X-Git-Url: http://git.plutz.net/?a=blobdiff_plain;f=markdown.awk;h=c42aa5ac318e544c7eb259481eb1842b33ddf895;hb=fc3451c360c190736b7355c318f937fe304bb3c4;hp=8ac8b6323dc20277efc35767f8d140a2afc17957;hpb=b4a3f6a471adcd2a1cb72f761c52b841e8bc297f;p=cgilite diff --git a/markdown.awk b/markdown.awk index 8ac8b63..c42aa5a 100755 --- a/markdown.awk +++ b/markdown.awk @@ -40,6 +40,8 @@ # ---------------------------- # - [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 @@ -53,7 +55,7 @@ # - [x] Pipe table (php md, pandoc) # - [x] Line blocks (pandoc) # - [x] Task lists (pandoc, custom) -# - [ ] Definition lists (php md, pandoc) +# - [x] Definition lists (php md, pandoc) # - [-] Numbered example lists (pandoc) # - [-] Metadata blocks (pandoc) # - [x] Metadata blocks (custom) @@ -105,7 +107,7 @@ 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) @@ -132,7 +134,7 @@ 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( /^ | $/, "", code) # escape HTML within code span gsub( /&/, "\\&", code ); gsub( //, "\\>", code ); return "" code "" inline( substr( line, len + 1 ) ) @@ -307,27 +309,27 @@ function inline( line, LOCAL, len, code, href, guard ) { } } -function headline( hlvl, htxt, LOCAL, sec, n, HL) { - split( gensub( /^(.* )?([0-9]+( [0-9]+){5})$/, "\\2" ,"1", hstack), HL); +function headline( hlvl, htxt, attrib, LOCAL, sec, n, 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})$/, "", hstack); + hstack = hstack HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6]; - return sec "
" \ - "" inline( htxt ) \ + return sec "
" \ + "" inline( htxt ) \ "" \ - "\n\n"; + "\n"; } # Nested Block, resets heading counters -function _nblock( block, LOCAL, hlsav, sec, n ) { - hlsav = hstack; +function _nblock( block, LOCAL, sec, n ) { hstack = hstack " 0 0 0 0 0 0"; # Block Level @@ -335,14 +337,15 @@ function _nblock( block, LOCAL, hlsav, sec, n ) { for ( n = blvl + 1; n in BL; n++) { delete BL[n]; } block = _block( block ); - split( gensub( /^(.* )?([0-9]+( [0-9]+){5})$/, "\\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 ""; @@ -379,8 +382,9 @@ 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 "
\n" _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$/, "", text ) + return "
" text "
\n\n" _block( substr(block, st + len) ); # Pipe Tables (pandoc / php md / gfm ) } else if ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?)\n" \ @@ -513,12 +517,12 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at # Line Blocks (pandoc) } else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\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|$))*/) ) { @@ -532,7 +536,7 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at # Fenced Divs (pandoc, custom) } else if ( match( block, /^(:::+)/ ) ) { guard = substr( block, 1, RLENGTH ); - code = gensub(/^[^\n]+\n/, "", 1, block); + code = block; sub(/^[^\n]+\n/, "", code); attrib = gensub(/^:::+[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\1", 1, block); gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib); @@ -565,53 +569,57 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at _block( substr(block, st + len) ); } - # Unordered list - } else if ( match( block, "^ ? ? ?[-+*][ \t]+[^\n]+(\n|$)" \ - "(([ \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]+.*$/, "", 1, list) ); - - gsub("(^|\n) {0," indent "}", "\n", list); - return "\n
    \n" _list( substr(list, 2) ) "
\n" _block( block ); + # First Order Heading H1 + Attrib + } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n===+(\n|$)/ ) ) { + 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; + } else if ( match( block, /^([^\n]+)\n===+(\n|$)/ ) ) { + len = RLENGTH; text = substr(block, 1, len); + sub(/\n===+(\n.*)?$/, "", text); - return headline(1, gensub( /\n.*$/, "", "g", block )) \ - _block( substr( block, len + 1 ) ); + return headline(1, text, 0) _block( substr( block, len + 1 ) ); + + # Second Order Heading H2 + Attrib + } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n---+(\n|$)/ ) ) { + len = RLENGTH; text = 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; + } else if ( match( block, /^([^\n]+)\n---+(\n|$)/ ) ) { + len = RLENGTH; text = substr(block, 1, len); + sub(/\n---+(\n.*)?$/, "", text); - return headline(2, gensub( /\n.*$/, "", "g", block )) \ - _block( substr( block, len + 1) ); + return headline(2, text, 0) _block( substr( block, len + 1) ); + + # Nth Order Heading H1 H2 H3 H4 H5 H6 + Attrib + } else if ( match( block, /^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n|$)/ ) ) { + len = RLENGTH; 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(/(^ | $)/, "", attrib); + + return headline( n, text, attrib ) _block( substr( block, len + 1) ); # Nth Order Heading H1 H2 H3 H4 H5 H6 - } else if ( match( block, /^#{1,6}[ \t]*[^\n]+([ \t]*#*)(\n|$)/ ) ) { - len = RLENGTH; + } else if ( match( block, /^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n|$)/ ) ) { + len = RLENGTH; text = substr(block, 1, len); + match(block, /^#{1,6}/); n = RLENGTH; + sub(/^(#{1,6})[ \t]*/, "", text); sub(/[ \t]*#*(\n.*)?$/, "", text); - return headline( \ - length( gensub( /^(#{1,6}).*$/, "\\1", "g", block ) ), \ - gensub(/^#{1,6}[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[^\n#])+)([ \t]*#*)(\n.*)?$/, "\\1", 1, block) \ - ) \ - _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|$)/) ) { @@ -671,6 +679,35 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at text = gensub(/^<<(([^>]|>[^>])+)>>(\n.*)?$/, "\\1", 1, block); return macro(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|$))*)+" \ + )) { + list = substr( block, 1, RLENGTH); block = substr( block, RLENGTH + 1); + return "\n
\n" _dlist( list ) "
\n" _block( block ); + + # Unordered list types + } else if ( text = _startlist( block, "ul", "-", "([+*]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { + return text; + } else if ( text = _startlist( block, "ul", "\\+", "([-*]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { + return text; + } else if ( text = _startlist( block, "ul", "\\*", "([-+]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { + return text; + + # Ordered list types + } else if ( text = _startlist( block, "ol", "[0-9]+\\.", "([-+*]|#\\.|[0-9]+\\)|#\\))") ) { + return text; + } else if ( text = _startlist( block, "ol", "[0-9]+\\)", "([-+*]|[0-9]+\\.|#\\.|#\\))") ) { + return text; + } else if ( text = _startlist( block, "ol", "#\\.", "([-+*]|[0-9]+\\.|[0-9]+\\)|#\\))") ) { + return text; + } else if ( text = _startlist( block, "ol", "#\\)", "([-+*]|[0-9]+\\.|#\\.|[0-9]+\\))") ) { + return text; + # Split paragraphs } else if ( match( block, /(^|\n)[[:space:]]*(\n|$)/) ) { len = RLENGTH; st = RSTART; @@ -688,52 +725,76 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at } } -function _list( block, last, LOCAL, p) { - if ( ! length(block) ) return ""; - gsub(/^([-+*]|[0-9]+\.|#\.)( ? ? ?|\t)/, "", block) +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, RSTART, RLENGTH); - # 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 ); + sub("^\n", "", list); match(list, "^ ? ? ?"); indent = RLENGTH; + gsub( "(^|\n) {0," indent - 1 "}", "\n", list); sub("^\n", "", list); - # 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 ); + text = substr(block, 1, st - 1); block = substr(block, st + len); + 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$)", "", text); + + return task text "
  • \n" _list(block, mark, p); +} + +function _dlist (block, LOCAL, len, st, text, indent, p) { + if (match( block, "^([ \t]*\n)*[^:\n \t][^\n]+\n" )) { + len = RLENGTH; text = substr(block, 1, len); + gsub( "(^\n*|\n*$)", "", text ); + return "
    " inline( text ) "
    \n" _dlist( substr(block, len + 1) ); + } else if (match( block, "^([ \t]*\n)* ? ? ?:[ \t][^\n]+(\n|$)" \ + "([^:\n \t][^\n]+(\n|$)" \ + "|( ? ? ?\t| +)[^\n]+(\n|$)" \ + "|([ \t]*\n)+( ? ? ?\t| +)[^\n]+(\n|$))*" \ + )) { + len = RLENGTH; text = substr(block, 1, len); + sub( "^([ \t]*\n)*", "", text); + match(text, "^ ? ? ?:(\t| +)"); indent = RLENGTH; + sub( "^ ? ? ?:(\t| +)", "", text); + gsub( "(^|\n) {0," indent "}", "\n", text ); + + text = _nblock(text); + if (match( text, "^

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

    |

    \n$)", "", text); + + return "
    " text "
    \n" _dlist( substr(block, len + 1) ); } - sub( /\n$/, "", 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 {