X-Git-Url: http://git.plutz.net/?a=blobdiff_plain;f=markdown.awk;h=5915f011ece716dc8ab33825017226bf368e3a19;hb=ca22f379dcbc2047479fd165d56f8c5c938dac43;hp=c4e1a72e3e023102f5a60a9ec8046065315114cc;hpb=4f6c3febe9c001b53be4949cccc7e92a20a16433;p=cgilite

diff --git a/markdown.awk b/markdown.awk
index c4e1a72..5915f01 100755
--- a/markdown.awk
+++ b/markdown.awk
@@ -4,26 +4,23 @@
 # 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] 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:
 # ---------------------------------
@@ -31,43 +28,56 @@
 # - [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)
-#   - [-] Fenced code attributes
-# - [ ] Tables
-#   - [?] Simple table (pandoc)
-#   - [?] Multiline table (pandoc)
-#   - [?] Grid table (pandoc)
-#   - [?] Pipe table (phpmarkdown, pandoc)
+# - [x] Automatic <section>-wrapping (custom)
+# -  ?  Heading identifiers (php md, pandoc)
+#   - [x] Heading attributes (custom)
+# - [x] Automatic heading identifiers (custom)
+# - [x] Fenced code blocks (php md, pandoc)
+#   - [x] Fenced code attributes
+# - [x] Images (as block elements, <figure>-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)
-# - [ ] Task lists (pandoc)
-# - [ ] Definition lists (phpmarkdown, pandoc)
+# - [x] Task lists (pandoc, custom)
+# - [x] Definition lists (php md, pandoc)
 # - [-] Numbered example lists (pandoc)
 # - [-] Metadata blocks (pandoc)
-# - [-] Fenced Divs (pandoc)
+# - [x] Metadata blocks (custom)
+# - [x] 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)
+# - [x] Image attributes (custom, pandoc inspired, not for reference style)
+# - [x] Wiki style links [[PageName]] / [[PageName|Link Text]]
 # - [-] 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 <-
+# - [x] Automatic -> Arrows <- (custom)
 
 function debug(text) { printf "\n---\n%s\n---\n", text > "/dev/stderr"; }
 
@@ -81,8 +91,23 @@ function HTML ( 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, 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)
@@ -92,9 +117,13 @@ function inline( line, LOCAL, len, code, href, guard ) {
   if ( line ~ /^$/ ) {  # Recursion End
     return "";
 
-  #  omit processing of escaped characters
-  } else if ( line ~ /^\\[]\\`\*_\{\}\(\)#\+-\.![]/) {
-    return substr(line, 2, 1) inline( substr(line, 3) );
+  # 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 "<br>\n" inline( substr(line, RLENGTH + 1) );
 
   #  ``code spans``
   } else if ( match( line, /^`+/) ) {
@@ -104,42 +133,97 @@ 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( / (.*) /, "\\1", "1" , code)
+      code = gensub( /^ | $/, "", "g" , code)
       #  escape HTML within code span
       gsub( /&/, "\\&amp;", code ); gsub( /</, "\\&lt;", code ); gsub( />/, "\\&gt;", code );
       return "<code>" code "</code>" 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 "<a href=\"" URL(href) "\">" HTML(text) "</a>" 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 = HTML( substr( line, 2, len - 2) );
+    href = URL( 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 = URL( substr( line, 2, len - 2) );
+    return "<a href=\"mailto:" href "\">" href "</a>" inline( substr( line, len + 1) );
+
   # inline links
-  } else if ( match(line, /^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/) ) {
+  #                                 ,_______________________Image____________________________,
+  } else if ( match(line, /^\[([^]]+|!\[[^]]*\]\([^"\)]+([ \t]+"[^"]+")?\)(\{[a-zA-Z \t-]*\})?)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/) ) {
     len = RLENGTH;
-    text  = gensub(/^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\1", "g", line);
-    href  = gensub(/^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\2", "g", line);
-    title = gensub(/^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\4", "g", line);
+    text  = gensub(/^\[([^]]+|!\[[^]]*\]\([^"\)]+([ \t]+"[^"]+")?\)(\{[a-zA-Z \t-]*\})?)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/, \
+                   "\\1", 1, substr(line, 1, len) );
+    href  = gensub(/^\[([^]]+|!\[[^]]*\]\([^"\)]+([ \t]+"[^"]+")?\)(\{[a-zA-Z \t-]*\})?)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/, \
+                   "\\4", 1, substr(line, 1, len) );
+    title = gensub(/^\[([^]]+|!\[[^]]*\]\([^"\)]+([ \t]+"[^"]+")?\)(\{[a-zA-Z \t-]*\})?)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/, \
+                   "\\6", 1, substr(line, 1, len) );
     if ( title ) {
-      return "<a href=\"" HTML(href) "\" title=\"" HTML(title) "\">" inline( text ) "</a>" inline( substr( line, len + 1) );
+      return "<a href=\"" URL(href) "\" title=\"" HTML(title) "\">" inline( text ) "</a>" inline( substr( line, len + 1) );
     } else {
-      return "<a href=\"" HTML(href) "\">" inline( text ) "</a>" inline( substr( line, len + 1) );
+      return "<a href=\"" URL(href) "\">" inline( text ) "</a>" inline( substr( line, len + 1) );
     }
 
   # 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=\"" rl_href[id] "\" title=\"" rl_title[id] "\">" inline(text) "</a>" inline( substr( line, len + 1) );
+      return "<a href=\"" URL(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=\"" URL(rl_href[id]) "\">" inline(text) "</a>" inline( substr( line, len + 1) );
+    } else {
+      return "" HTML(substr(line, 1, len)) inline( substr(line, len + 1) );
+    }
+
+  # inline images
+  } else if ( match(line, /^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/) ) {
+    len = RLENGTH;
+    text   = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\1", "g", substr(line, 1, len) );
+    href   = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\2", "g", substr(line, 1, len) );
+    title  = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\4", "g", substr(line, 1, len) );
+    attrib = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\6", "g", substr(line, 1, len) );
+    if ( title && attrib ) {
+      return "<img src=\"" URL(href, 1) "\" alt=\"" HTML(text) "\" title=\"" HTML(title) "\" class=\"" HTML(attrib) "\">" \
+             inline( substr( line, len + 1) );
+    } else if ( title ) {
+      return "<img src=\"" URL(href, 1) "\" alt=\"" HTML(text) "\" title=\"" HTML(title) "\">" \
+             inline( substr( line, len + 1) );
+    } else if ( attrib ) {
+      return "<img src=\"" URL(href, 1) "\" alt=\"" HTML(text) "\" class=\"" HTML(attrib) "\">" \
+             inline( substr( line, len + 1) );
     } else {
-      return "" substr(line, 1, len) inline( substr(line, len + 1) );
+      return "<img src=\"" URL(href, 1) "\" alt=\"" HTML(text) "\">" \
+             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 "<img src=\"" URL(rl_href[id], 1) "\" alt=\"" HTML(text) "\" title=\"" HTML(rl_title[id]) "\">" \
+             inline( substr( line, len + 1) );
+    } else if ( rl_href[id] ) {
+      return "<img src=\"" URL(rl_href[id], 1) "\" alt=\"" HTML(text) "\">" \
+             inline( substr( line, len + 1) );
+    } else {
+      return "" HTML(substr(line, 1, len)) inline( substr(line, len + 1) );
     }
 
   #  ~~strikeout~~ (pandoc)
@@ -157,57 +241,288 @@ function inline( line, LOCAL, len, code, href, guard ) {
     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));
+
+  # Arrows
+  } else if ( line ~ /^-->( |$)/) {  # ignore multidash-arrow
+    return "--&gt;" inline( substr(line, 4) );
+  } else if ( line ~ /^<-( |$)/) {
+    return "&larr;" inline( substr(line, 3) );
+  } else if ( line ~ /^->( |$)/) {
+    return "&rarr;" 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 _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent ) {
-  gsub( /^\n+|\n+$/, "", block );
+function headline( hlvl, htxt, attrib, LOCAL, sec, n, HL) {
+  split( gensub( /^(.* )?([0-9]+( [0-9]+){5})$/, "\\2" ,"1", hstack),  HL);
+
+  for ( n = hlvl; n <= 6; n++ ) { sec = sec (HL[n]?"</section>":""); }
+  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})$/, "\\1" ,"1", hstack) \
+           HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6];
+
+  return sec "<section class=\"" (attrib ? "h" hlvl " " attrib : "h" hlvl)  "\" id=\"" hid "\">" \
+         "<h" hlvl (attrib ? " class=\"" attrib "\"" : "") ">" inline( htxt ) \
+         "<a class=\"anchor\" href=\"#" hid "\"></a>" \
+         "</h" hlvl ">\n";
+}
+
+# Nested Block, resets heading counters
+function _nblock( block, LOCAL, hlsav, sec, n ) {
+  hlsav = hstack;
+  hstack = hstack " 0 0 0 0 0 0";
+
+  # Block Level
+  blvl++; BL[blvl]++;
+  for ( n = blvl + 1; n in BL; n++) { delete BL[n]; }
+
+  block = _block( block );
+  split( gensub( /^(.* )?([0-9]+( [0-9]+){5})$/, "\\2" ,"1", hstack),  HL);
+  sec = ""; for ( n = 1; n <= 6; n++ ) { sec = sec (HL[n]?"</section>":""); }
+  hstack = hlsav; 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 $5
+  } else if ( AllowHTML && match( block, /(^|\n) ? ? ?(<!--([^-]|-[^-]|--[^>])*(-->|$)|<\?([^\?]|\?[^>])*(\?>|$)|<![A-Z][^>]*(>|$)|<!\[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));
+
+  # 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;
-    return "<blockquote>\n" _block( gensub( /(^|\n)> /, "\n", "g", substr(block, 1, st - 1) ) ) "</blockquote>\n\n" \
+    return "<blockquote>" gensub( /^\n|\n$/, "", "g",  _nblock( 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\\&#x7C;", "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( /(^\||\|$)/, "", "g", \
+             gensub( /(^|[^\\])\\\|/, "\\1\\&#x7C;", "g", \
+             substr(block, 1, match(block, /(\n|$)/)) \
+      )), tarray, /\|/);
+      block = substr(block, match(block, /(\n|$)/) + 1 );
+
+      ttext = ttext "<tr>"
+      for (cnt = 1; cnt < cols; cnt++)
+        ttext = ttext "<td align=\"" talign[cnt] "\">" inline(tarray[cnt]) "</td>"
+      ttext = ttext "</tr>\n"
+    }
+    return "<table>" ttext "</tbody></table>\n" _block(block);
+
+  # Grid Tables (pandoc)
+  # (with, and without header)
+  } else if ( match( block, "^\\+(-+\\+)+\n" \
+                            "(\\|([^\n]+\\|)+\n)+" \
+                            "(\\+(:?=+:?\\+)+)\n" \
+                           "((\\|([^\n]+\\|)+\n)+" \
+                             "\\+(-+\\+)+(\n|$))+" \
+                   ) || \
+              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\\&#x7C;", "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 = "<thead>\n<tr>"
+      for (cnt = 1; cnt <= cols; cnt++)
+        ttext = ttext "<th align=\"" talign[cnt] "\">" _nblock(tarray[cnt]) "</th>"
+      ttext = ttext "</tr>\n</thead>"
+    }
+
+    # table body
+    block = substr(block, match(block, /(\n|$)/) + 1 );
+    ttext = ttext "<tbody>\n"
+
+    while ( match(block, /^((\|([^\n]+\|)+\n)+\+(-+\+)+(\n|$))+/ ) ){
+      split("", tarray);
+      while ( match(block, /^\|([^\n]+\|)+\n/) ) {
+        split( gensub( /(^\||\|$)/, "", "g", \
+               gensub( /(^|[^\\])\\\|/, "\\1\\&#x7C;", "g", \
+               substr(block, 1, match(block, /(\n|$)/)) \
+        )), 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] "\">" _nblock(tarray[cnt]) "</td>"
+      ttext = ttext "</tr>\n"
+    }
+    return "<table>" ttext "</tbody></table>\n" _nblock(block);
+
   # 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 "<div class=\"line-block\">" gensub(/\n/, "<br />\n", "g", inline( code )) "</div>\n" \
+    text = substr(block, 1, len);
+    gsub(/\n[[:space:]]+/, " ", text);
+    gsub(/\n\| /, "\n", text);
+    gsub(/^\| |\n$/, "", text);
+    return "<div class=\"line-block\">" gensub(/\n/, "<br>\n", "g", inline( text )) "</div>\n" \
            _block( substr( block, len + 1) );
 
   # Indented Code Block
-  } else if ( match(block, /^(    |\t)[^\n]+(\n|$)((    |\t)[^\n]+(\n|$)|[ \t]*(\n|$))*/) ) {
+  } else if ( match(block, /^(    |\t)( *\t*[^ \t\n]+ *\t*)+(\n|$)((    |\t)[^\n]+(\n|$)|[ \t]*(\n|$))*/) ) {
     len = RLENGTH; st = RSTART;
     code = substr(block, 1, len);
     gsub(/(^|\n)(    |\t)/, "\n", code);
@@ -215,13 +530,34 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent ) {
     return "<pre><code>" HTML( code ) "</code></pre>\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 "<div class=\"" attrib "\">" _nblock( substr(code, 1, st - 1) ) "</div>\n" \
+             _block( substr( code, st + len ) );
+    } 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) );
+    }
+
   # 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 "<pre><code>" HTML( substr(code, 1, st - 1) ) "</code></pre>\n" \
+      return "<pre><code class=\"" attrib "\">" HTML( substr(code, 1, st - 1) ) "</code></pre>\n" \
              _block( substr( code, st + len ) );
     } else {
       match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ );
@@ -230,91 +566,245 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent ) {
              _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]+.*$/, "", 1, list) );
+  # First Order Heading H1 + Attrib
+  } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n===+(\n|$)/ ) ) {
+    len = RLENGTH;
+    text   = gensub(/^([^\n]+)([ \t]*\{([^\}\n]+)\})\n===+(\n.*)?$/, "\\1", 1, block)
+    attrib = gensub(/^([^\n]+)([ \t]*\{([^\}\n]+)\})\n===+(\n.*)?$/, "\\3", 1, block)
+    gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib);
 
-  gsub("(^|\n) {0," indent "}", "\n", list);
-  return "\n<ul>\n" _list( substr(list, 2) ) "</ul>\n" _block( block );
+    return headline(1, text, attrib) \
+           _block( substr( block, len + 1 ) );
 
-  # 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]+.*$/, "", 1, list) );
-
-  gsub("(^|\n) {0," indent "}", "\n", list);
-  return "\n<ol>\n" _list( substr(list, 2) ) "</ol>\n" _block( block );
-
-  # First Order Heading
-  } else if ( match( block, /^[^\n]+\n===+(\n|$)/ ) ) {
+  # First Order Heading H1
+  } else if ( match( block, /^([^\n]+)\n===+(\n|$)/ ) ) {
     len = RLENGTH;
-    return "<h1>" inline( gensub( /\n.*$/, "", "g", block ) ) "</h1>\n\n" \
+    text   = gensub(/^([^\n]+)\n===+(\n.*)?$/, "\\1", 1, block)
+
+    return headline(1, text, 0) \
            _block( substr( block, len + 1 ) );
 
-  # Second Order Heading
-  } else if ( match( block, /^[^\n]+\n---+(\n|$)/ ) ) {
+  # Second Order Heading H2 + Attrib
+  } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n---+(\n|$)/ ) ) {
     len = RLENGTH;
-    return "<h2>" inline( gensub( /\n.*$/, "", "g", block ) ) "</h2>\n\n" \
+    text   = gensub(/^([^\n]+)([ \t]*\{([^\}\n]+)\})\n---+(\n.*)?$/, "\\1", 1, block)
+    attrib = gensub(/^([^\n]+)([ \t]*\{([^\}\n]+)\})\n---+(\n.*)?$/, "\\3", 1, block)
+    gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib);
+
+    return headline(2, text, attrib) \
            _block( substr( block, len + 1) );
 
-  # Nth Order Heading
-  } else if ( match( block, /^#{1,6}[[:space:]]*[^\n]+([[:space:]]*#*)(\n|$)/ ) ) {
+  # Second Order Heading H2
+  } else if ( match( block, /^([^\n]+)\n---+(\n|$)/ ) ) {
     len = RLENGTH;
-    hlvl = length( gensub( /^(#{1,6}).*$/, "\\1", "g", block ) );
-    htxt = gensub( /[[:space:]]*#*$/, "", "1", gensub( /^#{1,6}[[:space:]]*([^\n]+)([[:space:]]*#*)\n.*$/, "\\1", "g", block ) )
-    return "<h" hlvl ">" inline( htxt ) "</h" hlvl ">\n\n" \
+    text   = gensub(/^([^\n]+)\n---+(\n.*)?$/, "\\1", 1, block)
+
+    return headline(2, text, 0) \
            _block( substr( block, len + 1) );
 
-  # Plain paragraph
-  } else {
-    match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ );
+  # 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|$)/ ) ) {
+    len = RLENGTH;
+    n      = gensub(/^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n.*)?$/, "\\1", 1, block);
+    text   = gensub(/^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n.*)?$/, "\\2", 1, block);
+    attrib = gensub(/^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n.*)?$/, "\\5", 1, block);
+    gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib);
+
+    return headline( length(n), text, attrib ) \
+           _block( substr( block, len + 1) );
+
+  # Nth Order Heading H1 H2 H3 H4 H5 H6
+  } else if ( match( block, /^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n|$)/ ) ) {
+    len = RLENGTH;
+    n      = gensub(/^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n.*)?$/, "\\1", 1, block);
+    text   = gensub(/^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n.*)?$/, "\\2", 1, block);
+
+    return headline( length(n), text, 0 ) \
+           _block( substr( block, len + 1) );
+
+  # block images (wrapped in <figure>)
+  } else if ( match(block, /^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n|$)/) ) {
+    len = RLENGTH;
+    text   = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n.*)?$/, "\\1", "g", block);
+    href   = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n.*)?$/, "\\2", "g", block);
+    title  = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n.*)?$/, "\\4", "g", block);
+    attrib = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n.*)?$/, "\\6", "g", block);
+    if ( title && attrib ) {
+      return "<figure data-src=\"" URL(href, 1) "\" class=\"" HTML(attrib) "\">" \
+               "<img src=\"" URL(href, 1) "\" alt=\"" HTML(text) "\" class=\"" HTML(attrib) "\">" \
+               "<figcaption>" inline(title) "</figcaption>" \
+             "</figure>\n\n" \
+             _block( substr( block, len + 1) );
+    } else if ( title ) {
+      return "<figure data-src=\"" URL(href, 1) "\">" \
+               "<img src=\"" URL(href, 1) "\" alt=\"" HTML(text) "\">" \
+               "<figcaption>" inline(title) "</figcaption>" \
+             "</figure>\n\n" \
+             _block( substr( block, len + 1) );
+    } else if ( attrib ) {
+      return "<figure data-src=\"" URL(href, 1) "\" class=\"" HTML(attrib) "\">" \
+               "<img src=\"" URL(href, 1) "\" alt=\"" HTML(text) "\" class=\"" HTML(attrib) "\">" \
+             "</figure>\n\n" \
+             _block( substr( block, len + 1) );
+    } else {
+      return "<figure data-src=\"" URL(href, 1) "\">" \
+               "<img src=\"" URL(href, 1) "\" alt=\"" HTML(text) "\">" \
+             "</figure>\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.*)?$/, "\\2", 1, block);
+    if ( ! id ) id = text;
+    if ( rl_href[id] && rl_title[id] ) {
+      return "<figure data-src=\"" URL(rl_href[id], 1) "\">" \
+               "<img src=\"" URL(rl_href[id], 1) "\" alt=\"" HTML(text) "\">" \
+               "<figcaption>" inline(rl_title[id]) "</figcaption>" \
+             "</figure>\n\n" \
+             _block( substr( block, len + 1) );
+    } else if ( rl_href[id] ) {
+      return "<figure data-src=\"" URL(rl_href[id], 1) "\">" \
+               "<img src=\"" URL(rl_href[id], 1) "\" alt=\"" HTML(text) "\">" \
+             "</figure>\n\n" \
+             _block( substr( block, len + 1) );
+    } else {
+      return "<p>" HTML(substr(block, 1, len)) "</p>\n" _block( substr(block, len + 1) );
+    }
+
+  # Macros (standalone <<macro>> calls handled as block, so they are not wrapped in paragraph)
+  } else if ( AllowMacros && match( block, /^<<(([^>]|>[^>])+)>>(\n|$)/) ) {
+    len = RLENGTH;
+    text = gensub(/^<<(([^>]|>[^>])+)>>(\n.*)?$/, "\\1", 1, block);
+    return macro(text) _block(substr(block, len + 1) );
+
+  # Horizontal rule
+  } else if ( match( block, /(^|\n) ? ? ?((\* *){3,}|(- *){3,}|(_ *){3,})($|\n)/) ) {
+    len = RLENGTH; st = RSTART;
+    return _block(substr(block, 1, st - 1)) "<hr>\n" _block(substr(block, st + len));
+
+  # 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|$))*)+" \
+  )) {
+    list = substr( block, 1, RLENGTH); block = substr( block, RLENGTH + 1);
+    return "\n<dl>\n" _dlist( list ) "</dl>\n" _block( block );
+
+  # Unordered list
+  } else if ( match( block, "(^|\n) ? ? ?[-+*][ \t][^\n]+(\n|$)" \
+                 "(([ \t]*\n)* ? ? ?[-+*][ \t][^\n]+(\n|$)" \
+                 "|([ \t]*\n)*( ? ? ?\t|  +)[^\n]+(\n|$)" \
+                 "|[^\n \t][^\n]+(\n|$))*" ) ) {
+    st = RSTART; len = RLENGTH; list = substr( block, RSTART, RLENGTH);
+    sub("^\n", "", list); match(list, "^ ? ? ?[-+*]"); indent = RLENGTH;
+    gsub( "(^|\n) {0," indent - 1 "}", "\n", list); sub("^\n", "", list);
+
+    text = substr(block, 1, st - 1); block = substr(block, st + len);
+    if (match( list, "\n([0-9]+\\.|#\\.)[ \t]" )) {
+      block = substr(list, RSTART + 1) block;
+      list = substr(list, 1, RSTART);
+    }
+
+    return _block( text ) "<ul>\n" _list( list, "[-+*]" ) "</ul>\n" _block( block );
+
+  # Ordered list
+  } else if ( match( block, "(^|\n) ? ? ?([0-9]+\\.|#\\.)[ \t][^\n]+(\n|$)" \
+                 "(([ \t]*\n)* ? ? ?([0-9]+\\.|#\\.)[ \t][^\n]+(\n|$)" \
+                 "|([ \t]*\n)*( ? ? ?\t|  +)[^\n]+(\n|$)" \
+                 "|[^\n \t][^\n]+(\n|$))*" ) ) {
+    st = RSTART; len = RLENGTH; list = substr( block, RSTART, RLENGTH);
+    sub("^\n", "", list); match(list, "^ ? ? ?[0-9#]"); indent = RLENGTH;
+    gsub( "(^|\n) {0," indent - 1 "}", "\n", list); sub("^\n", "", list);
+
+    text = substr(block, 1, st - 1); block = substr(block, st + len);
+    if (match( list, "\n[-+*][ \t]" )) {
+      block = substr(list, RSTART + 1) block;
+      list = substr(list, 1, RSTART);
+    }
+
+    return _block( text ) "<ol>\n" _list( list, "([0-9]+\\.|#\\.)" ) "</ol>\n" _block( block );
+
+  # Split paragraphs
+  } else if ( match( block, /(^|\n)[[:space:]]*(\n|$)/) ) {
     len = RLENGTH; st = RSTART;
-    return "<p>" inline( substr(block, 1, st - 1) ) "</p>\n" \
+    return _block( substr(block, 1, st - 1) ) "\n" \
            _block( substr(block, st + len) );
+
+  # Plain paragraph
+  } else {
+    return "<p>" inline(block) "</p>\n";
   }
 }
 
-function _list( block, last, LOCAL, p) {
-  if ( ! length(block) ) return "";
-  gsub(/^([-+*]|[0-9]+\.|#\.)(  ? ? ?|\t)/, "", block)
+function _list (block, mark, LOCAL, len, st, text, indent, task) {
+  if ( match(block, "^([ \t]*\n)*$")) return;
+  match(block, "^" mark "[ \t]"); indent = RLENGTH;
+  sub("^" mark "[ \t]", "", block);
 
-  # 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 );
+  match( block, "\n" mark "[ \t][^\n]+(\n|$)" \
+      "(([ \t]*\n)* ? ? ?" mark "[ \t][^\n]+(\n|$)" \
+      "|([ \t]*\n)*( ? ? ?\t|  +)[^\n]+(\n|$)" \
+      "|[^\n \t][^\n]+(\n|$))*");
+  (RLENGTH == -1) ? st = length(block) + 1 : st = RSTART;
+  text = substr(block, 1, st); block = substr(block, st + 1);
 
-  # 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 = _block(p);
-  } else {
-    last = p; p = _block(p);
-    sub( /^<p>/, "", p );
-    sub( /<\/p>\n/, "", p );
+  gsub("\n {0," indent "}", "\n", text);
+
+  task = match( text, /^\[ \]/   ) ? "<li class=\"task pending\"><input type=checkbox disabled>"      : \
+         match( text, /^\[-\]/   ) ? "<li class=\"task negative\"><input type=checkbox disabled>"     : \
+         match( text, /^\[\/\]/  ) ? "<li class=\"task partial\"><input type=checkbox disabled>"      : \
+         match( text, /^\[\?\]/  ) ? "<li class=\"task unsure\"><input type=checkbox disabled>"       : \
+         match( text, /^\[[xX]\]/) ? "<li class=\"task done\"><input type=checkbox disabled checked>" : "<li>";
+  sub(/^\[[-? /xX]\]/, "", text);
+
+  text = _nblock( text );
+  if (match( text, "^<p>(</p[^>]|</[^p]|<[^/]|[^<])*</p>\n$" ))
+     gsub( "(^<p>|</p>\n$)", "", text);
+
+  return task text "</li>\n" _list(block, mark);
+}
+
+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*$)", "", text );
+    return "<dt>" inline( text ) "</dt>\n" _dlist( substr(block, len + 1) );
+  } else if (match( block, "^([ \t]*\n)* ? ? ?:[ \t][^\n]+(\n|$)" \
+                         "([^:\n \t][^\n]+(\n|$)" \
+                         "|( ? ? ?\t|  +)[^\n]+(\n|$)" \
+                         "|([ \t]*\n)+( ? ? ?\t|  +)[^\n]+(\n|$))*" \
+  )) {
+    len = RLENGTH; text = substr(block, 1, len);
+    sub( "^([ \t]*\n)*", "", text);
+    match(text, "^ ? ? ?:(\t| +)"); indent = RLENGTH;
+    sub( "^ ? ? ?:(\t| +)", "", text);
+    gsub( "(^|\n) {0," indent "}", "\n", text );
+
+    text = _nblock(text);
+    if (match( text, "^<p>(</p[^>]|</[^p]|<[^/]|[^<])*</p>\n$" ))
+       gsub( "(^<p>|</p>\n$)", "", text);
+
+    return "<dd>" text "</dd>\n" _dlist( substr(block, len + 1) );
   }
-  sub( /\n$/, "", p );
-  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;
+  # hls = "0 0 0 0 0 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;
@@ -333,5 +823,5 @@ BEGIN {
   # for (n in rl_href) { debug(n " | " rl_href[n] " | " rl_title[n] ); }
 
   # Run Block Processing -> The Actual Markdown!
-  printf "%s", _block( file );
+  printf "%s", _nblock( file );
 }