aboutsummaryrefslogtreecommitdiffhomepage
path: root/org/ao_rgx.org
blob: f168e7adc32ea02d3ac41041a75eb079906b6c3b (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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
#+TITLE: Emacs config file written in org-mode
#+AUTHOR: Ralph Amissah
#+EMAIL: ralph.amissah@gmail.com
#+STARTUP: indent
#+LANGUAGE: en
#+OPTIONS: H:3 num:nil toc:t \n:nil @:t ::t |:t ^:nil -:t f:t *:t <:t
#+OPTIONS: TeX:t LaTeX:t skip:nil d:nil todo:t pri:nil tags:not-in-toc
#+OPTIONS: author:nil email:nil creator:nil timestamp:nil
#+OPTIONS: ^:nil _:nil
#+EXPORT_SELECT_TAGS: export
#+EXPORT_EXCLUDE_TAGS: noexport
#+TAGS: Amissah(A) Class(c) WEB(W) noexport(n)
#+FILETAGS: :sdp:ao:

* regex
** misc
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* misc */
static flag_action               = ctRegex!(`^(--[a-z][a-z0-9-]+)$`);
static flag_action_str           = ctRegex!(` (--[a-z][a-z0-9-]+)`);
static src_pth                   = ctRegex!(`^([a-zA-Z0-9._-]+/)*([a-zA-Z0-9._-]+[.]ss[tm])$`);
static src_fn                    = ctRegex!(`^([a-zA-Z0-9._-]+/)*([a-zA-Z0-9._-]+[.]ss[tm])$`);
static src_fn_master             = ctRegex!(`^([a-zA-Z0-9._-]+/)*([a-zA-Z0-9._-]+[.]ssm)$`);
static src_fn_find_inserts       = ctRegex!(`^([a-zA-Z0-9._-]+/)*([a-zA-Z0-9._-]+[.]ss[im])$`);
static line_delimiter            = ctRegex!("\n");
static within_quotes             = ctRegex!(`"(.+?)"`);
static make_heading_delimiter    = ctRegex!(`[;][ ]*`);
static arr_delimiter             = ctRegex!(`[ ]*[;][ ]*`);
static name_delimiter            = ctRegex!(`^([^,]+)[ ]*,[ ]+(.+?)$`);
static book_index_go             = ctRegex!("([0-9]+)(?:-[0-9]+)?");
static trailing_comma            = ctRegex!(",[ ]*$");
static trailing_linebreak        = ctRegex!(",[ ]{1,2}\\\\\\\\\n[ ]{4}$","m");
static line_delimiter_ws_strip   = ctRegex!("[ ]*\n[ ]*");
static line_delimiter_only       = ctRegex!("^\n");
static para_delimiter            = ctRegex!("\n[ ]*\n+");
static levels_markup             = ctRegex!(`^[A-D1-4]$`);
static levels_numbered           = ctRegex!(`^[0-9]$`);
static levels_numbered_headings  = ctRegex!(`^[0-7]$`);
#+end_src
** markup insert file
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* insert markup file */
static insert_src_fn_ssi_or_sst  = ctRegex!(`^<<\s*(?P<path>[a-zA-Z0-9._-]+/)*(?P<filename>[a-zA-Z0-9._-]+[.]ss[ti])$`);
#+end_src
** header & comments
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* header & comments */
static comment                   = ctRegex!(`^%+ `);
static header                    = ctRegex!(`^@([a-z_]+):(?:\s|$)`);
static header_make               = ctRegex!(`^@(make):(?:\s|$)`);
static header_metadata           = ctRegex!(`^@([a-z_]+):(?:\s|$)`);
static header_sub                = ctRegex!(`^[ ]+:([a-z_]+):\s`);
static head_main                 = ctRegex!(`^@([a-z_]+):\s*(.*)`, "m");
static head_sub                  = ctRegex!(`^[ ]*:([a-z_]+):\s+(.+)`, "m");
#+end_src
** header & paragraph operators
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* heading & paragraph operators */
static heading            = ctRegex!(`^:?([A-D1-4])[~]([a-z0-9_.-]*[?]?) `);
static heading_marker     = ctRegex!(`^:?([A-D1-4])[~]`);
static heading_title      = ctRegex!(`^:?[A-D1-4][~][a-z0-9_.-]*[?]?\s+(.+?)$`);
static heading_all        = ctRegex!(`^:?([A-D1-4])[~]([a-z0-9_.-]*[?]?)\s+(.+?)$`); // test, particularly [2] name/hashtag which may or may not be, does this affect title [3]
static heading_biblio     = ctRegex!(`^:?(1)[~][!](biblio(?:graphy)?|references?)`);
static heading_glossary   = ctRegex!(`^:?(1)[~][!](glossary)`);
static para_bullet        = ctRegex!(`^_[*] `);
static para_bullet_indent = ctRegex!(`^_([1-9])[*] `);
static para_indent        = ctRegex!(`^_([1-9]) `);
static para_indent_hang   = ctRegex!(`^_([0-9])_([0-9]) `);
static para_attribs       = ctRegex!(`^_(([0-9])(_([0-9]))?|_([1-9])?[*]) `);
#+end_src
** blocked markup tics
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* blocked markup tics */
static block_tic_code_open       = ctRegex!("^`{3} (code)");
static block_tic_poem_open       = ctRegex!("^`{3} (poem)");
static block_tic_group_open      = ctRegex!("^`{3} (group)");
static block_tic_block_open      = ctRegex!("^`{3} (block)");
static block_tic_quote_open      = ctRegex!("^`{3} (quote)");
static block_tic_table_open      = ctRegex!("^`{3} (table)");
static block_tic_close           = ctRegex!("^(`{3})$","m");
#+end_src
** blocked markup curly
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* blocked markup curly */
static block_curly_code_open     = ctRegex!(`^(code[{].*?$)`);
static block_curly_code_close    = ctRegex!(`^([}]code)`);
static block_curly_poem_open     = ctRegex!(`^(poem[{].*?$)`);
static block_curly_poem_close    = ctRegex!(`^([}]poem)`);
static block_curly_group_open    = ctRegex!(`^(group[{].*?$)`);
static block_curly_group_close   = ctRegex!(`^([}]group)`);
static block_curly_block_open    = ctRegex!(`^(block[{].*?$)`);
static block_curly_block_close   = ctRegex!(`^([}]block)`);
static block_curly_quote_open    = ctRegex!(`^(quote[{].*?$)`);
static block_curly_quote_close   = ctRegex!(`^([}]quote)`);
static block_curly_table_open    = ctRegex!(`^(table[{].*?$)`);
static block_curly_table_close   = ctRegex!(`^([}]table)`);
#+end_src
** inline markup font face mod
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* inline markup font face mod */
static inline_emphasis           = ctRegex!(`\*\{(?P<text>.+?)\}\*`);
static inline_bold               = ctRegex!(`!\{(?P<text>.+?)\}!`);
static inline_italics            = ctRegex!(`/\{(?P<text>.+?)\}/`);
static inline_superscript        = ctRegex!(`\^\{(?P<text>.+?)\}\^`);
static inline_subscript          = ctRegex!(`,\{(?P<text>.+?)\},`);
static inline_strike             = ctRegex!(`-\{(?P<text>.+?)\}-`);
static inline_insert             = ctRegex!(`\+\{(?P<text>.+?)\}\+`);
static inline_mono               = ctRegex!(`#\{(?P<text>.+?)\}#`);
#+end_src
** inline markup footnotes
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* inline markup footnotes */
static true_dollar                           = ctRegex!(`\$`, "gm");
static inline_notes_al                       = ctRegex!(`【(?:[*+]\s+|\s*)(.+?)】`, "mg");
static inline_notes_al_gen                   = ctRegex!(`【.+?】`, "m");
static inline_notes_curly_gen                = ctRegex!(`~\{.+?\}~`, "m");
static inline_notes_curly                    = ctRegex!(`~\{\s*(.+?)\}~`, "mg");
static inline_al_delimiter_open_regular             = ctRegex!(`【`, "m");
static inline_al_delimiter_close_regular            = ctRegex!(`】`, "m");
static inline_al_delimiter_open_and_close_regular   = ctRegex!(`【|】`, "m");
static inline_notes_delimiter_al_regular            = ctRegex!(`【(.+?)】`, "m");
static inline_notes_delimiter_al_regular_number_note = ctRegex!(`【(\d+)\s+(.+?)】`, "m");
static inline_al_delimiter_open_asterisk         = ctRegex!(`【\*`, "m");
static inline_al_delimiter_open_plus             = ctRegex!(`【\+`, "m");
static inline_curly_delimiter_open_regular             = ctRegex!(`~\{\s*`, "m");
static inline_curly_delimiter_close_regular            = ctRegex!(`\s*\}~`, "m");
static inline_curly_delimiter_open_and_close_regular   = ctRegex!(`~\{\s*|\s*\}~`, "m");
static inline_notes_delimiter_curly_regular            = ctRegex!(`~\{[ ]*(.+?)\}~`, "m");
static inline_notes_curly_sp                 = ctRegex!(`~\{[*+]+\s+(.+?)\}~`, "m");
static inline_notes_curly_sp_asterisk        = ctRegex!(`~\{[*]+\s+(.+?)\}~`, "m");
static inline_notes_curly_sp_plus            = ctRegex!(`~\{[+]+\s+(.+?)\}~`, "m");
static inline_text_and_note_al               = ctRegex!(`(?P<text>.+?)【(?:[*+ ]*)(?P<note>.+?)】`, "mg");
static inline_text_and_note_curly            = ctRegex!(`(?P<text>.+?)(?:(?:[~])[{][*+ ]*)(?P<note>.+?)(?:[}][~])`, "mg");
static inline_note_curly_delimiters          = ctRegex!(`(~\{[*+]?\s*)(.+?)(\}~)`, "mg");
static inline_notes_square                   = ctRegex!(`~\[\s*(.+?)\]~`, "mg");
static inline_text_and_note_square_sp        = ctRegex!(`(.+?)~\[[*+]+\s+(.+?)\]~`, "mg");
static inline_text_and_note_square           = ctRegex!(`(.+?)~\[\s*(.+?)\]~`, "mg");
static inline_note_square_delimiters         = ctRegex!(`(~\[\s*)(.+?)(\]~)`, "mg");
#+end_src
** inline markup book index
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* inline markup book index */
static book_index                = ctRegex!(`^=\{\s*(.+?)\}$`, "m");
static book_index_open           = ctRegex!(`^=\{\s*([^}]+?)$`);
static book_index_close          = ctRegex!(`^(.*?)\}$`, "m"); // strip
#+end_src
** no ocn object
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* no ocn object */
static ocn_off                   = ctRegex!(`~#$`, "m");
static ocn_off_dh                = ctRegex!(`-#$`, "m");
static ocn_off_all               = ctRegex!(`[~-]#$`, "m");
#+end_src
** no ocn block
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* no ocn block */
static ocn_off_block             = ctRegex!(`^--~#$`);
static ocn_off_block_dh          = ctRegex!(`^---#$`);
static ocn_off_block_close       = ctRegex!(`^--\+#$`);
// static auto_ocn_ignore           = ctRegex!(`^[+~*$-]{3,}$`); // reminder
static ocn_block_marks           = ctRegex!(`^--[+~-]#$`);
#+end_src
** ignore outside code blocks
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* ignore outside code blocks */
static regular_parse_skip        = ctRegex!(`^(--[+~-]#|-[\\]{2}-|=[.\\]{2}=)$`); // not structural info
#+end_src
** line & page breaks
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* line & page breaks */
static break_line_within_object  = ctRegex!(`[\\]{2}( |$)`);
// static break_line_break_within_object  = ctRegex!(`( |^)[\\]{2}( |$)`);
static break_page                = ctRegex!(`^-[\\]{2}-$`);
static break_page_new            = ctRegex!(`^=[\\]{2}=$`);
static break_page_line_across    = ctRegex!(`^=[.]{2}=$`);
static break_string              = ctRegex!(`』`);
// ancestry, parent
static parent                    = ctRegex!(`([0-7]):([0-9]+)`);
#+end_src
** json
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* json */
static tailing_comma             = ctRegex!(`,$`, "m");
#+end_src
** head
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* head */
static main_headers              = ctRegex!(`^(?:creator|title|rights|date|original|classify|identifier|notes|publisher|make|links)$`, "m");
static subhead_creator           = ctRegex!(`^(?:author|translator|illustrator)$`, "m");
static subhead_title             = ctRegex!(`^(?:main|sub(?:title)?|full|language|edition|note)$`, "m");
static subhead_rights            = ctRegex!(`^(?:copyright|illustrations|license|cover)$`, "m");
static subhead_date              = ctRegex!(`^(?:published|created|issued|available|valid|modified|added_to_site)$`, "m");
static subhead_original          = ctRegex!(`^(?:title|language|source)$`, "m");
static subhead_classify          = ctRegex!(`^(?:topic_register|subject|keywords|loc|dewey)$`, "m");
static subhead_identifier        = ctRegex!(`^(?:oclc|pg|isbn)$`, "m");
static subhead_notes             = ctRegex!(`^(?:abstract|description)$`, "m");
static subhead_publisher         = ctRegex!(`^(?:name)$`, "m");
static subhead_make              = ctRegex!(`^(?:cover_image|home_button_image|home_button_text|footer|headings|num_top|breaks|substitute|bold|italics|emphasis|texpdf_font|css)$`, "m");
#+end_src
** biblio tags
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* biblio tags */
static biblio_tags               = ctRegex!(`^(is|au|author_raw|author|author_arr|editor_raw|ed|editor_arr|ti|title|subtitle|fulltitle|lng|language|trans|src|jo|journal|in|vol|volume|edn|edition|yr|year|pl|place|pb|pub|publisher|url|pg|pages|note|short_name|id):\s+(.+)`);
static biblio_abbreviations      = ctRegex!(`^(au|ed|ti|lng|jo|vol|edn|yr|pl|pb|pub|pg|pgs|sn)$`);
#+end_src
** bookindex split
#+name: ao_rgx
#+BEGIN_SRC d                                                  :exports none
/* bookindex split */
static bi_main_terms_split       = ctRegex!(`\s*;\s*`);
static bi_main_term_plus_rest_split = ctRegex!(`\s*:\s*`);
static bi_sub_terms_plus_ocn_offset_split = ctRegex!(`\s*\|\s*`);
static bi_term_and_ocns_match    = ctRegex!(`^(.+?)\+(\d+)`);
#+end_src
* tangles
** code structure:                                                   :ao_rgx.d:
#+name: tangle_ao_rgx
#+BEGIN_SRC d  :tangle ../lib/sdp/ao_rgx.d  :exports none :noweb yes
/*
  regex
  ao_rgx.d
*/
mixin template RgxInit() {
  class Rgx {
    <<ao_rgx>>
  }
}
#+end_src