diff options
Diffstat (limited to 'src/doc_reform/io_out/rgx.d')
| -rw-r--r-- | src/doc_reform/io_out/rgx.d | 114 |
1 files changed, 114 insertions, 0 deletions
diff --git a/src/doc_reform/io_out/rgx.d b/src/doc_reform/io_out/rgx.d new file mode 100644 index 0000000..4d0801c --- /dev/null +++ b/src/doc_reform/io_out/rgx.d @@ -0,0 +1,114 @@ +/++ + regex: regular expressions used in sisu document parser ++/ +module doc_reform.io_out.rgx; +static template spineOutputRgxInit() { + import doc_reform.io_out.defaults; + static struct Rgx { + 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 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})$`); // formalizes dir structure + /+ line breaks +/ + static br_empty_line = ctRegex!(`\n[ ]*\n`, "mg"); + static br_newlines_linebreaks = ctRegex!(`[\n┘┙]`, "mg"); + static br_line = ctRegex!(`┘`, "mg"); + static br_nl = ctRegex!(`┙`, "mg"); + /+ inline markup footnotes endnotes +/ + static inline_notes_al = ctRegex!(`【(?:[*+]\s+|\s*)(.+?)】`, "mg"); + static inline_notes_al_special = ctRegex!(`【(?:[*+]\s+)(.+?)】`, "mg"); // TODO remove match when special footnotes are implemented + static inline_notes_al_gen = ctRegex!(`【.+?】`, "m"); + static inline_notes_al_regular = ctRegex!(`【(.+?)】`, "mg"); + static inline_notes_al_gen_text = ctRegex!(`【(?P<text>.+?)】`, "m"); + static inline_notes_al_gen_ref = ctRegex!(`【(?P<ref>[*+]\s+)\s*(?P<text>.+?)】`, "mg"); + static inline_notes_al_all_note = ctRegex!(`【(?P<num>\d+|(?:[*]|[+])+)\s+(?P<note>.+?)\s*】`, "mg"); + static inline_notes_al_regular_number_note = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)\s*】`, "mg"); + static inline_notes_al_special_char_note = ctRegex!(`【(?P<char>(?:[*]|[+])+)\s+(?P<note>.+?)】`, "mg"); + static inline_al_delimiter_open_regular = ctRegex!(`【\s`, "m"); + static inline_al_delimiter_open_symbol_star = ctRegex!(`【[*]\s`, "m"); + static inline_al_delimiter_open_symbol_plus = ctRegex!(`【[+]\s`, "m"); + static inline_text_and_note_al_ = ctRegex!(`(.+?(?:【[*+]*\s+.+?】|$))`, "mg"); + /+ inline markup links +/ + static inline_image = ctRegex!(`(?P<pre>┥)☼(?P<imginf>(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+))\s*(?P<post>.*?┝┤.*?├)`, "mg"); + static inline_image_without_dimensions = ctRegex!(`(?P<pre>┥)☼(?P<imginf>(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>0)h(?P<height>0))\s*(?P<post>.*?┝┤.*?├)`, "mg"); + static inline_image_info = ctRegex!(`☼?(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+)`, "mg"); + static inline_link_anchor = ctRegex!(`┃(?P<anchor>\S+?)┃`, "mg"); // TODO *~text_link_anchor + static inline_link = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>#?(\S+?))├`, "mg"); + static inline_link_empty = ctRegex!(`┥(?P<text>.+?)┝┤├`, "mg"); + static inline_link_number = ctRegex!(`┥(?P<text>.+?)┝┤(?P<num>[0-9]+)├`, "mg"); // not used + static inline_link_number_only = ctRegex!(`(┥.+?┝)┤(?P<num>[0-9]+)├`, "mg"); + static inline_link_stow_uri = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>[^ 0-9#┥┝┤├][^ 0-9┥┝┤├]+)├`, "mg"); // will not stow (stowed links) or object number internal links + static inline_link_hash = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>#(?P<segname>\S+?))├`, "mg"); + static inline_link_clean = ctRegex!(`┤(?:.+?)├|[┥┝]`, "mg"); + static inline_link_toc_to_backmatter = ctRegex!(`┤#(?P<link>endnotes|bibliography|bookindex|glossary|blurb)├`, "mg"); + static url = ctRegex!(`https?://`, "mg"); + static uri = ctRegex!(`(?:https?|git)://`, "mg"); + static uri_identify_components = ctRegex!(`(?P<type>(?:https?|git)://)(?P<path>\S+?/)(?P<file>[^/]+)$`, "mg"); + static inline_link_subtoc = ctRegex!(`^(?P<level>[5-7])~ ┥(?P<text>.+?)┝┤(?P<link>.+?)├`, "mg"); + static inline_link_fn_suffix = ctRegex!(`¤(.+?)(\.fnSuffix)`, "mg"); + static inline_seg_link = ctRegex!(`(¤)(?:.+?)\.fnSuffix`, "mg"); + static mark_internal_site_lnk = ctRegex!(`¤`, "mg"); + static quotation_mark_sql_insert_delimiter = ctRegex!("[']", "mg"); + /+ inline markup font face mod +/ + static inline_mark_emphasis = ctRegex!(`(?P<mark>[*])\{(?P<text>.+?)\}[*]`, "mg"); + static inline_mark_bold = ctRegex!(`(?P<mark>[!])\{(?P<text>.+?)\}[!]`, "mg"); + static inline_mark_underscore = ctRegex!(`(?P<mark>[_])\{(?P<text>.+?)\}[_]`, "mg"); + static inline_mark_italics = ctRegex!(`(?P<mark>[/])\{(?P<text>.+?)\}[/]`, "mg"); + static inline_mark_superscript = ctRegex!(`(?P<mark>\^)\{(?P<text>.+?)\}\^`, "mg"); + static inline_mark_subscript = ctRegex!(`(?P<mark>[,])\{(?P<text>.+?)\}[,]`, "mg"); + static inline_mark_strike = ctRegex!(`(?P<mark>[-])\{(?P<text>.+?)\}[-]`, "mg"); + static inline_mark_insert = ctRegex!(`(?P<mark>[+])\{(?P<text>.+?)\}[+]`, "mg"); + static inline_mark_mono = ctRegex!(`(?P<mark>[#])\{(?P<text>.+?)\}[#]`, "mg"); + static inline_mark_cite = ctRegex!(`(?P<mark>["])\{(?P<text>.+?)\}["]`, "mg"); + static inline_faces_line = ctRegex!(`^[*!/_]_ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`); + 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}$)`); + static inline_underscore_line = ctRegex!(`^__ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`); + /+ inline markup font face mod +/ + static inline_emphasis = ctRegex!(`[*]┨(?P<text>.+?)┣[*]`, "mg"); + static inline_bold = ctRegex!(`[!]┨(?P<text>.+?)┣[!]`, "mg"); + static inline_underscore = ctRegex!(`[_]┨(?P<text>.+?)┣[_]`, "mg"); + static inline_italics = ctRegex!(`[/]┨(?P<text>.+?)┣[/]`, "mg"); + static inline_superscript = ctRegex!(`\^┨(?P<text>.+?)┣\^`, "mg"); + // static inline_superscript = ctRegex!(`[\^]┨(?P<text>.+?)┣[\^]`, "mg"); + static inline_subscript = ctRegex!(`[,]┨(?P<text>.+?)┣[,]`, "mg"); + static inline_strike = ctRegex!(`[-]┨(?P<text>.+?)┣[-]`, "mg"); + static inline_insert = ctRegex!(`[+]┨(?P<text>.+?)┣[+]`, "mg"); + static inline_mono = ctRegex!(`[■]┨(?P<text>.+?)┣[■]`, "mg"); + static inline_cite = ctRegex!(`[‖]┨(?P<text>.+?)┣[‖]`, "mg"); + static inline_fontface_clean = ctRegex!(`[*!_/^,+■‖-]┨|┣[*!_/^,+■‖-]`, "mg"); + /+ table delimiters +/ + static table_delimiter_col = ctRegex!("[ ]*[┊][ ]*", "mg"); + static table_delimiter_row = ctRegex!("[ ]*\n", "mg"); + static xhtml_ampersand = ctRegex!(`[&]`, "m"); // & + static xhtml_quotation = ctRegex!(`["]`, "m"); // " + static xhtml_less_than = ctRegex!(`[<]`, "m"); // < + static xhtml_greater_than = ctRegex!(`[>]`, "m"); // > + static xhtml_line_break = ctRegex!(` [\\]{2}`, "m"); // <br /> + static latex_special_char = ctRegex!(`([%${}_#&\\])`); + static latex_special_char_for_escape = ctRegex!(`([%${}_#\\])`); + static latex_special_char_for_escape_and_braces = ctRegex!(`([&])`); + static latex_special_char_for_escape_url = ctRegex!(`([%])`); + static latex_special_char_escaped = ctRegex!(`\\([%${}_#\\])`); + static latex_special_char_escaped_braced = ctRegex!(`[{]\\([&])[}]`); + static latex_identify_inline_link = ctRegex!(`┥.+?┝┤\S+?├`, "mg"); + static latex_clean_internal_link = ctRegex!(`^(?:#|¤\S+?#)`, "m"); + static latex_identify_inline_fontface = ctRegex!(`\\([_#$]┨.+?┣)\\([_#$])`, "mg"); + static latex_clean_bookindex_linebreak = ctRegex!(`\s*\\\\\\\\\s*`, "m"); + } +} |