_break_counter=1    include SiSU_Viz -  class Use_TeX -    attr_accessor :url,:txt,:date -    def initialize(md) -      @md=md -      @vz=SiSU_Env::Get_init.instance.skin -      @date=SiSU_Env::Info_date.new # #{@date.year} -      @copymark='{\\begin{footnotesize}\\raisebox{1ex}{\\copyright}\\end{footnotesize}}' -      @url_brace=SiSU_Viz::Skin.new.url_decoration -    end -    def skip -      "\n\\vspace*{\\smallskipamount} \n" -    end -    def paraskip_normal -      '\setlength{\parskip}{1ex plus0.5ex minus0.2ex}' -    end -    def paraskip_small -      '\setlength{\parskip}{0.5ex plus0.2ex minus0.1ex}' -    end -    def skip_small -      #"\\smallskip{}" -    end -    def skip_small_vspace -      "\n\\vspace*{\\smallskipamount} \n" -    end -    def skip_small_footnote -      #"\n\\smallskip{}\n" -    end -    def skip_medium -      "\n\\medskip{}\n\n" -    end -    def skip_dummy -      "\n" -    end -    def header -      "\\lhead[ ]{ }\n" + -      "\\chead[ \\fancyplain{} \\bfseries \\footnotesize  \\leftmark ]{ \\fancyplain{} \\bfseries \\footnotesize \\rightmark }\n" + -      "\\rhead[ ]{ }\n" -    end -    def footer -      base_prog_txt=if @md.base_program -        case @md.base_program -        when /kdissert/i; " \\\\ \\href{http://freehackers.org/~tnagy/kdissert/}{Kdissert}" -        else '' -        end -      else '' -      end -      "\\lfoot[\\textrm{\\thepage}]{\\tiny \\href{#{@vz.url_sisu}}{#{@vz.txt_signature}}#{base_prog_txt}}\n" + -      "\\cfoot[\\href{#{@vz.url_home}}{#{@vz.url_txt}}]{\\href{#{@vz.url_home}}{#{@vz.url_txt}}}\n" + -      "\\rfoot[\\tiny \\href{#{@vz.url_sisu}}{#{@vz.txt_signature}}]{\\textrm{\\thepage}}\n" -    end -    def site -      "\\href{#{@vz.url_home}}{#{@vz.url_txt}}" -    end -    def sitename                                   #owners site, eg freeculture, free.for.all, gutenberg etc. -      "\\href{#{@vz.url_home}}{#{@vz.txt_home}}" -    end -    def owner_chapter -      "Contact Details for Original Promulgating Authority" -    end -    #BOOK standard dimensions - 229x156 -    def newpage(orientation) -      case orientation -      when /landscape/ # using longtable latex package -<<WOK -\\clearpage -WOK -      when /portrait/ -<<WOK -\\newpage -WOK -      end -    end -    def sisu_rights -      v=SiSU_Env::Info_version.new.get_version -      base_prog_txt=if @md.base_program -        case @md.base_program -        when /kdissert/i; "\n\\\\ This document prepared using \\href{http://freehackers.org/~tnagy/kdissert/}{Kdissert \\ http://freehackers.org/~tnagy/kdissert/ } \\\\ Kdissert is Document Mapping software by Thomas Nagy" -        else '' -        end -      else '' -      end -<<WOK -\\\\ ~ -{\\begin{footnotesize}#{base_prog_txt} -\\\\ Generated by \\href{http://www.jus.uio.no/sisu}{SiSU} \\begin{tiny}[ #{v[:project]} #{v[:version]} of #{v[:date_stamp]} ]\\end{tiny} \\href{http://www.jus.uio.no/sisu}{www.jus.uio.no/sisu} -\\\\ Copyright #@copymark 1997, current #{@date.year_static} Ralph Amissah, All Rights Reserved. -\\\\ SiSU is software for document structuring, publishing and search (with object citation numbering), \\href{http://www.sisudoc.org}{www.sisudoc.org} -\\\\ SiSU is released under \\href{http://www.fsf.org/licenses/gpl.html}{GPL 3 } or later, #{@url_brace.tex_open}\\href{http://www.fsf.org/licenses/gpl.html}{http://www.fsf.org/licenses/gpl.html}#{@url_brace.tex_close}. -{\\end{footnotesize} -\\\\ -WOK -    end -    def doc_sc_info_footnote_full -<<WOK -\\footnote{%\nGenerated by \\href{http://www.jus.uio.no/sisu}{SiSU \\ www.jus.uio.no/sisu }\\ \\newline \\scriptsize{Document version information: \\emph{sourcefile} \\uline{#{@md.fnstex}}; \\emph{version} \\uline{#{@md.sc_number}}; \\emph{date} \\uline{#{@md.sc_date}}; \\emph{time} \\uline{#{@md.sc_time}}}} -WOK -    end -    def doc_sc_info_footnote_brief -      " \\footnote{%\nGenerated by \\href{http://www.jus.uio.no/sisu}{SiSU} \\ \\href{http://www.jus.uio.no/sisu}{www.jus.uio.no/sisu} \\newline \\href{http://www.sisudoc.org}{www.sisudoc.org} \\\n}" -    end -    def doc_sc_info -      v=SiSU_Env::Info_version.new.get_version -<<WOK -\\\\ -{\\begin{footnotesize} -Document version information: \\\\ -\\emph{sourcefile} \\uline{#{@md.fnstex}}; \\emph{version} \\uline{#{@md.sc_number}}; \\emph{date} \\uline{#{@md.sc_date}}; \\emph{time} \\uline{#{@md.sc_time}} \\\\ -Generated by \\href{http://www.jus.uio.no/sisu}{SiSU www.jus.uio.no/sisu }\\- version information: \\\\ -\\uline{ #{v[:project]} #{v[:version]} of #{v[:date_stamp]}} -\\end{footnotesize}}& -WOK -    end -    def doc_no_sc_info -      v=SiSU_Env::Info_version.new.get_version -<<WOK -\\\\ -{\\begin{small} -Document information: \\\\ -\\emph{sourcefile} \\uline{#{@md.fnstex}} \\\\ -Generated by \\href{http://www.jus.uio.no/sisu}{SiSU www.jus.uio.no/sisu } \\\\ version information: \\ -\\uline{ #{v[:project]} #{v[:version]} of #{v[:date_stamp]}} - -\\end{small}}& -WOK -    end -    def manifest_info -      url=@md.fnb.gsub(/(?:\\)*([$&~%_#}{^])/,'\\\\\1') -      fn=@md.fn[:manifest].gsub(/(?:\\)*([$&~%_#}{^])/,'\\\\\1') -<<WOK -{\\begin{footnotesize} -\\\\ For alternative output formats of this document check: -\\\\ #{@url_brace.tex_open}\\begin{scriptsize}\\href{#{@vz.url_root_http}/#{url}/#{fn}}{#{@vz.url_root_http}/#{url}/#{fn}}\\end{scriptsize}#{@url_brace.tex_close} -\\end{footnotesize}}& -WOK -    end -    def endnotes #not used should be inserted before MetaData section which preceeds doc_tail, but is "part of document" -<<WOK -\\subsection*{Endnotes} -\\addcontentsline{toc}{section}{Endnotes} -\\ -\\listofendnotes -WOK -    end -    def doc_tail -      dir=SiSU_Env::Info_env.new(@md.fns) -      base_html="#{dir.url.root}/#{@md.fnb}" -      v=SiSU_Env::Info_version.new.get_version -      sisu_ico=if FileTest.file?("#{dir.path.image_source_tex}/sisu.png") -        "\\includegraphics*[width=60pt]{#{dir.path.image_source_tex}/sisu.png}" -      else -        tell=SiSU_Screen::Ansi.new(@md.cmd,'WARNING - image directory or image(s) missing:', %{"#{dir.path.image_source_tex}"} ) -        tell.warn unless @md.cmd =~/q/ -        " SiSU " -      end -      url=@md.fnb.gsub(/(?:\\)*([$&~%_#}{^])/,'\\\\\1') -<<WOK -\\subsection*{Information on this document copy and an unofficial List of Some web related information and sources} -\\addcontentsline{toc}{section}{Information on this document copy and an unofficial List of Some web related information and sources} -\\\\ -\"Support Open Standards and Software Libre for the Information Technology Infrastructure\" RA\\subsubsection*{Information on this document copy #{site}} -\\addcontentsline{toc}{subsection}{Information on this document copy} -{\\begin{footnotesize} -\\\\ Generated by \\href{http://www.jus.uio.no/sisu/}{SiSU} found at \\href{http://www.jus.uio.no/sisu/}{www.jus.uio.no/sisu} \\begin{tiny}[ #{v[:project]} #{v[:version]} #{v[:date_stamp]} ]\\end{tiny}  \\href{http://www.sisudoc.org}{www.sisudoc.org}. SiSU is software for document structuring, publishing and search (using SiSU: object citation numbering, markup, meta-markup, and system) Copyright #@copymark 1997, current #{@date.year_static} Ralph Amissah, All Rights Reserved. -\\\\ SiSU is released under \\href{http://www.fsf.org/licenses/gpl.html}{GPL 3 } or later (\\href{http://www.fsf.org/licenses/gpl.html}{www.fsf.org/licenses/gpl.html}). {\\end{footnotesize} -{\\begin{small} -\\\\ W3 since October 3 1993 \\href{http://www.jus.uio.no/sisu/}{#{sisu_ico}}SiSU 1997, current #{@date.year_static}. \\\\ #{sitename} presentations at \\begin{bfseries}#{site}\\end{bfseries} \\\\ \\\\ #{@md.title} \\textbf{pdf} versions can be found at:  \\\\ -{\\end{small} -\\begin{scriptsize}\\href{#{@vz.url_root_http}/#{url}/#{@md.fn[:pdf_p]}}{#{@vz.url_root_http}/#{url}/#{@md.fn[:pdf_p]}}\\end{scriptsize}  \\\\ -\\begin{scriptsize}\\href{#{@vz.url_root_http}/#{url}/#{@md.fn[:pdf_l]}}{#{@vz.url_root_http}/#{url}/#{@md.fn[:pdf_l]}}\\end{scriptsize}  \\\\ -\\\\\n#{@md.title} \\textbf{html} versions may be found at: \\\\ -\\begin{scriptsize}\\href{#{@vz.url_root_http}/#{url}/#{@md.fn[:toc]}}{#{@vz.url_root_http}/#{url}/#{@md.fn[:toc]}}\\end{scriptsize} or \\\\ -\\begin{scriptsize}\\href{#{@vz.url_root_http}/#{url}/#{@md.fn[:doc]}}{#{@vz.url_root_http}/#{url}/#{@md.fn[:doc]}}\\end{scriptsize} -\\\\ -\\\\ -\\href{#{@vz.url_root_http}/#{url}/#{@md.fn[:manifest]}}{SiSU Manifest} of document output and metadata may be found at: \\\\ -\\begin{scriptsize}\\href{#{@vz.url_root_http}/#{url}/#{@md.fn[:manifest]}}{#{@vz.url_root_http}/#{url}/#{@md.fnl[:pre]}sisu\\_manifest#{@md.fnl[:mid]}.html#{@md.fnl[:post]}}\\end{scriptsize} -\\\\ -\\\\ - #{sitename} found at: \\begin{bfseries}#{site}\\end{bfseries}\\subsubsection*{Links that may be of interest at #{@vz.txt_home} and elsewhere:} -\\addcontentsline{toc}{subsection}{Links that may be of interest} -WOK -    end -    def mail_tail #not retested, the old mail_tail is commented out and appended to this program -      dir=SiSU_Env::Info_env.new(@md.fns) -<<WOK -\\subsection*{Mail sender details} -\\addcontentsline{toc}{subsection}{Mail sender details} -\\\\ -Mail from: ralph@amissah.com\\\\ -44 20 8789 3452\\\\ -44 77 9669 4448 -\\\\ - \"Support Open Standards and Open Sources for the Information Technology Infrastructure\" RA -\\subsubsection*{Information on this document copy #{site}\\copyright} -Presentations' look and feel generated by \\href{http://www.jus.uio.no/sisu/}{SiSU Scribe} \\href{http://www.jus.uio.no/sisu/}{http://www.jus.uio.no/sisu/} programmed in Ruby on Debian/Gnu/Linux by Copyright \\copyright Ralph Amissah, W3 since October 3 1993 \\href{http://www.jus.uio.no/sisu/}{\\includegraphics*[width=35pt]{#{dir.path.image_source_tex}/sisu.png}}for #{sitename}. SiSU Scribe (sisu information structuring unit) produces Electronic Documents, i.e. it generates structured output for use in a number of file formats, including the pdf file produced here. -WOK -    end -  end    class Format_text_object      require 'iconv'      require "#{SiSU_lib}/defaults" -    attr_accessor :string,:string1,:string,:orientation,:url,:dir,:tex +    attr_accessor :string,:string1,:orientation,:url,:dir,:tex      @@sys=SiSU_Env::System_call.new      @@tex_backslash="\\\\"      @@tilde='\\\\\\~' #?? debug crazy -    @@tex_pattern_margin_number="\\\\begin\\\{tiny\\\}~\\\\end\\\{tiny\\\}\\\{\\\\marginpar.+?\s+" -    @@tableheader={ :p => 0, :l => 0 } +    @@tex_pattern_margin_number=/\\begin\{tiny\}~\\end\{tiny\}\{\\marginpar.+?\}\}\}/ +    @@tableheader={ +      'a4' => { :p => 0, :l => 0 }, +      'a5' => { :p => 0, :l => 0 }, +      'b5' => { :p => 0, :l => 0 }, +      'letter' => { :p => 0, :l => 0 }, +      'legal' => { :p => 0, :l => 0 } +    }      @@sys=SiSU_Env::System_call.new -    @@flag_code=false      @@dp=nil      def initialize(md,string,string1=nil)        @md,@string,@string1=md,string,string1 @@ -283,13 +90,14 @@ WOK        @tx=SiSU_Env::Get_init.instance.tex        @url_brace=SiSU_Viz::Skin.new.url_decoration        @tex2pdf=@@tex3pdf ||=SiSU_Env::System_call.new.tex2pdf_engine +      @ps=string1 if string1=~/(?:a4|letter|legal|book|a5|b5)/i      end      def longtable_landscape        @end_table='\end{longtable}'        @row_break='\\\\\\' -      if @string[/<!Th?¡\s+c(\d+);(.+?)!\\~(\d+;\w\d+;\w\d+)>/u] +      if @string[/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s+c(\d+);(.+?)#{Mx[:tc_p]}\\~(\d+;\w\d+;\w\d+)#{Mx[:gr_c]}/u]          no_of_cols,cols_width,ocn=$1,$2,$3 -        tw=case @md.papersize +        tw=case @ps          when /a4/i;      @tx.a4.landscape.w     #European default, SiSU default          when /letter/i;  @tx.letter.landscape.w #U.S. default          when /legal/i;   @tx.legal.landscape.w  #U.S. alternative @@ -298,9 +106,10 @@ WOK          else             @tx.a4.landscape.w     #default currently A4          end          textwidth=(tw.to_i/2) - 24 -        @@tableheader[:l]=1 if @string =~/<!Th/ +        @@tableheader[@ps][:l]=1 if @string =~/#{Mx[:gr_o]}Th/          w=cols_width.split(/;\s*/) -        @@number_of_cols=no_of_cols +        @@number_of_cols=no_of_cols ||=@@number_of_cols +        #@@number_of_cols=0 unless @@number_of_cols.to_i > 0          @colW=[]          @colW << '{'          w.each  do |x| @@ -311,39 +120,40 @@ WOK          end          @colW << '}'          @colW=@colW.join -        @start_table="<~#{ocn}>\n\\setlength{\\LTleft}{0pt}\n\\setlength{\\LTright}{\\fill}\n" + +        @start_table="#{Mx[:id_o]}~#{ocn}#{Mx[:id_c]}\n\\setlength{\\LTleft}{0pt}\n\\setlength{\\LTright}{\\fill}\n" +            "\\begin{tiny}\n\\begin{longtable}#@colW\n" -        @string.gsub!(/<!Th?¡\s+c\d+?;.+!\\~\d+;\w\d+;\w\d+>/u,@start_table) +        @string.gsub!(/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s+c\d+?;.+#{Mx[:tc_p]}\\~\d+;\w\d+;\w\d+#{Mx[:gr_c]}/u,@start_table)        end -      if @string =~/<!TZ!>/ -        @string.gsub!(/<!TZ!>/," #@end_table\n\\end{tiny}") +      if @string =~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/ +        @string.gsub!(/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/," #@end_table\n\\end{tiny}")        end -      @string.gsub!(/<!¡/u,'') -      if @@tableheader[:l] == 1 -        if @string =~/¡\d+?¡(.+?)(?:¡|!)/u +      @string.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}/u,'') +      if @@tableheader[@ps][:l] == 1 +        if @string =~/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|#{Mx[:tc_p]})/u            tablefoot=@string[/\<!f(.+?)!\>/,1]            @string.gsub!(/\<!f(.+?)!\>/,'') -          @string.gsub!(/¡\d+?¡(.+?)(?:¡|!)/u,'\bfseries \1&') -          @string.gsub!(/&>\s*$/," #@row_break \\hline\\endhead #@row_break") +          @string.gsub!(/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|#{Mx[:tc_c]})/u,'\bfseries \1&') +          @string.gsub!(/&\s*$/," #@row_break \\hline\\endhead #@row_break")            @string="#@string \\multicolumn{#{@@number_of_cols}}{l}{\\tiny #{tablefoot}} \\\\ \\hline\n\\endfoot\n\\hline\n" if tablefoot -          @@tableheader[:l],@@number_of_cols=0,0 +          @@tableheader[@ps][:l]=0 +          #@@tableheader[@ps][:l],@@number_of_cols=0,0          end        else -        if @string =~/¡\d+?¡(.+?)(?:¡|!)/u -          @string.gsub!(/¡\d+?¡(.+?)(?:¡|!)/u,'\1&') -          @string.gsub!(/&>\s*$/," #@row_break") +        if @string =~/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|#{Mx[:tc_c]})/u +          @string.gsub!(/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|!)/u,'\1&') +          @string.gsub!(/&\s*$/," #@row_break")          end        end -      @string=if ocn; "<~#{ocn}>" + @string +      @string=if ocn; "#{Mx[:id_o]}~#{ocn}#{Mx[:id_c]}" + @string        else @string        end      end      def longtable_portrait        @end_table='\end{longtable}'        @row_break='\\\\\\' -      if @string[/<!Th?¡\s+c(\d+);(.+?)!\\~(\d+;\w\d+;\w\d+)>/u] +      if @string[/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s+c(\d+);(.+?)#{Mx[:tc_p]}\\~(\d+;\w\d+;\w\d+)#{Mx[:gr_c]}/u]          no_of_cols,cols_width,ocn=$1,$2,$3 -        tw=case @md.papersize +        tw=case @ps          when /a4/i;      @tx.a4.portrait.w     #European default, SiSU default          when /letter/i;  @tx.letter.portrait.w #U.S. default          when /legal/i;   @tx.legal.portrait.w  #U.S. alternative @@ -352,9 +162,9 @@ WOK          else             @tx.a4.portrait.w     #default currently A4          end          textwidth=tw.to_i - 20 -        @@tableheader[:p]=1 if @string =~/<!Th/ +        @@tableheader[@ps][:p]=1 if @string =~/#{Mx[:gr_o]}Th/          w=cols_width.split(/;\s*/) -        @@number_of_cols=no_of_cols +        @@number_of_cols=no_of_cols ||=@@number_of_cols          @colW=[]          @colW << '{'          w.each  do |x| @@ -366,30 +176,31 @@ WOK          end          @colW << '}'          @colW=@colW.join -        @start_table="<~#{ocn}>\n\\setlength{\\LTleft}{0pt}\n\\setlength{\\LTright}{\\fill}\n" + +        @start_table="#{Mx[:id_o]}~#{ocn}#{Mx[:id_c]}\n\\setlength{\\LTleft}{0pt}\n\\setlength{\\LTright}{\\fill}\n" +            "\\begin{tiny}\n\\begin{longtable}#@colW\n" -        @string.gsub!(/<!Th?¡\s+c\d+?;.+!\\~\d+;\w\d+;\w\d+>/u,"#@start_table") +        @string.gsub!(/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s+c\d+?;.+#{Mx[:tc_p]}\\~\d+;\w\d+;\w\d+#{Mx[:gr_c]}/u,"#@start_table")        end -      if @string =~/<!TZ!>/ -        @string.gsub!(/<!TZ!>/," #@end_table\n\\end{tiny}") +      if @string =~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/ +        @string.gsub!(/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/," #@end_table\n\\end{tiny}")        end -      @string.gsub!(/<!¡/u,'') -      if @@tableheader[:p] == 1 -        if @string =~/¡\d+?¡(.+?)(?:¡|!)/u +      @string.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}/u,'') +      if @@tableheader[@ps][:p] == 1 +        if @string =~/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|!)/u            tablefoot=@string[/\<!f(.+?)!\>/,1]            @string.gsub!(/\<!f(.+?)!\>/,'') -          @string.gsub!(/¡\d+?¡(.+?)(?:¡|!)/u,'\bfseries \1&') -          @string.gsub!(/&>\s*$/," #@row_break \\hline\\endhead #@row_break") +          @string.gsub!(/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|#{Mx[:tc_c]})/u,'\bfseries \1&') +          @string.gsub!(/&\s*$/," #@row_break \\hline\\endhead #@row_break")            @string="#@string \\multicolumn{#{@@number_of_cols}}{l}{\\tiny #{tablefoot}} \\\\ \\hline\n\\endfoot\n\\hline\n" if tablefoot -          @@tableheader[:p],@@number_of_cols=0,0 +          @@tableheader[@ps][:p]=0 +          #@@tableheader[@ps][:p],@@number_of_cols=0,0          end        else -        if @string =~/¡\d+?¡(.+?)(?:¡|!)/u -          @string.gsub!(/¡\d+?¡(.+?)(?:¡|!)/u,'\1&') -          @string.gsub!(/&>\s*$/," #@row_break") +        if @string =~/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|#{Mx[:tc_c]})/u +          @string.gsub!(/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|#{Mx[:tc_c]})/u,'\1&') +          @string.gsub!(/&\s*$/," #@row_break")          end        end -      @string=if ocn; "<~#{ocn}>" + @string +      @string=if ocn; "#{Mx[:id_o]}~#{ocn}#{Mx[:id_c]}" + @string        else @string        end      end @@ -399,7 +210,7 @@ WOK        @end_table="\\end{tabular}"        @row_break='\\\\\\\\'        @break_page="#@row_break\n#@row_break \n" -      if @string[/<!Th?¡\s+c(\d+);(.+?)!>/u] +      if @string[/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s+c(\d+);(.+?)#{Mx[:gr_c]}/u]          no_of_cols,cols_width=$1,$2          @w=cols_width.split(/;\s*/)          @colW=[] @@ -408,391 +219,49 @@ WOK            @colW << "p{#{col_w}cm}" if col_w          end          @start_table="\\begin{tabular}{#@colW}\n" -        @string.gsub!(/<!Th?¡\s+c\d+?;.+!>/u,"#@start_table}") +        @string.gsub!(/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}\s+c\d+?;.+#{Mx[:gr_c]}/u,"#@start_table}")        end -      if @string =~/<!TZ!>/ -        @string.gsub!(/<!TZ!>/,"#@end_table") +      if @string =~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/ +        @string.gsub!(/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/,"#@end_table")          @@table_pg_break_counter=1        end -      if @string =~/<!¡/u +      if @string =~/#{Mx[:tc_o]}#{Mx[:tc_p]}/u          if @@table_pg_break_counter == 28 # taken from 34 ideal for portrait to 28 which suits landscape            @string="\n\n#@end_table \n#@break_page#@start_table\n"            @@table_pg_break_counter=1          else -          @string.gsub!(/<!¡/u,'') +          @string.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}/u,'')            @@table_pg_break_counter+=1            tablefoot=@string[/\<!f(.+?)!\>/,1]            @string.gsub!(/\<!f(.+?)!\>/,'')          end        end -      if @string =~/¡\d+?¡(.+?)(?:¡|!)/u -      @string.gsub!(/¡\d+?¡(.+?)(?:¡|!)/u,"\\1&") -      @string.gsub!(/&>\s*$/,"#@row_break") +      if @string =~/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|#{Mx[:tc_p]})/u +        @string.gsub!(/#{Mx[:tc_p]}\d+?#{Mx[:tc_p]}(.+?)(?:#{Mx[:tc_p]}|#{Mx[:tc_p]})/u,"\\1&") +        @string.gsub!(/&\s*$/,"#@row_break")        end        @string      end -    def pdftex_special_characters_1(string)             # ~ ^ $ & % _ { }  #LaTeX special characters - KEEP list -      #p @@utf_8.list -      #@string=Iconv.conv('ISO-8859-1', 'UTF-8', @string) -      word=string.scan(/\S+|\n/) #unless line =~/^(?:0~\S|%+\s)/ -      para_array=[] -      string=if word -        word.each do |w| # _ - / # | : ! ^ ~ -          unless string =~/^(?:0~|%+ |<!Th?¡ )/um -            w.gsub!(/[\\]?~/,'<=tilde>') unless w=~/^[1-6]~|~\{|\}~|~\[|\]~|^\^~\s|~\^|\*~\S+|~#|\{t~|<~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+>/ -            w.gsub!(/&#(?:126|152);/,'<=tilde>') #126 usual -            #w.gsub!(/&#(?:126|152);/,'<=tilde>') unless w=~/https?:\/\/\S+/ #126 usual -            w.gsub!(/\\?\|||/,'<=pipe>') #unless w=~/<~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+>/ # | SiSU not really special sisu character but done, also LaTeX -          end -          para_array << w -        end -        string=para_array.join(' ') -        string=string.strip -        string -      else '' -      end -      string.gsub!(/<~\d+;(?:\w|[0-6]:)\d+;[umdv]\d+><#@dp:#@dp>/,'') -      string.gsub!(/.+?<-#>/,'') -      string.gsub!(/<EOF>/,'') -      string.gsub!(/<ENDNOTES?>/,'') -      #problem sequence -> -      string.gsub!(/&(?:nbsp);/,'<=hardspace>')                                 # < SiSU special character also LaTeX -      string.gsub!(/&(?:lt|#060);/,'<=lt>')                                     # < SiSU special character also LaTeX -      string.gsub!(/&(?:gt|#062);/,'<=gt>')                                     # > SiSU special character also LaTeX -      string.gsub!(/{/,'<=curlyopen>')                                     # { SiSU special character also LaTeX -      string.gsub!(/}/,'<=curlyclose>')                                    # } SiSU special character also LaTeX -      string.gsub!(/&#(?:126|152);/,'<=tilde>')                                 # ~ SiSU special character also LaTeX -      string.gsub!(/#/,'\#')                                               # # SiSU special character also LaTeX -      string.gsub!(/!/,'!')                                                # ! SiSU not really special sisu character but done, also LaTeX -      string.gsub!(/*/,'*')                                                # * should you wish to escape astrisk e.g. describing \*{bold}* -      string.gsub!(/-/,'-')                                                # - SiSU special character also LaTeX -      string.gsub!(/+/,'+')                                                # + SiSU special character also LaTeX -      string.gsub!(/,/,',')                                                # + SiSU special character also LaTeX -      string.gsub!(/&/,'<=amp>') #unless @string=~/<:code>/                   # / SiSU special character also LaTeX -      string.gsub!(///,'<=slash>')                                         # / SiSU special character also LaTeX -      string.gsub!(/\/,'<=backslash>')                                     # \ SiSU special character also LaTeX -      string.gsub!(/_/,'<=underscore>')                                    # _ SiSU special character also LaTeX -      string.gsub!(/|/,'|')                                                # | SiSU not really special sisu character but done, also LaTeX -      string.gsub!(/:/,':')                                                # : SiSU not really special sisu character but done, also LaTeX -      string.gsub!(/^|\^/,'<=caret>')                                      # ^ SiSU not really special sisu character but done, also LaTeX -      string.gsub!(/\#/,'<=hash>') -      ##watch placement, problem sequence ^ -      string.gsub!(/<sup><font face=symbol>&atild;<\/font><\/sup>/,' ') -      string.gsub!(/<:pb>/,'\newpage') -      string.gsub!(/<:pn>/,'\clearpage') -      string.gsub!(/\\copy(right|mark)?/,'<=copymark>') # ok problem with superscript -      string -    end -    def pdftex_special_characters_2(string) -      string.gsub!(/œ/,'\oe ') -      string.gsub!(/\$/,'\$') -      string.gsub!(/\#/,'\#') -      string.gsub!(/\%/,'\%') -      string.gsub!(/\~/,'\~') #revist, should not be necessary to mark remaining tildes -      if string !~/^\s*<:image|\}:image\s/ -        string.gsub!(/_/,'\_') -      end -      string.gsub!(/\{/,'\{') -      string.gsub!(/\}/,'\}') -      string.gsub!(/ /,'~') # ~ character for hardspace -      # sequence important must appear after removal of { and } -      string.gsub!(/&\S+?;/,'') #hmmm -      # sequence imortant place before removal of & -      if string=~/<:code>/;        @@flag_code=true -      elsif string=~/<:code-end>/; @@flag_code=false -      end -      if @@flag_code; string.gsub!(/&/,'{\\\&}') -      else string.gsub!(/(\s+&\s+)/,' and ') -      end -      string.gsub!(/§/u,'\S') #latex: space between next character not preserved? #string.gsub!(/§ /,'\S ') -      string.gsub!(/£/u,'\pounds') -      string.gsub!(/&\S+?;/,' ') -      string.gsub!(/<a href=".+?">/,' ') -      string.gsub!(/<\/a>/,' ') -      string.gsub!(/[^\}>_]((?:https?|file|ftp):\/\/\S+?)(<\/\S>)/,' \begin{scriptsize}\href{\1}{\1} \end{scriptsize}\2') #special case -      string.gsub!(/((?:^|\s)[}])((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'\1\begin{scriptsize}\\href{\2}{\2}\end{scriptsize}\3') #special case \{ e.g. \}http://url -      string.gsub!(/\B(?:\\_|\\)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'\begin{scriptsize}\\href{\1}{\1}\end{scriptsize}\2') #specially escaped url no decoration -      unless @@flag_code -        string.gsub!(/(^|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/,"\\1#{@url_brace.tex_open}\\begin{scriptsize}\\href{\\2}{\\2}\\end{scriptsize}#{@url_brace.tex_close}\\3") #url matching with decoration <url> positive lookahead, sequence issue with { linked }http://url cannot use \b at start -      else #code-block: angle brackets special characters, note _ already escaped -        string.gsub!(/\\_</,'{\UseTextSymbol{OML}{<}}') -        string.gsub!(/\\_>/,'{\UseTextSymbol{OML}{>}}') -      end -      string.gsub!(/<:ee>/,'') -      string.gsub!(/<!>/,' ') -      #proposed change, insert, but may be redundant -      string.gsub!(/ \/><:i[12]>(.+?)(?:\}~|<br)/,' \begin{ParagraphIndent}{0.01\columnwidth}\1\end{ParagraphIndent} ') # footnote indents, problems if match exists in ordinary paragraphs? check! Work Area 200501 a bit tricky as must be able to match multiple times, and to clean remainder -      string.gsub!(/<(br|p)>|<\/\s*(br|p)>|<(br|p)\s*\/>/," #{@@tex_backslash*2} ") # Work Area -      string.gsub!(/<b>(.+?)<\/b>/,'\begin{bfseries}\1 \end{bfseries}') -      string.gsub!(/<em>(.+?)<\/em>/,'\begin{bfseries}\1 \end{bfseries}') -      string.gsub!(/<(bold|strong)>(.+?)<\/(bold|strong)>/,'\begin{bfseries}\1 \end{bfseries}') -      string.gsub!(/<h\d+>(.+?)<\/h\d+>/,'\begin{bfseries}\1 \end{bfseries}') -      string.gsub!(/<i>(.+?)<\/i>/,'\emph{\1}') -      string.gsub!(/<italic>(.+?)<\/italic>/,'\emph{\1}') -      string.gsub!(/<u>(.+?)<\/u>/,'\uline{\1}') # ulem -      string.gsub!(/<cite>(.+?)<\/cite>/,"``\\1''") # quote -      string.gsub!(/<ins>(.+?)<\/ins>/,'\uline{\1}') # ulem -      string.gsub!(/<del>(.+?)<\/del>/,'\sout{\1}') # ulem -      string.gsub!(/<sub>(.+?)<\/sub>/,"\$_{\\textrm{\\1}}\$") -      string.gsub!(/<sup>(.+?)<\/sup>/,"\$^{\\textrm{\\1}}\$") -      unless @@flag_code -        string.gsub!(/"(.+?)"/,'“\1”')  # quote marks / quotations open & close " need condition exclude for code -        string.gsub!(/\s+"/,' “')                                # open " -        string.gsub!(/^([1-6-]#{@@tilde}\S*|<.+?>)?\s*"/,'\1“')  # open " -        string.gsub!(/"(\s|\.|,|:|;)/,'”\1')                     # close " -        string.gsub!(/"([1-6-]#{@@tilde}\S*|<.+?>)?\s*$/,'”\1')  # close " -        string.gsub!(/"(\.|,)/,'”')                              # close " -        string.gsub!(/\s+'/,' `')                                # open ' -        string.gsub!(/^([1-6-]#{@@tilde}\S*|<.+?>)?\s*'/,'\1`')  # open ' -      end -      string.gsub!(/^(<:i[1-9]>)?\s*\\_\*\s*/,'\1 \begin{math} \bullet \end{math}~~') #bullets - added 2004w17 watch \\_ -      string.gsub!(/(<font.*?>|<\/font>)/,'') -      string.gsub!(/\s*<sup>(\S+?)<\/sup>/,'^\1') -      string.gsub!(/(<sup>|<\/sup>)/,'') -      string -    end -    def pdftex_special_characters_3(string) -      string.gsub!(/<br(\s*[^\/][^>])/,'\1') # clean up, incredibly messy :-( footnote indents, problems if match exists in ordinary paragraphs? check! Work Area 200501 a bit tricky as must be able to match multiple times, and to clean remainder -      string.gsub!(/([^<][^b][^r]\s+)\/>/,'\1') # clean up, incredibly messy :-( footnote indents, problems if match exists in ordinary paragraphs? check! Work Area 200501 a bit tricky as must be able to match multiple times, and to clean remainder -      #problem sequence (another kludge) -> -      string.gsub!(/<=lt>/,'{\UseTextSymbol{OML}{<}}') -      string.gsub!(/<=gt>/,'{\UseTextSymbol{OML}{>}}') -      #string.gsub!(/<=lt>/,'\<') -      #string.gsub!(/<=gt>/,'\>') -      string.gsub!(/<=underscore>/,'\_') -      string.gsub!(/(\href\{http:\/\/\S+?)(?:(?:<=tilde>)(\S+))+\}/,'\1\~\2}') #tildes in urls \href treated differently from text -      string.gsub!(/<=tilde>/,'{\~~}') -      string.gsub!(/<=pipe>/,'{\textbar}') -      string.gsub!(/<=caret>/,'{\^{~}}') -      #string.gsub!(/<=caret>/,'\^{}') -      string.gsub!(/<=exclaim>/,'\Verbatim{!}') -      string.gsub!(/<=hash>/,'{\#}') -      #string.gsub!(/<=hash>/,'{\UseTextSymbol{OT1}{#}}') -      #string.gsub!(/<=slash>/,'{\slash}') -      string.gsub!(/<=hardspace>/,'{~}') #changed ... 2005 -      string.gsub!(/<=amp>/,'{\\\&}') #changed ... 2005 -      #string.gsub!(/<=amp>/,'{\UseTextSymbol{OT1}{&}}') -      string.gsub!(/<=slash>/,'{/}') -      string.gsub!(/<=backslash>/,'{\textbackslash}') -      #string.gsub!(/<=asterisk>/,'*') -      #string.gsub!(/<=exclaim>/,'!') -      #string.gsub!(/<=asterisk>/,'{\ast}') -      #string.gsub!(/<=copymark>/,"^{\\copyright} ") # watch has been problematic -      #copymark='{\\begin{small}\\raisebox{1ex}{\\copyright}\\end{small}} ' -      string.gsub!(/<=copymark>\s*(.+)?\s+(<\\~\d+;\w(?:[0-6]:)?\d+;\w\d+><#@dp:#@dp>)/,"^\\copyright \\textnormal{\\1} \\2") # watch likely to be problematic -      string -    end -    def xetex_special_characters_1(string)             # ~ ^ $ & % _ { }  #LaTeX special characters - KEEP list -      #p @@utf_8.list -      #string=Iconv.conv('ISO-8859-1', 'UTF-8', @string) -      word=string.scan(/\S+|\n/) #unless line =~/^(?:0~\S|%+\s)/ -      para_array=[] -      string=if word -        word.each do |w| # _ - / # | : ! ^ ~ -          unless string =~/^(?:0~|%+ |<!Th?¡ )/um -            w.gsub!(/[\\]?~/,'<=tilde>') unless w=~/^[1-6]~|~\{|\}~|~\[|\]~|^\^~\s|~\^|\*~\S+|~#|\{t~|<~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+>/ -            w.gsub!(/&#(?:126|152);/,'<=tilde>') #126 usual -            #w.gsub!(/&#(?:126|152);/,'<=tilde>') unless w=~/https?:\/\/\S+/ #126 usual -            w.gsub!(/\\?\|||/,'<=pipe>') #unless w=~/<~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+>/ # | SiSU not really special sisu character but done, also LaTeX -          end -          para_array << w -        end -        string=para_array.join(' ') -        string=string.strip -        string -      else '' -      end -      string.gsub!(/<~\d+;(?:\w|[0-6]:)\d+;[umdv]\d+><#@dp:#@dp>/,'') -      string.gsub!(/.+?<-#>/,'') -      string.gsub!(/<EOF>/,'') -      string.gsub!(/<ENDNOTES?>/,'') -      #problem sequence -> -      string.gsub!(/&(?:nbsp);/,'<=hardspace>')                                 # < SiSU special character also LaTeX -      string.gsub!(/&(?:lt|#060);/,'<=lt>')                                     # < SiSU special character also LaTeX -      string.gsub!(/&(?:gt|#062);/,'<=gt>')                                     # > SiSU special character also LaTeX -      string.gsub!(/{/,'<=curlyopen>')                                     # { SiSU special character also LaTeX -      string.gsub!(/}/,'<=curlyclose>')                                    # } SiSU special character also LaTeX -      string.gsub!(/&#(?:126|152);/,'<=tilde>')                                 # ~ SiSU special character also LaTeX -      string.gsub!(/#/,'\#')                                               # # SiSU special character also LaTeX -      string.gsub!(/!/,'!')                                                # ! SiSU not really special sisu character but done, also LaTeX -      string.gsub!(/*/,'*')                                                # * should you wish to escape astrisk e.g. describing \*{bold}* -      string.gsub!(/-/,'-')                                                # - SiSU special character also LaTeX -      string.gsub!(/+/,'+')                                                # + SiSU special character also LaTeX -      string.gsub!(/,/,',')                                                # + SiSU special character also LaTeX -      string.gsub!(/&/,'<=amp>') #unless @string=~/<:code>/                   # / SiSU special character also LaTeX -      string.gsub!(///,'<=slash>')                                         # / SiSU special character also LaTeX -      string.gsub!(/\/,'<=backslash>')                                     # \ SiSU special character also LaTeX -      string.gsub!(/_/,'<=underscore>')                                    # _ SiSU special character also LaTeX -      string.gsub!(/|/,'|')                                                # | SiSU not really special sisu character but done, also LaTeX -      string.gsub!(/:/,':')                                                # : SiSU not really special sisu character but done, also LaTeX -      string.gsub!(/^|\^/,'<=caret>')                                      # ^ SiSU not really special sisu character but done, also LaTeX -      string.gsub!(/\#/,'<=hash>') -      ##watch placement, problem sequence ^ -      string.gsub!(/<sup><font face=symbol>&atild;<\/font><\/sup>/,' ') -      string.gsub!(/<:pb>/,'\newpage') -      string.gsub!(/<:pn>/,'\clearpage') -      string.gsub!(/\\copy(right|mark)?/,'<=copymark>') # ok problem with superscript -      string -    end -    def xetex_special_characters_2(string) -      string.gsub!(/œ/,'\oe ') -      string.gsub!(/\$/,'\$') -      string.gsub!(/\#/,'\#') -      string.gsub!(/\%/,'\%') -      string.gsub!(/\~/,'\~') #revist, should not be necessary to mark remaining tildes -      if string !~/^\s*<:image|\}:image\s/ -        string.gsub!(/_/,'\_') -      end -      string.gsub!(/\{/,'\{') -      string.gsub!(/\}/,'\}') -      string.gsub!(/ /,'~') # ~ character for hardspace -      # sequence important must appear after removal of { and } -      string.gsub!(/&\S+?;/,'') #hmmm -      # sequence imortant place before removal of & -      if string=~/<:code>/;        @@flag_code=true -      elsif string=~/<:code-end>/; @@flag_code=false -      end -      if @@flag_code; string.gsub!(/&/,'{\\\&}') -      else string.gsub!(/(\s+&\s+)/,' and ') -      end -      string.gsub!(/§/u,'\S') #latex: space between next character not preserved? #string.gsub!(/§ /,'\S ') -      string.gsub!(/£/u,'\pounds') -      string.gsub!(/&\S+?;/,' ') -      string.gsub!(/<a href=".+?">/,' ') -      string.gsub!(/<\/a>/,' ') -      string.gsub!(/[^\}>_]((?:https?|file|ftp):\/\/\S+?)(<\/\S>)/,' \begin{scriptsize}\href{\1}{\1} \end{scriptsize}\2') #special case -      string.gsub!(/((?:^|\s)[}])((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'\1\begin{scriptsize}\\href{\2}{\2}\end{scriptsize}\3') #special case \{ e.g. \}http://url -      string.gsub!(/\B(?:\\_|\\)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'\begin{scriptsize}\\href{\1}{\1}\end{scriptsize}\2') #specially escaped url no decoration -      unless @@flag_code -        string.gsub!(/(^|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/,"\\1#{@url_brace.tex_open}\\begin{scriptsize}\\href{\\2}{\\2}\\end{scriptsize}#{@url_brace.tex_close}\\3") #url matching with decoration <url> positive lookahead, sequence issue with { linked }http://url cannot use \b at start -      else #code-block: angle brackets special characters, note _ already escaped -        string.gsub!(/\\_</,'{\UseTextSymbol{OML}{<}}') -        string.gsub!(/\\_>/,'{\UseTextSymbol{OML}{>}}') -      end -      string.gsub!(/<:ee>/,'') -      string.gsub!(/<!>/,' ') -      #proposed change, insert, but may be redundant -      string.gsub!(/ \/><:i[12]>(.+?)(?:\}~|<br)/,' \begin{ParagraphIndent}{0.01\columnwidth}\1\end{ParagraphIndent} ') # footnote indents, problems if match exists in ordinary paragraphs? check! Work Area 200501 a bit tricky as must be able to match multiple times, and to clean remainder -      string.gsub!(/<(br|p)>|<\/\s*(br|p)>|<(br|p)\s*\/>/," #{@@tex_backslash*2} ") # Work Area -      string.gsub!(/<b>(.+?)<\/b>/,'\begin{bfseries}\1 \end{bfseries}') -      string.gsub!(/<em>(.+?)<\/em>/,'\begin{bfseries}\1 \end{bfseries}') -      string.gsub!(/<(bold|strong)>(.+?)<\/(bold|strong)>/,'\begin{bfseries}\1 \end{bfseries}') -      string.gsub!(/<h\d+>(.+?)<\/h\d+>/,'\begin{bfseries}\1 \end{bfseries}') -      string.gsub!(/<i>(.+?)<\/i>/,'\emph{\1}') -      string.gsub!(/<italic>(.+?)<\/italic>/,'\emph{\1}') -      string.gsub!(/<u>(.+?)<\/u>/,'\uline{\1}') # ulem -      string.gsub!(/<cite>(.+?)<\/cite>/,"``\\1''") # quote -      string.gsub!(/<ins>(.+?)<\/ins>/,'\uline{\1}') # ulem -      string.gsub!(/<del>(.+?)<\/del>/,'\sout{\1}') # ulem -      string.gsub!(/<sub>(.+?)<\/sub>/,"\$_{\\textrm{\\1}}\$") -      string.gsub!(/<sup>(.+?)<\/sup>/,"\$^{\\textrm{\\1}}\$") -      unless @@flag_code -        string.gsub!(/"(.+?)"/,'“\1”')  # quote marks / quotations open & close " need condition exclude for code -        string.gsub!(/\s+"/,' “')                                # open " -        string.gsub!(/^([1-6-]#{@@tilde}\S*|<.+?>)?\s*"/,'\1“')  # open " -        string.gsub!(/"(\s|\.|,|:|;)/,'”\1')                     # close " -        string.gsub!(/"([1-6-]#{@@tilde}\S*|<.+?>)?\s*$/,'”\1')  # close " -        string.gsub!(/"(\.|,)/,'”')                              # close " -        string.gsub!(/\s+'/,' `')                                # open ' -        string.gsub!(/^([1-6-]#{@@tilde}\S*|<.+?>)?\s*'/,'\1`')  # open ' -      end -      #string.gsub!(/^(<:i[1-9]>)?\s*\\_\*\s*/,'\1 \begin{math} \bullet \end{math}~~') #bullets - added 2004w17 watch \\_ -      string.gsub!(/^(<:i[1-9]>)?\s*\\_\*\s*/,'\1 ● ~~') -      string.gsub!(/(<font.*?>|<\/font>)/,'') -      string.gsub!(/\s*<sup>(\S+?)<\/sup>/,'^\1') -      string.gsub!(/(<sup>|<\/sup>)/,'') -      string -    end -    def xetex_special_characters_3(string) -      string.gsub!(/<br(\s*[^\/][^>])/,'\1') # clean up, incredibly messy :-( footnote indents, problems if match exists in ordinary paragraphs? check! Work Area 200501 a bit tricky as must be able to match multiple times, and to clean remainder -      string.gsub!(/([^<][^b][^r]\s+)\/>/,'\1') # clean up, incredibly messy :-( footnote indents, problems if match exists in ordinary paragraphs? check! Work Area 200501 a bit tricky as must be able to match multiple times, and to clean remainder -      #problem sequence (another kludge) -> -      string.gsub!(/<=lt>/,'{\UseTextSymbol{OML}{<}}') -      string.gsub!(/<=gt>/,'{\UseTextSymbol{OML}{>}}') -      #string.gsub!(/<=lt>/,'\<') -      #string.gsub!(/<=gt>/,'\>') -      string.gsub!(/<=underscore>/,'\_') -      string.gsub!(/(\href\{http:\/\/\S+?)(?:(?:<=tilde>)(\S+))+\}/,'\1\~\2}') #tildes in urls \href treated differently from text -      string.gsub!(/<=tilde>/,'{\~~}') -      string.gsub!(/<=pipe>/,'{\textbar}') -      string.gsub!(/<=caret>/,'{\^{~}}') -      #string.gsub!(/<=caret>/,'\^{}') -      string.gsub!(/<=exclaim>/,'\Verbatim{!}') -      string.gsub!(/<=hash>/,'{\#}') -      #string.gsub!(/<=hash>/,'{\UseTextSymbol{OT1}{#}}') -      #string.gsub!(/<=slash>/,'{\slash}') -      string.gsub!(/<=hardspace>/,'{~}') #changed ... 2005 -      string.gsub!(/<=amp>/,'{\\\&}') #changed ... 2005 -      #string.gsub!(/<=amp>/,'{\UseTextSymbol{OT1}{&}}') -      string.gsub!(/<=slash>/,'{/}') -      string.gsub!(/<=backslash>/,'{\textbackslash}') -      #string.gsub!(/<=asterisk>/,'*') -      #string.gsub!(/<=exclaim>/,'!') -      #string.gsub!(/<=asterisk>/,'{\ast}') -      #string.gsub!(/<=copymark>/,"^{\\copyright} ") # watch has been problematic -      #copymark='{\\begin{small}\\raisebox{1ex}{\\copyright}\\end{small}} ' -      string.gsub!(/<=copymark>\s*(.+)?\s+(<\\~\d+;\w(?:[0-6]:)?\d+;\w\d+><#@dp:#@dp>)/,"^\\copyright \\textnormal{\\1} \\2") # watch likely to be problematic -      string -    end -    def special_characters_curly(string) -      string.gsub!(/<=curlyopen>/,'\{') -      string.gsub!(/<=curlyclose>/,'\}') -      string -    end - - -    def special_characters_unsafe_1(string) #depreciated, make obsolete -      # some substitutions are sequence sensitive, rearrange with care. -      string.gsub!(/\\backslash (copyright|clearpage|newpage)/,"\\\\\\1")  #kludge bad solution, find out where tail is sent through specChar ! -      string -    end -    def special_characters                                                       #special characters - some substitutions are sequence sensitive, rearrange with care. -      string=@string -      case @tex2pdf -      when /pdf/ -        string=pdftex_special_characters_1(string) unless string.nil? -        string=special_characters_unsafe_1(string) unless string.nil? #pdftex_special_characters_unsafe_1(@string) -        string=pdftex_special_characters_2(string) unless string.nil? -        string=pdftex_special_characters_3(string) unless string.nil? -      when /xe/ -        string=xetex_special_characters_1(string) unless string.nil? -        string=special_characters_unsafe_1(string) unless string.nil? #xetex_special_characters_unsafe_1(@string) -        string=xetex_special_characters_2(string) unless string.nil? #issues with xetex -        string=xetex_special_characters_3(string) unless string.nil? -      end -      @string=string -    end -    def special_characters_safe                                                  #special characters - some substitutions are sequence sensitive, rearrange with care. -      string=@string -      case @tex2pdf -      when /pdf/ -        string=pdftex_special_characters_1(@string) unless string.nil? -        string=pdftex_special_characters_2(@string) unless string.nil? -        #special_characters_3(@string) -      when /xe/ -        string=xetex_special_characters_1(@string) unless string.nil? -        string=xetex_special_characters_2(@string) unless string.nil? # remove this to start with, causes issues -      end -      @string=string -    end -    def heading_major(para,lev) +    def heading_major(para,lev) #\emph{        title=@md.title        para.strip! if para        para.gsub!(/(?:\\begin\{bfseries\}|\\begin\{itshape\})(.+?)(?:\\end\{bfseries\}|\\end\{itshape\})/m,'\1')        cont_ln=para.dup -      cont_ln.gsub!(/#{@@tex_pattern_margin_number}/,'') -      cont_ln.gsub!(/#{lev}#{@@tilde}(?:\S+)?\s+/,'') +      cont_ln.gsub!(@@tex_pattern_margin_number,'') +      cont_ln.gsub!(/#{Mx[:lv_o]}#{lev}:\S*?#{Mx[:lv_c]}\s*/,'')        if para =~/\\[Ff]ootnote/ #and para =~/^[1-6]#{@@tilde}/ # removing footnotes from headings!          cont_ln.gsub!(/\s*\\footnote\[\d+\]\{%\n .+? \}\s*/,' ')          cont_ln.gsub!(/\s*\\Footnote[A]\{[*+]+\d*\}\{%\n .+? \}\s*/,' ')        end -      para.gsub!(/(#{@md.lev}.*)\n?$/m,"\\part*{\\1} +      para.gsub!(/(#{@md.lev}.*)\n?$/m, #apparently not used @md.lev does not exist +        "\\part*{\\1}  \\addcontentsline{toc}{section}{#{cont_ln}} -\\markboth{#{title}}\n") if (para !~/#{lev}#{@@tilde}/) -      para.gsub!(/^#{lev}#{@@tilde}\s*(.*)\n?$/m, +\\markboth{#{title}}\n") if (para !~/#{Mx[:lv_o]}#{lev}:/) +      para.gsub!(/^#{Mx[:lv_o]}#{lev}:\S*?#{Mx[:lv_c]}\s*(.*)\n?$/m,          "\\part*{\\1}  \\addcontentsline{toc}{section}{#{cont_ln}}  \\markboth{#{title}}\n") +para      end      def level1        heading_major(@string,1) @@ -807,14 +276,14 @@ WOK        @string.strip! if @string        @string.gsub!(/(?:\\begin\{bfseries\}|\\begin\{itshape\})(.+?)(?:\\end\{bfseries\}|\\end\{itshape\})/m,'\1')        cont_ln=@string.dup -      cont_ln.gsub!(/#{@@tex_pattern_margin_number}/,'') +      cont_ln.gsub!(@@tex_pattern_margin_number,'')        cont_ln.gsub!(/#{@@tex_backslash*2}/,"#{@@tex_backslash*4}") # added w42 -      cont_ln.gsub!(/4#{@@tilde}\S+\s+/,'') +      cont_ln.gsub!(/#{Mx[:lv_o]}4:\S+?#{Mx[:lv_c]}\s*/,'')        cont_ln.gsub!(/\\footnote\[\d+\]\{%.+?\\end\{scriptsize\}\s*\}/m,'') #arbitrary bugfix, revisit should not be necessary, eg. wta.1994 2004w22        cont_ln.gsub!(/\\Footnote[A]\{[*+]+\d*\}\{%.+?\\end\{scriptsize\}\s*\}/m,'') #arbitrary bugfix, revisit should not be necessary, eg. wta.1994 2004w22        title=@md.title        @string.gsub!(/#{@md.lv4}\s+(#{@md.lv4})/m,'\1') -      if @string =~/4#{@@tilde}endnotes|<:4-endnotes>/ +      if @string =~/#{Mx[:lv_o]}4:endnotes#{Mx[:lv_c]}|<:4-endnotes>/          # watch exclusion removes endnotes marker from pdf 2003w03          @string.gsub!(/.+/m,'')        end @@ -822,12 +291,12 @@ WOK          cont_ln.gsub!(/\s*\\footnote\[\d+\]\{%\n .+? \}\s*/,' ')          cont_ln.gsub!(/\s*\\Footnote[A]\{[*+]+\d*\}\{%\n .+? \}\s*/,' ')        end -      if @string !~/4#{@@tilde}/ +      if @string !~/#{Mx[:lv_o]}4:/          @string.gsub!(/(#{@md.lv4}.*)\n?$/m,"\\subsubsection*{\\1}  \\addcontentsline{toc}{subsection}{#{cont_ln}}  \\markright{#{title}}")        else -        @string.gsub!(/^\s*4#{@@tilde}\S+\s*(.*)?\n?$/m,"\\subsubsection*{\\1} +        @string.gsub!(/^\s*#{Mx[:lv_o]}4:\S+?#{Mx[:lv_c]}\s*(.*)?\n?$/m,"\\subsubsection*{\\1}  \\addcontentsline{toc}{subsection}{#{cont_ln}}  \\markright{#{title}}")        end @@ -838,8 +307,8 @@ WOK        @string.strip! if @string        @string.gsub!(/(?:\\begin\{bfseries\}|\\begin\{itshape\})(.+?)(?:\\end\{bfseries\}|\\end\{itshape\})/m,'\1')        cont_ln=@string.dup -      cont_ln.gsub!(/#{@@tex_pattern_margin_number}/,'') -      cont_ln.gsub!(/5#{@@tilde}\S*\s+/,'') +      cont_ln.gsub!(@@tex_pattern_margin_number,'') +      cont_ln.gsub!(/#{Mx[:lv_o]}5:\S*?#{Mx[:lv_c]}\s*/,'')        cont_ln.gsub!(/\\footnote\[\d+\]\{%.+?\\end\{scriptsize\}\s*\}/m,'') #arbitrary bugfix, revisit should not be necessary, eg. wta.1994 2004w22        cont_ln.gsub!(/\\Footnote[A]\{[*+]+\d*\}\{%.+?\\end\{scriptsize\}\s*\}/m,'') #arbitrary bugfix, revisit should not be necessary, eg. wta.1994 2004w22        cont_ln.gsub!(/\\\&/,' and ') #revisit: tmp bugfix 200507, substitutes & with 'and' in toc, needed e.g. for AT&T, see ffa @@ -848,12 +317,13 @@ WOK          cont_ln.gsub!(/\s*\\footnote\[\d+\]\{%\n .+? \}\s*/,' ')          cont_ln.gsub!(/\s*\\Footnote[A]\{[*+]+\d*\}\{%\n .+? \}\s*/,' ')        end -      if @string !~/5#{@@tilde}/ +      if @string !~/#{Mx[:lv_o]}5:/          @string.gsub!(/(#{@md.lv5}.*?)\n?$/m,"\\subsubsection*{\\1}  \\addcontentsline{toc}{subsubsection}{#{cont_ln} \\\\  }")        else -        @string.gsub!(/^\s*5#{@@tilde}\S*\s*(.*)?\n?$/m,"\\subsubsection*{\\1} +        @string.gsub!(/^\s*#{Mx[:lv_o]}5:\S*?#{Mx[:lv_c]}\s*(.*)?\n?$/m, +          "\\subsubsection*{\\1}  \\addcontentsline{toc}{subsubsection}{#{cont_ln} \\\\  }")        end @@ -864,8 +334,8 @@ WOK        @string.strip! if @string        @string.gsub!(/(?:\\begin\{bfseries\}|\\begin\{itshape\})(.+?)(?:\\end\{bfseries\}|\\end\{itshape\})/m,'\1')        cont_ln=@string.dup -      cont_ln.gsub!(/#{@@tex_pattern_margin_number}/,'') -      cont_ln.gsub!(/6#{@@tilde}\S*\s+/,'') +      cont_ln.gsub!(@@tex_pattern_margin_number,'') +      cont_ln.gsub!(/#{Mx[:lv_o]}6:\S*?#{Mx[:lv_c]}\s*/,'')        cont_ln.gsub!(/\\footnote\[\d+\]\{%.+?\\end\{scriptsize\}\s*\}/m,'') #arbitrary bugfix, revisit should not be necessary, eg. wta.1994 2004w22        cont_ln.gsub!(/\\Footnote[A]\{[*+]+\d*\}\{%.+?\\end\{scriptsize\}\s*\}/m,'') #arbitrary bugfix, revisit should not be necessary, eg. wta.1994 2004w22        @string.gsub!(/#{@md.lv6}\s+(#{@md.lv6})/m,'\1') @@ -874,8 +344,8 @@ WOK          cont_ln.gsub!(/\s*\\Footnote[A]\{[*+]+\d*\}\{%\n .+? \}\s*/,' ')        end        @string.gsub!(/(#{@md.lv6}.*)\n?$/m, -        "\\subsubsection*{\\1}") if (@string !~/6#{@@tilde}/) -      @string.gsub!(/^\s*6#{@@tilde}\S*\s*(.*)?\n?$/m, +        "\\subsubsection*{\\1}") if (@string !~/#{Mx[:lv_o]}6:/) +      @string.gsub!(/^\s*#{Mx[:lv_o]}6:\S*?#{Mx[:lv_c]}\s*(.*)?\n?$/m,          '\subsubsection*{\1}')        @string.gsub!(/#{@md.lv6}\s*(.marginpar)/m,'\1')        #end BUGWATCH @@ -892,7 +362,7 @@ WOK        when /8/; '70mm'        when /9/; '80mm'        end -      @string.gsub!(/<:i#{lev}>\s*(.*)/m, +      @string.gsub!(/#{Mx[:pa_o]}:i#{lev}#{Mx[:pa_c]}\s*(.*)/m,          "\\begin{ParagraphIndent}{#{indent}}\\1  \\end{ParagraphIndent}}")      end @@ -951,7 +421,6 @@ WOK        end        hsp="\n{\\color{mywhite} .}&~\n" # ~ character for hardspace        caption="{\\\\\\\ \n\\begin{scriptsize}#{hsp*3}#{c}\\end{scriptsize}&}" if c -      #caption="{\\\\\\\ \n\\begin{scriptsize}#{hsp*3}#{c[1]}\\end{scriptsize}&}" if c        image_source=if @md.fns =~/\.(?:ssm\.)?sst$/ \        and FileTest.file?("#{dir.path.image_source_local_tex}/#{image}")          dir.path.image_source_local_tex @@ -999,16 +468,16 @@ WOK                z[/(\d+)x\d*/,1]              else 200              end -            dm=case @md.papersize -            when /a4/;     @tx.a4 -            when /letter/; @tx.letter -            when /legal/;  @tx.legal -            when /b5/;     @tx.b5 -            when /a5/;     @tx.a5 -            else           @tx.a4 +            dm=case @ps # @md.papersize +            when /a4/;     @tx.a4.landscape.img_px +            when /letter/; @tx.letter.landscape.img_px +            when /legal/;  @tx.legal.landscape.img_px +            when /b5/;     @tx.b5.landscape.img_px +            when /a5/;     @tx.a5.landscape.img_px +            else           @tx.a4.landscape.img_px              end -            width=if width.to_i > dm.landscape.img_px -              dm.landscape.img_px +            width=if width.to_i > dm +              dm              else width              end              c=z[/``(.+?)''/m,1] @@ -1058,7 +527,54 @@ WOK      end      def http        wm=@string.dup.scan(/\\\{.+?\\\}(?:(?:https?|file|ftp):\S+|image)|\w+\s*|./m) -      @string=SiSU_TeX_Pdf::Format_text_object.new(@md,wm).http_word_mode #(orientation) +      @string=SiSU_TeX_Pdf::Format_text_object.new(@md,wm,@ps).http_word_mode #GET PAPER SIZE AND USE IT +    end +    def title +      @string=SiSU_TeX_Pdf::Special_characters.new(@md,@string).special_characters_safe +      if @string1 +        @string1=SiSU_TeX_Pdf::Special_characters.new(@md,@string1).special_characters_safe +        @string1.gsub!(/\$/,"\\$") +        "\n\\title{#@string#{@@tex_backslash*2} \\textbf{\\normalsize #@string1}\\normalsize}" +      else "\n\\title{#@string}" +      end +    end +    def title_landscape +      title +    end +    def title_portrait +      title +    end +    def para_num +      paranumber_display=if @md.markup.inspect =~/no_ocn/ \ +      or @md.mod.inspect =~/--no-ocn/ +        '' +      else "\\begin{tiny}~\\end{tiny}{\\marginpar{\\begin{tiny}#@string1\\end{tiny}}}" #ocn object citation numbering +      end +      if @string !~/^(?:#{Mx[:lv_o]}[1-6a-z-]:|#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]}|<:.+?>|#{@md.lv1}|#{@md.lv2}|#{@md.lv3}|#{@md.lv4}|#{@md.lv5}|#{@md.lv6})/ +        @string.gsub!(/^\s*(.+)/m,"#{paranumber_display}\\1\n") #watch - in 1-6 is suspect +      else +        if (@string =~/^(?:#{Mx[:lv_o]}[1-6a-z-]:|#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]})/) #watch - in 1-6 is suspect +          @string.gsub!(/^(#{Mx[:lv_o]}[1-6a-z-]:\S*?#{Mx[:lv_c]})\s*(.+)/m,"\\1 #{paranumber_display}\\2\n") #watch - in 1-6 is suspect +          #@string.gsub!(/^(#{Mx[:lv_o]}[1-6a-z-]:\S*?#{Mx[:lv_c]})\s*(.+)/m,"\\1 #{paranumber_display} \\begin{bfseries}\\2 \\end{bfseries}\n") #watch - in 1-6 is suspect +          #@string.gsub!(/^(#{Mx[:lv_o]}[1-6a-z-]:\S*?#{Mx[:lv_c]})\s*(.+)/m,"\\1 #{paranumber_display} \\emph{\\2}\n") #watch - in 1-6 is suspect +          @string.gsub!(/^(#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]})\s*(.+)/m,"\\1 #{paranumber_display}\\2\n") #WHAT? +          #@string.gsub!(/^(<:.+?>)\s*(.+)/m,"\\1 #{paranumber_display}\\2\n") #WHAT? +        else +          @string.gsub!(/((#{@md.lv1}|#{@md.lv2}|#{@md.lv3}|#{@md.lv4}|#{@md.lv5}|#{@md.lv6}).+)$/,"\\2 #{paranumber_display} \\1\n") +          #@string.gsub!(/((#{@md.lv1}|#{@md.lv2}|#{@md.lv3}|#{@md.lv4}|#{@md.lv5}|#{@md.lv6}).+)$/,"\\2 #{paranumber_display} \\begin{bfseries}\\1 \\end{bfseries}\n") +          #@string.gsub!(/((#{@md.lv1}|#{@md.lv2}|#{@md.lv3}|#{@md.lv4}|#{@md.lv5}|#{@md.lv6}).+)$/,"\\2 #{paranumber_display}\\emph{\\1}\n") +        end +      end +      @string +    end +  end +  class Format_head +    def initialize(md,ps,layout=nil,string1=nil) +      @md,@ps,@layout,@string1=md,ps,layout,string1 +      @tx=SiSU_Env::Get_init.instance.tex +      @url_brace=SiSU_Viz::Skin.new.url_decoration +      @tex2pdf=@@tex3pdf ||=SiSU_Env::System_call.new.tex2pdf_engine +      @ps=@string if @string=~/(?:a4|letter|legal|book|a5|b5)/i      end      def language        @lang=if @md.dc_language[:code] @@ -1095,21 +611,6 @@ WOK        else         'english'        end      end -    def title -      @string=Format_text_object.new(@md,@string).special_characters_safe -      if @string1 -        @string1=Format_text_object.new(@md,@string1).special_characters_safe -        @string1.gsub!(/\$/,"\\$") -        "\n\\title{#@string#{@@tex_backslash*2} \\textbf{\\normalsize #@string1}\\normalsize}" -      else "\n\\title{#@string}" -      end -    end -    def title_landscape -      title -    end -    def title_portrait -      title -    end      def tex_head_lang #babel 18n        language        #@md.dc_language[:name] @@ -1193,14 +694,14 @@ WOK      end      def tex_head_paper_dimensions        d={} -      case @string +      case @layout        when /portrait/          #textheight,textwidth=@tx.a4.portrait.h,@tx.a4.portrait.w          d[:papertype],d[:fontsize]='a4paper','11pt'          d[:oddsidemargin],d[:evensidemargin],d[:topmargin]='0mm','0mm','-12pt'          d[:headheight],d[:headsep],d[:columnsep]='12pt','35pt',''          d[:marginparsep],d[:marginparwidth]='4mm','8mm' -        case @md.papersize +        case @ps #@md.papersize          when /a4/i           #European default, SiSU default            d[:papertype],d[:fontsize]='a4paper','12pt'            d[:textheight],d[:textwidth]=@tx.a4.portrait.h,@tx.a4.portrait.w @@ -1231,7 +732,7 @@ WOK          d[:oddsidemargin],d[:evensidemargin],d[:topmargin]='-8mm','-8mm','-18mm'          d[:headheight],d[:headsep],d[:columnsep]='12pt','20pt','40pt'          d[:marginparsep],d[:marginparwidth]='4mm','8mm' -        case @md.papersize +        case @ps #@md.papersize          when /a4/i                            #European default, SiSU default            d[:papertype],d[:fontsize]='a4paper','12pt'            d[:textheight],d[:textwidth]=@tx.a4.landscape.h,@tx.a4.landscape.w @@ -1245,7 +746,7 @@ WOK            d[:papertype],d[:fontsize],d[:columnsep]='b5paper','11pt','35pt'            d[:textheight],d[:textwidth]=@tx.b5.landscape.h,@tx.b5.landscape.w          when /a5/i -          d[:papertype],d[:fontsize],d[:columnsep]='a5paper','10pt','38pt' +          d[:papertype],d[:fontsize],d[:columnsep]='a5paper','10pt','32pt'            d[:textheight],d[:textwidth]=@tx.a5.landscape.h,@tx.a5.landscape.w          else                            #default currently A4            d[:papertype],d[:fontsize]='a4paper','12pt' @@ -1255,8 +756,7 @@ WOK        d      end      def tex_head_paper -      d={} -      case @string +      case @layout        when /portrait/          tex_head_paper_portrait(tex_head_paper_dimensions)        when /landscape/ @@ -1264,7 +764,7 @@ WOK        end      end      def tex_head_pdftex_dvi -      color=case @string +      color=case @layout        when /portrait/        <<WOK    colorlinks=true, @@ -1280,7 +780,7 @@ WOK    linkcolor=myred,    % \\href{...} and \\pageref{...}  WOK        end -      if @string =~/portrait|landscape/ +      if @layout =~/portrait|landscape/        <<WOK  \\usepackage{url}  \\usepackage{alltt} @@ -1388,69 +888,606 @@ WOK  \\usepackage{fancyhdr}  \\lhead{}  \\renewcommand{\\part}{\\\@startsection -{part}% -{1}% -{-2mm}% -{-\\baselineskip}% -{0.5\\baselineskip}% -{\\bfseries\\large\\scshape}}% +  {part}{1}{-2mm}% +  {-\\baselineskip}{0.5\\baselineskip}% +  {\\bfseries\\large\\upshape\\raggedright}}  \\renewcommand{\\section}{\\\@startsection -{section}% -{2}% -{-2mm}% -{-\\baselineskip}% -{0.5\\baselineskip}% -{\\bfseries\\Large\\upshape}}% +  {section}{2}{-2mm}% +  {-\\baselineskip}{0.5\\baselineskip}% +  {\\bfseries\\large\\upshape\\raggedright}}  \\renewcommand{\\subsection}{\\\@startsection -{subsection}% -{3}% -{-2mm}% -{-\\baselineskip}% -{0.5\\baselineskip}% -{\\bfseries\\large\\upshape}}% +  {subsection}{3}{-2mm}% +  {-\\baselineskip}{0.5\\baselineskip}% +  {\\bfseries\\large\\upshape\\raggedright}}  \\renewcommand{\\subsubsection}{\\\@startsection -{subsubsection}% -{4}% -{-2mm}% -{-\\baselineskip}% -{0.5\\baselineskip}% -{\\bfseries\\normalsize\\upshape}}% +  {subsubsection}{4}{-2mm}% +  {-\\baselineskip}{0.5\\baselineskip}% +  {\\normalfont\\normalsize\\bfseries\\raggedright}}  \\renewcommand{\\paragraph}{\\\@startsection -{paragraph}% -{5}% -{-2mm}% -{-\\baselineskip}% -{0.5\\baselineskip}% -{\\normalfont\\normalsize\\itshape}}% +  {paragraph}{5}{-2mm}% +  {-\\baselineskip}{0.5\\baselineskip}% +  {\\normalfont\\normalsize\\itshape\\raggedright}}  \\renewcommand{\\subparagraph}{\\\@startsection -{subparagraph}% -{6}% -{-2mm}% -{-\\baselineskip}% -{0.5\\baselineskip}% -{\\normalfont\\normalsize\\itshape}}% +  {subparagraph}%{6}%{-2mm}% +  {-\\baselineskip}{0.5\\baselineskip}% +  {\\normalfont\\normalsize\\itshape\\raggedright}} +% \\makeatother  \\selectlanguage{#{language}}  WOK      end      def a4generic      end -    def para_num -      paranumber_display=if @md.markup.inspect =~/no_ocn/ \ -      or @md.mod.inspect =~/--no-ocn/ -        '' -      else "\\begin{tiny}~\\end{tiny}{\\marginpar{\\begin{tiny}#@string1\\end{tiny}}}" #ocn object citation numbering +  end +  class Special_characters +    @@flag_code=false +    @@tex_backslash="\\\\" +    def initialize(md,string) +      @md,@string=md,string +      @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern +      #@tx=SiSU_Env::Get_init.instance.tex +      @url_brace=SiSU_Viz::Skin.new.url_decoration +      @tex2pdf=@@tex3pdf ||=SiSU_Env::System_call.new.tex2pdf_engine +    end +    def pdftex_special_characters_1(string)             # ~ ^ $ & % _ { }  #LaTeX special characters - KEEP list +      #p @@utf_8.list +      #@string=Iconv.conv('ISO-8859-1', 'UTF-8', @string) +      word=string.scan(/#{Mx[:mk_o]}\S+?#{Mx[:mk_c]}|\S+|\n/) #unless line =~/^(?:0~\S|%+\s)/ +      para_array=[] +      string=if word +        word.each do |w| # _ - / # | : ! ^ ~ +          unless string =~/^(?:#{Rx[:meta]}|%+ |#{Mx[:gr_o]}Th?#{Mx[:tc_p]} )/um +            unless w=~/^#{Mx[:lv_o]}[1-6]:|~\{|\}~|~\[|\]~|^\^~\s|~\^|\*~\S+|~#|\{t~|#{Mx[:id_o]}~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}/ +              w.gsub!(/[\\]?~/,'<=tilde>') +              #if w !~/^(\s*<:image|\}:image\s)|/ +              #  w.gsub!(/_/,'\_') +              #end +            end +            w.gsub!(/#{Mx[:gl_o]}#(?:126|152)#{Mx[:gl_c]}/,'<=tilde>') #126 usual +            #w.gsub!(/&#(?:126|152);/,'<=tilde>') unless w=~/https?:\/\/\S+/ #126 usual +            w.gsub!(/\\?\||#{Mx[:gl_o]}#124#{Mx[:gl_c]}/,'<=pipe>') #unless w=~/<~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+>/ # | SiSU not really special sisu character but done, also LaTeX +          end +          para_array << w +        end +        string=para_array.join(' ') +        string=string.strip +        string +      else ''        end -      if @string !~/^([1-6a-z-]#{@@tilde}\S*|<:.+?>|#{@md.lv1}|#{@md.lv2}|#{@md.lv3}|#{@md.lv4}|#{@md.lv5}|#{@md.lv6})/ -        @string.gsub!(/^\s*(.+)/m,"#{paranumber_display}\\1\n") #watch - in 1-6 is suspect -      else -        if (@string =~/^(?:[1-6a-z-]#{@@tilde}\S*|<:.+?>)/) #watch - in 1-6 is suspect -          @string.gsub!(/^([1-6a-z-]#{@@tilde}\S*)\s*(.+)/m,"\\1 #{paranumber_display} \\2\n") #watch - in 1-6 is suspect -          @string.gsub!(/^(<:.+?>)\s*(.+)/m,"\\1 #{paranumber_display}\\2\n") -        else -          @string.gsub!(/((#{@md.lv1}|#{@md.lv2}|#{@md.lv3}|#{@md.lv4}|#{@md.lv5}|#{@md.lv6}).+)$/,"\\2 #{paranumber_display}\\1\n") +      string.gsub(/\s*#{Mx[:mk_o]}:name#\S+?#{Mx[:mk_c]}\s*/,' ') +      string.gsub!(/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;[umdv]\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}/,'') +      string.gsub!(/.+?<-#>/,'') +      string.gsub!(/#{Mx[:br_eof]}|#{Mx[:br_endnotes]}/,'') +      #problem sequence -> +      string.gsub!(/&(?:nbsp);/,'<=hardspace>')                                 # < SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#nbsp#{Mx[:gl_c]}/,'<=hardspace>')                                 # < SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}(?:#lt|#060)#{Mx[:gl_c]}/,'<=lt>')                                     # < SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}(?:#gt|#062)#{Mx[:gl_c]}/,'<=gt>')                                     # > SiSU special character also LaTeX +      #string.gsub!(/#{Mx[:gl_o]}(#[a-z]+|#[0-9]+)#{Mx[:gl_c]}/,'\1') #i don't think so +      string.gsub!(/#{Mx[:gl_o]}#123#{Mx[:gl_c]}/,'<=curlyopen>')                                     # { SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#125#{Mx[:gl_c]}/,'<=curlyclose>')                                    # } SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#(?:126|152)#{Mx[:gl_c]}/,'<=tilde>')                                 # ~ SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#035#{Mx[:gl_c]}/,'\#')                                               # # SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#033#{Mx[:gl_c]}/,'!')                                                # ! SiSU not really special sisu character but done, also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#042#{Mx[:gl_c]}/,'*')                                                # * should you wish to escape astrisk e.g. describing \*{bold}* +      string.gsub!(/#{Mx[:gl_o]}#045#{Mx[:gl_c]}/,'-')                                                # - SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#043#{Mx[:gl_c]}/,'+')                                                # + SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#044#{Mx[:gl_c]}/,',')                                                # + SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#038#{Mx[:gl_c]}/,'<=amp>') #unless @string=~/<:code>/                   # / SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#047#{Mx[:gl_c]}/,'<=slash>')                                         # / SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#092#{Mx[:gl_c]}/,'<=backslash>')                                     # \ SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#095#{Mx[:gl_c]}/,'<=underscore>')                                    # _ SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#124#{Mx[:gl_c]}/,'|')                                                # | SiSU not really special sisu character but done, also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#058#{Mx[:gl_c]}/,':')                                                # : SiSU not really special sisu character but done, also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#094#{Mx[:gl_c]}|\^/,'<=caret>')                                      # ^ SiSU not really special sisu character but done, also LaTeX +      string.gsub!(/\#/,'<=hash>') +      ##watch placement, problem sequence ^ +      string.gsub!(/<sup><font face=symbol>&atild;<\/font><\/sup>/,' ') +      string.gsub!(/#{Mx[:br_page]}/,'\newpage') +      string.gsub!(/#{Mx[:br_page_new]}/,'\clearpage') +      string.gsub!(/\\copy(right|mark)?/,'<=copymark>') # ok problem with superscript +      string +    end +    def pdftex_special_characters_2(string) +      string.gsub!(/#{Mx[:gl_o]}#156#{Mx[:gl_c]}/,'\oe ') +      string.gsub!(/\$/,'\$') +      string.gsub!(/\#/,'\#') +      string.gsub!(/\%/,'\%') +      string.gsub!(/\~/,'\~') #revist, should not be necessary to mark remaining tildes +      if string !~/^\s*<:image|\}:image\s/ +        string.gsub!(/_/,'\_') +      end +      string.gsub!(/\{/,'\{') +      #string.gsub!(/\}/,'\}') +      string.gsub!(/ /,'~') # ~ character for hardspace +      # sequence important must appear after removal of { and } +      string.gsub!(/&\S+?;/,'') #hmmm +      # sequence imortant place before removal of & +      if string=~/#{Mx[:gr_o]}code#{Mx[:gr_c]}/;        @@flag_code=true +      elsif string=~/#{Mx[:gr_o]}code-end#{Mx[:gr_c]}/; @@flag_code=false +      end +      if @@flag_code; string.gsub!(/&/,'{\\\&}') +      else string.gsub!(/(\s+&\s+)/,' and ') +      end +      string.gsub!(/§/u,'\S') #latex: space between next character not preserved? #string.gsub!(/§ /,'\S ') +      string.gsub!(/£/u,'\pounds') +      string.gsub!(/&\S+?;/,' ') +      string.gsub!(/<a href=".+?">/,' ') +      string.gsub!(/<\/a>/,' ') +      string.gsub!(/[^\}>_]((?:https?|file|ftp):\/\/\S+?)(<\/\S>)/,' \begin{scriptsize}\href{\1}{\1} \end{scriptsize}\2') #special case +      string.gsub!(/((?:^|\s)[}])((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'\1\begin{scriptsize}\\href{\2}{\2}\end{scriptsize}\3') #special case \{ e.g. \}http://url +      string.gsub!(/\B(?:\\_|\\)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'\begin{scriptsize}\\href{\1}{\1}\end{scriptsize}\2') #specially escaped url no decoration +      unless @@flag_code +        string.gsub!(/(^|#{Mx[:gl_c]}|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/,"\\1#{@url_brace.tex_open}\\begin{scriptsize}\\href{\\2}{\\2}\\end{scriptsize}#{@url_brace.tex_close}\\3") #url matching with decoration <url> positive lookahead, sequence issue with { linked }http://url cannot use \b at start +      else #code-block: angle brackets special characters, note _ already escaped +        string.gsub!(/\\_</,'{\UseTextSymbol{OML}{<}}') +        string.gsub!(/\\_>/,'{\UseTextSymbol{OML}{>}}') +      end +      string.gsub!(/<:ee>/,'') +      string.gsub!(/<!>/,' ') +      #proposed change, insert, but may be redundant +      string.gsub!(/ \/>#{Mx[:pa_o]}:i[12]#{Mx[:pa_c]}(.+?)(?:\}~|<br)/,' \begin{ParagraphIndent}{0.01\columnwidth}\1\end{ParagraphIndent} ') # footnote indents, problems if match exists in ordinary paragraphs? check! Work Area 200501 a bit tricky as must be able to match multiple times, and to clean remainder +      string.gsub!(/<(br|p)>|<\/\s*(br|p)>|<(br|p)\s*\/>/," #{@@tex_backslash*2} ") # Work Area +      string.gsub!(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'\begin{bfseries}\1 \end{bfseries}') +      #string.gsub!(/<em>(.+?)<\/em>/,'\begin{bfseries}\1 \end{bfseries}') +      #string.gsub!(/<(bold|strong)>(.+?)<\/(bold|strong)>/,'\begin{bfseries}\1 \end{bfseries}') +      string.gsub!(/<h\d+>(.+?)<\/h\d+>/,'\begin{bfseries}\1 \end{bfseries}') +      string.gsub!(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'\emph{\1}') +      #string.gsub!(/<italic>(.+?)<\/italic>/,'\emph{\1}') +      string.gsub!(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'\uline{\1}') # ulem +      string.gsub!(/#{Mx[:fa_cite_o]}(.+?)#{Mx[:fa_cite_c]}/,"``\\1''") # quote #CHECK +      string.gsub!(/#{Mx[:fa_insert_o]}(.+?)#{Mx[:fa_insert_c]}/,'\uline{\1}') # ulem +      string.gsub!(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'\sout{\1}') # ulem +      string.gsub!(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,"\$^{\\textrm{\\1}}\$") +      string.gsub!(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,"\$_{\\textrm{\\1}}\$") +      unless @@flag_code +        string.gsub!(/"(.+?)"/,'“\1”')  # quote marks / quotations open & close " need condition exclude for code +        string.gsub!(/\s+"/,' “')                                # open " +        string.gsub!(/^(#{Mx[:lv_o]}[1-6-]:\S*?#{Mx[:lv_c]}|<.+?>)?\s*"/,'\1“')  # open " +        string.gsub!(/"(\s|\.|,|:|;)/,'”\1')                     # close " +        string.gsub!(/"(#{Mx[:lv_o]}[1-6-]:\S*?#{Mx[:lv_c]}|<.+?>)?\s*$/,'”\1')  # close " +        string.gsub!(/"(\.|,)/,'”')                              # close " +        string.gsub!(/\s+'/,' `')                                # open ' +        string.gsub!(/^(#{Mx[:lv_o]}[1-6-]:\S*?#{Mx[:lv_c]}|<.+?>)?\s*'/,'\1`')  # open ' +      end +      string.gsub!(/^(#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]})?\s*#{Mx[:gl_bullet]}\s*/,'\1 \begin{math} \bullet \end{math}~~') #bullets - added 2004w17 watch \\_ +      string.gsub!(/(<font.*?>|<\/font>)/,'') +      string.gsub!(/\s*#{Mx[:fa_superscript_o]}(\S+?)#{Mx[:fa_superscript_c]}/,'^\1') +      #string.gsub!(/\s*(?:#{Mx[:br_line]}|#{Mx[:br_paragraph]}|\n)\*/,' \\\\ ') +      #string.gsub!(/(<sup>|<\/sup>)/,'') +      string +    end +    def pdftex_special_characters_3(string) +      string.gsub!(/<br(\s*[^\/][^>])/,'\1') # clean up, incredibly messy :-( footnote indents, problems if match exists in ordinary paragraphs? check! Work Area 200501 a bit tricky as must be able to match multiple times, and to clean remainder +      string.gsub!(/([^<][^b][^r]\s+)\/>/,'\1') # clean up, incredibly messy :-( footnote indents, problems if match exists in ordinary paragraphs? check! Work Area 200501 a bit tricky as must be able to match multiple times, and to clean remainder +      #problem sequence (another kludge) -> +      string.gsub!(/<=lt>/,'{\UseTextSymbol{OML}{<}}') +      string.gsub!(/<=gt>/,'{\UseTextSymbol{OML}{>}}') +      #string.gsub!(/<=lt>/,'\<') +      #string.gsub!(/<=gt>/,'\>') +      string.gsub!(/<=underscore>/,'\_') +      string.gsub!(/(\href\{http:\/\/\S+?)(?:(?:<=tilde>)(\S+))+\}/,'\1\~\2}') #tildes in urls \href treated differently from text +      string.gsub!(/<=tilde>/,'{\~~}') +      string.gsub!(/<=pipe>/,'{\textbar}') +      string.gsub!(/<=caret>/,'{\^{~}}') +      #string.gsub!(/<=caret>/,'\^{}') +      string.gsub!(/<=exclaim>/,'\Verbatim{!}') +      string.gsub!(/<=hash>/,'{\#}') +      #string.gsub!(/<=hash>/,'{\UseTextSymbol{OT1}{#}}') +      #string.gsub!(/<=slash>/,'{\slash}') +      string.gsub!(/<=hardspace>/,'{~}') #changed ... 2005 +      string.gsub!(/<=amp>/,'{\\\&}') #changed ... 2005 +      #string.gsub!(/<=amp>/,'{\UseTextSymbol{OT1}{&}}') +      string.gsub!(/<=slash>/,'{/}') +      string.gsub!(/<=backslash>/,'{\textbackslash}') +      #string.gsub!(/<=asterisk>/,'*') +      #string.gsub!(/<=exclaim>/,'!') +      #string.gsub!(/<=asterisk>/,'{\ast}') +      #string.gsub!(/<=copymark>/,"^{\\copyright} ") # watch has been problematic +      #copymark='{\\begin{small}\\raisebox{1ex}{\\copyright}\\end{small}} ' +      string.gsub!(/<=copymark>\s*(.+)?\s+(#{Mx[:id_o]}\\~\d+;\w(?:[0-6]:)?\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]})/,"^\\copyright \\textnormal{\\1} \\2") # watch likely to be problematic +      string +    end +    def xetex_special_characters_1(string)             # ~ ^ $ & % _ { }  #LaTeX special characters - KEEP list +      #p @@utf_8.list +      #string=Iconv.conv('ISO-8859-1', 'UTF-8', @string) +      word=string.scan(/\S+|\n/) #unless line =~/^(?:0~\S|%+\s)/ +      para_array=[] +      string=if word +        word.each do |w| # _ - / # | : ! ^ ~ +          unless string =~/^(?:#{Rx[:meta]}|%+ |#{Mx[:gr_o]}Th?#{Mx[:tc_p]} )/um +            unless w=~/^#{Mx[:lv_o]}[1-6]:|~\{|\}~|~\[|\]~|^\^~\s|~\^|\*~\S+|~#|\{t~|#{Mx[:id_o]}~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}/ +              w.gsub!(/[\\]?~/,'<=tilde>') +              #if w !~/^(\s*<:image|\}:image\s)/ +              #  w.gsub!(/_/,'\_') +              #end +            end +            w.gsub!(/#{Mx[:gl_o]}#(?:126|152)#{Mx[:gl_c]}/,'<=tilde>') #126 usual +            #w.gsub!(/&#(?:126|152);/,'<=tilde>') unless w=~/https?:\/\/\S+/ #126 usual +            w.gsub!(/\\?\||#{Mx[:gl_o]}#124#{Mx[:gl_c]}/,'<=pipe>') #unless w=~/<~\d+;(?:[ohmu]|[0-6]:)\d+;\w\d+>/ # | SiSU not really special sisu character but done, also LaTeX +          end +          para_array << w          end +        string=para_array.join(' ') +        string=string.strip +        string +      else ''        end -      @string +      string.gsub(/\s*#{Mx[:mk_o]}:name#\S+?#{Mx[:mk_c]}\s*/,' ') +      string.gsub!(/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;[umdv]\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}/,'') +      string.gsub!(/.+?<-#>/,'') +      string.gsub!(/#{Mx[:br_eof]}/,'') +      string.gsub!(/#{Mx[:br_endnotes]}/,'') +      #string.gsub!(/<ENDNOTES?>/,'') +      #problem sequence -> +      string.gsub!(/&(?:nbsp);/,'<=hardspace>')                                 # < SiSU special character also LaTeX +      string.gsub!(/&(?:lt|#060);/,'<=lt>')                                     # < SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#(?:gt|062)#{Mx[:gl_c]}/,'<=gt>')                                     # > SiSU special character also LaTeX +      #string.gsub!(/#{Mx[:gl_o]}(&#(?:[a-z]+|[0-9]+);)#{Mx[:gl_c]}/,'\1') +      string.gsub!(/#{Mx[:gl_o]}#123#{Mx[:gl_c]}/,'<=curlyopen>')                                     # { SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#125#{Mx[:gl_c]}/,'<=curlyclose>')                                    # } SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#(?:126|152)#{Mx[:gl_c]}/,'<=tilde>')                                 # ~ SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#035#{Mx[:gl_c]}/,'\#')                                               # # SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#033#{Mx[:gl_c]}/,'!')                                                # ! SiSU not really special sisu character but done, also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#042#{Mx[:gl_c]}/,'*')                                                # * should you wish to escape astrisk e.g. describing \*{bold}* +      string.gsub!(/#{Mx[:gl_o]}#045#{Mx[:gl_c]}/,'-')                                                # - SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#043#{Mx[:gl_c]}/,'+')                                                # + SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#044#{Mx[:gl_c]}/,',')                                                # + SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#038#{Mx[:gl_c]}/,'<=amp>') #unless @string=~/<:code>/                   # / SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#047#{Mx[:gl_c]}/,'<=slash>')                                         # / SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#092#{Mx[:gl_c]}/,'<=backslash>')                                     # \ SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#095#{Mx[:gl_c]}/,'<=underscore>')                                    # _ SiSU special character also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#124#{Mx[:gl_c]}/,'|')                                                # | SiSU not really special sisu character but done, also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#058#{Mx[:gl_c]}/,':')                                                # : SiSU not really special sisu character but done, also LaTeX +      string.gsub!(/#{Mx[:gl_o]}#094#{Mx[:gl_c]}|\^/,'<=caret>')                                      # ^ SiSU not really special sisu character but done, also LaTeX +      string.gsub!(/\#/,'<=hash>') +      ##watch placement, problem sequence ^ +      string.gsub!(/<sup><font face=symbol>&atild;<\/font><\/sup>/,' ') +      string.gsub!(/#{Mx[:br_page]}/,'\newpage') +      string.gsub!(/#{Mx[:br_page_new]}/,'\clearpage') +      string.gsub!(/\\copy(right|mark)?/,'<=copymark>') # ok problem with superscript +      string +    end +    def xetex_special_characters_2(string) +      string.gsub!(/#{Mx[:gl_o]}#156#{Mx[:gl_c]}/,'\oe ') +      string.gsub!(/\$/,'\$') +      string.gsub!(/\#/,'\#') +      string.gsub!(/\%/,'\%') +      string.gsub!(/\~/,'\~') #revist, should not be necessary to mark remaining tildes +      if string !~/^\s*<:image|\}:image\s/ +        string.gsub!(/_/,'\_') +      end +      string.gsub!(/\{/,'\{') +      string.gsub!(/\}/,'\}') +      string.gsub!(/ /,'~') # ~ character for hardspace +      # sequence important must appear after removal of { and } +      string.gsub!(/&\S+?;/,'') #hmmm +      # sequence imortant place before removal of & +      if string=~/#{Mx[:gr_o]}code#{Mx[:gr_c]}/;        @@flag_code=true +      elsif string=~/#{Mx[:gr_o]}code-end#{Mx[:gr_c]}/; @@flag_code=false +      end +      if @@flag_code; string.gsub!(/&/,'{\\\&}') +      else string.gsub!(/(\s+&\s+)/,' and ') +      end +      string.gsub!(/§/u,'\S') #latex: space between next character not preserved? #string.gsub!(/§ /,'\S ') +      string.gsub!(/£/u,'\pounds') +      string.gsub!(/&\S+?;/,' ') +      string.gsub!(/<a href=".+?">/,' ') +      string.gsub!(/<\/a>/,' ') +      string.gsub!(/[^\}>_]((?:https?|file|ftp):\/\/\S+?)(<\/\S>)/,' \begin{scriptsize}\href{\1}{\1} \end{scriptsize}\2') #special case +      string.gsub!(/((?:^|\s)[}])((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'\1\begin{scriptsize}\\href{\2}{\2}\end{scriptsize}\3') #special case \{ e.g. \}http://url +      string.gsub!(/\B(?:\\_|\\)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'\begin{scriptsize}\\href{\1}{\1}\end{scriptsize}\2') #specially escaped url no decoration +      unless @@flag_code +        string.gsub!(/(^|#{Mx[:gl_c]}|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/,"\\1#{@url_brace.tex_open}\\begin{scriptsize}\\href{\\2}{\\2}\\end{scriptsize}#{@url_brace.tex_close}\\3") #url matching with decoration <url> positive lookahead, sequence issue with { linked }http://url cannot use \b at start +      else #code-block: angle brackets special characters, note _ already escaped +        string.gsub!(/\\_</,'{\UseTextSymbol{OML}{<}}') +        string.gsub!(/\\_>/,'{\UseTextSymbol{OML}{>}}') +      end +      string.gsub!(/<:ee>/,'') +      string.gsub!(/<!>/,' ') +      #proposed change, insert, but may be redundant +      string.gsub!(/ \/>#{Mx[:pa_o]}:i[12]#{Mx[:pa_c]}(.+?)(?:\}~|<br)/,' \begin{ParagraphIndent}{0.01\columnwidth}\1\end{ParagraphIndent} ') # footnote indents, problems if match exists in ordinary paragraphs? check! Work Area 200501 a bit tricky as must be able to match multiple times, and to clean remainder +      string.gsub!(/<(br|p)>|<\/\s*(br|p)>|<(br|p)\s*\/>/," #{@@tex_backslash*2} ") # Work Area +      string.gsub!(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'\begin{bfseries}\1 \end{bfseries}') +      #string.gsub!(/<em>(.+?)<\/em>/,'\begin{bfseries}\1 \end{bfseries}') +      #string.gsub!(/<(bold|strong)>(.+?)<\/(bold|strong)>/,'\begin{bfseries}\1 \end{bfseries}') +      string.gsub!(/<h\d+>(.+?)<\/h\d+>/,'\begin{bfseries}\1 \end{bfseries}') +      string.gsub!(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'\emph{\1}') +      #string.gsub!(/<italic>(.+?)<\/italic>/,'\emph{\1}') +      string.gsub!(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'\uline{\1}') # ulem +      string.gsub!(/#{Mx[:fa_cite_o]}(.+?)#{Mx[:fa_cite_c]}/,"``\\1''") # quote #CHECK +      string.gsub!(/#{Mx[:fa_insert_o]}(.+?)#{Mx[:fa_insert_c]}/,'\uline{\1}') # ulem +      string.gsub!(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'\sout{\1}') # ulem +      string.gsub!(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,"\$^{\\textrm{\\1}}\$") +      string.gsub!(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,"\$_{\\textrm{\\1}}\$") +      unless @@flag_code +        string.gsub!(/"(.+?)"/,'“\1”')  # quote marks / quotations open & close " need condition exclude for code +        string.gsub!(/\s+"/,' “')                                # open " +        string.gsub!(/^(#{Mx[:lv_o]}[1-6-]:\S*?#{Mx[:lv_c]}|<.+?>)?\s*"/,'\1“')  # open " +        string.gsub!(/"(\s|\.|,|:|;)/,'”\1')                     # close " +        string.gsub!(/"(#{Mx[:lv_o]}[1-6-]:\S*?#{Mx[:lv_c]}|<.+?>)?\s*$/,'”\1')  # close " +        string.gsub!(/"(\.|,)/,'”')                              # close " +        string.gsub!(/\s+'/,' `')                                # open ' +        string.gsub!(/^(#{Mx[:lv_o]}[1-6-]:\S*?#{Mx[:lv_c]}|<.+?>)?\s*'/,'\1`')  # open ' +      end +      string.gsub!(/^\s*#{Mx[:gl_bullet]}\s*/,'\begin{math} \bullet \end{math}~~') +      string.gsub!(/^(#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]})?\s*#{Mx[:gl_bullet]}\s*/,'\1 \begin{math} \bullet \end{math}~~') +      #string.gsub!(/^\s*#{Mx[:gl_bullet]}\s*/,'● ~~') +      #string.gsub!(/^(#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]})?\s*#{Mx[:gl_bullet]}\s*/,'\1 ● ~~') +      ##string.gsub!(/^(#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]})?\s*\\_\*\s*/,'\1 ● ~~') +      ##string.gsub!(/^\\_\*\s*/,'● ~~') +      string.gsub!(/(<font.*?>|<\/font>)/,'') +      string.gsub!(/\s*#{Mx[:fa_superscript_o]}(\S+?)#{Mx[:fa_superscript_c]}/,'^\1') +      #string.gsub!(/\s*(?:#{Mx[:br_line]}|#{Mx[:br_paragraph]}|\n)\*/,' \\\\ ') +      #string.gsub!(/(<sup>|<\/sup>)/,'') +      string +    end +    def xetex_special_characters_3(string) +      string.gsub!(/<br(\s*[^\/][^>])/,'\1') # clean up, incredibly messy :-( footnote indents, problems if match exists in ordinary paragraphs? check! Work Area 200501 a bit tricky as must be able to match multiple times, and to clean remainder +      string.gsub!(/([^<][^b][^r]\s+)\/>/,'\1') # clean up, incredibly messy :-( footnote indents, problems if match exists in ordinary paragraphs? check! Work Area 200501 a bit tricky as must be able to match multiple times, and to clean remainder +      #problem sequence (another kludge) -> +      string.gsub!(/<=lt>/,'{\UseTextSymbol{OML}{<}}') +      string.gsub!(/<=gt>/,'{\UseTextSymbol{OML}{>}}') +      #string.gsub!(/<=lt>/,'\<') +      #string.gsub!(/<=gt>/,'\>') +      string.gsub!(/<=underscore>/,'\_') +      string.gsub!(/(\href\{http:\/\/\S+?)(?:(?:<=tilde>)(\S+))+\}/,'\1\~\2}') #tildes in urls \href treated differently from text +      string.gsub!(/<=tilde>/,'{\~~}') +      string.gsub!(/<=pipe>/,'{\textbar}') +      string.gsub!(/<=caret>/,'{\^{~}}') +      #string.gsub!(/<=caret>/,'\^{}') +      string.gsub!(/<=exclaim>/,'\Verbatim{!}') +      string.gsub!(/<=hash>/,'{\#}') +      #string.gsub!(/<=hash>/,'{\UseTextSymbol{OT1}{#}}') +      #string.gsub!(/<=slash>/,'{\slash}') +      string.gsub!(/<=hardspace>/,'{~}') #changed ... 2005 +      string.gsub!(/<=amp>/,'{\\\&}') #changed ... 2005 +      #string.gsub!(/<=amp>/,'{\UseTextSymbol{OT1}{&}}') +      string.gsub!(/<=slash>/,'{/}') +      string.gsub!(/<=backslash>/,'{\textbackslash}') +      #string.gsub!(/<=asterisk>/,'*') +      #string.gsub!(/<=exclaim>/,'!') +      #string.gsub!(/<=asterisk>/,'{\ast}') +      #string.gsub!(/<=copymark>/,"^{\\copyright} ") # watch has been problematic +      #copymark='{\\begin{small}\\raisebox{1ex}{\\copyright}\\end{small}} ' +      string.gsub!(/<=copymark>\s*(.+)?\s+(#{Mx[:id_o]}\\~\d+;\w(?:[0-6]:)?\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]})/,"^\\copyright \\textnormal{\\1} \\2") # watch likely to be problematic +      string +    end +    def special_characters_curly(string) +      string.gsub!(/<=curlyopen>/,'\{') +      string.gsub!(/<=curlyclose>/,'\}') +      string +    end +    def special_characters_unsafe_1(string) #depreciated, make obsolete +      # some substitutions are sequence sensitive, rearrange with care. +      string.gsub!(/\\backslash (copyright|clearpage|newpage)/,"\\\\\\1")  #kludge bad solution, find out where tail is sent through specChar ! +      string +    end +    def special_characters                                                       #special characters - some substitutions are sequence sensitive, rearrange with care. +      string=@string +      case @tex2pdf +      when /pdf/ +        string=pdftex_special_characters_1(string) unless string.nil? +        string=special_characters_unsafe_1(string) unless string.nil? #pdftex_special_characters_unsafe_1(@string) +        string=pdftex_special_characters_2(string) unless string.nil? +        string=pdftex_special_characters_3(string) unless string.nil? +      when /xe/ +        string=xetex_special_characters_1(string) unless string.nil? +        string=special_characters_unsafe_1(string) unless string.nil? #xetex_special_characters_unsafe_1(@string) +        string=xetex_special_characters_2(string) unless string.nil? #issues with xetex +        string=xetex_special_characters_3(string) unless string.nil? +      end +      @string=string +    end +    def special_characters_safe                                                  #special characters - some substitutions are sequence sensitive, rearrange with care. +      string=@string +      case @tex2pdf +      when /pdf/ +        string=pdftex_special_characters_1(@string) unless string.nil? +        string=pdftex_special_characters_2(@string) unless string.nil? +        #special_characters_3(@string) +      when /xe/ +        string=xetex_special_characters_1(@string) unless string.nil? +        string=xetex_special_characters_2(@string) unless string.nil? # remove this to start with, causes issues +      end +      @string=string +    end +  end +  class Use_TeX +    attr_accessor :url,:txt,:date +    def initialize(md) +      @md=md +      @vz=SiSU_Env::Get_init.instance.skin +      @date=SiSU_Env::Info_date.new # #{@date.year} +      @copymark='{\\begin{footnotesize}\\raisebox{1ex}{\\copyright}\\end{footnotesize}}' +      @url_brace=SiSU_Viz::Skin.new.url_decoration +    end +    def skip +      "\n\\vspace*{\\smallskipamount} \n" +    end +    def paraskip_normal +      '\setlength{\parskip}{1ex plus0.5ex minus0.2ex}' +    end +    def paraskip_small +      '\setlength{\parskip}{0.5ex plus0.2ex minus0.1ex}' +    end +    def skip_small +      #"\\smallskip{}" +    end +    def skip_small_vspace +      "\n\\vspace*{\\smallskipamount} \n" +    end +    def skip_small_footnote +      #"\n\\smallskip{}\n" +    end +    def skip_medium +      "\n\\medskip{}\n\n" +    end +    def skip_dummy +      "\n" +    end +    def header +      "\\lhead[ ]{ }\n" + +      "\\chead[ \\fancyplain{} \\bfseries \\footnotesize  \\leftmark ]{ \\fancyplain{} \\bfseries \\footnotesize \\rightmark }\n" + +      "\\rhead[ ]{ }\n" +    end +    def footer +      base_prog_txt=if @md.base_program +        case @md.base_program +        when /kdissert/i; " \\\\ \\href{http://freehackers.org/~tnagy/kdissert/}{Kdissert}" +        else '' +        end +      else '' +      end +      "\\lfoot[\\textrm{\\thepage}]{\\tiny \\href{#{@vz.url_sisu}}{#{@vz.txt_signature}}#{base_prog_txt}}\n" + +      "\\cfoot[\\href{#{@vz.url_home}}{#{@vz.url_txt}}]{\\href{#{@vz.url_home}}{#{@vz.url_txt}}}\n" + +      "\\rfoot[\\tiny \\href{#{@vz.url_sisu}}{#{@vz.txt_signature}}]{\\textrm{\\thepage}}\n" +    end +    def site +      "\\href{#{@vz.url_home}}{#{@vz.url_txt}}" +    end +    def sitename                                   #owners site, eg freeculture, free.for.all, gutenberg etc. +      "\\href{#{@vz.url_home}}{#{@vz.txt_home}}" +    end +    def owner_chapter +      "Contact Details for Original Promulgating Authority" +    end +    #BOOK standard dimensions - 229x156 +    def newpage(orientation) +      case orientation +      when /landscape/ # using longtable latex package +<<WOK +\\clearpage +WOK +      when /portrait/ +<<WOK +\\newpage +WOK +      end +    end +    def sisu_rights +      v=SiSU_Env::Info_version.new.get_version +      base_prog_txt=if @md.base_program +        case @md.base_program +        when /kdissert/i; "\n\\\\ This document prepared using \\href{http://freehackers.org/~tnagy/kdissert/}{Kdissert \\ http://freehackers.org/~tnagy/kdissert/ } \\\\ Kdissert is Document Mapping software by Thomas Nagy" +        else '' +        end +      else '' +      end +<<WOK +\\\\ ~ +{\\begin{footnotesize}#{base_prog_txt} +\\\\ Generated by \\href{http://www.jus.uio.no/sisu}{SiSU} \\begin{tiny}[ #{v[:project]} #{v[:version]} of #{v[:date_stamp]} ]\\end{tiny} \\href{http://www.jus.uio.no/sisu}{www.jus.uio.no/sisu} +\\\\ Copyright #@copymark 1997, current #{@date.year_static} Ralph Amissah, All Rights Reserved. +\\\\ SiSU is software for document structuring, publishing and search (with object citation numbering), \\href{http://www.sisudoc.org}{www.sisudoc.org} +\\\\ SiSU is released under \\href{http://www.fsf.org/licenses/gpl.html}{GPL 3 } or later, #{@url_brace.tex_open}\\href{http://www.fsf.org/licenses/gpl.html}{http://www.fsf.org/licenses/gpl.html}#{@url_brace.tex_close}. +{\\end{footnotesize} +\\\\ +WOK +    end +    def doc_sc_info_footnote_full +<<WOK +\\footnote{%\nGenerated by \\href{http://www.jus.uio.no/sisu}{SiSU \\ www.jus.uio.no/sisu }\\ \\newline \\scriptsize{Document version information: \\emph{sourcefile} \\uline{#{@md.fnstex}}; \\emph{version} \\uline{#{@md.sc_number}}; \\emph{date} \\uline{#{@md.sc_date}}; \\emph{time} \\uline{#{@md.sc_time}}}} +WOK +    end +    def doc_sc_info_footnote_brief +      " \\footnote{%\nGenerated by \\href{http://www.jus.uio.no/sisu}{SiSU} \\ \\href{http://www.jus.uio.no/sisu}{www.jus.uio.no/sisu} \\newline \\href{http://www.sisudoc.org}{www.sisudoc.org} \\\n}" +    end +    def doc_sc_info +      v=SiSU_Env::Info_version.new.get_version +<<WOK +\\\\ +{\\begin{footnotesize} +Document version information: \\\\ +\\emph{sourcefile} \\uline{#{@md.fnstex}}; \\emph{version} \\uline{#{@md.sc_number}}; \\emph{date} \\uline{#{@md.sc_date}}; \\emph{time} \\uline{#{@md.sc_time}} \\\\ +Generated by \\href{http://www.jus.uio.no/sisu}{SiSU www.jus.uio.no/sisu }\\- version information: \\\\ +\\uline{ #{v[:project]} #{v[:version]} of #{v[:date_stamp]}} +\\end{footnotesize}}& +WOK +    end +    def doc_no_sc_info +      v=SiSU_Env::Info_version.new.get_version +<<WOK +\\\\ +{\\begin{small} +Document information: \\\\ +\\emph{sourcefile} \\uline{#{@md.fnstex}} \\\\ +Generated by \\href{http://www.jus.uio.no/sisu}{SiSU www.jus.uio.no/sisu } \\\\ version information: \\ +\\uline{ #{v[:project]} #{v[:version]} of #{v[:date_stamp]}} + +\\end{small}}& +WOK +    end +    def manifest_info +      url=@md.fnb.gsub(/(?:\\)*([$&~%_#}{^])/,'\\\\\1') +      fn=@md.fn[:manifest].gsub(/(?:\\)*([$&~%_#}{^])/,'\\\\\1') +<<WOK +{\\begin{footnotesize} +\\\\ For alternative output formats of this document check: +\\\\ #{@url_brace.tex_open}\\begin{scriptsize}\\href{#{@vz.url_root_http}/#{url}/#{fn}}{#{@vz.url_root_http}/#{url}/#{fn}}\\end{scriptsize}#{@url_brace.tex_close} +\\end{footnotesize}}& +WOK +    end +    def endnotes #not used should be inserted before MetaData section which preceeds doc_tail, but is "part of document" +<<WOK +\\subsection*{Endnotes} +\\addcontentsline{toc}{section}{Endnotes} +\\ +\\listofendnotes +WOK +    end +    def doc_tail +      dir=SiSU_Env::Info_env.new(@md.fns) +      base_html="#{dir.url.root}/#{@md.fnb}" +      v=SiSU_Env::Info_version.new.get_version +      sisu_ico=if FileTest.file?("#{dir.path.image_source_tex}/sisu.png") +        "\\includegraphics*[width=60pt]{#{dir.path.image_source_tex}/sisu.png}" +      else +        tell=SiSU_Screen::Ansi.new(@md.cmd,'WARNING - image directory or image(s) missing:', %{"#{dir.path.image_source_tex}"} ) +        tell.warn unless @md.cmd =~/q/ +        " SiSU " +      end +      url=@md.fnb.gsub(/(?:\\)*([$&~%_#}{^])/,'\\\\\1') +<<WOK +\\subsection*{Information on this document copy and an unofficial List of Some web related information and sources} +\\addcontentsline{toc}{section}{Information on this document copy and an unofficial List of Some web related information and sources} +\\\\ +\"Support Open Standards and Software Libre for the Information Technology Infrastructure\" RA\\subsubsection*{Information on this document copy #{site}} +\\addcontentsline{toc}{subsection}{Information on this document copy} +{\\begin{footnotesize} +\\\\ Generated by \\href{http://www.jus.uio.no/sisu/}{SiSU} found at \\href{http://www.jus.uio.no/sisu/}{www.jus.uio.no/sisu} \\begin{tiny}[ #{v[:project]} #{v[:version]} #{v[:date_stamp]} ]\\end{tiny}  \\href{http://www.sisudoc.org}{www.sisudoc.org}. SiSU is software for document structuring, publishing and search (using SiSU: object citation numbering, markup, meta-markup, and system) Copyright #@copymark 1997, current #{@date.year_static} Ralph Amissah, All Rights Reserved. +\\\\ SiSU is released under \\href{http://www.fsf.org/licenses/gpl.html}{GPL 3 } or later (\\href{http://www.fsf.org/licenses/gpl.html}{www.fsf.org/licenses/gpl.html}). {\\end{footnotesize} +{\\begin{small} +\\\\ W3 since October 3 1993 \\href{http://www.jus.uio.no/sisu/}{#{sisu_ico}}SiSU 1997, current #{@date.year_static}. \\\\ #{sitename} presentations at \\begin{bfseries}#{site}\\end{bfseries} \\\\ \\\\ #{@md.title} \\textbf{pdf} versions can be found at:  \\\\ +{\\end{small} +\\begin{scriptsize}\\href{#{@vz.url_root_http}/#{url}/#{@md.fn[:pdf_p]}}{#{@vz.url_root_http}/#{url}/#{@md.fn[:pdf_p]}}\\end{scriptsize}  \\\\ +\\begin{scriptsize}\\href{#{@vz.url_root_http}/#{url}/#{@md.fn[:pdf_l]}}{#{@vz.url_root_http}/#{url}/#{@md.fn[:pdf_l]}}\\end{scriptsize}  \\\\ +\\\\\n#{@md.title} \\textbf{html} versions may be found at: \\\\ +\\begin{scriptsize}\\href{#{@vz.url_root_http}/#{url}/#{@md.fn[:toc]}}{#{@vz.url_root_http}/#{url}/#{@md.fn[:toc]}}\\end{scriptsize} or \\\\ +\\begin{scriptsize}\\href{#{@vz.url_root_http}/#{url}/#{@md.fn[:doc]}}{#{@vz.url_root_http}/#{url}/#{@md.fn[:doc]}}\\end{scriptsize} +\\\\ +\\\\ +\\href{#{@vz.url_root_http}/#{url}/#{@md.fn[:manifest]}}{SiSU Manifest} of document output and metadata may be found at: \\\\ +\\begin{scriptsize}\\href{#{@vz.url_root_http}/#{url}/#{@md.fn[:manifest]}}{#{@vz.url_root_http}/#{url}/#{@md.fnl[:pre]}sisu\\_manifest#{@md.fnl[:mid]}.html#{@md.fnl[:post]}}\\end{scriptsize} +\\\\ +\\\\ + #{sitename} found at: \\begin{bfseries}#{site}\\end{bfseries}\\subsubsection*{Links that may be of interest at #{@vz.txt_home} and elsewhere:} +\\addcontentsline{toc}{subsection}{Links that may be of interest} +WOK +    end +    def mail_tail #not retested, the old mail_tail is commented out and appended to this program +      dir=SiSU_Env::Info_env.new(@md.fns) +<<WOK +\\subsection*{Mail sender details} +\\addcontentsline{toc}{subsection}{Mail sender details} +\\\\ +Mail from: ralph@amissah.com\\\\ +44 20 8789 3452\\\\ +44 77 9669 4448 +\\\\ + \"Support Open Standards and Open Sources for the Information Technology Infrastructure\" RA +\\subsubsection*{Information on this document copy #{site}\\copyright} +Presentations' look and feel generated by \\href{http://www.jus.uio.no/sisu/}{SiSU Scribe} \\href{http://www.jus.uio.no/sisu/}{http://www.jus.uio.no/sisu/} programmed in Ruby on Debian/Gnu/Linux by Copyright \\copyright Ralph Amissah, W3 since October 3 1993 \\href{http://www.jus.uio.no/sisu/}{\\includegraphics*[width=35pt]{#{dir.path.image_source_tex}/sisu.png}}for #{sitename}. SiSU Scribe (sisu information structuring unit) produces Electronic Documents, i.e. it generates structured output for use in a number of file formats, including the pdf file produced here. +WOK      end    end  end diff --git a/lib/sisu/v0/urls.rb b/lib/sisu/v0/urls.rb index 794270f6..ad017bc5 100644 --- a/lib/sisu/v0/urls.rb +++ b/lib/sisu/v0/urls.rb @@ -273,6 +273,8 @@ module SiSU_urls            SiSU_Screen::Ansi.new(@opt.cmd,"-#{x}","#@browser #@webserv_url/sitemap/#{y}")          when /^I/            SiSU_Screen::Ansi.new(@opt.cmd,"-#{x}","cd #{@path.path.texinfo}; pinfo ./#@fnb.#{y}; cd -") +        when /^i/ +          SiSU_Screen::Ansi.new(@opt.cmd,"-#{x}","#@manpage_gen #{@path.path.manpage}/#@fnb.1 |most")          end          tellx.result if tellx          tell.result if tell diff --git a/lib/sisu/v0/wikispeak.rb b/lib/sisu/v0/wikispeak.rb index 8ac3b351..967387d9 100644 --- a/lib/sisu/v0/wikispeak.rb +++ b/lib/sisu/v0/wikispeak.rb @@ -110,25 +110,25 @@ module SiSU_Wikispeak        end        def lev_segname_para_ocn          @text=nil -        if @para =~/^(\d~|<:.+?>).+?<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ -          if /^(([1-6])~(\S+))\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) +        if @para =~/^(\d~|<:.+?>).+?#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ +          if /^(([1-6])~(\S+))\s+(\S.+?)#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m.match(@para)              @format,@lev,segname,@text,@ocn=$1,$2,$3,$4,$5 -          elsif  /^(([1-6])~)\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) +          elsif  /^(([1-6])~)\s+(\S.+?)#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m.match(@para)              @format,@lev,@text,@ocn=$1,$2,$3,$4 -          elsif /<:(.+?)>\s*(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) +          elsif /<:(.+?)>\s*(\S.+?)#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m.match(@para)              @format,@text,@ocn=$1,$2,$3 -          elsif /^(([1-6])~(\S+))\s+(\S.+?)<~(\d+);(?:\w|[0-6]:)\d+;[um]\d+><#@dp:#@dp>$/m.match(@para) +          elsif /^(([1-6])~(\S+))\s+(\S.+?)#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;[um]\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m.match(@para)              @@alt_id_count+=1              @format,@lev,segname,@text,@ocn=$1,$2,$3,$4,"x#{@@alt_id_count}" -          elsif  /^(([1-6])~)\s+(\S.+?)<~(\d+);[um]\d+;\w\d+><#@dp:#@dp>$/m.match(@para) +          elsif  /^(([1-6])~)\s+(\S.+?)#{Mx[:id_o]}~(\d+);[um]\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m.match(@para)              @@alt_id_count+=1              @format,@lev,@text,@ocn=$1,$2,$3,"x#{@@alt_id_count}"            end          else -          if /(.+?)<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/m.match(@para) +          if /(.+?)#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/m.match(@para)              @text,@ocn=$1,$2            end -          if @para !~/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$|^$/ #added 2002w06 +          if @para !~/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$|^$/ #added 2002w06              @text=/(.+?)/m.match(@para)[1]            end            if /^((\d)~(?:~\S+)?)\s+(.+)/m.match(@para) @@ -136,10 +136,10 @@ module SiSU_Wikispeak            end          end          format=@format.dup -        @lev_para_ocn=if @para =~/.+<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +        @lev_para_ocn=if @para =~/.+#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{#Mx[:id_c]}$/            Format::Format_text_object.new(format,@text,@ocn)          else -          Format::Format_text_object.new(format,@text,"<~(\d+);[um]\d+;\w\d+><#@dp:#@dp>") +          Format::Format_text_object.new(format,@text,"#{Mx[:id_o]}~(\d+);[um]\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}")          end          self        end @@ -154,7 +154,7 @@ module SiSU_Wikispeak          @data,@md=data,md          @vz=SiSU_Env::Get_init.instance.skin          @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -        @regx=/^(?:(?:<:p[bn]>\s*)?\d~(?:(\S+))?\s+)?(.+?)\s*<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ #m # 2004w18 pb pn removal added +        @regx=/^(?:(?:#{Mx[:br_line]}\s*|#{Mx[:br_nl]}\s*)?#{Mx[:lv_o]}\d:(\S*?)#{Mx[:lv_c]}\s*)?(.+?)\s*#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ #m # 2004w18 pb pn removal added          @tab="\t"          @@dostype='unix footnotes'          @br="\n" @@ -168,7 +168,7 @@ module SiSU_Wikispeak        end        # Used for extraction of endnotes from paragraphs        def extract_endnotes(para='') -        notes=para.scan(/~[{\[]([\d*+]+\s+.+?)\s*<#@dp>[}\]]~/) +        notes=para.scan(/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})([\d*+]+\s+.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/)          @n=[]        end        def wiki_metadata(meta) @@ -220,9 +220,9 @@ WOK          n3=lv + 2          lv=nil if lv == 0          extract_endnotes(para) -        para.gsub!(/~[{\[](?:[\d*+]+)\s+(.+?)<#@dp>[}\]]~/,'<ref>\1</ref>') # endnote marker marked up -        para.gsub!(/^\d~\S*\s+/,'') # endnote marker marked up -        para.gsub!(/<\S+?><#@dp:#@dp>/,'') # endnote marker marked up +        para.gsub!(/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})(?:[\d*+]+)\s+(.+?)#{Mx[:id_o]}#@dp#{Mx[:id_c]}(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/,'<ref>\1</ref>') # endnote marker marked up +        para.gsub!(/^#{Rx[:lv]}\S*\s+/,'') # endnote marker marked up +        para.gsub!(/<\S+?>#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}/,'') # endnote marker marked up          if lv            @@wiki[:body] << case lv            when 1;      '='*2 << para.strip  << @br*2 @@ -243,7 +243,7 @@ WOK          table_message='[table omitted, see other document formats]'          fix=[]          data.each do |para| -          para.gsub!(/<!Th?¡.+/um,"#@br#{table_message}") +          para.gsub!(/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}.+/um,"#@br#{table_message}")            para.gsub!(/.+?<-#>/,'')                                           # remove dummy headings (used by html) #check            para.gsub!(/_\*\s+/,'* ')                                           # bullet markup, marked down            para.gsub!(/©/,'©')                                           # bullet markup, marked down @@ -255,9 +255,9 @@ WOK            para.gsub!(/<u>(.+?)<\/u>/,'_\1_')            para.gsub!(/\{(.+?)\}(https?:\/\/\S+)/,'[\2 \1]')            para.gsub!(/(https?:\/\/\S+)/,'[\1]') -          para.gsub!(/<:(?:group|verse|alt|code)(?:-end)?>(?:\s+<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)?/,'') +          para.gsub!(/<:(?:group|verse|alt|code)(?:-end)?>(?:\s+#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]})?/,'')            para.gsub!(/<:p[bn]>/,'')                                         # remove page breaks -          para.gsub!(/^\s*<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/,'') # remove empty lines - check +          para.gsub!(/^\s*#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/,'') # remove empty lines - check            para.gsub!(/<a href=".+?">(.+?)<\/a>/m,'\1')            para.gsub!(/<:name#\S+?>/,'')                                       # remove name links            para.gsub!(/ /,' ')                                            # decide on @@ -270,14 +270,14 @@ WOK              if d_meta; wiki_metadata(d_meta)              end            end -          if para !~/(^0~|<ENDNOTES>|<EOF>)/ +          if para !~/(^0~|#{Mx[:br_endnotes]}|#{Mx[:br_eof]})/              if para =~@regx #/.+?<~\d+;\w\d+;\w\d+>.*/ #watch change                paranum=para[@regx,3]                @p_num=Format::Paragraph_number.new(paranum)              end              @sto=Split_text_object.new(para).lev_segname_para_ocn              ### problem in scroll, it appears tables are getting paragraph numbers -            m=/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +            m=/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/              if para =~m \              and para=~/\S+/                para=case @sto.format @@ -325,17 +325,17 @@ WOK              elsif para =~/#{table_message}/                @@wiki[:body] << para << @br              elsif para =~/(Note|Endnotes?)/ \ -            and para !~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +            and para !~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/              elsif para =~/(MetaData)/ \ -            and para =~/<~(\d+);[um]\d+;\w\d+><#@dp:#@dp>$/ #debug 2003w46 add rc info ####suspect visit +            and para =~/#{Mx[:id_o]}~(\d+);[um]\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ #debug 2003w46 add rc info ####suspect visit                #formatMono=MonoSiSU.new('<br /><a name="metadata">MetaData</a>')                #para=formatMono.bold_para              elsif para.include? 'Owner Details' \ -            and para !~/<~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +            and para !~/#{Mx[:id_o]}~(\d+);(?:[oh]|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                #formatMono=MonoSiSU.new('<br /><a name="owner.details">Owner Details</a>')                #@@wiki[:owner_details]=formatMono.bold_para                #para='' -            elsif para =~/(¡|<!Th?)/u #tables ! +            elsif para =~/(#{Mx[:tc_p]}|#{Mx[:gr_o]}Th?)/u #tables !              elsif para =~/(.*)<!#!>(.*)/                one,two=$1,$2                format_text=Format_text_object.new(one,two) diff --git a/lib/sisu/v0/xhtml.rb b/lib/sisu/v0/xhtml.rb index 8503bddb..067ed8a8 100644 --- a/lib/sisu/v0/xhtml.rb +++ b/lib/sisu/v0/xhtml.rb @@ -111,16 +111,16 @@ module SiSU_XHTML        end      end      class Scroll -      @@xml={ :body=>[],:sisu=>[],:open=>[],:close=>[],:head=>[] }        require "#{SiSU_lib}/shared_txt"        require "#{SiSU_lib}/css"        include SiSU_text_utils        @@dp=nil +      @@xml={ :body=>[],:sisu=>[],:open=>[],:close=>[],:head=>[] }        def initialize(particulars)          @env,@md,@dal_array=particulars.env,particulars.md,particulars.dal_array          @vz=SiSU_Env::Get_init.instance.skin          @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -        @regx=/^(?:(?:<:p[nb]>\s*)?\d~(?:(\S+))?\s+)?(.+?)\s*<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +        @regx=/^(?:(?:#{Mx[:br_page]}\s*|#{Mx[:br_page_new]}\s*)?#{Mx[:lv_o]}\d:(\S*)#{Mx[:lv_c]}\s*)?(.+?)\s*#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/          @tab="\t"          @trans=SiSU_XML_munge::Trans.new(@md)          @sys=SiSU_Env::System_call.new @@ -132,16 +132,16 @@ module SiSU_XHTML          publish        end      protected -      def embedded_endntoes(para='') -        para.gsub!(/~\{(\d+)\s+(.+?)\s*<#@dp>\}~/, +      def embedded_endnotes(para='') +        para.gsub!(/#{Mx[:en_a_o]}(\d+)\s+(.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/,            '<endnote><number>\1</number><note>\2</note></endnote> ') -        para.gsub!(/~\[([*+]\d+)\s+(.+?)\s*<#@dp>\]~/, +        para.gsub!(/#{Mx[:en_b_o]}([*+]\d+)\s+(.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_b_c]}/,            '<endnote><symbol>\1</symbol><note>\2</note></endnote> ') -        para.gsub!(/~\{([*+]+)\s+(.+?)\s*<#@dp>\}~/, +        para.gsub!(/#{Mx[:en_a_o]}([*+]+)\s+(.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/,            '<endnote><symbol>\1</symbol><note>\2</note></endnote> ')        end        def extract_endnotes(para='') -        notes=para.scan(/~[{\[]([\d*+]+\s+.+?)\s*<#@dp>[}\]]~/) +        notes=para.scan(/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})([\d*+]+\s+.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/)          notes.flatten.each do |e|            s=e.to_s            util=SiSU_text_utils::Wrap.new(s,70) @@ -176,7 +176,7 @@ WOK        end        def xml_head(meta)          txt=meta.text -        txt.gsub!(/<br(?: \/)?>/,'') +        txt.gsub!(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,' ')          txt.gsub!(/ & /,' and ')          el=meta.el.gsub(/\./,'_')          el_txt=meta.el.gsub(/\./,' ') @@ -197,7 +197,8 @@ WOK          n3=lv + 2          lv=nil if lv == 0          extract_endnotes(para) -        para.gsub!(/~[{\[]([\d*+]+)\s+(?:.+?)\s*<#@dp>[}\]]~/,'<en>\1</en>') #footnote/endnote clean +        para.gsub!(/#{Mx[:en_a_o]}([\d*+]+)\s+(?:.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/,'<en>\1</en>') #footnote/endnote clean +        para.gsub!(/#{Mx[:en_b_o]}([\d*+]+)\s+(?:.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_b_c]}/,'<en>\1</en>') #footnote/endnote clean          if para[@regx]            paragraph="#{para[@regx,2]}"            util=SiSU_text_utils::Wrap.new(paragraph,70) @@ -218,9 +219,11 @@ WOK          @endnotes=[]        end        def group_structure(para='',ocn='') -        para.gsub!(/<:group(?:-end)?>/,'') +        para.gsub!(/#{Mx[:gr_o]}group(?:-end)?#{Mx[:gr_c]}/,'')          para=@trans.markup_group(para)          para.strip! +        para.gsub!(/#{Mx[:en_a_o]}([\d*+]+)\s+(?:.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/,'<en>\1</en>') #footnote/endnote clean +        para.gsub!(/#{Mx[:en_b_o]}([\d*+]+)\s+(?:.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_b_c]}/,'<en>\1</en>') #footnote/endnote clean          @@xml[:body] << %{#{@tab*0}<object id="#{ocn}">} << "\n"          @@xml[:body] << %{#{@tab*1}<ocn>#{ocn}</ocn>} << "\n"          @@xml[:body] << %{#{@tab*1}<text class="group">#{@tab*1}\n} @@ -229,7 +232,7 @@ WOK          @@xml[:body] << "#{@tab*0}</object>" << "\n"        end        def poem_structure(para='',ocn='') -        para.gsub!(/<:verse(?:-end)?>/,'') +        para.gsub!(/#{Mx[:gr_o]}verse(?:-end)?#{Mx[:gr_c]}/,'')          para=@trans.markup_group(para)          para.strip!          @@xml[:body] << %{#{@tab*0}<object id="#{ocn}">} << "\n" @@ -240,7 +243,7 @@ WOK          @@xml[:body] << "#{@tab*0}</object>" << "\n"        end        def code_structure(para='',ocn='') -        para.gsub!(/<:code(?:-end)?>/,'') +        para.gsub!(/#{Mx[:gr_o]}code(?:-end)?#{Mx[:gr_c]}/,'')          para=@trans.markup_group(para)          para.gsub!(/\s\s/,'  ')          para.strip! @@ -266,67 +269,67 @@ WOK          data.each do |para|            para=@trans.markup(para)            @trans.char_enc.utf8(para) if @sys.locale =~/utf-?8/i #% utf8 -          if para =~/^0~(\S+)\s+(.+?)$/ # for headers +          if para =~/^#{Rx[:meta]}\s*.+?$/ # for headers              d_meta=SiSU_text_utils::Header_scan.new(@md,para).meta              if d_meta; xml_head(d_meta)              end            end            if @rcdc==false \            and (para =~/~metadata/ \ -          or para =~/1~meta\s+Document Information/) +          or para =~/#{Mx[:lv_o]}1:meta#{Mx[:lv_c]}\s*Document Information/)              @rcdc=true            end -          if para !~/(^0~|<ENDNOTES>|<EOF>)/ -            if para =~/.+?<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +          if para !~/(^#{Rx[:meta]}|#{Mx[:br_eof]}|#{Mx[:br_endnotes]})/ +            if para =~/.+?#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                paranum=para[@regx,3]                @p_num=SiSU_XML_format::Paragraph_number.new(@md,paranum)              end -            @sto=SiSU_text_parts::Split_text_object.new(@md,para).lev_segname_para_ocn +            @sto=SiSU_text_parts::Split_text_object.new(@md,para).xml              ### problem in scroll, it appears tables are getting paragraph numbers              unless @rcdc -              m=/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +              m=/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                if para =~m -                format_scroll=SiSU_XML_format::Format_scroll.new(@md,@sto.text) if @sto.format =~/i[12]|null/ +                format_scroll=SiSU_XML_format::Format_scroll.new(@md,@sto.text) if @sto.format =~/i[1-9]|null/                  case @sto.format -                when /^(1)~(?:(\S+))?/ +                when /^(1):(\S*)/                    xml_structure(para,$1,@sto.ocn,$2)                    para=@sto.lev_para_ocn.heading_body1 -                when /^(2)~(?:(\S+))?/ +                when /^(2):(\S*)/                    xml_structure(para,$1,@sto.ocn,$2)                    para=@sto.lev_para_ocn.heading_body2 -                when /^(3)~(?:(\S+))?/ +                when /^(3):(\S*)/                    xml_structure(para,$1,@sto.ocn,$2)                    para=@sto.lev_para_ocn.heading_body3 -                when /^(4)~(\S+)/ # work on see SiSU_text_parts::Split_text_object +                when /^(4):(\S+)/ # work on see SiSU_text_parts::Split_text_object                    xml_structure(para,$1,@sto.ocn,$2)                    para=@sto.lev_para_ocn.heading_body4 -                when /^(5)~(?:(\S+))?/ +                when /^(5):(\S*)/                    xml_structure(para,$1,@sto.ocn,$2)                    para=@sto.lev_para_ocn.heading_body5 -                when /^(6)~(?:(\S+))?/ +                when /^(6):(\S*)/                    xml_structure(para,$1,@sto.ocn,$2)                    para=@sto.lev_para_ocn.heading_body6                  else -                  matched=/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/mi.match(para) +                  matched=/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/mi.match(para)                    stamp,ocn=matched[0],matched[1] -                  if para =~ /<:verse>/ +                  if para =~ /#{Mx[:gr_o]}verse#{Mx[:gr_c]}/                      para.gsub!(/#{stamp}/,'')                      poem_structure(para,ocn) -                  elsif para =~ /<:group>/ +                  elsif para =~ /#{Mx[:gr_o]}group#{Mx[:gr_c]}/                      para.gsub!(/#{stamp}/,'')                      group_structure(para,ocn) -                  elsif para =~ /<:code>/ +                  elsif para =~ /#{Mx[:gr_o]}code#{Mx[:gr_c]}/                      para.gsub!(/#{stamp}/,'')                      code_structure(para,ocn) -                  elsif para =~/<!Th?.+/ # tables come as single block #work area 2005w13 +                  elsif para =~/#{Mx[:gr_o]}Th?.+/ # tables come as single block #work area 2005w13                      table=SiSU_Tables::Table_xml.new(para,ocn)                      para=table.table_split                      table_structure(para,ocn) -                  elsif para =~ /^\s*(?:<:i([1-9])> )?_\*/ +                  elsif para =~ /^\s*(?:#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]})?#{Mx[:gl_bullet]}/                      m=$1 -                    para.gsub!(/^(\s*(?:<:i[1-9]> )?)_\*/,'\1') +                    para.gsub!(/^(\s*(?:#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]})?)#{Mx[:gl_bullet]}/,'\1')                      xml_structure(para,nil,nil,nil,"indent_bullet#{m}") -                  elsif para =~ /<:i([1-9])>/ +                  elsif para =~ /^\s*#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]}/                      xml_structure(para,nil,nil,nil,"indent#{$1}")                    else xml_structure(para,nil,nil,nil)                    end @@ -335,14 +338,14 @@ WOK                    #@@xml[:body] << "#{@tab*7}<text>#{para[@regx,2]}</text>\n" if para[@regx,2] # main text, contents, body KEEP                    #@@xml[:body] << "#{@tab*6}</object>" << "\n" if para[@regx]                  end -              elsif para =~/(Note|Endnotes?)/ \ -              and para !~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +              elsif para =~/(#{Mx[:br_eof]}|#{Mx[:br_endnotes]})/ \ +              and para !~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                elsif para =~/(MetaData)/ \ -              and para =~/<~(\d+);[m]\d+;\w\d+><#@dp:#@dp>$/ #debug 2003w46 add rc info +              and para =~/#{Mx[:id_o]}~\d+;[m]\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ #debug 2003w46 add rc info                  format_scroll=Format_scroll.new(@md,'<br /><a name="metadata">MetaData</a>')                  para=format_scroll.bold_para                elsif para =~/(Owner Details)/ \ -              and para !~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +              and para !~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                  format_scroll=Format_scroll.new(@md,'<br /><a name="owner.details">Owner Details</a>')                  @@xml[:owner_details]=format_scroll.bold_para                  para='' @@ -351,12 +354,12 @@ WOK                  format_text=Format_text_object.new(one,two)                  para=format_text.seg_no_paranum                end -              if (para =~/<a name="n\d+">/ \ -              and para =~/^(-\{{2}~\d+|<!e[:_]\d+!>)/) # -endnote +              if para =~/<a name="n\d+">/ \ +              and para =~/^(-\{{2}~\d+|<!e[:_]\d+!>)/ # -endnote                  para=''                end                para=case para -              when /<:i[1-9]>/ +              when /#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]}/                  if para =~/.*<:#>.*$/                    format_text=Format_text_object.new(para,'')                    format_text.scr_inden_ocn_e_no_paranum @@ -373,7 +376,7 @@ WOK                end              else #              end -            para.gsub!(/<:\S+?>|<!.+!>/,'') if para +            para.gsub!(/#{Mx[:pa_o]}:\S+#{Mx[:pa_c]}/,'') if para            end          end          6.downto(4) do |x| @@ -428,7 +431,7 @@ WOK          SiSU_Env::SiSU_file.new(@md).mkdir          filename_xml=SiSU_Env::SiSU_file.new(@md,@md.fn[:xhtml]).mkfile          @data.each do |para| -          para.gsub!(/<:\S+?>|<!.+?!>/,'') +          para.gsub!(/#{Mx[:pa_o]}:\S+#{Mx[:pa_c]}/,'') #; para.gsub!(/<:\S+?>|<!.+?!>/,'')            para.gsub!(/^\s*\n$/,'')            filename_xml.puts para unless para.empty?          end diff --git a/lib/sisu/v0/xml.rb b/lib/sisu/v0/xml.rb index 23125e05..9f897266 100644 --- a/lib/sisu/v0/xml.rb +++ b/lib/sisu/v0/xml.rb @@ -118,7 +118,7 @@ module SiSU_XML_SAX          @env,@md,@dal_array=particulars.env,particulars.md,particulars.dal_array          @vz=SiSU_Env::Get_init.instance.skin          @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -        @regx=/^(?:(?:<:p[bn]>\s*)?\d~(?:(\S+))?\s+)?(.+?)\s*<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +        @regx=/^(?:(?:#{Mx[:br_page]}\s*|#{Mx[:br_page_new]}\s*)?#{Mx[:lv_o]}\d:(\S*?)#{Mx[:lv_c]})?\s*(.+?)\s*#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/          @tab="\t"          @trans=SiSU_XML_munge::Trans.new(@md)          @sys=SiSU_Env::System_call.new @@ -130,16 +130,16 @@ module SiSU_XML_SAX          publish        end      protected -      def embedded_endntoes(para='') -        para.gsub!(/~\{(\d+)\s+(.+?)\s*<#@dp>\}~/, +      def embedded_endnotes(para='') +        para.gsub!(/#{Mx[:en_a_o]}(\d+)\s+(.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/,            '<endnote><number>\1</number><note>\2</note></endnote> ') -        para.gsub!(/~\[([*+]\d+)\s+(.+?)\s*<#@dp>\]~/, +        para.gsub!(/#{Mx[:en_b_o]}([*+]\d+)\s+(.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_b_c]}/,            '<endnote><symbol>\1</symbol><note>\2</note></endnote> ') -        para.gsub!(/~\{([*+]+)\s+(.+?)\s*<#@dp>\}~/, +        para.gsub!(/#{Mx[:en_a_o]}([*+]+)\s+(.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/,            '<endnote><symbol>\1</symbol><note>\2</note></endnote> ')        end        def extract_endnotes(para='') -        notes=para.scan(/~[{\[]([\d*+]+\s+.+?)\s*<#@dp>[}\]]~/) +        notes=para.scan(/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})([\d*+]+\s+.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/)          notes.flatten.each do |e|            s=e.to_s            util=SiSU_text_utils::Wrap.new(s,70) @@ -176,7 +176,7 @@ WOK        end        def xml_head(meta)          txt=meta.text -        txt.gsub!(/<br(?: \/)?>/,'') +        txt.gsub!(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,' ')          txt.gsub!(/ & /,' and ')          el=meta.el.gsub(/\./,'_')          el_txt=meta.el.gsub(/\./,' ') @@ -219,7 +219,8 @@ WOK          n3=lv + 2          lv=nil if lv == 0          extract_endnotes(para) -        para.gsub!(/~[{\[]([\d*+]+)\s+(?:.+?)\s*<#@dp>[}\]]~/,'<en>\1</en>') #footnote/endnote clean +        para.gsub!(/#{Mx[:en_a_o]}([\d*+]+)\s+(?:.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/,'<en>\1</en>') #footnote/endnote clean +        para.gsub!(/#{Mx[:en_b_o]}([\d*+]+)\s+(?:.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_b_c]}/,'<en>\1</en>') #footnote/endnote clean          if para[@regx]            paragraph="#{para[@regx,2]}"            util=SiSU_text_utils::Wrap.new(paragraph,70) @@ -238,9 +239,10 @@ WOK          @endnotes=[]        end        def group_structure(para='',ocn='') -        para.gsub!(/<:group(?:-end)?>/,'') +        para.gsub!(/#{Mx[:gr_o]}group(?:-end)?#{Mx[:gr_c]}/,'')          extract_endnotes(para) -        para.gsub!(/~[{\[]([\d*+]+)\s+(?:.+?)\s*<#@dp>[}\]]~/,'<en>\1</en>') #footnote/endnote clean +        para.gsub!(/#{Mx[:en_a_o]}([\d*+]+)\s+(?:.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/,'<en>\1</en>') #footnote/endnote clean +        para.gsub!(/#{Mx[:en_b_o]}([\d*+]+)\s+(?:.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_b_c]}/,'<en>\1</en>') #footnote/endnote clean          para=@trans.markup_group(para)          para.strip!          @@xml[:body] << %{#{@tab*0}<object id="#{ocn}">} << "\n" @@ -253,7 +255,7 @@ WOK          @endnotes=[]        end        def poem_structure(para='',ocn='') -        para.gsub!(/<:verse(?:-end)?>/,'') +        para.gsub!(/#{Mx[:gr_o]}verse(?:-end)?#{Mx[:gr_c]}/,'')          para=@trans.markup_group(para)          #para.gsub!(/\s\s/,'  ')          para.strip! @@ -265,7 +267,7 @@ WOK          @@xml[:body] << "#{@tab*0}</object>" << "\n"        end        def code_structure(para='',ocn='') -        para.gsub!(/<:code(?:-end)?>/,'') +        para.gsub!(/#{Mx[:gr_o]}code(?:-end)?#{Mx[:gr_c]}/,'')          para=@trans.markup_group(para)          para.gsub!(/\s\s/,'  ')          para.strip! @@ -291,82 +293,79 @@ WOK          data.each do |para|            para=@trans.markup(para)            @trans.char_enc.utf8(para) if @sys.locale =~/utf-?8/i #% utf8 -          if para =~/^0~(\S+)\s+(.+?)$/ # for headers +          if para =~/^#{Rx[:meta]}\s*.+?$/ # for headers              d_meta=SiSU_text_utils::Header_scan.new(@md,para).meta              if d_meta; xml_head(d_meta)              end            end            if @rcdc==false \ -          and (para =~/~metadata/ or para =~/1~meta\s+Document Information/) +          and (para =~/~metadata/ \ +          or para =~/#{Mx[:lv_o]}1:meta#{Mx[:lv_c]}\s*Document Information/)              @rcdc=true            end -          if para !~/(^0~|<ENDNOTES>|<EOF>)/ -            if para =~/.+?<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +          if para !~/(^#{Rx[:meta]}|#{Mx[:br_eof]}|#{Mx[:lv_o]}4:endnotes#{Mx[:lv_c]}|#{Mx[:br_endnotes]})/ +            if para =~/.+?#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                paranum=para[@regx,3]                @p_num=SiSU_XML_format::Paragraph_number.new(@md,paranum)              end -            @sto=SiSU_text_parts::Split_text_object.new(@md,para).lev_segname_para_ocn -            ### problem in scroll, it appears tables are getting paragraph numbers +            @sto=SiSU_text_parts::Split_text_object.new(@md,para).xml +            #@sto=SiSU_text_parts::Split_text_object.new(@md,para).lev_segname_para_ocn              unless @rcdc -              m=/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +              m=/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                if para =~m -                format_scroll=SiSU_XML_format::Format_scroll.new(@md,@sto.text) if @sto.format =~/i[12]|null/ +                format_scroll=SiSU_XML_format::Format_scroll.new(@md,@sto.text) if @sto.format =~/i[1-9]|null/                  case @sto.format -                when /^(1)~(?:(\S+))?/ +                when /^(1):(\S*)/                    xml_structure(para,$1,@sto.ocn,$2)                    para=@sto.lev_para_ocn.heading_body1 -                when /^(2)~(?:(\S+))?/ +                when /^(2):(\S*)/                    xml_structure(para,$1,@sto.ocn,$2)                    para=@sto.lev_para_ocn.heading_body2 -                when /^(3)~(?:(\S+))?/ +                when /^(3):(\S*)/                    xml_structure(para,$1,@sto.ocn,$2)                    para=@sto.lev_para_ocn.heading_body3 -                when /^(4)~(\S+)/ # work on see Split_text_object +                when /^(4):(\S+)/ # work on see Split_text_object                    xml_structure(para,$1,@sto.ocn,$2)                    para=@sto.lev_para_ocn.heading_body4 -                when /^(5)~(?:(\S+))?/ +                when /^(5):(\S*)/                    xml_structure(para,$1,@sto.ocn,$2)                    para=@sto.lev_para_ocn.heading_body5 -                when /^(6)~(?:(\S+))?/ +                when /^(6):(\S*)/                    xml_structure(para,$1,@sto.ocn,$2)                    para=@sto.lev_para_ocn.heading_body6                  else -                  matched=/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/mi.match(para) +                  matched=/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/mi.match(para)                    stamp,ocn=matched[0],matched[1] -                  if para =~ /<:verse>/ +                  if para =~ /#{Mx[:gr_o]}verse#{Mx[:gr_c]}/                      para.gsub!(/#{stamp}/,'')                      poem_structure(para,ocn) -                  elsif para =~ /<:group>/ +                  elsif para =~ /#{Mx[:gr_o]}group#{Mx[:gr_c]}/                      para.gsub!(/#{stamp}/,'')                      group_structure(para,ocn) -                  elsif para =~ /<:code>/ +                  elsif para =~ /#{Mx[:gr_o]}code#{Mx[:gr_c]}/                      para.gsub!(/#{stamp}/,'')                      code_structure(para,ocn) -                  elsif para =~/<!Th?.+/ # tables come as single block #work area 2005w13 +                  elsif para =~/#{Mx[:gr_o]}Th?.+/ # tables come as single block #work area 2005w13                      table=SiSU_Tables::Table_xml.new(para,ocn)                      para=table.table_split                      table_structure(para) -                  elsif para =~ /^\s*(?:<:i([1-9])> )?_\*/                           #uncomment +                  elsif para =~ /^\s*(?:#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]})?#{Mx[:gl_bullet]}/                           #uncomment                      m=$1 -                    para.gsub!(/^(\s*(?:<:i[1-9]> )?)_\*/,'\1') +                    para.gsub!(/^(\s*(?:#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]})?)#{Mx[:gl_bullet]}/,'\1')                      xml_structure(para,nil,nil,nil,"indent_bullet#{m}") -                  elsif para =~ /<:i([1-9])>/ +                  elsif para =~ /#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]}/                      xml_structure(para,nil,nil,nil,"indent#{$1}")                    else xml_structure(para,nil,nil,nil)                    end -                  #@@xml[:body] << "#{@tab*6}<object>" << "\n" if para[@regx] -                  #@@xml[:body] << "#{@tab*7}<ocn>#{para[@regx,3]}</ocn>" << "\n" if para[@regx,3] -                  #@@xml[:body] << "#{@tab*7}<text>#{para[@regx,2]}</text>\n" if para[@regx,2] # main text, contents, body KEEP -                  #@@xml[:body] << "#{@tab*6}</object>" << "\n" if para[@regx]                  end -              elsif para =~/(Note|Endnotes?)/ \ -              and para !~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +              elsif para =~/(#{Mx[:br_eof]}|#{Mx[:br_endnotes]})/ \ +              and para !~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                elsif para =~/(MetaData)/ \ -              and para =~/<~(\d+);[m]\d+;\w\d+><#@dp:#@dp>$/ #debug 2003w46 add rc info +              and para =~/#{Mx[:id_o]}~\d+;[m]\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ #debug 2003w46 add rc info                  format_scroll=Format_scroll.new(@md,'<br /><a name="metadata">MetaData</a>')                  para=format_scroll.bold_para                elsif para =~/(Owner Details)/ \ -              and para !~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +              and para !~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                  format_scroll=Format_scroll.new(@md,'<br /><a name="owner.details">Owner Details</a>')                  @@xml[:owner_details]=format_scroll.bold_para                  para='' @@ -379,8 +378,8 @@ WOK                and para =~/^(-\{{2}~\d+|<!e[:_]\d+!>)/ # -endnote                  para=''                end -              if para =~/.*<:#>.*$/ -                para=if para =~ /<:i[1-9]>/ +              if para =~/.*<:#>.*$/ #investigate removal +                para=if para =~ /#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]}/                    format_text=Format_text_object.new(para,'')                    format_text.scr_inden_ocn_e_no_paranum                  end @@ -395,7 +394,7 @@ WOK                end              else #              end -            para.gsub!(/<:\S+?>|<!.+!>/,'') if para +            para.gsub!(/#{Mx[:pa_o]}:\S+#{Mx[:pa_c]}/,'') if para            end          end          6.downto(4) do |x| @@ -451,7 +450,7 @@ WOK          SiSU_Env::SiSU_file.new(@md).mkdir          filename_xml=SiSU_Env::SiSU_file.new(@md,@md.fn[:sax]).mkfile          @data.each do |para| -          para.gsub!(/<:\S+?>|<!.+?!>/,'') +          para.gsub!(/#{Mx[:pa_o]}:\S+#{Mx[:pa_c]}/,'') #; para.gsub!(/<:\S+?>|<!.+?!>/,'')            para.gsub!(/^\s*\n$/,'')            filename_xml.puts para unless para.empty?          end diff --git a/lib/sisu/v0/xml_dom.rb b/lib/sisu/v0/xml_dom.rb index 008a8ed2..9bcb15ec 100644 --- a/lib/sisu/v0/xml_dom.rb +++ b/lib/sisu/v0/xml_dom.rb @@ -112,15 +112,15 @@ module SiSU_XML_DOM        end      end      class Scroll -      @@xml={ :body=>[],:open=>[],:close=>[],:head=>[],:sc=>[] }        require "#{SiSU_lib}/shared_txt"        include SiSU_text_utils        @@dp=nil +      @@xml={ :body=>[],:open=>[],:close=>[],:head=>[],:sc=>[] }        def initialize(particulars)          @env,@md,@dal_array=particulars.env,particulars.md,particulars.dal_array          @vz=SiSU_Env::Get_init.instance.skin          @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -        @regx=/^(?:(?:<:p[bn]>\s*)?\d~(?:(\S+))?\s+)?(.+?)\s*<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ # +        @regx=/^(?:(?:#{Mx[:br_page]}\s*|#{Mx[:br_page_new]}\s*)?#{Mx[:lv_o]}\d:(\S*)#{Mx[:lv_c]}\s*)?(.+?)\s*#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/          @tab="\t"          @trans=SiSU_XML_munge::Trans.new(@md)          @sys=SiSU_Env::System_call.new @@ -133,16 +133,16 @@ module SiSU_XML_DOM        end      protected        def xml_markup(para='') -        para.gsub!(/~\{(\d+)\s+(.+?)\s*<#@dp>\}~/, +        para.gsub!(/#{Mx[:en_a_o]}(\d+)\s+(.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/,            '<endnote><number>\1</number><note>\2</note></endnote> ') -        para.gsub!(/~\[([*+]\d+)\s+(.+?)\s*<#@dp>\]~/, +        para.gsub!(/#{Mx[:en_b_o]}([*+]\d+)\s+(.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_b_c]}/,            '<endnote><symbol>\1</symbol><note>\2</note></endnote> ') -        para.gsub!(/~\{([*+]+)\s+(.+?)\s*<#@dp>\}~/, +        para.gsub!(/#{Mx[:en_a_o]}([*+]+)\s+(.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/,            '<endnote><symbol>\1</symbol><note>\2</note></endnote> ')        end        def xml_head(meta)          txt=meta.text -        txt.gsub!(/<br(?: \/)?>/,'') +        txt.gsub!(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,' ')          txt.gsub!(/ & /,' and ')          el=meta.el.gsub(/\./,'_')          el_txt=meta.el.gsub(/\./,' ') @@ -301,9 +301,9 @@ WOK          ((lv+1)..6).each { |x| @level[x]=false }        end        def group_structure(para='',ocn='') -        para.gsub!(/<:group(?:-end)?>/,'') +        para.gsub!(/#{Mx[:gr_o]}group(?:-end)?#{Mx[:gr_c]}/,'')          para=@trans.markup_group(para) -        para.gsub!(/~\{(\d+)\s+(.+?)\s*<#@dp>\}~/m, +        para.gsub!(/#{Mx[:en_a_o]}(\d+)\s+(.+?)\s*#{Mx[:id_o]}#@dp#{Mx[:id_c]}#{Mx[:en_a_c]}/m,            '<endnote><number>\1</number><note>\2</note></endnote> ')          para.strip!          @@xml[:body] << %{#{@tab*6}<object id="#{ocn}">} << "\n" @@ -314,7 +314,7 @@ WOK          @@xml[:body] << "#{@tab*6}</object>" << "\n"        end        def poem_structure(para='',ocn='') -        para.gsub!(/<:verse(?:-end)?>/,'') +        para.gsub!(/#{Mx[:gr_o]}verse(?:-end)?#{Mx[:gr_c]}/,'')          para=@trans.markup_group(para)          para.strip!          @@xml[:body] << %{#{@tab*6}<object id="#{ocn}">} << "\n" @@ -325,7 +325,7 @@ WOK          @@xml[:body] << "#{@tab*6}</object>" << "\n"        end        def code_structure(para='',ocn='') -        para.gsub!(/<:code(?:-end)?>/,'') +        para.gsub!(/#{Mx[:gr_o]}code(?:-end)?#{Mx[:gr_c]}/,'')          para=@trans.markup_group(para)          para.gsub!(/\s\s/,'  ')          para.strip! @@ -344,82 +344,82 @@ WOK        end        def markup(data)          xml_sc(@md) -        @rcdc=false          @level,@cont,@copen,@xml_contents_close=[],[],[],[] +        @rcdc=false          (0..6).each { |x| @cont[x]=@level[x]=false }          (4..6).each { |x| @xml_contents_close[x]='' }          data.each do |para|            para=@trans.markup(para)            @trans.char_enc.utf8(para) if @sys.locale =~/utf-?8/i #% utf8 -          if para =~/^0~(\S+)\s+(.+?)$/ # for headers +          if para =~/^#{Rx[:meta]}\s*(.+?)$/ # for headers              d_meta=SiSU_text_utils::Header_scan.new(@md,para).meta              if d_meta; xml_head(d_meta)              end            end            if @rcdc==false \            and (para =~/~metadata/ \ -          or para =~/1~meta\s+Document Information/) +          or para =~/#{Mx[:lv_o]}1:meta#{Mx[:lv_x]}\s*Document Information/)              @rcdc=true            end -          if para !~/(^0~|<ENDNOTES>|<EOF>)/ -            if para =~/.+?<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +          if para !~/(^#{Rx[:meta]}|#{Mx[:br_eof]}|#{Mx[:br_endnotes]})/ +            if para =~/.+?#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                paranum=para[@regx,3]                @p_num=SiSU_XML_format::Paragraph_number.new(@md,paranum)              end -            @sto=SiSU_text_parts::Split_text_object.new(@md,para).lev_segname_para_ocn +            @sto=SiSU_text_parts::Split_text_object.new(@md,para).xml              ### problem in scroll, it appears tables are getting paragraph numbers              unless @rcdc -              m=/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +              m=/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                if para =~m -                format_scroll=SiSU_XML_format::Format_scroll.new(@md,@sto.text) if @sto.format =~/i[12]|null/ +                format_scroll=SiSU_XML_format::Format_scroll.new(@md,@sto.text) if @sto.format =~/i[1-9]|null/                  case @sto.format -                when /^(1)~(?:(\S+))?/ +                when /^(1):(\S*)/                    xml_markup(para)                    xml_structure($1,@sto.ocn,para,$2)                    para=@sto.lev_para_ocn.heading_body1 #if para =~m -                when /^(2)~(?:(\S+))?/ +                when /^(2):(\S*)/                    xml_markup(para)                    xml_structure($1,@sto.ocn,para,$2)                    para=@sto.lev_para_ocn.heading_body2 #if para =~m -                when /^(3)~(?:(\S+))?/ +                when /^(3):(\S*)/                    xml_markup(para)                    xml_structure($1,@sto.ocn,para,$2)                    para=@sto.lev_para_ocn.heading_body3 #if para =~m -                when /^(4)~(\S+)/ # work on see SiSU_text_parts::Split_text_object +                when /^(4):(\S+)/ # work on see SiSU_text_parts::Split_text_object                    xml_markup(para)                    xml_structure($1,@sto.ocn,para,$2)                    para=@sto.lev_para_ocn.heading_body4 #if para =~m -                when /^(5)~(?:(\S+))?/ +                when /^(5):(\S*)/                    xml_markup(para)                    xml_structure($1,@sto.ocn,para,$2)                    para=@sto.lev_para_ocn.heading_body5 #if para =~m -                when /^(6)~(?:(\S+))?/ +                when /^(6):(\S*)/                    xml_markup(para)                    xml_structure($1,@sto.ocn,para,$2)                    para=@sto.lev_para_ocn.heading_body6 #if para =~m                  else -                  matched=/<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/mi.match(para) +                  matched=/#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/mi.match(para)                    stamp,ocn=matched[0],matched[1] -                  if para =~ /<:verse>/ +                  if para =~ /#{Mx[:gr_o]}verse#{Mx[:gr_c]}/                      para.gsub!(/#{stamp}/,'')                      poem_structure(para,ocn) -                  elsif para =~ /<:group>/ +                  elsif para =~ /#{Mx[:gr_o]}group#{Mx[:gr_c]}/                      para.gsub!(/#{stamp}/,'')                      group_structure(para,ocn) -                  elsif para =~ /<:code>/ +                  elsif para =~ /#{Mx[:gr_o]}code#{Mx[:gr_c]}/                      para.gsub!(/#{stamp}/,'')                      code_structure(para,ocn) -                  elsif para =~/<!Th?.+/ # tables come as single block #work area 2005w13 +                  elsif para =~/#{Mx[:gr_o]}Th?.+/ # tables come as single block #work area 2005w13                      table=SiSU_Tables::Table_xml.new(para,ocn)                      para=table.table_split                      @@xml[:body] << table_structure(para,ocn)                    else #xml_structure(para, nil, nil, nil)                      type=case para -                    when /^\s*(?:<:i([1-9])> )?_\*/ +                    when /^\s*(?:#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]}\s*)?#{Mx[:gl_bullet]}/                        m=$1 -                      para.gsub!(/^(\s*(?:<:i[1-9]> )?)_\*/,'\1') +                      para.gsub!(/^(\s*(?:#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]}\s*)?)#{Mx[:gl_bullet]}/,'\1')                        "indent_bullet#{m}" -                    when /^\s*<:i([1-9])>/; "indent#{$1}" +                    when /^\s*#{Mx[:pa_o]}:i([1-9])#{Mx[:pa_c]}/; "indent#{$1}"                      else                    'norm'                      end                      xml_markup(para) @@ -432,16 +432,16 @@ WOK                      @@xml[:body] << "#{@tab*6}</object>" << "\n" if para[@regx]                    end                  end -              elsif para =~/(Note|Endnotes?)/ \ -              and para !~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +              elsif para =~/(#{Mx[:br_eof]}|#{Mx[:br_endnotes]})/ \ +              and para !~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                  #format_scroll=MonoSiSU.new('<br /><a name="notes">Note</a>')                  #para=format_scroll.boldPara                elsif para =~/(MetaData)/ \ -              and para =~/<~\d+;[m]\d+;\w\d+><#@dp:#@dp>$/ #debug 2003w46 add rc info +              and para =~/#{Mx[:id_o]}~\d+;[m]\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ #debug 2003w46 add rc info                  format_scroll=Format_scroll.new(@md,'<br /><a name="metadata">MetaData</a>')                  para=format_scroll.bold_para                elsif para =~/(Owner Details)/ \ -              and para !~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>$/ +              and para !~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/                  format_scroll=Format_scroll.new(@md,'<br /><a name="owner.details">Owner Details</a>')                  @@xml[:owner_details]=format_scroll.bold_para                  para='' @@ -455,8 +455,7 @@ WOK                  para=''                end                if para =~/.*<:#>.*$/ -                para=case para -                when /<:i[1-9]>/ +                para=if para =~ /#{Mx[:pa_o]}:i[1-9]#{Mx[:pa_c]}/                    format_text=Format_text_object.new(para,'')                    format_text.scr_inden_ocn_e_no_paranum                  end @@ -471,8 +470,7 @@ WOK                end              else #              end -            para.gsub!(/<:\S+?>/,'') -            para.gsub!(/<!.+!>/,' ') ## Clean Prepared Text +            para.gsub!(/#{Mx[:pa_o]}:\S+#{Mx[:pa_c]}/,'') if para            end          end          @content_flag=true @@ -535,8 +533,7 @@ WOK          filename_xml=SiSU_Env::SiSU_file.new(@md,@md.fn[:dom]).mkfile          @data.each do |para|            #para.strip! -          para.gsub!(/<:\S+?>/,'') -          para.gsub!(/<!.+?!>/,'') +          para.gsub!(/#{Mx[:pa_o]}:\S+#{Mx[:pa_c]}/,'') #; para.gsub!(/<:\S+?>|<!.+?!>/,'')            para="#{para}\n" unless para.empty?            filename_xml.puts para          end diff --git a/lib/sisu/v0/xml_fictionbook.rb b/lib/sisu/v0/xml_fictionbook.rb index 9e9a42f9..ce100f3b 100644 --- a/lib/sisu/v0/xml_fictionbook.rb +++ b/lib/sisu/v0/xml_fictionbook.rb @@ -177,8 +177,8 @@ WOK        end        def markup(para,type='')          para.strip! -        para=para.gsub(/^[1-9]~(?:\S+)?\s+/,'') -        para=para.gsub(/<~(\d+);(?:\d:\d+|\S\d+);\S\d+><#@dp:#@dp>/,'[(\1)]') +        para=para.gsub(/^#{Mx[:lv_o]}[1-9]:\S*?#{Mx[:lv_c]}\s*/,'') +        para=para.gsub(/#{Mx[:id_o]}~(\d+);(?:\d:\d+|\S\d+);\S\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}/,'[(\1)]')          para=@trans.markup_fictionbook(para)          para=if type.empty?; "<p>#{para}</p>"          else "<#{type}><p>#{para}</p></#{type}>" @@ -288,7 +288,7 @@ WOK          @ds=[]          c=0          data.each do |para| -          rgx_headers=/<~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)>/ +          rgx_headers=/#{Mx[:id_o]}~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)#{Mx[:id_c]}/            if para =~rgx_headers              x=(rgx_headers).match(para)              if x[3] =~/^[hum]\d+/ diff --git a/lib/sisu/v0/xml_format.rb b/lib/sisu/v0/xml_format.rb index 5558bd80..20eb6736 100644 --- a/lib/sisu/v0/xml_format.rb +++ b/lib/sisu/v0/xml_format.rb @@ -292,7 +292,7 @@ WOK          @paranum=/(\d+)/m.match(txt[2])[1]          @headname=''          #if txt[2]=~/\d+/ -        m=/\d~(\S+)/m.match(format) +        m=/#{Mx[:lv_o]}\d:(\S+?)#{Mx[:lv_c]}/m.match(format)          headname=m[1] if m          @headname=%{<a name="h#{headname}"></a>} unless headname.nil?          @p_num=SiSU_XML_format::Paragraph_number.new(@md,@paranum) @@ -301,7 +301,7 @@ WOK        rgx=/^[1-6-]~{1,2}/ #watch        link=txt[0].gsub(rgx,'') if @one =~rgx        @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern -      rgx=/~\{\d+\s+(.+?)<#@dp>\}~/ +      rgx=/~\{\d+\s+(.+?)#{Mx[:id_o]}#@dp#{Mx[:id_c]}\}~/        link=txt[0].gsub(rgx,'\1') if txt[0] =~rgx        @link,@linkname=link,txt[1]        @vz=SiSU_Env::Get_init.instance.skin diff --git a/lib/sisu/v0/xml_scaffold.rb b/lib/sisu/v0/xml_scaffold.rb index 1404567c..9c3a7128 100644 --- a/lib/sisu/v0/xml_scaffold.rb +++ b/lib/sisu/v0/xml_scaffold.rb @@ -185,8 +185,8 @@ module SiSU_XML_scaffold          @ds=[]          c=0          data.each do |para| -          if para =~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+>/ -            x=(/<~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)>/).match(para) +          if para =~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}/ +            x=(/#{Mx[:id_o]}~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)#{Mx[:id_c]}/).match(para)              if x[3] =~/^[hu]\d+/                @ds[c]={}                @ds[c][:ocn]=x[1] diff --git a/lib/sisu/v0/xml_tables.rb b/lib/sisu/v0/xml_tables.rb index 1e08f3eb..98eab515 100644 --- a/lib/sisu/v0/xml_tables.rb +++ b/lib/sisu/v0/xml_tables.rb @@ -88,43 +88,43 @@ module SiSU_Tables        m=@parablock[/<!f(.+?)!>/,1]        @@tablefoot << m if m        @parablock.gsub!(/<!f.+?!>/,'') -      @@tablehead=1 if @parablock =~/<!Th¡/u -      if @parablock =~/<!Th?¡/u -        @parablock.gsub!(/<!Th?¡.+?!~(\d+);\w\d+;\w\d+>/u, +      @@tablehead=1 if @parablock =~/#{Mx[:gr_o]}Th#{Mx[:tc_p]}/u +      if @parablock =~/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}/u +        @parablock.gsub!(/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}.+?#{Mx[:tc_p]}~(\d+);\w\d+;\w\d+#{Mx[:gr_c]}/u,            %{\n<ocn>#@ocn</ocn><table summary="normal text css" width="100%" border="0" bgcolor="white" cellpadding="2" align="center">})        end -      if @parablock =~/<!TZ!>/ +      if @parablock =~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/          tablefoot=[]          #bug table footers need rethink, removed for now          @@tablefoot.each {|x| tablefoot << ''}          @@tablefoot=[] -        @parablock.gsub!(/<!TZ!>\s+<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>/,"</table>\n") # + -        @parablock.gsub!(/<!TZ!>\s*/,"</table>\n") +        @parablock.gsub!(/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}\s+#{Mx[:id_o]}~(\d+);(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}/,"</table>\n") # + +        @parablock.gsub!(/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}\s*/,"</table>\n")        end        if @@tablehead == 1 -        if @parablock =~/¡¡/u -          @parablock.gsub!(/<!¡¡(\d+?)¡/u, +        if @parablock =~/#{Mx[:tc_p]}#{Mx[:tc_p]}/u +          @parablock.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,              %{<tr>    <td width="\\1%" valign="top">      #{@vz.paragraph_table_xml}<b>}) -          @parablock.gsub!(/¡¡(\d+?)¡/u, +          @parablock.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,              %{</b></td><td width="\\1%" valign="top">    #{@vz.paragraph_table_xml}<b>}) -          @parablock.gsub!(/!>/,"</b>\n</td>\n</tr>") +          @parablock.gsub!(/#{Mx[:tc_c]}/,"</b>\n</td>\n</tr>")            @@tablehead=0          end          @parablock        else -        @parablock.gsub!(/<!¡¡(\d+?)¡/u, +        @parablock.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,            %{<tr>    <td width="\\1%" valign="top">      #{@vz.paragraph_table_xml}}) -        @parablock.gsub!(/¡¡(\d+?)¡/u, +        @parablock.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,            %{    </td>    <td width="\\1%" valign="top">      #{@vz.paragraph_table_xml}}) -        @parablock.gsub!(/!>/,"\n</td>\n</tr>\n") +        @parablock.gsub!(/#{Mx[:tc_c]}/,"\n</td>\n</tr>\n")        end        @parablock      end @@ -171,39 +171,39 @@ module SiSU_Tables        m=@parablock[/<!f(.+?)!>/,1]        @@tablefoot << m if m        @parablock.gsub!(/<!f.+?!>/,'') -      @@tablehead=1 if @parablock =~/<!Th¡/u -      if @parablock =~/<!Th?¡.+?!~(\d+);\w\d+;\w\d+>/u; @parablock=table_head($1) +      @@tablehead=1 if @parablock =~/#{Mx[:gr_o]}Th#{Mx[:tc_p]}/u +      if @parablock =~/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}.+?#{Mx[:tc_p]}~(\d+);\w\d+;\w\d+#{Mx[:gr_c]}/u; @parablock=table_head($1)        end -      if @parablock =~/<!TZ!>/ +      if @parablock =~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/          tablefoot=[]          @@tablefoot.each {|x| tablefoot << ''}          @@tablefoot=[] -        if @parablock =~/<!TZ!>/; @parablock=table_end +        if @parablock =~/#{Mx[:gr_o]}TZ#{Mx[:gr_c]}/; @parablock=table_end          end        end        if @@tablehead == 1 -        if @parablock =~/¡¡/u -          if @parablock =~/<!¡¡(\d+?)¡/u -            @parablock.gsub!(/<!¡¡(\d+?)¡/u,table_row($1,true)) +        if @parablock =~/#{Mx[:tc_p]}#{Mx[:tc_p]}/u +          if @parablock =~/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u +            @parablock.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,table_row($1,true))            end -          if @parablock =~/¡¡(\d+?)¡/u -            @parablock.gsub!(/¡¡(\d+?)¡/u,table_cell($1,true)) +          if @parablock =~/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u +            @parablock.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,table_cell($1,true))            end -          if @parablock =~/!>/ -            @parablock.gsub!(/!>/,table_row_close(true)) +          if @parablock =~/#{Mx[:tc_c]}/ +            @parablock.gsub!(/#{Mx[:tc_c]}/,table_row_close(true))            end            @@tablehead=0          end          @parablock        else -        if @parablock =~/<!¡¡(\d+?)¡/u -          @parablock.gsub!(/<!¡¡(\d+?)¡/u,table_row($1)) +        if @parablock =~/^#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u +          @parablock.gsub!(/^#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,table_row($1))          end -        if @parablock =~/¡¡(\d+?)¡/u -          @parablock.gsub!(/¡¡(\d+?)¡/u,table_cell($1)) +        if @parablock =~/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u +          @parablock.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}(\d+?)#{Mx[:tc_p]}/u,table_cell($1))          end -        if @parablock =~/!>/ -          @parablock.gsub!(/!>/,table_row_close) +        if @parablock =~/#{Mx[:tc_c]}/ +          @parablock.gsub!(/#{Mx[:tc_c]}/,table_row_close)          end          @parablock        end @@ -211,4 +211,5 @@ module SiSU_Tables      end    end  end +__END__ diff --git a/man/man1/sisu.1 b/man/man1/sisu.1 index 59acec9f..fe745b87 100644 --- a/man/man1/sisu.1 +++ b/man/man1/sisu.1 @@ -1,4 +1,4 @@ -.TH "sisu" "1" "2008-05-22" "0.67.0" "SiSU" +.TH "sisu" "1" "2008-07-21" "0.68.0" "SiSU"  .SH NAME  sisu \- documents: markup, structuring, publishing in multiple standard formats, and search  .SH SYNOPSIS @@ -179,14 +179,14 @@ content prepared in  \- Structured information, Serialized Units \- a document publishing system  .BR -sisu \ [ \ \-abcDdFHhIiMmNnopqRrSsTtUuVvwXxYyZz0\-9 \ ] \ [ \ filename/ \ -wildcard \ ] +sisu [ \ \-abcDdFHhIiMmNnopqRrSsTtUuVvwXxYyZz0\-9 \ ] [ \ filename/ \ wildcard +\ ]  .BR -sisu \ [ \ \-Ddcv \ ] \ [ \ instruction \ ] +sisu [ \ \-Ddcv \ ] [ \ instruction \ ]  .BR -sisu \ [ \ \-CcFLSVvW \ ] +sisu [ \ \-CcFLSVvW \ ]  .BR  Note: commands should be issued from within the directory that contains the @@ -208,20 +208,20 @@ structure information. For more see: <http://www.jus.uio.no/sisu>  2.3 DOCUMENT PROCESSING COMMAND FLAGS  .TP -.B \ \-a \ \ [filename/wildcard] +.B \-a [filename/wildcard]  produces plaintext with Unix linefeeds and without markup, (object numbers -are omitted), has footnotes at end of each paragraph that contains them \ [ \ -\-A \ for \ equivalent \ dos \ (linefeed) \ output \ file] \ [see \ \-e \ for \ +are omitted), has footnotes at end of each paragraph that contains them [ \ \-A +\ for \ equivalent \ dos \ (linefeed) \ output \ file] [see \ \-e \ for \  endnotes]. (Options include: \-\-endnotes for endnotes \-\-footnotes for  footnotes at the end of each paragraph \-\-unix for unix linefeed (default)  \-\-msdos for msdos linefeed)  .TP -.B \ \-b \ \ [filename/wildcard] +.B \-b [filename/wildcard]  produces xhtml/XML output for browser viewing (sax parsing).  .TP -.B \ \-C \ \ [\-\-init\-site] +.B \-C [\-\-init\-site]  configure/initialise shared output directory files initialize shared output  directory (config files such as css and dtd files are not updated if they  already exist unless modifier is used). \-C \-\-init\-site configure/initialise @@ -230,40 +230,37 @@ update, existing shared output config files such as css and dtd files are  updated if this modifier is used.  .TP -.B \ \-CC -\ configure/initialise \ shared \ output \ directory \ files \ initialize \ -shared \ output \ directory \ (config \ files \ such \ as \ css \ and \ dtd \ -files \ are \ not \ updated \ if \ they \ already \ exist \ unless \ modifier \ -is \ used). \ The \ equivalent \ of: \ \-C \ \-\-init\-site \ -configure/initialise \ site, \ more \ extensive \ than \ \-C \ on \ its \ own, -\ shared \ output \ directory \ files/force \ update, \ existing \ shared \ -output \ config \ files \ such \ as \ css \ and \ dtd \ files \ are \ updated \ -if \ \-CC \ is \ used. \ +.B \-CC +configure/initialise shared output directory files initialize shared output +directory (config files such as css and dtd files are not updated if they +already exist unless modifier is used). The equivalent of: \-C \-\-init\-site +configure/initialise site, more extensive than \-C on its own, shared output +directory files/force update, existing shared output config files such as css +and dtd files are updated if \-CC is used.  .TP -.B \ \-c \ \ [filename/wildcard] +.B \-c [filename/wildcard]  screen toggle ansi screen colour on or off depending on default set (unless  \-c flag is used: if sisurc colour default is set to \'true\', output to screen  will be with colour, if sisurc colour default is set to \'false\' or is  undefined screen output will be without colour).  .TP -.B \ \-D \ \ [instruction] \ [filename] +.B \-D [instruction] [filename]  database postgresql ( \-\-pgsql may be used instead) possible instructions, -include: \-\-createdb; \-\-create; \-\-dropall; \-\-import \ [filename]; -\-\-update \ [filename]; \-\-remove \ [filename]; see database section below. +include: \-\-createdb; \-\-create; \-\-dropall; \-\-import [filename]; +\-\-update [filename]; \-\-remove [filename]; see database section below.  .TP -.B \ \-d \ \ [\-\-db\-[database \ type \ (sqlite|pg)]] \-\-[instruction] \ -[filename] +.B \-d [\-\-db\-[database \ type \ (sqlite|pg)]] \-\-[instruction] [filename]  database type default set to sqlite, (for which \-\-sqlite may be used  instead) or to specify another database \-\-db\-[pgsql, \ sqlite] (however see  \-D) possible instructions include: \-\-createdb; \-\-create; \-\-dropall; -\-\-import \ [filename]; \-\-update \ [filename]; \-\-remove \ [filename]; see +\-\-import [filename]; \-\-update [filename]; \-\-remove [filename]; see  database section below.  .TP -.B \ \-F \ \ [\-\-webserv=webrick] +.B \-F [\-\-webserv=webrick]  generate examples of (naive) cgi search form for sqlite and pgsql depends on  your already having used sisu to populate an sqlite and/or pgsql database, (the  sqlite version scans the output directories for existing sisu_sqlite databases, @@ -277,71 +274,71 @@ that they be copied to the cgi\-bin directory). \-Fv (in addition to the above)  provides some information on setting up hyperestraier for sisu  .TP -.B \ \-H \ \ [filename/wildcard] +.B \-H [filename/wildcard]  produces html without link suffixes (.html \.pdf etc.) (\"Hide\"). Requires -an appropriately configured web server. \ [behaviour \ switched \ after \ 0.35 -\ see \ \-h]. +an appropriately configured web server. [behaviour \ switched \ after \ 0.35 \ +see \ \-h].  .TP -.B \ \-h \ \ [filename/wildcard] +.B \-h [filename/wildcard]  produces html (with hardlinks i.e. with name suffixes in links/local urls).  html, with internal document links that include the document suffix, i.e.  whether it is \.html or \.pdf (required for browsing directly off a file -system, and works with most web servers). \ [behaviour \ switched \ after \ -0.35 \ see \ \-H]. +system, and works with most web servers). [behaviour \ switched \ after \ 0.35 +\ see \ \-H].  .TP -.B \ \-I \ \ [filename/wildcard] +.B \-I [filename/wildcard]  produces texinfo and info file, (view with pinfo).  .TP -.B \ \-i \ \ [filename/wildcard] +.B \-i [filename/wildcard]  produces man page of file, not suitable for all outputs.  .TP -.B \ \-L -\ prints \ license \ information. \ +.B \-L +prints license information.  .TP -.B \ \-M \ \ [filename/wildcard/url] +.B \-M [filename/wildcard/url]  maintenance mode files created for processing preserved and their locations  indicated. (also see \-V)  .TP -.B \ \-m \ \ [filename/wildcard/url] +.B \-m [filename/wildcard/url]  assumed for most other flags, creates new meta\-markup file, (the metaverse )  that is used in all subsequent processing of other output. This step is assumed  for most processing flags. To skip it see \-n  .TP -.B \ \-N \ \ [filename/wildcard/url] +.B \-N [filename/wildcard/url]  document digest or document content certificate ( DCC ) as md5 digest tree of  the document: the digest for the document, and digests for each object  contained within the document (together with information on software versions  that produced it) (digest.txt). \-NV for verbose digest output to screen.  .TP -.B \ \-n \ \ [filename/wildcard/url] +.B \-n [filename/wildcard/url]  skip meta\-markup (building of \"metaverse\"), this skips the equivalent of  \-m which is otherwise assumed by most processing flags.  .TP -.B \ \-o \ \ [filename/wildcard/url] +.B \-o [filename/wildcard/url]  output basic document in opendocument file format (opendocument.odt).  .TP -.B \ \-p \ \ [filename/wildcard] +.B \-p [filename/wildcard]  produces LaTeX pdf (portrait.pdf & landscape.pdf). Default paper size is set  in config file, or document header, or provided with additional command line  parameter, e.g. \-\-papersize\-a4 preset sizes include: \'A4\', U.S. \'letter\'  and \'legal\' and book sizes \'A5\' and \'B5\' (system defaults to A4).  .TP -.B \ \-q \ \ [filename/wildcard] +.B \-q [filename/wildcard]  quiet less output to screen.  .TP -.B \ \-R \ \ [filename/wildcard] +.B \-R [filename/wildcard]  copies sisu output files to remote host using rsync. This requires that  sisurc.yml has been provided with information on hostname and username, and  that you have your \"keys\" and ssh agent in place. Note the behavior of rsync @@ -350,22 +347,21 @@ different if \-R is used with other flags from if used alone. Alone the rsync  \-R is used together with other flags, it is not). Also see \-r  .TP -.B \ \-r \ \ [filename/wildcard] +.B \-r [filename/wildcard]  copies sisu output files to remote host using scp. This requires that  sisurc.yml has been provided with information on hostname and username, and  that you have your \"keys\" and ssh agent in place. Also see \-R  .TP -.B \ \-S -\ produces \ a \ sisupod \ a \ zipped \ sisu \ directory \ of \ markup \ -files \ including \ sisu \ markup \ source \ files \ and \ the \ directories \ -local \ configuration \ file, \ images \ and \ skins. \ Note: \ this \ only \ -includes \ the \ configuration \ files \ or \ skins \ contained \ in \ \./_sisu -\ not \ those \ in \ ~/.sisu \ \-S \ \ [filename/wildcard] option. Note: (this +.B \-S +produces a sisupod a zipped sisu directory of markup files including sisu +markup source files and the directories local configuration file, images and +skins. Note: this only includes the configuration files or skins contained in + \./_sisu not those in ~/.sisu \-S [filename/wildcard] option. Note: (this  option is tested only with zsh).  .TP -.B \ \-S \ \ [filename/wildcard] +.B \-S [filename/wildcard]  produces a zipped file of the prepared document specified along with  associated images, by default named sisupod.zip they may alternatively be named  with the filename extension \.ssp This provides a quick way of gathering the @@ -382,19 +378,18 @@ that file that are not your own are treated as untrusted. The directory  structure of the unzipped file is understood by sisu, and sisu commands can be  run within it. Note: if you wish to send multiple files, it quickly becomes  more space efficient to zip the sisu markup directory, rather than the -individual files for sending). See the \-S option without \ -[filename/wildcard]. +individual files for sending). See the \-S option without [filename/wildcard].  .TP -.B \ \-s \ \ [filename/wildcard] +.B \-s [filename/wildcard]  copies sisu markup file to output directory.  .TP -.B \ \-t \ \ [filename/wildcard \ (*.termsheet.rb)] +.B \-t [filename/wildcard \ (*.termsheet.rb)]  standard form document builder, preprocessing feature  .TP -.B \ \-U \ \ [filename/wildcard] +.B \-U [filename/wildcard]  prints url output list/map for the available processing flags options and  resulting files that could be requested, (can be used to get a list of  processing options in relation to a file, together with information on the @@ -404,77 +399,76 @@ provides webrick url mappings where appropriate, but these can be switched to  file system paths in sisurc.yml  .TP -.B \ \-u \ \ [filename/wildcard] +.B \-u [filename/wildcard]  provides url mapping of output files for the flags requested for processing,  also see \-U  .TP -.B \ \-V -\ on \ its \ own, \ provides -.B \ SiSU -\ version \ and \ environment \ information \ (sisu \ \-\-help \ env) \ +.B \-V +on its own, provides +.B SiSU +version and environment information (sisu \-\-help env)  .TP -.B \ \-V \ \ [filename/wildcard] +.B \-V [filename/wildcard]  even more verbose than the \-v flag. (also see \-M)  .TP -.B \ \-v -\ on \ its \ own, \ provides -.B \ SiSU -\ version \ information \ +.B \-v +on its own, provides +.B SiSU +version information  .TP -.B \ \-v \ \ [filename/wildcard] +.B \-v [filename/wildcard]  provides verbose output of what is being built, where it is being built (and  error messages if any), as with \-u flag provides a url mapping of files  created for each of the processing flag requests. See also \-V  .TP -.B \ \-W -\ starts \ ruby\'s \ webrick \ webserver \ points \ at \ sisu \ output \ -directories, \ the \ default \ port \ is \ set \ to \ 8081 \ and \ can \ be \ -changed \ in \ the \ resource \ configuration \ files. \ \ [tip: \ the \ -webrick \ server \ requires \ link \ suffixes, \ so \ html \ output \ should \ -be \ created \ using \ the \ \-h \ option \ rather \ than \ \-H; \ also, \ note -\ \-F \ webrick \ ]. +.B \-W +starts ruby\'s webrick webserver points at sisu output directories, the +default port is set to 8081 and can be changed in the resource configuration +files. [tip: \ the \ webrick \ server \ requires \ link \ suffixes, \ so \ html +\ output \ should \ be \ created \ using \ the \ \-h \ option \ rather \ than \ +\-H; \ also, \ note \ \-F \ webrick \ ].  .TP -.B \ \-w \ \ [filename/wildcard] +.B \-w [filename/wildcard]  produces concordance (wordmap) a rudimentary index of all the words in a  document. (Concordance files are not generated for documents of over 260,000  words unless this limit is increased in the file sisurc.yml)  .TP -.B \ \-X \ \ [filename/wildcard] +.B \-X [filename/wildcard]  produces XML output with deep document structure, in the nature of dom.  .TP -.B \ \-x \ \ [filename/wildcard] +.B \-x [filename/wildcard]  produces XML output shallow structure (sax parsing).  .TP -.B \ \-Y \ \ [filename/wildcard] +.B \-Y [filename/wildcard]  produces a short sitemap entry for the document, based on html output and the  sisu_manifest. \-\-sitemaps generates/updates the sitemap index of existing -sitemaps. (Experimental, \ [g,y,m \ announcement \ this \ week]) +sitemaps. (Experimental, [g,y,m \ announcement \ this \ week])  .TP -.B \ \-y \ \ [filename/wildcard] +.B \-y [filename/wildcard]  produces an html summary of output generated (hyperlinked to content) and  document specific metadata (sisu_manifest.html). This step is assumed for most  processing flags.  .TP -.B \ \-Z \ \ [filename/wildcard] +.B \-Z [filename/wildcard]  Zap, if used with other processing flags deletes output files of the type  about to be processed, prior to processing. If \-Z is used as the lone  processing related flag (or in conjunction with a combination of \-[mMvVq]),  will remove the related document output directory.  .TP -.B \ \-z \ \ [filename/wildcard] -produces php (zend) \ [this \ feature \ is \ disabled \ for \ the \ time \ +.B \-z [filename/wildcard] +produces php (zend) [this \ feature \ is \ disabled \ for \ the \ time \  being]  .SH @@ -482,25 +476,22 @@ being]  .BR  .TP -.B \ \-\-no\-ocn -\ \ [with \ \-h \ \-H \ or \ \-p] switches off object citation numbering. -Produce output without identifying numbers in margins of html or LaTeX/pdf -output. +.B \-\-no\-ocn +[with \ \-h \ \-H \ or \ \-p] switches off object citation numbering. Produce +output without identifying numbers in margins of html or LaTeX/pdf output.  .TP -.B \ \-\-no\-annotate -\ strips \ output \ text \ of \ editor \ endnotes[^*1] denoted by asterisk or -dagger/plus sign +.B \-\-no\-annotate +strips output text of editor endnotes[^*1] denoted by asterisk or dagger/plus +sign  .TP -.B \ \-\-no\-asterisk -\ strips \ output \ text \ of \ editor \ endnotes[^*2] denoted by asterisk -sign +.B \-\-no\-asterisk +strips output text of editor endnotes[^*2] denoted by asterisk sign  .TP -.B \ \-\-no\-dagger -\ strips \ output \ text \ of \ editor \ endnotes[^+1] denoted by dagger/plus -sign +.B \-\-no\-dagger +strips output text of editor endnotes[^+1] denoted by dagger/plus sign  .SH  4. DATABASE COMMANDS @@ -514,36 +505,35 @@ dbi \- database interface  \-d is modifiable with \-\-db=[database \ type \ (pgsql \ or \ sqlite)]  .TP -.B \ \-Dv \ \-\-createall -\ initial \ step, \ creates \ required \ relations \ (tables, \ indexes) \ in -\ existing \ postgresql \ database \ (a \ database \ should \ be \ created \ -manually \ and \ given \ the \ same \ name \ as \ working \ directory, \ as \ -requested) \ (rb.dbi) \ \ [ \ \-dv \ \-\-createall \ sqlite \ equivalent] it -may be necessary to run sisu \-Dv \-\-createdb initially NOTE: at the present -time for postgresql it may be necessary to manually create the database. The -command would be \'createdb \ [database \ name]\' where database name would be -SiSU_[present \ working \ directory \ name \ (without \ path)]. Please use only -alphanumerics and underscores. +.B \-Dv \-\-createall +initial step, creates required relations (tables, indexes) in existing +postgresql database (a database should be created manually and given the same +name as working directory, as requested) (rb.dbi) [ \ \-dv \ \-\-createall \ +sqlite \ equivalent] it may be necessary to run sisu \-Dv \-\-createdb +initially NOTE: at the present time for postgresql it may be necessary to +manually create the database. The command would be \'createdb [database \ +name]\' where database name would be SiSU_[present \ working \ directory \ name +\ (without \ path)]. Please use only alphanumerics and underscores.  .TP -.B \ \-Dv \ \-\-import -\ \ [filename/wildcard] imports data specified to postgresql db (rb.dbi) \ [ -\ \-dv \ \-\-import \ sqlite \ equivalent] +.B \-Dv \-\-import +[filename/wildcard] imports data specified to postgresql db (rb.dbi) [ \ \-dv +\ \-\-import \ sqlite \ equivalent]  .TP -.B \ \-Dv \ \-\-update -\ \ [filename/wildcard] updates/imports specified data to postgresql db -(rb.dbi) \ [ \ \-dv \ \-\-update \ sqlite \ equivalent] +.B \-Dv \-\-update +[filename/wildcard] updates/imports specified data to postgresql db (rb.dbi) +[ \ \-dv \ \-\-update \ sqlite \ equivalent]  .TP -.B \ \-D \ \-\-remove -\ \ [filename/wildcard] removes specified data to postgresql db (rb.dbi) \ [ -\ \-d \ \-\-remove \ sqlite \ equivalent] +.B \-D \-\-remove +[filename/wildcard] removes specified data to postgresql db (rb.dbi) [ \ \-d +\ \-\-remove \ sqlite \ equivalent]  .TP -.B \ \-D \ \-\-dropall -\ kills \ data\" \ and \ drops \ (postgresql \ or \ sqlite) \ db, \ tables \ -& \ indexes \ \ [ \ \-d \ \-\-dropall \ sqlite \ equivalent] +.B \-D \-\-dropall +kills data\" and drops (postgresql or sqlite) db, tables & indexes [ \ \-d \ +\-\-dropall \ sqlite \ equivalent]  .BR  The v in e.g. \-Dv is for verbose output. @@ -553,7 +543,7 @@ The v in e.g. \-Dv is for verbose output.  .BR  .TP -.B \ \-\-update \ \ [filename/wildcard] +.B \-\-update [filename/wildcard]  Checks existing file output and runs the flags required to update this  output. This means that if only html and pdf output was requested on previous  runs, only the \-hp files will be applied, and only these will be generated @@ -561,37 +551,37 @@ this time, together with the summary. This can be very convenient, if you offer  different outputs of different files, and just want to do the same again.  .TP -.B \ \-0 \ to \ \-5 \ \ [filename \ or \ wildcard] +.B \-0 to \-5 [filename \ or \ wildcard]  Default shorthand mappings (note that the defaults can be changed/configured  in the sisurc.yml file):  .TP -.B \ \-0 -\ \-mNhwpAobxXyYv \ \ [this \ is \ the \ default \ action \ run \ when \ no \ -options \ are \ give, \ i.e. \ on \ \'sisu \ \ [filename]\'] +.B \-0 +\-mNhwpAobxXyYv [this \ is \ the \ default \ action \ run \ when \ no \ +options \ are \ give, \ i.e. \ on \ \'sisu \ [filename]\']  .TP -.B \ \-1 -\ \-mNHwpy \ +.B \-1 +\-mNHwpy  .TP -.B \ \-2 -\ \-mNHwpaoy \ +.B \-2 +\-mNHwpaoy  .TP -.B \ \-3 -\ \-mNhwpAobxXyY \ +.B \-3 +\-mNhwpAobxXyY  .TP -.B \ \-4 -\ \-mNhwpAobxXDyY \ \-\-import \ +.B \-4 +\-mNhwpAobxXDyY \-\-import  .TP -.B \ \-5 -\ \-mNhwpAobxXDyY \ \-\-update \ +.B \-5 +\-mNhwpAobxXDyY \-\-update  .BR -add \-v for verbose mode and \-c for color, e.g. sisu \-2vc \ [filename \ or \ +add \-v for verbose mode and \-c for color, e.g. sisu \-2vc [filename \ or \  wildcard]  .BR @@ -630,7 +620,7 @@ The manual can be generated from source, found respectively, either within the  tarball or installed locally at:  .BR -  \./data/doc/sisu/sisu_markup_samples/sisu_manual/ +  ./data/doc/sisu/sisu_markup_samples/sisu_manual/  .BR    /usr/share/doc/sisu/sisu_markup_samples/sisu_manual/ @@ -667,7 +657,7 @@ the sisu manual, the sources files for which are located within the  tarball at:  .BR -  \./data/doc/sisu/sisu_manual/ +  ./data/doc/sisu/sisu_manual/  .BR  Once installed, directory equivalent to: @@ -682,16 +672,16 @@ Available man pages are converted back to html using man2html:    /usr/share/doc/sisu/html/  .BR -  \./data/doc/sisu/html/ +  ./data/doc/sisu/html/  .BR  An online version of the sisu man page is available here:  .BR -* various sisu man pages <http://www.jus.uio.no/sisu/man/> \ [^7] +* various sisu man pages <http://www.jus.uio.no/sisu/man/> [^7]  .BR -* sisu.1 <http://www.jus.uio.no/sisu/man/sisu.1.html> \ [^8] +* sisu.1 <http://www.jus.uio.no/sisu/man/sisu.1.html> [^8]  .SH  6.3 SISU BUILT\-IN INTERACTIVE HELP @@ -704,7 +694,7 @@ information:    sisu \-\-help  .BR -  sisu \-\-help \ [subject] +  sisu \-\-help [subject]  .BR      sisu \-\-help commands @@ -713,11 +703,11 @@ information:      sisu \-\-help markup  .BR -    sisu \-\-help env \ [for \ feedback \ on \ the \ way \ your \ system \ is \ +    sisu \-\-help env [for \ feedback \ on \ the \ way \ your \ system \ is \      setup \ with \ regard \ to \ sisu]  .BR -  sisu \-V \ [environment \ information, \ same \ as \ above \ command] +  sisu \-V [environment \ information, \ same \ as \ above \ command]  .BR    sisu (on its own provides version and some help information) @@ -814,7 +804,7 @@ markup or sisu \-\-help markup  To check the markup in a file:  .BR -  sisu \-\-identify \ [filename].sst +  sisu \-\-identify [filename].sst  .BR  For brief descriptive summary of markup history @@ -945,12 +935,12 @@ This is a sample header  .BR  .B % SiSU 0.38 -\ [declared \ file\-type \ identifier \ with \ markup \ version] +[declared \ file\-type \ identifier \ with \ markup \ version] +  .BR  .B @title: -\ [title \ text] This is the title of the document and used as such, this -header is the only one that is + \ [title \ text] This is the title of the document and used as such, this header is the only one that is  .I mandatory  .BR @@ -959,7 +949,7 @@ The Subtitle if any  .BR  .B @creator: -\ [or \ @author:] Name of Author +[or \ @author:] Name of Author  .BR  .B @subject: @@ -988,8 +978,9 @@ The Subtitle if any  .BR  .B @date: 2000\-08\-27 -\ [ \ also \ @date.created: \ @date.issued: \ @date.available: \ @date.valid: -\ @date.modified: \ ] +[ \ also \ @date.created: \ @date.issued: \ @date.available: \ @date.valid: \ +@date.modified: \ ] +  .BR  .B @type: article @@ -1005,13 +996,13 @@ The Subtitle if any  .BR  .B @language: -\ [or \ @language.document:] \ [country \ code \ for \ language \ if \ -available, \ or \ language, \ English, \ en \ is \ the \ default \ setting] (en -\- English, fr \- French, de \- German, it \- Italian, es \- Spanish, pt \- +[or \ @language.document:] [country \ code \ for \ language \ if \ available, +\ or \ language, \ English, \ en \ is \ the \ default \ setting] (en \- +English, fr \- French, de \- German, it \- Italian, es \- Spanish, pt \-  Portuguese, sv \- Swedish, da \- Danish, fi \- Finnish, no \- Norwegian, is \-  Icelandic, nl \- Dutch, et \- Estonian, hu \- Hungarian, pl \- Polish, ro \-  Romanian, ru \- Russian, el \- Greek, uk \- Ukranian, tr \- Turkish, sk \- -Slovak, sl \- Slovenian, hr \- Croatian, cs \- Czech, bg \- Bul garian ) \ +Slovak, sl \- Slovenian, hr \- Croatian, cs \- Czech, bg \- Bul garian )  [however, \ encodings \ are \ not \ available \ for \ all \ of \ the \  languages \ listed.] @@ -1040,16 +1031,16 @@ public domain, copyleft, creative commons variant, etc.  .BR  .B @keywords:  text document generation processing management latex pdf structured xml -citation \ [your \ keywords \ here, \ used \ for \ example \ by \ rss \ feeds, -\ and \ in \ sql \ searches] +citation [your \ keywords \ here, \ used \ for \ example \ by \ rss \ feeds, \ +and \ in \ sql \ searches]  .BR  .B @abstract: -\ [paper \ abstract, \ placed \ after \ table \ of \ contents] +[paper \ abstract, \ placed \ after \ table \ of \ contents]  .BR  .B @comment: -\ [...] +[...]  .BR  .B @catalogue: @@ -1058,27 +1049,27 @@ classification]; isbn=[ISBN]; pg=[Project \ Gutenberg \ text \ number]  .BR  .B @classify_loc: -\ [Library \ of \ Congress \ classification] +[Library \ of \ Congress \ classification]  .BR  .B @classify_dewey: -\ [Dewey \ classification] +[Dewey \ classification]  .BR  .B @classify_isbn: -\ [ISBN] +[ISBN]  .BR  .B @classify_pg: -\ [Project \ Gutenberg \ text \ number] +[Project \ Gutenberg \ text \ number]  .BR  .B @prefix: -\ [prefix \ is \ placed \ just \ after \ table \ of \ contents] +[prefix \ is \ placed \ just \ after \ table \ of \ contents]  .BR  .B @prefix_a: -\ [prefix \ is \ placed \ just \ before \ table \ of \ contents \ \- \ not \ +[prefix \ is \ placed \ just \ before \ table \ of \ contents \ \- \ not \  implemented]  .BR @@ -1086,8 +1077,8 @@ implemented]  .BR  .B @rcs: -$Id: sisu_markup.sst,v 1.2 2007/09/08 17:12:47 ralph Exp $ \ [used \ by \ rcs -\ or \ cvs \ to \ embed \ version \ (revision \ control) \ information \ into \ +$Id: sisu_markup.sst,v 1.2 2007/09/08 17:12:47 ralph Exp $ [used \ by \ rcs \ +or \ cvs \ to \ embed \ version \ (revision \ control) \ information \ into \  document, \ rcs \ or \ cvs \ can \ usefully \ provide \ a \ history \ of \  updates \ to \ a \ document \ ] @@ -1104,35 +1095,35 @@ for @toc:)  .BR  .B @level:  newpage=3; breakpage=4 -\ [paragraph \ level, \ used \ by \ latex \ to \ breakpages, \ the \ page \ -is \ optional \ eg. \ in \ newpage] +[paragraph \ level, \ used \ by \ latex \ to \ breakpages, \ the \ page \ is +\ optional \ eg. \ in \ newpage]  .BR  .B @markup: -information on the markup used, e.g. new=1,2,3; break=4; num_top=4 \ [or \ +information on the markup used, e.g. new=1,2,3; break=4; num_top=4 [or \  newpage=1,2,3; \ breakpage=4; \ num_top=4] newpage and breakpage, heading  level, used by LaTeX to breakpages. breakpage: starts on a new page in single  column text and on a new column in double column text; newpage: starts on a new  page for both single and double column texts. -num_top=4 \ [auto\-number \ document, \ starting \ at \ level \ 4. \ the \ +num_top=4 [auto\-number \ document, \ starting \ at \ level \ 4. \ the \  default \ is \ to \ provide \ 3 \ levels, \ as \ in \ 1 \ level \ 4, \ 1.1 \  level \ 5, \ 1.1.1 \ level \ 6, \ markup \ to \ be \ merged \ within \ level] -num_extract \ [take \ numbering \ of \ headings \ provided \ (manually \ in \ +num_extract [take \ numbering \ of \ headings \ provided \ (manually \ in \  marked \ up \ source \ document), \ and \ use \ for \ numbering \ of \  segments. \ Available \ where \ a \ clear \ numbering \ structure \ is \  provided \ within \ document, \ without \ the \ repetition \ of \ a \ number \ -in \ a \ header.] \ [In \ 0.38 \ notation, \ you \ would \ map \ to \ the \ +in \ a \ header.] [In \ 0.38 \ notation, \ you \ would \ map \ to \ the \  equivalent \ levels, \ the \ examples \ provided \ would \ map \ to \ the \ -following \ new=A,B,C; \ break=1; \ num_top=1 \ \ [or \ newpage=A,B,C; \ +following \ new=A,B,C; \ break=1; \ num_top=1 \ [or \ newpage=A,B,C; \  breakpage=1; \ num_top=1] see headings]  .BR  .B @bold: -\ [regular \ expression \ of \ words/phrases \ to \ be \ made \ bold] +[regular \ expression \ of \ words/phrases \ to \ be \ made \ bold]  .BR  .B @italics: -\ [regular \ expression \ of \ words/phrases \ to \ italicise] +[regular \ expression \ of \ words/phrases \ to \ italicise]  .BR  .B @vocabulary: @@ -1146,12 +1137,13 @@ generated, such as the urls of the home site, and the icon/logo for the  document or site.  .TP -.B \ @man: \ 8; -\ name=sisu \ \- \ documents: \ markup, \ structuring, \ publishing \ in \ -multiple \ standard \ formats, \ and \ search; \ synopsis=sisu \ \ -[\-abcDdFHhIiMmNnopqRrSsTtUuVvwXxYyZz0\-9] \ [filename/wildcard \ ] -sisu \ [\-Ddcv] \ [instruction] -sisu \ [\-CcFLSVvW] +.B @man: 8; +name=sisu \- documents: markup, structuring, publishing in multiple standard +formats, and search; +synopsis=sisu [\-abcDdFHhIiMmNnopqRrSsTtUuVvwXxYyZz0\-9] [filename/wildcard \ +] +sisu [\-Ddcv] [instruction] +sisu [\-CcFLSVvW]  the man page category number (default 1) and special tags used in preparing  man page headings @@ -1165,7 +1157,7 @@ man page headings  .BR  .B @promo:  sisu, ruby, search_libre_docs, open_society -\ [places \ content \ in \ right \ pane \ in \ html, \ makes \ use \ of \ +[places \ content \ in \ right \ pane \ in \ html, \ makes \ use \ of \  list.yml \ and \ promo.yml, \ commented \ out \ sample \ in \ document \  sample: \  free_as_in_freedom.richard_stallman_crusade_for_free_software.sam_williams.sst] @@ -1185,21 +1177,21 @@ level 1 heading (used where a stand\-alone document may be imported into  another)  .BR -.B :A~ \ [heading \ text] -Top level heading \ [this \ usually \ has \ similar \ content \ to \ the \ +.B :A~ [heading \ text] +Top level heading [this \ usually \ has \ similar \ content \ to \ the \  title \ @title: \ ] NOTE: the heading levels described here are in 0.38  notation, see heading  .BR -.B :B~ \ [heading \ text] -Second level heading \ [this \ is \ a \ heading \ level \ divider] +.B :B~ [heading \ text] +Second level heading [this \ is \ a \ heading \ level \ divider]  .BR -.B :C~ \ [heading \ text] -Third level heading \ [this \ is \ a \ heading \ level \ divider] +.B :C~ [heading \ text] +Third level heading [this \ is \ a \ heading \ level \ divider]  .BR -.B 1~ \ [heading \ text] +.B 1~ [heading \ text]  Top level heading preceding substantive text of document or sub\-heading 2,  the heading level that would normally be marked 1. or 2. or 3. etc. in a  document, and the level on which sisu by default would break html output into @@ -1207,19 +1199,20 @@ named segments, names are provided automatically if none are given (a number),  otherwise takes the form 1~my_filename_for_this_segment  .BR -.B 2~ \ [heading \ text] +.B 2~ [heading \ text]  Second level heading preceding substantive text of document or sub\-heading  3, the heading level that would normally be marked 1.1 or 1.2 or 1.3 or 2.1  etc. in a document.  .BR -.B 3~ \ [heading \ text] +.B 3~ [heading \ text]  Third level heading preceding substantive text of document, that would  normally be marked 1.1.1 or 1.1.2 or 1.2.1 or 2.1.1 etc. in a document  .nf    1~filename level 1 heading, +.BR    % the primary division such as Chapter that is followed by substantive text, and may be further subdivided (this is the level on which by default html segments are made)  .fi @@ -1232,15 +1225,25 @@ normally be marked 1.1.1 or 1.1.2 or 1.2.1 or 2.1.1 etc. in a document  .nf    normal text !{emphasis}! *{bold text}* _{underscore}_ /{italics}/ \"{citation}\" ^{superscript}^ ,{subscript}, +{inserted text}+ +.BR    normal text +.BR    !{emphasis}! +.BR    *{bold text}* +.BR    _{underscore}_ +.BR    /{italics}/ +.BR    \"{citation}\" +.BR    ^{superscript}^ +.BR    ,{subscript}, +.BR    +{inserted text}+ +.BR    \-{strikethrough}\-  .fi @@ -1248,7 +1251,8 @@ normally be marked 1.1.1 or 1.1.2 or 1.2.1 or 2.1.1 etc. in a document  .B resulting output:  .BR -normal text <em>emphasis</em> +normal text +.B emphasis  .B bold text  .I underscore  .I italics @@ -1258,8 +1262,6 @@ normal text <em>emphasis</em>  .BR  normal text -.BR -<em>emphasis</em>  .BR  .B bold text @@ -1294,12 +1296,15 @@ normal text  .nf    ordinary paragraph +.BR    _1 indent paragraph one step +.BR    _2 indent paragraph two steps +.BR    _9 indent paragraph nine steps  .fi -.BR +  .B resulting output:  .BR @@ -1319,8 +1324,10 @@ ordinary paragraph  .nf -  * bullet text +  _* bullet text +.BR    _1* bullet text, first indent +.BR    _2* bullet text, two step indent  .fi @@ -1345,6 +1352,7 @@ Numbered List (not to be confused with headings/titles, (document structure))  .nf    # numbered list                numbered list 1., 2., 3, etc. +.BR    _# numbered list numbered list indented a., b., c., d., etc.  .fi @@ -1390,6 +1398,7 @@ normal text[^12] continues  .nf    normal text ~{* unnumbered asterisk footnote/endnote, insert multiple asterisks if required }~ continues +.BR    normal text ~{** another unnumbered asterisk footnote/endnote }~ continues  .fi @@ -1397,10 +1406,11 @@ normal text[^12] continues  .B resulting output:  .BR -normal text \ [^*] continues +normal text [^*] continues  .BR -normal text \ [^**] continues +normal text [^**] continues +  .BR  .B markup example: @@ -1408,6 +1418,7 @@ normal text \ [^**] continues  .nf    normal text ~[* \ editors \ notes, \ numbered \ asterisk \ footnote/endnote \ series \ ]~ continues +.BR    normal text ~[+ \ editors \ notes, \ numbered \ asterisk \ footnote/endnote \ series \ ]~ continues  .fi @@ -1415,19 +1426,21 @@ normal text \ [^**] continues  .B resulting output:  .BR -normal text \ [^*3] continues +normal text [^*3] continues  .BR -normal text \ [^+2] continues +normal text [^+2] continues +  .BR  .B Alternative endnote pair notation for footnotes/endnotes:  .nf -.nf    % note the endnote marker \"~^\" +.BR    normal text~^ continues +.BR    ^~ endnote text following the paragraph in which the marker occurs  .fi @@ -1470,6 +1483,7 @@ An escaped url without decoration  .nf    normal text http://www.jus.uio.no/sisu continues +.BR    deb http://www.jus.uio.no/sisu/archive unstable main non\-free  .fi @@ -1492,6 +1506,7 @@ blocks are discussed later in this document  .nf    deb http://www.jus.uio.no/sisu/archive unstable main non\-free +.BR    deb\-src http://www.jus.uio.no/sisu/archive unstable main non\-free  .fi @@ -1531,7 +1546,7 @@ automatically as a footnote  .B resulting output:  .BR -about SiSU <http://www.jus.uio.no/sisu/> \ [^13] markup +about SiSU <http://www.jus.uio.no/sisu/> [^13] markup  .SH  9.5.3 LINKING IMAGES @@ -1541,11 +1556,19 @@ about SiSU <http://www.jus.uio.no/sisu/> \ [^13] markup  .nf -     [ tux.png ] +     \ [ tux.png ] +.BR    % various url linked images -     [ tux.png ] -     [ GnuDebianLinuxRubyBetterWay.png ] +.BR +     \ [ tux.png ] +.BR +.BR +     \ [ GnuDebianLinuxRubyBetterWay.png ] +.BR +.BR    {~^ ruby_logo.png \"Ruby\" }http://www.ruby\-lang.org/en/ +.BR +.BR  .fi  .BR @@ -1570,7 +1593,10 @@ and Ruby\" <http://www.jus.uio.no/sisu/>  .nf    {~^ \ [text \ to \ link] }http://url.org +.BR +.BR    % maps to: { \ [text \ to \ link] }http://url.org ~{ http://url.org }~ +.BR    % which produces hyper\-linked text within a document/paragraph, with an endnote providing the url for the text location used in the hyperlink  .fi @@ -1599,12 +1625,19 @@ Tables may be prepared in two either of two forms  .nf    table{ c3; 40; 30; 30; +.BR    This is a table +.BR    this would become column two of row one +.BR    column three of row one is here +.BR    And here begins another row +.BR    column two of row two +.BR    column three of row two, and so on +.BR    }table  .fi @@ -1624,13 +1657,21 @@ information in each column  .nf    !_ Table 3.1: Contributors to Wikipedia, January 2001 \- June 2005 +.BR    {table~h 24; 12; 12; 12; 12; 12; 12;} +.BR                                    |Jan. 2001|Jan. 2002|Jan. 2003|Jan. 2004|July 2004|June 2006 +.BR    Contributors*                   |       10|      472|    2,188|    9,653|   25,011|   48,721 +.BR    Active contributors**           |        9|      212|      846|    3,228|    8,442|   16,945 +.BR    Very active contributors***     |        0|       31|      190|      692|    1,639|    3,016 +.BR    No. of English language articles|       25|   16,000|  101,000|  190,000|  320,000|  630,000 +.BR    No. of articles, all languages  |       25|   19,000|  138,000|  490,000|  862,000|1,600,000 +.BR    \\* Contributed at least ten times; \\** at least 5 times in last month; \\*\** more than 100 times in last month.  .fi @@ -1655,8 +1696,11 @@ than 100 times in last month.  .nf    poem{ +.BR      Your poem here +.BR    }poem +.BR    Each verse in a poem is given a separate object number.  .fi @@ -1666,50 +1710,95 @@ than 100 times in last month.  .nf    poem{ +.BR                        \'Fury said to a +.BR                       mouse, That he +.BR                     met in the +.BR                   house, +.BR                \"Let us +.BR                  both go to +.BR                    law:  I will +.BR                      prosecute +.BR                        YOU.  \-\-Come, +.BR                           I\'ll take no +.BR                            denial; We +.BR                         must have a +.BR                     trial:  For +.BR                  really this +.BR               morning I\'ve +.BR              nothing +.BR             to do.\" +.BR               Said the +.BR                 mouse to the +.BR                   cur, \"Such +.BR                     a trial, +.BR                       dear Sir, +.BR                             With +.BR                         no jury +.BR                      or judge, +.BR                    would be +.BR                  wasting +.BR                 our +.BR                  breath.\" +.BR                   \"I\'ll be +.BR                     judge, I\'ll +.BR                       be jury,\" +.BR                             Said +.BR                        cunning +.BR                          old Fury: +.BR                         \"I\'ll +.BR                          try the +.BR                             whole +.BR                              cause, +.BR                                 and +.BR                            condemn +.BR                           you +.BR                          to +.BR                           death.\"\' +.BR    }poem  .fi @@ -1718,93 +1807,93 @@ than 100 times in last month.                      \'Fury said to a -.P +.BR                     mouse, That he -.P +.BR                   met in the -.P +.BR                 house, -.P +.BR              \"Let us -.P +.BR                both go to -.P +.BR                  law:  I will -.P +.BR                    prosecute -.P +.BR                      YOU.  \-\-Come, -.P +.BR                         I\'ll take no -.P +.BR                          denial; We -.P +.BR                       must have a -.P +.BR                   trial:  For -.P +.BR                really this -.P +.BR             morning I\'ve -.P +.BR            nothing -.P +.BR           to do.\" -.P +.BR             Said the -.P +.BR               mouse to the -.P +.BR                 cur, \"Such -.P +.BR                   a trial, -.P +.BR                     dear Sir, -.P +.BR                           With -.P +.BR                       no jury -.P +.BR                    or judge, -.P +.BR                  would be -.P +.BR                wasting -.P +.BR               our -.P +.BR                breath.\" -.P +.BR                 \"I\'ll be -.P +.BR                   judge, I\'ll -.P +.BR                     be jury,\" -.P +.BR                           Said -.P +.BR                      cunning -.P +.BR                        old Fury: -.P +.BR                       \"I\'ll -.P +.BR                        try the -.P +.BR                           whole -.P +.BR                            cause, -.P +.BR                               and -.P +.BR                          condemn -.P +.BR                         you -.P +.BR                        to -.P +.BR                         death.\"\' -.P +.BR  .SH  9.6.3 GROUP @@ -1815,8 +1904,11 @@ than 100 times in last month.  .nf    group{ +.BR      Your grouped text here +.BR    }group +.BR    A group is treated as an object and given a single object number.  .fi @@ -1826,50 +1918,95 @@ than 100 times in last month.  .nf    group{ +.BR                        \'Fury said to a +.BR                       mouse, That he +.BR                     met in the +.BR                   house, +.BR                \"Let us +.BR                  both go to +.BR                    law:  I will +.BR                      prosecute +.BR                        YOU.  \-\-Come, +.BR                           I\'ll take no +.BR                            denial; We +.BR                         must have a +.BR                     trial:  For +.BR                  really this +.BR               morning I\'ve +.BR              nothing +.BR             to do.\" +.BR               Said the +.BR                 mouse to the +.BR                   cur, \"Such +.BR                     a trial, +.BR                       dear Sir, +.BR                             With +.BR                         no jury +.BR                      or judge, +.BR                    would be +.BR                  wasting +.BR                 our +.BR                  breath.\" +.BR                   \"I\'ll be +.BR                     judge, I\'ll +.BR                       be jury,\" +.BR                             Said +.BR                        cunning +.BR                          old Fury: +.BR                         \"I\'ll +.BR                          try the +.BR                             whole +.BR                              cause, +.BR                                 and +.BR                            condemn +.BR                           you +.BR                          to +.BR                           death.\"\' +.BR    }group  .fi @@ -1878,93 +2015,93 @@ than 100 times in last month.                      \'Fury said to a -.P +.BR                     mouse, That he -.P +.BR                   met in the -.P +.BR                 house, -.P +.BR              \"Let us -.P +.BR                both go to -.P +.BR                  law:  I will -.P +.BR                    prosecute -.P +.BR                      YOU.  \-\-Come, -.P +.BR                         I\'ll take no -.P +.BR                          denial; We -.P +.BR                       must have a -.P +.BR                   trial:  For -.P +.BR                really this -.P +.BR             morning I\'ve -.P +.BR            nothing -.P +.BR           to do.\" -.P +.BR             Said the -.P +.BR               mouse to the -.P +.BR                 cur, \"Such -.P +.BR                   a trial, -.P +.BR                     dear Sir, -.P +.BR                           With -.P +.BR                       no jury -.P +.BR                    or judge, -.P +.BR                  would be -.P +.BR                wasting -.P +.BR               our -.P +.BR                breath.\" -.P +.BR                 \"I\'ll be -.P +.BR                   judge, I\'ll -.P +.BR                     be jury,\" -.P +.BR                           Said -.P +.BR                      cunning -.P +.BR                        old Fury: -.P +.BR                       \"I\'ll -.P +.BR                        try the -.P +.BR                           whole -.P +.BR                            cause, -.P +.BR                               and -.P +.BR                          condemn -.P +.BR                         you -.P +.BR                        to -.P +.BR                         death.\"\' -.P +.BR  .SH  9.6.4 CODE @@ -1977,7 +2114,7 @@ markup. You cannot however use code tags to escape code tags. They are  however used in the same way as group or poem tags.  .BR -A code\-block is treated as an object and given a single object number. \ [an \ +A code\-block is treated as an object and given a single object number. [an \  option \ to \ number \ each \ line \ of \ code \ may \ be \ considered \ at \  some \ later \ time] @@ -1987,48 +2124,91 @@ some \ later \ time]  .nf                        \'Fury said to a +.BR                       mouse, That he +.BR                     met in the +.BR                   house, +.BR                \"Let us +.BR                  both go to +.BR                    law:  I will +.BR                      prosecute +.BR                        YOU.  \-\-Come, +.BR                           I\'ll take no +.BR                            denial; We +.BR                         must have a +.BR                     trial:  For +.BR                  really this +.BR               morning I\'ve +.BR              nothing +.BR             to do.\" +.BR               Said the +.BR                 mouse to the +.BR                   cur, \"Such +.BR                     a trial, +.BR                       dear Sir, +.BR                             With +.BR                         no jury +.BR                      or judge, +.BR                    would be +.BR                  wasting +.BR                 our +.BR                  breath.\" +.BR                   \"I\'ll be +.BR                     judge, I\'ll +.BR                       be jury,\" +.BR                             Said +.BR                        cunning +.BR                          old Fury: +.BR                         \"I\'ll +.BR                          try the +.BR                             whole +.BR                              cause, +.BR                                 and +.BR                            condemn +.BR                           you +.BR                          to +.BR                           death.\"\'  .fi @@ -2061,6 +2241,7 @@ basic markup for importing a document into a master document  .nf    << filename1.sst +.BR    << filename2.ssi  .fi @@ -2073,8 +2254,11 @@ documents under consideration, and occasionally supported have been.  .nf    << filename.ssi +.BR    <<{filename.ssi} +.BR    % using textlink alternatives +.BR    << |filename.ssi|@|^|  .fi @@ -2091,7 +2275,7 @@ MARKUP SYNTAX HISTORY  were changed at 0.37  .BR -* sisu \-\-query=[sisu \ version \ \ [0.38] or \'history] +* sisu \-\-query=[sisu \ version \ [0.38] or \'history]  .BR  provides a short history of changes to @@ -2103,7 +2287,7 @@ markup  (2007w34/4)  .B SiSU  0.57 is the same as 0.42 with the introduction of some a shortcut to use the -headers @title and @creator in the first heading \ [expanded \ using \ the \ +headers @title and @creator in the first heading [expanded \ using \ the \  contents \ of \ the \ headers \ @title: \ and \ @author:] @@ -2130,7 +2314,7 @@ or, backward compatible using the comment marker:  .BR  variations include \'  .B SiSU -(text|master|insert) \ [version]\' and \'sisu\-[version]\' +(text|master|insert) [version]\' and \'sisu\-[version]\'  .BR  .B 0.51 @@ -2237,7 +2421,9 @@ this is captured by the following file \'rename\' instruction:  .nf    rename \'s/\.s[123]$/\.sst/\' *.s{1,2,3} +.BR    rename \'s/\.r[123]$/\.ssm/\' *.r{1,2,3} +.BR    rename \'s/\.si$/\.ssi/\' *.si  .fi @@ -2266,7 +2452,7 @@ relied upon  .BR  .B 0.16  (2005w25/2) substantial changes introduced to make markup cleaner, header -0~title type, and headings \ [1\-6]~ introduced, also percentage sign (%) at +0~title type, and headings [1\-6]~ introduced, also percentage sign (%) at  start of a text line as comment marker  .BR @@ -2318,7 +2504,7 @@ located locally or on a remote server for which a url is provided.  source markup can be shared with the command:  .BR -  sisu \-s \ [filename] +  sisu \-s [filename]  .SH  12.1.1 SISU TEXT \- REGULAR FILES (.SST) @@ -2363,7 +2549,7 @@ contain other documents.  .BR  Note: a secondary file of the composite document is built prior to processing -with the same prefix and the suffix \._sst \ [^16] +with the same prefix and the suffix \._sst [^16]  .BR  <http://www.jus.uio.no/sisu/sisu_markup> @@ -2416,7 +2602,7 @@ documents.  The command to create a sisupod is:  .BR -  sisu \-S \ [filename] +  sisu \-S [filename]  .BR  Alternatively, make a pod of the contents of a whole directory: @@ -2452,28 +2638,26 @@ incomplete and should be handled with care.  .B convert from sst to simple xml representations (sax, dom and node):  .BR -  sisu \-\-to\-sax \ [filename/wildcard] or sisu \-\-to\-sxs \ -  [filename/wildcard] +  sisu \-\-to\-sax [filename/wildcard] or sisu \-\-to\-sxs [filename/wildcard]  .BR -  sisu \-\-to\-dom \ [filename/wildcard] or sisu \-\-to\-sxd \ -  [filename/wildcard] +  sisu \-\-to\-dom [filename/wildcard] or sisu \-\-to\-sxd [filename/wildcard]  .BR -  sisu \-\-to\-node \ [filename/wildcard] or sisu \-\-to\-sxn \ -  [filename/wildcard] +  sisu \-\-to\-node [filename/wildcard] or sisu \-\-to\-sxn [filename/wildcard] +  .BR  .B convert to sst from any sisu xml representation (sax, dom and node):  .BR -  sisu \-\-from\-xml2sst \ [filename/wildcard \ \ [.sxs.xml,.sxd.xml,sxn.xml]] +  sisu \-\-from\-xml2sst [filename/wildcard \ [.sxs.xml,.sxd.xml,sxn.xml]]  .BR  or the same:  .BR -  sisu \-\-from\-sxml \ [filename/wildcard \ \ [.sxs.xml,.sxd.xml,sxn.xml]] +  sisu \-\-from\-sxml [filename/wildcard \ [.sxs.xml,.sxd.xml,sxn.xml]]  .SH  13.1.1 XML SAX REPRESENTATION @@ -2482,20 +2666,19 @@ or the same:  To convert from sst to simple xml (sax) representation:  .BR -  sisu \-\-to\-sax \ [filename/wildcard] or sisu \-\-to\-sxs \ -  [filename/wildcard] +  sisu \-\-to\-sax [filename/wildcard] or sisu \-\-to\-sxs [filename/wildcard]  .BR  To convert from any sisu xml representation back to sst  .BR -  sisu \-\-from\-xml2sst \ [filename/wildcard \ \ [.sxs.xml,.sxd.xml,sxn.xml]] +  sisu \-\-from\-xml2sst [filename/wildcard \ [.sxs.xml,.sxd.xml,sxn.xml]]  .BR  or the same:  .BR -  sisu \-\-from\-sxml \ [filename/wildcard \ \ [.sxs.xml,.sxd.xml,sxn.xml]] +  sisu \-\-from\-sxml [filename/wildcard \ [.sxs.xml,.sxd.xml,sxn.xml]]  .SH  13.1.2 XML DOM REPRESENTATION @@ -2504,20 +2687,19 @@ or the same:  To convert from sst to simple xml (dom) representation:  .BR -  sisu \-\-to\-dom \ [filename/wildcard] or sisu \-\-to\-sxd \ -  [filename/wildcard] +  sisu \-\-to\-dom [filename/wildcard] or sisu \-\-to\-sxd [filename/wildcard]  .BR  To convert from any sisu xml representation back to sst  .BR -  sisu \-\-from\-xml2sst \ [filename/wildcard \ \ [.sxs.xml,.sxd.xml,sxn.xml]] +  sisu \-\-from\-xml2sst [filename/wildcard \ [.sxs.xml,.sxd.xml,sxn.xml]]  .BR  or the same:  .BR -  sisu \-\-from\-sxml \ [filename/wildcard \ \ [.sxs.xml,.sxd.xml,sxn.xml]] +  sisu \-\-from\-sxml [filename/wildcard \ [.sxs.xml,.sxd.xml,sxn.xml]]  .SH  13.1.3 XML NODE REPRESENTATION @@ -2526,20 +2708,19 @@ or the same:  To convert from sst to simple xml (node) representation:  .BR -  sisu \-\-to\-node \ [filename/wildcard] or sisu \-\-to\-sxn \ -  [filename/wildcard] +  sisu \-\-to\-node [filename/wildcard] or sisu \-\-to\-sxn [filename/wildcard]  .BR  To convert from any sisu xml representation back to sst  .BR -  sisu \-\-from\-xml2sst \ [filename/wildcard \ \ [.sxs.xml,.sxd.xml,sxn.xml]] +  sisu \-\-from\-xml2sst [filename/wildcard \ [.sxs.xml,.sxd.xml,sxn.xml]]  .BR  or the same:  .BR -  sisu \-\-from\-sxml \ [filename/wildcard \ \ [.sxs.xml,.sxd.xml,sxn.xml]] +  sisu \-\-from\-sxml [filename/wildcard \ [.sxs.xml,.sxd.xml,sxn.xml]]  .SH  14. CONFIGURATION @@ -2587,7 +2768,7 @@ resource configuration is determined by looking at the following files if  they exist:  .BR -  \./_sisu/sisurc.yml +  ./_sisu/sisurc.yml  .BR    ~/.sisu/sisurc.yml @@ -2620,7 +2801,7 @@ Skins modify the default appearance of document output on a document,  directory, or site wide basis. Skins are looked for in the following locations:  .BR -  \./_sisu/skin +  ./_sisu/skin  .BR    ~/.sisu/skin @@ -2633,13 +2814,13 @@ directory, or site wide basis. Skins are looked for in the following locations:  are the following the default sub\-directories for document skins:  .BR -  \./skin/doc +  ./skin/doc  .BR -  \./skin/dir +  ./skin/dir  .BR -  \./skin/site +  ./skin/site  .BR  A skin is placed in the appropriate directory and the file named skin_[name].rb @@ -2838,16 +3019,27 @@ skin_poems.rb  .nf      class Home +.BR        def homepage +.BR          # place the html content of your homepage here, this will become index.html +.BR          <<HOME <html> +.BR    <head></head> +.BR    <doc> +.BR    <p>this is my new homepage.</p> +.BR    </doc> +.BR    </html> +.BR    HOME +.BR        end +.BR      end  .fi @@ -2991,10 +3183,10 @@ to populate a postgresql database, this being part of  22.3 SYNOPSIS  .BR -  sisu \-D \ [instruction] \ [filename/wildcard \ if \ required] +  sisu \-D [instruction] [filename/wildcard \ if \ required]  .BR -  sisu \-D \-\-pg \-\-[instruction] \ [filename/wildcard \ if \ required] +  sisu \-D \-\-pg \-\-[instruction] [filename/wildcard \ if \ required]  .SH  22.4 COMMANDS @@ -3013,46 +3205,43 @@ may be used interchangeably.  22.4.1 CREATE AND DESTROY DATABASE  .TP -.B \ \-\-pgsql \ \-\-createall -\ initial \ step, \ creates \ required \ relations \ (tables, \ indexes) \ in -\ existing \ (postgresql) \ database \ (a \ database \ should \ be \ created \ -manually \ and \ given \ the \ same \ name \ as \ working \ directory, \ as \ -requested) \ (rb.dbi) \ +.B \-\-pgsql \-\-createall +initial step, creates required relations (tables, indexes) in existing +(postgresql) database (a database should be created manually and given the same +name as working directory, as requested) (rb.dbi)  .TP -.B \ sisu \ \-D \ \-\-createdb -\ creates \ database \ where \ no \ database \ existed \ before \ +.B sisu \-D \-\-createdb +creates database where no database existed before  .TP -.B \ sisu \ \-D \ \-\-create -\ creates \ database \ tables \ where \ no \ database \ tables \ existed \ -before \ +.B sisu \-D \-\-create +creates database tables where no database tables existed before  .TP -.B \ sisu \ \-D \ \-\-Dropall -\ destroys \ database \ (including \ all \ its \ content)! \ kills \ data \ -and \ drops \ tables, \ indexes \ and \ database \ associated \ with \ a \ -given \ directory \ (and \ directories \ of \ the \ same \ name). \ +.B sisu \-D \-\-Dropall +destroys database (including all its content)! kills data and drops tables, +indexes and database associated with a given directory (and directories of the +same name).  .TP -.B \ sisu \ \-D \ \-\-recreate -\ destroys \ existing \ database \ and \ builds \ a \ new \ empty \ database -\ structure \ +.B sisu \-D \-\-recreate +destroys existing database and builds a new empty database structure  .SH  22.4.2 IMPORT AND REMOVE DOCUMENTS  .TP -.B \ sisu \ \-D \ \-\-import \ \-v \ \ [filename/wildcard] +.B sisu \-D \-\-import \-v [filename/wildcard]  populates database with the contents of the file. Imports documents(s)  specified to a postgresql database (at an object level).  .TP -.B \ sisu \ \-D \ \-\-update \ \-v \ \ [filename/wildcard] +.B sisu \-D \-\-update \-v [filename/wildcard]  updates file contents in database  .TP -.B \ sisu \ \-D \ \-\-remove \ \-v \ \ [filename/wildcard] +.B sisu \-D \-\-remove \-v [filename/wildcard]  removes specified document from postgresql database.  .SH @@ -3081,10 +3270,10 @@ to populate an sqlite database, this being part of  23.3 SYNOPSIS  .BR -  sisu \-d \ [instruction] \ [filename/wildcard \ if \ required] +  sisu \-d [instruction] [filename/wildcard \ if \ required]  .BR -  sisu \-d \-\-(sqlite|pg) \-\-[instruction] \ [filename/wildcard \ if \ +  sisu \-d \-\-(sqlite|pg) \-\-[instruction] [filename/wildcard \ if \    required]  .SH @@ -3104,46 +3293,43 @@ may be used interchangeably.  23.4.1 CREATE AND DESTROY DATABASE  .TP -.B \ \-\-sqlite \ \-\-createall -\ initial \ step, \ creates \ required \ relations \ (tables, \ indexes) \ in -\ existing \ (sqlite) \ database \ (a \ database \ should \ be \ created \ -manually \ and \ given \ the \ same \ name \ as \ working \ directory, \ as \ -requested) \ (rb.dbi) \ +.B \-\-sqlite \-\-createall +initial step, creates required relations (tables, indexes) in existing +(sqlite) database (a database should be created manually and given the same +name as working directory, as requested) (rb.dbi)  .TP -.B \ sisu \ \-d \ \-\-createdb -\ creates \ database \ where \ no \ database \ existed \ before \ +.B sisu \-d \-\-createdb +creates database where no database existed before  .TP -.B \ sisu \ \-d \ \-\-create -\ creates \ database \ tables \ where \ no \ database \ tables \ existed \ -before \ +.B sisu \-d \-\-create +creates database tables where no database tables existed before  .TP -.B \ sisu \ \-d \ \-\-dropall -\ destroys \ database \ (including \ all \ its \ content)! \ kills \ data \ -and \ drops \ tables, \ indexes \ and \ database \ associated \ with \ a \ -given \ directory \ (and \ directories \ of \ the \ same \ name). \ +.B sisu \-d \-\-dropall +destroys database (including all its content)! kills data and drops tables, +indexes and database associated with a given directory (and directories of the +same name).  .TP -.B \ sisu \ \-d \ \-\-recreate -\ destroys \ existing \ database \ and \ builds \ a \ new \ empty \ database -\ structure \ +.B sisu \-d \-\-recreate +destroys existing database and builds a new empty database structure  .SH  23.4.2 IMPORT AND REMOVE DOCUMENTS  .TP -.B \ sisu \ \-d \ \-\-import \ \-v \ \ [filename/wildcard] +.B sisu \-d \-\-import \-v [filename/wildcard]  populates database with the contents of the file. Imports documents(s)  specified to an sqlite database (at an object level).  .TP -.B \ sisu \ \-d \ \-\-update \ \-v \ \ [filename/wildcard] +.B sisu \-d \-\-update \-v [filename/wildcard]  updates file contents in database  .TP -.B \ sisu \ \-d \ \-\-remove \ \-v \ \ [filename/wildcard] +.B sisu \-d \-\-remove \-v [filename/wildcard]  removes specified document from sqlite database.  .SH @@ -3155,7 +3341,7 @@ removes specified document from sqlite database.  INCLUDING OBJECT CITATION NUMBERING (BACKEND CURRENTLY POSTGRESQL)  .BR -Sample search frontend <http://search.sisudoc.org> \ [^20] A small database and +Sample search frontend <http://search.sisudoc.org> [^20] A small database and  sample query front\-end (search from) that makes use of the citation system,  .I object citation numbering  to demonstrates functionality.[^21] @@ -3176,9 +3362,8 @@ the names of the documents matched along with the objects (paragraphs) that  meet the search criteria.[^22]  .TP -.B \ sisu \ \-F \ \-\-webserv\-webrick -\ builds \ a \ cgi \ web \ search \ frontend \ for \ the \ database \ created -\ +.B sisu \-F \-\-webserv\-webrick +builds a cgi web search frontend for the database created  .BR  The following is feedback on the setup on a machine provided by the help @@ -3190,12 +3375,19 @@ command:  .nf    Postgresql +.BR      user:             ralph +.BR      current db set:   SiSU_sisu +.BR      port:             5432 +.BR      dbi connect:      DBI:Pg:database=SiSU_sisu;port=5432 +.BR    sqlite +.BR      current db set:   /home/ralph/sisu_www/sisu/sisu_sqlite.db +.BR      dbi connect       DBI:SQLite:/home/ralph/sisu_www/sisu/sisu_sqlite.db  .fi @@ -3203,36 +3395,34 @@ command:  Note on databases built  .BR -By default, \ [unless \ otherwise \ specified] databases are built on a -directory basis, from collections of documents within that directory. The name -of the directory you choose to work from is used as the database name, i.e. if -you are working in a directory called /home/ralph/ebook the database SiSU_ebook -is used. \ [otherwise \ a \ manual \ mapping \ for \ the \ collection \ is \ +By default, [unless \ otherwise \ specified] databases are built on a directory +basis, from collections of documents within that directory. The name of the +directory you choose to work from is used as the database name, i.e. if you are +working in a directory called /home/ralph/ebook the database SiSU_ebook is +used. [otherwise \ a \ manual \ mapping \ for \ the \ collection \ is \  necessary]  .SH  24.2 SEARCH FORM  .TP -.B \ sisu \ \-F -\ generates \ a \ sample \ search \ form, \ which \ must \ be \ copied \ to \ -the \ web\-server \ cgi \ directory \ +.B sisu \-F +generates a sample search form, which must be copied to the web\-server cgi +directory  .TP -.B \ sisu \ \-F \ \-\-webserv\-webrick -\ generates \ a \ sample \ search \ form \ for \ use \ with \ the \ webrick \ -server, \ which \ must \ be \ copied \ to \ the \ web\-server \ cgi \ directory -\ +.B sisu \-F \-\-webserv\-webrick +generates a sample search form for use with the webrick server, which must be +copied to the web\-server cgi directory  .TP -.B \ sisu \ \-Fv -\ as \ above, \ and \ provides \ some \ information \ on \ setting \ up \ -hyperestraier \ +.B sisu \-Fv +as above, and provides some information on setting up hyperestraier  .TP -.B \ sisu \ \-W -\ starts \ the \ webrick \ server \ which \ should \ be \ available \ -wherever \ sisu \ is \ properly \ installed \ +.B sisu \-W +starts the webrick server which should be available wherever sisu is properly +installed  .BR  The generated search form must be copied manually to the webserver directory as @@ -3271,7 +3461,7 @@ directory /home/ralph/sisu_www  (A) to generate the index within the webserver directory to be indexed:  .BR -  estcmd gather \-sd \ [index \ name] \ [directory \ path \ to \ index] +  estcmd gather \-sd [index \ name] [directory \ path \ to \ index]  .BR  the following are examples that will need to be tailored according to your @@ -3334,7 +3524,7 @@ rune along the following lines:    sudo cp \-v /usr/share/hyperestraier/estseek.* /usr/lib/cgi\-bin  .BR -  \ [see \ estraier \ documentation \ for \ paths] +  [see \ estraier \ documentation \ for \ paths]  .BR  (ii) edit estseek.conf, with attention to the lines starting \'indexname:\' and @@ -3373,13 +3563,13 @@ and try open the url: <http://localhost:8081/cgi\-bin/estseek.cgi>  26.2 SYNOPSIS  .BR -sisu_webrick \ [port] +sisu_webrick [port]  .BR  or  .BR -sisu \-W \ [port] +sisu \-W [port]  .SH  26.3 DESCRIPTION @@ -3404,8 +3594,8 @@ yaml file: ~/.sisu/sisurc.yml a sample of which is provided as  26.4 SUMMARY OF MAN PAGE  .BR -sisu_webrick, may be started on it\'s own with the command: sisu_webrick \ -[port] or using the sisu command with the \-W flag: sisu \-W \ [port] +sisu_webrick, may be started on it\'s own with the command: sisu_webrick [port] +or using the sisu command with the \-W flag: sisu \-W [port]  .BR  where no port is given and settings are unchanged the default port is 8081 @@ -3414,7 +3604,7 @@ where no port is given and settings are unchanged the default port is 8081  26.5 DOCUMENT PROCESSING COMMAND FLAGS  .BR -sisu \-W \ [port] starts +sisu \-W [port] starts  .B Ruby  Webrick web\-server, serving  .B SiSU @@ -3540,7 +3730,7 @@ may be used in conjunction with other processing flags, e.g.  28.1 COMMANDS  .TP -.B \ \-R \ \ [filename/wildcard] +.B \-R [filename/wildcard]  copies sisu output files to remote host using rsync. This requires that  sisurc.yml has been provided with information on hostname and username, and  that you have your \"keys\" and ssh agent in place. Note the behavior of rsync @@ -3549,7 +3739,7 @@ different if \-R is used with other flags from if used alone. Alone the rsync  \-R is used together with other flags, it is not). Also see \-r  .TP -.B \ \-r \ \ [filename/wildcard] +.B \-r [filename/wildcard]  copies sisu output files to remote host using scp. This requires that  sisurc.yml has been provided with information on hostname and username, and  that you have your \"keys\" and ssh agent in place. Also see \-R @@ -3600,6 +3790,7 @@ Sid and testing archives (and possibly Ubuntu), assuming your  .nf      aptitude update +.BR      aptitude install sisu\-complete  .fi @@ -3610,8 +3801,11 @@ markup samples:  .nf    #/etc/apt/sources.list +.BR      deb http://ftp.fi.debian.org/debian/ unstable main non\-free contrib +.BR      deb\-src http://ftp.fi.debian.org/debian/ unstable main non\-free contrib +.BR    d  .fi @@ -3621,6 +3815,7 @@ The aptitude commands become:  .nf      aptitude update +.BR      aptitude install sisu\-complete sisu\-markup\-samples  .fi @@ -3635,7 +3830,9 @@ archives, they will be available by adding the following to your  .nf    #/etc/apt/sources.list +.BR      deb http://www.jus.uio.no/sisu/archive unstable main non\-free +.BR      deb\-src http://www.jus.uio.no/sisu/archive unstable main non\-free  .fi @@ -3645,6 +3842,7 @@ repeat the aptitude commands  .nf      aptitude update +.BR      aptitude install sisu\-complete sisu\-markup\-samples  .fi @@ -3670,7 +3868,7 @@ They may be downloaded from:  as root type:  .BR -  rpm \-i \ [rpm \ package \ name] +  rpm \-i [rpm \ package \ name]  .SH  30.1.3 INSTALLATION FROM SOURCE @@ -3719,8 +3917,11 @@ as root type:  .nf        ruby setup.rb config +.BR        ruby setup.rb setup +.BR        #[and \ as \ root:] +.BR        ruby setup.rb install  .fi @@ -3888,13 +4089,13 @@ The man pages are also available online, though not always kept as up to date  as within the package itself:  .BR -* sisu.1 <http://www.jus.uio.no/sisu/man/sisu.1> \ [^24] +* sisu.1 <http://www.jus.uio.no/sisu/man/sisu.1> [^24]  .BR -* sisu.8 <http://www.jus.uio.no/sisu/man/sisu.8> \ [^25] +* sisu.8 <http://www.jus.uio.no/sisu/man/sisu.8> [^25]  .BR -* man directory <http://www.jus.uio.no/sisu/man> \ [^26] +* man directory <http://www.jus.uio.no/sisu/man> [^26]  .SH  30.3.2 BUILT IN HELP @@ -4055,12 +4256,10 @@ comments: assumes dark background; no display line\-wrap      ~/.kde/share/apps/katepart/syntax  .BR -  \ [settings::configure \ kate::{highlighting,filetypes}] +  [settings::configure \ kate::{highlighting,filetypes}]  .BR -  \ [tools::highlighting::{markup,scripts}:: -.B \ SiSU -] +  [tools::highlighting::{markup,scripts}:: \ .B \ SiSU \ ]  .BR  * nedit <http://www.nedit.org> @@ -4072,7 +4271,7 @@ comments: assumes dark background; no display line\-wrap    nedit \-import sisu_nedit.pats  .BR -  status: a very clumsy first attempt \ [not \ really \ done] +  status: a very clumsy first attempt [not \ really \ done]  .BR    comments: this editor features display line wrap @@ -4093,7 +4292,7 @@ comments: assumes dark background; no display line\-wrap      (require \'sisu\-mode.el)  .BR -  \ [not \ done \ / \ not \ yet \ included] +  [not \ done \ / \ not \ yet \ included]  .BR  * vim & gvim <http://www.vim.org> @@ -4116,11 +4315,9 @@ comments: assumes dark background; no display line\-wrap  NOTE:  .BR -[ -.B \ SiSU -\ parses \ files \ with \ long \ lines \ or \ line \ breaks, \ but, \ display -\ linewrap \ (without \ line\-breaks) \ is \ a \ convenient \ editor \ feature -\ to \ have \ for \ sisu \ markup] +[ \ .B \ SiSU \ parses \ files \ with \ long \ lines \ or \ line \ breaks, \ +but, \ display \ linewrap \ (without \ line\-breaks) \ is \ a \ convenient \ +editor \ feature \ to \ have \ for \ sisu \ markup]  .SH  32. HOW DOES SISU WORK? @@ -4159,9 +4356,8 @@ headers are optional.  .BR  * markup is easily readable/parsable by the human eye, (basic markup is simpler -and more sparse than the most basic HTML), \ [this \ may \ also \ be \ -converted \ to \ XML \ representations \ of \ the \ same \ input/source \ -document]. +and more sparse than the most basic HTML), [this \ may \ also \ be \ converted +\ to \ XML \ representations \ of \ the \ same \ input/source \ document].  .BR  * markup defines document structure (this may be done once in a header @@ -4173,7 +4369,7 @@ may also contain processing instructions.  .B SiSU  markup is primarily an abstraction of document structure and document  metadata to permit taking advantage of the basic strengths of existing -alternative practical standard ways of representing documents \ [be \ that \ +alternative practical standard ways of representing documents [be \ that \  browser \ viewing, \ paper \ publication, \ sql \ search \ etc.] (html, xml,  odf, latex, pdf, sql) @@ -4232,8 +4428,8 @@ level (roughly headings, paragraphs, verse, tables) and become searchable with  that degree of granularity, the output information provides the  object/paragraph numbers which are relevant across all generated outputs; it is  also possible to look at just the matching paragraphs of the documents in the -database; \ [output \ indexing \ also \ work \ well \ with \ search \ indexing -\ tools \ like \ hyperestraier]. +database; [output \ indexing \ also \ work \ well \ with \ search \ indexing \ +tools \ like \ hyperestraier].  .BR  * long term maintainability of document collections in a world of changing @@ -4536,17 +4732,13 @@ Document Manifest @ <http://sisudoc.org/sisu_manual/sisu/sisu_manifest.html>  .BR  .I DC tags included with this document are provided here. -.BR  DC Title:  .I SiSU \- Manual -.BR  DC Creator:  .I Ralph Amissah -.BR  DC Rights: -.I Copyright (C) Ralph Amissah 2008, part of SiSU documentation, License GPL  3  .BR @@ -4586,7 +4778,7 @@ Filetype:  .BR  Sourcefile Digest, MD5(sisu.ssm.sst)= -.I 7568e6bc171256672e0820a333b37459 +.I 7fbab3b7c0fd0ed2e128585c2982c5c8  .BR  Skin_Digest: MD5(skin_sisu_manual.rb)= @@ -4597,17 +4789,17 @@ Skin_Digest: MD5(skin_sisu_manual.rb)=  .BR  Document (metaverse) last generated: -.I Thu May 22 21:53:23 \-0400 2008 +.I Mon Jul 21 02:54:34 \-0400 2008  .BR  Generated by:  .I SiSU -.I 0.67.0 -of 2008w20/4 (2008\-05\-22) +.I 0.68.0 +of 2008w29/1 (2008\-07\-21)  .BR  Ruby version: -.I ruby 1.8.6 (2008\-03\-03 patchlevel 114) \ [i486\-linux] +.I  ruby 1.8.7 (2008\-06\-20 patchlevel 22) \ [i486\-linux]  .TP  .BI 1. @@ -4630,7 +4822,7 @@ code-blocks  .BI 5.  Specification submitted by Adobe to ISO to become a full open ISO  specification - <http://www.linux-watch.com/news/NS7542722606.html> +<http://www.linux-watch.com/news/NS7542722606.html>  .TP  .BI 6.  ISO/IEC 26300:2006 @@ -4683,7 +4875,7 @@ editors notes, numbered asterisk footnote/endnote series  .TP  .BI 15.  Table from the Wealth of Networks by Yochai Benkler - <http://www.jus.uio.no/sisu/the_wealth_of_networks.yochai_benkler> +<http://www.jus.uio.no/sisu/the_wealth_of_networks.yochai_benkler>  .TP  .BI 16.  \.ssc (for composite) is under consideration but \._sst makes clear that this @@ -4700,12 +4892,12 @@ and this behaviour could be reinstated.  .TP  .BI 18.  <http://www.postgresql.org/> - <http://advocacy.postgresql.org/> - <http://en.wikipedia.org/wiki/Postgresql> +<http://advocacy.postgresql.org/> +<http://en.wikipedia.org/wiki/Postgresql>  .TP  .BI 19.  <http://www.hwaci.com/sw/sqlite/> - <http://en.wikipedia.org/wiki/Sqlite> +<http://en.wikipedia.org/wiki/Sqlite>  .TP  .BI 20.  <http://search.sisudoc.org> @@ -4736,9 +4928,11 @@ There is nothing to stop MySQL support being added in future.  <http://www.jus.uio.no/sisu/man>  .TP  .BI 27. -the  \.B Debian -Free Software guidelines require that everything distributed within  \.B Debian -can be changed - and the documents are authors\' works that while freely +the +.B Debian +Free Software guidelines require that everything distributed within +.B Debian +can be changed - and the documents are authors' works that while freely  distributable are not freely changeable.  .TP  .BI 28. @@ -4758,10 +4952,10 @@ pdf: <http://www.jus.uio.no/sisu/sisu/landscape.pdf>  at: <http://www.jus.uio.no/sisu>  .TP  .TP -* Generated by: SiSU 0.67.0 of 2008w20/4 (2008-05-22) +* Generated by: SiSU 0.68.0 of 2008w29/1 (2008-07-21)  .TP -* Ruby version: ruby 1.8.6 (2008-03-03 patchlevel 114) [i486-linux] +* Ruby version: ruby 1.8.7 (2008-06-20 patchlevel 22) [i486-linux]  .TP -* Last Generated on: Thu May 22 21:53:23 -0400 2008 +* Last Generated on: Mon Jul 21 02:54:35 -0400 2008  .TP  * SiSU http://www.jus.uio.no/sisu | 
