sdp, abstract objects, a start

1 files changed, 195 insertions, 0 deletions

diff --git a/lib/sdp/ao_rgx.d b/lib/sdp/ao_rgx.d
new file mode 100644
index 0000000..755ba11
--- /dev/null
+++ b/lib/sdp/ao_rgx.d
@@ -0,0 +1,195 @@
+/*
+#+OPTIONS: ^:nil _:nil#+OPTIONS: ^:nil _:nil
+* sisu_rgx.d
+*/
+mixin template RgxInit() {
+/*
+** misc
+*/
+  class Rgx {
+    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]$`);
+/*
+** insert markup file
+*/
+    static insert_src_fn_ssi_or_sst  = ctRegex!(`^<<\s*(?P<path>[a-zA-Z0-9._-]+/)*(?P<filename>[a-zA-Z0-9._-]+[.]ss[ti])$`);
+/*
+** header & comments
+*/
+    static comment                   = ctRegex!(`^%+ `);
+    static header                    = ctRegex!(`^@([a-z_]+):(?:\s|$)`);
+    static header_make               = ctRegex!(`^@(make):(?:\s|$)`);
+    static header_metadata           = ctRegex!(`^@([a-z_]+):(?:\s|$)`);
+    static header_sub                = ctRegex!(`^[ ]+:([a-z_]+):\s`);
+    static head_main                 = ctRegex!(`^@([a-z_]+):\s*(.*)`, "m");
+    static head_sub                  = ctRegex!(`^[ ]*:([a-z_]+):\s+(.+)`, "m");
+/*
+** heading & paragraph operators
+*/
+    static heading                   = ctRegex!(`^:?([A-D1-4])[~]([a-z0-9_.-]*[?]?) `);
+    static heading_marker            = ctRegex!(`^:?([A-D1-4])[~]`);
+    static heading_title             = ctRegex!(`^:?[A-D1-4][~][a-z0-9_.-]*[?]?\s+(.+?)$`);
+    static heading_all               = ctRegex!(`^:?([A-D1-4])[~]([a-z0-9_.-]*[?]?)\s+(.+?)$`); // test, particularly [2] name/hashtag which may or may not be, does this affect title [3]
+    static heading_biblio            = ctRegex!(`^:?(1)[~][!](biblio(?:graphy)?|references?)`);
+    static heading_glossary          = ctRegex!(`^:?(1)[~][!](glossary)`);
+    static para_bullet               = ctRegex!(`^_[*] `);
+    static para_bullet_indent        = ctRegex!(`^_([1-9])[*] `);
+    static para_indent               = ctRegex!(`^_([1-9]) `);
+    static para_indent_hang          = ctRegex!(`^_([0-9])_([0-9]) `);
+    static para_attribs              = ctRegex!(`^_(([0-9])(_([0-9]))?|_([1-9])?[*]) `);
+/*
+** blocked markup tics
+*/
+    static block_tic_code_open       = ctRegex!("^`{3} (code)");
+    static block_tic_poem_open       = ctRegex!("^`{3} (poem)");
+    static block_tic_group_open      = ctRegex!("^`{3} (group)");
+    static block_tic_block_open      = ctRegex!("^`{3} (block)");
+    static block_tic_quote_open      = ctRegex!("^`{3} (quote)");
+    static block_tic_table_open      = ctRegex!("^`{3} (table)");
+    static block_tic_close           = ctRegex!("^(`{3})$","m");
+/*
+** 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)`);
+/*
+** 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>.+?)\}#`);
+/*
+** 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");
+/*
+** inline markup book index
+*/
+    static book_index                = ctRegex!(`^=\{\s*(.+?)\}$`, "m");
+    static book_index_open           = ctRegex!(`^=\{\s*([^}]+?)$`);
+    static book_index_close          = ctRegex!(`^(.*?)\}$`, "m"); // strip
+/*
+** no ocn object
+*/
+    static ocn_off                   = ctRegex!(`~#$`, "m");
+    static ocn_off_dh                = ctRegex!(`-#$`, "m");
+    static ocn_off_all               = ctRegex!(`[~-]#$`, "m");
+/*
+** no ocn block
+*/
+    static ocn_off_block             = ctRegex!(`^--~#$`);
+    static ocn_off_block_dh          = ctRegex!(`^---#$`);
+    static ocn_off_block_close       = ctRegex!(`^--\+#$`);
+    static ocn_block_marks           = ctRegex!(`^--[+~-]#$`);
+/*
+** ignore outside code blocks
+*/
+    static regular_parse_skip        = ctRegex!(`^(--[+~-]#|-[\\]{2}-|=[.\\]{2}=)$`); // not structural info
+/*
+** line& page breaks
+*/
+    static break_line_within_object  = ctRegex!(`[\\]{2}( |$)`);
+// 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]+)`);
+/*
+** json
+*/
+    static tailing_comma             = ctRegex!(`,$`, "m");
+/*
+** head
+*/
+    static main_headers              = ctRegex!(`^(?:creator|title|rights|date|original|classify|identifier|notes|publisher|make|links)$`, "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");
+/*
+** 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)$`);
+/*
+** 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+)`);
+/*
+* url matching     http://url.is/got and { text }http://url.is/got
+* image matching
+* header substitution & bold & italics lists
+*/
+  }
+}