# - [x] Automatic <section>-wrapping (custom)
# - ? Heading identifiers (php md, pandoc)
# - [x] Heading attributes (custom)
+# - [ ] <hr> terminates section
# - [x] Automatic heading identifiers (custom)
# - [x] Fenced code blocks (php md, pandoc)
# - [x] Fenced code attributes
return text;
}
-function inline( line, LOCAL, len, code, href, guard ) {
+function inline( line, LOCAL, len, text, code, href, guard ) {
nu = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\_]|_[[:alnum:]])*" # not underline (except when escaped)
na = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\\\*])*" # not asterisk (except when escaped)
ieu = "_([^_[:space:]]|[^_[:space:]]" nu "[^_[:space:]])_" # inner <em> (underline)
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( /^ | $/, "", "g" , code)
+ gsub( /^ | $/, "", code)
# escape HTML within code span
gsub( /&/, "\\&", code ); gsub( /</, "\\<", code ); gsub( />/, "\\>", code );
return "<code>" code "</code>" inline( substr( line, len + 1 ) )
}
function headline( hlvl, htxt, attrib, LOCAL, sec, n, HL) {
- split( gensub( /^(.* )?([0-9]+( [0-9]+){5})$/, "\\2" ,"1", hstack), HL);
+ match(hstack, /([0-9]+( [0-9]+){5})$/); split( substr(hstack, RSTART), HL);
for ( n = hlvl; n <= 6; n++ ) { sec = sec (HL[n]?"</section>":""); }
HL[hlvl]++; for ( n = hlvl + 1; n <= 6; n++) { HL[n] = 0;}
+
hid = ""; for ( n = 2; n <= blvl; n++) { hid = hid BL[n] "/"; }
hid = hid HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; }
hid = hid ":" URL(htxt, 1);
- hstack = gensub( /^(.* )?([0-9]+( [0-9]+){5})$/, "\\1" ,"1", hstack) \
- HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6];
+ sub(/([0-9]+( [0-9]+){5})$/, "", hstack);
+ hstack = hstack HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6];
return sec "<section class=\"" (attrib ? "h" hlvl " " attrib : "h" hlvl) "\" id=\"" hid "\">" \
"<h" hlvl (attrib ? " class=\"" attrib "\"" : "") ">" inline( htxt ) \
}
# Nested Block, resets heading counters
-function _nblock( block, LOCAL, hlsav, sec, n ) {
- hlsav = hstack;
+function _nblock( block, LOCAL, sec, n ) {
hstack = hstack " 0 0 0 0 0 0";
# Block Level
for ( n = blvl + 1; n in BL; n++) { delete BL[n]; }
block = _block( block );
- split( gensub( /^(.* )?([0-9]+( [0-9]+){5})$/, "\\2" ,"1", hstack), HL);
+ match(hstack, /([0-9]+( [0-9]+){5})$/); split( substr(hstack, RSTART), HL);
sec = ""; for ( n = 1; n <= 6; n++ ) { sec = sec (HL[n]?"</section>":""); }
- hstack = hlsav; blvl--;
+
+ sub("( +[0-9]+){6} *$", "", hstack); blvl--;
return block sec;
}
} else if ( match( block, /^> /) ) {
match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match(block, /$/);
len = RLENGTH; st = RSTART;
- return "<blockquote>" gensub( /^\n|\n$/, "", "g", _nblock( gensub( /(^|\n)> /, "\n", "g", substr(block, 1, st - 1) ) ) ) "</blockquote>\n\n" \
- _block( substr(block, st + len) );
+ text = substr(block, 1, st - 1); gsub( /(^|\n)> /, "\n", text );
+ text = _nblock( text ); gsub( /^\n|\n$/, "", text )
+ return "<blockquote>" text "</blockquote>\n\n" _block( substr(block, st + len) );
# Pipe Tables (pandoc / php md / gfm )
} else if ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?)\n" \
# Line Blocks (pandoc)
} else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\n]*(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) {
len = RLENGTH; st = RSTART;
- text = substr(block, 1, len);
- gsub(/\n[[:space:]]+/, " ", text);
- gsub(/\n\| /, "\n", text);
- gsub(/^\| |\n$/, "", text);
- return "<div class=\"line-block\">" gensub(/\n/, "<br>\n", "g", inline( text )) "</div>\n" \
- _block( substr( block, len + 1) );
+
+ text = substr(block, 1, len); gsub(/\n[[:space:]]+/, " ", text);
+ gsub(/\n\| /, "\n", text); gsub(/^\| |\n$/, "", text);
+ text = inline(text); gsub(/\n/, "<br>\n", text);
+
+ return "<div class=\"line-block\">" text "</div>\n" _block( substr( block, len + 1) );
# Indented Code Block
} else if ( match(block, /^( |\t)( *\t*[^ \t\n]+ *\t*)+(\n|$)(( |\t)[^\n]+(\n|$)|[ \t]*(\n|$))*/) ) {
# 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.*)?$/, "\\3", 1, block)
+ len = RLENGTH; text = attrib = block;
+ sub(/([ \t]*\{([^\}\n]+)\})\n===+(\n.*)?$/, "", text);
+ sub(/\}\n===+(\n.*)?$/, "", attrib); sub(/^([^\n]+)[ \t]*\{/, "", attrib);
gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib);
- return headline(1, text, attrib) \
- _block( substr( block, len + 1 ) );
+ return headline(1, text, attrib) _block( substr( block, len + 1 ) );
# First Order Heading H1
} else if ( match( block, /^([^\n]+)\n===+(\n|$)/ ) ) {
- len = RLENGTH;
- text = gensub(/^([^\n]+)\n===+(\n.*)?$/, "\\1", 1, block)
+ len = RLENGTH; text = substr(block, 1, len);
+ sub(/\n===+(\n.*)?$/, "", text);
- return headline(1, text, 0) \
- _block( substr( block, len + 1 ) );
+ return headline(1, text, 0) _block( substr( block, len + 1 ) );
# Second Order Heading H2 + 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.*)?$/, "\\3", 1, block)
+ len = RLENGTH; text = attrib = block;
+ sub(/([ \t]*\{([^\}\n]+)\})\n---+(\n.*)?$/, "", text);
+ sub(/\}\n---+(\n.*)?$/, "", attrib); sub(/^([^\n]+)[ \t]*\{/, "", attrib);
gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib);
- return headline(2, text, attrib) \
- _block( substr( block, len + 1) );
+ return headline(2, text, attrib) _block( substr( block, len + 1) );
# Second Order Heading H2
} else if ( match( block, /^([^\n]+)\n---+(\n|$)/ ) ) {
- len = RLENGTH;
- text = gensub(/^([^\n]+)\n---+(\n.*)?$/, "\\1", 1, block)
+ len = RLENGTH; text = substr(block, 1, len);
+ sub(/\n---+(\n.*)?$/, "", text);
- return headline(2, text, 0) \
- _block( substr( block, len + 1) );
+ return headline(2, text, 0) _block( substr( block, len + 1) );
# 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);
+ len = RLENGTH; text = attrib = substr(block, 1, len);
+ match(block, /^#{1,6}/); n = RLENGTH;
+
+ sub(/^(#{1,6})[ \t]*/, "", text); sub(/[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n.*)?$/, "", text);
+ sub(/^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*[ \t]*\{/, "", attrib);
+ sub(/\})(\n.*)?$/, "", attrib);
gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib);
- return headline( length(n), text, attrib ) \
- _block( substr( block, len + 1) );
+ return headline( n, text, attrib ) _block( substr( block, len + 1) );
# Nth Order Heading H1 H2 H3 H4 H5 H6
} else if ( match( block, /^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n|$)/ ) ) {
- 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);
+ len = RLENGTH; text = substr(block, 1, len);
+ match(block, /^#{1,6}/); n = RLENGTH;
+ sub(/^(#{1,6})[ \t]*/, "", text); sub(/[ \t]*#*(\n.*)?$/, "", text);
- return headline( length(n), text, 0 ) \
- _block( substr( block, len + 1) );
+ return headline( n, text, 0 ) _block( substr( block, len + 1) );
# block images (wrapped in <figure>)
} else if ( match(block, /^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n|$)/) ) {
text = gensub(/^<<(([^>]|>[^>])+)>>(\n.*)?$/, "\\1", 1, block);
return macro(text) _block(substr(block, len + 1) );
- # Horizontal rule
- } else if ( match( block, /(^|\n) ? ? ?((\* *){3,}|(- *){3,}|(_ *){3,})($|\n)/) ) {
- len = RLENGTH; st = RSTART;
- return _block(substr(block, 1, st - 1)) "<hr>\n" _block(substr(block, st + len));
-
# Definition list
} else if (match( block, "^(([ \t]*\n)*[^:\n \t][^\n]+\n" \
"([ \t]*\n)* ? ? ?:[ \t][^\n]+(\n|$)" \
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 );
+ # Unordered list types
+ } else if ( text = _startlist( block, "ul", "-", "([+*]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) {
+ return text;
+ } else if ( text = _startlist( block, "ul", "\\+", "([-*]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) {
+ return text;
+ } else if ( text = _startlist( block, "ul", "\\*", "([-+]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) {
+ return text;
+
+ # Ordered list types
+ } else if ( text = _startlist( block, "ol", "[0-9]+\\.", "([-+*]|#\\.|[0-9]+\\)|#\\))") ) {
+ return text;
+ } else if ( text = _startlist( block, "ol", "[0-9]+\\)", "([-+*]|[0-9]+\\.|#\\.|#\\))") ) {
+ return text;
+ } else if ( text = _startlist( block, "ol", "#\\.", "([-+*]|[0-9]+\\.|[0-9]+\\)|#\\))") ) {
+ return text;
+ } else if ( text = _startlist( block, "ol", "#\\)", "([-+*]|[0-9]+\\.|#\\.|[0-9]+\\))") ) {
+ return text;
# Split paragraphs
} else if ( match( block, /(^|\n)[[:space:]]*(\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";
}
}
-function _list (block, mark, LOCAL, len, st, text, indent, task) {
+function _startlist(block, type, mark, exclude, LOCAL, st, len, list, indent, text) {
+ if (match( block, "(^|\n) ? ? ?" mark "[ \t][^\n]+(\n|$)" \
+ "(([ \t]*\n)* ? ? ?" mark "[ \t][^\n]+(\n|$)" \
+ "|([ \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" exclude "[ \t]" )) {
+ block = substr(list, RSTART + 1) block;
+ list = substr(list, 1, RSTART);
+ }
+
+ return _block( text ) "<" type ">\n" _list( list, mark ) "</" type ">\n" _block( block );
+ } else return 0;
+}
+
+function _list (block, mark, p, LOCAL, len, st, text, indent, task) {
if ( match(block, "^([ \t]*\n)*$")) return;
+
match(block, "^" mark "[ \t]"); indent = RLENGTH;
sub("^" mark "[ \t]", "", block);
- match( block, "\n" mark "[ \t][^\n]+(\n|$)" \
- "(([ \t]*\n)* ? ? ?" mark "[ \t][^\n]+(\n|$)" \
- "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \
- "|[^\n \t][^\n]+(\n|$))*");
- (RLENGTH == -1) ? st = length(block) + 1 : st = RSTART;
+ if (match(block, /\n[ \t]*\n/)) p = 1;
+
+ match( block, "\n" mark "[ \t][^\n]+(\n|$)" );
+ st = (RLENGTH == -1) ? length(block) + 1 : RSTART;
text = substr(block, 1, st); block = substr(block, st + 1);
gsub("\n {0," indent "}", "\n", text);
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);
+ sub(/^\[[-? \/xX]\]/, "", text);
text = _nblock( text );
- if (match( text, "^<p>(</p[^>]|</[^p]|<[^/]|[^<])*</p>\n$" ))
+ if ( ! p && match( text, "^<p>(</p[^>]|</[^p]|<[^/]|[^<])*</p>\n$" ))
gsub( "(^<p>|</p>\n$)", "", text);
- return task text "</li>\n" _list(block, mark);
+ return task text "</li>\n" _list(block, mark, p);
}
function _dlist (block, LOCAL, len, st, text, indent, p) {