diff options
Diffstat (limited to 'dlang/src/write/rgx.d')
| -rw-r--r-- | dlang/src/write/rgx.d | 104 |
1 files changed, 104 insertions, 0 deletions
diff --git a/dlang/src/write/rgx.d b/dlang/src/write/rgx.d new file mode 100644 index 0000000..23c848d --- /dev/null +++ b/dlang/src/write/rgx.d @@ -0,0 +1,104 @@ +module write.rgx; + +/+ ↓ the internal markup, as regular expressions. + . + An object's text is *spine's internal representation*, not the author's + markup and not any output: the markers are single Unicode characters + chosen not to occur in text. A writer's first job is to turn them into + something the target format understands, so every writer needs these + and they live in one place. + . + Taken from the specification's description of object text and matched + against spine's own outputs/io_out/rgx.d, which is normative. The + characters are load bearing: do not "tidy" them into ASCII. ++/ + +import std.regex; + +static struct Rgx { + /+ ↓ spacing and line breaks +/ + static nbsp_char = ctRegex!(`░`, "mg"); + static br_line = ctRegex!(`\s*┘\s*`, "mg"); + static br_line_inline = ctRegex!(`\s*┙\s*`, "mg"); + static br_line_spaced = ctRegex!(`\s*┚\s*`, "mg"); + + /+ ↓ font face, each ⑆<mark>┨ text ┣<mark> +/ + static inline_strike = ctRegex!(`⑆[-]┨(?P<text>.+?)┣[-]`, "mg"); + static inline_insert = ctRegex!(`⑆[+]┨(?P<text>.+?)┣[+]`, "mg"); + static inline_cite = ctRegex!(`⑆[‖]┨(?P<text>.+?)┣[‖]`, "mg"); + static inline_emphasis = ctRegex!(`⑆[*]┨(?P<text>.+?)┣[*]`, "mg"); + static inline_bold = ctRegex!(`⑆[!]┨(?P<text>.+?)┣[!]`, "mg"); + static inline_italics = ctRegex!(`⑆[/]┨(?P<text>.+?)┣[/]`, "mg"); + static inline_underscore = ctRegex!(`⑆[_]┨(?P<text>.+?)┣[_]`, "mg"); + static inline_superscript = ctRegex!(`⑆\^┨(?P<text>.+?)┣\^`, "mg"); + static inline_subscript = ctRegex!(`⑆[,]┨(?P<text>.+?)┣[,]`, "mg"); + static inline_mono = ctRegex!(`⑆[■]┨(?P<text>.+?)┣[■]`, "mg"); + + /+ ↓ links and images. Capture 1 is the text, 3 the target without its + leading "#" where it has one +/ + static inline_link = ctRegex!(`┥(?P<text>.+?)┝┤(?P<link>#?(\S+?))├`, "mg"); + 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"); + + /+ ↓ notes, carried inline in the object that refers to them +/ + static inline_notes_al_gen = ctRegex!(`【.+?】`, "m"); + static inline_notes_al_regular_number_note = ctRegex!(`【(?P<num>\d+)\s+(?P<note>.+?)\s*】`, "mg"); + /+ ↓ and the same for a note marked with a run of stars or pluses + instead of a number, which the markup also allows +/ + static inline_notes_al_all_note = ctRegex!(`【(?P<num>\d+|(?:[*]|[+])+)\s+(?P<note>.+?)\s*】`, "mg"); + + /+ ↓ tables: the object's text is rows and columns in one string +/ + static table_delimiter_row = ctRegex!("[ ]*\n", "mg"); + static table_delimiter_col = ctRegex!("[ ]*[┊][ ]*", "mg"); + + /+ ↓ the book index, whose entries carry their own links +/ + static find_bookindex_ocn_link_and_comma = ctRegex!(`[, ]*┥.+?┝┤#?\S+?├`, "mg"); + + /+ ↓ end of *input*, not end of line: spine's table layout strips the + whole accumulated string after every cell +/ + static trailing_whitespace_all = ctRegex!(`\s*$`); + static trailing_backslash = ctRegex!(`\s*\\`, "mg"); + + /+ ↓ a link before its url has been substituted in: the number is an index + into the object's .stow_link list, not a target +/ + static inline_link_number_only = ctRegex!(`(?P<linked_text>┥.+?┝)┤(?P<num>[0-9]+)├`, "mg"); + static inline_link_empty = ctRegex!(`┥(?P<text>.+?)┝┤├`, "mg"); + + /+ ↓ an anchor the markup placed in the text, ┃name┃ +/ + static inline_link_anchor = ctRegex!(`┃(?P<anchor>\S+?)┃`, "mg"); + + /+ ↓ "¤" marks a link that is internal to the document collection, and + ".fnSuffix" stands where an output's file suffix goes +/ + static mark_internal_site_lnk = ctRegex!(`¤`, "mg"); + static inline_seg_link = ctRegex!(`(¤)(?:.+?)\.fnSuffix`, "mg"); + + /+ ↓ the same target taken apart: the segment it names and whatever + follows it, which is what a segmented output needs +/ + static internal_target = ctRegex!(`^¤(?P<seg>.+?)\.fnSuffix(?P<frag>.*)$`); + + /+ ↓ an image's alt text, which the markup carries as a quoted string + following the image +/ + static inline_image_alt = ctRegex!(`^\s*[“"](?P<alt>[^”"]*)[”"]`, "m"); + + /+ ↓ a line break the markup asked for, " \\" +/ + static line_break = ctRegex!(` [\\]{2}`, "m"); + + /+ ↓ the leading markers of a line inside a group: indent, hang, bullet. + "_2 " is indent two, "_2*" a bullet at indent two, "_2_1 " a hanging + indent. They are line-leading and so anchored, with "m". + +/ + static grouped_para_indent = ctRegex!(`^_(?P<indent>[1-9])[ ]`, "m"); + static grouped_para_bullet = ctRegex!(`^_[*] `, "m"); + static grouped_para_bullet_at = ctRegex!(`^_(?P<indent>[1-9])[*] `, "m"); + static grouped_para_indent_hang = ctRegex!(`^_(?P<hang>[0-9])_(?P<indent>[0-9])[ ]`, "m"); + + /+ ↓ an internal link target as the abstraction writes it, with or without + the segment prefix a segmented output would use. Read to decide whether + a table of contents entry points at anything this writer renders. +/ + static any_internal_target = ctRegex!(`┤(?:¤.+?\.fnSuffix)?#(?P<frag>[^├]+)├`, "mg"); + + /+ ↓ the four characters html reserves +/ + static ampersand = ctRegex!(`[&]`, "mg"); + static quotation = ctRegex!(`["]`, "mg"); + static less_than = ctRegex!(`[<]`, "mg"); + static greater_than = ctRegex!(`[>]`, "mg"); +} |