X-Git-Url: http://git.plutz.net/?a=blobdiff_plain;f=markdown.awk;h=7ec1280d34784d35377afd860d88b81f47df4906;hb=31cfd890119d30e03201d29c307203ccd304e1c0;hp=86657adf28c4c347b49557bc77e8c2a9105efb42;hpb=3d2d97555791bee190efed33f4af120ef8240189;p=cgilite diff --git a/markdown.awk b/markdown.awk index 86657ad..7ec1280 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 @@ -41,7 +55,7 @@ # - [x] Automatic
-wrapping (custom) # - ? Heading identifiers (php md, pandoc) # - [x] Heading attributes (custom) -# - [ ]
ends section +# - [ ]
terminates section # - [x] Automatic heading identifiers (custom) # - [x] Fenced code blocks (php md, pandoc) # - [x] Fenced code attributes @@ -107,7 +121,7 @@ function URL ( text, sharp ) { return text; } -function inline( line, LOCAL, len, code, href, guard ) { +function inline( line, LOCAL, len, text, code, href, guard ) { nu = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\_]|_[[:alnum:]])*" # not underline (except when escaped) na = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\\\*])*" # not asterisk (except when escaped) ieu = "_([^_[:space:]]|[^_[:space:]]" nu "[^_[:space:]])_" # inner (underline) @@ -134,12 +148,17 @@ 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; @@ -160,6 +179,11 @@ function inline( line, LOCAL, len, code, href, guard ) { href = URL( 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:]]+"([^"]+)")?\)/) ) { @@ -276,16 +300,6 @@ 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; @@ -310,7 +324,7 @@ 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;} @@ -319,8 +333,8 @@ function headline( hlvl, htxt, attrib, LOCAL, sec, n, HL) { 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 ) \ @@ -337,7 +351,7 @@ function _nblock( block, LOCAL, 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]?"
":""); } sub("( +[0-9]+){6} *$", "", hstack); blvl--; @@ -382,12 +396,13 @@ function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, } else if ( match( block, /^> /) ) { match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || 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 @@ -516,12 +531,12 @@ function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, # Line Blocks (pandoc) } else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\n]*(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) { len = RLENGTH; st = RSTART; - text = substr(block, 1, len); - gsub(/\n[[:space:]]+/, " ", text); - gsub(/\n\| /, "\n", text); - gsub(/^\| |\n$/, "", text); - return "
" gensub(/\n/, "
\n", "g", inline( text )) "
\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|$)|[ \t]*(\n|$))*/) ) { @@ -570,53 +585,55 @@ function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, # 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(/(^ | $)/, "", attrib); return headline(1, text, attrib) _block( substr( block, len + 1 ) ); # First Order Heading H1 } else if ( match( block, /^([^\n]+)\n===+(\n|$)/ ) ) { - 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 ) ); # 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(/(^ | $)/, "", attrib); return headline(2, text, attrib) _block( substr( block, len + 1) ); # Second Order Heading H2 } else if ( match( block, /^([^\n]+)\n---+(\n|$)/ ) ) { - 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) ); # 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|$)/) ) { @@ -671,10 +688,10 @@ function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, } # Macros (standalone <> calls handled as block, so they are not wrapped in paragraph) - } else if ( AllowMacros && match( block, /^<<(([^>]|>[^>])+)>>(\n|$)/) ) { + } 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" \ @@ -687,39 +704,25 @@ function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, list = substr( block, 1, RLENGTH); block = substr( block, RLENGTH + 1); return "\n
\n" _dlist( list ) "
\n" _block( block ); - # Unordered list - } else if ( match( block, "(^|\n) ? ? ?[-+*][ \t][^\n]+(\n|$)" \ - "(([ \t]*\n)* ? ? ?[-+*][ \t][^\n]+(\n|$)" \ - "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \ - "|[^\n \t][^\n]+(\n|$))*" ) ) { - st = RSTART; len = RLENGTH; list = substr( block, RSTART, RLENGTH); - sub("^\n", "", list); match(list, "^ ? ? ?[-+*]"); indent = RLENGTH; - gsub( "(^|\n) {0," indent - 1 "}", "\n", list); sub("^\n", "", list); - - text = substr(block, 1, st - 1); block = substr(block, st + len); - if (match( list, "\n([0-9]+\\.|#\\.)[ \t]" )) { - block = substr(list, RSTART + 1) block; - list = substr(list, 1, RSTART); - } - - return _block( text ) "
    \n" _list( list, "[-+*]" ) "
\n" _block( block ); - - # Ordered list - } else if ( match( block, "(^|\n) ? ? ?([0-9]+\\.|#\\.)[ \t][^\n]+(\n|$)" \ - "(([ \t]*\n)* ? ? ?([0-9]+\\.|#\\.)[ \t][^\n]+(\n|$)" \ - "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \ - "|[^\n \t][^\n]+(\n|$))*" ) ) { - st = RSTART; len = RLENGTH; list = substr( block, RSTART, RLENGTH); - sub("^\n", "", list); match(list, "^ ? ? ?[0-9#]"); indent = RLENGTH; - gsub( "(^|\n) {0," indent - 1 "}", "\n", list); sub("^\n", "", list); - - text = substr(block, 1, st - 1); block = substr(block, st + len); - if (match( list, "\n[-+*][ \t]" )) { - block = substr(list, RSTART + 1) block; - list = substr(list, 1, RSTART); - } - - return _block( text ) "
    \n" _list( list, "([0-9]+\\.|#\\.)" ) "
\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|$)/) ) { @@ -738,16 +741,38 @@ function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, } } -function _list (block, mark, LOCAL, len, st, text, indent, task) { +function _startlist(block, type, mark, exclude, LOCAL, st, len, list, indent, text) { + if (match( block, "(^|\n) ? ? ?" mark "[ \t][^\n]+(\n|$)" \ + "(([ \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); - match( block, "\n" mark "[ \t][^\n]+(\n|$)" \ - "(([ \t]*\n)* ? ? ?" mark "[ \t][^\n]+(\n|$)" \ - "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \ - "|[^\n \t][^\n]+(\n|$))*"); - (RLENGTH == -1) ? st = length(block) + 1 : st = RSTART; + 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); @@ -757,13 +782,13 @@ function _list (block, mark, LOCAL, len, st, text, indent, task) { match( text, /^\[\/\]/ ) ? "
  • " : \ match( text, /^\[\?\]/ ) ? "
  • " : \ match( text, /^\[[xX]\]/) ? "
  • " : "
  • "; - sub(/^\[[-? /xX]\]/, "", text); + sub(/^\[[-? \/xX]\]/, "", text); text = _nblock( text ); - if (match( text, "^

    (]|\n$" )) + if ( ! p && match( text, "^

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

    |

    \n$)", "", text); - return task text "
    • \n" _list(block, mark); + return task text "\n" _list(block, mark, p); } function _dlist (block, LOCAL, len, st, text, indent, p) {