#!/bin/awk -f #!/opt/busybox/awk -f # EXPERIMENTAL Markdown processor with minimal dependencies. # 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 # # Basic Markdown - Block elements: # ------------------------------- # - [x] Paragraphs # - [x] Double space line breaks # - [x] Proper block element nesting # - [x] Headings # - [x] ATX-Style Headings # - [x] Blockquotes # - [x] Lists (ordered, unordered) # - [x] Code blocks (using indention) # - [x] Horizontal rules # - [x] Verbatim HTML block (disabled by default) # # Basic Markdown - Inline elements: # --------------------------------- # - [x] Links # - [x] Reference style links # - [x] Emphasis *em*/**strong** (*Asterisk*, _Underscore_) # - [x] `code`, also ``code containing `backticks` `` # - [x] Images / reference style images # - [x] # - [x] backslash escapes # - [x] Verbatim HTML inline (disabled by default) # - [x] HTML escaping # # NOTE: Set the environment variable MD_HTML=true to enable verbatim HTML # # Extensions - Block elements: # ---------------------------- # - [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 # - [x] Images (as block elements,
-wrapped) (custom) # - [x] reference style block images # - [/] Tables # - ? Simple table (pandoc) # - ? Multiline table (pandoc) # - [x] Grid table (pandoc) # - [x] Headerless # - [x] Pipe table (php md, pandoc) # - [x] Line blocks (pandoc) # - [x] Task lists (pandoc, custom) # - [x] Definition lists (php md, pandoc) # - [-] Numbered example lists (pandoc) # - [-] Metadata blocks (pandoc) # - [x] Metadata blocks (custom) # - [x] Fenced Divs (pandoc) # # Extensions - Inline elements: # ---------------------------- # - [x] Ignore embedded_underscores (php md, pandoc) # - [x] ~~strikeout~~ (pandoc) # - [x] ^Superscript^ ~Subscript~ (pandoc) # - [-] Bracketed spans (pandoc) # - [-] Inline attributes (pandoc) # - [x] Image attributes (custom, pandoc inspired, not for reference style) # - [x] Wiki style links [[PageName]] / [[PageName|Link Text]] # - [-] TEX-Math (pandoc) # - ? Footnotes (php md) # - ? Abbreviations (php md) # - ? "Curly quotes" (smartypants) # - [ ] em-dashes (--) (smartypants old) # - ? ... three-dot ellipsis (smartypants) # - [-] en-dash (smartypants) # - [ ] Automatic em-dash / en-dash # - [x] Automatic -> Arrows <- (custom) function debug(text) { printf "\n---\n%s\n---\n", text > "/dev/stderr"; } function HTML ( text ) { gsub( /&/, "\\&", text ); gsub( //, "\\>", text ); gsub( /"/, "\\"", text ); gsub( /'/, "\\'", text ); gsub( /\\/, "\\\", text ); return text; } function URL ( text, sharp ) { gsub( /&/, "%26", text ); gsub( /"/, "%22", text ); gsub( /'/, "%27", text ); gsub( /`/, "%60", text ); gsub( /\?/, "%3F", text ); if (sharp) gsub( /#/, "%23", text ); gsub( /\[/, "%5B", text ); gsub( /\]/, "%5D", text ); gsub( / /, "%20", text ); gsub( / /, "%09", text ); gsub( /\\/, "%5C", text ); return text; } function inline( line, LOCAL, len, text, code, href, guard ) { if ( line ~ /^$/ ) { # Recursion End return ""; # omit processing of escaped characters } else if ( line ~ /^\\./) { return HTML(substr(line, 2, 1)) inline( substr(line, 3) ); # hard brakes } else if ( match(line, /^ \n/) ) { return "
\n" inline( substr(line, RLENGTH + 1) ); # ``code spans`` } else if ( match( line, /^`+/) ) { len = RLENGTH guard = substr( line, 1, len ) if ( match(line, guard ".*" guard) ) { code = substr( line, len + 1, match( substr(line, len + 1), guard ) - 1) len = 2 * length(guard) + length(code) # strip single surrounding white spaces 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) ); # 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) ); 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) ); 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 } else if ( match(line, "^" lii "\\([\\n\\t ]*" lid "([\\n\\t ]+" lit ")?[\\n\\t ]*\\)") ) { len = RLENGTH; 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, /^\[([^]]+)\] ?\[([^]]*)\]/ ) ) { len = RLENGTH; text = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\1", 1, substr(line, 1, len) ); 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) ); } else if ( rl_href[id] ) { 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, "^!" 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, /^!\[([^]]*)\] ?\[([^]]*)\]/ ) ) { len = RLENGTH; text = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\].*/, "\\1", 1, substr(line, 1, len) ); id = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\].*/, "\\2", 1, substr(line, 1, len) ); if ( ! id ) id = text; if ( rl_href[id] && rl_title[id] ) { return "\""" \ inline( substr( line, len + 1) ); } else if ( rl_href[id] ) { return "\""" \ inline( substr( line, len + 1) ); } else { return "" HTML(substr(line, 1, len)) inline( substr(line, len + 1) ); } # ~~strikeout~~ (pandoc) } else if ( match(line, /^~~([[:graph:]]|[[:graph:]]([^~]|~[^~])*[[:graph:]])~~/) ) { len = RLENGTH; return "" inline( substr( line, 3, len - 4 ) ) "" inline( substr( line, len + 1 ) ); # ^superscript^ (pandoc) } else if ( match(line, /^\^([^[:space:]^]|\\[ ^])+\^/) ) { len = RLENGTH; return "" inline( substr( line, 2, len - 2 ) ) "" inline( substr( line, len + 1 ) ); # ~subscript~ (pandoc) } else if ( match(line, /^~([^[:space:]~]|\\[ ~])+~/) ) { len = RLENGTH; return "" inline( substr( line, 2, len - 2 ) ) "" inline( substr( line, len + 1 ) ); # ignore embedded underscores (pandoc, php md) } else if ( match(line, "^[[:alnum:]](__|_)") ) { return HTML(substr( line, 1, RLENGTH)) inline( substr(line, RLENGTH + 1) ); # __strong__$ } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__$") ) { len = RLENGTH; return "" inline( substr( line, 3, len - 4 ) ) "" inline( substr( line, len + 1 ) ); # __strong__ } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__[[:space:][:punct:]]") ) { len = RLENGTH; return "" inline( substr( line, 3, len - 5 ) ) "" inline( substr( line, len) ); # **strong** } else if ( match(line, "^\\*\\*(([^\\*[:space:]]|" iea ")|([^\\*[:space:]]|" iea ")(" na "|" iea ")*([^\\*[:space:]]|" iea "))\\*\\*") ) { len = RLENGTH; return "" inline( substr( line, 3, len - 4 ) ) "" inline( substr( line, len + 1 ) ); # _em_$ } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_$") ) { len = RLENGTH; return "" inline( substr( line, 2, len - 2 ) ) "" inline( substr( line, len + 1 ) ); # _em_ } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_[[:space:][:punct:]]") ) { len = RLENGTH; return "" inline( substr( line, 2, len - 3 ) ) "" inline( substr( line, len ) ); # *em* } else if ( match(line, "^\\*(([^\\*[:space:]]|" isa ")|([^\\*[:space:]]|" isa ")(" na "|" isa ")*([^\\*[:space:]]|" isa "))\\*") ) { len = RLENGTH; return "" inline( substr( line, 2, len - 2 ) ) "" inline( substr( line, len + 1 ) ); # Literal HTML entities } else if ( match( line, /^&([a-zA-Z]{2,32}|#[0-9]{1,7}|#[xX][0-9a-fA-F]{1,6});/) ) { len = RLENGTH; return substr( line, 1, len ) inline(substr(line, len + 1)); # Arrows } else if ( line ~ /^-->( |$)/) { # ignore multidash-arrow return "-->" inline( substr(line, 4) ); } else if ( line ~ /^<-( |$)/) { return "←" inline( substr(line, 3) ); } else if ( line ~ /^->( |$)/) { return "→" inline( substr(line, 3) ); # Escape lone HTML character } else if ( match( line, /^[&<>"']/) ) { return HTML(substr(line, 1, 1)) inline(substr(line, 2)); # continue walk over string } else { return substr(line, 1, 1) inline( substr(line, 2) ); } } function headline( hlvl, htxt, attrib, LOCAL, sec, n, HL) { match(hstack, /([0-9]+( [0-9]+){5})$/); split( substr(hstack, RSTART), HL); for ( n = hlvl; n <= 6; n++ ) { sec = sec (HL[n]?"
":""); } HL[hlvl]++; for ( n = hlvl + 1; n <= 6; n++) { HL[n] = 0;} hid = ""; for ( n = 2; n <= blvl; n++) { hid = hid BL[n] "/"; } hid = hid HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; } hid = hid ":" URL(htxt, 1); sub(/([0-9]+( [0-9]+){5})$/, "", hstack); hstack = hstack HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6]; return sec "
" \ "" inline( htxt ) \ "" \ "\n"; } # Nested Block, resets heading counters function _nblock( block, LOCAL, sec, n ) { hstack = hstack " 0 0 0 0 0 0"; # Block Level blvl++; BL[blvl]++; for ( n = blvl + 1; n in BL; n++) { delete BL[n]; } block = _block( block ); 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--; return block sec; } function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, indent, list ) { gsub( "(^\n+|\n+$)", "", block ); if ( block == "" ) { return ""; # HTML #2 #3 #4 $5 } else if ( AllowHTML && match( block, /(^|\n) ? ? ?(|$)|<\?([^\?]|\?[^>])*(\?>|$)|]*(>|$)|])*(\]\]>|$))/) ) { len = RLENGTH; st = RSTART; return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len)); # HTML #6 } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<\/?(address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset|h[123456]|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul)([[:space:]\n>]|\/>)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) { len = RLENGTH; st = RSTART; return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len)); # HTML #1 } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<(script|pre|style)([[:space:]\n>]).*(<\/script>|<\/pre>|<\/style>|$)/) ) { len = RLENGTH; st = RSTART; match( tolower(substr(block, st, len)), /(<\/script>|<\/pre>|<\/style>)/); len = RSTART + RLENGTH; return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len)); # HTML #7 } else if ( AllowHTML && match( block, /^ ? ? ?(<\/[A-Za-z][A-Za-z0-9-]*[[:space:]]*>|<[A-Za-z][A-Za-z0-9-]*([[:space:]]+[A-Za-z_:][A-Za-z0-9_\.:-]*([[:space:]]*=[[:space:]]*([[:space:]"'=<>`]+|"[^"]*"|'[^']*'))?)*[[:space:]]*\/?>)([[:space:]]*\n)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) { len = RLENGTH; st = RSTART; return substr(block, st, len) _block(substr(block, st + len)); # 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|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) { len = RLENGTH; st = RSTART; return _block( substr( block, len + 1) ); # Blockquote (leading >) } else if ( match( block, /^> /) ) { match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match(block, /$/); len = RLENGTH; st = RSTART; text = substr(block, 1, st - 1); gsub( /(^|\n)> /, "\n", text ); text = _nblock( text ); gsub( /^\n|\n$/, "", text ) return "
" text "
\n\n" _block( substr(block, st + len) ); # Pipe Tables (pandoc / php md / gfm ) } else if ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?)\n" \ "((\\|)?(:?-+:?[\\|+])+:?-+:?(\\|)?)\n" \ "((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ) { len = RLENGTH; st = RSTART; #initialize empty arrays split("", talign); split("", tarray); cols = 0; cnt=0; ttext = ""; # table header and alignment split( gensub( /(^\||\|$)/, "", "g", \ gensub( /(^|[^\\])\\\|/, "\\1\\|", "g", \ substr(block, 1, match(block, /(\n|$)/)) \ )), tarray, /\|/); block = substr(block, match(block, /(\n|$)/) + 1 ); cols = split( \ gensub( /(^\||\|$)/, "", "g", \ substr(block, 1, match(block, /(\n|$)/)) \ ), talign, /[+\|]/); block = substr(block, match(block, /(\n|$)/) + 1 ); for( cnt = 1; cnt < cols; cnt++ ) { if (match(talign[cnt], /:-+:/)) talign[cnt]="center"; else if (match(talign[cnt], /-+:/)) talign[cnt]="right"; else if (match(talign[cnt], /:-+/)) talign[cnt]="left"; else talign[cnt]=""; } ttext = "\n" for (cnt = 1; cnt < cols; cnt++) ttext = ttext "" inline(tarray[cnt]) "" ttext = ttext "\n\n" while ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ){ split( gensub( /(^\||\|$)/, "", "g", \ gensub( /(^|[^\\])\\\|/, "\\1\\|", "g", \ substr(block, 1, match(block, /(\n|$)/)) \ )), tarray, /\|/); block = substr(block, match(block, /(\n|$)/) + 1 ); ttext = ttext "" for (cnt = 1; cnt < cols; cnt++) ttext = ttext "" inline(tarray[cnt]) "" ttext = ttext "\n" } return "" ttext "
\n" _block(block); # Grid Tables (pandoc) # (with, and without header) } else if ( match( block, "^\\+(-+\\+)+\n" \ "(\\|([^\n]+\\|)+\n)+" \ "(\\+(:?=+:?\\+)+)\n" \ "((\\|([^\n]+\\|)+\n)+" \ "\\+(-+\\+)+(\n|$))+" \ ) || \ match( block, "^()()()" \ "(\\+(:?-+:?\\+)+)\n" \ "((\\|([^\n]+\\|)+\n)+" \ "\\+(-+\\+)+(\n|$))+" \ ) ) { len = RLENGTH; st = RSTART; #initialize empty arrays split("", talign); split("", tarray); split("", tread); cols = 0; cnt=0; ttext = ""; # Column Count cols = split( gensub( "^(\\+(:?-+:?\\+)+)(\n.*)*$", "\\1", 1, block), tread, /\+/) - 2; # debug(" Cols: " gensub( "^(\\+(:?-+:?\\+)+)(\n.*)*$", "\\1", 1, block )); # table alignment split( gensub( "^(.*\n)?\\+((:?=+:?\\+|(:-+|-+:|:-+:)\\+)+)(\n.*)$", "\\2", "g", block ), talign, /\+/ ); # debug("Align: " gensub( "^(.*\n)?\\+((:?=+:?\\+|(:-+|-+:|:-+:)\\+)+)(\n.*)$", "\\2", "g", block )); for (cnt = 1; cnt <= cols; cnt++) { if (match(talign[cnt], /:(-+|=+):/)) talign[cnt]="center"; else if (match(talign[cnt], /(-+|=+):/)) talign[cnt]="right"; else if (match(talign[cnt], /:(-+|=+)/ )) talign[cnt]="left"; else talign[cnt]=""; } if ( match(block, "^\\+(-+\\+)+\n" \ "(\\|([^\n]+\\|)+\n)+" \ "\\+(:?=+:?\\+)+\n" \ "((\\|([^\n]+\\|)+\n)+" \ "\\+(-+\\+)+(\n|$))+" \ ) ) { # table header block = substr(block, match(block, /(\n|$)/) + 1 ); while ( match(block, "^\\|([^\n]+\\|)+\n") ) { split( gensub( /(^\||\|$)/, "", "g", \ gensub( /(^|[^\\])\\\|/, "\\1\\|", "g", \ substr(block, 1, match(block, /(\n|$)/)) \ )), tread, /\|/); block = substr(block, match(block, /(\n|$)/) + 1 ); for (cnt = 1; cnt <= cols; cnt++) tarray[cnt] = tarray[cnt] "\n" tread[cnt]; } ttext = "\n" for (cnt = 1; cnt <= cols; cnt++) ttext = ttext "" _nblock(tarray[cnt]) "" ttext = ttext "\n" } # table body block = substr(block, match(block, /(\n|$)/) + 1 ); ttext = ttext "\n" while ( match(block, /^((\|([^\n]+\|)+\n)+\+(-+\+)+(\n|$))+/ ) ){ split("", tarray); while ( match(block, /^\|([^\n]+\|)+\n/) ) { split( gensub( /(^\||\|$)/, "", "g", \ gensub( /(^|[^\\])\\\|/, "\\1\\|", "g", \ substr(block, 1, match(block, /(\n|$)/)) \ )), tread, /\|/); block = substr(block, match(block, /(\n|$)/) + 1 ); for (cnt = 1; cnt <= cols; cnt++) tarray[cnt] = tarray[cnt] "\n" tread[cnt]; } block = substr(block, match(block, /(\n|$)/) + 1 ); ttext = ttext "" for (cnt = 1; cnt <= cols; cnt++) ttext = ttext "" _nblock(tarray[cnt]) "" ttext = ttext "\n" } return "" ttext "
\n" _nblock(block); # Line Blocks (pandoc) } else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\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$/, "", text); text = inline(text); gsub(/\n/, "
\n", text); return "
" text "
\n" _block( substr( block, len + 1) ); # Indented Code Block } else if ( match(block, /^( |\t)( *\t*[^ \t\n]+ *\t*)+(\n|$)(( |\t)[^\n]+(\n|$)|[ \t]*(\n|$))*/) ) { len = RLENGTH; st = RSTART; code = substr(block, 1, len); gsub(/(^|\n)( |\t)/, "\n", code); gsub(/^\n|\n+$/, "", code); return "
" HTML( code ) "
\n" \ _block( substr( block, len + 1 ) ); # Fenced Divs (pandoc, custom) } else if ( match( block, /^(:::+)/ ) ) { guard = substr( block, 1, RLENGTH ); code = block; sub(/^[^\n]+\n/, "", code); attrib = gensub(/^:::+[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\1", 1, block); gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib); if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) { len = RLENGTH; st = RSTART; return "
" _nblock( substr(code, 1, st - 1) ) "
\n" \ _block( substr( code, st + len ) ); } else { match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ ); len = RLENGTH; st = RSTART; return "

" inline( substr(block, 1, st - 1) ) "

\n" \ _block( substr(block, st + len) ); } # Fenced Code Block (pandoc) } else if ( match( block, /^(~~~+|```+)/ ) ) { guard = substr( block, 1, RLENGTH ); code = gensub(/^[^\n]+\n/, "", 1, block); attrib = gensub(/^(~~~+|```+)[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\2", 1, block); gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib); if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) { len = RLENGTH; st = RSTART; return "
" HTML( substr(code, 1, st - 1) ) "
\n" \ _block( substr( code, st + len ) ); } else { match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ ); len = RLENGTH; st = RSTART; return "

" inline( substr(block, 1, st - 1) ) "

\n" \ _block( substr(block, st + len) ); } # 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; 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 = 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 = 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; 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(/(^ | $)/, "", attrib); return headline( n, text, attrib ) _block( substr( block, len + 1) ); # Nth Order Heading H1 H2 H3 H4 H5 H6 } else if ( match( block, /^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n|$)/ ) ) { len = RLENGTH; text = substr(block, 1, len); match(block, /^#{1,6}/); n = RLENGTH; sub(/^(#{1,6})[ \t]*/, "", text); sub(/[ \t]*#*(\n.*)?$/, "", text); return headline( n, text, 0 ) _block( substr( block, len + 1) ); # block images (wrapped in
) } else if ( match(block, "^!" lix "\\([\\n\\t ]*" lid "([\\n\\t ]+" lit ")?[\\n\\t ]*\\)(\\{[a-zA-Z \\t-]*\\})?(\\n|$)") ) { 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|$)/ ) ) { len = RLENGTH; text = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\](\n.*)?$/, "\\1", 1, block); id = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\](\n.*)?$/, "\\2", 1, block); if ( ! id ) id = text; if ( rl_href[id] && rl_title[id] ) { return "
" \ "\""" \ "
" inline(rl_title[id]) "
" \ "
\n\n" \ _block( substr( block, len + 1) ); } else if ( rl_href[id] ) { return "
" \ "\""" \ "
\n\n" \ _block( substr( block, len + 1) ); } else { return "

" HTML(substr(block, 1, len)) "

\n" _block( substr(block, len + 1) ); } # Macros (standalone <> calls handled as block, so they are not wrapped in paragraph) } else if ( match( block, /^<<(([^>]|>[^>])+)>>(\n|$)/ ) ) { len = RLENGTH; text = gensub(/^<<(([^>]|>[^>])+)>>(\n.*)?$/, "\\1", 1, block); 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|$))*)+" \ )) { list = substr( block, 1, RLENGTH); block = substr( block, RLENGTH + 1); return "\n
\n" _dlist( list ) "
\n" _block( block ); # Unordered list types } else if ( text = _startlist( block, "ul", "-", "([+*•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { return text; } else if ( text = _startlist( block, "ul", "\\+", "([-*•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { return text; } else if ( text = _startlist( block, "ul", "\\*", "([-+•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { return text; } else if ( text = _startlist( block, "ul", "•", "([-+*]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { return text; # Ordered list types } else if ( text = _startlist( block, "ol", "[0-9]+\\.", "([-+*•]|#\\.|[0-9]+\\)|#\\))") ) { return text; } else if ( text = _startlist( block, "ol", "[0-9]+\\)", "([-+*•]|[0-9]+\\.|#\\.|#\\))") ) { return text; } else if ( text = _startlist( block, "ol", "#\\.", "([-+*•]|[0-9]+\\.|[0-9]+\\)|#\\))") ) { return text; } else if ( text = _startlist( block, "ol", "#\\)", "([-+*•]|[0-9]+\\.|#\\.|[0-9]+\\))") ) { return text; # Split paragraphs } else if ( match( block, /(^|\n)[[:space:]]*(\n|$)/) ) { len = RLENGTH; st = RSTART; return _block( substr(block, 1, st - 1) ) "\n" \ _block( substr(block, st + len) ); # Horizontal rule } else if ( match( block, /(^|\n) ? ? ?((\* *){3,}|(- *){3,}|(_ *){3,})($|\n)/) ) { len = RLENGTH; st = RSTART; return _block(substr(block, 1, st - 1)) "
\n" _block(substr(block, st + len)); # Plain paragraph } else { return "

" inline(block) "

\n"; } } 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$)", "", text); return task text "
  • \n" _list(block, mark, p); } function _dlist (block, LOCAL, len, st, text, indent, p) { if (match( block, "^([ \t]*\n)*[^:\n \t][^\n]+\n" )) { len = RLENGTH; text = substr(block, 1, len); gsub( "(^\n*|\n*$)", "", 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) ); } } BEGIN { # Global Vars file = ""; rl_href[""] = ""; rl_title[""] = ""; if (ENVIRON["MD_HTML"] == "true") { AllowHTML = "true"; } 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 $0 "\n"; } # Clean up MS-DOS line breaks gsub(/\r\n/, "\n", file); # Fill array of reference links f = file; rl_id; re_reflink = "(^|\n) ? ? ?\\[([^]\n]+)\\]: ([^ \t\n]+)(\n?[ \t]+(\"([^\"]+)\"|'([^']+)'|\\(([^)]+)\\)))?(\n|$)"; # /(^|\n) ? ? ?\[([^]\n]+)\]: ([^ \t\n]+)(\n?[ \t]+("([^"]+)"|'([^']+)'|\(([^)]+)\)))?(\n|$)/ while ( match(f, re_reflink ) ) { rl_id = gensub( re_reflink, "\\2", 1, substr(f, RSTART, RLENGTH) ); rl_href[rl_id] = gensub( re_reflink, "\\3", 1, substr(f, RSTART, RLENGTH) ); rl_title[rl_id] = gensub( re_reflink, "\\5", 1, substr(f, RSTART, RLENGTH) ); f = substr(f, RSTART + RLENGTH); rl_title[rl_id] = substr( rl_title[rl_id], 2, length(rl_title[rl_id]) - 2 ); if ( rl_href[rl_id] ~ /<.*>/ ) rl_href[rl_id] = substr( rl_href[rl_id], 2, length(rl_href[rl_id]) - 2 ); } # Clear reflinks from File while( gsub(re_reflink, "\n", file ) ); # for (n in rl_href) { debug(n " | " rl_href[n] " | " rl_title[n] ); } # Run Block Processing -> The Actual Markdown! printf "%s", _nblock( file ); }