# ----------------------------
# - [x] Automatic <section>-wrapping (custom)
# - ? Heading identifiers (php md, pandoc)
+# - [x] Heading attributes (custom)
+# - [ ] <hr> ends section
# - [x] Automatic heading identifiers (custom)
# - [x] Fenced code blocks (php md, pandoc)
# - [x] Fenced code attributes
# - [x] Pipe table (php md, pandoc)
# - [x] Line blocks (pandoc)
# - [x] Task lists (pandoc, custom)
-# - [ ] Definition lists (php md, pandoc)
+# - [x] Definition lists (php md, pandoc)
# - [-] Numbered example lists (pandoc)
# - [-] Metadata blocks (pandoc)
# - [x] Metadata blocks (custom)
return text;
}
-function URL ( text ) {
+function URL ( text, sharp ) {
gsub( /&/, "%26", text );
gsub( /"/, "%22", text );
gsub( /'/, "%27", text );
gsub( /`/, "%60", text );
gsub( /\?/, "%3F", text );
- gsub( /#/, "%23", text );
+ if (sharp) gsub( /#/, "%23", text );
gsub( /\[/, "%5B", text );
gsub( /\]/, "%5D", text );
gsub( / /, "%20", text );
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) "\">" \
+ 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) "\" alt=\"" HTML(text) "\" title=\"" HTML(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) "\" alt=\"" HTML(text) "\" class=\"" HTML(attrib) "\">" \
+ return "<img src=\"" URL(href, 1) "\" alt=\"" HTML(text) "\" class=\"" HTML(attrib) "\">" \
inline( substr( line, len + 1) );
} else {
- return "<img src=\"" URL(href) "\" alt=\"" HTML(text) "\">" \
+ return "<img src=\"" URL(href, 1) "\" alt=\"" HTML(text) "\">" \
inline( substr( line, len + 1) );
}
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]) "\">" \
+ 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]) "\" alt=\"" HTML(text) "\">" \
+ 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) );
}
}
+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 ) {
- # 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;
+function _nblock( block, LOCAL, sec, n ) {
+ hstack = hstack " 0 0 0 0 0 0";
# Block Level
- blvl++;
+ blvl++; BL[blvl]++;
+ for ( n = blvl + 1; n in BL; n++) { delete BL[n]; }
block = _block( block );
+ split( gensub( /^(.* )?([0-9]+( [0-9]+){5})$/, "\\2" ,"1", hstack), HL);
sec = ""; for ( n = 1; n <= 6; n++ ) { sec = sec (HL[n]?"</section>":""); }
- split(hlsav, HL); blvl--;
+
+ sub("( +[0-9]+){6} *$", "", hstack); blvl--;
return block sec;
}
-function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, attrib ) {
- gsub( /^\n+|\n+$/, "", block );
+function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, indent, list ) {
+ gsub( "(^\n+|\n+$)", "", block );
if ( block == "" ) {
return "";
} else if ( match( block, /^> /) ) {
match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match(block, /$/);
len = RLENGTH; st = RSTART;
- return "<blockquote>\n" _nblock( gensub( /(^|\n)> /, "\n", "g", substr(block, 1, st - 1) ) ) "</blockquote>\n\n" \
+ return "<blockquote>" gensub( /^\n|\n$/, "", "g", _nblock( gensub( /(^|\n)> /, "\n", "g", substr(block, 1, st - 1) ) ) ) "</blockquote>\n\n" \
_block( substr(block, st + len) );
# Pipe Tables (pandoc / php md / gfm )
# Line Blocks (pandoc)
} else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\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
# Fenced Divs (pandoc, custom)
} else if ( match( block, /^(:::+)/ ) ) {
guard = substr( block, 1, RLENGTH );
- code = gensub(/^[^\n]+\n/, "", 1, block);
+ code = block; sub(/^[^\n]+\n/, "", code);
attrib = gensub(/^:::+[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\1", 1, block);
gsub(/[^a-zA-Z0-9_-]+/, " ", attrib);
gsub(/(^ | $)/, "", attrib);
_block( substr(block, st + len) );
}
- # Unordered list
- } else if ( match( block, "^ ? ? ?[-+*][ \t]+[^\n]+(\n|$)" \
- "(([ \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) );
-
- gsub("(^|\n) {0," indent "}", "\n", list);
- return "\n<ul>\n" _list( substr(list, 2) ) "</ul>\n" _block( block );
-
- # 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]+.*$/, "", 1, list) );
+ # First Order Heading H1 + Attrib
+ } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n===+(\n|$)/ ) ) {
+ 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(/(^ | $)/, "", attrib);
- gsub("(^|\n) {0," indent "}", "\n", list);
- return "\n<ol>\n" _list( substr(list, 2) ) "</ol>\n" _block( block );
+ return headline(1, text, attrib) _block( substr( block, len + 1 ) );
# First Order Heading H1
- } else if ( match( block, /^[^\n]+\n===+(\n|$)/ ) ) {
- len = RLENGTH; sec = "";
+ } else if ( match( block, /^([^\n]+)\n===+(\n|$)/ ) ) {
+ len = RLENGTH;
+ text = gensub(/^([^\n]+)\n===+(\n.*)?$/, "\\1", 1, block)
- 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;
- hid = HL[1] ":" URL(gensub( /\n.*$/, "", "g", block ));
+ return headline(1, text, 0) _block( substr( block, len + 1 ) );
- return sec "<section class=\"h1\"" ((blvl > 1)?"":" id=\"" hid "\"") ">" \
- "<h1>" inline( gensub( /\n.*$/, "", "g", block ) ) \
- ((blvl > 1)?"":"<a class=\"anchor\" href=\"#" hid "\"></a>") \
- "</h1>\n\n" \
- _block( substr( block, len + 1 ) );
+ # Second Order Heading 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)
+ gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib);
- # Second Order Heading H2
- } else if ( match( block, /^[^\n]+\n---+(\n|$)/ ) ) {
- len = RLENGTH; sec = "";
+ return headline(2, text, attrib) _block( substr( block, len + 1) );
- 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;
- hid= HL[1] "." HL[2] ":" URL(gensub( /\n.*$/, "", "g", block ));
+ # Second Order Heading H2
+ } else if ( match( block, /^([^\n]+)\n---+(\n|$)/ ) ) {
+ len = RLENGTH;
+ text = gensub(/^([^\n]+)\n---+(\n.*)?$/, "\\1", 1, block)
- return sec "<section class=\"h2\"" ((blvl > 1)?"":" id=\"" hid "\"") ">" \
- "<h2>" inline( gensub( /\n.*$/, "", "g", block ) ) \
- ((blvl > 1)?"":"<a class=\"anchor\" href=\"#" hid "\"></a>") \
- "</h2>\n\n" \
- _block( substr( block, len + 1) );
+ return headline(2, text, 0) _block( substr( block, len + 1) );
- # Nth Order Heading H1 H2 H3 H4 H5 H6
- } else if ( match( block, /^#{1,6}[ \t]*[^\n]+([ \t]*#*)(\n|$)/ ) ) {
- len = RLENGTH; sec = "";
+ # Nth Order Heading H1 H2 H3 H4 H5 H6 + Attrib
+ } else if ( match( block, /^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n|$)/ ) ) {
+ 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(/(^ | $)/, "", attrib);
- hlvl = length( gensub( /^(#{1,6}).*$/, "\\1", "g", block ) );
- htxt = gensub(/^#{1,6}[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[^\n#])+)([ \t]*#*)(\n.*)?$/, "\\1", 1, block);
+ return headline( length(n), text, attrib ) _block( substr( block, len + 1) );
- for ( n = hlvl; n <= 6; n++ ) { sec = sec (HL[n]?"</section>":""); }
- HL[hlvl]++; for ( n = hlvl + 1; n <= 6; n++) { HL[n] = 0;}
- hid = HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; }
- hid = hid ":" URL(htxt);
+ # Nth Order Heading H1 H2 H3 H4 H5 H6
+ } else if ( match( block, /^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n|$)/ ) ) {
+ 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 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) );
+ 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|$)/) ) {
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) "\">" \
+ 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) "\">" \
- "<img src=\"" URL(href) "\" alt=\"" HTML(text) "\">" \
+ 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) "\" class=\"" HTML(attrib) "\">" \
- "<img src=\"" URL(href) "\" alt=\"" HTML(text) "\" class=\"" HTML(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) "\">" \
- "<img src=\"" URL(href) "\" alt=\"" HTML(text) "\">" \
+ return "<figure data-src=\"" URL(href, 1) "\">" \
+ "<img src=\"" URL(href, 1) "\" alt=\"" HTML(text) "\">" \
"</figure>\n\n" \
_block( substr( block, len + 1) );
}
id = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\](\n.*)?$/, "\\2", 1, block);
if ( ! id ) id = text;
if ( rl_href[id] && rl_title[id] ) {
- return "<figure data-src=\"" URL(rl_href[id]) "\">" \
- "<img src=\"" URL(rl_href[id]) "\" alt=\"" HTML(text) "\">" \
+ return "<figure data-src=\"" URL(rl_href[id], 1) "\">" \
+ "<img src=\"" URL(rl_href[id], 1) "\" alt=\"" HTML(text) "\">" \
"<figcaption>" inline(rl_title[id]) "</figcaption>" \
"</figure>\n\n" \
_block( substr( block, len + 1) );
} else if ( rl_href[id] ) {
- return "<figure data-src=\"" URL(rl_href[id]) "\">" \
- "<img src=\"" URL(rl_href[id]) "\" alt=\"" HTML(text) "\">" \
+ return "<figure data-src=\"" URL(rl_href[id], 1) "\">" \
+ "<img src=\"" URL(rl_href[id], 1) "\" alt=\"" HTML(text) "\">" \
"</figure>\n\n" \
_block( substr( block, len + 1) );
} else {
text = gensub(/^<<(([^>]|>[^>])+)>>(\n.*)?$/, "\\1", 1, block);
return macro(text) _block(substr(block, len + 1) );
+ # 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;
}
}
-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 = _nblock(p);
- } else {
- last = p; p = _nblock(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 );
-
- # 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 {