# encoding: utf-8
=begin
* Name: SiSU
** Description: documents, structuring, processing, publishing, search
*** common file for xml generation
** Author: Ralph Amissah
** Copyright: (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016 Ralph Amissah,
All Rights Reserved.
** License: GPL 3 or later:
SiSU, a framework for document structuring, publishing and search
Copyright (C) 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/licenses/gpl.html]
** 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]
** Git
[http://git.sisudoc.org/gitweb/?p=code/sisu.git;a=summary]
[http://git.sisudoc.org/gitweb/?p=code/sisu.git;a=blob;f=lib/sisu/xml_shared.rb;hb=HEAD]
** Ralph Amissah
[ralph@amissah.com]
[ralph.amissah@gmail.com]
=end
module SiSU_XML_Munge
require_relative 'xml_parts' # xml_parts.rb
class Trans
include SiSU_Parts_XML
def initialize(md)
@md=md
@sys=SiSU_Env::SystemCall.new
@dir=SiSU_Env::InfoEnv.new(@md.fns)
if @md.sem_tag
@ab ||=semantic_tags.default
end
end
def semantic_tags
def default
{
pub: 'publication',
conv: 'convention',
vol: 'volume',
pg: 'page',
cty: 'city',
org: 'organization',
uni: 'university',
dept: 'department',
fac: 'faculty',
inst: 'institute',
co: 'company',
com: 'company',
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
def char_enc #character encode
def utf8(dob='')
if @sys.locale =~/utf-?8/i # instead ucs for utf8 # String#encode Iñtërnâtiônàlizætiøn
str=if defined? dob.obj then dob.obj
elsif dob.is_a?(String) then dob
end
if str
#¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûü
#¢£¥§©ª«®°±²³µ¶¹º»¼½¾×÷
str=str.gsub(//um,'>'). # '>' # >
gsub(/¢/um,'¢'). # '¢' # ¢
gsub(/£/um,'£'). # '£' # £
gsub(/¥/um,'¥'). # '¥' # ¥
gsub(/§/um,'§'). # '§' # §
gsub(/©/um,'©'). # '©' # ©
gsub(/ª/um,'ª'). # 'ª' # ª
gsub(/«/um,'«'). # '«' # «
gsub(/®/um,'®'). # '®' # ®
gsub(/°/um,'°'). # '°' # °
gsub(/±/um,'±'). # '±' # ±
gsub(/²/um,'²'). # '²' # ²
gsub(/³/um,'³'). # '³' # ³
gsub(/µ/um,'µ'). # 'µ' # µ
gsub(/¶/um,'¶'). # '¶' # ¶
gsub(/¹/um,'¹'). # '¹' # ¹
gsub(/º/um,'º'). # 'º' # º
gsub(/»/um,'»'). # '»' # »
gsub(/¼/um,'¼'). # '¼' # ¼
gsub(/½/um,'½'). # '½' # ½
gsub(/¾/um,'¾'). # '¾' # ¾
gsub(/×/um,'×'). # '×' # ×
gsub(/÷/um,'÷'). # '÷' # ÷
gsub(/¿/um,'¿'). # '¿' # ¿
gsub(/À/um,'À'). # 'À' # À
gsub(/Á/um,'Á'). # 'Á' # Á
gsub(/Â/um,'Â'). # 'Â' # Â
gsub(/Ã/um,'Ã'). # 'Ã' # Ã
gsub(/Ä/um,'Ä'). # 'Ä' # Ä
gsub(/Å/um,'Å'). # 'Å' # Å
gsub(/Æ/um,'Æ'). # 'Æ' # Æ
gsub(/Ç/um,'Ç'). # 'Ç' # Ç
gsub(/È/um,'È'). # 'È' # È
gsub(/É/um,'É'). # 'É' # É
gsub(/Ê/um,'Ê'). # 'Ê' # Ê
gsub(/Ë/um,'Ë'). # 'Ë' # Ë
gsub(/Ì/um,'Ì'). # 'Ì' # Ì
gsub(/Í/um,'Í'). # 'Í' # Í
gsub(/Î/um,'Î'). # 'Î' # Î
gsub(/Ï/um,'Ï'). # 'Ï' # Ï
gsub(/Ð/um,'Ð'). # 'Ð' # Ð
gsub(/Ñ/um,'Ñ'). # 'Ñ' # Ñ
gsub(/Ò/um,'Ò'). # 'Ò' # Ò
gsub(/Ó/um,'Ó'). # 'Ó' # Ó
gsub(/Ô/um,'Ô'). # 'Ô' # Ô
gsub(/Õ/um,'Õ'). # 'Õ' # Õ
gsub(/Ö/um,'Ö'). # 'Ö' # Ö
gsub(/Ø/um,'Ø'). # 'Ø' # Ø
gsub(/Ù/um,'Ù'). # 'Ù' # Ù
gsub(/Ú/um,'Ú'). # 'Ú' # Ú
gsub(/Û/um,'Û'). # 'Û' # Û
gsub(/Ü/um,'Ü'). # 'Ü' # Ü
gsub(/Ý/um,'Ý'). # 'Ý' # Ý
gsub(/Þ/um,'Þ'). # 'Þ' # Þ
gsub(/ß/um,'ß'). # 'ß' # ß
gsub(/à/um,'à'). # 'à' # à
gsub(/á/um,'á'). # 'á' # á
gsub(/â/um,'â'). # 'â' # â
gsub(/ã/um,'ã'). # 'ã' # ã
gsub(/ä/um,'ä'). # 'ä' # ä
gsub(/å/um,'å'). # 'å' # å
gsub(/æ/um,'æ'). # 'æ' # æ
gsub(/ç/um,'ç'). # 'ç' # ç
gsub(/è/um,'è'). # 'è' # è
gsub(/é/um,'é'). # '´' # é
gsub(/ê/um,'ê'). # 'ˆ' # ê
gsub(/ë/um,'ë'). # 'ë' # ë
gsub(/ì/um,'ì'). # 'ì' # ì
gsub(/í/um,'í'). # '´' # í
gsub(/î/um,'î'). # 'î' # î
gsub(/ï/um,'ï'). # 'ï' # ï
gsub(/ð/um,'ð'). # 'ð' # ð
gsub(/ñ/um,'ñ'). # 'ñ' # ñ
gsub(/ò/um,'ò'). # 'ò' # ò
gsub(/ó/um,'ó'). # 'ó' # ó
gsub(/ô/um,'ô'). # 'ô' # ô
gsub(/õ/um,'õ'). # 'õ' # õ
gsub(/ö/um,'ö'). # 'ö' # ö
gsub(/ø/um,'ø'). # 'ø' # ø
gsub(/ù/um,'ú'). # 'ù' # ú
gsub(/ú/um,'û'). # 'ú' # û
gsub(/û/um,'ü'). # 'û' # ü
gsub(/ü/um,'ý'). # 'ü' # ý
gsub(/þ/um,'þ'). # 'þ' # þ
gsub(/ÿ/um,'ÿ'). # 'ÿ' # ÿ
gsub(/‘/um,'‘'). # '‘' # ‘
gsub(/’/um,'’'). # '’' # ’
gsub(/“/um,'“'). # “ # “
gsub(/”/um,'”'). # ” # ”
gsub(/–/um,'–'). # – # –
gsub(/—/um,'—'). # — # —
gsub(/∝/um,'∝'). # ∝ # ∝
gsub(/∞/um,'∞'). # ∞ # ∞
gsub(/™/um,'™'). # ™ # ™
gsub(/✠/um,'✠'). # ✗ # ✠
gsub(/ /um,' '). # space identify
gsub(/ /um,' ') # space identify
end
dob=if defined? dob.obj
dob.obj=str
dob
elsif dob.is_a?(String)
str
end
dob
end
end
def html(dob='')
if @sys.locale =~/utf-?8/i # instead ucs for utf8 # String#encode Iñtërnâtiônàlizætiøn
dob.obj=dob.obj.gsub(/ /u,' '). # space identify
gsub(/ /u,' ') # space identify
end
end
self
end
def tidywords(wordlist)
wordlist_new=[]
wordlist.each do |x|
#imperfect solution will not catch all possible cases
x=x.gsub(/&/,'&') unless x =~/&\S+;/
x=x.gsub(/&([A-Z])/,'&\1')
wordlist_new << x
end
wordlist_new
end
def markup(dob='')
wordlist=dob.obj.scan(/&[#0-9a-z]+;|\S+|\n/) #\n needed for tables, check though added 2005w17
dob.obj=tidywords(wordlist).join(' ').strip
unless dob.is==:table
dob.obj=dob.obj.gsub(/#{Mx[:br_line]}/u,'
').
gsub(/#{Mx[:br_paragraph]}/u,'
').
gsub(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,'
')
end
dob.obj=dob.obj.gsub(/#{Mx[:mk_o]}:name#\S+?#{Mx[:mk_c]}/,'').
gsub(/#{Mx[:mk_o]}#([a-zA-Z]+)#{Mx[:mk_c]}/,'&\1;').
gsub(/#{Mx[:mk_o]}(#[0-9]+)#{Mx[:mk_c]}/,'&\1;').
gsub(/(^|#{Mx[:gl_c]}|\s+)<\s+/,'\1< ').gsub(/\s+>(\s+|$)/,' >\1').
#gsub(/#{Mx[:fa_emphasis_o]}(.+?)#{Mx[:fa_emphasis_c]}/,'\1'). #reinstate
gsub(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/m,'\1').
gsub(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/m,'\1').
gsub(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'\1').
gsub(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,'\1').
gsub(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,'\1').
gsub(/#{Mx[:fa_insert_o]}(.+?)#{Mx[:fa_insert_c]}/,'\1').
gsub(/#{Mx[:fa_cite_o]}(.+?)#{Mx[:fa_cite_c]}/,'\1').
gsub(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'\1').
gsub(/#{Mx[:fa_monospace_o]}(.+?)#{Mx[:fa_monospace_c]}/,'\1').
gsub(/<:pb>\s*/,''). #Fix
gsub(/<+[-~]#>+/,'')
if dob.is !=:code
#embeds a red-bullet image -->
dob.obj=dob.obj.gsub(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'\1').
gsub(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'\1').
gsub(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'\1').
gsub(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'\1')
dob.obj=dob.obj.gsub(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,'
') unless dob.is==:table
dob.obj=dob.obj.gsub(/#{Mx[:br_page]}\s*/,'').
gsub(/#{Mx[:br_page_new]}\s*/,'').
gsub(/#{Mx[:br_page_line]}\s*/,'').
gsub(/#{Mx[:pa_non_object_no_heading]}|#{Mx[:pa_non_object_dummy_heading]}/,'').
gsub(/<[-~]#>/,'').
gsub(/href="#{Xx[:segment]}/m,'href="').
gsub(/#{Mx[:lnk_o]}([^#{Mx[:lnk_o]}#{Mx[:lnk_c]}#{Mx[:rel_o]}#{Mx[:rel_c]}]+?)#{Mx[:lnk_c]}#{Mx[:rel_o]}(\.\.\/\S+?)#{Mx[:rel_c]}/,
'\1').
gsub(/#{Mx[:lnk_o]}([^#{Mx[:lnk_o]}#{Mx[:lnk_c]}#{Mx[:rel_o]}#{Mx[:rel_c]}]+?)#{Mx[:lnk_c]}#{Mx[:rel_o]}:(\S+?)#{Mx[:rel_c]}/,
'\1').
gsub(/#{Mx[:lnk_o]}(.+?)#{Mx[:lnk_c]}#{Mx[:rel_o]}(\S+?)#{Mx[:rel_c]}/,
'\1').
gsub(/(?:^|[^_\\])#{Mx[:lnk_o]}[ ]*(\S+?\.(?:jpg|png|gif))[ ]+(\d+)x(\d+)(\s+[^}]+)?#{Mx[:lnk_c]}#{Mx[:url_o]}(\S+?)#{Mx[:url_c]}/,
%{[\\1] \\4}).
gsub(/(?:^|[^_\\])#{Mx[:lnk_o]}[ ]*(\S+?\.(?:jpg|png|gif))([ ]+[^}]+)?#{Mx[:lnk_c]}#{Mx[:url_o]}(\S+?)#{Mx[:url_c]}/,
%{\\1}).
gsub(/(?:^|[^_\\])#{Mx[:lnk_o]}[ ]*(\S+?\.(?:jpg|png|gif))[ ]+(\d+)x(\d+)(\s+[^}]+)?#{Mx[:lnk_c]}image/,
%{[\\1] \\4}).
gsub(/(?:^|[^_\\])#{Mx[:lnk_o]}[ ]*(\S+?\.(?:jpg|png|gif))([ ]+[^}]+)?#{Mx[:lnk_c]}image/,
%{\\1}).
gsub(/#{Mx[:lnk_o]}(.+?)#{Mx[:lnk_c]}#{Mx[:url_o]}(\S+?)#{Mx[:url_c]}/,
'\1'). #watch, compare html_tune
gsub(/#{Mx[:url_o]}(\S+?)#{Mx[:url_c]}/,
%{#{the_url_decoration.xml_open}\\1#{the_url_decoration.xml_close}}).
gsub(/#{Mx[:url_o]}_(\S+?)#{Mx[:url_c]}/,
'\1') #escaped urls not linked, deal with later
else
dob.obj=dob.obj.gsub(//m,'>')
end
if dob.of==:block
dob.obj=dob.obj.gsub(/#{Mx[:gl_bullet]}/,'● ')
end
dob.obj=dob.obj.gsub(/#{Mx[:url_o]}([a-zA-Z0-9._-]+\@\S+?\.[a-zA-Z0-9._-]+)#{Mx[:url_c]}/,
%{#{the_url_decoration.xml_open}\\1#{the_url_decoration.xml_close}}).
gsub(/#{Dx[:url_o]}/,"#{Dx[:url_o_xml]}").
gsub(/#{Dx[:url_c]}/,"#{Dx[:url_c_xml]}").
gsub(/ |#{Mx[:nbsp]}/m,' ').
gsub(/;&([^#]|(?:[^gl][^t]|[^a][^m][^p]|[^n][^b][^s][^p])[^;])/,';&\1') # pattern not to match
dob
end
def markup_light(dob='')
dob.obj=dob.obj.gsub(/\/\{(.+?)\}\//,'\1').
gsub(/[*!]\{(.+?)\}[*!]/,'\1').
gsub(/_\{(.+?)\}_/,'\1').
gsub(/-\{(.+?)\}-/,'\1').
gsub(/
/,'
').
gsub(/<:pb>\s*/,'').
gsub(/<[-~]#>/,'').
gsub(/(^|#{Mx[:gl_c]}|\s)&\s+/,'\1& '). #sort
gsub(/&([^;]{1,5})/,'&\1'). #sort, rough estimate, revisit #WATCH found in node not sax
gsub(/(?:^|[^_\\])#{Mx[:lnk_o]}(\S+?\.(?:png|jpg|gif))[ ]+.+?#{Mx[:lnk_c]}(?:#{Mx[:url_o]}\S+?#{Mx[:url_c]}|image)/,
"#{@md.file.output_path.xml.rel_image}\/\\1").
gsub(/ |#{Mx[:nbsp]}/,' ').
gsub(/;&([^#]|(?:[^gl][^t]|[^a][^m][^p]|[^n][^b][^s][^p])[^;])/,';&\1') # pattern not to match
wordlist=dob.obj.scan(/&[#0-9a-z]+;|\S+|\n/) #\n needed for tables, check though added 2005w17
dob.obj=tidywords(wordlist).join(' ').strip
dob
end
def clean(str)
str=str.gsub(/#{Mx[:gl_o]}(#[0-9]{3})#{Mx[:gl_c]}/u,'&\1;').
gsub(/#{Mx[:gl_o]}#([a-z]{2,4})#{Mx[:gl_c]}/u,'&\1;')
end
def markup_fictionbook(str='',is='')
str=str.gsub(/#{Mx[:en_a_o]}([\d+*]+).+?#{Mx[:en_a_c]}/m,'[\1]').
gsub(/&/,'&'). #sort
gsub(/#{Mx[:mk_o]}#([a-zA-Z]+)#{Mx[:mk_c]}/,'&\1;').
gsub(/(^|#{Mx[:gl_c]}|\s)&\s+/,'\1& '). #sort
gsub(/#{Mx[:mk_o]}(#[0-9]+)#{Mx[:mk_c]}/,'&\1;')
str=str.gsub(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,'
') unless is==:table
str=str.gsub(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'\1').
gsub(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'\1').
gsub(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'\1').
gsub(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,'\1').
gsub(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,'\1').
gsub(/#{Mx[:fa_insert_o]}(.+?)#{Mx[:fa_insert_c]}/,'\1').
gsub(/#{Mx[:fa_cite_o]}(.+?)#{Mx[:fa_cite_c]}/,'\1').
gsub(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'\1').
gsub(/#{Mx[:fa_monospace_o]}(.+?)#{Mx[:fa_monospace_c]}/,'\1'). # tt, kbd
gsub(/#{Mx[:lnk_o]}\s*(\S+?\.(?:png|jpg|gif)).+?#{Mx[:lnk_c]}(?:#{Mx[:url_o]}\S+?#{Mx[:url_c]}|#{Mx[:rel_o]}\S+?#{Mx[:rel_c]}|image)/m,'').
gsub(/#{Mx[:url_o]}(.+?)#{Mx[:url_c]}/,"#{Dx[:url_o]}\\1#{Dx[:url_c]}").
gsub(/#{Mx[:mk_o]}:name#(\S+?)#{Mx[:mk_c]}/,'').
gsub(/#{Mx[:gl_bullet]}/m,'● '). # not available
gsub(/#{Mx[:nbsp]}/,' '). # not available
gsub(/<(p|br)>/,'<\1 />')
clean(str)
end
def markup_docbook(dob='') # work on, initially a copy of fictionbook!
if dob.is !=:code
dob.obj=dob.obj.gsub(/#{Mx[:en_a_o]}(\d+)\s*(.+?)#{Mx[:en_a_c]}/m,'\2').
gsub(/\\\\/,'').
gsub(/&/,'&'). #sort
gsub(/#{Mx[:mk_o]}#([a-zA-Z]+)#{Mx[:mk_c]}/,'&\1;').
gsub(/(^|#{Mx[:gl_c]}|\s)&\s+/,'\1& '). #sort
gsub(/#{Mx[:mk_o]}(#[0-9]+)#{Mx[:mk_c]}/,'&\1;')
dob.obj=dob.obj.gsub(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,'
') unless dob.is==:table
dob.obj=dob.obj.gsub(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'\1').
gsub(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'\1').
gsub(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'\1').
gsub(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,'\1').
gsub(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,'\1').
gsub(/#{Mx[:fa_insert_o]}(.+?)#{Mx[:fa_insert_c]}/,'\1').
gsub(/#{Mx[:fa_cite_o]}(.+?)#{Mx[:fa_cite_c]}/,'\1').
gsub(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'\1').
gsub(/#{Mx[:fa_monospace_o]}(.+?)#{Mx[:fa_monospace_c]}/,'\1'). # tt, kbd
gsub(/#{Mx[:lnk_o]}\s*(\S+?)\.(png|jpg|gif).+?#{Mx[:lnk_c]}(?:#{Mx[:url_o]}\S+?#{Mx[:url_c]}|#{Mx[:rel_o]}\S+?#{Mx[:rel_c]}|image)/m,
%{#{Xx[:split]}:spaces0:\n:spaces1:\n:spaces1:
\n:spaces0:#{Xx[:split]}}). # common image location, else use ./images
gsub(/#{Mx[:lnk_o]}(.+?)#{Mx[:lnk_c]}#{Mx[:url_o]}(.+?)#{Mx[:url_c]}/,
'\1').
gsub(/#{Mx[:url_o]}(.+?)#{Mx[:url_c]}/,
'\1').
gsub(/#{Mx[:mk_o]}:name#(\S+?)#{Mx[:mk_c]}/,'').
gsub(/#{Mx[:gl_bullet]}/m,'● '). # not available
gsub(/#{Mx[:nbsp]}/,' '). # not available
gsub(/<(p|br)>/,'<\1 />')
dob.obj=clean(dob.obj)
elsif dob.is == :code
dob.obj=dob.obj.gsub(/&/m,'&'). #sort
gsub(/,'<').gsub(/>/,'>')
else # p dob.is ??
end
dob
end
def markup_group(dob='')
dob.obj=dob.obj.gsub(/,'<').gsub(/>/,'>').
gsub(/<:?br(?:\s+\/)?>/,'
').
gsub(/<(link xmlns:xl=".+?")>/,'<\1>').
gsub(/<(\/link)>/,'<\1>').
gsub(/<(\/?en)>/,'<\1>')
dob
end
def markup_block(dob='')
dob.obj=dob.obj.gsub(/,'<').gsub(/>/,'>').
gsub(/<:?br(?:\s+\/)?>/,'
').
gsub(/<(link xmlns:xl=".+?")>/,'<\1>').
gsub(/<(\/link)>/,'<\1>').
gsub(/<(\/?en)>/,'<\1>')
dob
end
def xml_sem_block_paired(matched) # colon depth: many, recurs
matched=matched.gsub(/\b(au):\{(.+?)\}:\1\b/m, %{\\2}).
gsub(/\b(vol):\{(.+?)\}:\1\b/m, %{\\2}).
gsub(/\b(pub):\{(.+?)\}:\1\b/m, %{\\2}).
gsub(/\b(ref):\{(.+?)\}:\1\b/m, %{\\2}).
gsub(/\b(desc):\{(.+?)\}:\1\b/m,%{\\2}).
gsub(/\b(conv):\{(.+?)\}:\1\b/m,%{\\2}).
gsub(/\b(ct):\{(.+?)\}:\1\b/m, %{\\2}).
gsub(/\b(cty):\{(.+?)\}:\1\b/m, %{\\2}).
gsub(/\b(org):\{(.+?)\}:\1\b/m, %{\\2}).
gsub(/\b(dt):\{(.+?)\}:\1\b/m, %{\\2}).
gsub(/\b(n):\{(.+?)\}:\1\b/m, %{\\2}).
gsub(/([a-z]+(?:[_:.][a-z]+)*)(?::\{(.+?)\}:\1)/m,'\2')
end
def xml_semantic_tags(dob)
if @md.sem_tag
dob.obj.gsub!(/([a-z]+(?:[_:.][a-z]+)*)(?::\{(.+?)\}:\1)/m) {|c| xml_sem_block_paired(c) }
dob.obj.gsub!(/([a-z]+(?:[_:.][a-z]+)*)(?::\{(.+?)\}:\1)/m) {|c| xml_sem_block_paired(c) }
dob.obj.gsub!(/([a-z]+(?:[_:.][a-z]+)*)(?::\{(.+?)\}:\1)/m) {|c| xml_sem_block_paired(c) }
dob.obj=dob.obj.gsub(/:\{(.+?)\}:au\b/m, %{\\1}).
gsub(/:\{(.+?)\}:n\b/m, %{\\1}).
gsub(/:\{(.+?)\}:ti\b/m, %{\\1}).
gsub(/:\{(.+?)\}:ref\b/m, %{\\1}).
gsub(/:\{(.+?)\}:desc\b/m, %{\\1}).
gsub(/:\{(.+?)\}:cty\b/m, %{\\1}).
gsub(/:\{(.+?)\}:org\b/m, %{\\1}).
gsub(/:\{(.+?)\}:([a-z]+(?:[_:.][a-z]+)*)/m,'\1').
gsub(/;\{([^}]+(?![;]))\};ti\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};qt\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};ref\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};ed\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};v\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};desc\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};def\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};trans\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};y\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};ab\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};pg\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};fn?\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};mn?\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};ln?\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};in\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};uni\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};fac\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};inst\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};dept\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};org\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};com?\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};cty\b/m, %{\\1}).
gsub(/;\{([^}]+(?![;]))\};([a-z]+(?:[_:.][a-z]+)*)/m,'\1')
end
dob
end
end
end
module SiSU_XML_Tags #Format
require_relative 'dp' # dp.rb
include SiSU_Param
class RDF
include SiSU_Parts_XML
def initialize(md='',seg_name=[],tracker=0)
@full_title=@subtitle=@author=@subject=@description=@publisher=@contributor=@date=@date_created=@date_issued=@date_available=@date_valid=@date_modified=@type=@format=@identifier=@source=@language=@relation=@coverage=@rights=@copyright=@owner=@keywords=''
@md=md
@rdfurl=%{ rdf:about="http://www.jus.uio.no/lm/toc"\n}
if defined? @md.title.full \
and @md.title.full # DublinCore 1 - title
@rdf_title=%{ dc.title="#{seg_name}#{@md.title.full}"\n}
@full_title=%{ \n}
end
if defined? @md.creator.author \
and @md.creator.author=~/\S+/ # DublinCore 2 - creator/author (author)
@rdf_author=%{ dc.author="#{@md.creator.author}"\n}
content=meta_content_clean(@md.creator.author)
@author=%{ \n}
end
if defined? @md.publisher \
and @md.publisher # DublinCore 5 - publisher (current copy published by)
@rdf_publisher=%{ dc.publisher="#{@md.publisher}"\n}
content=meta_content_clean(@md.publisher)
@publisher=%{ \n}
end
if defined? @md.creator.contributor \
and @md.creator.contributor=~/\S+/ # DublinCore 6 - contributor
@rdf_contributor=%{ dc.contributor="#{@md.creator.contributor}"\n}
content=meta_content_clean(@md.creator.contributor)
@contributor=%{ \n}
end
if defined? @md.date.published \
and @md.date.published=~/\S+/ # DublinCore 7 - date year-mm-dd
@rdf_date=%{ dc.date="#{@md.date.published}"\n}
@date=%{ \n} # fix @md.date_scheme
end
if defined? @md.date.created \
and @md.date.created=~/\S+/ # DublinCore 7 - date.created year-mm-dd
@rdf_date_created=%{ dc.date.created="#{@md.date.created}"\n}
@date_created=%{ \n}
end
if defined? @md.date.issued \
and @md.date.issued=~/\S+/ # DublinCore 7 - date.issued year-mm-dd
@rdf_date_issued=%{ dc.date.issued="#{@md.date.issued}"\n}
@date_issued=%{ \n}
end
if defined? @md.date.available \
and @md.date.available=~/\S+/ # DublinCore 7 - date.available year-mm-dd
@rdf_date_available=%{ dc.date.available="#{@md.date.available}"\n}
@date_available=%{ \n}
end
if defined? @md.date.valid \
and @md.date.valid=~/\S+/ # DublinCore 7 - date.valid year-mm-dd
@rdf_date_valid=%{ dc.date.valid="#{@md.date.valid}"\n}
@date_valid=%{ \n}
end
if defined? @md.date.modified \
and @md.date.modified=~/\S+/ # DublinCore 7 - date.modified year-mm-dd
@rdf_date_modified=%{ dc.date.modified="#{@md.date.modified}"\n}
@date_modified=%{ \n}
end
if defined? @md.rights.all \
and @md.rights.all # DublinCore 15 - rights
@rdf_rights=%{ dc.rights="#{@md.rights.all}"\n}
content=meta_content_clean(@md.rights.all)
@rights=%{ \n}
end
if defined? @md.classify.subject \
and @md.classify.subject=~/\S+/ # DublinCore 3 - subject (us library of congress, eric or udc, or schema???)
@rdf_subject=%{ dc.subject="#{@md.classify.subject}"\n}
content=meta_content_clean(@md.classify.subject)
@subject=%{ \n}
end
if defined? @md.notes.description \
and @md.notes.description=~/\S+/ # DublinCore 4 - description
@rdf_description=%{ dc.description="#{@md.notes.description}"\n}
content=meta_content_clean(@md.notes.description)
@description=%{ \n}
end
if defined? @md.notes.coverage \
and @md.notes.coverage=~/\S+/ # DublinCore 14 - coverage
@rdf_coverage=%{ dc.coverage="#{@md.notes.coverage}"\n}
content=meta_content_clean(@md.notes.coverage)
@coverage=%{ \n}
end
if defined? @md.notes.relation \
and @md.notes.relation=~/\S+/ # DublinCore 13 - relation
@rdf_relation=%{ dc.relation="#{@md.notes.relation}"\n}
content=meta_content_clean(@md.notes.relation)
@relation=%{ \n}
end
if defined? @md.notes.type \
and @md.notes.type # DublinCore 8 - type (genre eg. report, convention etc)
@rdf_type=%{ dc.type="#{@md.notes.type}"\n}
content=meta_content_clean(@md.notes.type)
@type=%{ \n}
end
if defined? @md.notes.format \
and @md.notes.format=~/\S+/ # DublinCore 9 - format (use your mime type)
@rdf_format=%{ dc.format="#{@md.notes.format}"\n}
content=meta_content_clean(@md.notes.format)
@format=%{ \n}
end
#if defined? @md.identifier.sisupod \
#and @md.identifier.sisupod=~/\S+/ # DublinCore 10 - identifier (your identifier, could use urn which is free)
# @rdf_identifier=%{ dc.identifier="#{@md.identifier.sisupod}"\n}
# content=meta_content_clean(@md.identifier.sisupod)
# @identifier=%{ \n}
#end
if defined? @md.original.source \
and @md.original.source=~/\S+/ # DublinCore 11 - source (document source)
@rdf_source=%{ dc.source="#{@md.original.source}"\n}
content=meta_content_clean(@md.original.source)
@source=%{ \n}
end
if defined? @md.title.language \
and @md.title.language=~/\S+/ # DublinCore 12 - language (English)
@rdf_language=%{ dc.language="#{@md.title.language}"\n}
@language=%{ \n}
end
if defined? @md.original.language \
and @md.original.language=~/\S+/
@rdf_language_original=%{ dc.language="#{@md.original.language}"\n}
@language_original=%{ \n}
end
content=meta_content_clean(@md.keywords)
@keywords=%{ \n} if @md.keywords
end
def meta_content_clean(content='')
content=if not content.nil?
content=content.tr('"',"'").
gsub(/&/,'&')
else content
end
end
def rdfseg #segHead
rdftoc
end
def comment_xml(extra='')
generator="Generated by: #{@md.project_details.project} #{@md.project_details.version} of #{@md.project_details.date_stamp} (#{@md.project_details.date})" if @md.project_details.version
lastdone="Last Generated on: #{Time.now}"
rubyv="Ruby version: #{@md.ruby_version}"
sc=if @md.sc_info
"Source file: #{@md.sc_filename} version: #{@md.sc_number} of: #{@md.sc_date}"
else ''
end
if extra.empty?
<
WOK
else
<
WOK
end
end
def comment_xml_sax
desc='SiSU XML, SAX type representation'
comment_xml(desc)
end
def comment_xml_node
desc='SiSU XML, Node type representation'
comment_xml(desc)
end
def comment_xml_dom
desc='SiSU XML, DOM type representation'
comment_xml(desc)
end
def metatag_html #values strung together, because some empty, and resulting output (line breaks) is much better
<