aboutsummaryrefslogtreecommitdiffhomepage
path: root/misc/util/d/tools/markup_conversion/markup_changes.d
blob: 4274f784c4a0610b7e7f120d9886c414808f07b4 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
#!/usr/bin/env rdmd
/+
  - read in file .sst .ssi .ssm
  - loop twice
    - first
      - check for and skip code blocks
      - use unique code marker for endnote markers in text and give an endnote
        number ★1, increment
      - extract all endnotes in array
    - second
      - check that the footnote marker number count matches the number of notes
        in the array
        - if they match either:
            - substitute each endnote marker with the array footnote[number-1]
            - substitute each endnote marker with footnote
              as inlined footnote markup (footnote number not needed)
        - if they do not match exit
  - check whether changes have been made
    - if so write file with inline footnotes in sub-directory converted_output_/
      using the same name as the original file
    - else, exit
+/
import std.stdio;
import std.file;
import std.array : split;
import std.exception;
import core.stdc.errno;
import std.regex;
import std.format;
import std.conv;
void main(string[] args) {
  static comment                 = ctRegex!(`^%+ `);
  static block_tic_code_open     = ctRegex!("^`{3} code(?:[.](?P<syntax>[a-z][0-9a-z#+_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?");
  static block_tic_close         = ctRegex!("^(`{3})$","m");
  static block_curly_code_open   = ctRegex!(`^(?:code(?:[.](?P<syntax>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`);
  static block_curly_code_close  = ctRegex!(`^([}]code)`);
  auto rgx_endnote_ref           = ctRegex!(`([~]\^)(?P<tail>[)\]]? |$)`, "gm");
  auto rgx_endnote               = ctRegex!(`^\^~\s+(.+|\n)`, "gm");
  foreach(arg; args[1..$]) {
    if (
      !(arg.match(regex(r"--\w+")))
      && arg.match(regex(r"\w+?\.ss[itm]"))
    ) {
      writeln(arg);
      string filename                  = arg;
      try {
        string[] contents, endnotes, endnote_refs;
        string text                    = filename.readText;
        string[] paragraphs            = text.split("\n\n");
        int endnote_ref_count          = 0;
        int[string] type = [
          "curly_code"                 : 0,
          "tic_code"                   : 0,
        ];
        foreach (paragraph; paragraphs) { /+ loop to gather binary endnotes +/
          if ( !( type["curly_code"] == 1 || type["tic_code"] == 1)
            && paragraph.match(rgx_endnote)
          ) {
            endnotes ~= replaceAll!(m => m[1])
              (paragraph, rgx_endnote);
          } else {
            if ( type["curly_code"] == 1 || type["tic_code"] == 1
              || paragraph.matchFirst(block_curly_code_open)
              || paragraph.matchFirst(block_tic_code_open)
            ) { /+ code blocks identified, no munging +/
              if ( type["curly_code"] == 1
                && paragraph.matchFirst(block_curly_code_close)
              ) {
                type["curly_code"] = 0;
              } else if (type["tic_code"] == 1
                && paragraph.matchFirst(block_tic_close)
              ) {
                type["tic_code"] = 0;
              } else if (paragraph.matchFirst(block_curly_code_open)) {
                type["curly_code"] = 1;
              } else if (paragraph.matchFirst(block_tic_code_open)) {
                type["tic_code"] = 1;
              }
              contents ~= paragraph;
            } else { /+ regular content, not a code block +/
              if (auto m = paragraph.matchAll(rgx_endnote_ref)) {
                foreach (n; m) {
                  endnote_ref_count++; // endnote_refs ~= (n.captures[1]);
                }
              }
              paragraph = replaceAll!(m => " \\\\ " )
                (paragraph, regex(r"\s*<(?:/\s*|:)?br>\s*")); // (paragraph, regex(r"(<br>)"));
              contents ~= paragraph;
            }
          }
        }
        {
          import std.outbuffer;
          auto buffer = new OutBuffer();
          if (endnotes.length == endnote_ref_count) {
            // writeln("endnote ref count:         ", endnote_ref_count);
            // writeln("number of binary endnotes: ", endnotes.length);
            int endnote_count = -1;
            foreach (content; contents) { /+ loop to inline endnotes +/
              content = replaceAll!(m => "~{ " ~ endnotes[++endnote_count] ~ " }~" ~ m["tail"] )
                (content, rgx_endnote_ref); // endnote_ref cannot occur in a code block or else fail
              buffer.write(content ~ "\n\n");
            }
            if (buffer) {
              try {
                string dir_out = "converted_output_";
                string path_and_file_out = dir_out ~ "/" ~ filename;
                dir_out.mkdirRecurse;
                auto f = File(path_and_file_out, "w");
                f.write(buffer);
                writeln("wrote: ", path_and_file_out);
              } catch (FileException ex) {
                writeln("did not write file");
                // Handle errors
              }
            }
          } else {
            foreach (content; contents) { /+ loop to inline endnotes +/
              buffer.write(content ~ "\n\n");
            }
          }
        }
      } catch (ErrnoException ex) {
        switch(ex.errno) {
          case EPERM:
          case EACCES: // Permission denied
            break;
          case ENOENT: // File does not exist
            break;
          default:     // Handle other errors
            break;
        }
      }
    }
  }
}