# 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
-#
-# ToDo:
-# - HTML processing / escaping (according to environment flag)
-# - em-dashes and arrows
# Supported Features / TODO:
# ==========================
# - [x] Automatic heading identifiers (custom)
# - [x] Fenced code blocks (php md, pandoc)
# - [x] Fenced code attributes
-# - [ ] Tables
+# - [/] Tables
# - ? Simple table (pandoc)
# - ? Multiline table (pandoc)
-# - ? Grid table (pandoc)
-# - ? Pipe table (php md pandoc)
+# - [x] Grid table (pandoc)
+# - [x] Pipe table (php md pandoc)
# - [x] Line blocks (pandoc)
-# - [x] Task lists (pandoc)
+# - [x] Task lists (pandoc, custom)
# - [ ] Definition lists (php md, pandoc)
# - [-] Numbered example lists (pandoc)
# - [-] Metadata blocks (pandoc)
+# - [x] Metadata blocks (custom)
# - [x] Fenced Divs (pandoc)
#
# Extensions - Inline elements:
href = HTML( substr( line, 2, len - 2) );
return "<a href=\"" href "\">" href "</a>" 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 = HTML( substr( line, 2, len - 2) );
+ return "<a href=\"mailto:" href "\">" href "</a>" inline( substr( line, len + 1) );
+
# inline links
- } else if ( match(line, /^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/) ) {
+ } else if ( match(line, /^\[([^]]+)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/) ) {
len = RLENGTH;
- text = gensub(/^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\1", "g", line);
- href = gensub(/^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\2", "g", line);
- title = gensub(/^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\4", "g", line);
+ text = gensub(/^\[([^]]+)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/, "\\1", 1, substr(line, 1, len) );
+ href = gensub(/^\[([^]]+)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/, "\\2", 1, substr(line, 1, len) );
+ title = gensub(/^\[([^]]+)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/, "\\4", 1, substr(line, 1, len) );
if ( title ) {
return "<a href=\"" HTML(href) "\" title=\"" HTML(title) "\">" inline( text ) "</a>" inline( substr( line, len + 1) );
} else {
# reference style links
} else if ( match(line, /^\[([^]]+)\] ?\[([^]]*)\]/ ) ) {
len = RLENGTH;
- text = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\1", 1, line);
- id = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\2", 1, line);
+ 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 "<a href=\"" HTML(rl_href[id]) "\" title=\"" HTML(rl_title[id]) "\">" inline(text) "</a>" inline( substr( line, len + 1) );
# inline images
} else if ( match(line, /^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/) ) {
len = RLENGTH;
- text = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\1", "g", line);
- href = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\2", "g", line);
- title = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\4", "g", line);
+ text = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\1", "g", substr(line, 1, len) );
+ href = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\2", "g", substr(line, 1, len) );
+ title = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\4", "g", substr(line, 1, len) );
if ( title ) {
return "<img src=\"" HTML(href) "\" alt=\"" HTML(text) "\" title=\"" HTML(title) "\" />" inline( substr( line, len + 1) );
} else {
# reference style images
} else if ( match(line, /^!\[([^]]+)\] ?\[([^]]*)\]/ ) ) {
len = RLENGTH;
- text = gensub(/^!\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\1", 1, line);
- id = gensub(/^!\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\2", 1, line);
+ 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 "<img src=\"" HTML(rl_href[id]) "\" alt=\"" HTML(text) "\" title=\"" HTML(rl_title[id]) "\" />" inline( substr( line, len + 1) );
} 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|$))*/) ) {
+ len = RLENGTH; st = RSTART;
+ return _block( substr( block, len + 1) );
# Blockquote (leading >)
} else if ( match( block, /^> /) ) {
return "<blockquote>\n" _block( gensub( /(^|\n)> /, "\n", "g", substr(block, 1, st - 1) ) ) "</blockquote>\n\n" \
_block( substr(block, st + len) );
+ # Pipe Tables (pandoc / php md / gfm )
+ } else if ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?)\n" \
+ "((\\|)?:?(-+:?[\\|+])+:?-+:?(\\|)?)\n" \
+ "((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ) {
+ 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 = "<thead>\n<tr>"
+ for (cnt = 1; cnt < cols; cnt++)
+ ttext = ttext "<th align=\"" talign[cnt] "\">" inline(tarray[cnt]) "</th>"
+ ttext = ttext "</tr>\n</thead><tbody>\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 "<tr>"
+ for (cnt = 1; cnt < cols; cnt++)
+ ttext = ttext "<td align=\"" talign[cnt] "\">" inline(tarray[cnt]) "</td>"
+ ttext = ttext "</tr>\n"
+ }
+ return "<table>" ttext "</tbody></table>\n" _block(block);
+
+ # Grid Tables (pandoc)
+ } else if ( match(block, "^\\+(-+\\+)+\n" \
+ "(\\|([^\n]+\\|)+\n)+" \
+ "\\+(:?=+:?\\+)+\n" \
+ "((\\|([^\n]+\\|)+\n)+" \
+ "\\+(-+\\+)+(\n|$))+" \
+ ) ) {
+ len = RLENGTH; st = RSTART;
+ #initialize empty arrays
+ split("", talign); split("", tarray); split("", tread);
+ cols = 0; cnt=0; ttext = "";
+
+ # table header and alignment
+ block = substr(block, match(block, /(\n|$)/) + 1 );
+ while ( match(block, "^\\|([^\n]+\\|)+\n") ) {
+ cols = split( gensub( /(^\||\|$)/, "", "g", \
+ gensub( /(^|[^\\])\\\|/, "\\1\\|", "g", \
+ substr(block, 1, match(block, /(\n|$)/)) \
+ )), tread, /\|/);
+ block = substr(block, match(block, /(\n|$)/) + 1 );
+ for (cnt = 1; cnt < cols; cnt++)
+ tarray[cnt] = tarray[cnt] "\n" tread[cnt];
+ }
+
+ cols = split( \
+ gensub( /(^\+|\+$)/, "", "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 = "<thead>\n<tr>"
+ for (cnt = 1; cnt < cols; cnt++)
+ ttext = ttext "<th align=\"" talign[cnt] "\">" _block(tarray[cnt]) "</th>"
+ ttext = ttext "</tr>\n</thead><tbody>\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|$)/) + 1 );
+
+ ttext = ttext "<tr>"
+ for (cnt = 1; cnt < cols; cnt++)
+ ttext = ttext "<td align=\"" talign[cnt] "\">" _block(tarray[cnt]) "</td>"
+ ttext = ttext "</tr>\n"
+ }
+ return "<table>" ttext "</tbody></table>\n" _block(block);
+
# Line Blocks (pandoc)
} else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\n]*(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) {
len = RLENGTH; st = RSTART;
_block( substr( block, len + 1) );
# Indented Code Block
- } else if ( match(block, /^( |\t)[^\n]+(\n|$)(( |\t)[^\n]+(\n|$)|[ \t]*(\n|$))*/) ) {
+ } else if ( match(block, /^( |\t)( *\t*[^ \t\n])+(\n|$)(( |\t)[^\n]+(\n|$)|[ \t]*(\n|$))*/) ) {
len = RLENGTH; st = RSTART;
code = substr(block, 1, len);
gsub(/(^|\n)( |\t)/, "\n", code);
} else if ( match( block, /^(~~~+|```+)/ ) ) {
guard = substr( block, 1, RLENGTH );
code = gensub(/^[^\n]+\n/, "", 1, block);
- attrib = gensub(/^:::+[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\1", 1, block);
+ attrib = gensub(/^(~~~+|```+)[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\2", 1, block);
gsub(/[^a-zA-Z0-9_-]+/, " ", attrib);
gsub(/(^ | $)/, "", attrib);
if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) {
} else if ( match( block, /^[^\n]+\n===+(\n|$)/ ) ) {
len = RLENGTH;
HL[1]++; HL[2] = 0; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
- return "<h1 id=\"" HL[1] " - " HTML(gensub( /\n.*$/, "", "g", block )) "\">" inline( gensub( /\n.*$/, "", "g", block ) ) "</h1>\n\n" \
+ return "<h1 id=\"" HL[1] " - " HTML(gensub( /\n.*$/, "", "g", block )) "\">" \
+ inline( gensub( /\n.*$/, "", "g", block ) ) \
+ "<a class=\"anchor\" href=\"#" HL[1] " - " \
+ HTML(gensub( /\n.*$/, "", "g", block )) "\"></a></h1>\n\n" \
_block( substr( block, len + 1 ) );
# Second Order Heading
} else if ( match( block, /^[^\n]+\n---+(\n|$)/ ) ) {
len = RLENGTH;
HL[2]++; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
- return "<h2 id=\"" HL[1] "." HL[2] " - " HTML(gensub( /\n.*$/, "", "g", block )) "\">" inline( gensub( /\n.*$/, "", "g", block ) ) "</h2>\n\n" \
+ return "<h2 id=\"" HL[1] "." HL[2] " - " HTML(gensub( /\n.*$/, "", "g", block )) "\">" \
+ inline( gensub( /\n.*$/, "", "g", block ) ) \
+ "<a class=\"anchor\" href=\"#" HL[1] "." HL[2] " - " \
+ HTML(gensub( /\n.*$/, "", "g", block )) "\"></a></h2>\n\n" \
_block( substr( block, len + 1) );
# Nth Order Heading
htxt = gensub(/^#{1,6}[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[^\n#])+)([ \t]*#*)(\n.*)?$/, "\\1", 1, block);
HL[hlvl]++; for ( n = hlvl + 1; n < 7; n++) { HL[n] = 0;}
hid = HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; }
- return "<h" hlvl " id=\"" hid " - " HTML(htxt) "\">" inline( htxt ) "</h" hlvl ">\n\n" \
+ return "<h" hlvl " id=\"" hid " - " HTML(htxt) "\">" inline( htxt ) \
+ "<a class=\"anchor\" href=\"#" hid "\"></a></h" hlvl ">\n\n" \
_block( substr( block, len + 1) );
# Split paragraphs
}
sub( /\n$/, "", p );
- # Task List (pandoc)
- if ( p ~ /^\[ \].*/ ) { p = "<input type=checkbox disabled />" substr(p, 4); }
- else if ( p ~ /^\[[xX]\].*/ ) { p = "<input type=checkbox disabled checked />" substr(p, 4); }
- else if ( p ~ /^<p>\[ \].*/ ) { p = "<p><input type=checkbox disabled />" substr(p, 7); }
- else if ( p ~ /^<p>\[[xX]\].*/ ) { p = "<p><input type=checkbox disabled checked />" substr(p, 7); }
- return "<li>" p "</li>\n" _list( block, last );
+ # Task List (pandoc, custom)
+ if ( p ~ /^\[ \].*/ ) { return "<li class=\"task pending\"><input type=checkbox disabled />" \
+ substr(p, 4) "</li>\n" _list( block, last );
+ } else if ( p ~ /^\[-\].*/ ) { return "<li class=\"task negative\"><input type=checkbox disabled />" \
+ substr(p, 4) "</li>\n" _list( block, last );
+ } else if ( p ~ /^\[\?\].*/ ) { return "<li class=\"task unsure\"><input type=checkbox disabled />" \
+ substr(p, 4) "</li>\n" _list( block, last );
+ } else if ( p ~ /^\[\/\].*/ ) { return "<li class=\"task partial\"><input type=checkbox disabled />" \
+ substr(p, 4) "</li>\n" _list( block, last );
+ } else if ( p ~ /^\[[xX]\].*/ ) { return "<li class=\"task done\"><input type=checkbox disabled checked />" \
+ substr(p, 4) "</li>\n" _list( block, last );
+ } else if ( p ~ /^<p>\[ \].*/ ) { return "<li class=\"task pending\"><p><input type=checkbox disabled />" \
+ substr(p, 7) "</li>\n" _list( block, last );
+ } else if ( p ~ /^<p>\[-\].*/ ) { return "<li class=\"task negative\"><p><input type=checkbox disabled />" \
+ substr(p, 7) "</li>\n" _list( block, last );
+ } else if ( p ~ /^<p>\[\?\].*/ ) { return "<li class=\"task unsure\"><p><input type=checkbox disabled />" \
+ substr(p, 7) "</li>\n" _list( block, last );
+ } else if ( p ~ /^<p>\[\/\].*/ ) { return "<li class=\"task partial\"><p><input type=checkbox disabled />" \
+ substr(p, 7) "</li>\n" _list( block, last );
+ } else if ( p ~ /^<p>\[[xX]\].*/ ) { return "<li class=\"task done\"><p><input type=checkbox disabled checked />" \
+ substr(p, 7) "</li>\n" _list( block, last );
+ } else { return "<li>" p "</li>\n" _list( block, last ); }
}
BEGIN {