aboutsummaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
-rw-r--r--org/default_regex.org79
-rw-r--r--src/doc_reform/meta/rgx.d71
-rw-r--r--src/doc_reform/output/rgx.d36
3 files changed, 2 insertions, 184 deletions
diff --git a/org/default_regex.org b/org/default_regex.org
index 08af2ce..e14748f 100644
--- a/org/default_regex.org
+++ b/org/default_regex.org
@@ -51,10 +51,9 @@ static template DocReformRgxInit() {
#+name: meta_rgx
#+BEGIN_SRC d
/+ misc +/
-static true_dollar = ctRegex!(`\$`, "gm");
+// static true_dollar = ctRegex!(`\$`, "gm");
static sep = ctRegex!(`ā£`, "gm");
static flag_action = ctRegex!(`^(--[a-z][a-z0-9-]+)$`);
-static flag_action_str = ctRegex!(` (--[a-z][a-z0-9-]+)`);
static within_quotes = ctRegex!(`"(.+?)"`, "m");
static yaml_tag_is_str = ctRegex!(`:str$`);
static yaml_tag_is_int = ctRegex!(`:int$`);
@@ -79,7 +78,6 @@ static table_col_delimiter = ctRegex!("[ ]*\n+", "mg"
static table_row_delimiter = ctRegex!("\n[ ]*\n+", "mg");
static table_row_delimiter_special = ctRegex!("[ ]*\n", "mg");
static table_col_delimiter_special = ctRegex!("[ ]*[|][ ]*", "mg");
-static levels_markup = ctRegex!(`^[A-D1-4]$`);
static levels_numbered = ctRegex!(`^[0-9]$`);
static levels_numbered_headings = ctRegex!(`^[0-7]$`);
static numeric = ctRegex!(`[ 0-9,.-]+`);
@@ -92,7 +90,6 @@ static numeric_col = ctRegex!(`^[ 0-9,.%$Ā£ā‚
#+BEGIN_SRC d
/+ comments +/
static comment = ctRegex!(`^%+ `);
-static comments = ctRegex!(`^%+ |^%+$`);
#+END_SRC
** config
@@ -100,8 +97,6 @@ static comments = ctRegex!(`^%+ |^%+$`);
#+name: meta_rgx
#+BEGIN_SRC d
/+ header +/
-static make_simple_substitutions_rb = ctRegex!(`(?P<substitution>/(?P<match>.+?)/,[ ]*['"](?P<replace>.+?)['"])`);
-static make_simple_substitutions_d = ctRegex!(`(?P<substitution>` ~ '`' ~ `(?P<match>.+?)` ~ '`' ~ `,[ ]*['"](?P<replace>.+?)['"])`);
#+END_SRC
** native headers
@@ -133,9 +128,6 @@ static heading_extract_unnamed_anchor_tag = ctRegex!(`^:?[A-D1-4][~]
static heading_marker_missing_tag = ctRegex!(`^:?([A-D1-4])[~] `);
static heading_anchor_tag_plus_colon = ctRegex!(`^:?([A-D1-4][~])([a-z0-9_.:-]+) `,"i");
static heading_marker_tag_has_colon = ctRegex!(`([:])`);
-static heading_title = ctRegex!(`^:?[A-D1-4][~][a-z0-9_.-]*[?]?\s+(.+?)$`);
-static heading_all = ctRegex!(`^:?([A-D1-4])[~]([a-z0-9_.-]*[?]?)\s+(.+?)$`);
-static heading_backmatter = ctRegex!(`^:?1[~][!](glossary|bibliography|biblio|blurb)\s+`,"i");
static heading_biblio = ctRegex!(`^:?(1)[~][!](biblio(?:graphy)?|references?)`);
static heading_glossary = ctRegex!(`^:?(1)[~][!](glossary)`);
static heading_blurb = ctRegex!(`^:?(1)[~][!](blurb)`);
@@ -165,7 +157,6 @@ static block_poem_open = ctRegex!("^((poem(?:[(][
#+name: meta_rgx
#+BEGIN_SRC d
/+ blocked markup tics +/
-static block_tic_open = ctRegex!("^`{3} (code(?:[.][a-z][0-9a-z#+_]+)?|(?:poem|group|block|quote)(?:[.][a-z][0-9a-z_]+)?|table)");
static block_tic_code_open = ctRegex!("^`{3} code(?:[.](?P<syntax>[a-z][0-9a-z#+_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?");
static block_tic_poem_open = ctRegex!("^`{3} poem(?:[.](?P<lang>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?");
static block_tic_group_open = ctRegex!("^`{3} group(?:[.](?P<lang>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?");
@@ -180,7 +171,6 @@ static block_tic_close = ctRegex!("^(`{3})$","m")
#+name: meta_rgx
#+BEGIN_SRC d
/+ blocked markup curly +/
-static block_curly_open = ctRegex!(`^((?:code([.][a-z][0-9a-z#+_]+)?|(?:poem|group|block|quote)(?:[.][a-z][0-9a-z_]+)?|table)(?:[(][ a-zA-Z0-9;:,]*[)])?[{][ ]*$)`);
static block_curly_code_open = ctRegex!(`^(?:code(?:[.](?P<syntax>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`);
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;:,]*)[)])?[{][ ]*$)`);
@@ -225,8 +215,6 @@ static table_col_separator_nl = ctRegex!(`[ā”Š]$`, "mg")
/+ inline markup footnotes endnotes +/
static inline_notes_curly_gen = ctRegex!(`~\{.+?\}~`, "m");
static inline_notes_curly = ctRegex!(`~\{\s*(.+?)\}~`, "mg");
-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");
@@ -235,12 +223,6 @@ static inline_notes_square = ctRegex!(`~\[\s*(.+?)\]~
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 inline_curly_delimiter_open_regular = ctRegex!(`~\{\s*`, "m");
-static inline_curly_delimiter_open_symbol_star = ctRegex!(`~\{[*]\s`, "m");
-static inline_curly_delimiter_open_symbol_plus = ctRegex!(`~\{[+]\s`, "m");
-static inline_curly_delimiter_open_star_or_plus = ctRegex!(`~\{[+*]`, "m");
-static inline_curly_delimiter_close_regular = ctRegex!(`\s*\}~`, "m");
-static inline_text_and_note_curly = ctRegex!(`(?P<text>.+?)(?:(?:[~])[{][*+ ]*)(?P<note>.+?)(?:[}][~])`, "mg");
static note_ref = ctRegex!(`^\S+?noteref_(?P<ref>[0-9]+)`, "mg"); // {^{73.}^}#noteref_73
#+END_SRC
@@ -267,13 +249,6 @@ static smid_image_generic = ctRegex!(`(?:^|[ ]|[^\S
static smid_image_with_dimensions = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)[{ā”„](?:~\^\s+|\s*))(?P<image>[a-zA-Z0-9._-]+?\.(?:png|gif|jpg))\s+(?P<width>\d+)x(?P<height>\d+)\s*(?P<post>(?:.*?)\s*[}ā”](?:image|ā”¤.*?ā”œ|(?:(?:https?|git):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
static smid_mod_image_without_dimensions = ctRegex!(`[{ā”„](?:~\^\s+|\s*)ā˜¼\S+\.(?:png|gif|jpg),w0h0.*[}ā”](?:image|ā”¤.*?ā”œ|(?: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):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
-static smid_a_image_generic = ctRegex!(`(?:^|[ ]|[^\S]?)[{](?:~\^\s+|\s*)\S+\.(?:png|gif|jpg).*?[}](?:image|(?:(?:https?|git):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
-static smid_a_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):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
-static smid_a_mod_image_without_dimensions = ctRegex!(`[{](?:~\^\s+|\s*)ā˜¼\S+\.(?:png|gif|jpg),w0h0.*[}](?:image|(?:https?|git):\/\/\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
-static smid_b_image = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)[ā”„](?:~\^\s+|\s*))(?P<image>[a-zA-Z0-9._-]+?\.(?:png|gif|jpg))(?P<post>(?:.*?)\s*[ā”](?:ā”¤.*?ā”œ|(?:(?:https?|git):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
-static smid_b_image_generic = ctRegex!(`(?:^|[ ]|[^\S]?)[ā”„](?:~\^\s+|\s*)\S+\.(?:png|gif|jpg).*?[ā”](?:ā”¤.*?ā”œ|(?:(?:https?|git):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
-static smid_b_image_with_dimensions = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)[ā”„](?:~\^\s+|\s*))(?P<image>[a-zA-Z0-9._-]+?\.(?:png|gif|jpg))\s+(?P<width>\d+)x(?P<height>\d+)\s*(?P<post>(?:.*?)\s*[ā”](?:ā”¤.*?ā”œ|(?:(?:https?|git):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
-static smid_b_mod_image_without_dimensions = ctRegex!(`[ā”„](?:~\^\s+|\s*)ā˜¼\S+\.(?:png|gif|jpg),w0h0.*[ā”](?:ā”¤.*?ā”œ|(?:https?|git):\/\/\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
static smid_image_delimit = ctRegex!(`(?P<pre>^|[ ]|[^\S]?)\{\s*(?P<text>.+?)\s*\}(?:image)(?=[;:!,?.]?([ )\]]|$))`, "mg");
#+END_SRC
@@ -338,21 +313,7 @@ static skip_from_regular_parse = ctRegex!(`^(--[+~-]#|-[\\]{2}-|=[.\\]{2}=)$`
#+name: meta_rgx
#+BEGIN_SRC d
/+ line & page breaks +/
-static break_line_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!(`怏`);
-static parent = ctRegex!(`([0-7]):([0-9]+)`);
-static header_regex_content = ctRegex!(`([0-7]):([0-9]+)`);
-#+END_SRC
-
-** json :json:
-
-#+name: meta_rgx
-#+BEGIN_SRC d
-/+ json +/
-static tailing_comma = ctRegex!(`,$`, "m");
#+END_SRC
** biblio tags :biblio:tags:
@@ -390,8 +351,6 @@ static topic_register_multiple_sub_terms_split = ctRegex!(`ā£([^|ā£]+(?
#+name: meta_rgx
#+BEGIN_SRC d
/+ language codes +/
-auto language_codes =
- ctRegex!("(am|bg|bn|br|ca|cs|cy|da|de|el|en|eo|es|et|eu|fi|fr|ga|gl|he|hi|hr|hy|ia|is|it|ja|ko|la|lo|lt|lv|ml|mr|nl|no|nn|oc|pl|pt|pt_BR|ro|ru|sa|se|sk|sl|sq|sr|sv|ta|te|th|tk|tr|uk|ur|vi|zh)");
auto language_code_and_filename =
ctRegex!("(?:^|[/])(am|bg|bn|br|ca|cs|cy|da|de|el|en|eo|es|et|eu|fi|fr|ga|gl|he|hi|hr|hy|ia|is|it|ja|ko|la|lo|lt|lv|ml|mr|nl|no|nn|oc|pl|pt|pt_BR|ro|ru|sa|se|sk|sl|sq|sr|sv|ta|te|th|tk|tr|uk|ur|vi|zh)/[A-Za-z0-9._-].+?[.](?:sst|ssm)$");
#+END_SRC
@@ -436,8 +395,6 @@ static xhtml_line_break = ctRegex!(` [\\]{2}`, "m"); /
#+name: sp_ch_xhtml_rgx
#+BEGIN_SRC d
-static latex_special_char_shortlist = ctRegex!(`([%$_#&\\])`);
-static latex_special_char_curlybraces = ctRegex!(`([{}])`);
static latex_special_char = ctRegex!(`([%${}_#&\\])`);
static latex_special_char_for_escape = ctRegex!(`([%${}_#\\])`);
static latex_special_char_for_escape_and_braces = ctRegex!(`([&])`);
@@ -456,17 +413,10 @@ static latex_clean_bookindex_linebreak = ctRegex!(`\s*\\\\\\\\\s*`, "
#+name: prgmkup_rgx
#+BEGIN_SRC d
static newline = ctRegex!("\n", "mg");
-static strip_br = ctRegex!("^<br>\n|<br>\n*$");
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 spaces_multiple = ctRegex!(`(?P<multiple_spaces>[ ]{2,})`, "mg");
-static two_spaces = ctRegex!(`[ ]{2}`, "mg");
static nbsp_char = ctRegex!(`ā–‘`, "mg");
-static nbsp_chars_line_start = ctRegex!(`^ā–‘+`, "mg");
-static nbsp_and_space = ctRegex!(`&nbsp;[ ]`, "mg");
-static nbsp_char_and_space = ctRegex!(`ā–‘[ ]`, "mg");
-static special_markup_chars = ctRegex!(`[怐怑怖怗ā”„ā”ā”¤ā”œĀ¤ā–‘ā”˜ā”™ā”šā”¼ā”æā•‚ā”Šā”ā”šā”†ā– ]`, "mg");
#+END_SRC
** filename (& path) (including insert file) :insert:file:path:filename:
@@ -477,20 +427,14 @@ static src_pth_sst_or_ssm = ctRegex!(`^(?P<path>[/]?
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)$`);
-static src_pth_unzip_pod = ctRegex!(`^(?P<path>media/text/[a-z]{2}/)*(?P<filename>[a-zA-Z0-9._-]+[.]ss[im])$`);
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))$`);
-static pod_content_location =
- ctRegex!(`^(?P<filename>[a-zA-Z0-9._-]+[.]ss[tm])(?P<languages>(?:\s+[a-z]{2}(?:,|$))+)`, "mg");
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_text = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]sst)$`);
-static src_fn_insert = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ssi)$`);
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})$`); // formalizes dir structure
-static src_base_parent_path = ctRegex!(`(?P<dir>(?:[/a-zA-Z0-9._-]+))(?:/media/text/[a-z]{2})$`); // 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})$`); // formalizes dir structure
#+END_SRC
@@ -501,17 +445,10 @@ static src_formalised_file_path_parts = ctRegex!(`(?P<pth>(?:[/a
#+name: prgmkup_rgx
#+BEGIN_SRC d
/+ line breaks +/
-static empty_line = ctRegex!(`^\s*$`);
-static empty_block = ctRegex!(`^\s*$`, "mg");
-static br_line_natural = ctRegex!(`\n`, "mg");
static br_empty_line = ctRegex!(`\n[ ]*\n`, "mg");
static br_newlines_linebreaks = ctRegex!(`[\nā”˜ā”™]`, "mg");
static br_line = ctRegex!(`ā”˜`, "mg");
static br_nl = ctRegex!(`ā”™`, "mg");
-static br_paragraph = ctRegex!(`ā”š`, "mg");
-static br_page_line = ctRegex!(`ā”¼`, "mg");
-static br_page = ctRegex!(`ā”æ`, "mg");
-static br_page_new = ctRegex!(`ā•‚`, "mg");
#+END_SRC
*** inline (internal program) markup footnotes endnotes :inline:footnote:
@@ -531,11 +468,6 @@ static inline_notes_al_special_char_note = ctRegex!(`怐(?P<char>(?
static inline_al_delimiter_open_regular = ctRegex!(`怐\s`, "m");
static inline_al_delimiter_open_symbol_star = ctRegex!(`怐[*]\s`, "m");
static inline_al_delimiter_open_symbol_plus = ctRegex!(`怐[+]\s`, "m");
-static inline_al_delimiter_close_regular = ctRegex!(`怑`, "m");
-static inline_al_delimiter_open_and_close_regular = ctRegex!(`怐|怑`, "m");
-static inline_al_delimiter_open_asterisk = ctRegex!(`怐\*`, "m");
-static inline_al_delimiter_open_plus = ctRegex!(`怐\+`, "m");
-static inline_text_and_note_al = ctRegex!(`(?P<text>.+?)怐(?:[*+ ]*)(?P<note>.+?)怑`, "mg");
static inline_text_and_note_al_ = ctRegex!(`(.+?(?:怐[*+]*\s+.+?怑|$))`, "mg");
#+END_SRC
@@ -548,7 +480,6 @@ static inline_image = ctRegex!(`(?P<pre>ā”„)ā˜
static inline_image_without_dimensions = ctRegex!(`(?P<pre>ā”„)ā˜¼(?P<imginf>(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>0)h(?P<height>0))\s*(?P<post>.*?ā”ā”¤.*?ā”œ)`, "mg");
static inline_image_info = ctRegex!(`ā˜¼?(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+)`, "mg");
static inline_link_anchor = ctRegex!(`ā”ƒ(?P<anchor>\S+?)ā”ƒ`, "mg"); // TODO *~text_link_anchor
-static inline_link_ = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤(?P<link>.+?)ā”œ`, "mg");
static inline_link = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤(?P<link>#?(\S+?))ā”œ`, "mg");
static inline_link_empty = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤ā”œ`, "mg");
static inline_link_number = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤(?P<num>[0-9]+)ā”œ`, "mg"); // not used
@@ -557,17 +488,14 @@ static inline_link_stow_uri = ctRegex!(`ā”„(?P<text>.+
static inline_link_hash = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤(?P<link>#(?P<segname>\S+?))ā”œ`, "mg");
static inline_link_clean = ctRegex!(`ā”¤(?:.+?)ā”œ|[ā”„ā”]`, "mg");
static inline_link_toc_to_backmatter = ctRegex!(`ā”¤#(?P<link>endnotes|bibliography|bookindex|glossary|blurb)ā”œ`, "mg");
-static inline_a_url = ctRegex!(`(ā”¤)([^\sā”„ā”ā”¤ā”œ]+)(ā”œ)`, "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>[^/]+)$`, "mg");
static inline_link_subtoc = ctRegex!(`^(?P<level>[5-7])~ ā”„(?P<text>.+?)ā”ā”¤(?P<link>.+?)ā”œ`, "mg");
-static fn_suffix = ctRegex!(`\.fnSuffix`, "mg");
static inline_link_fn_suffix = ctRegex!(`Ā¤(.+?)(\.fnSuffix)`, "mg");
static inline_seg_link = ctRegex!(`(Ā¤)(?:.+?)\.fnSuffix`, "mg");
static mark_internal_site_lnk = ctRegex!(`Ā¤`, "mg");
static quotation_mark_sql_insert_delimiter = ctRegex!("[']", "mg");
-static quotation_mark_various = ctRegex!(q"ā”ƒ['ā€˜ā€™ā€œā€"`Ā“ĀØ]ā”ƒ", "mg");
#+END_SRC
*** inline markup font face mod :inline:font:face:
@@ -575,8 +503,6 @@ static quotation_mark_various = ctRegex!(q"ā”ƒ['ā€˜ā€™ā€
#+name: prgmkup_rgx
#+BEGIN_SRC d
/+ inline markup font face mod +/
-static inline_mark_faces = ctRegex!(`(?P<markup>(?P<mod>[*!/_^,+#"-])\{(?P<text>.+?)\}[*!/_^,+#"-])`, "mg");
-static inline_mark_faces_to_mod = ctRegex!(`(?P<mod>[*!/_^,+#"-])\{(?P<text>.+?)\}([*!/_^,+#"-])`, "mg");
static inline_mark_emphasis = ctRegex!(`(?P<mark>[*])\{(?P<text>.+?)\}[*]`, "mg");
static inline_mark_bold = ctRegex!(`(?P<mark>[!])\{(?P<text>.+?)\}[!]`, "mg");
static inline_mark_underscore = ctRegex!(`(?P<mark>[_])\{(?P<text>.+?)\}[_]`, "mg");
@@ -587,7 +513,6 @@ static inline_mark_strike = ctRegex!(`(?P<mark>[-])\{(
static inline_mark_insert = ctRegex!(`(?P<mark>[+])\{(?P<text>.+?)\}[+]`, "mg");
static inline_mark_mono = ctRegex!(`(?P<mark>[#])\{(?P<text>.+?)\}[#]`, "mg");
static inline_mark_cite = ctRegex!(`(?P<mark>["])\{(?P<text>.+?)\}["]`, "mg");
-static inline_mark_fontface_clean = ctRegex!(`[*!_/^,+#ā– "-]\{|\}[*!_/^,+#ā– "-]`, "mg");
#+END_SRC
#+name: prgmkup_rgx
@@ -597,13 +522,11 @@ static inline_emphasis_line = ctRegex!(`^\*_ (?P<text>
static inline_bold_line = ctRegex!(`^!_ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
static inline_italics_line = ctRegex!(`^/_ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
static inline_underscore_line = ctRegex!(`^__ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
-static no_header_rgx = ctRegex!(`^=NULL$`);
#+END_SRC
#+name: prgmkup_rgx
#+BEGIN_SRC d
/+ inline markup font face mod +/
-static inline_faces = ctRegex!(`(?P<markup>(?P<mod>[*!_^,+ā– ā€–-])ā”Ø(?P<text>.+?)ā”£[*!_^,+ā– ā€–-])`, "mg");
static inline_emphasis = ctRegex!(`[*]ā”Ø(?P<text>.+?)ā”£[*]`, "mg");
static inline_bold = ctRegex!(`[!]ā”Ø(?P<text>.+?)ā”£[!]`, "mg");
static inline_underscore = ctRegex!(`[_]ā”Ø(?P<text>.+?)ā”£[_]`, "mg");
diff --git a/src/doc_reform/meta/rgx.d b/src/doc_reform/meta/rgx.d
index 11f4aa5..a7826be 100644
--- a/src/doc_reform/meta/rgx.d
+++ b/src/doc_reform/meta/rgx.d
@@ -6,10 +6,9 @@ static template DocReformRgxInit() {
import doc_reform.meta.defaults;
static struct Rgx {
/+ misc +/
- static true_dollar = ctRegex!(`\$`, "gm");
+ // static true_dollar = ctRegex!(`\$`, "gm");
static sep = ctRegex!(`ā£`, "gm");
static flag_action = ctRegex!(`^(--[a-z][a-z0-9-]+)$`);
- static flag_action_str = ctRegex!(` (--[a-z][a-z0-9-]+)`);
static within_quotes = ctRegex!(`"(.+?)"`, "m");
static yaml_tag_is_str = ctRegex!(`:str$`);
static yaml_tag_is_int = ctRegex!(`:int$`);
@@ -34,17 +33,13 @@ static template DocReformRgxInit() {
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_markup = ctRegex!(`^[A-D1-4]$`);
static levels_numbered = ctRegex!(`^[0-9]$`);
static levels_numbered_headings = ctRegex!(`^[0-7]$`);
static numeric = ctRegex!(`[ 0-9,.-]+`);
static numeric_col = ctRegex!(`^[ 0-9,.%$Ā£ā‚¤Š„ā‚¬ā‚¬Ā„()-]+$`);
/+ comments +/
static comment = ctRegex!(`^%+ `);
- static comments = ctRegex!(`^%+ |^%+$`);
/+ header +/
- static make_simple_substitutions_rb = ctRegex!(`(?P<substitution>/(?P<match>.+?)/,[ ]*['"](?P<replace>.+?)['"])`);
- static make_simple_substitutions_d = ctRegex!(`(?P<substitution>` ~ '`' ~ `(?P<match>.+?)` ~ '`' ~ `,[ ]*['"](?P<replace>.+?)['"])`);
/+ header +/
static variable_doc_title = ctRegex!(`@title`);
static variable_doc_author = ctRegex!(`@author|@creator`);
@@ -63,9 +58,6 @@ static template DocReformRgxInit() {
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_title = ctRegex!(`^:?[A-D1-4][~][a-z0-9_.-]*[?]?\s+(.+?)$`);
- static heading_all = ctRegex!(`^:?([A-D1-4])[~]([a-z0-9_.-]*[?]?)\s+(.+?)$`);
- static heading_backmatter = ctRegex!(`^:?1[~][!](glossary|bibliography|biblio|blurb)\s+`,"i");
static heading_biblio = ctRegex!(`^:?(1)[~][!](biblio(?:graphy)?|references?)`);
static heading_glossary = ctRegex!(`^:?(1)[~][!](glossary)`);
static heading_blurb = ctRegex!(`^:?(1)[~][!](blurb)`);
@@ -82,7 +74,6 @@ static template DocReformRgxInit() {
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;:,]*[)])?)");
/+ blocked markup tics +/
- static block_tic_open = ctRegex!("^`{3} (code(?:[.][a-z][0-9a-z#+_]+)?|(?:poem|group|block|quote)(?:[.][a-z][0-9a-z_]+)?|table)");
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;:,]*)[)])?");
@@ -91,7 +82,6 @@ static template DocReformRgxInit() {
static block_tic_table_open = ctRegex!("^`{3} table(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?"); // ctRegex!("^`{3} table(?:\(.*?\))?");
static block_tic_close = ctRegex!("^(`{3})$","m");
/+ blocked markup curly +/
- static block_curly_open = ctRegex!(`^((?:code([.][a-z][0-9a-z#+_]+)?|(?:poem|group|block|quote)(?:[.][a-z][0-9a-z_]+)?|table)(?:[(][ a-zA-Z0-9;:,]*[)])?[{][ ]*$)`);
static block_curly_code_open = ctRegex!(`^(?:code(?:[.](?P<syntax>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`);
static block_curly_code_close = ctRegex!(`^([}]code)`);
static block_curly_poem_open = ctRegex!(`^(poem(?:[.](?P<lang>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`);
@@ -116,8 +106,6 @@ static template DocReformRgxInit() {
/+ inline markup footnotes endnotes +/
static inline_notes_curly_gen = ctRegex!(`~\{.+?\}~`, "m");
static inline_notes_curly = ctRegex!(`~\{\s*(.+?)\}~`, "mg");
- 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");
@@ -126,12 +114,6 @@ static template DocReformRgxInit() {
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 inline_curly_delimiter_open_regular = ctRegex!(`~\{\s*`, "m");
- static inline_curly_delimiter_open_symbol_star = ctRegex!(`~\{[*]\s`, "m");
- static inline_curly_delimiter_open_symbol_plus = ctRegex!(`~\{[+]\s`, "m");
- static inline_curly_delimiter_open_star_or_plus = ctRegex!(`~\{[+*]`, "m");
- static inline_curly_delimiter_close_regular = ctRegex!(`\s*\}~`, "m");
- static inline_text_and_note_curly = ctRegex!(`(?P<text>.+?)(?:(?:[~])[{][*+ ]*)(?P<note>.+?)(?:[}][~])`, "mg");
static note_ref = ctRegex!(`^\S+?noteref_(?P<ref>[0-9]+)`, "mg"); // {^{73.}^}#noteref_73
static webserv_url_doc_root = ctRegex!(`(?P<url>(?P<domain>https?:\/\/[^ /]+)\/(?P<path>\S*))`, "mg");
static smid_inline_url_generic = ctRegex!(`(?:^|[}(\[ ])(?:(?:https?|git):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)[a-zA-Z0-9_#]`, "mg");
@@ -146,13 +128,6 @@ static template DocReformRgxInit() {
static smid_image_with_dimensions = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)[{ā”„](?:~\^\s+|\s*))(?P<image>[a-zA-Z0-9._-]+?\.(?:png|gif|jpg))\s+(?P<width>\d+)x(?P<height>\d+)\s*(?P<post>(?:.*?)\s*[}ā”](?:image|ā”¤.*?ā”œ|(?:(?:https?|git):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
static smid_mod_image_without_dimensions = ctRegex!(`[{ā”„](?:~\^\s+|\s*)ā˜¼\S+\.(?:png|gif|jpg),w0h0.*[}ā”](?:image|ā”¤.*?ā”œ|(?: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):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
- static smid_a_image_generic = ctRegex!(`(?:^|[ ]|[^\S]?)[{](?:~\^\s+|\s*)\S+\.(?:png|gif|jpg).*?[}](?:image|(?:(?:https?|git):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
- static smid_a_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):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
- static smid_a_mod_image_without_dimensions = ctRegex!(`[{](?:~\^\s+|\s*)ā˜¼\S+\.(?:png|gif|jpg),w0h0.*[}](?:image|(?:https?|git):\/\/\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
- static smid_b_image = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)[ā”„](?:~\^\s+|\s*))(?P<image>[a-zA-Z0-9._-]+?\.(?:png|gif|jpg))(?P<post>(?:.*?)\s*[ā”](?:ā”¤.*?ā”œ|(?:(?:https?|git):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
- static smid_b_image_generic = ctRegex!(`(?:^|[ ]|[^\S]?)[ā”„](?:~\^\s+|\s*)\S+\.(?:png|gif|jpg).*?[ā”](?:ā”¤.*?ā”œ|(?:(?:https?|git):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
- static smid_b_image_with_dimensions = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)[ā”„](?:~\^\s+|\s*))(?P<image>[a-zA-Z0-9._-]+?\.(?:png|gif|jpg))\s+(?P<width>\d+)x(?P<height>\d+)\s*(?P<post>(?:.*?)\s*[ā”](?:ā”¤.*?ā”œ|(?:(?:https?|git):\/\/|Ā¤?\.\.\/|Ā¤?\.\/|Ā¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
- static smid_b_mod_image_without_dimensions = ctRegex!(`[ā”„](?:~\^\s+|\s*)ā˜¼\S+\.(?:png|gif|jpg),w0h0.*[ā”](?:ā”¤.*?ā”œ|(?:https?|git):\/\/\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
static smid_image_delimit = ctRegex!(`(?P<pre>^|[ ]|[^\S]?)\{\s*(?P<text>.+?)\s*\}(?:image)(?=[;:!,?.]?([ )\]]|$))`, "mg");
/+ inline markup book index +/
static book_index = ctRegex!(`^=\{\s*(?P<bookindex>.+?)\}$`, "m");
@@ -180,15 +155,7 @@ static template DocReformRgxInit() {
/+ ignore outside code blocks +/
static skip_from_regular_parse = ctRegex!(`^(--[+~-]#|-[\\]{2}-|=[.\\]{2}=)$`);
/+ line & page breaks +/
- static break_line_within_object = ctRegex!(`[\\]{2}( |$)`);
- static break_page = ctRegex!(`^-[\\]{2}-$`);
- static break_page_new = ctRegex!(`^=[\\]{2}=$`);
- static break_page_line_across = ctRegex!(`^=[.]{2}=$`);
static break_string = ctRegex!(`怏`);
- static parent = ctRegex!(`([0-7]):([0-9]+)`);
- static header_regex_content = ctRegex!(`([0-7]):([0-9]+)`);
- /+ json +/
- static tailing_comma = ctRegex!(`,$`, "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)$`);
@@ -202,53 +169,31 @@ static template DocReformRgxInit() {
static topic_register_sub_terms_split = ctRegex!(`\s*\|\s*`);
static topic_register_multiple_sub_terms_split = ctRegex!(`ā£([^|ā£]+(?:\|[^|ā£]+)+)`);
/+ language codes +/
- auto language_codes =
- ctRegex!("(am|bg|bn|br|ca|cs|cy|da|de|el|en|eo|es|et|eu|fi|fr|ga|gl|he|hi|hr|hy|ia|is|it|ja|ko|la|lo|lt|lv|ml|mr|nl|no|nn|oc|pl|pt|pt_BR|ro|ru|sa|se|sk|sl|sq|sr|sv|ta|te|th|tk|tr|uk|ur|vi|zh)");
auto language_code_and_filename =
ctRegex!("(?:^|[/])(am|bg|bn|br|ca|cs|cy|da|de|el|en|eo|es|et|eu|fi|fr|ga|gl|he|hi|hr|hy|ia|is|it|ja|ko|la|lo|lt|lv|ml|mr|nl|no|nn|oc|pl|pt|pt_BR|ro|ru|sa|se|sk|sl|sq|sr|sv|ta|te|th|tk|tr|uk|ur|vi|zh)/[A-Za-z0-9._-].+?[.](?:sst|ssm)$");
static newline = ctRegex!("\n", "mg");
- static strip_br = ctRegex!("^<br>\n|<br>\n*$");
static space = ctRegex!(`[ ]`, "mg");
static spaces_keep = ctRegex!(`(?P<keep_spaces>^[ ]+|[ ]{2,})`, "mg"); // code, verse, block
static spaces_line_start = ctRegex!(`^(?P<opening_spaces>[ ]+)`, "mg");
- static spaces_multiple = ctRegex!(`(?P<multiple_spaces>[ ]{2,})`, "mg");
- static two_spaces = ctRegex!(`[ ]{2}`, "mg");
static nbsp_char = ctRegex!(`ā–‘`, "mg");
- static nbsp_chars_line_start = ctRegex!(`^ā–‘+`, "mg");
- static nbsp_and_space = ctRegex!(`&nbsp;[ ]`, "mg");
- static nbsp_char_and_space = ctRegex!(`ā–‘[ ]`, "mg");
- static special_markup_chars = ctRegex!(`[怐怑怖怗ā”„ā”ā”¤ā”œĀ¤ā–‘ā”˜ā”™ā”šā”¼ā”æā•‚ā”Šā”ā”šā”†ā– ]`, "mg");
static src_pth_sst_or_ssm = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.](?P<extension>ss[tm]))$`);
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)$`);
- static src_pth_unzip_pod = ctRegex!(`^(?P<path>media/text/[a-z]{2}/)*(?P<filename>[a-zA-Z0-9._-]+[.]ss[im])$`);
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))$`);
- static pod_content_location =
- ctRegex!(`^(?P<filename>[a-zA-Z0-9._-]+[.]ss[tm])(?P<languages>(?:\s+[a-z]{2}(?:,|$))+)`, "mg");
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_text = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]sst)$`);
- static src_fn_insert = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ssi)$`);
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})$`); // formalizes dir structure
- static src_base_parent_path = ctRegex!(`(?P<dir>(?:[/a-zA-Z0-9._-]+))(?:/media/text/[a-z]{2})$`); // 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})$`); // formalizes dir structure
/+ line breaks +/
- static empty_line = ctRegex!(`^\s*$`);
- static empty_block = ctRegex!(`^\s*$`, "mg");
- static br_line_natural = ctRegex!(`\n`, "mg");
static br_empty_line = ctRegex!(`\n[ ]*\n`, "mg");
static br_newlines_linebreaks = ctRegex!(`[\nā”˜ā”™]`, "mg");
static br_line = ctRegex!(`ā”˜`, "mg");
static br_nl = ctRegex!(`ā”™`, "mg");
- static br_paragraph = ctRegex!(`ā”š`, "mg");
- static br_page_line = ctRegex!(`ā”¼`, "mg");
- static br_page = ctRegex!(`ā”æ`, "mg");
- static br_page_new = ctRegex!(`ā•‚`, "mg");
/+ inline markup footnotes endnotes +/
static inline_notes_al = ctRegex!(`怐(?:[*+]\s+|\s*)(.+?)怑`, "mg");
static inline_notes_al_special = ctRegex!(`怐(?:[*+]\s+)(.+?)怑`, "mg"); // TODO remove match when special footnotes are implemented
@@ -262,18 +207,12 @@ static template DocReformRgxInit() {
static inline_al_delimiter_open_regular = ctRegex!(`怐\s`, "m");
static inline_al_delimiter_open_symbol_star = ctRegex!(`怐[*]\s`, "m");
static inline_al_delimiter_open_symbol_plus = ctRegex!(`怐[+]\s`, "m");
- static inline_al_delimiter_close_regular = ctRegex!(`怑`, "m");
- static inline_al_delimiter_open_and_close_regular = ctRegex!(`怐|怑`, "m");
- static inline_al_delimiter_open_asterisk = ctRegex!(`怐\*`, "m");
- static inline_al_delimiter_open_plus = ctRegex!(`怐\+`, "m");
- static inline_text_and_note_al = ctRegex!(`(?P<text>.+?)怐(?:[*+ ]*)(?P<note>.+?)怑`, "mg");
static inline_text_and_note_al_ = ctRegex!(`(.+?(?:怐[*+]*\s+.+?怑|$))`, "mg");
/+ inline markup links +/
static inline_image = ctRegex!(`(?P<pre>ā”„)ā˜¼(?P<imginf>(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+))\s*(?P<post>.*?ā”ā”¤.*?ā”œ)`, "mg");
static inline_image_without_dimensions = ctRegex!(`(?P<pre>ā”„)ā˜¼(?P<imginf>(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>0)h(?P<height>0))\s*(?P<post>.*?ā”ā”¤.*?ā”œ)`, "mg");
static inline_image_info = ctRegex!(`ā˜¼?(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+)`, "mg");
static inline_link_anchor = ctRegex!(`ā”ƒ(?P<anchor>\S+?)ā”ƒ`, "mg"); // TODO *~text_link_anchor
- static inline_link_ = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤(?P<link>.+?)ā”œ`, "mg");
static inline_link = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤(?P<link>#?(\S+?))ā”œ`, "mg");
static inline_link_empty = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤ā”œ`, "mg");
static inline_link_number = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤(?P<num>[0-9]+)ā”œ`, "mg"); // not used
@@ -282,20 +221,15 @@ static template DocReformRgxInit() {
static inline_link_hash = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤(?P<link>#(?P<segname>\S+?))ā”œ`, "mg");
static inline_link_clean = ctRegex!(`ā”¤(?:.+?)ā”œ|[ā”„ā”]`, "mg");
static inline_link_toc_to_backmatter = ctRegex!(`ā”¤#(?P<link>endnotes|bibliography|bookindex|glossary|blurb)ā”œ`, "mg");
- static inline_a_url = ctRegex!(`(ā”¤)([^\sā”„ā”ā”¤ā”œ]+)(ā”œ)`, "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>[^/]+)$`, "mg");
static inline_link_subtoc = ctRegex!(`^(?P<level>[5-7])~ ā”„(?P<text>.+?)ā”ā”¤(?P<link>.+?)ā”œ`, "mg");
- static fn_suffix = ctRegex!(`\.fnSuffix`, "mg");
static inline_link_fn_suffix = ctRegex!(`Ā¤(.+?)(\.fnSuffix)`, "mg");
static inline_seg_link = ctRegex!(`(Ā¤)(?:.+?)\.fnSuffix`, "mg");
static mark_internal_site_lnk = ctRegex!(`Ā¤`, "mg");
static quotation_mark_sql_insert_delimiter = ctRegex!("[']", "mg");
- static quotation_mark_various = ctRegex!(q"ā”ƒ['ā€˜ā€™ā€œā€"`Ā“ĀØ]ā”ƒ", "mg");
/+ inline markup font face mod +/
- static inline_mark_faces = ctRegex!(`(?P<markup>(?P<mod>[*!/_^,+#"-])\{(?P<text>.+?)\}[*!/_^,+#"-])`, "mg");
- static inline_mark_faces_to_mod = ctRegex!(`(?P<mod>[*!/_^,+#"-])\{(?P<text>.+?)\}([*!/_^,+#"-])`, "mg");
static inline_mark_emphasis = ctRegex!(`(?P<mark>[*])\{(?P<text>.+?)\}[*]`, "mg");
static inline_mark_bold = ctRegex!(`(?P<mark>[!])\{(?P<text>.+?)\}[!]`, "mg");
static inline_mark_underscore = ctRegex!(`(?P<mark>[_])\{(?P<text>.+?)\}[_]`, "mg");
@@ -306,15 +240,12 @@ static template DocReformRgxInit() {
static inline_mark_insert = ctRegex!(`(?P<mark>[+])\{(?P<text>.+?)\}[+]`, "mg");
static inline_mark_mono = ctRegex!(`(?P<mark>[#])\{(?P<text>.+?)\}[#]`, "mg");
static inline_mark_cite = ctRegex!(`(?P<mark>["])\{(?P<text>.+?)\}["]`, "mg");
- static inline_mark_fontface_clean = ctRegex!(`[*!_/^,+#ā– "-]\{|\}[*!_/^,+#ā– "-]`, "mg");
static inline_faces_line = ctRegex!(`^[*!/_]_ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`);
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}$)`);
static inline_underscore_line = ctRegex!(`^__ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
- static no_header_rgx = ctRegex!(`^=NULL$`);
/+ inline markup font face mod +/
- static inline_faces = ctRegex!(`(?P<markup>(?P<mod>[*!_^,+ā– ā€–-])ā”Ø(?P<text>.+?)ā”£[*!_^,+ā– ā€–-])`, "mg");
static inline_emphasis = ctRegex!(`[*]ā”Ø(?P<text>.+?)ā”£[*]`, "mg");
static inline_bold = ctRegex!(`[!]ā”Ø(?P<text>.+?)ā”£[!]`, "mg");
static inline_underscore = ctRegex!(`[_]ā”Ø(?P<text>.+?)ā”£[_]`, "mg");
diff --git a/src/doc_reform/output/rgx.d b/src/doc_reform/output/rgx.d
index 89d5858..1c569f9 100644
--- a/src/doc_reform/output/rgx.d
+++ b/src/doc_reform/output/rgx.d
@@ -6,48 +6,28 @@ static template DocReformOutputRgxInit() {
import doc_reform.output.defaults;
static struct Rgx {
static newline = ctRegex!("\n", "mg");
- static strip_br = ctRegex!("^<br>\n|<br>\n*$");
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 spaces_multiple = ctRegex!(`(?P<multiple_spaces>[ ]{2,})`, "mg");
- static two_spaces = ctRegex!(`[ ]{2}`, "mg");
static nbsp_char = ctRegex!(`ā–‘`, "mg");
- static nbsp_chars_line_start = ctRegex!(`^ā–‘+`, "mg");
- static nbsp_and_space = ctRegex!(`&nbsp;[ ]`, "mg");
- static nbsp_char_and_space = ctRegex!(`ā–‘[ ]`, "mg");
- static special_markup_chars = ctRegex!(`[怐怑怖怗ā”„ā”ā”¤ā”œĀ¤ā–‘ā”˜ā”™ā”šā”¼ā”æā•‚ā”Šā”ā”šā”†ā– ]`, "mg");
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_unzip_pod = ctRegex!(`^(?P<path>media/text/[a-z]{2}/)*(?P<filename>[a-zA-Z0-9._-]+[.]ss[im])$`);
static src_pth_types =
ctRegex!(`^(?P<path>[/]?[a-zA-Z0-9._-]+/)*(?P<gotfile>(?P<filename>[a-zA-Z0-9._-]+[.]ss[tm])|(?P<filelist>[a-zA-Z0-9._-]+/pod[.]manifest)|(?P<filezip>[a-zA-Z0-9._-]+[.]zip))$`);
- static pod_content_location =
- ctRegex!(`^(?P<filename>[a-zA-Z0-9._-]+[.]ss[tm])(?P<languages>(?:\s+[a-z]{2}(?:,|$))+)`, "mg");
static src_fn =
ctRegex!(`^([/]?(?:[a-zA-Z0-9._-]+/)*)(?P<fn_src>(?P<fn_base>[a-zA-Z0-9._-]+)[.](?P<fn_src_suffix>ss[tm]))$`);
static src_fn_master = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ssm)$`);
- static src_fn_text = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]sst)$`);
- static src_fn_insert = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ssi)$`);
static src_fn_find_inserts = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ss[im])$`);
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_base_parent_path = 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
/+ line breaks +/
- static empty_line = ctRegex!(`^\s*$`);
- static empty_block = ctRegex!(`^\s*$`, "mg");
- static br_line_natural = ctRegex!(`\n`, "mg");
static br_empty_line = ctRegex!(`\n[ ]*\n`, "mg");
static br_newlines_linebreaks = ctRegex!(`[\nā”˜ā”™]`, "mg");
static br_line = ctRegex!(`ā”˜`, "mg");
static br_nl = ctRegex!(`ā”™`, "mg");
- static br_paragraph = ctRegex!(`ā”š`, "mg");
- static br_page_line = ctRegex!(`ā”¼`, "mg");
- static br_page = ctRegex!(`ā”æ`, "mg");
- static br_page_new = ctRegex!(`ā•‚`, "mg");
/+ inline markup footnotes endnotes +/
static inline_notes_al = ctRegex!(`怐(?:[*+]\s+|\s*)(.+?)怑`, "mg");
static inline_notes_al_special = ctRegex!(`怐(?:[*+]\s+)(.+?)怑`, "mg"); // TODO remove match when special footnotes are implemented
@@ -61,18 +41,12 @@ static template DocReformOutputRgxInit() {
static inline_al_delimiter_open_regular = ctRegex!(`怐\s`, "m");
static inline_al_delimiter_open_symbol_star = ctRegex!(`怐[*]\s`, "m");
static inline_al_delimiter_open_symbol_plus = ctRegex!(`怐[+]\s`, "m");
- static inline_al_delimiter_close_regular = ctRegex!(`怑`, "m");
- static inline_al_delimiter_open_and_close_regular = ctRegex!(`怐|怑`, "m");
- static inline_al_delimiter_open_asterisk = ctRegex!(`怐\*`, "m");
- static inline_al_delimiter_open_plus = ctRegex!(`怐\+`, "m");
- static inline_text_and_note_al = ctRegex!(`(?P<text>.+?)怐(?:[*+ ]*)(?P<note>.+?)怑`, "mg");
static inline_text_and_note_al_ = ctRegex!(`(.+?(?:怐[*+]*\s+.+?怑|$))`, "mg");
/+ inline markup links +/
static inline_image = ctRegex!(`(?P<pre>ā”„)ā˜¼(?P<imginf>(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+))\s*(?P<post>.*?ā”ā”¤.*?ā”œ)`, "mg");
static inline_image_without_dimensions = ctRegex!(`(?P<pre>ā”„)ā˜¼(?P<imginf>(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>0)h(?P<height>0))\s*(?P<post>.*?ā”ā”¤.*?ā”œ)`, "mg");
static inline_image_info = ctRegex!(`ā˜¼?(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+)`, "mg");
static inline_link_anchor = ctRegex!(`ā”ƒ(?P<anchor>\S+?)ā”ƒ`, "mg"); // TODO *~text_link_anchor
- static inline_link_ = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤(?P<link>.+?)ā”œ`, "mg");
static inline_link = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤(?P<link>#?(\S+?))ā”œ`, "mg");
static inline_link_empty = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤ā”œ`, "mg");
static inline_link_number = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤(?P<num>[0-9]+)ā”œ`, "mg"); // not used
@@ -81,20 +55,15 @@ static template DocReformOutputRgxInit() {
static inline_link_hash = ctRegex!(`ā”„(?P<text>.+?)ā”ā”¤(?P<link>#(?P<segname>\S+?))ā”œ`, "mg");
static inline_link_clean = ctRegex!(`ā”¤(?:.+?)ā”œ|[ā”„ā”]`, "mg");
static inline_link_toc_to_backmatter = ctRegex!(`ā”¤#(?P<link>endnotes|bibliography|bookindex|glossary|blurb)ā”œ`, "mg");
- static inline_a_url = ctRegex!(`(ā”¤)([^\sā”„ā”ā”¤ā”œ]+)(ā”œ)`, "mg");
static url = ctRegex!(`https?://`, "mg");
static uri = ctRegex!(`(?:https?|git)://`, "mg");
static uri_identify_components = ctRegex!(`(?P<type>(?:https?|git)://)(?P<path>\S+?/)(?P<file>[^/]+)$`, "mg");
static inline_link_subtoc = ctRegex!(`^(?P<level>[5-7])~ ā”„(?P<text>.+?)ā”ā”¤(?P<link>.+?)ā”œ`, "mg");
- static fn_suffix = ctRegex!(`\.fnSuffix`, "mg");
static inline_link_fn_suffix = ctRegex!(`Ā¤(.+?)(\.fnSuffix)`, "mg");
static inline_seg_link = ctRegex!(`(Ā¤)(?:.+?)\.fnSuffix`, "mg");
static mark_internal_site_lnk = ctRegex!(`Ā¤`, "mg");
static quotation_mark_sql_insert_delimiter = ctRegex!("[']", "mg");
- static quotation_mark_various = ctRegex!(q"ā”ƒ['ā€˜ā€™ā€œā€"`Ā“ĀØ]ā”ƒ", "mg");
/+ inline markup font face mod +/
- static inline_mark_faces = ctRegex!(`(?P<markup>(?P<mod>[*!/_^,+#"-])\{(?P<text>.+?)\}[*!/_^,+#"-])`, "mg");
- static inline_mark_faces_to_mod = ctRegex!(`(?P<mod>[*!/_^,+#"-])\{(?P<text>.+?)\}([*!/_^,+#"-])`, "mg");
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");
@@ -105,15 +74,12 @@ static template DocReformOutputRgxInit() {
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");
- static inline_mark_fontface_clean = ctRegex!(`[*!_/^,+#ā– "-]\{|\}[*!_/^,+#ā– "-]`, "mg");
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}$)`);
- static no_header_rgx = ctRegex!(`^=NULL$`);
/+ inline markup font face mod +/
- static inline_faces = ctRegex!(`(?P<markup>(?P<mod>[*!_^,+ā– ā€–-])ā”Ø(?P<text>.+?)ā”£[*!_^,+ā– ā€–-])`, "mg");
static inline_emphasis = ctRegex!(`[*]ā”Ø(?P<text>.+?)ā”£[*]`, "mg");
static inline_bold = ctRegex!(`[!]ā”Ø(?P<text>.+?)ā”£[!]`, "mg");
static inline_underscore = ctRegex!(`[_]ā”Ø(?P<text>.+?)ā”£[_]`, "mg");
@@ -134,8 +100,6 @@ static template DocReformOutputRgxInit() {
static xhtml_less_than = ctRegex!(`[<]`, "m"); // &lt;
static xhtml_greater_than = ctRegex!(`[>]`, "m"); // &gt;
static xhtml_line_break = ctRegex!(` [\\]{2}`, "m"); // <br />
- static latex_special_char_shortlist = ctRegex!(`([%$_#&\\])`);
- static latex_special_char_curlybraces = ctRegex!(`([{}])`);
static latex_special_char = ctRegex!(`([%${}_#&\\])`);
static latex_special_char_for_escape = ctRegex!(`([%${}_#\\])`);
static latex_special_char_for_escape_and_braces = ctRegex!(`([&])`);