X-Git-Url: https://git.plutz.net/?p=cgilite;a=blobdiff_plain;f=markdown.awk;h=361e6005c3fc42fa5e1f81859d69ec59d0c0a138;hp=be7d723b6b96d0efa7ccdc9ecc5be38c881f1026;hb=HEAD;hpb=ae55f6f3fd50539c90fbc8237ae025edc9b17ba4 diff --git a/markdown.awk b/markdown.awk index be7d723..34879d2 100755 --- a/markdown.awk +++ b/markdown.awk @@ -5,6 +5,20 @@ # Meant to support all features of John Grubers basic Markdown # + a number of common extensions, mostly inspired by Pandoc Markdown +# Copyright 2021 - 2023 Paul Hänsch +# +# Permission to use, copy, modify, and/or distribute this software for any +# purpose with or without fee is hereby granted, provided that the above +# copyright notice and this permission notice appear in all copies. +# +# THE SOFTWARE IS PROVIDED “AS IS” AND THE AUTHOR DISCLAIMS ALL WARRANTIES +# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF +# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY +# SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES +# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN +# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR +# IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + # Supported Features / TODO: # ========================== # [x] done [ ] todo [-] not planned ? unsure @@ -41,6 +55,7 @@ # - [x] Automatic
-wrapping (custom) # - ? Heading identifiers (php md, pandoc) # - [x] Heading attributes (custom) +# - [ ]
terminates section # - [x] Automatic heading identifiers (custom) # - [x] Fenced code blocks (php md, pandoc) # - [x] Fenced code attributes @@ -106,14 +121,7 @@ function URL ( text, sharp ) { return text; } -function inline( line, LOCAL, len, code, href, guard ) { - nu = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\_]|_[[:alnum:]])*" # not underline (except when escaped) - na = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\\\*])*" # not asterisk (except when escaped) - ieu = "_([^_[:space:]]|[^_[:space:]]" nu "[^_[:space:]])_" # inner (underline) - isu = "__([^_[:space:]]|[^_[:space:]]" nu "[^_[:space:]])__" # inner (underline) - iea = "\\*([^\\*[:space:]]|[^\\*[:space:]]" na "[^\\*[:space:]])\\*" # inner (asterisk) - isa = "\\*\\*([^\\*[:space:]]|[^\\*[:space:]]" na "[^\\*[:space:]])\\*\\*" # inner (asterisk) - +function inline( line, LOCAL, len, text, code, href, guard ) { if ( line ~ /^$/ ) { # Recursion End return ""; @@ -133,47 +141,59 @@ function inline( line, LOCAL, len, code, href, guard ) { code = substr( line, len + 1, match( substr(line, len + 1), guard ) - 1) len = 2 * length(guard) + length(code) # strip single surrounding white spaces - code = gensub( /^ | $/, "", "g" , code) + gsub( /^ | $/, "", code) # escape HTML within code span gsub( /&/, "\\&", code ); gsub( //, "\\>", code ); return "" code "" inline( substr( line, len + 1 ) ) } + # Macros + } else if ( match( line, /^<<([^>]|>[^>])+>>/ ) ) { + len = RLENGTH; + return "" HTML( substr( line, 3, len - 4 ) ) "" inline(substr(line, len + 1)); + # Wiki style links } else if ( match( line, /^\[\[([^]|]+)(\|[^]]+)?\]\]/) ) { len = RLENGTH; href = gensub(/^\[\[([^]|]+)(\|([^]]+))?\]\]/, "\\1", 1, substr(line, 1, len) ); text = gensub(/^\[\[([^]|]+)(\|([^]]+))?\]\]/, "\\3", 1, substr(line, 1, len) ); if ( ! text ) text = href; - return "" HTML(text) "" inline( substr( line, len + 1) ); + return "" HTML(text) "" inline( substr( line, len + 1) ); # quick links ("automatic links" in md doc) } else if ( match( line, /^<[a-zA-Z]+:\/\/([-\.[:alnum:]]+)(:[0-9]*)?(\/[^>]*)?>/ ) ) { len = RLENGTH; - href = URL( substr( line, 2, len - 2) ); + href = HTML( substr( line, 2, len - 2) ); return "" href "" inline( substr( line, len + 1) ); # quick link email } else if ( match( line, /^<[a-zA-Z0-9.!#$%&'\''*+\/=?^_`{|}~-]+@[a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(\.[a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*>/ ) ) { len = RLENGTH; - href = URL( substr( line, 2, len - 2) ); + href = HTML( substr( line, 2, len - 2) ); return "" href "" inline( substr( line, len + 1) ); + # Verbatim inline HTML + } else if ( AllowHTML && match( line, /^(|<\?([^\?]|\?[^>])*\?>|]*>|])*\]\]>|<\/[A-Za-z][A-Za-z0-9-]*[[:space:]]*>|<[A-Za-z][A-Za-z0-9-]*([[:space:]]+[A-Za-z_:][A-Za-z0-9_\.:-]*([[:space:]]*=[[:space:]]*([[:space:]"'=<>`]+|"[^"]*"|'[^']*'))?)*[[:space:]]*\/?>)/) ) { + len = RLENGTH; + return substr( line, 1, len) inline(substr(line, len + 1)); + # inline links - # ,_______________________Image____________________________, - } else if ( match(line, /^\[([^]]+|!\[[^]]*\]\([^"\)]+([ \t]+"[^"]+")?\)(\{[a-zA-Z \t-]*\})?)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/) ) { + } else if ( match(line, "^" lii "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)") ) { len = RLENGTH; - text = gensub(/^\[([^]]+|!\[[^]]*\]\([^"\)]+([ \t]+"[^"]+")?\)(\{[a-zA-Z \t-]*\})?)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/, \ - "\\1", 1, substr(line, 1, len) ); - href = gensub(/^\[([^]]+|!\[[^]]*\]\([^"\)]+([ \t]+"[^"]+")?\)(\{[a-zA-Z \t-]*\})?)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/, \ - "\\4", 1, substr(line, 1, len) ); - title = gensub(/^\[([^]]+|!\[[^]]*\]\([^"\)]+([ \t]+"[^"]+")?\)(\{[a-zA-Z \t-]*\})?)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/, \ - "\\6", 1, substr(line, 1, len) ); - if ( title ) { - return "" inline( text ) "" inline( substr( line, len + 1) ); - } else { - return "" inline( text ) "" inline( substr( line, len + 1) ); - } + text = href = title = substr( line, 1, len); + sub("^\\[", "", text); sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)$", "", text); + sub("^" lii "\\([\n\t ]*", "", href); sub("([\n\t ]+" lit ")?[\n\t ]*\\)$", "", href); + sub("^" lii "\\([\n\t ]*" lid, "", title); sub("[\n\t ]*\\)$", "", title); sub("^[\n\t ]+", "", title); + + if ( match(href, /^<.*>$/) ) { sub(/^$/, "", href); } + if ( match(title, /^".*"$/) ) { sub(/^"/, "", title); sub(/"$/, "", title); } + else if ( match(title, /^'.*'$/) ) { sub(/^'/, "", title); sub(/'$/, "", title); } + else if ( match(title, /^\(.*\)$/) ) { sub(/^\(/, "", title); sub(/\)$/, "", title); } + + gsub(/\\/, "", href); gsub(/\\/, "", title); gsub(/[\n\t]+/, " ", title); + + return "" \ + inline( text ) "" inline( substr( line, len + 1) ); # reference style links } else if ( match(line, /^\[([^]]+)\] ?\[([^]]*)\]/ ) ) { @@ -182,33 +202,41 @@ function inline( line, LOCAL, len, code, href, guard ) { id = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\2", 1, substr(line, 1, len) ); if ( ! id ) id = text; if ( rl_href[id] && rl_title[id] ) { - return "" inline(text) "" inline( substr( line, len + 1) ); + return "" inline(text) "" inline( substr( line, len + 1) ); } else if ( rl_href[id] ) { - return "" inline(text) "" inline( substr( line, len + 1) ); + return "" inline(text) "" inline( substr( line, len + 1) ); } else { return "" HTML(substr(line, 1, len)) inline( substr(line, len + 1) ); } # inline images - } else if ( match(line, /^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/) ) { - len = RLENGTH; - text = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\1", "g", substr(line, 1, len) ); - href = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\2", "g", substr(line, 1, len) ); - title = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\4", "g", substr(line, 1, len) ); - attrib = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\6", "g", substr(line, 1, len) ); - if ( title && attrib ) { - return "\""" \ - inline( substr( line, len + 1) ); - } else if ( title ) { - return "\""" \ - inline( substr( line, len + 1) ); - } else if ( attrib ) { - return "\""" \ - inline( substr( line, len + 1) ); - } else { - return "\""" \ - inline( substr( line, len + 1) ); - } + } else if ( match(line, "^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?") ) { + len = RLENGTH; text = href = title = attrib = substr( line, 1, len); + + sub("^!\\[", "", text); + sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", text); + + sub("^!" lix "\\([\n\t ]*", "", href); + sub("([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", href); + + sub("^!" lix "\\([\n\t ]*" lid, "", title); + sub("[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", title); + sub("^[\n\t ]+", "", title); + + sub("^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)", "", attrib); + sub(/^\{[ \t]*/, "", attrib); sub(/[ \t]*\}$/, "", attrib); gsub(/[ \t]+/, " ", attrib); + + if ( match(href, /^<.*>$/) ) { sub(/^$/, "", href); } + if ( match(title, /^".*"$/) ) { sub(/^"/, "", title); sub(/"$/, "", title); } + else if ( match(title, /^'.*'$/) ) { sub(/^'/, "", title); sub(/'$/, "", title); } + else if ( match(title, /^\(.*\)$/) ) { sub(/^\(/, "", title); sub(/\)$/, "", title); } + + gsub(/^[\t ]+$/, "", text); gsub(/\\/, "", href); + gsub(/\\/, "", title); gsub(/[\n\t]+/, " ", title); + + return "\""" inline( substr( line, len + 1) ); # reference style images } else if ( match(line, /^!\[([^]]*)\] ?\[([^]]*)\]/ ) ) { @@ -217,10 +245,10 @@ function inline( line, LOCAL, len, code, href, guard ) { id = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\].*/, "\\2", 1, substr(line, 1, len) ); if ( ! id ) id = text; if ( rl_href[id] && rl_title[id] ) { - return "\""" \ + return "\""" \ inline( substr( line, len + 1) ); } else if ( rl_href[id] ) { - return "\""" \ + return "\""" \ inline( substr( line, len + 1) ); } else { return "" HTML(substr(line, 1, len)) inline( substr(line, len + 1) ); @@ -275,16 +303,6 @@ function inline( line, LOCAL, len, code, href, guard ) { len = RLENGTH; return "" inline( substr( line, 2, len - 2 ) ) "" inline( substr( line, len + 1 ) ); - # Macros - } else if ( AllowMacros && match( line, /^<<([^>]|>[^>])+>>/) ) { - len = RLENGTH; - return macro( substr( line, 3, len - 4 ) ) inline(substr(line, len + 1)); - - # Verbatim inline HTML - } else if ( AllowHTML && match( line, /^(|<\?([^\?]|\?[^>])*\?>|]*>|])*\]\]>|<\/[A-Za-z][A-Za-z0-9-]*[[:space:]]*>|<[A-Za-z][A-Za-z0-9-]*([[:space:]]+[A-Za-z_:][A-Za-z0-9_\.:-]*([[:space:]]*=[[:space:]]*([[:space:]"'=<>`]+|"[^"]*"|'[^']*'))?)*[[:space:]]*\/?>)/) ) { - len = RLENGTH; - return substr( line, 1, len) inline(substr(line, len + 1)); - # Literal HTML entities } else if ( match( line, /^&([a-zA-Z]{2,32}|#[0-9]{1,7}|#[xX][0-9a-fA-F]{1,6});/) ) { len = RLENGTH; @@ -309,26 +327,26 @@ function inline( line, LOCAL, len, code, href, guard ) { } function headline( hlvl, htxt, attrib, LOCAL, sec, n, HL) { - split( gensub( /^(.* )?([0-9]+( [0-9]+){5})$/, "\\2" ,"1", hstack), HL); + match(hstack, /([0-9]+( [0-9]+){5})$/); split( substr(hstack, RSTART), HL); for ( n = hlvl; n <= 6; n++ ) { sec = sec (HL[n]?"
":""); } HL[hlvl]++; for ( n = hlvl + 1; n <= 6; n++) { HL[n] = 0;} + hid = ""; for ( n = 2; n <= blvl; n++) { hid = hid BL[n] "/"; } hid = hid HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; } hid = hid ":" URL(htxt, 1); - hstack = gensub( /^(.* )?([0-9]+( [0-9]+){5})$/, "\\1" ,"1", hstack) \ - HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6]; + sub(/([0-9]+( [0-9]+){5})$/, "", hstack); + hstack = hstack HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6]; return sec "
" \ "" inline( htxt ) \ "" \ - "\n\n"; + "\n"; } # Nested Block, resets heading counters -function _nblock( block, LOCAL, hlsav, sec, n ) { - hlsav = hstack; +function _nblock( block, LOCAL, sec, n ) { hstack = hstack " 0 0 0 0 0 0"; # Block Level @@ -336,14 +354,15 @@ function _nblock( block, LOCAL, hlsav, sec, n ) { for ( n = blvl + 1; n in BL; n++) { delete BL[n]; } block = _block( block ); - split( gensub( /^(.* )?([0-9]+( [0-9]+){5})$/, "\\2" ,"1", hstack), HL); + match(hstack, /([0-9]+( [0-9]+){5})$/); split( substr(hstack, RSTART), HL); sec = ""; for ( n = 1; n <= 6; n++ ) { sec = sec (HL[n]?"
":""); } - hstack = hlsav; blvl--; + + sub("( +[0-9]+){6} *$", "", hstack); blvl--; return block sec; } -function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, attrib ) { - gsub( /^\n+|\n+$/, "", block ); +function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, indent, list ) { + gsub( "(^\n+|\n+$)", "", block ); if ( block == "" ) { return ""; @@ -372,7 +391,7 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at # Metadata (custom, block starting with %something) # Metadata is ignored but can be interpreted externally - } else if ( match(block, /^%[a-zA-Z]+([[:space:]][^\n]*)?(\n|$)(%[a-zA-Z]+([[:space:]][^\n]*)?(\n|$)|%([[:space:]][^\n]*)?(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) { + } else if ( match(block, /^%[a-zA-Z-]+([[:space:]][^\n]*)?(\n|$)(%[a-zA-Z-]+([[:space:]][^\n]*)?(\n|$)|%([[:space:]][^\n]*)?(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) { len = RLENGTH; st = RSTART; return _block( substr( block, len + 1) ); @@ -380,12 +399,13 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at } else if ( match( block, /^> /) ) { match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match(block, /$/); len = RLENGTH; st = RSTART; - return "
" gensub( /^\n|\n$/, "", "g", _nblock( gensub( /(^|\n)> /, "\n", "g", substr(block, 1, st - 1) ) ) ) "
\n\n" \ - _block( substr(block, st + len) ); + text = substr(block, 1, st - 1); gsub( /(^|\n)> /, "\n", text ); + text = _nblock( text ); gsub( /^\n|\n$/, "", text ) + return "
" text "
\n\n" _block( substr(block, st + len) ); # Pipe Tables (pandoc / php md / gfm ) } else if ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?)\n" \ - "((\\|)?:?(-+:?[\\|+])+:?-+:?(\\|)?)\n" \ + "((\\|)?(:?-+:?[\\|+])+:?-+:?(\\|)?)\n" \ "((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ) { len = RLENGTH; st = RSTART; #initialize empty arrays @@ -514,12 +534,12 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at # Line Blocks (pandoc) } else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\n]*(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) { len = RLENGTH; st = RSTART; - code = substr(block, 1, len); - gsub(/\n[[:space:]]+/, " ", code); - gsub(/\n\| /, "\n", code); - gsub(/^\| |\n$/, "", code); - return "
" gensub(/\n/, "
\n", "g", inline( code )) "
\n" \ - _block( substr( block, len + 1) ); + + text = substr(block, 1, len); gsub(/\n[[:space:]]+/, " ", text); + gsub(/\n\| /, "\n", text); gsub(/^\| |\n$/, "", text); + text = inline(text); gsub(/\n/, "
\n", text); + + return "
" text "
\n" _block( substr( block, len + 1) ); # Indented Code Block } else if ( match(block, /^( |\t)( *\t*[^ \t\n]+ *\t*)+(\n|$)(( |\t)[^\n]+(\n|$)|[ \t]*(\n|$))*/) ) { @@ -533,7 +553,7 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at # Fenced Divs (pandoc, custom) } else if ( match( block, /^(:::+)/ ) ) { guard = substr( block, 1, RLENGTH ); - code = gensub(/^[^\n]+\n/, "", 1, block); + code = block; sub(/^[^\n]+\n/, "", code); attrib = gensub(/^:::+[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\1", 1, block); gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib); @@ -566,127 +586,89 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at _block( substr(block, st + len) ); } - # Unordered list - } else if ( match( block, "^ ? ? ?[-+*][ \t]+[^\n]+(\n|$)" \ - "(([ \t]*\n)* ? ? ?[-+*][ \t]+[^\n]+(\n|$)" \ - "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \ - "|[^\n]+(\n|$))*" ) ) { - list = substr( block, 1, RLENGTH); - block = substr( block, RLENGTH + 1); - indent = length( gensub(/[-+*][ \t]+[^\n]+.*$/, "", 1, list) ); - - gsub("(^|\n) {0," indent "}", "\n", list); - return "\n
    \n" _list( substr(list, 2) ) "
\n" _block( block ); - - # Ordered list - } else if ( match( block, "^ ? ? ?([0-9]+|#)\\.[ \t]+[^\n]+(\n|$)" \ - "(([ \t]*\n)* ? ? ?([0-9]+|#)\\.[ \t]+[^\n]+(\n|$)" \ - "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \ - "|[^\n]+(\n|$))*" ) ) { - list = substr( block, 1, RLENGTH); - block = substr( block, RLENGTH + 1); - indent = length( gensub(/([0-9]+|#)\.[ \t]+[^\n]+.*$/, "", 1, list) ); - - gsub("(^|\n) {0," indent "}", "\n", list); - return "\n
    \n" _list( substr(list, 2) ) "
\n" _block( block ); - - # Definition list - } else if (match( block, "^(([ \t]*\n)*[^:\n \t][^\n]+\n" \ - "([ \t]*\n)* ? ? ?:[ \t][^\n]+(\n|$)" \ - "(([ \t]*\n)* ? ? ?:[ \t][^\n]+(\n|$)" \ - "|[^:\n \t][^\n]+(\n|$)" \ - "|( ? ? ?\t| +)[^\n]+(\n|$)" \ - "|([ \t]*\n)+( ? ? ?\t| +)[^\n]+(\n|$))*)+" \ - )) { - list = substr( block, 1, RLENGTH); block = substr( block, RLENGTH + 1); - return "\n
\n" _dlist( list ) "
\n" _block( block ); - # First Order Heading H1 + Attrib } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n===+(\n|$)/ ) ) { - len = RLENGTH; - text = gensub(/^([^\n]+)([ \t]*\{([^\}\n]+)\})\n===+(\n.*)?$/, "\\1", 1, block) - attrib = gensub(/^([^\n]+)([ \t]*\{([^\}\n]+)\})\n===+(\n.*)?$/, "\\3", 1, block) + len = RLENGTH; text = attrib = block; + sub(/([ \t]*\{([^\}\n]+)\})\n===+(\n.*)?$/, "", text); + sub(/\}\n===+(\n.*)?$/, "", attrib); sub(/^([^\n]+)[ \t]*\{/, "", attrib); gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib); - return headline(1, text, attrib) \ - _block( substr( block, len + 1 ) ); + return headline(1, text, attrib) _block( substr( block, len + 1 ) ); # First Order Heading H1 } else if ( match( block, /^([^\n]+)\n===+(\n|$)/ ) ) { - len = RLENGTH; - text = gensub(/^([^\n]+)\n===+(\n.*)?$/, "\\1", 1, block) + len = RLENGTH; text = substr(block, 1, len); + sub(/\n===+(\n.*)?$/, "", text); - return headline(1, text, 0) \ - _block( substr( block, len + 1 ) ); + return headline(1, text, 0) _block( substr( block, len + 1 ) ); # Second Order Heading H2 + Attrib } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n---+(\n|$)/ ) ) { - len = RLENGTH; - text = gensub(/^([^\n]+)([ \t]*\{([^\}\n]+)\})\n---+(\n.*)?$/, "\\1", 1, block) - attrib = gensub(/^([^\n]+)([ \t]*\{([^\}\n]+)\})\n---+(\n.*)?$/, "\\3", 1, block) + len = RLENGTH; text = attrib = block; + sub(/([ \t]*\{([^\}\n]+)\})\n---+(\n.*)?$/, "", text); + sub(/\}\n---+(\n.*)?$/, "", attrib); sub(/^([^\n]+)[ \t]*\{/, "", attrib); gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib); - return headline(2, text, attrib) \ - _block( substr( block, len + 1) ); + return headline(2, text, attrib) _block( substr( block, len + 1) ); # Second Order Heading H2 } else if ( match( block, /^([^\n]+)\n---+(\n|$)/ ) ) { - len = RLENGTH; - text = gensub(/^([^\n]+)\n---+(\n.*)?$/, "\\1", 1, block) + len = RLENGTH; text = substr(block, 1, len); + sub(/\n---+(\n.*)?$/, "", text); - return headline(2, text, 0) \ - _block( substr( block, len + 1) ); + return headline(2, text, 0) _block( substr( block, len + 1) ); # Nth Order Heading H1 H2 H3 H4 H5 H6 + Attrib } else if ( match( block, /^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n|$)/ ) ) { - len = RLENGTH; - n = gensub(/^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n.*)?$/, "\\1", 1, block); - text = gensub(/^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n.*)?$/, "\\2", 1, block); - attrib = gensub(/^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n.*)?$/, "\\5", 1, block); + len = RLENGTH; text = attrib = substr(block, 1, len); + match(block, /^#{1,6}/); n = RLENGTH; + + sub(/^(#{1,6})[ \t]*/, "", text); sub(/[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n.*)?$/, "", text); + sub(/^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*[ \t]*\{/, "", attrib); + sub(/\})(\n.*)?$/, "", attrib); gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib); - return headline( length(n), text, attrib ) \ - _block( substr( block, len + 1) ); + return headline( n, text, attrib ) _block( substr( block, len + 1) ); # Nth Order Heading H1 H2 H3 H4 H5 H6 } else if ( match( block, /^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n|$)/ ) ) { - len = RLENGTH; - n = gensub(/^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n.*)?$/, "\\1", 1, block); - text = gensub(/^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n.*)?$/, "\\2", 1, block); + len = RLENGTH; text = substr(block, 1, len); + match(block, /^#{1,6}/); n = RLENGTH; + sub(/^(#{1,6})[ \t]*/, "", text); sub(/[ \t]*#*(\n.*)?$/, "", text); - return headline( length(n), text, 0 ) \ - _block( substr( block, len + 1) ); + return headline( n, text, 0 ) _block( substr( block, len + 1) ); # block images (wrapped in
) - } else if ( match(block, /^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n|$)/) ) { - len = RLENGTH; - text = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n.*)?$/, "\\1", "g", block); - href = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n.*)?$/, "\\2", "g", block); - title = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n.*)?$/, "\\4", "g", block); - attrib = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n.*)?$/, "\\6", "g", block); - if ( title && attrib ) { - return "
" \ - "\""" \ - "
" inline(title) "
" \ - "
\n\n" \ - _block( substr( block, len + 1) ); - } else if ( title ) { - return "
" \ - "\""" \ - "
" inline(title) "
" \ - "
\n\n" \ - _block( substr( block, len + 1) ); - } else if ( attrib ) { - return "
" \ - "\""" \ - "
\n\n" \ - _block( substr( block, len + 1) ); - } else { - return "
" \ - "\""" \ - "
\n\n" \ - _block( substr( block, len + 1) ); - } + } else if ( match(block, "^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n|$)") ) { + len = RLENGTH; text = href = title = attrib = substr( block, 1, len); + + sub("^!\\[", "", text); + sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", text); + + sub("^!" lix "\\([\n\t ]*", "", href); + sub("([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", href); + + sub("^!" lix "\\([\n\t ]*" lid, "", title); + sub("[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", title); + sub("^[\n\t ]+", "", title); + + sub("^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)", "", attrib); + sub("(\n.*)?$", "", attrib); + sub(/^\{[ \t]*/, "", attrib); sub(/[ \t]*\}$/, "", attrib); gsub(/[ \t]+/, " ", attrib); + + if ( match(href, /^<.*>$/) ) { sub(/^$/, "", href); } + if ( match(title, /^".*"$/) ) { sub(/^"/, "", title); sub(/"$/, "", title); } + else if ( match(title, /^'.*'$/) ) { sub(/^'/, "", title); sub(/'$/, "", title); } + else if ( match(title, /^\(.*\)$/) ) { sub(/^\(/, "", title); sub(/\)$/, "", title); } + + gsub(/^[\t ]+$/, "", text); gsub(/\\/, "", href); + + return "
" \ + "\""" \ + (title?"
" inline(title) "
":"") \ + "
\n\n" \ + _block( substr( block, len + 1) ); # reference style images (block) } else if ( match(line, /^!\[([^]]*)\] ?\[([^]]*)\](\n|$)/ ) ) { @@ -695,14 +677,14 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at id = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\](\n.*)?$/, "\\2", 1, block); if ( ! id ) id = text; if ( rl_href[id] && rl_title[id] ) { - return "
" \ - "\""" \ + return "
" \ + "\""" \ "
" inline(rl_title[id]) "
" \ "
\n\n" \ _block( substr( block, len + 1) ); } else if ( rl_href[id] ) { - return "
" \ - "\""" \ + return "
" \ + "\""" \ "
\n\n" \ _block( substr( block, len + 1) ); } else { @@ -710,10 +692,41 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at } # Macros (standalone <> calls handled as block, so they are not wrapped in paragraph) - } else if ( AllowMacros && match( block, /^<<(([^>]|>[^>])+)>>(\n|$)/) ) { + } else if ( match( block, /^<<(([^>]|>[^>])+)>>(\n|$)/ ) ) { len = RLENGTH; text = gensub(/^<<(([^>]|>[^>])+)>>(\n.*)?$/, "\\1", 1, block); - return macro(text) _block(substr(block, len + 1) ); + return "" HTML(text) "" _block(substr(block, len + 1) ); + + # Definition list + } else if (match( block, "^(([ \t]*\n)*[^:\n \t][^\n]+\n" \ + "([ \t]*\n)* ? ? ?:[ \t][^\n]+(\n|$)" \ + "(([ \t]*\n)* ? ? ?:[ \t][^\n]+(\n|$)" \ + "|[^:\n \t][^\n]+(\n|$)" \ + "|( ? ? ?\t| +)[^\n]+(\n|$)" \ + "|([ \t]*\n)+( ? ? ?\t| +)[^\n]+(\n|$))*)+" \ + )) { + list = substr( block, 1, RLENGTH); block = substr( block, RLENGTH + 1); + return "\n
\n" _dlist( list ) "
\n" _block( block ); + + # Unordered list types + } else if ( text = _startlist( block, "ul", "-", "([+*•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { + return text; + } else if ( text = _startlist( block, "ul", "\\+", "([-*•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { + return text; + } else if ( text = _startlist( block, "ul", "\\*", "([-+•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { + return text; + } else if ( text = _startlist( block, "ul", "•", "([-+*]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { + return text; + + # Ordered list types + } else if ( text = _startlist( block, "ol", "[0-9]+\\.", "([-+*•]|#\\.|[0-9]+\\)|#\\))") ) { + return text; + } else if ( text = _startlist( block, "ol", "[0-9]+\\)", "([-+*•]|[0-9]+\\.|#\\.|#\\))") ) { + return text; + } else if ( text = _startlist( block, "ol", "#\\.", "([-+*•]|[0-9]+\\.|[0-9]+\\)|#\\))") ) { + return text; + } else if ( text = _startlist( block, "ol", "#\\)", "([-+*•]|[0-9]+\\.|#\\.|[0-9]+\\))") ) { + return text; # Split paragraphs } else if ( match( block, /(^|\n)[[:space:]]*(\n|$)/) ) { @@ -732,6 +745,56 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at } } +function _startlist(block, type, mark, exclude, LOCAL, st, len, list, indent, text) { + if (match( block, "(^|\n) ? ? ?" mark "[ \t][^\n]+(\n|$)" \ + "(([ \t]*\n)* ? ? ?" mark "[ \t][^\n]+(\n|$)" \ + "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \ + "|[^\n \t][^\n]+(\n|$))*" ) ) { + st = RSTART; len = RLENGTH; list = substr( block, st, len); + + sub("^\n", "", list); match(list, "^ ? ? ?"); indent = RLENGTH; + gsub( "(^|\n) {0," indent "}", "\n", list); sub("^\n", "", list); + + text = substr(block, 1, st - 1); block = substr(block, st + len); + if (match(text, /\n[[:space:]]*\n/)) return 0; + if (match(text, "(^|\n) ? ? ?" exclude "[ \t][^\n]+")) return 0; + if (match( list, "\n" exclude "[ \t]" )) { + block = substr(list, RSTART + 1) block; + list = substr(list, 1, RSTART); + } + + return _block( text ) "<" type ">\n" _list( list, mark ) "\n" _block( block ); + } else return 0; +} + +function _list (block, mark, p, LOCAL, len, st, text, indent, task) { + if ( match(block, "^([ \t]*\n)*$")) return; + + match(block, "^" mark "[ \t]"); indent = RLENGTH; + sub("^" mark "[ \t]", "", block); + + if (match(block, /\n[ \t]*\n/)) p = 1; + + match( block, "\n" mark "[ \t][^\n]+(\n|$)" ); + st = (RLENGTH == -1) ? length(block) + 1 : RSTART; + text = substr(block, 1, st); block = substr(block, st + 1); + + gsub("\n {0," indent "}", "\n", text); + + task = match( text, /^\[ \]/ ) ? "
  • " : \ + match( text, /^\[-\]/ ) ? "
  • " : \ + match( text, /^\[\/\]/ ) ? "
  • " : \ + match( text, /^\[\?\]/ ) ? "
  • " : \ + match( text, /^\[[xX]\]/) ? "
  • " : "
  • "; + sub(/^\[[-? \/xX]\]/, "", text); + + text = _nblock( text ); + if ( ! p && match( text, "^

    (]|\n$" )) + gsub( "(^

    |

    \n$)", "", text); + + return task text "
    • \n" _list(block, mark, p); +} + function _dlist (block, LOCAL, len, st, text, indent, p) { if (match( block, "^([ \t]*\n)*[^:\n \t][^\n]+\n" )) { len = RLENGTH; text = substr(block, 1, len); @@ -743,66 +806,17 @@ function _dlist (block, LOCAL, len, st, text, indent, p) { "|([ \t]*\n)+( ? ? ?\t| +)[^\n]+(\n|$))*" \ )) { len = RLENGTH; text = substr(block, 1, len); - if (match( text, "^ ? ? ?:[ \t][^\n]+(\n|$)" \ - "([^:\n \t][^\n]+(\n|$)" \ - "|( ? ? ?\t| +)[^\t\n ][^\n]*(\n|$))*$" \ - )) p = 1; else p = 0; sub( "^([ \t]*\n)*", "", text); match(text, "^ ? ? ?:(\t| +)"); indent = RLENGTH; sub( "^ ? ? ?:(\t| +)", "", text); gsub( "(^|\n) {0," indent "}", "\n", text ); - text = _block(text); - if (p) gsub("(^\n*

    |

    \n*$)", "", text); - return "
    " text "
    \n" _dlist( substr(block, len + 1) ); - } -} - -function _list( block, last, LOCAL, p) { - if ( ! length(block) ) return ""; - gsub(/^([-+*]|[0-9]+\.|#\.)( ? ? ?|\t)/, "", block) - # slice next list item from input - if ( match( block, /\n([-+*]|[0-9]+\.|#\.)[ \t]+[^\n]+/) ) { - p = substr( block, 1, RSTART); - block = substr( block, RSTART + 1); - } else { - p = block; block = ""; - } - sub( /\n +([-+*]|[0-9]+\.|#\.)/, "\n&", p ); + text = _nblock(text); + if (match( text, "^

    (]|\n$" )) + gsub( "(^

    |

    \n$)", "", text); - # if this should be a paragraph item - # either previous item (last) or current item (p) contains blank lines - if (match(last, /\n[[:space:]]*\n/) || match(p, /\n[[:space:]]*\n/) ) { - last = p; p = _nblock(p); - } else { - last = p; p = _nblock(p); - sub( /^

    /, "", p ); - sub( /<\/p>\n/, "", p ); + return "

    " text "
    \n" _dlist( substr(block, len + 1) ); } - sub( /\n$/, "", p ); - - # Task List (pandoc, custom) - if ( p ~ /^\[ \].*/ ) { return "
  • " \ - substr(p, 4) "
    • \n" _list( block, last ); - } else if ( p ~ /^\[-\].*/ ) { return "
  • " \ - substr(p, 4) "
    • \n" _list( block, last ); - } else if ( p ~ /^\[\?\].*/ ) { return "
  • " \ - substr(p, 4) "
    • \n" _list( block, last ); - } else if ( p ~ /^\[\/\].*/ ) { return "
  • " \ - substr(p, 4) "
    • \n" _list( block, last ); - } else if ( p ~ /^\[[xX]\].*/ ) { return "
  • " \ - substr(p, 4) "
    • \n" _list( block, last ); - } else if ( p ~ /^

    \[ \].*/ ) { return "

  • " \ - substr(p, 7) "

    • \n" _list( block, last ); - } else if ( p ~ /^

    \[-\].*/ ) { return "

  • " \ - substr(p, 7) "

    • \n" _list( block, last ); - } else if ( p ~ /^

    \[\?\].*/ ) { return "

  • " \ - substr(p, 7) "

    • \n" _list( block, last ); - } else if ( p ~ /^

    \[\/\].*/ ) { return "

  • " \ - substr(p, 7) "

    • \n" _list( block, last ); - } else if ( p ~ /^

    \[[xX]\].*/ ) { return "

  • " \ - substr(p, 7) "

    • \n" _list( block, last ); - } else { return "
  • " p "
    • \n" _list( block, last ); } } BEGIN { @@ -812,6 +826,20 @@ BEGIN { HL[1] = 0; HL[2] = 0; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0; # hls = "0 0 0 0 0 0"; + # Universal Patterns + nu = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\_]|_[[:alnum:]])*" # not underline (except when escaped) + na = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\\\*])*" # not asterisk (except when escaped) + ieu = "_([^_[:space:]]|[^_[:space:]]" nu "[^_[:space:]])_" # inner (underline) + isu = "__([^_[:space:]]|[^_[:space:]]" nu "[^_[:space:]])__" # inner (underline) + iea = "\\*([^\\*[:space:]]|[^\\*[:space:]]" na "[^\\*[:space:]])\\*" # inner (asterisk) + isa = "\\*\\*([^\\*[:space:]]|[^\\*[:space:]]" na "[^\\*[:space:]])\\*\\*" # inner (asterisk) + + lix="\\[(\\\\[^\n]|[^]\n\\\\[])*\\]" # link text + lid="(<(\\\\[^\n]|[^\n<>\\\\])*>|(\\\\.|[^()\"'\\\\])+|([^<\n\t ()\\\\]|\\\\[^\n])(\\\\[\n]|[^\n\t \\(\\)\\\\])*)" # link dest + lit="(\"(\\\\.|[^\"\\\\])*\"|'(\\\\.|[^'\\\\])*'|\\((\\\\.|[^\\(\\)\\\\])*\\))" # link text + # link text with image def + lii="\\[(\\\\[^\n]|[^]\n\\\\[])*(!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\))?(\\\\[^\n]|[^]\n\\\\[])*\\]" + # Buffering of full file ist necessary, e.g. to find reference links while (getline) { file = file $0 "\n"; } # Clean up MS-DOS line breaks