#
# 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)
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 );
return "";
# omit processing of escaped characters
- } else if ( line ~ /^\\[]\\`\*_\{\}\(\)#\+-\.![]/) {
- return substr(line, 2, 1) inline( substr(line, 3) );
+ } else if ( line ~ /^\\./) {
+ return HTML(substr(line, 2, 1)) inline( substr(line, 3) );
# hard brakes
} else if ( match(line, /^ \n/) ) {
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, /^\[\[([^\]\|]+)(\|([^\]]+))?\]\]/) ) {
+ } else if ( match( line, /^\[\[([^]|]+)(\|[^]]+)?\]\]/) ) {
len = RLENGTH;
- href = gensub(/^\[\[([^\]\|]+)(\|([^\]]+))?\]\]/, "\\1", 1, substr(line, 1, len) );
- text = gensub(/^\[\[([^\]\|]+)(\|([^\]]+))?\]\]/, "\\3", 1, substr(line, 1, len) );
+ 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) );
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 _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib ) {
+function headline( hlvl, htxt, LOCAL, sec, n, HL) {
+ split( gensub( /^(.* )?(([0-9]+ ){5}[0-9]+)$/, "\\2" ,"1", hstack), HL);
+
+ for ( n = hlvl; n <= 6; n++ ) { sec = sec (HL[n]?"</section>":""); }
+ HL[hlvl]++; for ( n = hlvl + 1; n <= 6; n++) { HL[n] = 0;}
+ hid = HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; }
+ # hid = hid ":" URL(htxt, 1);
+
+ hstack = HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6];
+
+ return sec "<section class=\"h1\"" ((blvl > 10)?"":" id=\"" hid "\"") ">" \
+ "<h1>" inline( htxt ) \
+ ((blvl > 0)?"":"<a class=\"anchor\" href=\"#" hid "\"></a>") \
+ "</h1>\n\n";
+}
+
+# Nested Block, resets heading counters
+function _nblock( block, LOCAL, hlsav, sec ) {
+ hlsav = hstack;
+ hstack = "0 0 0 0 0 0";
+
+ # Block Level
+ blvl++;
+
+ block = _block( block );
+ split( gensub( /^(.* )?(([0-9]+ ){5}[0-9]+)$/, "\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, hlvl, htxt, sec, guard, code, indent, attrib ) {
gsub( /^\n+|\n+$/, "", block );
if ( block == "" ) {
} else if ( match( block, /^> /) ) {
match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match(block, /$/);
len = RLENGTH; st = RSTART;
- return "<blockquote>\n" _block( gensub( /(^|\n)> /, "\n", "g", substr(block, 1, st - 1) ) ) "</blockquote>\n\n" \
+ return "<blockquote>\n" _nblock( gensub( /(^|\n)> /, "\n", "g", substr(block, 1, st - 1) ) ) "</blockquote>\n\n" \
_block( substr(block, st + len) );
# Pipe Tables (pandoc / php md / gfm )
"(\\|([^\n]+\\|)+\n)+" \
"(\\+(:?=+:?\\+)+)\n" \
"((\\|([^\n]+\\|)+\n)+" \
- "\\+(-+\\+)+(\n|$))+", \
- tread \
+ "\\+(-+\\+)+(\n|$))+" \
) || \
match( block, "^()()()" \
"(\\+(:?-+:?\\+)+)\n" \
"((\\|([^\n]+\\|)+\n)+" \
- "\\+(-+\\+)+(\n|$))+", \
- tread \
+ "\\+(-+\\+)+(\n|$))+" \
) ) {
len = RLENGTH; st = RSTART;
#initialize empty arrays
- split("", talign); split("", tarray); # split("", tread);
+ split("", talign); split("", tarray); split("", tread);
cols = 0; cnt=0; ttext = "";
+ # Column Count
+ cols = split( gensub( "^(\\+(:?-+:?\\+)+)(\n.*)*$", "\\1", 1, block), tread, /\+/) - 2;
+ # debug(" Cols: " gensub( "^(\\+(:?-+:?\\+)+)(\n.*)*$", "\\1", 1, block ));
+
# table alignment
- cols = split( gensub( /(^\+|\+$)/, "", "g", tread[4] ), talign, /\+/ );
+ 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";
# table header
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|$)/)) \
+ split( gensub( /(^\||\|$)/, "", "g", \
+ gensub( /(^|[^\\])\\\|/, "\\1\\|", "g", \
+ substr(block, 1, match(block, /(\n|$)/)) \
)), tread, /\|/);
block = substr(block, match(block, /(\n|$)/) + 1 );
for (cnt = 1; cnt <= cols; cnt++)
ttext = "<thead>\n<tr>"
for (cnt = 1; cnt <= cols; cnt++)
- ttext = ttext "<th align=\"" talign[cnt] "\">" _block(tarray[cnt]) "</th>"
+ ttext = ttext "<th align=\"" talign[cnt] "\">" _nblock(tarray[cnt]) "</th>"
ttext = ttext "</tr>\n</thead>"
}
ttext = ttext "<tr>"
for (cnt = 1; cnt <= cols; cnt++)
- ttext = ttext "<td align=\"" talign[cnt] "\">" _block(tarray[cnt]) "</td>"
+ ttext = ttext "<td align=\"" talign[cnt] "\">" _nblock(tarray[cnt]) "</td>"
ttext = ttext "</tr>\n"
}
- return "<table>" ttext "</tbody></table>\n" _block(block);
+ return "<table>" ttext "</tbody></table>\n" _nblock(block);
# Line Blocks (pandoc)
} else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\n]*(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) {
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|$)/ ) || match( block, /$/ );
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|$)/ ) ) {
len = RLENGTH;
- HL[1]++; HL[2] = 0; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
- return "<h1 id=\"" HL[1] ":" URL(gensub( /\n.*$/, "", "g", block )) "\">" \
- inline( gensub( /\n.*$/, "", "g", block ) ) \
- "<a class=\"anchor\" href=\"#" HL[1] ":" \
- URL(gensub( /\n.*$/, "", "g", block )) "\"></a></h1>\n\n" \
+
+ return headline(1, gensub( /\n.*$/, "", "g", block )) \
_block( substr( block, len + 1 ) );
- # Second Order Heading
+ # Second Order Heading H2
} else if ( match( block, /^[^\n]+\n---+(\n|$)/ ) ) {
len = RLENGTH;
- 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.*$/, "", "g", block )) "\"></a></h2>\n\n" \
+
+ return headline(2, gensub( /\n.*$/, "", "g", block )) \
_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|$)/ ) ) {
len = RLENGTH;
- hlvl = length( gensub( /^(#{1,6}).*$/, "\\1", "g", block ) );
- htxt = gensub(/^#{1,6}[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[^\n#])+)([ \t]*#*)(\n.*)?$/, "\\1", 1, block);
- HL[hlvl]++; for ( n = hlvl + 1; n < 7; n++) { HL[n] = 0;}
- hid = HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; }
- return "<h" hlvl " id=\"" hid ":" URL(htxt) "\">" inline( htxt ) \
- "<a class=\"anchor\" href=\"#" hid "\"></a></h" hlvl ">\n\n" \
+
+ return headline( \
+ length( gensub( /^(#{1,6}).*$/, "\\1", "g", block ) ), \
+ gensub(/^#{1,6}[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[^\n#])+)([ \t]*#*)(\n.*)?$/, "\\1", 1, block) \
+ ) \
_block( substr( block, len + 1) );
# block images (wrapped in <figure>)
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.*)?$/, "\\2", 1, block);
if ( ! id ) id = text;
if ( rl_href[id] && rl_title[id] ) {
- return "<figure data-src=\"" URL(rl_href[id]) "\">" \
- "<img src=\"" URL(rl_href[id]) "\" alt=\"" HTML(text) "\">" \
+ return "<figure data-src=\"" URL(rl_href[id], 1) "\">" \
+ "<img src=\"" URL(rl_href[id], 1) "\" alt=\"" HTML(text) "\">" \
"<figcaption>" inline(rl_title[id]) "</figcaption>" \
"</figure>\n\n" \
_block( substr( block, len + 1) );
} else if ( rl_href[id] ) {
- return "<figure data-src=\"" URL(rl_href[id]) "\">" \
- "<img src=\"" URL(rl_href[id]) "\" alt=\"" HTML(text) "\">" \
+ return "<figure data-src=\"" URL(rl_href[id], 1) "\">" \
+ "<img src=\"" URL(rl_href[id], 1) "\" alt=\"" HTML(text) "\">" \
"</figure>\n\n" \
_block( substr( block, len + 1) );
} else {
} else if ( AllowMacros && match( block, /^<<(([^>]|>[^>])+)>>(\n|$)/) ) {
len = RLENGTH;
text = gensub(/^<<(([^>]|>[^>])+)>>(\n.*)?$/, "\\1", 1, block);
- return macro(text) _block(substr(block, len + 1));
+ return macro(text) _block(substr(block, len + 1) );
# Split paragraphs
} else if ( match( block, /(^|\n)[[:space:]]*(\n|$)/) ) {
# 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 );
}
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 );
}