housekeepingdoc-reform_v0.5.0

1 files changed, 34 insertions, 9 deletions

diff --git a/src/doc_reform/meta/rgx.d b/src/doc_reform/meta/rgx.d
index 2bdb3ec..73900b6 100644
--- a/src/doc_reform/meta/rgx.d
+++ b/src/doc_reform/meta/rgx.d
@@ -88,8 +88,8 @@ static template DocReformRgxInit() {
     static heading_blurb_glossary                         = ctRegex!(`^:?(?:(1)[~][!](?:blurb|glossary)|[A-D1][~])`);
     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_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_.-]+)(?= |$)`,"i");
     /+ blocked markup +/
@@ -155,19 +155,37 @@ static template DocReformRgxInit() {
     static smid_inline_link_endnote_url_helper_punctuated = ctRegex!(`\{~\^\s+(?P<content>.+?)\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[.,;:?!]?([ ]|$))`, "mg");
     static smid_inline_link_endnote_url_helper            = ctRegex!(`\{~\^\s+(?P<content>.+?)\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+)`, "mg");
     static image                                           = ctRegex!(`([a-zA-Z0-9._-]+?\.(?:png|gif|jpg))`, "mg");
-    static smid_image                                      = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)[{┥](?:~\^\s+|\s*))(?P<image>\S+\.(?:png|gif|jpg))(?P<post>(?:.*?)\s*[}┝](?:image|┤.*?├|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "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>\S+\.(?:png|gif|jpg))\s+(?P<width>\d+)x(?P<height>\d+)\s*(?P<post>(?:.*?)\s*[}┝](?: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_a_image_generic                            = ctRegex!(`(?:^|[ ]|[^\S]?)[{](?:~\^\s+|\s*)\S+\.(?:png|gif|jpg).*?[}](?:image|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\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):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
+    static smid_a_mod_image_without_dimensions             = ctRegex!(`[{](?:~\^\s+|\s*)☼\S+\.(?:png|gif|jpg),w0h0.*[}](?:image|(?:https?|git):\/\/\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
+    static smid_b_image                                    = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)[┥](?:~\^\s+|\s*))(?P<image>[a-zA-Z0-9._-]+?\.(?:png|gif|jpg))(?P<post>(?:.*?)\s*[┝](?:┤.*?├|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
+    static smid_b_image_generic                            = ctRegex!(`(?:^|[ ]|[^\S]?)[┥](?:~\^\s+|\s*)\S+\.(?:png|gif|jpg).*?[┝](?:┤.*?├|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
+    static smid_b_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*[┝](?:┤.*?├|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
+    static smid_b_mod_image_without_dimensions             = ctRegex!(`[┥](?:~\^\s+|\s*)☼\S+\.(?:png|gif|jpg),w0h0.*[┝](?:┤.*?├|(?:https?|git):\/\/\S+?)(?=[;:!,?.]?([ )\]]|$))`, "mg");
     static smid_image_delimit                              = ctRegex!(`(?P<pre>^|[ ]|[^\S]?)\{\s*(?P<text>.+?)\s*\}(?:image)(?=[;:!,?.]?([ )\]]|$))`, "mg");
     /+ inline markup book index +/
     static book_index                                     = ctRegex!(`^=\{\s*(.+?)\}$`, "m");
     static book_index_open                                = ctRegex!(`^=\{\s*([^}]*?)$`);
     static book_index_close                               = ctRegex!(`^(.*?)\}$`, "m");
+    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");
     /+ no object_number object +/
     static object_number_off                            = ctRegex!(`~#[ ]*$`, "m");
     static object_number_off_dh                         = ctRegex!(`-#$`, "m");
     static object_number_off_all                        = ctRegex!(`[~-]#$`, "m");
+    static repeated_character_line_separator            = ctRegex!(`^(?:(?:(?:[.][ ]?){4,}|(?:[-][ ]?|[~][ ]?|[*][ ]?|[$][ ]?|[#][ ]?|[\\][ ]?|[/][ ]?){2,})\s*?)*$`);
     /+ no object_number block +/
     static object_number_off_block                      = ctRegex!(`^--~#$`);
     static object_number_off_block_dh                   = ctRegex!(`^---#$`);
@@ -231,6 +249,11 @@ static template DocReformRgxInit() {
     static src_base_parent_path                           = ctRegex!(`(?P<dir>(?:[/a-zA-Z0-9._-]+))(?:/media/text/[a-z]{2})$`); // 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!(`[\n┘┙]`, "mg");
     static br_line                                        = ctRegex!(`┘`, "mg");
     static br_nl                                          = ctRegex!(`┙`, "mg");
     static br_paragraph                                   = ctRegex!(`┚`, "mg");
@@ -241,22 +264,23 @@ static template DocReformRgxInit() {
     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_regular_number_note            = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)\s*】`, "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_al_delimiter_close_regular              = ctRegex!(`】`, "m");
     static inline_al_delimiter_open_and_close_regular     = ctRegex!(`【|】`, "m");
-    static inline_notes_delimiter_al_regular              = ctRegex!(`【(.+?)】`, "mg");
-    static inline_notes_delimiter_al_regular_number_note  = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)】`, "mg");
     static inline_al_delimiter_open_asterisk              = ctRegex!(`【\*`, "m");
     static inline_al_delimiter_open_plus                  = ctRegex!(`【\+`, "m");
     static inline_text_and_note_al                        = ctRegex!(`(?P<text>.+?)【(?:[*+ ]*)(?P<note>.+?)】`, "mg");
     static inline_text_and_note_al_                       = ctRegex!(`(.+?(?:【[*+]*\s+.+?】|$))`, "mg");
-    /+ inline markup footnotes endnotes +/
-    static inline_image                                   = ctRegex!(`(?P<pre>┥)☼(?P<imginf>(?P<img>\S+?\.(?: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>\S+?\.(?:jpg|gif|png)),w(?P<width>0)h(?P<height>0))\s*(?P<post>.*?┝┤.*?├)`, "mg");
+    /+ 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>.+?)├`, "mg");
     static inline_link                                    = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>\S+?)├`, "mg");
@@ -268,6 +292,7 @@ static template DocReformRgxInit() {
     static inline_link_clean                              = ctRegex!(`┤(?:.+?)├|[┥┝]`, "mg");
     static inline_a_url                                   = ctRegex!(`(┤)([^\s┥┝┤├]+)(├)`, "mg");
     static url                                            = ctRegex!(`https?://`, "mg");
+    static uri                                            = ctRegex!(`(?:https?|git)://`, "mg");
     static inline_link_subtoc                             = ctRegex!(`^(?P<level>[5-7])~ ┥(?P<text>.+?)┝┤(?P<link>.+?)├`, "mg");
     static fn_suffix                                      = ctRegex!(`\.fnSuffix`, "mg");
     static inline_link_fn_suffix                          = ctRegex!(`¤(.+?)(\.fnSuffix)`, "mg");