# Meant to support all features of John Grubers basic Markdown
# + a number of common extensions, mostly inspired by Pandoc Markdown
+# Copyright 2021 - 2023 Paul Hänsch
+#
+# Permission to use, copy, modify, and/or distribute this software for any
+# purpose with or without fee is hereby granted, provided that the above
+# copyright notice and this permission notice appear in all copies.
+#
+# THE SOFTWARE IS PROVIDED “AS IS” AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
+# SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR
+# IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
# Supported Features / TODO:
# ==========================
# [x] done [ ] todo [-] not planned ? unsure
return "<code>" code "</code>" inline( substr( line, len + 1 ) )
}
+ # Macros
+ } else if ( match( line, /^<<([^>]|>[^>])+>>/ ) ) {
+ len = RLENGTH;
+ return "<code class=\"macro\">" HTML( substr( line, 3, len - 4 ) ) "</code>" inline(substr(line, len + 1));
+
# Wiki style links
} else if ( match( line, /^\[\[([^]|]+)(\|[^]]+)?\]\]/) ) {
len = RLENGTH;
href = URL( substr( line, 2, len - 2) );
return "<a href=\"mailto:" href "\">" href "</a>" 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));
+
# inline links
# ,_______________________Image____________________________,
} else if ( match(line, /^\[([^]]+|!\[[^]]*\]\([^"\)]+([ \t]+"[^"]+")?\)(\{[a-zA-Z \t-]*\})?)\]\(([^"\)]+)([[:space:]]+"([^"]+)")?\)/) ) {
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;
# Pipe Tables (pandoc / php md / gfm )
} else if ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?)\n" \
- "((\\|)?:?(-+:?[\\|+])+:?-+:?(\\|)?)\n" \
+ "((\\|)?(:?-+:?[\\|+])+:?-+:?(\\|)?)\n" \
"((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ) {
len = RLENGTH; st = RSTART;
#initialize empty arrays
}
# Macros (standalone <<macro>> calls handled as block, so they are not wrapped in paragraph)
- } else if ( AllowMacros && match( block, /^<<(([^>]|>[^>])+)>>(\n|$)/) ) {
+ } else if ( match( block, /^<<(([^>]|>[^>])+)>>(\n|$)/ ) ) {
len = RLENGTH;
text = gensub(/^<<(([^>]|>[^>])+)>>(\n.*)?$/, "\\1", 1, block);
- return macro(text) _block(substr(block, len + 1) );
+ return "<code class=\"macro\">" HTML(text) "</code>" _block(substr(block, len + 1) );
# Definition list
} else if (match( block, "^(([ \t]*\n)*[^:\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;
+ } 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|$)/) ) {
}
}
+function _startlist(block, type, mark, exclude, LOCAL, st, len, list, indent, text) {
+ if (match( block, "(^|\n) ? ? ?" mark "[ \t][^\n]+(\n|$)" \
+ "(([ \t]*\n)* ? ? ?" mark "[ \t][^\n]+(\n|$)" \
+ "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \
+ "|[^\n \t][^\n]+(\n|$))*" ) ) {
+ st = RSTART; len = RLENGTH; list = substr( block, st, len);
+
+ sub("^\n", "", list); match(list, "^ ? ? ?"); indent = RLENGTH;
+ gsub( "(^|\n) {0," indent "}", "\n", list); sub("^\n", "", list);
+
+ text = substr(block, 1, st - 1); block = substr(block, st + len);
+ if (match(text, /\n[[:space:]]*\n/)) return 0;
+ if (match(text, "(^|\n) ? ? ?" exclude "[ \t][^\n]+")) return 0;
+ if (match( list, "\n" exclude "[ \t]" )) {
+ block = substr(list, RSTART + 1) block;
+ list = substr(list, 1, RSTART);
+ }
+
+ return _block( text ) "<" type ">\n" _list( list, mark ) "</" type ">\n" _block( block );
+ } else return 0;
+}
+
function _list (block, mark, p, LOCAL, len, st, text, indent, task) {
if ( match(block, "^([ \t]*\n)*$")) return;
+
match(block, "^" mark "[ \t]"); indent = RLENGTH;
sub("^" mark "[ \t]", "", block);
+
if (match(block, /\n[ \t]*\n/)) p = 1;
- 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;
+ 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 ( ! p && match( text, "^<p>(</p[^>]|</[^p]|<[^/]|[^<])*</p>\n$" ))