-*- mode: org -*-
#+TITLE:       spine (doc_reform) regex defaults
#+DESCRIPTION: documents - structuring, publishing in multiple formats & search
#+FILETAGS:    :spine:regex:
#+AUTHOR:      Ralph Amissah
#+EMAIL:       [[mailto:ralph.amissah@gmail.com][ralph.amissah@gmail.com]]
#+COPYRIGHT:   Copyright (C) 2015 - 2019 Ralph Amissah
#+LANGUAGE:    en
#+STARTUP:     indent content hideblocks hidestars
#+OPTIONS:     H:3 num:nil toc:t \n:nil @:t ::t |:t ^:nil _: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
#+PROPERTY:    header-args :padline no :exports code :cache no :noweb yes
#+EXPORT_SELECT_TAGS:  export
#+EXPORT_EXCLUDE_TAGS: noexport
#+TAGS: assert(a) class(c) debug(d) mixin(m) spine(s) tangle(T) template(t) WEB(W) noexport(n)

[[./spine.org][spine]]  [[./][org/]]
* meta ctRegex
[[./spine.org][spine]]  [[./][org/]]
http://dlang.org/phobos/std_regex.html
- Plain string, in which case it's compiled to bytecode before matching.
- Regex!char (wchar/dchar) that contains a pattern in the form of compiled bytecode.
- StaticRegex!char (wchar/dchar) that contains a pattern in the form of compiled native machine code.

22 special characters used:

#+BEGIN_SRC text
【】〖〗┥┝┤├¤░┘┙┚┼┿╂┊┏┚┆■☼
#+END_SRC

** _module template_                                                  :module:

#+name: tangle_meta_rgx
#+BEGIN_SRC d :tangle "../src/doc_reform/meta/rgx.d"
/++
  regex: regular expressions used in sisu document parser
+/
module doc_reform.meta.rgx;
static template spineRgxInit() {
  import doc_reform.meta.defaults;
  static struct Rgx {
    <<meta_rgx>>
    <<prgmkup_rgx>>
  }
}
#+END_SRC

** misc                                                               :misc:

#+name: meta_rgx
#+BEGIN_SRC d
/+ misc +/
// static true_dollar                                    = ctRegex!(`\$`, "gm");
static sep                                            = ctRegex!(`␣`, "gm");
static flag_action                                    = ctRegex!(`^(--[a-z][a-z0-9-]+)$`);
static within_quotes                                  = ctRegex!(`"(.+?)"`, "m");
static yaml_tag_is_str                                = ctRegex!(`:str$`);
static yaml_tag_is_int                                = ctRegex!(`:int$`);
static yaml_tag_is_map                                = ctRegex!(`:map$`);
static yaml_tag_is_seq                                = ctRegex!(`:seq$`);
static make_heading_delimiter                         = ctRegex!(`[;][ ]*`);
static arr_delimiter                                  = ctRegex!(`[ ]*[;][ ]*`);
static name_delimiter                                 = ctRegex!(`^([^,]+)[ ]*,[ ]+(.+?)$`);
static book_index_go                                  = ctRegex!("(?P<link>(?P<ocn>[0-9]+)(?:-[0-9]+)?)");
static book_index_go_scroll                           = ctRegex!("(?P<link>(?P<ocn>[0-9]+)(?:-[0-9]+)?)");
static book_index_go_seg                              = ctRegex!("(?P<link>(?P<ocn>[0-9]+)(?:-[0-9]+)?):(?P<seg>[a-z0-9_-]+)");
static book_index_go_seg_                             = ctRegex!("(?P<link>(?P<ocn>[0-9]+)(?:-[0-9]+)?)(:(?P<seg>[a-z0-9_-]+))?");
static book_index_go_seg_anchorless                   = ctRegex!("(?P<link>(?P<ocn>[0-9]+)(?:-[0-9]+)?)");
static trailing_comma                                 = ctRegex!(",[ ]*$");
static trailing_linebreak                             = ctRegex!(",[ ]{1,2}\\\\\\\\\n[ ]{4}$","m");
static newline_eol_delimiter                          = ctRegex!("\n");
static newline_eol_strip_preceding                    = ctRegex!("[ ]*\n");
static newline_eol_delimiter_only                     = ctRegex!("^\n");
static line_delimiter_ws_strip                        = ctRegex!("[ ]*\n[ ]*");
static para_delimiter                                 = ctRegex!("\n[ ]*\n+");
static table_col_delimiter                            = ctRegex!("[ ]*\n+", "mg");
static table_row_delimiter                            = ctRegex!("\n[ ]*\n+", "mg");
static table_row_delimiter_special                    = ctRegex!("[ ]*\n", "mg");
static table_col_delimiter_special                    = ctRegex!("[ ]*[|][ ]*", "mg");
static levels_numbered                                = ctRegex!(`^[0-9]$`);
static levels_numbered_headings                       = ctRegex!(`^[0-7]$`);
static numeric                                        = ctRegex!(`[ 0-9,.-]+`);
static numeric_col                                    = ctRegex!(`^[ 0-9,.%$£₤Є€€¥()-]+$`);
#+END_SRC

** comments                                                        :comment:

#+name: meta_rgx
#+BEGIN_SRC d
/+ comments +/
static comment                                        = ctRegex!(`^%+ `);
#+END_SRC

** config

#+name: meta_rgx
#+BEGIN_SRC d
/+ header +/
#+END_SRC

** native headers
*** native header                                           :native:header:

#+name: meta_rgx
#+BEGIN_SRC d
/+ header +/
static variable_doc_title                             = ctRegex!(`@title`);
static variable_doc_author                            = ctRegex!(`@author|@creator`);
static raw_author_munge                               = ctRegex!(`(?P<last>\S.+?),\s+(?P<first>.+)`,"i");
static yaml_header_meta_title                         = ctRegex!(`^\s*title\s*:\s*(?:"?\w|$)`, "m");
static yaml_config                                    = ctRegex!(`^[a-z]+\s*:\s*(?:"?\w|$)`, "m");
#+END_SRC

** heading & paragraph operators                        :paragraph:operator:

#+name: meta_rgx
#+BEGIN_SRC d
/+ heading & paragraph operators +/
static heading_a                                      = ctRegex!(`^:?[A][~] `, "m");
static heading                                        = ctRegex!(`^:?([A-D1-4])[~]([a-z0-9_.-]*[?]?)\s+`,"i");
static heading_seg_and_above                          = ctRegex!(`^:?([A-D1])[~]([a-z0-9_.-]*[?]?)\s+`,"i");
static heading_marker                                 = ctRegex!(`^:?([A-D1-4])[~]`);
static heading_anchor_tag                             = ctRegex!(`^:?[A-D1-4][~](?P<anchor>[a-z0-9_.-]+) `,"i");
static heading_identify_anchor_tag                    = ctRegex!(`^:?[A-D1-4][~]\s+(?:(?:(?:chapter|article|section|clause)\s+[0-9.]+)|(?:[0-9]+))`,"i");
static heading_extract_named_anchor_tag               = ctRegex!(`^:?[A-D1-4][~]\s+(chapter|article|section|clause)\s+((?:[0-9]+[.:])*[0-9]+)(?=[.:;, ]|$)`,"i");
static heading_extract_unnamed_anchor_tag             = ctRegex!(`^:?[A-D1-4][~]\s+((?:[0-9]+.)*[0-9]+)(?=[.:;, ]|$)`);
static heading_marker_missing_tag                     = ctRegex!(`^:?([A-D1-4])[~] `);
static heading_anchor_tag_plus_colon                  = ctRegex!(`^:?([A-D1-4][~])([a-z0-9_.:-]+) `,"i");
static heading_marker_tag_has_colon                   = ctRegex!(`([:])`);
static heading_biblio                                 = ctRegex!(`^:?(1)[~][!](biblio(?:graphy)?|references?)`);
static heading_glossary                               = ctRegex!(`^:?(1)[~][!](glossary)`);
static heading_blurb                                  = ctRegex!(`^:?(1)[~][!](blurb)`);
static heading_biblio_glossary                        = ctRegex!(`^:?(?:(1)[~][!](?:(?:biblio(?:graphy)?|references?)|glossary)|[A-D1][~])`);
static heading_biblio_blurb                           = ctRegex!(`^:?(?:(1)[~][!](?:(?:biblio(?:graphy)?|references?)|blurb)|[A-D1][~])`);
static heading_blurb_glossary                         = ctRegex!(`^:?(?:(1)[~][!](?:blurb|glossary)|[A-D1][~])`);
static para_bullet                                    = ctRegex!(`^_[*] `);
static para_bullet_indent                             = ctRegex!(`^_(?P<indent>[1-9])[*] `);
static para_indent                                    = ctRegex!(`^_(?P<indent>[1-9])[ ]`);
static para_indent_hang                               = ctRegex!(`^_(?P<hang>[0-9])_(?P<indent>[0-9])[ ]`);
static para_attribs                                   = ctRegex!(`^_(?:(?:[0-9])(?:_([0-9]))?|(?:[1-9])?[*]) `);
static para_inline_link_anchor                        = ctRegex!(`\*[~](?P<anchor>[a-z0-9_.-]+)(?= |$)`,"i");
#+END_SRC

** blocked markup
*** blocked markup curly & tic                                      :block:

#+name: meta_rgx
#+BEGIN_SRC d
/+ blocked markup +/
static block_open                                     = ctRegex!("^((code(?:[.][a-z][0-9a-z#+_]+)?|(?:poem|group|block|quote)(?:[.][a-z][0-9a-z_]+)?|table)(?:[(][ a-zA-Z0-9;:,]*[)])?[{][ ]*$)|^`{3} (code(?:[.][a-z][0-9a-z#+_]+)?|(?:poem|group|block|quote)(?:[.][a-z][0-9a-z_]+)?|table)(?:[(][ a-zA-Z0-9;:,]*[)])?|^[{]table[(](?:h;)?(?P<columns>(?:[ ,]+[0-9]+)+)[)][}]");
static block_poem_open                                = ctRegex!("^((poem(?:[(][ a-zA-Z0-9;:,]*[)])?[{][ ]*$)|`{3} poem(?:[(][ a-zA-Z0-9;:,]*[)])?)");
#+END_SRC

*** blocked markup tic                                          :block:tic:

#+name: meta_rgx
#+BEGIN_SRC d
/+ blocked markup tics +/
static block_tic_code_open                            = ctRegex!("^`{3} code(?:[.](?P<syntax>[a-z][0-9a-z#+_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?");
static block_tic_poem_open                            = ctRegex!("^`{3} poem(?:[.](?P<lang>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?");
static block_tic_group_open                           = ctRegex!("^`{3} group(?:[.](?P<lang>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?");
static block_tic_block_open                           = ctRegex!("^`{3} block(?:[.](?P<lang>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?");
static block_tic_quote_open                           = ctRegex!("^`{3} quote(?:[.](?P<lang>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?");
static block_tic_table_open                           = ctRegex!("^`{3} table(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?"); // ctRegex!("^`{3} table(?:\(.*?\))?");
static block_tic_close                                = ctRegex!("^(`{3})$","m");
#+END_SRC

*** blocked markup curly                                      :block:curly:

#+name: meta_rgx
#+BEGIN_SRC d
/+ blocked markup curly +/
static block_curly_code_open                          = ctRegex!(`^(?:code(?:[.](?P<syntax>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`);
static block_curly_code_close                         = ctRegex!(`^([}]code)`);
static block_curly_poem_open                          = ctRegex!(`^(poem(?:[.](?P<lang>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`);
static block_curly_poem_close                         = ctRegex!(`^([}]poem)`);
static block_curly_group_open                         = ctRegex!(`^(group(?:[.](?P<lang>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`);
static block_curly_group_close                        = ctRegex!(`^([}]group)`);
static block_curly_block_open                         = ctRegex!(`^(block(?:[.](?P<lang>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`);
static block_curly_block_close                        = ctRegex!(`^([}]block)`);
static block_curly_quote_open                         = ctRegex!(`^(quote(?:[.](?P<lang>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`);
static block_curly_quote_close                        = ctRegex!(`^([}]quote)`);
static block_curly_table_open                         = ctRegex!(`^table(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$`);
static block_curly_table_close                        = ctRegex!(`^([}]table)`);
static block_curly_table_special_markup               = ctRegex!(`^[{]table[(](?P<attrib>(?:(h);)?(?P<columns>(?:[, ]+[0-9]+)+))[)][}]`, "mg");
#+END_SRC

*** block sub-matches                                               :block:
**** code

#+name: meta_rgx
#+BEGIN_SRC d
static code_numbering                                 = ctRegex!(`(?P<number>\blinenumber\b|\bnumber\b|\blnr\b)`);
#+END_SRC

**** table

#+name: meta_rgx
#+BEGIN_SRC d
static table_head_instructions                        = ctRegex!(`(?:(?P<c_heading>h);)?(?:[ ]+c(?P<c_num>[0-9]):)?(?P<c_widths>(?:[, ]+[0-9]+[lr]?)+)`);
static table_col_widths_and_alignment                 = ctRegex!(`(?P<width>[0-9]+)(?P<align>[lr]?)`);
static table_col_widths                               = ctRegex!(`(?P<widths>[0-9]+)`);
static table_col_align                                = ctRegex!(`(?P<align>[lr]?)`);
static table_col_align_match                          = ctRegex!(`(?P<align>[lr])`);
static table_col_separator                            = ctRegex!(`┊`);
static table_col_separator_nl                         = ctRegex!(`[┊]$`, "mg");
#+END_SRC

** inline markup                                           :inline:footnote:
*** footnotes & endnotes

#+name: meta_rgx
#+BEGIN_SRC d
/+ inline markup footnotes endnotes +/
static inline_notes_curly_gen                         = ctRegex!(`~\{.+?\}~`, "m");
static inline_notes_curly                             = ctRegex!(`~\{\s*(.+?)\}~`, "mg");
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_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");
static note_ref                                       = ctRegex!(`^\S+?noteref_(?P<ref>[0-9]+)`, "mg");     // {^{73.}^}#noteref_73
#+END_SRC

*** links/ urls                                           :inline:footnote:

#+name: meta_rgx
#+BEGIN_SRC d
static webserv_url_doc_root                           = ctRegex!(`(?P<url>(?P<domain>https?:\/\/[^ /]+)\/(?P<path>\S*))`, "mg");
static smid_inline_url_generic                        = ctRegex!(`(?:^|[}(\[ ])(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)[a-zA-Z0-9_#]`, "mg");
static smid_inline_url                                = ctRegex!(`((?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)[a-zA-Z0-9_]\S*)`, "mg");
static smid_inline_link_naked_url                     = ctRegex!(`(?P<pre>^|[ (\[])(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤)\S+?)(?=[.,;:?!'"]?([ )\]]|$))`, "mg");
static smid_inline_link_markup_regular                = ctRegex!(`(?P<pre>^|[ (\[])\{\s*(?P<content>.+?)\s*\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
static smid_inline_link_endnote_url_helper_punctuated = ctRegex!(`\{~\^\s+(?P<content>.+?)\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[.,;:?!]?([ ]|$))`, "mg");
static smid_inline_link_endnote_url_helper            = ctRegex!(`\{~\^\s+(?P<content>.+?)\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+)`, "mg");
#+END_SRC

*** images                                                         :images:

#+name: meta_rgx
#+BEGIN_SRC d
static image                                           = ctRegex!(`([a-zA-Z0-9._-]+?\.(?:png|gif|jpg))`, "mg");
static smid_image                                      = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)[{┥](?:~\^\s+|\s*))(?P<image>[a-zA-Z0-9._-]+?\.(?:png|gif|jpg))(?P<post>(?:.*?)\s*[}┝](?:image|┤.*?├|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
static smid_image_generic                              = ctRegex!(`(?:^|[ ]|[^\S]?)[{┥](?:~\^\s+|\s*)\S+\.(?:png|gif|jpg).*?[}┝](?:image|┤.*?├|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
static smid_image_with_dimensions                      = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)[{┥](?:~\^\s+|\s*))(?P<image>[a-zA-Z0-9._-]+?\.(?:png|gif|jpg))\s+(?P<width>\d+)x(?P<height>\d+)\s*(?P<post>(?:.*?)\s*[}┝](?:image|┤.*?├|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
static smid_mod_image_without_dimensions               = ctRegex!(`[{┥](?:~\^\s+|\s*)☼\S+\.(?:png|gif|jpg),w0h0.*[}┝](?:image|┤.*?├|(?:https?|git):\/\/\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
static smid_a_image                                    = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)[{](?:~\^\s+|\s*))(?P<image>[a-zA-Z0-9._-]+?\.(?:png|gif|jpg))(?P<post>(?:.*?)\s*[}](?:image|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
static smid_image_delimit                              = ctRegex!(`(?P<pre>^|[ ]|[^\S]?)\{\s*(?P<text>.+?)\s*\}(?:image)(?=[;:!,?.]?([ )\]]|$))`, "mg");
#+END_SRC

*** inline markup book index                             :inline:bookindex:

#+name: meta_rgx
#+BEGIN_SRC d
/+ inline markup book index +/
static book_index                                     = ctRegex!(`^=\{\s*(?P<bookindex>.+?)\}$`, "m");
static book_index_open                                = ctRegex!(`^=\{\s*([^}]*?)$`);
static book_index_close                               = ctRegex!(`^(.*?)\}$`, "m");
#+END_SRC

** switch
*** switch off auto-heading number

#+name: meta_rgx
#+BEGIN_SRC d
static auto_heading_numbering_lv1                    = ctRegex!(`^1~`, "m");
static auto_heading_numbering_lv2                    = ctRegex!(`^2~`, "m");
static auto_heading_numbering_lv3                    = ctRegex!(`^3~`, "m");
static auto_heading_numbering_lv4                    = ctRegex!(`^4~`, "m");
static auto_heading_numbering_off                    = ctRegex!(`^[A-D1-4]~\S*?-\s`, "m");
static auto_heading_numbering_off_lv1                = ctRegex!(`^1~\S*?-\s`, "m");
static auto_heading_numbering_off_lv2                = ctRegex!(`^2~\S*?-\s`, "m");
static auto_heading_numbering_off_lv3                = ctRegex!(`^3~\S*?-\s`, "m");
static auto_heading_numbering_off_lv4                = ctRegex!(`^4~\S*?-\s`, "m");
#+END_SRC

** no object_number object                                :ocn:off:object:

#+name: meta_rgx
#+BEGIN_SRC d
/+ no object_number object +/
static object_number_off                            = ctRegex!(`~#[ ]*$`, "m");
static object_number_off_dummy_heading              = ctRegex!(`-#$`, "m");
static object_number_off_all                        = ctRegex!(`[~-]#$`, "m");
static repeated_character_line_separator            = ctRegex!(`^(?:[ ]*(?:(?:[.][ ]*){4,}|(?:[-][ ]*|[~][ ]*|[*][ ]*|[$][ ]*|[#][ ]*|[\\][ ]*|[/][ ]*){2,})\s*?)+$`);
#+END_SRC

** no object_number block                                  :ocn:off:block:

#+name: meta_rgx
#+BEGIN_SRC d
/+ no object_number block +/
static object_number_off_block                      = ctRegex!(`^--~#$`);
static object_number_off_block_dummy_heading        = ctRegex!(`^---#$`);
static object_number_off_block_close                = ctRegex!(`^--\+#$`);
static object_number_block_marks                    = ctRegex!(`^--[+~-]#$`);
#+END_SRC

** ignore outside code blocks                                   :block:code:

#+name: meta_rgx
#+BEGIN_SRC d
/+ ignore outside code blocks +/
static skip_from_regular_parse    = ctRegex!(`^(--[+~-]#|-[\\]{2}-|=[.\\]{2}=)$`);
#+END_SRC

** line & page breaks                                                :break:

#+name: meta_rgx
#+BEGIN_SRC d
/+ line & page breaks +/
static break_string                                   = ctRegex!(`』`);
#+END_SRC

** biblio tags                                                 :biblio:tags:

#+name: meta_rgx
#+BEGIN_SRC d
/+ 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                                         :bookindex:split:

#+name: meta_rgx
#+BEGIN_SRC d
/+ 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_object_number_offset_split   = ctRegex!(`\s*\|\s*`);
static bi_term_and_object_numbers_match               = ctRegex!(`^(.+?)\+(\d+)`);
#+END_SRC

** topic register split (document classify)

#+name: meta_rgx
#+BEGIN_SRC d
static topic_register_main_terms_split                = ctRegex!(`\s*;\s*`);
static topic_register_main_term_plus_rest_split       = ctRegex!(`\s*:\s*`);
static topic_register_sub_terms_split                 = ctRegex!(`\s*\|\s*`);
static topic_register_multiple_sub_terms_split        = ctRegex!(`␣([^|␣]+(?:\|[^|␣]+)+)`);
#+END_SRC

** language codes                                           :language:codes:

#+name: meta_rgx
#+BEGIN_SRC d
/+ language codes +/
auto language_code_and_filename                                    =
   ctRegex!("(?:^|[/])(am|bg|bn|br|ca|cs|cy|da|de|el|en|eo|es|et|eu|fi|fr|ga|gl|he|hi|hr|hy|ia|is|it|ja|ko|la|lo|lt|lv|ml|mr|nl|no|nn|oc|pl|pt|pt_BR|ro|ru|sa|se|sk|sl|sq|sr|sv|ta|te|th|tk|tr|uk|ur|vi|zh)/[A-Za-z0-9._-].+?[.](?:sst|ssm)$");
#+END_SRC

* 1. output ctRegex
[[./spine.org][spine]]  [[./][org/]]
http://dlang.org/phobos/std_regex.html
- Plain string, in which case it's compiled to bytecode before matching.
- Regex!char (wchar/dchar) that contains a pattern in the form of compiled bytecode.
- StaticRegex!char (wchar/dchar) that contains a pattern in the form of compiled native machine code.

** _module template_                                           :module:output:

#+BEGIN_SRC d :tangle "../src/doc_reform/io_out/rgx.d"
/++
  regex: regular expressions used in sisu document parser
+/
module doc_reform.io_out.rgx;
static template spineOutputRgxInit() {
  import doc_reform.io_out.defaults;
  static struct Rgx {
    <<prgmkup_rgx>>
    <<sp_ch_xhtml_rgx>>
  }
}
#+END_SRC

** special characters
*** xhtml special characters

#+name: sp_ch_xhtml_rgx
#+BEGIN_SRC d
static xhtml_ampersand                            = ctRegex!(`[&]`, "m");      // &amp;
static xhtml_quotation                            = ctRegex!(`["]`, "m");      // &quot;
static xhtml_less_than                            = ctRegex!(`[<]`, "m");      // &lt;
static xhtml_greater_than                         = ctRegex!(`[>]`, "m");      // &gt;
static xhtml_line_break                           = ctRegex!(` [\\]{2}`, "m"); // <br />
#+END_SRC

*** latex special characters

#+name: sp_ch_xhtml_rgx
#+BEGIN_SRC d
static latex_special_char                         = ctRegex!(`([%${}_#&\\])`);
static latex_special_char_for_escape              = ctRegex!(`([%${}_#\\])`);
static latex_special_char_for_escape_and_braces   = ctRegex!(`([&])`);
static latex_special_char_for_escape_url          = ctRegex!(`([%])`);
static latex_special_char_escaped                 = ctRegex!(`\\([%${}_#\\])`);
static latex_special_char_escaped_braced          = ctRegex!(`[{]\\([&])[}]`);
static latex_identify_inline_link                 = ctRegex!(`┥.+?┝┤\S+?├`, "mg");
static latex_clean_internal_link                  = ctRegex!(`^(?:#|¤\S+?#)`, "m");
static latex_identify_inline_fontface             = ctRegex!(`\\([_#$]┨.+?┣)\\([_#$])`, "mg");
static latex_clean_bookindex_linebreak            = ctRegex!(`\s*\\\\\\\\\s*`, "m");
#+END_SRC

* 2. ctRegex defaults shared by meta & output (generic)
** misc generic

#+name: prgmkup_rgx
#+BEGIN_SRC d
static newline                                        = ctRegex!("\n", "mg");
static space                                          = ctRegex!(`[ ]`, "mg");
static spaces_keep                                    = ctRegex!(`(?P<keep_spaces>^[ ]+|[ ]{2,})`, "mg"); // code, verse, block
static spaces_line_start                              = ctRegex!(`^(?P<opening_spaces>[ ]+)`, "mg");
static nbsp_char                                      = ctRegex!(`░`, "mg");
#+END_SRC

** filename (& path) (including insert file)     :insert:file:path:filename:

#+name: prgmkup_rgx
#+BEGIN_SRC d
static src_pth_sst_or_ssm                             = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.](?P<extension>ss[tm]))$`);
static src_pth_pod_sst_or_ssm                         = ctRegex!(`^(?P<podpath>[/]?(?:[a-zA-Z0-9._-]+/)*)media/text/[a-z]{2}/(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*?[.]ss[tm])$`);
static src_pth_contents                               = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*)/pod[.]manifest$`);
static src_pth_zip                                    = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]zip)$`);
static src_pth_types                                  =
  ctRegex!(`^(?P<path>[/]?[a-zA-Z0-9._-]+/)*(?P<gotfile>(?P<filename>[a-zA-Z0-9._-]+[.]ss[tm])|(?P<filelist>[a-zA-Z0-9._-]+/pod[.]manifest)|(?P<filezip>[a-zA-Z0-9._-]+[.]zip))$`);
static src_fn                                         =
  ctRegex!(`^([/]?(?:[a-zA-Z0-9._-]+/)*)(?P<fn_src>(?P<fn_base>[a-zA-Z0-9._-]+)[.](?P<fn_src_suffix>ss[tm]))$`);
static src_fn_master                                  = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ssm)$`);
static src_fn_find_inserts                            = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ss[im])$`);
static insert_src_fn_ssi_or_sst                       = ctRegex!(`^<<\s*(?P<path>[a-zA-Z0-9._-]+/)*(?P<filename>[a-zA-Z0-9._-]+[.]ss[ti])$`);
static src_base_parent_dir_name                       = ctRegex!(`[/](?P<dir>(?:[a-zA-Z0-9._-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
static src_formalised_file_path_parts                 = ctRegex!(`(?P<pth>(?:[/a-zA-Z0-9._-]+?)(?P<dir>[a-zA-Z0-9._-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
#+END_SRC

** inline markup

*** inline breaks

#+name: prgmkup_rgx
#+BEGIN_SRC d
/+ line breaks +/
static br_empty_line                                  = ctRegex!(`\n[ ]*\n`, "mg");
static br_newlines_linebreaks                         = ctRegex!(`[\n┘┙]`, "mg");
static br_line                                        = ctRegex!(`┘`, "mg");
static br_nl                                          = ctRegex!(`┙`, "mg");
#+END_SRC

*** inline (internal program) markup footnotes endnotes   :inline:footnote:

#+name: prgmkup_rgx
#+BEGIN_SRC d
/+ inline markup footnotes endnotes +/
static inline_notes_al                                = ctRegex!(`【(?:[*+]\s+|\s*)(.+?)】`, "mg");
static inline_notes_al_special                        = ctRegex!(`【(?:[*+]\s+)(.+?)】`, "mg"); // TODO remove match when special footnotes are implemented
static inline_notes_al_gen                            = ctRegex!(`【.+?】`, "m");
static inline_notes_al_regular                        = ctRegex!(`【(.+?)】`, "mg");
static inline_notes_al_gen_text                       = ctRegex!(`【(?P<text>.+?)】`, "m");
static inline_notes_al_gen_ref                        = ctRegex!(`【(?P<ref>[*+]\s+)\s*(?P<text>.+?)】`, "mg");
static inline_notes_al_all_note                       = ctRegex!(`【(?P<num>\d+|(?:[*]|[+])+)\s+(?P<note>.+?)\s*】`, "mg");
static inline_notes_al_regular_number_note            = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)\s*】`, "mg");
static inline_notes_al_special_char_note              = ctRegex!(`【(?P<char>(?:[*]|[+])+)\s+(?P<note>.+?)】`, "mg");
static inline_al_delimiter_open_regular               = ctRegex!(`【\s`, "m");
static inline_al_delimiter_open_symbol_star           = ctRegex!(`【[*]\s`, "m");
static inline_al_delimiter_open_symbol_plus           = ctRegex!(`【[+]\s`, "m");
static inline_text_and_note_al_                       = ctRegex!(`(.+?(?:【[*+]*\s+.+?】|$))`, "mg");
#+END_SRC

*** inline links

#+name: prgmkup_rgx
#+BEGIN_SRC d
/+ inline markup links +/
static inline_image                                   = ctRegex!(`(?P<pre>┥)☼(?P<imginf>(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+))\s*(?P<post>.*?┝┤.*?├)`, "mg");
static inline_image_without_dimensions                = ctRegex!(`(?P<pre>┥)☼(?P<imginf>(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>0)h(?P<height>0))\s*(?P<post>.*?┝┤.*?├)`, "mg");
static inline_image_info                              = ctRegex!(`☼?(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+)`, "mg");
static inline_link_anchor                             = ctRegex!(`┃(?P<anchor>\S+?)┃`, "mg"); // TODO *~text_link_anchor
static inline_link                                    = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>#?(\S+?))├`, "mg");
static inline_link_empty                              = ctRegex!(`┥(?P<text>.+?)┝┤├`, "mg");
static inline_link_number                             = ctRegex!(`┥(?P<text>.+?)┝┤(?P<num>[0-9]+)├`, "mg"); // not used
static inline_link_number_only                        = ctRegex!(`(┥.+?┝)┤(?P<num>[0-9]+)├`, "mg");
static inline_link_stow_uri                           = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>[^ 0-9#┥┝┤├][^ 0-9┥┝┤├]+)├`, "mg"); // will not stow (stowed links) or object number internal links
static inline_link_hash                               = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>#(?P<segname>\S+?))├`, "mg");
static inline_link_clean                              = ctRegex!(`┤(?:.+?)├|[┥┝]`, "mg");
static inline_link_toc_to_backmatter                  = ctRegex!(`┤#(?P<link>endnotes|bibliography|bookindex|glossary|blurb)├`, "mg");
static url                                            = ctRegex!(`https?://`, "mg");
static uri                                            = ctRegex!(`(?:https?|git)://`, "mg");
static uri_identify_components                        = ctRegex!(`(?P<type>(?:https?|git)://)(?P<path>\S+?/)(?P<file>[^/]+)$`, "mg");
static inline_link_subtoc                             = ctRegex!(`^(?P<level>[5-7])~ ┥(?P<text>.+?)┝┤(?P<link>.+?)├`, "mg");
static inline_link_fn_suffix                          = ctRegex!(`¤(.+?)(\.fnSuffix)`, "mg");
static inline_seg_link                                = ctRegex!(`(¤)(?:.+?)\.fnSuffix`, "mg");
static mark_internal_site_lnk                         = ctRegex!(`¤`, "mg");
static quotation_mark_sql_insert_delimiter            = ctRegex!("[']", "mg");
#+END_SRC

*** inline markup font face mod                          :inline:font:face:

#+name: prgmkup_rgx
#+BEGIN_SRC d
/+ inline markup font face mod +/
static inline_mark_emphasis                         = ctRegex!(`(?P<mark>[*])\{(?P<text>.+?)\}[*]`, "mg");
static inline_mark_bold                             = ctRegex!(`(?P<mark>[!])\{(?P<text>.+?)\}[!]`, "mg");
static inline_mark_underscore                       = ctRegex!(`(?P<mark>[_])\{(?P<text>.+?)\}[_]`, "mg");
static inline_mark_italics                          = ctRegex!(`(?P<mark>[/])\{(?P<text>.+?)\}[/]`, "mg");
static inline_mark_superscript                      = ctRegex!(`(?P<mark>\^)\{(?P<text>.+?)\}\^`, "mg");
static inline_mark_subscript                        = ctRegex!(`(?P<mark>[,])\{(?P<text>.+?)\}[,]`, "mg");
static inline_mark_strike                           = ctRegex!(`(?P<mark>[-])\{(?P<text>.+?)\}[-]`, "mg");
static inline_mark_insert                           = ctRegex!(`(?P<mark>[+])\{(?P<text>.+?)\}[+]`, "mg");
static inline_mark_mono                             = ctRegex!(`(?P<mark>[#])\{(?P<text>.+?)\}[#]`, "mg");
static inline_mark_cite                             = ctRegex!(`(?P<mark>["])\{(?P<text>.+?)\}["]`, "mg");
#+END_SRC

#+name: prgmkup_rgx
#+BEGIN_SRC d
static inline_faces_line                              = ctRegex!(`^[*!/_]_ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`);
static inline_emphasis_line                           = ctRegex!(`^\*_ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
static inline_bold_line                               = ctRegex!(`^!_ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
static inline_italics_line                            = ctRegex!(`^/_ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
static inline_underscore_line                         = ctRegex!(`^__ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
#+END_SRC

#+name: prgmkup_rgx
#+BEGIN_SRC d
/+ inline markup font face mod +/
static inline_emphasis                                = ctRegex!(`[*]┨(?P<text>.+?)┣[*]`, "mg");
static inline_bold                                    = ctRegex!(`[!]┨(?P<text>.+?)┣[!]`, "mg");
static inline_underscore                              = ctRegex!(`[_]┨(?P<text>.+?)┣[_]`, "mg");
static inline_italics                                 = ctRegex!(`[/]┨(?P<text>.+?)┣[/]`, "mg");
static inline_superscript                             = ctRegex!(`\^┨(?P<text>.+?)┣\^`, "mg");
// static inline_superscript                             = ctRegex!(`[\^]┨(?P<text>.+?)┣[\^]`, "mg");
static inline_subscript                               = ctRegex!(`[,]┨(?P<text>.+?)┣[,]`, "mg");
static inline_strike                                  = ctRegex!(`[-]┨(?P<text>.+?)┣[-]`, "mg");
static inline_insert                                  = ctRegex!(`[+]┨(?P<text>.+?)┣[+]`, "mg");
static inline_mono                                    = ctRegex!(`[■]┨(?P<text>.+?)┣[■]`, "mg");
static inline_cite                                    = ctRegex!(`[‖]┨(?P<text>.+?)┣[‖]`, "mg");
static inline_fontface_clean                          = ctRegex!(`[*!_/^,+■‖-]┨|┣[*!_/^,+■‖-]`, "mg");
#+END_SRC

*** table related

#+name: prgmkup_rgx
#+BEGIN_SRC d
/+ table delimiters +/
static table_delimiter_col                           = ctRegex!("[ ]*[┊][ ]*", "mg");
static table_delimiter_row                           = ctRegex!("[ ]*\n", "mg");
#+END_SRC

* __END__