#
# Extensions - Block elements:
# ----------------------------
+# - [x] Automatic <section>-wrapping (custom)
# - ? Heading identifiers (php md, pandoc)
# - [x] Automatic heading identifiers (custom)
# - [x] Fenced code blocks (php md, pandoc)
# - [x] Fenced code attributes
-# - [ ] Tables
+# - [x] Images (as block elements, <figure>-wrapped) (custom)
+# - [x] reference style block images
+# - [/] Tables
# - ? Simple table (pandoc)
# - ? Multiline table (pandoc)
-# - ? Grid table (pandoc)
-# - ? Pipe table (php md pandoc)
+# - [x] Grid table (pandoc)
+# - [x] Headerless
+# - [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] ^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 (php md)
# - ? Abbreviations (php md)
# - ? ... 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"; }
return text;
}
+function URL ( text ) {
+ gsub( /&/, "%26", text );
+ gsub( /"/, "%22", text );
+ gsub( /'/, "%27", text );
+ gsub( /`/, "%60", 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 = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\_]|_[[:alnum:]])*" # not underline (except when escaped)
na = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\\\*])*" # not asterisk (except when escaped)
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) );
+ return "<br>\n" inline( substr(line, RLENGTH + 1) );
# ``code spans``
} else if ( match( line, /^`+/) ) {
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( /&/, "\\&", code ); gsub( /</, "\\<", code ); gsub( />/, "\\>", 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 = HTML( substr( line, 2, len - 2) );
+ 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, /^\[([^]]+)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/) ) {
+ # ,_______________________Image____________________________,
+ } else if ( match(line, /^\[([^]]+|!\[[^]]*\]\([^"\)]+([ \t]+"[^"]+")?\)(\{[a-zA-Z \t-]*\})?)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/) ) {
len = RLENGTH;
- 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) );
+ 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
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) );
+ 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=\"" HTML(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]+"([^"]+)")?\)/) ) {
+ } else if ( match(line, /^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/) ) {
len = RLENGTH;
- 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) );
+ 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=\"" HTML(href) "\" alt=\"" HTML(text) "\" />" inline( substr( line, len + 1) );
+ return "<img src=\"" URL(href) "\" alt=\"" HTML(text) "\">" \
+ inline( substr( line, len + 1) );
}
# reference style images
- } else if ( match(line, /^!\[([^]]+)\] ?\[([^]]*)\]/ ) ) {
+ } 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) );
+ 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) );
+ 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=\"" HTML(rl_href[id]) "\" alt=\"" HTML(text) "\" />" inline( substr( line, len + 1) );
+ 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) );
}
len = RLENGTH;
return substr( line, 1, len ) inline(substr(line, len + 1));
+ # Arrows
+ } else if ( line ~ /^-->( |$)/) { # ignore multidash-arrow
+ return "-->" inline( substr(line, 4) );
+ } else if ( line ~ /^<-( |$)/) {
+ return "←" inline( substr(line, 3) );
+ } else if ( line ~ /^->( |$)/) {
+ return "→" inline( substr(line, 3) );
+
# Escape lone HTML character
} else if ( match( line, /^[&<>"']/) ) {
return HTML(substr(line, 1, 1)) inline(substr(line, 2));
}
}
-function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib ) {
+# Nested Block, resets heading counters
+function _nblock( block, LOCAL, hlsav, sec ) {
+ # Keeping arrays in a local scope is awkward, so we serialize the HL array
+ # into the scalar hlsav
+ hlsav = HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6];
+ HL[1] = 0; HL[2] = 0; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
+
+ # Block Level
+ blvl++;
+
+ block = _block( block );
+ sec = ""; for ( n = 1; n <= 6; n++ ) { sec = sec (HL[n]?"</section>":""); }
+ split(hlsav, HL); blvl--;
+ return block sec;
+}
+
+function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, attrib ) {
gsub( /^\n+|\n+$/, "", block );
if ( block == "" ) {
} 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>\n" _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\\|", "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|$)/) + 1 );
+
+ ttext = ttext "<tr>"
+ for (cnt = 1; cnt < cols; cnt++)
+ ttext = ttext "<td align=\"" talign[cnt] "\">" inline(tarray[cnt]) "</td>"
+ ttext = ttext "</tr>\n"
+ }
+ return "<table>" ttext "</tbody></table>\n" _block(block);
+
+ # Grid Tables (pandoc)
+ # (with, and without header)
+ } else if ( match( block, "^\\+(-+\\+)+\n" \
+ "(\\|([^\n]+\\|)+\n)+" \
+ "(\\+(:?=+:?\\+)+)\n" \
+ "((\\|([^\n]+\\|)+\n)+" \
+ "\\+(-+\\+)+(\n|$))+" \
+ ) || \
+ 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\\|", "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( /(^\||\|$)/, "", "g", \
+ gensub( /(^|[^\\])\\\|/, "\\1\\|", "g", \
+ substr(block, 1, match(block, /(\n|$)/)) \
+ )), 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|$))*/) ) {
len = RLENGTH; st = RSTART;
gsub(/\n[[:space:]]+/, " ", code);
gsub(/\n\| /, "\n", code);
gsub(/^\| |\n$/, "", 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);
gsub(/(^ | $)/, "", attrib);
if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) {
len = RLENGTH; st = RSTART;
- return "<div class=\"" attrib "\">" _block( substr(code, 1, st - 1) ) "</div>\n" \
+ return "<div class=\"" attrib "\">" _nblock( substr(code, 1, st - 1) ) "</div>\n" \
_block( substr( code, st + len ) );
} else {
match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ );
} 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(/(^ | $)/, "", attrib);
if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) {
gsub("(^|\n) {0," indent "}", "\n", list);
return "\n<ol>\n" _list( substr(list, 2) ) "</ol>\n" _block( block );
- # First Order Heading
+ # First Order Heading H1
} else if ( match( block, /^[^\n]+\n===+(\n|$)/ ) ) {
- len = RLENGTH;
+ len = RLENGTH; sec = "";
+
+ for ( n = 1; n <= 6; n++ ) { sec = sec (HL[n]?"</section>":""); }
HL[1]++; HL[2] = 0; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
- return "<h1 id=\"" HL[1] " - " HTML(gensub( /\n.*$/, "", "g", block )) "\">" inline( gensub( /\n.*$/, "", "g", block ) ) "</h1>\n\n" \
+ hid = HL[1] ":" URL(gensub( /\n.*$/, "", "g", block ));
+
+ return sec "<section class=\"h1\"" ((blvl > 1)?"":" id=\"" hid "\"") ">" \
+ "<h1>" inline( gensub( /\n.*$/, "", "g", block ) ) \
+ ((blvl > 1)?"":"<a class=\"anchor\" href=\"#" hid "\"></a>") \
+ "</h1>\n\n" \
_block( substr( block, len + 1 ) );
- # Second Order Heading
+ # Second Order Heading H2
} else if ( match( block, /^[^\n]+\n---+(\n|$)/ ) ) {
- len = RLENGTH;
+ len = RLENGTH; sec = "";
+
+ for ( n = 2; n <= 6; n++ ) { sec = sec (HL[n]?"</section>":""); }
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" \
+ hid= HL[1] "." HL[2] ":" URL(gensub( /\n.*$/, "", "g", block ));
+
+ return sec "<section class=\"h2\"" ((blvl > 1)?"":" id=\"" hid "\"") ">" \
+ "<h2>" inline( gensub( /\n.*$/, "", "g", block ) ) \
+ ((blvl > 1)?"":"<a class=\"anchor\" href=\"#" hid "\"></a>") \
+ "</h2>\n\n" \
_block( substr( block, len + 1) );
- # Nth Order Heading
+ # Nth Order Heading H1 H2 H3 H4 H5 H6
} else if ( match( block, /^#{1,6}[ \t]*[^\n]+([ \t]*#*)(\n|$)/ ) ) {
- len = RLENGTH;
+ len = RLENGTH; sec = "";
+
hlvl = length( gensub( /^(#{1,6}).*$/, "\\1", "g", block ) );
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;}
+
+ for ( n = hlvl; n <= 6; n++ ) { sec = sec (HL[n]?"</section>":""); }
+ HL[hlvl]++; for ( n = hlvl + 1; n <= 6; 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" \
+ hid = hid ":" URL(htxt);
+
+ return sec "<section class=\"h" hlvl "\"" ((blvl > 1)?"":" id=\"" hid "\"") ">" \
+ "<h" hlvl ">" inline( htxt ) \
+ ((blvl > 1)?"":"<a class=\"anchor\" href=\"#" hid "\"></a>") \
+ "</h" hlvl ">\n\n" \
_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) "\" class=\"" HTML(attrib) "\">" \
+ "<img src=\"" URL(href) "\" 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) "\">" \
+ "<img src=\"" URL(href) "\" alt=\"" HTML(text) "\">" \
+ "<figcaption>" inline(title) "</figcaption>" \
+ "</figure>\n\n" \
+ _block( substr( block, len + 1) );
+ } else if ( attrib ) {
+ return "<figure data-src=\"" URL(href) "\" class=\"" HTML(attrib) "\">" \
+ "<img src=\"" URL(href) "\" alt=\"" HTML(text) "\" class=\"" HTML(attrib) "\">" \
+ "</figure>\n\n" \
+ _block( substr( block, len + 1) );
+ } else {
+ return "<figure data-src=\"" URL(href) "\">" \
+ "<img src=\"" URL(href) "\" 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.*)?$/, "\\2", 1, block);
+ if ( ! id ) id = text;
+ if ( rl_href[id] && rl_title[id] ) {
+ return "<figure data-src=\"" URL(rl_href[id]) "\">" \
+ "<img src=\"" URL(rl_href[id]) "\" alt=\"" HTML(text) "\">" \
+ "<figcaption>" inline(rl_title[id]) "</figcaption>" \
+ "</figure>\n\n" \
+ _block( substr( block, len + 1) );
+ } else if ( rl_href[id] ) {
+ return "<figure data-src=\"" URL(rl_href[id]) "\">" \
+ "<img src=\"" URL(rl_href[id]) "\" alt=\"" HTML(text) "\">" \
+ "</figure>\n\n" \
+ _block( substr( block, len + 1) );
+ } else {
+ return "<p>" HTML(substr(block, 1, len)) "</p>\n" _block( substr(block, len + 1) );
+ }
+
+ # Macros (standalone <<macro>> calls handled as block, so they are not wrapped in paragraph)
+ } else if ( AllowMacros && match( block, /^<<(([^>]|>[^>])+)>>(\n|$)/) ) {
+ len = RLENGTH;
+ text = gensub(/^<<(([^>]|>[^>])+)>>(\n.*)?$/, "\\1", 1, block);
+ return macro(text) _block(substr(block, len + 1) );
+
# Split paragraphs
} else if ( match( block, /(^|\n)[[:space:]]*(\n|$)/) ) {
len = RLENGTH; st = RSTART;
# Horizontal rule
} else if ( match( block, /(^|\n) ? ? ?((\* *){3,}|(- *){3,}|(_ *){3,})($|\n)/) ) {
len = RLENGTH; st = RSTART;
- return _block(substr(block, 1, st - 1)) "<hr />\n" _block(substr(block, st + len));
+ return _block(substr(block, 1, st - 1)) "<hr>\n" _block(substr(block, st + len));
# Plain paragraph
} else {
# if this should be a paragraph item
# either previous item (last) or current item (p) contains blank lines
if (match(last, /\n[[:space:]]*\n/) || match(p, /\n[[:space:]]*\n/) ) {
- last = p; p = _block(p);
+ last = p; p = _nblock(p);
} else {
- last = p; p = _block(p);
+ last = p; p = _nblock(p);
sub( /^<p>/, "", p );
sub( /<\/p>\n/, "", p );
}
sub( /\n$/, "", 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 );
+ # 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 {
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"; }
# 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 );
}