# 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:
# ---------------------------------
# - [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)
+# - ? Heading identifiers (php md, pandoc)
+# - [x] Automatic heading identifiers (custom)
+# - [x] Fenced code blocks (php md, pandoc)
+# - [x] Fenced code attributes
+# - [/] Tables
+# - ? Simple table (pandoc)
+# - ? Multiline table (pandoc)
+# - [x] Grid table (pandoc)
+# - [x] Pipe table (php md pandoc)
# - [x] Line blocks (pandoc)
-# - [ ] Task lists (pandoc)
-# - [ ] Definition lists (phpmarkdown, pandoc)
+# - [x] Task lists (pandoc, custom)
+# - [ ] 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, inline only)
+# - [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 <-
function debug(text) { printf "\n---\n%s\n---\n", text > "/dev/stderr"; }
return text;
}
+function URL ( text ) {
+ gsub( /&/, "%26", text );
+ gsub( /"/, "%22", text );
+ gsub( /'/, "%27", text );
+ gsub( /\?/, "%3F", text );
+ 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)
} 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
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 "" 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]+"([^"]+)")?\)(\{([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) "\" alt=\"" HTML(text) "\" title=\"" HTML(title) "\" class=\"" HTML(attrib) "\">" \
+ inline( substr( line, len + 1) );
+ } else if ( title ) {
+ return "<img src=\"" URL(href) "\" alt=\"" HTML(text) "\" title=\"" HTML(title) "\">" \
+ inline( substr( line, len + 1) );
+ } else if ( attrib ) {
+ return "<img src=\"" URL(href) "\" alt=\"" HTML(text) "\" class=\"" HTML(attrib) "\">" \
+ inline( substr( line, len + 1) );
+ } else {
+ return "<img src=\"" URL(href) "\" 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]) "\" 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]) "\" 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) );
}
}
-function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent ) {
+function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib ) {
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, /^> /) ) {
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|$))*/) ) {
len = RLENGTH; st = RSTART;
gsub(/\n[[:space:]]+/, " ", code);
gsub(/\n\| /, "\n", code);
gsub(/^\| |\n$/, "", code);
- return "<div class=\"line-block\">" gensub(/\n/, "<br />\n", "g", inline( code )) "</div>\n" \
+ return "<div class=\"line-block\">" gensub(/\n/, "<br>\n", "g", inline( code )) "</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);
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 = gensub(/^[^\n]+\n/, "", 1, block);
+ 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 "\">" _block( 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|$)/ ) || match( block, /$/ );
# 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] ":" URL(gensub( /\n.*$/, "", "g", block )) "\">" \
+ inline( gensub( /\n.*$/, "", "g", block ) ) \
+ "<a class=\"anchor\" href=\"#" HL[1] ":" \
+ URL(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;
- return "<h2>" inline( gensub( /\n.*$/, "", "g", block ) ) "</h2>\n\n" \
+ HL[2]++; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
+ return "<h2 id=\"" HL[1] "." HL[2] ":" URL(gensub( /\n.*$/, "", "g", block )) "\">" \
+ inline( gensub( /\n.*$/, "", "g", block ) ) \
+ "<a class=\"anchor\" href=\"#" HL[1] "." HL[2] ":" \
+ URL(gensub( /\n.*$/, "", "g", block )) "\"></a></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 ":" URL(htxt) "\">" inline( htxt ) \
+ "<a class=\"anchor\" href=\"#" hid "\"></a></h" hlvl ">\n\n" \
_block( substr( block, len + 1) );
- # Plain paragraph
- } else {
- match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ );
+ # Split paragraphs
+ } else if ( match( block, /(^|\n)[[:space:]]*(\n|$)/) ) {
len = RLENGTH; st = RSTART;
- return "<p>" inline( substr(block, 1, st - 1) ) "</p>\n" \
+ return _block( substr(block, 1, st - 1) ) "\n" \
_block( substr(block, st + len) );
+
+ # Horizontal rule
+ } else if ( match( block, /(^|\n) ? ? ?((\* *){3,}|(- *){3,}|(_ *){3,})($|\n)/) ) {
+ len = RLENGTH; st = RSTART;
+ return _block(substr(block, 1, st - 1)) "<hr>\n" _block(substr(block, st + len));
+
+ # Plain paragraph
+ } else {
+ return "<p>" inline(block) "</p>\n";
}
}
sub( /<\/p>\n/, "", p );
}
sub( /\n$/, "", p );
- 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 {
# 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;