# 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:
# ==========================
# - ? Grid table (pandoc)
# - ? 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|$))*/) ) {
+ len = RLENGTH; st = RSTART;
+ return _block( substr( block, len + 1) );
# Blockquote (leading >)
} else if ( match( block, /^> /) ) {
return "<h" hlvl " id=\"" hid " - " HTML(htxt) "\">" inline( htxt ) "</h" hlvl ">\n\n" \
_block( substr( block, len + 1) );
+ # Split paragraphs
+ } else if ( match( block, /(^|\n)[[:space:]]*(\n|$)/) ) {
+ 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,})($|\n)/) ) {
len = RLENGTH; st = RSTART;
# Plain paragraph
} else {
- match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ );
- len = RLENGTH; st = RSTART;
- return "<p>" inline( substr(block, 1, st - 1) ) "</p>\n" \
- _block( substr(block, st + len) );
+ return "<p>" inline(block) "</p>\n";
}
}
}
sub( /\n$/, "", 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 {