# Supported Features / TODO:
# ==========================
-# [x] done [ ] todo [-] not planned [?] unsure
+# [x] done [ ] todo [-] not planned ? unsure
#
# Basic Markdown - Block elements:
# -------------------------------
# - [x] Paragraphs
-# - [ ] Double space line breaks
+# - [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)
-# - [ ] Horizontal rules
+# - [x] Horizontal rules
+# - [x] Verbatim HTML block (disabled by default)
#
# Basic Markdown - Inline elements:
# ---------------------------------
# - [x] Reference style links
# - [x] Emphasis *em*/**strong** (*Asterisk*, _Underscore_)
# - [x] `code`, also ``code containing `backticks` ``
-# - [ ] Images / reference style images
+# - [x] Images / reference style images
# - [x] <automatic links>
# - [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:
# ----------------------------
-# - [?] Heading identifiers (phpmarkdown, pandoc)
-# - [x] Fenced code blocks (phpmarkdown, pandoc)
+# - ? Heading identifiers (php md, pandoc)
+# - [x] Automatic heading identifiers (custom)
+# - [x] Fenced code blocks (php md, pandoc)
# - [-] Fenced code attributes
# - [ ] Tables
-# - [?] Simple table (pandoc)
-# - [?] Multiline table (pandoc)
-# - [?] Grid table (pandoc)
-# - [?] Pipe table (phpmarkdown, pandoc)
+# - ? Simple table (pandoc)
+# - ? Multiline table (pandoc)
+# - ? Grid table (pandoc)
+# - ? Pipe table (php md pandoc)
# - [x] Line blocks (pandoc)
-# - [ ] Task lists (pandoc)
-# - [ ] Definition lists (phpmarkdown, pandoc)
+# - [x] Task lists (pandoc)
+# - [ ] Definition lists (php md, pandoc)
# - [-] Numbered example lists (pandoc)
# - [-] Metadata blocks (pandoc)
# - [-] Fenced Divs (pandoc)
#
# Extensions - Inline elements:
# ----------------------------
-# - [ ] Ignore embedded_underscores (phpmarkdown, pandoc)
+# - [x] Ignore embedded_underscores (php md, pandoc)
# - [x] ~~strikeout~~ (pandoc)
# - [x] ^Superscript^ ~Subscript~ (pandoc)
# - [-] Bracketed spans (pandoc)
# - [-] Inline attributes (pandoc)
# - [-] TEX-Math (pandoc)
-# - [?] Footnotes (phpmarkdown)
-# - [?] Abbreviations (phpmarkdown)
-# - [?] "Curly quotes" (smartypants)
+# - ? Footnotes (php md)
+# - ? Abbreviations (php md)
+# - ? "Curly quotes" (smartypants)
# - [ ] em-dashes (--) (smartypants old)
-# - [?] ... three-dot ellipsis (smartypants)
+# - ? ... three-dot ellipsis (smartypants)
# - [-] en-dash (smartypants)
# - [ ] Automatic em-dash / en-dash
# - [ ] Automatic -> Arrows <-
}
function inline( line, LOCAL, len, code, href, guard ) {
- nu = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\_])*" # not underline (except when escaped)
+ nu = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\_]|_[[:alnum:]])*" # not underline (except when escaped)
na = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\\\*])*" # not asterisk (except when escaped)
ieu = "_([^_[:space:]]|[^_[:space:]]" nu "[^_[:space:]])_" # inner <em> (underline)
isu = "__([^_[:space:]]|[^_[:space:]]" nu "[^_[:space:]])__" # inner <strong> (underline)
} else if ( line ~ /^\\[]\\`\*_\{\}\(\)#\+-\.![]/) {
return substr(line, 2, 1) inline( substr(line, 3) );
+ # hard brakes
+ } else if ( match(line, /^ \n/) ) {
+ return "<br />\n" inline( substr(line, RLENGTH + 1) );
+
# ``code spans``
} else if ( match( line, /^`+/) ) {
len = RLENGTH
id = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\2", 1, line);
if ( ! id ) id = text;
if ( rl_href[id] && rl_title[id] ) {
- return "<a href=\"" rl_href[id] "\" title=\"" rl_title[id] "\">" inline(text) "</a>" inline( substr( line, len + 1) );
+ return "<a href=\"" HTML(rl_href[id]) "\" title=\"" HTML(rl_title[id]) "\">" inline(text) "</a>" inline( substr( line, len + 1) );
} else if ( rl_href[id] ) {
- return "<a href=\"" rl_href[id] "\">" inline(text) "</a>" inline( substr( line, len + 1) );
+ return "<a href=\"" HTML(rl_href[id]) "\">" inline(text) "</a>" inline( substr( line, len + 1) );
} else {
- return "" substr(line, 1, len) inline( substr(line, len + 1) );
+ return "" HTML(substr(line, 1, len)) 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);
+ if ( title ) {
+ return "<img src=\"" HTML(href) "\" alt=\"" HTML(text) "\" title=\"" HTML(title) "\" />" inline( substr( line, len + 1) );
+ } else {
+ return "<img src=\"" HTML(href) "\" alt=\"" HTML(text) "\" />" inline( substr( line, len + 1) );
+ }
+
+ # reference style images
+ } else if ( match(line, /^!\[([^]]+)\] ?\[([^]]*)\]/ ) ) {
+ len = RLENGTH;
+ text = gensub(/^!\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\1", 1, line);
+ id = gensub(/^!\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\2", 1, line);
+ 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 ( rl_href[id] ) {
+ return "<img src=\"" HTML(rl_href[id]) "\" alt=\"" HTML(text) "\" />" inline( substr( line, len + 1) );
+ } else {
+ return "" HTML(substr(line, 1, len)) inline( substr(line, len + 1) );
}
# ~~strikeout~~ (pandoc)
len = RLENGTH;
return "<sub>" inline( substr( line, 2, len - 2 ) ) "</sub>" inline( substr( line, len + 1 ) );
- # __strong__
- } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__") ) {
+ # 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 "))__$") ) {
len = RLENGTH;
return "<strong>" inline( substr( line, 3, len - 4 ) ) "</strong>" inline( substr( line, len + 1 ) );
+ # __strong__
+ } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__[[:space:][:punct:]]") ) {
+ len = RLENGTH;
+ return "<strong>" inline( substr( line, 3, len - 5 ) ) "</strong>" inline( substr( line, len) );
+
# **strong**
} else if ( match(line, "^\\*\\*(([^\\*[:space:]]|" iea ")|([^\\*[:space:]]|" iea ")(" na "|" iea ")*([^\\*[:space:]]|" iea "))\\*\\*") ) {
len = RLENGTH;
return "<strong>" inline( substr( line, 3, len - 4 ) ) "</strong>" inline( substr( line, len + 1 ) );
- # _em_
- } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_") ) {
+ # _em_$
+ } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_$") ) {
len = RLENGTH;
return "<em>" inline( substr( line, 2, len - 2 ) ) "</em>" inline( substr( line, len + 1 ) );
+ # _em_
+ } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_[[:space:][:punct:]]") ) {
+ len = RLENGTH;
+ return "<em>" inline( substr( line, 2, len - 3 ) ) "</em>" inline( substr( line, len ) );
+
# *em*
} else if ( match(line, "^\\*(([^\\*[:space:]]|" isa ")|([^\\*[:space:]]|" isa ")(" na "|" isa ")*([^\\*[:space:]]|" isa "))\\*") ) {
len = RLENGTH;
return "<em>" inline( substr( line, 2, len - 2 ) ) "</em>" 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-Z][^>]*>|<!\[CDATA\[([^\]]|\][^\]]|\]\][^>])*\]\]>|<\/[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;
+ return substr( line, 1, len ) inline(substr(line, len + 1));
+
+ # 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) );
if ( block == "" ) {
return "";
+
+ # HTML #2 #3 #4 $5
+ } else if ( AllowHTML && match( block, /(^|\n) ? ? ?(<!--([^-]|-[^-]|--[^>])*(-->|$)|<\?([^\?]|\?[^>])*(\?>|$)|<![A-Z][^>]*(>|$)|<!\[CDATA\[([^\]]|\][^\]]|\]\][^>])*(\]\]>|$))/) ) {
+ len = RLENGTH; st = RSTART;
+ return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len));
+
+ # HTML #6
+ } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<\/?(address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset|h[123456]|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul)([[:space:]\n>]|\/>)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) {
+ 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));
# Blockquote (leading >)
} else if ( match( block, /^> /) ) {
# First Order Heading
} else if ( match( block, /^[^\n]+\n===+(\n|$)/ ) ) {
len = RLENGTH;
- return "<h1>" inline( gensub( /\n.*$/, "", "g", block ) ) "</h1>\n\n" \
+ 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" \
_block( substr( block, len + 1 ) );
# Second Order Heading
} else if ( match( block, /^[^\n]+\n---+(\n|$)/ ) ) {
len = RLENGTH;
- return "<h2>" inline( gensub( /\n.*$/, "", "g", block ) ) "</h2>\n\n" \
+ 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" \
_block( substr( block, len + 1) );
# Nth Order Heading
- } else if ( match( block, /^#{1,6}[[:space:]]*[^\n]+([[:space:]]*#*)(\n|$)/ ) ) {
+ } else if ( match( block, /^#{1,6}[ \t]*[^\n]+([ \t]*#*)(\n|$)/ ) ) {
len = RLENGTH;
hlvl = length( gensub( /^(#{1,6}).*$/, "\\1", "g", block ) );
- htxt = gensub( /[[:space:]]*#*$/, "", "1", gensub( /^#{1,6}[[:space:]]*([^\n]+)([[:space:]]*#*)\n.*$/, "\\1", "g", block ) )
- return "<h" hlvl ">" inline( htxt ) "</h" hlvl ">\n\n" \
+ htxt = gensub(/^#{1,6}[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[^\n#])+)([ \t]*#*)(\n.*)?$/, "\\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" \
_block( substr( block, len + 1) );
+ # Horizontal rule
+ } else if ( match( block, /(^|\n) ? ? ?((\* *){3,}|(- *){3,}|(_ *){3,})($|\n)/) ) {
+ len = RLENGTH; st = RSTART;
+ return _block(substr(block, 1, st - 1)) "<hr />\n" _block(substr(block, st + len));
+
# Plain paragraph
} else {
match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ );
sub( /<\/p>\n/, "", p );
}
sub( /\n$/, "", 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 );
}
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;
# 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;