-*- mode: org -*- #+TITLE: sisudoc 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 - 2024 Ralph Amissah #+LANGUAGE: en #+STARTUP: content hideblocks hidestars noindent entitiespretty #+PROPERTY: header-args :exports code #+PROPERTY: header-args+ :noweb yes #+PROPERTY: header-args+ :results no #+PROPERTY: header-args+ :cache no #+PROPERTY: header-args+ :padline no #+PROPERTY: header-args+ :mkdirp yes #+OPTIONS: H:3 num:nil toc:t \n:t ::t |:t ^:nil -:t f:t *:t - [[./doc-reform.org][doc-reform.org]] [[./][org/]] * meta ctRegex - [[./doc-reform.org][doc-reform.org]] [[./][org/]] https://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 txt 【】〖〗┥┝┤├¤░┘┙┚┼┿╂┊┏┚┆■☼ #+END_SRC ** _module template_ :module: #+HEADER: :tangle "../src/sisudoc/meta/rgx.d" #+HEADER: :noweb yes #+BEGIN_SRC d <<doc_header_including_copyright_and_license>> /++ regex: regular expressions used in sisu document parser +/ module sisudoc.meta.rgx; @safe: static template spineRgxIn() { static struct RgxI { <<meta_rgx_misc>> <<meta_rgx_comments>> <<meta_rgx_config>> <<meta_rgx_headers>> <<meta_rgx_heading_marks>> <<meta_rgx_paragraph_marks>> <<meta_rgx_blocks>> <<meta_rgx_block_tic>> <<meta_rgx_block_curly>> <<meta_rgx_sub_match_code>> <<meta_rgx_table>> <<meta_rgx_footnote_endnote>> <<meta_rgx_url>> <<meta_rgx_images>> <<meta_rgx_book_index>> <<meta_rgx_heading_number>> <<meta_rgx_object_number_off_object>> <<meta_rgx_object_number_off_block>> <<meta_rgx_code_block>> <<meta_rgx_line_and_page_breaks>> <<meta_rgx_bibliography>> <<meta_rgx_book_index_split>> <<meta_rgx_topic_register_split>> <<prgmkup_rgx_spaces>> <<prgmkup_rgx_filename_and_path>> <<prgmkup_rgx_inline_breaks>> <<prgmkup_rgx_internal_footnotes_and_endnotes>> <<prgmkup_rgx_inline_links>> <<prgmkup_rgx_font_face>> <<prgmkup_rgx_font_face_line>> } } #+END_SRC ** misc :misc: #+NAME: meta_rgx_misc #+BEGIN_SRC d /+ misc +/ static flag_action = ctRegex!(`^(--[a-z][a-z0-9-]+)$`); static within_quotes = ctRegex!(`"(.+?)"`, "m"); static make_heading_delimiter = ctRegex!(`[;][ ]*`); static arr_delimiter = ctRegex!(`[ ]*[;][ ]*`); static name_delimiter = ctRegex!(`^([^,]+)[ ]*,[ ]+(.+?)$`); static book_index_go = ctRegex!("(?P<link>(?P<ocn>[0-9]+)(?:-[0-9]+)?)"); static trailing_comma = ctRegex!(",[ ]*$"); static trailing_linebreak = ctRegex!(",[ ]{1,2}\\\\\\\\\n[ ]{4}$","m"); static newline_eol_strip_preceding = ctRegex!("[ ]*\n"); static newline_eol_delimiter_only = ctRegex!("^\n"); static markup_inline_linebreak = ctRegex!(`\s*\\\\s*`, "m"); 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_col = ctRegex!(`^[ 0-9,.%$£₤Є€€¥()-]+$`); #+END_SRC #+BEGIN_SRC d // static true_dollar = ctRegex!(`\$`, "gm"); // static sep = ctRegex!(`␣`, "gm"); // static uid_sep = ctRegex!(`:`, "gm"); // ctRegex!(`␣`, "gm"); // 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 numeric = ctRegex!(`[ 0-9,.-]+`); #+END_SRC ** comments :comment: #+NAME: meta_rgx_comments #+BEGIN_SRC d /+ comments +/ static comment = ctRegex!(`^%+ `); #+END_SRC ** config #+NAME: meta_rgx_config #+BEGIN_SRC d /+ header +/ #+END_SRC ** native headers *** native header :native:header: #+NAME: meta_rgx_headers #+BEGIN_SRC d /+ header +/ static variable_doc_title_author_date = ctRegex!(`@title-author-date`); static variable_doc_title_author = ctRegex!(`@title-author`); static variable_doc_title = ctRegex!(`@title`); static variable_doc_author = ctRegex!(`@author|@creator`); static variable_doc_date = ctRegex!(`@date`); static raw_author_munge = ctRegex!(`(?P<last>\S.+?),\s+(?P<first>.+)`,"i"); static yaml_config = ctRegex!(`^[a-z]+\s*:\s*(?:"?\w|$)`, "m"); #+END_SRC ** heading operators :heading:operator: #+NAME: meta_rgx_heading_marks #+BEGIN_SRC d /+ heading operators +/ static heading_a = ctRegex!(`^:?[A][~] `, "m"); static heading = ctRegex!(`^:?([A-D1-4])[~]([a-z0-9_.-]*[?]?)\s+`,"i"); static headings = ctRegex!(`^:?(?P<level>[A-D1-4])[~](?:[a-z0-9_.-]*[?]?|[!](?:glossary|bibliogrphy|biblio|references?|blurb))(?:\s|$)`,"i"); static heading_seg_and_above = ctRegex!(`^:?([A-D1])[~]([a-z0-9_.-]*[?]?)\s+`,"i"); 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)`); #+END_SRC #+BEGIN_SRC d // static heading_marker = ctRegex!(`^:?([A-D1-4])[~]`); #+END_SRC ** paragraph operators :paragraph:operator: #+NAME: meta_rgx_paragraph_marks #+BEGIN_SRC d /+ paragraph operators +/ 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_.-]+)(?= |$)`,"i"); #+END_SRC #+NAME: grouped_text_rgx_paragraph_marks #+BEGIN_SRC d /+ paragraph operators +/ static grouped_para_indent_1 = ctRegex!(`^_1[ ]`, "m"); static grouped_para_indent_2 = ctRegex!(`^_2[ ]`, "m"); static grouped_para_indent_3 = ctRegex!(`^_3[ ]`, "m"); static grouped_para_indent_4 = ctRegex!(`^_4[ ]`, "m"); static grouped_para_indent_5 = ctRegex!(`^_5[ ]`, "m"); static grouped_para_indent_6 = ctRegex!(`^_6[ ]`, "m"); static grouped_para_indent_7 = ctRegex!(`^_7[ ]`, "m"); static grouped_para_indent_8 = ctRegex!(`^_8[ ]`, "m"); static grouped_para_indent_9 = ctRegex!(`^_9[ ]`, "m"); static grouped_para_bullet = ctRegex!(`^_[*] `, "m"); static grouped_para_bullet_indent_1 = ctRegex!(`^_1[*] `, "m"); static grouped_para_bullet_indent_2 = ctRegex!(`^_2[*] `, "m"); static grouped_para_bullet_indent_3 = ctRegex!(`^_3[*] `, "m"); static grouped_para_bullet_indent_4 = ctRegex!(`^_4[*] `, "m"); static grouped_para_bullet_indent_5 = ctRegex!(`^_5[*] `, "m"); static grouped_para_bullet_indent_6 = ctRegex!(`^_6[*] `, "m"); static grouped_para_bullet_indent_7 = ctRegex!(`^_7[*] `, "m"); static grouped_para_bullet_indent_8 = ctRegex!(`^_8[*] `, "m"); static grouped_para_bullet_indent_9 = ctRegex!(`^_9[*] `, "m"); static grouped_para_bullet_indent = ctRegex!(`^_(?P<indent>[1-9])[*] `, "m"); static grouped_para_indent_hang = ctRegex!(`^_(?P<hang>[0-9])_(?P<indent>[0-9])[ ]`, "m"); #+END_SRC #+BEGIN_SRC d // static grouped_para_indent = ctRegex!(`^_(?P<indent>[1-9])[ ]`, "m"); #+END_SRC ** blocked markup *** blocked markup curly & tic :block: #+NAME: meta_rgx_blocks #+BEGIN_SRC d /+ blocked markup +/ static block_open = ctRegex!("^((code(?:[.][a-z][0-9a-z#+_]+)?|(?:poem|group|block|quote)(?:[.][a-z][0-9a-z_]+)?|table)(?:[(][ a-zA-Z0-9;:,]*[)])?[{][ ]*$)|^`{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_block_tic #+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})$","m"); #+END_SRC *** blocked markup curly :block:curly: #+NAME: meta_rgx_block_curly #+BEGIN_SRC d /+ blocked markup curly +/ static block_curly_code_open = ctRegex!(`^(?:code(?:[.](?P<syntax>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`); 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;:,]*)[)])?[{][ ]*$`); static block_curly_table_close = ctRegex!(`^([}]table)`); static block_curly_table_special_markup = ctRegex!(`^[{]table[(](?P<attrib>(?:(h);)?(?P<columns>(?:[, ]+[0-9]+)+))[)][}]`, "mg"); #+END_SRC *** block sub-matches :block: **** code #+NAME: meta_rgx_sub_match_code #+BEGIN_SRC d static code_numbering = ctRegex!(`(?P<number>\blinenumber\b|\bnumber\b|\blnr\b)`); #+END_SRC **** table #+NAME: meta_rgx_table #+BEGIN_SRC d static table_head_instructions = ctRegex!(`(?:(?P<c_heading>h);)?(?:[ ]+c(?P<c_num>[0-9]):)?(?P<c_widths>(?:[, ]+[0-9]+[lr]?)+)`); static table_col_widths_and_alignment = ctRegex!(`(?P<width>[0-9]+)(?P<align>[lr]?)`); static table_col_widths = ctRegex!(`(?P<widths>[0-9]+)`); static table_col_align_match = ctRegex!(`(?P<align>[lr])`); static table_col_separator_nl = ctRegex!(`[┊]$`, "mg"); #+END_SRC #+BEGIN_SRC d // static table_col_align = ctRegex!(`(?P<align>[lr]?)`); // static table_col_separator = ctRegex!(`┊`); #+END_SRC ** inline markup :inline:footnote: *** footnotes & endnotes #+NAME: meta_rgx_footnote_endnote #+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_asterisk = ctRegex!(`~\{[*]+\s+(.+?)\}~`, "m"); static inline_notes_curly_sp_plus = ctRegex!(`~\{[+]+\s+(.+?)\}~`, "m"); static note_ref = ctRegex!(`^\S+?noteref_(?P<ref>[0-9]+)`, "mg"); // {^{73.}^}#noteref_73 #+END_SRC #+BEGIN_SRC d // static inline_notes_curly_sp = 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"); #+END_SRC *** links/ urls :inline:footnote: #+NAME: meta_rgx_url #+BEGIN_SRC d 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 #+BEGIN_SRC d // static webserv_url_doc_root = ctRegex!(`(?P<url>(?P<domain>https?:\/\/[^ /]+)\/(?P<path>\S*))`, "mg"); #+END_SRC *** images :images: #+NAME: meta_rgx_images #+BEGIN_SRC d static image = ctRegex!(`([a-zA-Z0-9._-]+?\.(?:png|gif|jpg))`, "mg"); static smid_image = ctRegex!(`(?P<pre>(?:^|[ ])[{┥](?:~\^\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+\.(?:png|gif|jpg).*?[}┝](?:image|┤.*?├|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg"); static smid_image_with_dimensions = ctRegex!(`(?P<pre>(?:^|[ ])[{┥](?:~\^\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_image_delimit = ctRegex!(`(?P<pre>^|[ ])\{\s*(?P<text>.+?)\s*\}(?:image)(?=[;:!,?.]?([ )\]]|$))`, "mg"); #+END_SRC #+BEGIN_SRC d // static smid_a_image = ctRegex!(`(?P<pre>(?:^|[ ])[{](?:~\^\s+|\s*))(?P<image>[a-zA-Z0-9._-]+?\.(?:png|gif|jpg))(?P<post>(?:.*?)\s*[}](?:image|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg"); #+END_SRC *** inline markup book index :inline:bookindex: #+NAME: meta_rgx_book_index #+BEGIN_SRC d /+ inline markup book index +/ static book_index_item = ctRegex!(`^=\{\s*(?P<bookindex>.+?)\}$`, "m"); static book_index_item_open = ctRegex!(`^=\{\s*([^}]*?)$`); static book_index_item_close = ctRegex!(`^(.*?)\}$`, "m"); #+END_SRC ** switch *** switch off auto-heading number #+NAME: meta_rgx_heading_number #+BEGIN_SRC d static auto_heading_numbering_lv1 = ctRegex!(`^1~`, "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 #+BEGIN_SRC d // static auto_heading_numbering_lv2 = ctRegex!(`^2~`, "m"); // bug? // static auto_heading_numbering_lv3 = ctRegex!(`^3~`, "m"); // bug? // static auto_heading_numbering_lv4 = ctRegex!(`^4~`, "m"); // bug? // static auto_heading_numbering_off = ctRegex!(`^[A-D1-4]~\S*?-\s`, "m"); #+END_SRC ** no object_number object :ocn:off:object: #+NAME: meta_rgx_object_number_off_object #+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*?)+$`); #+END_SRC ** no object_number block :ocn:off:block: #+NAME: meta_rgx_object_number_off_block #+BEGIN_SRC d /+ no object_number block +/ static object_number_off_block = ctRegex!(`^--~#$`); static object_number_off_block_dummy_heading = ctRegex!(`^---#$`); static object_number_off_block_close = ctRegex!(`^--\+#$`); static object_number_block_marks = ctRegex!(`^--[+~-]#$`); #+END_SRC ** ignore outside code blocks :block:code: #+NAME: meta_rgx_code_block #+BEGIN_SRC d /+ ignore outside code blocks +/ static skip_from_regular_parse = ctRegex!(`^(--[+~-]#|-[\\]{2}-|=[.\\]{2}=)$`); #+END_SRC ** line & page breaks :break: #+NAME: meta_rgx_line_and_page_breaks #+BEGIN_SRC d /+ line & page breaks +/ static break_string = ctRegex!(`』`); #+END_SRC ** biblio tags :biblio:tags: #+NAME: meta_rgx_bibliography #+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)$`); #+END_SRC ** bookindex split :bookindex:split: #+NAME: meta_rgx_book_index_split #+BEGIN_SRC d /+ bookindex split +/ static bi_main_terms_split = ctRegex!(`\s*;\s*`); static bi_main_term_plus_rest_split = ctRegex!(`\s*:\s*`); static bi_sub_terms_plus_object_number_offset_split = ctRegex!(`\s*\|\s*`); static bi_term_and_object_numbers_match = ctRegex!(`^(.+?)\+(\d+)`); #+END_SRC ** topic register split (document classify) #+NAME: meta_rgx_topic_register_split #+BEGIN_SRC d static topic_register_main_terms_split = ctRegex!(`\s*;\s*`); static topic_register_main_term_plus_rest_split = ctRegex!(`\s*:\s*`); static topic_register_sub_terms_split = ctRegex!(`\s*\|\s*`); static topic_register_multiple_sub_terms_split = ctRegex!(`␣([^|␣]+(?:\|[^|␣]+)+)`); #+END_SRC ** language codes :language:codes: #+NAME: meta_rgx_language_codes #+BEGIN_SRC d /+ language codes +/ auto language_code_and_filename = ctRegex!("(?:^|[/])(am|bg|bn|br|ca|cs|cy|da|de|el|en|eo|es|et|eu|fi|fr|ga|gl|he|hi|hr|hy|ia|is|it|ja|ko|la|lo|lt|lv|ml|mr|nl|no|nn|oc|pl|pt|pt_BR|ro|ru|sa|se|sk|sl|sq|sr|sv|ta|te|th|tk|tr|uk|ur|vi|zh)/[A-Za-z0-9._-].+?[.](?:sst|ssm)$"); #+END_SRC * 1. output ctRegex - [[./doc-reform.org][doc-reform.org]] [[./][org/]] https://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: #+HEADER: :tangle "../src/sisudoc/io_out/rgx.d" #+HEADER: :noweb yes #+BEGIN_SRC d <<doc_header_including_copyright_and_license>> /++ regex: regular expressions used in sisu document parser +/ module sisudoc.io_out.rgx; @safe: static template spineRgxOut() { static struct RgxO { <<makes>> <<prgmkup_rgx_spaces>> <<prgmkup_rgx_filename_and_path>> <<prgmkup_rgx_inline_breaks>> <<prgmkup_rgx_inline_quotes>> <<prgmkup_rgx_internal_footnotes_and_endnotes>> <<prgmkup_rgx_inline_links>> <<prgmkup_rgx_inline_font_face>> <<prgmkup_rgx_table>> <<grouped_text_rgx_paragraph_marks>> } } #+END_SRC ** make *** various #+NAME: makes #+BEGIN_SRC d static make_breakpage = ctRegex!(`new=(?P<breakpage>.+?)(?:;|$)`); static make_breakcolumn = ctRegex!(`break=(?P<breakcolumn>.+?)(?:;|$)`,); #+END_SRC * 2. ctRegex defaults shared by meta & output (generic) ** meta #+NAME: prgmkup_rgx_meta #+BEGIN_SRC d static space = ctRegex!(`[ ]`, "mg"); static spaces_keep = ctRegex!(`(?P<keep_spaces>^[ ]+|[ ]{2,})`, "mg"); // code, verse, block #+END_SRC ** spine & source_in #+NAME: prgmkup_rgx_in #+BEGIN_SRC d #+END_SRC ** misc generic #+NAME: prgmkup_rgx_spaces #+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"); static nbsp_chars = ctRegex!(`[░]+`, "mg"); static middle_dot = ctRegex!(`·`, "mg"); #+END_SRC ** inline markup *** inline breaks #+NAME: prgmkup_rgx_inline_breaks #+BEGIN_SRC d /+ line breaks +/ static br_empty_line = ctRegex!(`\n[ ]*\n`, "mg"); static br_linebreaks_newlines = ctRegex!(`[\n┘┙]`, "mg"); static br_linebreaks = ctRegex!(`[┘┙]`, "mg"); static br_line = ctRegex!(`┘`, "mg"); static br_line_inline = ctRegex!(`┙`, "mg"); static br_line_spaced = ctRegex!(`┚`, "mg"); #+END_SRC #+BEGIN_SRC d // static brln = ctRegex!(`(?:\\\\)+`, "mg"); #+END_SRC *** quote marks #+NAME: prgmkup_rgx_inline_quotes #+BEGIN_SRC d /+ quotation marks +/ static quotes_open_and_close = ctRegex!(`[“”]`, "mg"); #+END_SRC #+BEGIN_SRC d // static quote_open = ctRegex!(`[“]`, "mg"); // static quote_close = ctRegex!(`[”]`, "mg"); #+END_SRC *** inline markup font face mod :inline:font:face: #+NAME: prgmkup_rgx_font_face #+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_font_face_line #+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 *** inline (internal program) markup footnotes endnotes :inline:footnote: #+NAME: prgmkup_rgx_internal_footnotes_and_endnotes #+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_gen_text = ctRegex!(`【(?P<text>.+?)】`, "m"); 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 #+BEGIN_SRC d // static inline_notes_al_regular = ctRegex!(`【(.+?)】`, "mg"); // static inline_notes_al_gen_ref = ctRegex!(`【(?P<ref>[*+]\s+)\s*(?P<text>.+?)】`, "mg"); #+END_SRC *** inline links #+NAME: prgmkup_rgx_inline_links #+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<linked_text>┥.+?┝)┤(?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<hash>\S+?))├`, "mg"); static inline_link_seg_and_hash = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>(?P<seg>[^/#├]*)#(?P<hash>.+?))├`, "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_inline_font_face #+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_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"); #+END_SRC #+BEGIN_SRC d // static inline_superscript = ctRegex!(`⑆[\^]┨(?P<text>.+?)┣[\^]`, "mg"); // static inline_fontface_clean = ctRegex!(`⑆[*!_/^,+■‖-]┨|┣[*!_/^,+■‖-]`, "mg"); #+END_SRC *** table related #+NAME: prgmkup_rgx_table #+BEGIN_SRC d /+ table delimiters +/ static table_delimiter_col = ctRegex!("[ ]*[┊][ ]*", "mg"); static table_delimiter_row = ctRegex!("[ ]*\n", "mg"); #+END_SRC ** files filename (& path) (including insert file) :insert:file:path:filename: #+HEADER: :tangle "../src/sisudoc/meta/rgx_files.d" #+HEADER: :noweb yes #+BEGIN_SRC d <<doc_header_including_copyright_and_license>> /++ regex: regular expressions used in sisu document parser +/ module sisudoc.meta.rgx_files; @safe: static template spineRgxFiles() { static struct RgxFiles { <<prgmkup_rgx_filename_and_path>> <<meta_rgx_language_codes>> } } #+END_SRC #+NAME: prgmkup_rgx_filename_and_path #+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})$`); // formalizes dir structure #+END_SRC ** _module template yaml tags #+HEADER: :tangle "../src/sisudoc/meta/rgx_yaml_tags.d" #+HEADER: :noweb yes #+BEGIN_SRC d <<doc_header_including_copyright_and_license>> /++ regex: regular expressions used in sisu document parser +/ module sisudoc.meta.rgx_yaml; @safe: static template spineRgxYamlTags() { static struct RgxYaml { <<meta_rgx_yaml>> } } #+END_SRC #+NAME: meta_rgx_yaml #+BEGIN_SRC d static yaml_tag_is_str = ctRegex!(`:str$`); static yaml_tag_is_int = ctRegex!(`:int$`); static yaml_tag_is_map = ctRegex!(`:map$`); static yaml_tag_is_seq = ctRegex!(`:seq$`); #+END_SRC ** special characters *** xhtml special characters template #+HEADER: :tangle "../src/sisudoc/io_out/rgx_xhtml.d" #+HEADER: :noweb yes #+BEGIN_SRC d <<doc_header_including_copyright_and_license>> /++ regex: regular expressions used in sisu document parser +/ module sisudoc.io_out.rgx_xhtml; @safe: static template spineRgxXHTML() { static struct RgxXHTML { <<sp_ch_xhtml_rgx>> } } #+END_SRC *** xhtml special characters #+NAME: sp_ch_xhtml_rgx #+BEGIN_SRC d static ampersand = ctRegex!(`[&]`, "m"); // & static quotation = ctRegex!(`["]`, "m"); // " static less_than = ctRegex!(`[<]`, "m"); // < static greater_than = ctRegex!(`[>]`, "m"); // > static line_break = ctRegex!(` [\\]{2}`, "m"); // <br /> #+END_SRC *** LaTeX special characters template #+HEADER: :tangle "../src/sisudoc/io_out/rgx_latex.d" #+HEADER: :noweb yes #+BEGIN_SRC d <<doc_header_including_copyright_and_license>> /++ regex: regular expressions used in sisu document parser +/ module sisudoc.io_out.rgx_latex; @safe: static template spineRgxLSC() { static struct RgxLSC { <<sp_ch_latex_rgx>> } } #+END_SRC *** latex special characters #+NAME: sp_ch_latex_rgx #+BEGIN_SRC d static latex_special_char = ctRegex!(`([%${}_#&\\])`); 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_identify_inline_fontface = ctRegex!(`\\([_#$]┨.+?┣)\\([_#$])`, "mg"); static latex_clean_internal_link = ctRegex!(`^(?:#|¤\S+?#)`, "m"); static latex_clean_bookindex_linebreak = ctRegex!(`\s*\\\\\\\\\s*`, "m"); #+END_SRC * document header including copyright & license #+NAME: doc_header_including_copyright_and_license #+HEADER: :noweb yes #+BEGIN_SRC emacs-lisp <<./sisudoc_spine_version_info_and_doc_header_including_copyright_and_license.org:spine_doc_header_including_copyright_and_license()>> #+END_SRC * __END__