# 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
#
# Extensions - Block elements:
# ----------------------------
+# - [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
+# - [x] Images (as block elements, <figure>-wrapped) (custom)
+# - [x] reference style block images
# - [/] Tables
# - ? Simple table (pandoc)
# - ? Multiline table (pandoc)
# - [x] Grid table (pandoc)
-# - [x] Pipe table (php md pandoc)
+# - [x] Headerless
+# - [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)
# - [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 inline( line, LOCAL, len, code, href, guard ) {
- nu = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\_]|_[[:alnum:]])*" # not underline (except when escaped)
- na = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\\\*])*" # not asterisk (except when escaped)
- ieu = "_([^_[:space:]]|[^_[:space:]]" nu "[^_[:space:]])_" # inner <em> (underline)
- isu = "__([^_[:space:]]|[^_[:space:]]" nu "[^_[:space:]])__" # inner <strong> (underline)
- iea = "\\*([^\\*[:space:]]|[^\\*[:space:]]" na "[^\\*[:space:]])\\*" # inner <em> (asterisk)
- isa = "\\*\\*([^\\*[:space:]]|[^\\*[:space:]]" na "[^\\*[:space:]])\\*\\*" # inner <strong> (asterisk)
-
- if ( line ~ /^$/ ) { # Recursion End
- return "";
-
- # omit processing of escaped characters
- } else if ( line ~ /^\\[]\\`\*_\{\}\(\)#\+-\.![]/) {
- return substr(line, 2, 1) inline( substr(line, 3) );
-
- # hard brakes
- } else if ( match(line, /^ \n/) ) {
- return "<br />\n" inline( substr(line, RLENGTH + 1) );
-
- # ``code spans``
- } else if ( match( line, /^`+/) ) {
- len = RLENGTH
- guard = substr( line, 1, len )
- if ( match(line, guard ".*" guard) ) {
- 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)
- # escape HTML within code span
- gsub( /&/, "\\&", code ); gsub( /</, "\\<", code ); gsub( />/, "\\>", code );
- return "<code>" code "</code>" 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) );
- 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) );
- return "<a href=\"mailto:" href "\">" href "</a>" inline( substr( line, len + 1) );
-
- # inline links
- } else if ( match(line, /^\[([^]]+)\]\(([^"\)]+)([[: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) );
- if ( title ) {
- return "<a href=\"" HTML(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) );
- }
+function URL ( text, sharp ) {
+ gsub( /&/, "%26", text );
+ gsub( /"/, "%22", text );
+ gsub( /'/, "%27", text );
+ gsub( /`/, "%60", text );
+ gsub( /\?/, "%3F", text );
+ if (sharp) gsub( /#/, "%23", text );
+ gsub( /\[/, "%5B", text );
+ gsub( /\]/, "%5D", text );
+ gsub( / /, "%20", text );
+ gsub( / /, "%09", text );
+ gsub( /\\/, "%5C", text );
+ return text;
+}
- # reference style links
- } 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) );
- 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) );
- } else if ( rl_href[id] ) {
- return "<a href=\"" HTML(rl_href[id]) "\">" inline(text) "</a>" inline( substr( line, len + 1) );
- } else {
- return "" HTML(substr(line, 1, len)) inline( substr(line, len + 1) );
- }
+function inline( line, LOCAL, len, text, code, href, guard, ret ) {
+ ret = "";
+ while (line !~ /^$/) {
+ # omit processing of escaped characters
+ if ( line ~ /^\\./) {
+ ret = ret HTML(substr(line, 2, 1)); line = substr(line, 3);
+ continue;
+
+ # hard brakes
+ } else if ( match(line, /^ \n/) ) {
+ ret = ret "<br>\n"; line = substr(line, RLENGTH + 1);
+ continue;
+
+ # ``code spans``
+ } else if ( match( line, /^`+/) ) {
+ len = RLENGTH
+ guard = substr( line, 1, len )
+ if ( match(line, guard ".*" guard) ) {
+ code = substr( line, len + 1, match( substr(line, len + 1), guard ) - 1)
+ len = 2 * length(guard) + length(code)
+ # strip single surrounding white spaces
+ gsub( /^ | $/, "", code)
+ # escape HTML within code span
+ gsub( /&/, "\\&", code ); gsub( /</, "\\<", code ); gsub( />/, "\\>", code );
+ ret = ret "<code>" code "</code>"; line = substr( line, len + 1 );
+ continue;
+ }
- # inline images
- } else if ( match(line, /^!\[([^]]+)\]\(([^"\)]+)([ \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) );
- } else {
- return "<img src=\"" HTML(href) "\" alt=\"" HTML(text) "\" />" inline( substr( line, len + 1) );
- }
+ # Macros
+ } else if ( match( line, /^<<([^>]|>[^>])+>>/ ) ) {
+ len = RLENGTH;
+ ret = ret "<code class=\"macro\">" HTML( substr( line, 3, len - 4 ) ) "</code>"; line = substr(line, len + 1);
+ continue;
+
+ # Wiki style links
+ } else if ( match( line, /^\[\[([^]|]+)(\|[^]]+)?\]\]/) ) {
+ len = RLENGTH; href = text = substr(line, 1, len);
+ sub(/^\[\[/, "", href); sub(/(\|([^]]+))?\]\].*$/, "", href);
+ sub(/^\[\[([^]|]+)/, "", text); sub(/\]\].*$/, "", text); sub(/^\|/, "", text);
+ # sub(/^\[\[([^]|]+)(\|([^]]+))?\]\]/, "\\1", href );
+ # sub(/^\[\[([^]|]+)(\|([^]]+))?\]\]/, "\\3", text );
+ if ( ! text ) text = href;
+ ret = ret "<a href=\"" HTML(href) "\">" HTML(text) "</a>"; line = substr( line, len + 1);
+ continue;
+
+ # 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) );
+ ret = ret "<a href=\"" href "\">" href "</a>"; line = substr( line, len + 1);
+ continue;
+
+ # quick link email
+ # } else if ( match( line, /^<[a-zA-Z0-9.!#$%&'\''*+\/=?^_`{|}~-]+@[a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(\.[a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*>/ ) ) {
+ } else if ( match( line, /^<[a-zA-Z0-9.!#$%&'\''*+\/=?^_`{|}~-]+@([a-zA-Z0-9]\.[a-zA-Z0-9]|[a-zA-Z0-9-])+>/ ) ) {
+ len = RLENGTH;
+ href = HTML( substr( line, 2, len - 2) );
+ ret = ret "<a href=\"mailto:" href "\">" href "</a>"; line = substr( line, len + 1);
+ continue;
+
+ # 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;
+ ret = ret substr( line, 1, len); line =substr(line, len + 1);
+ continue;
+
+ # inline links
+ } else if ( match(line, "^" lii "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)") ) {
+ len = RLENGTH;
+ text = href = title = substr( line, 1, len);
+ sub("^\\[", "", text); sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)$", "", text);
+ sub("^" lii "\\([\n\t ]*", "", href); sub("([\n\t ]+" lit ")?[\n\t ]*\\)$", "", href);
+ sub("^" lii "\\([\n\t ]*" lid, "", title); sub("[\n\t ]*\\)$", "", title); sub("^[\n\t ]+", "", title);
+
+ if ( match(href, /^<.*>$/) ) { sub(/^</, "", href); sub(/>$/, "", href); }
+ if ( match(title, /^".*"$/) ) { sub(/^"/, "", title); sub(/"$/, "", title); }
+ else if ( match(title, /^'.*'$/) ) { sub(/^'/, "", title); sub(/'$/, "", title); }
+ else if ( match(title, /^\(.*\)$/) ) { sub(/^\(/, "", title); sub(/\)$/, "", title); }
+
+ gsub(/\\/, "", href); gsub(/\\/, "", title); gsub(/[\n\t]+/, " ", title);
+
+ ret = ret "<a href=\"" HTML(href) "\"" (title?" title=\"" HTML(title) "\"":"") ">" \
+ inline( text ) "</a>";
+ line = substr( line, len + 1);
+ continue;
+
+ # reference style links
+ } else if ( match(line, /^\[([^]]+)\] ?\[([^]]*)\]/ ) ) {
+ len = RLENGTH; text = id = substr(line, 1, len);
+ sub(/\n.*$/, "", text); sub(/^\[/, "", text); sub(/\] ?\[([^\n]*)\].*$/, "", text);
+ sub(/\n.*$/, "", id); sub(/^\[([^]]+)\] ?\[/, "", id); sub(/\].*$/, "", id);
+ # text = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\1", 1, text );
+ # id = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\2", 1, id );
+ if ( ! id ) id = text;
+
+ if ( rl_href[id] && rl_title[id] ) {
+ ret = ret "<a href=\"" HTML(rl_href[id]) "\" title=\"" HTML(rl_title[id]) "\">" inline(text) "</a>";
+ line = substr( line, len + 1);
+ continue;
+
+ } else if ( rl_href[id] ) {
+ ret = ret "<a href=\"" HTML(rl_href[id]) "\">" inline(text) "</a>"; line = substr( line, len + 1);
+ continue;
+
+ } else {
+ ret = ret "" HTML(substr(line, 1, len)); line = substr(line, len + 1);
+ continue;
+ }
- # reference style images
- } 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) );
- 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) );
- } else if ( rl_href[id] ) {
- return "<img src=\"" HTML(rl_href[id]) "\" alt=\"" HTML(text) "\" />" inline( substr( line, len + 1) );
- } else {
- return "" HTML(substr(line, 1, len)) inline( substr(line, len + 1) );
- }
+ # inline images
+ } else if ( match(line, "^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?") ) {
+ len = RLENGTH; text = href = title = attrib = substr( line, 1, len);
+
+ sub("^!\\[", "", text);
+ sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", text);
+
+ sub("^!" lix "\\([\n\t ]*", "", href);
+ sub("([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", href);
+
+ sub("^!" lix "\\([\n\t ]*" lid, "", title);
+ sub("[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", title);
+ sub("^[\n\t ]+", "", title);
+
+ sub("^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)", "", attrib);
+ sub(/^\{[ \t]*/, "", attrib); sub(/[ \t]*\}$/, "", attrib); gsub(/[ \t]+/, " ", attrib);
+
+ if ( match(href, /^<.*>$/) ) { sub(/^</, "", href); sub(/>$/, "", href); }
+ if ( match(title, /^".*"$/) ) { sub(/^"/, "", title); sub(/"$/, "", title); }
+ else if ( match(title, /^'.*'$/) ) { sub(/^'/, "", title); sub(/'$/, "", title); }
+ else if ( match(title, /^\(.*\)$/) ) { sub(/^\(/, "", title); sub(/\)$/, "", title); }
+
+ gsub(/^[\t ]+$/, "", text); gsub(/\\/, "", href);
+ gsub(/\\/, "", title); gsub(/[\n\t]+/, " ", title);
+
+ ret = ret "<img src=\"" HTML(href) "\" alt=\"" HTML(text?text:title?title:href) "\"" \
+ (title?" title=\"" HTML(title) "\"":"") (attrib?" class=\"" HTML(attrib) "\"":"") \
+ ">";
+ line = substr( line, len + 1);
+ continue;
+
+ # reference style images
+ } else if ( match(line, /^!\[([^]]*)\] ?\[([^]]*)\]/ ) ) {
+ len = RLENGTH; text = id = substr(line, 1, len);
+ sub(/\n.*$/, "", text); sub(/^!\[/, "", text); sub(/\] ?\[([^\n]*)\].*$/, "", text);
+ sub(/\n.*$/, "", id); sub(/^!\[([^]]+)\] ?\[/, "", id); sub(/\].*$/, "", id);
+ # 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] ) {
+ ret = ret "<img src=\"" HTML(rl_href[id]) "\" alt=\"" HTML(text) "\" title=\"" HTML(rl_title[id]) "\">";
+ line = substr( line, len + 1);
+ continue;
+
+ } else if ( rl_href[id] ) {
+ ret = ret "<img src=\"" HTML(rl_href[id]) "\" alt=\"" HTML(text) "\">";
+ line = substr( line, len + 1);
+ continue;
+
+ } else {
+ ret = ret "" HTML(substr(line, 1, len)); line = substr(line, len + 1);
+ continue;
+ }
- # ~~strikeout~~ (pandoc)
- } else if ( match(line, /^~~([[:graph:]]|[[:graph:]]([^~]|~[^~])*[[:graph:]])~~/) ) {
- len = RLENGTH;
- return "<del>" inline( substr( line, 3, len - 4 ) ) "</del>" inline( substr( line, len + 1 ) );
-
- # ^superscript^ (pandoc)
- } else if ( match(line, /^\^([^[:space:]^]|\\[ ^])+\^/) ) {
- len = RLENGTH;
- return "<sup>" inline( substr( line, 2, len - 2 ) ) "</sup>" inline( substr( line, len + 1 ) );
-
- # ~subscript~ (pandoc)
- } else if ( match(line, /^~([^[:space:]~]|\\[ ~])+~/) ) {
- len = RLENGTH;
- return "<sub>" inline( substr( line, 2, len - 2 ) ) "</sub>" inline( substr( line, len + 1 ) );
-
- # ignore embedded underscores (pandoc, php md)
- } else if ( match(line, "^[[:alnum:]](__|_)") ) {
- return HTML(substr( line, 1, RLENGTH)) inline( substr(line, RLENGTH + 1) );
-
- # __strong__$
- } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__$") ) {
- len = RLENGTH;
- return "<strong>" inline( substr( line, 3, len - 4 ) ) "</strong>" inline( substr( line, len + 1 ) );
-
- # __strong__
- } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__[[:space:][:punct:]]") ) {
- len = RLENGTH;
- return "<strong>" inline( substr( line, 3, len - 5 ) ) "</strong>" inline( substr( line, len) );
-
- # **strong**
- } else if ( match(line, "^\\*\\*(([^\\*[:space:]]|" iea ")|([^\\*[:space:]]|" iea ")(" na "|" iea ")*([^\\*[:space:]]|" iea "))\\*\\*") ) {
- len = RLENGTH;
- return "<strong>" inline( substr( line, 3, len - 4 ) ) "</strong>" inline( substr( line, len + 1 ) );
-
- # _em_$
- } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_$") ) {
- len = RLENGTH;
- return "<em>" inline( substr( line, 2, len - 2 ) ) "</em>" inline( substr( line, len + 1 ) );
-
- # _em_
- } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_[[:space:][:punct:]]") ) {
- len = RLENGTH;
- return "<em>" inline( substr( line, 2, len - 3 ) ) "</em>" inline( substr( line, len ) );
-
- # *em*
- } else if ( match(line, "^\\*(([^\\*[:space:]]|" isa ")|([^\\*[:space:]]|" isa ")(" na "|" isa ")*([^\\*[:space:]]|" isa "))\\*") ) {
- 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;
- return substr( line, 1, len ) inline(substr(line, len + 1));
-
- # Escape lone HTML character
- } else if ( match( line, /^[&<>"']/) ) {
- return HTML(substr(line, 1, 1)) inline(substr(line, 2));
-
- # continue walk over string
- } else {
- return substr(line, 1, 1) inline( substr(line, 2) );
+ # ~~strikeout~~ (pandoc)
+ } else if ( match(line, /^~~([[:graph:]]|[[:graph:]]([^~]|~[^~])*[[:graph:]])~~/) ) {
+ len = RLENGTH;
+ ret = ret "<del>" inline( substr( line, 3, len - 4 ) ) "</del>"; line = substr( line, len + 1 );
+ continue;
+
+ # ^superscript^ (pandoc)
+ } else if ( match(line, /^\^([^[:space:]^]|\\[ ^])+\^/) ) {
+ len = RLENGTH;
+ ret = ret "<sup>" inline( substr( line, 2, len - 2 ) ) "</sup>"; line = substr( line, len + 1 );
+ continue;
+
+ # ~subscript~ (pandoc)
+ } else if ( match(line, /^~([^[:space:]~]|\\[ ~])+~/) ) {
+ len = RLENGTH;
+ ret = ret "<sub>" inline( substr( line, 2, len - 2 ) ) "</sub>"; line = substr( line, len + 1 );
+ continue;
+
+ # ignore embedded underscores (pandoc, php md)
+ } else if ( match(line, "^[[:alnum:]](__|_)") ) {
+ ret = ret HTML(substr( line, 1, RLENGTH)); line = substr(line, RLENGTH + 1);
+ continue;
+
+ # strong / em matchers use pre match pattern to make processing cheaper
+ # __strong__$
+ } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__$") ) {
+ len = RLENGTH;
+ ret = ret "<strong>" inline( substr( line, 3, len - 4 ) ) "</strong>"; line = substr( line, len + 1 );
+ continue;
+
+ # __strong__
+ } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__[[:space:][:punct:]]") ) {
+ len = RLENGTH;
+ ret = ret "<strong>" inline( substr( line, 3, len - 5 ) ) "</strong>"; line = substr( line, len);
+ continue;
+
+ # **strong**
+ } else if ( match(line, "^\\*\\*(([^*[:space:]]|" iea ")|([^*[:space:]]|" iea ")(" na "|" iea ")*([^*[:space:]]|" iea "))\\*\\*") ) {
+ len = RLENGTH;
+ ret = ret "<strong>" inline( substr( line, 3, len - 4 ) ) "</strong>"; line = substr( line, len + 1 );
+ continue;
+
+ # _em_$
+ } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_$") ) {
+ len = RLENGTH;
+ ret = ret "<em>" inline( substr( line, 2, len - 2 ) ) "</em>"; line = substr( line, len + 1 );
+ continue;
+
+ # _em_
+ } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_[[:space:][:punct:]]") ) {
+ len = RLENGTH;
+ ret = ret "<em>" inline( substr( line, 2, len - 3 ) ) "</em>"; line = substr( line, len );
+ continue;
+
+ # *em*
+ } else if ( match(line, "^\\*(([^*[:space:]]|" isa ")|([^*[:space:]]|" isa ")(" na "|" isa ")*([^*[:space:]]|" isa "))\\*") ) {
+ len = RLENGTH;
+ ret = ret "<em>" inline( substr( line, 2, len - 2 ) ) "</em>"; line = substr( line, len + 1 );
+ continue;
+
+ # Literal HTML entities
+ # } else if ( match( line, /^&([a-zA-Z]{2,32}|#[0-9]{1,7}|#[xX][0-9a-fA-F]{1,6});/) ) {
+ # mawk does not support repitition ranges
+ } else if ( match( line, /^&[a-zA-Z][a-zA-Z][a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?;/) ) {
+ len = RLENGTH;
+ ret = ret substr( line, 1, len ); line = substr(line, len + 1);
+ continue;
+ } else if ( match( line, /^&(#[0-9][0-9]?[0-9]?[0-9]?[0-9]?[0-9]?[0-9]?|#[xX][0-9a-fA-F][0-9a-fA-F]?[0-9a-fA-F]?[0-9a-fA-F]?[0-9a-fA-F]?[0-9a-fA-F]?);/) ) {
+ len = RLENGTH;
+ ret = ret substr( line, 1, len ); line = substr(line, len + 1);
+ continue;
+
+ # Arrows
+ } else if ( line ~ /^-->( |$)/) { # ignore multidash-arrow
+ ret = ret "-->"; line = substr(line, 4);
+ continue;
+ } else if ( line ~ /^<-( |$)/) {
+ ret = ret "←"; line = substr(line, 3);
+ continue;
+ } else if ( line ~ /^->( |$)/) {
+ ret = ret "→"; line = substr(line, 3);
+ continue;
+
+ # Escape lone HTML character
+ } else if ( match( line, /^[&<>"']/) ) {
+ ret = ret HTML(substr(line, 1, 1)); line = substr(line, 2);
+ continue;
+
+ } # inline patterns end
+
+ # continue walk over string
+ ret = ret substr(line, 1, 1); line = substr(line, 2);
}
+ return ret;
}
-function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib ) {
- gsub( /^\n+|\n+$/, "", block );
-
- if ( block == "" ) {
- return "";
-
- # HTML #2 #3 #4 $5
- } else if ( AllowHTML && match( block, /(^|\n) ? ? ?(<!--([^-]|-[^-]|--[^>])*(-->|$)|<\?([^\?]|\?[^>])*(\?>|$)|<![A-Z][^>]*(>|$)|<!\[CDATA\[([^\]]|\][^\]]|\]\][^>])*(\]\]>|$))/) ) {
- len = RLENGTH; st = RSTART;
- return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len));
-
- # HTML #6
- } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<\/?(address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset|h[123456]|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul)([[:space:]\n>]|\/>)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) {
- len = RLENGTH; st = RSTART;
- return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len));
-
- # HTML #1
- } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<(script|pre|style)([[:space:]\n>]).*(<\/script>|<\/pre>|<\/style>|$)/) ) {
- len = RLENGTH; st = RSTART;
- match( tolower(substr(block, st, len)), /(<\/script>|<\/pre>|<\/style>)/);
- len = RSTART + RLENGTH;
- return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len));
-
- # HTML #7
- } else if ( AllowHTML && match( block, /^ ? ? ?(<\/[A-Za-z][A-Za-z0-9-]*[[:space:]]*>|<[A-Za-z][A-Za-z0-9-]*([[:space:]]+[A-Za-z_:][A-Za-z0-9_\.:-]*([[:space:]]*=[[:space:]]*([[:space:]"'=<>`]+|"[^"]*"|'[^']*'))?)*[[:space:]]*\/?>)([[:space:]]*\n)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) {
- len = RLENGTH; st = RSTART;
- return substr(block, st, len) _block(substr(block, st + len));
-
- # Metadata (custom, block starting with %something)
- # Metadata is ignored but can be interpreted externally
- } else if ( match(block, /^%[a-zA-Z]+([[:space:]][^\n]*)?(\n|$)(%[a-zA-Z]+([[:space:]][^\n]*)?(\n|$)|%([[:space:]][^\n]*)?(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) {
- len = RLENGTH; st = RSTART;
- return _block( substr( block, len + 1) );
-
- # Blockquote (leading >)
- } 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" \
- _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|$)/) + 1 );
-
- for( cnt = 1; cnt < cols; cnt++ ) {
- if (match(talign[cnt], /:-+:/)) talign[cnt]="center";
- else if (match(talign[cnt], /-+:/)) talign[cnt]="right";
- else if (match(talign[cnt], /:-+/)) talign[cnt]="left";
- else talign[cnt]="";
- }
+function headline( hlvl, htxt, attrib, LOCAL, sec, n, HL) {
+ # match(hstack, /([0-9]+( [0-9]+){5})$/); split( substr(hstack, RSTART), HL);
+ match(hstack, /([0-9]+( [0-9]+)( [0-9]+)( [0-9]+)( [0-9]+)( [0-9]+))$/); split( substr(hstack, RSTART), HL);
- ttext = "<thead>\n<tr>"
- for (cnt = 1; cnt < cols; cnt++)
- ttext = ttext "<th align=\"" talign[cnt] "\">" inline(tarray[cnt]) "</th>"
- ttext = ttext "</tr>\n</thead><tbody>\n"
+ for ( n = hlvl; n <= 6; n++ ) { sec = sec (HL[n]?"</section>":""); }
+ HL[hlvl]++; for ( n = hlvl + 1; n <= 6; n++) { HL[n] = 0;}
- while ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ){
- split( gensub( /(^\||\|$)/, "", "g", \
- gensub( /(^|[^\\])\\\|/, "\\1\\|", "g", \
- substr(block, 1, match(block, /(\n|$)/)) \
- )), tarray, /\|/);
- block = substr(block, match(block, /(\n|$)/) + 1 );
+ hid = ""; for ( n = 2; n <= blvl; n++) { hid = hid BL[n] "/"; }
+ hid = hid HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; }
+ hid = hid ":" URL(htxt, 1);
- ttext = ttext "<tr>"
- for (cnt = 1; cnt < cols; cnt++)
- ttext = ttext "<td align=\"" talign[cnt] "\">" inline(tarray[cnt]) "</td>"
- ttext = ttext "</tr>\n"
- }
- return "<table>" ttext "</tbody></table>\n" _block(block);
-
- # Grid Tables (pandoc)
- } else if ( match(block, "^\\+(-+\\+)+\n" \
- "(\\|([^\n]+\\|)+\n)+" \
- "\\+(:?=+:?\\+)+\n" \
- "((\\|([^\n]+\\|)+\n)+" \
- "\\+(-+\\+)+(\n|$))+" \
- ) ) {
- len = RLENGTH; st = RSTART;
- #initialize empty arrays
- split("", talign); split("", tarray); split("", tread);
- cols = 0; cnt=0; ttext = "";
-
- # table header and alignment
- 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|$)/)) \
- )), tread, /\|/);
+ # sub(/([0-9]+( [0-9]+){5})$/, "", hstack);
+ sub(/([0-9]+( [0-9]+)( [0-9]+)( [0-9]+)( [0-9]+)( [0-9]+))$/, "", hstack);
+ hstack = hstack HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6];
+
+ return sec "<section class=\"" (attrib ? "h" hlvl " " attrib : "h" hlvl) "\" id=\"" hid "\">" \
+ "<h" hlvl (attrib ? " class=\"" attrib "\"" : "") ">" inline( htxt ) \
+ "<a class=\"anchor\" href=\"#" hid "\"></a>" \
+ "</h" hlvl ">\n";
+}
+
+# Nested Block, resets heading counters
+function _nblock( block, LOCAL, sec, n ) {
+ hstack = hstack " 0 0 0 0 0 0";
+
+ # Block Level
+ blvl++; BL[blvl]++;
+ for ( n = blvl + 1; n in BL; n++) { delete BL[n]; }
+
+ block = _block( block );
+ match(hstack, /([0-9]+( [0-9]+)( [0-9]+)?( [0-9]+)?( [0-9]+)?( [0-9]+)?)$/); split( substr(hstack, RSTART), HL);
+ sec = ""; for ( n = 1; n <= 6; n++ ) { sec = sec (HL[n]?"</section>":""); }
+
+ sub("( +[0-9]+)( +[0-9]+)?( +[0-9]+)?( +[0-9]+)?( +[0-9]+)?( +[0-9]+)? *$", "", hstack); blvl--;
+ return block sec;
+}
+
+function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, indent, list, tmp, ret) {
+ ret = "";
+ while ( block != "" ) {
+ gsub( "(^\n+|\n+$)", "", block );
+
+ # HTML #2 #3 #4 $5
+ if ( AllowHTML && match( block, /(^|\n) ? ? ?(<!--([^-]|-[^-]|--[^>])*(-->|$)|<\?([^\?]|\?[^>])*(\?>|$)|<![A-Z][^>]*(>|$)|<!\[CDATA\[([^\]]|\][^\]]|\]\][^>])*(\]\]>|$))/) ) {
+ len = RLENGTH; st = RSTART;
+ ret = ret _block(substr(block, 1, st - 1)) substr(block, st, len); block = substr(block, st + len);
+ continue;
+
+ # HTML #6 (part1)
+ } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<\/?(address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset)([[:space:]\n>]|\/>)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) {
+ len = RLENGTH; st = RSTART;
+ ret = ret _block(substr(block, 1, st - 1)) substr(block, st, len); block = substr(block, st + len);
+ continue;
+
+ # HTML #6 (part2)
+ } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<\/?(h[123456]|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul)([[:space:]\n>]|\/>)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) {
+ len = RLENGTH; st = RSTART;
+ ret = ret _block(substr(block, 1, st - 1)) substr(block, st, len); block = substr(block, st + len);
+ continue;
+
+ # HTML #1
+ } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<(script|pre|style)([[:space:]\n>]).*(<\/script>|<\/pre>|<\/style>|$)/) ) {
+ len = RLENGTH; st = RSTART;
+ match( tolower(substr(block, st, len)), /(<\/script>|<\/pre>|<\/style>)/);
+ len = RSTART + RLENGTH;
+ ret = ret _block(substr(block, 1, st - 1)) substr(block, st, len); block = substr(block, st + len);
+ continue;
+
+ # HTML #7
+ } else if ( AllowHTML && match( block, /^ ? ? ?(<\/[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:]]*\/?>)([[:space:]]*\n)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) {
+ len = RLENGTH; st = RSTART;
+ ret = ret substr(block, st, len); block = substr(block, st + len);
+ continue;
+
+ # Metadata (custom, block starting with %something)
+ # Metadata is ignored but can be interpreted externally
+ } else if ( match(block, /^%[a-zA-Z-]+([[:space:]][^\n]*)?(\n|$)(%[a-zA-Z-]+([[:space:]][^\n]*)?(\n|$)|%([[:space:]][^\n]*)?(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) {
+ len = RLENGTH; st = RSTART;
+ block = substr( block, len + 1);
+ continue;
+
+ # Blockquote (leading >)
+ } else if ( match( block, /^> /) ) {
+ match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match(block, /$/);
+ len = RLENGTH; st = RSTART;
+ text = substr(block, 1, st - 1); gsub( /(^|\n)> /, "\n", text );
+ text = _nblock( text ); gsub( /^\n|\n$/, "", text )
+ ret = ret "<blockquote>" text "</blockquote>\n\n"; block = substr(block, st + len);
+ continue;
+
+ # Pipe Tables (pandoc / php md / gfm )
+ } else if ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?)\n" \
+ "((\\|)?(:?-+:?[\\|+])+:?-+:?(\\|)?)\n" \
+ "((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ) {
+ len = RLENGTH; st = RSTART;
+ #initialize empty arrays
+ split("", talign); split("", tarray);
+ cols = 0; cnt=0; ttext = "";
+
+ # table header and alignment
+ tmp = substr(block, 1, match(block, /(\n|$)/));
+ gsub( /(^|[^\\])\\\|/, "\\1\\|", tmp );
+ gsub( /(^\||\|$)/, "", tmp)
+ split( tmp, tarray, /\|/);
+ block = substr(block, match(block, /(\n|$)/) + 1 );
+ tmp = substr(block, 1, match(block, /(\n|$)/));
+ gsub( /(^\||\|$)/, "", tmp );
+ cols = split( tmp , talign, /[+\|]/);
block = substr(block, match(block, /(\n|$)/) + 1 );
- for (cnt = 1; cnt < cols; cnt++)
- tarray[cnt] = tarray[cnt] "\n" tread[cnt];
- }
- cols = split( \
- gensub( /(^\+|\+$)/, "", "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]="";
- }
+ 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] "\">" _block(tarray[cnt]) "</th>"
- ttext = ttext "</tr>\n</thead><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|$)/)) \
- )), tread, /\|/);
+ ttext = "<thead>\n<tr>"
+ for (cnt = 1; cnt < cols; cnt++)
+ ttext = ttext "<th align=\"" talign[cnt] "\">" inline(tarray[cnt]) "</th>"
+ ttext = ttext "</tr>\n</thead><tbody>\n"
+
+ while ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ){
+ tmp = substr(block, 1, match(block, /(\n|$)/));
+ gsub( /(^|[^\\])\\\|/, "\\1\\|", tmp );
+ gsub( /(^\||\|$)/, "", tmp );
+ split( tmp, tarray, /\|/);
block = substr(block, match(block, /(\n|$)/) + 1 );
+
+ ttext = ttext "<tr>"
for (cnt = 1; cnt < cols; cnt++)
- tarray[cnt] = tarray[cnt] "\n" tread[cnt];
+ ttext = ttext "<td align=\"" talign[cnt] "\">" inline(tarray[cnt]) "</td>"
+ ttext = ttext "</tr>\n"
+ }
+ ret = ret "<table>" ttext "</tbody></table>\n";
+ continue;
+
+ # Grid Tables (pandoc)
+ # (with, and without header)
+ } else if ( match( block, "^\\+(-+\\+)+\n" \
+ "(\\|([^\n]+\\|)+\n)+" \
+ "(\\+(:?=+:?\\+)+)\n" \
+ "((\\|([^\n]+\\|)+\n)+" \
+ "\\+(-+\\+)+(\n|$))+" \
+ ) || \
+ match( block, "^(\\+(:?-+:?\\+)+)\n" \
+ "((\\|([^\n]+\\|)+\n)+" \
+ "\\+(-+\\+)+(\n|$))+" \
+ ) ) {
+ len = RLENGTH; st = RSTART;
+ #initialize empty arrays
+ split("", talign); split("", tarray); split("", tread);
+ cols = 0; cnt=0; ttext = "";
+
+ # Column Count
+ tmp = block; sub( "(\n.*)*$", "", tmp);
+ cols = split( tmp, tread, /\+/) - 2;
+ # debug(" Cols: " gensub( "^(\\+(:?-+:?\\+)+)(\n.*)*$", "\\1", 1, block ));
+
+ # table alignment
+ match(block, "((:?=+:?\\+|(:-+|-+:|:-+:)\\+)+)");
+ split( substr(block, RSTART, RLENGTH) , talign, /\+/ );
+ # split( gensub( "^(.*\n)?\\+((:?=+:?\\+|(:-+|-+:|:-+:)\\+)+)(\n.*)$", "\\2", "g", block ), talign, /\+/ );
+ # debug("Align: " gensub( "^(.*\n)?\\+((:?=+:?\\+|(:-+|-+:|:-+:)\\+)+)(\n.*)$", "\\2", "g", block ));
+
+ for (cnt = 1; cnt <= cols; cnt++) {
+ if (match(talign[cnt], /:(-+|=+):/)) talign[cnt]="center";
+ else if (match(talign[cnt], /(-+|=+):/)) talign[cnt]="right";
+ else if (match(talign[cnt], /:(-+|=+)/ )) talign[cnt]="left";
+ else talign[cnt]="";
}
+
+ if ( match(block, "^\\+(-+\\+)+\n" \
+ "(\\|([^\n]+\\|)+\n)+" \
+ "\\+(:?=+:?\\+)+\n" \
+ "((\\|([^\n]+\\|)+\n)+" \
+ "\\+(-+\\+)+(\n|$))+" \
+ ) ) {
+ # table header
+ block = substr(block, match(block, /(\n|$)/) + 1 );
+ while ( match(block, "^\\|([^\n]+\\|)+\n") ) {
+ tmp = substr(block, 1, match(block, /(\n|$)/));
+ gsub( /\\\\/, "\\\", tmp); gsub(/\\\|/, "\\|", tmp);
+ gsub( /(^\||\|$)/, "", tmp );
+ split(tmp, tread, /\|/);
+ block = substr(block, match(block, /(\n|$)/) + 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/) ) {
+ tmp = substr(block, 1, match(block, /(\n|$)/));
+ gsub( /\\\\/, "\\\", tmp); gsub(/\\\|/, "\\|", tmp);
+ gsub( /(^\||\|$)/, "", tmp);
+ split( tmp, 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] "\">" _block(tarray[cnt]) "</td>"
- ttext = ttext "</tr>\n"
- }
- return "<table>" ttext "</tbody></table>\n" _block(block);
-
- # 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" \
- _block( substr( block, len + 1) );
-
- # Indented Code Block
- } else if ( match(block, /^( |\t)( *\t*[^ \t\n]+ *\t*)+(\n|$)(( |\t)[^\n]+(\n|$)|[ \t]*(\n|$))*/) ) {
- len = RLENGTH; st = RSTART;
- code = substr(block, 1, len);
- gsub(/(^|\n)( |\t)/, "\n", code);
- gsub(/^\n|\n+$/, "", code);
- return "<pre><code>" HTML( code ) "</code></pre>\n" \
- _block( substr( block, len + 1 ) );
-
- # Fenced Divs (pandoc, custom)
- } 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);
- gsub(/[^a-zA-Z0-9_-]+/, " ", attrib);
- gsub(/(^ | $)/, "", attrib);
- if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) {
+ ttext = ttext "<tr>"
+ for (cnt = 1; cnt <= cols; cnt++)
+ ttext = ttext "<td align=\"" talign[cnt] "\">" _nblock(tarray[cnt]) "</td>"
+ ttext = ttext "</tr>\n"
+ }
+ return ret "<table>" ttext "</tbody></table>\n" _nblock(block);
+
+ # Line Blocks (pandoc)
+ } else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\n]*(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) {
len = RLENGTH; st = RSTART;
- return "<div class=\"" attrib "\">" _block( substr(code, 1, st - 1) ) "</div>\n" \
- _block( substr( code, st + len ) );
- } else {
- match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ );
+
+ text = substr(block, 1, len); gsub(/\n[[:space:]]+/, " ", text);
+ gsub(/\n\| /, "\n", text); gsub(/^\| |\n$/, "", text);
+ text = inline(text); gsub(/\n/, "<br>\n", text);
+
+ ret = ret "<div class=\"line-block\">" text "</div>\n"; block = substr( block, len + 1);
+ continue;
+
+ # Indented Code Block
+ } else if ( match(block, /^(( |\t)[^\n]*[^\n\t ][^\n]*(\n|$))(( |\t)[^\n]*(\n|$)|[\t ]*(\n|$))*/) ) {
len = RLENGTH; st = RSTART;
- return "<p>" inline( substr(block, 1, st - 1) ) "</p>\n" \
- _block( substr(block, st + len) );
- }
- # Fenced Code Block (pandoc)
- } else if ( match( block, /^(~~~+|```+)/ ) ) {
- guard = substr( block, 1, RLENGTH );
- code = gensub(/^[^\n]+\n/, "", 1, block);
- attrib = gensub(/^(~~~+|```+)[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\2", 1, block);
- gsub(/[^a-zA-Z0-9_-]+/, " ", attrib);
- gsub(/(^ | $)/, "", attrib);
- if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) {
+ code = substr(block, 1, len);
+ gsub(/(^|\n)( |\t)/, "\n", code);
+ gsub(/^\n|\n+$/, "", code);
+ ret = ret "<pre><code>" HTML( code ) "</code></pre>\n"; block = substr( block, len + 1 );
+ continue;
+
+ # Fenced Divs (pandoc, custom)
+ } else if ( match( block, /^(:::+)/ ) ) {
+ guard = substr( block, 1, RLENGTH ); attrib = code = block;
+ sub(/^[^\n]+\n/, "", code);
+ sub(/^:::+[ \t]*\{?[ \t]*/, "", attrib); sub(/\}?[ \t]*\n.*$/, "", attrib);
+ # attrib = gensub(/^:::+[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\1", 1, attrib);
+ gsub(/[^a-zA-Z0-9_-]+/, " ", attrib);
+ gsub(/(^ | $)/, "", attrib);
+ if ( match(code, "(^|\n)" guard "+(\n|$)" ) && attrib ) {
+ len = RLENGTH; st = RSTART;
+ ret = ret "<div class=\"" attrib "\">" _nblock( substr(code, 1, st - 1) ) "</div>\n";
+ block = substr( code, st + len );
+ continue;
+
+ } else if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) {
+ len = RLENGTH; st = RSTART;
+ ret = ret "<div>" _nblock( substr(code, 1, st - 1) ) "</div>\n"; block = substr( code, st + len );
+ continue;
+
+ } else {
+ match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ );
+ len = RLENGTH; st = RSTART;
+ ret = ret "<p>" inline( substr(block, 1, st - 1) ) "</p>\n"; block = substr(block, st + len);
+ continue;
+ }
+
+ # Fenced Code Block (pandoc)
+ } else if ( match( block, /^(~~~+|```+)/ ) ) {
+ guard = substr( block, 1, RLENGTH ); attrib = code = block;
+ sub(/^[^\n]+\n/, "", code);
+ sub(/^(~~~+|```+)[ \t]*\{?[ \t]*/, "", attrib); sub(/\}?[ \t]*\n.*$/, "", attrib);
+ # attrib = gensub(/^(~~~+|```+)[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\2", 1, attrib);
+ gsub(/[^a-zA-Z0-9_-]+/, " ", attrib);
+ gsub(/(^ | $)/, "", attrib);
+ if ( match(code, "(^|\n)" guard "+(\n|$)" ) && attrib ) {
+ len = RLENGTH; st = RSTART;
+ ret = ret "<pre><code class=\"" attrib "\">" HTML( substr(code, 1, st - 1) ) "</code></pre>\n";
+ block = substr( code, st + len );
+ continue;
+
+ } else if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) {
+ len = RLENGTH; st = RSTART;
+ ret = ret "<pre><code>" HTML( substr(code, 1, st - 1) ) "</code></pre>\n";
+ block = substr( code, st + len );
+ continue;
+
+ } else {
+ match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ );
+ len = RLENGTH; st = RSTART;
+ ret = ret "<p>" inline( substr(block, 1, st - 1) ) "</p>\n"; block = substr(block, st + len);
+ continue;
+ }
+
+ # First Order Heading H1 + Attrib
+ } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n===+(\n|$)/ ) ) {
+ 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(/(^ | $)/, "", attrib);
+
+ ret = ret headline(1, text, attrib) ; block = substr( block, len + 1 );
+ continue;
+
+ # First Order Heading H1
+ } else if ( match( block, /^([^\n]+)\n===+(\n|$)/ ) ) {
+ len = RLENGTH; text = substr(block, 1, len);
+ sub(/\n===+(\n.*)?$/, "", text);
+
+ ret = ret headline(1, text, 0) ; block = substr( block, len + 1 );
+ continue;
+
+ # Second Order Heading H2 + Attrib
+ } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n---+(\n|$)/ ) ) {
+ 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(/(^ | $)/, "", attrib);
+
+ ret = ret headline(2, text, attrib) ; block = substr( block, len + 1);
+ continue;
+
+ # Second Order Heading H2
+ } else if ( match( block, /^([^\n]+)\n---+(\n|$)/ ) ) {
+ len = RLENGTH; text = substr(block, 1, len);
+ sub(/\n---+(\n.*)?$/, "", text);
+
+ ret = ret headline(2, text, 0) ; block = substr( block, len + 1);
+ continue;
+
+ # # Nth Order Heading H1 H2 H3 H4 H5 H6 + Attrib
+ # } else if ( match( block, /^(##?#?#?#?#?)[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*[ \t]*\{[a-zA-Z \t-]*\}(\n|$)/ ) ) {
+ } else if ( match( block, /^##?#?#?#?#?[^#\n]([^\n#]|#[^\t\n# ]|#[\t ]+[^\t\n ])+#*[\t ]*\{[\ta-zA-Z -]*\}(\n|$)/ ) ) {
+ len = RLENGTH; text = attrib = substr(block, 1, len);
+ match(block, /^##?#?#?#?#?[^#]/); n = RLENGTH - 1;
+ # sub(/^(##?#?#?#?#?)[ \t]*/, "", text); # not working in mawk
+ text = substr(text, n + 1); sub(/^[ \t]*/, "", text);
+ sub(/[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n.*)?$/, "", text);
+
+ sub(/^##?#?#?#?#?[^#\n]([^\n#]|#[^\t\n# ]|#[\t ]+[^\t\n ])+#*[\t ]*\{/, "", attrib);
+ sub(/\}(\n.*)?$/, "", attrib);
+ gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib);
+
+ ret = ret headline( n, text, attrib ); block = substr( block, len + 1);
+ continue;
+
+ # Nth Order Heading H1 H2 H3 H4 H5 H6
+ # } else if ( match( block, /^(##?#?#?#?#?)[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n|$)/ ) ) {
+ } else if ( match( block, /^##?#?#?#?#?[^#\n]([^\n#]|#[^\t\n# ]|#[\t ]+[^\t\n ])+#*(\n|$)/ ) ) {
+ len = RLENGTH; text = substr(block, 1, len);
+ match(block, /^##?#?#?#?#?[^#]/); n = RLENGTH - 1;
+ # sub(/^(##?#?#?#?#?)[ \t]+/, "", text); # not working in mawk
+ text = substr(text, n + 1); sub(/^[ \t]*/, "", text);
+ sub(/[ \t]*#*(\n.*)?$/, "", text);
+
+ ret = ret headline( n, text, 0 ) ; block = substr( block, len + 1);
+ continue;
+
+ # block images (wrapped in <figure>)
+ } else if ( match(block, "^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n|$)") ) {
+ len = RLENGTH; text = href = title = attrib = substr( block, 1, len);
+
+ sub("^!\\[", "", text);
+ sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", text);
+
+ sub("^!" lix "\\([\n\t ]*", "", href);
+ sub("([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", href);
+
+ sub("^!" lix "\\([\n\t ]*" lid, "", title);
+ sub("[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", title);
+ sub("^[\n\t ]+", "", title);
+
+ sub("^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)", "", attrib);
+ sub("(\n.*)?$", "", attrib);
+ sub(/^\{[ \t]*/, "", attrib); sub(/[ \t]*\}$/, "", attrib); gsub(/[ \t]+/, " ", attrib);
+
+ if ( match(href, /^<.*>$/) ) { sub(/^</, "", href); sub(/>$/, "", href); }
+ if ( match(title, /^".*"$/) ) { sub(/^"/, "", title); sub(/"$/, "", title); }
+ else if ( match(title, /^'.*'$/) ) { sub(/^'/, "", title); sub(/'$/, "", title); }
+ else if ( match(title, /^\(.*\)$/) ) { sub(/^\(/, "", title); sub(/\)$/, "", title); }
+
+ gsub(/^[\t ]+$/, "", text); gsub(/\\/, "", href);
+
+ ret = ret "<figure data-src=\"" HTML(href) "\"" (attrib?" class=\"" HTML(attrib) "\"":"") ">" \
+ "<img src=\"" HTML(href) "\" alt=\"" HTML(text?text:title?title:href) "\"" \
+ (attrib?" class=\"" HTML(attrib) "\"":"") ">" \
+ (title?"<figcaption>" inline(title) "</figcaption>":"") \
+ "</figure>\n\n";
+ block = substr( block, len + 1);
+ continue;
+
+ } else if ( match(block, /^!\[([^]]*)\] ?\[([^]]*)\](\n|$)/ ) ) {
+ len = RLENGTH; text = id = block;
+ sub(/(\n.*)?$/, "", text); sub( /^!\[/, "", text); sub(/\] ?\[([^\n]*)\]$/, "", text);
+ sub(/(\n.*)?$/, "", id); sub( /^!\[([^\n]*)\] ?\[/, "", id); sub(/\]$/, "", id);
+ # text = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\](\n.*)?$/, "\\1", 1, block);
+ # id = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\](\n.*)?$/, "\\2", 1, block);
+ if ( ! id ) id = text;
+ if ( rl_href[id] && rl_title[id] ) {
+ ret = ret "<figure data-src=\"" HTML(rl_href[id]) "\">" \
+ "<img src=\"" HTML(rl_href[id]) "\" alt=\"" HTML(text) "\">" \
+ "<figcaption>" inline(rl_title[id]) "</figcaption>" \
+ "</figure>\n\n";
+ block = substr( block, len + 1);
+ continue;
+
+ } else if ( rl_href[id] ) {
+ ret = ret "<figure data-src=\"" HTML(rl_href[id]) "\">" \
+ "<img src=\"" HTML(rl_href[id]) "\" alt=\"" HTML(text) "\">" \
+ "</figure>\n\n";
+ block = substr( block, len + 1);
+ continue;
+ } else {
+ ret = ret "<p>" HTML(substr(block, 1, len)) "</p>\n" ; block = substr(block, len + 1);
+ continue;
+ }
+
+ # Macros (standalone <<macro>> calls handled as block, so they are not wrapped in paragraph)
+ } else if ( match( block, /^<<(([^>]|>[^>])+)>>(\n|$)/ ) ) {
+ len = RLENGTH; text = block;
+ sub(/^<</, "", text); sub(/>>(\n.*)?$/, "", text);
+ # text = gensub(/^<<(([^>]|>[^>])+)>>(\n.*)?$/, "\\1", 1, block);
+ ret = ret "<code class=\"macro\">" HTML(text) "</code>" ; block = substr(block, len + 1);
+ continue;
+
+ # 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|$))*)+" \
+ )) {
+ list = substr( block, 1, RLENGTH); block = substr( block, RLENGTH + 1);
+ ret = ret "<dl>\n" _dlist( list ) "</dl>\n";
+ continue;
+
+ # Unordered list types
+ } else if ( text = _startlist( block, "ul", "-", "([+*•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) {
+ return ret text;
+ } else if ( text = _startlist( block, "ul", "\\+", "([-*•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) {
+ return ret text;
+ } else if ( text = _startlist( block, "ul", "\\*", "([-+•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) {
+ return ret text;
+ } else if ( text = _startlist( block, "ul", "•", "([-+*]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) {
+ return ret text;
+
+ # Ordered list types
+ } else if ( text = _startlist( block, "ol", "[0-9]+\\.", "([-+*•]|#\\.|[0-9]+\\)|#\\))") ) {
+ return ret text;
+ } else if ( text = _startlist( block, "ol", "[0-9]+\\)", "([-+*•]|[0-9]+\\.|#\\.|#\\))") ) {
+ return ret text;
+ } else if ( text = _startlist( block, "ol", "#\\.", "([-+*•]|[0-9]+\\.|[0-9]+\\)|#\\))") ) {
+ return ret text;
+ } else if ( text = _startlist( block, "ol", "#\\)", "([-+*•]|[0-9]+\\.|#\\.|[0-9]+\\))") ) {
+ return ret text;
+
+ # Split paragraphs
+ } else if ( match( block, /(^|\n)[[:space:]]*(\n|$)/) ) {
len = RLENGTH; st = RSTART;
- return "<pre><code class=\"" attrib "\">" HTML( substr(code, 1, st - 1) ) "</code></pre>\n" \
- _block( substr( code, st + len ) );
- } else {
- match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ );
+ ret = ret _block( substr(block, 1, st - 1) ) "\n"; block = substr(block, st + len);
+ continue;
+
+ # Horizontal rule
+ # } else if ( match( block, /(^|\n) ? ? ?((\* *){3,}|(- *){3,}|(_ *){3,})($|\n)/) ) {
+ } else if ( match( block, /(^|\n) ? ? ?((\* *)(\* *)(\* *)(\* *)*|(- *)(- *)(- *)(- *)*|(_ *)(_ *)(_ *)(_ *)*)($|\n)/) ) {
len = RLENGTH; st = RSTART;
- return "<p>" inline( substr(block, 1, st - 1) ) "</p>\n" \
- _block( substr(block, st + len) );
- }
+ ret = ret _block(substr(block, 1, st - 1)) "<hr>\n"; block = substr(block, st + len);
+ continue;
- # 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) );
-
- gsub("(^|\n) {0," indent "}", "\n", list);
- return "\n<ol>\n" _list( substr(list, 2) ) "</ol>\n" _block( block );
-
- # First Order Heading
- } else if ( match( block, /^[^\n]+\n===+(\n|$)/ ) ) {
- len = RLENGTH;
- HL[1]++; HL[2] = 0; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
- return "<h1 id=\"" HL[1] " - " HTML(gensub( /\n.*$/, "", "g", block )) "\">" \
- inline( gensub( /\n.*$/, "", "g", block ) ) \
- "<a class=\"anchor\" href=\"#" HL[1] " - " \
- HTML(gensub( /\n.*$/, "", "g", block )) "\"></a></h1>\n\n" \
- _block( substr( block, len + 1 ) );
-
- # Second Order Heading
- } else if ( match( block, /^[^\n]+\n---+(\n|$)/ ) ) {
- len = RLENGTH;
- HL[2]++; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
- return "<h2 id=\"" HL[1] "." HL[2] " - " HTML(gensub( /\n.*$/, "", "g", block )) "\">" \
- inline( gensub( /\n.*$/, "", "g", block ) ) \
- "<a class=\"anchor\" href=\"#" HL[1] "." HL[2] " - " \
- HTML(gensub( /\n.*$/, "", "g", block )) "\"></a></h2>\n\n" \
- _block( substr( block, len + 1) );
-
- # Nth Order Heading
- } 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.*)?$/, "\\1", 1, block);
- HL[hlvl]++; for ( n = hlvl + 1; n < 7; n++) { HL[n] = 0;}
- hid = HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; }
- return "<h" hlvl " id=\"" hid " - " HTML(htxt) "\">" inline( htxt ) \
- "<a class=\"anchor\" href=\"#" hid "\"></a></h" hlvl ">\n\n" \
- _block( substr( block, len + 1) );
-
- # Split paragraphs
- } else if ( match( block, /(^|\n)[[:space:]]*(\n|$)/) ) {
- len = RLENGTH; st = RSTART;
- return _block( substr(block, 1, st - 1) ) "\n" \
- _block( substr(block, st + len) );
-
- # Horizontal rule
- } else if ( match( block, /(^|\n) ? ? ?((\* *){3,}|(- *){3,}|(_ *){3,})($|\n)/) ) {
- len = RLENGTH; st = RSTART;
- return _block(substr(block, 1, st - 1)) "<hr />\n" _block(substr(block, st + len));
-
- # Plain paragraph
- } else {
- return "<p>" inline(block) "</p>\n";
+ } # block patterns end
+
+ # Plain paragraph
+ return ret "<p>" inline(block) "</p>\n";
}
+ return ret;
}
-function _list( block, last, LOCAL, p) {
- if ( ! length(block) ) return "";
- gsub(/^([-+*]|[0-9]+\.|#\.)( ? ? ?|\t)/, "", block)
+function _startlist(block, type, mark, exclude, LOCAL, st, len, list, indent, it, text) {
+ if (match( block, "(^|\n) ? ? ?" mark "[ \t][^\n]+(\n|$)" \
+ "(([ \t]*\n)* ? ? ?" mark "[ \t][^\n]+(\n|$)" \
+ "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \
+ "|[^\n \t][^\n]+(\n|$))*" ) ) {
+ st = RSTART; len = RLENGTH; list = substr( block, st, len);
+
+ sub("^\n", "", list); match(list, "^( | | )?"); indent = RLENGTH;
+ # gsub( "(^|\n) {0," indent "}", "\n", list); sub("^\n", "", list);
+ # emulate greedy range matcher for mawk
+ it = "("; while ( indent > 0 ) { for (k = indent; k > 0; k--) { it = it " "; } it = it "|"; indent--; }
+ sub(/\|$/, ")?", it); sub(/^\($/, "", it);
+ gsub( "(^|\n)" it, "\n", list ); sub("^\n", "", list);
+
+ text = substr(block, 1, st - 1); block = substr(block, st + len);
+ if (match(text, /\n[[:space:]]*\n/)) return 0;
+ if (match(text, "(^|\n) ? ? ?" exclude "[ \t][^\n]+")) return 0;
+ if (match( list, "\n" exclude "[ \t]" )) {
+ block = substr(list, RSTART + 1) block;
+ list = substr(list, 1, RSTART);
+ }
- # slice next list item from input
- if ( match( block, /\n([-+*]|[0-9]+\.|#\.)[ \t]+[^\n]+/) ) {
- p = substr( block, 1, RSTART);
- block = substr( block, RSTART + 1);
- } else {
- p = block; block = "";
- }
- sub( /\n +([-+*]|[0-9]+\.|#\.)/, "\n&", p );
-
- # if this should be a paragraph item
- # either previous item (last) or current item (p) contains blank lines
- if (match(last, /\n[[:space:]]*\n/) || match(p, /\n[[:space:]]*\n/) ) {
- last = p; p = _block(p);
- } else {
- last = p; p = _block(p);
- sub( /^<p>/, "", p );
- sub( /<\/p>\n/, "", p );
+ return _block( text ) "<" type ">\n" _list( list, mark ) "</" type ">\n" _block( block );
+ } else return 0;
+}
+
+function _list (block, mark, p, LOCAL, len, st, text, indent, it, task) {
+ if ( match(block, "^([ \t]*\n)*$")) 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|$)" );
+ st = (RLENGTH == -1) ? length(block) + 1 : RSTART;
+ text = substr(block, 1, st); block = substr(block, st + 1);
+
+ # gsub("\n {0," indent "}", "\n", text);
+ # emulate greedy range matcher for mawk
+ it = "("; while ( indent > 0 ) { for (k = indent; k > 0; k--) { it = it " "; } it = it "|"; indent--; }
+ sub(/\|$/, ")?", it); sub(/^\($/, "", it);
+ gsub("\n" it, "\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 ( ! p && match( text, "^<p>(</p[^>]|</[^p]|<[^/]|[^<])*</p>\n$" ))
+ gsub( "(^<p>|</p>\n$)", "", text);
+
+ return task text "</li>\n" _list(block, mark, p);
+}
+
+function _dlist (block, LOCAL, len, st, text, indent, it, 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|$))*" \
+ )) {
+ len = RLENGTH; text = substr(block, 1, len);
+ sub( "^([ \t]*\n)*", "", text);
+ match(text, "^ ? ? ?:(\t| +)"); indent = RLENGTH;
+ sub( "^ ? ? ?:(\t| +)", "", text);
+ # gsub( "(^|\n) {0," indent "}", "\n", text );
+ # emulate greedy range matcher for mawk
+ it = "("; while ( indent > 0 ) { for (k = indent; k > 0; k--) { it = it " "; } it = it "|"; indent--; }
+ sub(/\|$/, ")?", it); sub(/^\($/, "", it);
+ gsub( "(^|\n)" it, "\n", text );
+
+ text = _nblock(text);
+ if (match( text, "^<p>(</p[^>]|</[^p]|<[^/]|[^<])*</p>\n$" ))
+ 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 {
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";
+
+ # Universal Patterns
+ nu = "([^_\\\\]|\\\\.|_[[:alnum:]])" # not underline (except when escaped, or inside a word)
+ na = "([^*\\\\]|\\\\.)" # not asterisk (except when escaped)
+ ieu = "_([^_[:space:]]|[^_[:space:]]" nu "*[^_[:space:]])_" # inner <em> (underline)
+ isu = "__([^_[:space:]]|[^_[:space:]]" nu "*[^_[:space:]])__" # inner <strong> (underline)
+ iea = "\\*([^*[:space:]]|[^*[:space:]]" na "*[^*[:space:]])\\*" # inner <em> (asterisk)
+ isa = "\\*\\*([^*[:space:]]|[^*[:space:]]" na "*[^*[:space:]])\\*\\*" # inner <strong> (asterisk)
+
+ lix="\\[(\\\\[^\n]|[^]\n\\\\[])*\\]" # link text
+ lid="(<(\\\\[^\n]|[^\n<>\\\\])*>|(\\\\.|[^()\"'\\\\])+|([^<\n\t ()\\\\]|\\\\[^\n])(\\\\[\n]|[^\n\t \\(\\)\\\\])*)" # link dest
+ lit="(\"(\\\\.|[^\"\\\\])*\"|'(\\\\.|[^'\\\\])*'|\\((\\\\.|[^\\(\\)\\\\])*\\))" # link text
+ # link text with image def
+ lii="\\[(\\\\[^\n]|[^]\n\\\\[])*(!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\))?(\\\\[^\n]|[^]\n\\\\[])*\\]"
# Buffering of full file ist necessary, e.g. to find reference links
while (getline) { file = file $0 "\n"; }
re_reflink = "(^|\n) ? ? ?\\[([^]\n]+)\\]: ([^ \t\n]+)(\n?[ \t]+(\"([^\"]+)\"|'([^']+)'|\\(([^)]+)\\)))?(\n|$)";
# /(^|\n) ? ? ?\[([^]\n]+)\]: ([^ \t\n]+)(\n?[ \t]+("([^"]+)"|'([^']+)'|\(([^)]+)\)))?(\n|$)/
while ( match(f, re_reflink ) ) {
- rl_id = gensub( re_reflink, "\\2", 1, substr(f, RSTART, RLENGTH) );
- rl_href[rl_id] = gensub( re_reflink, "\\3", 1, substr(f, RSTART, RLENGTH) );
- rl_title[rl_id] = gensub( re_reflink, "\\5", 1, substr(f, RSTART, RLENGTH) );
- f = substr(f, RSTART + RLENGTH);
+ tt = th = ti = substr(f, RSTART, RLENGTH); f = substr(f, RSTART + RLENGTH);
+ sub("(^|\n) ? ? ?\\[", "", ti); sub("\\]: ([^ \t\n]+)(\n?[ \t]+(\"([^\"]+)\"|'([^']+)'|\\(([^)]+)\\)))?(\n.*)?$", "", ti);
+ sub("(^|\n) ? ? ?\\[([^]\n]+)\\]: ", "", th); sub("(\n?[ \t]+(\"([^\"]+)\"|'([^']+)'|\\(([^)]+)\\)))?(\n.*)?$", "", th);
+ if (match(tt, "(^|\n) ? ? ?\\[([^]\n]+)\\]: ([^ \t\n]+)(\n?[ \t]+(\"([^\"]+)\"|'([^']+)'|\\(([^)]+)\\)))(\n|$)")) {
+ sub("(^|\n) ? ? ?\\[([^]\n]+)\\]: ([^ \t\n]+)", "", tt); sub("^\n?[ \t]+", "", tt); sub("(\n.*)?$", "", tt);
+ } else { tt = ""; }
+ rl_id = ti; rl_href[rl_id] = th; rl_title[rl_id] = tt;
+ # rl_id = gensub( re_reflink, "\\2", 1, substr(f, RSTART, RLENGTH) );
+ # rl_href[rl_id] = gensub( re_reflink, "\\3", 1, substr(f, RSTART, RLENGTH) );
+ # rl_title[rl_id] = gensub( re_reflink, "\\5", 1, substr(f, RSTART, RLENGTH) );
+ # f = substr(f, RSTART + RLENGTH);
rl_title[rl_id] = substr( rl_title[rl_id], 2, length(rl_title[rl_id]) - 2 );
if ( rl_href[rl_id] ~ /<.*>/ ) rl_href[rl_id] = substr( rl_href[rl_id], 2, length(rl_href[rl_id]) - 2 );
}
# for (n in rl_href) { debug(n " | " rl_href[n] " | " rl_title[n] ); }
# Run Block Processing -> The Actual Markdown!
- printf "%s", _block( file );
+ printf "%s", _nblock( file );
}
--- /dev/null
+#!/bin/sh
+
+runtimes="gawk busybox mawk goawk"
+
+BR='
+'
+CR="$(printf \r)"
+fail() { printf '%s\n' "$@"; exit 1; }
+
+awk() { /bin/awk "$@"; }
+md_gawk() { gawk -f markdown.awk "$@"; }
+md_busybox() { busybox awk -f markdown.awk "$@"; }
+md_mawk() { mawk -f markdown.awk "$@"; }
+md_goawk() { goawk -f markdown.awk "$@"; }
+
+acnt=1 # assertion count
+assert() {
+ local md comp="$2" msg="$3" ex
+ printf "%3i: %s ... " $acnt "$msg"
+
+ for proc in $runtimes; do
+ printf '%s ' $proc
+ md="$(printf '%s' "$1" |md_"$proc")"; ex=$?
+ if [ "$ex" != 0 ]; then
+ printf "Fail!\nExit Code: %i\n" $ex
+ exit 1
+ fi
+ if [ "$md" != "$comp" ]; then
+ printf "Fail!\n:\n%s\n:\n%s\n" "$md" "$comp"
+ exit 1
+ fi
+ done
+ printf 'OK\n'
+ acnt=$((acnt + 1))
+}
+
+# Inline checks
+printf '## Testing Inline markup ##\n'
+
+# strong / em / ...
+assert '~~strikeout~~' '<p><del>strikeout</del></p>' "strikeout"
+assert '~~~strikeout~~' '<p><del>~strikeout</del></p>' "strikeout"
+assert '^super^' '<p><sup>super</sup></p>' "superscript"
+assert '~sub~' '<p><sub>sub</sub></p>' "subscript"
+
+assert "foo ${BR}bar" "<p>foo<br>${BR}bar</p>" 'double space line break'
+assert '```©```' "<p><code>&copy;</code></p>" "code span escape"
+assert '````' "<pre><code>````</code></pre>" "empty code span"
+
+assert '_emphasized text_' '<p><em>emphasized text</em></p>' "em"
+assert '_emphasized_text_' '<p><em>emphasized_text</em></p>' "em"
+assert 'empha*sized* text_' '<p>empha<em>sized</em> text_</p>' "em"
+assert '__empha*sized* text__' '<p><strong>empha<em>sized</em> text</strong></p>' "strong em"
+assert '***strem***' '<p><strong><em>strem</em></strong></p>' "strong em"
+assert '***str**em*' '<p><em><strong>str</strong>em</em></p>' "em strong"
+assert '_**strem**_' '<p><em><strong>strem</strong></em></p>' "em strong"
+
+assert '*foo**str**bar**str**qua*' '<p><em>foo<strong>str</strong>bar<strong>str</strong>qua</em></p>' 'em strong asterisk'
+assert '**foo*em*bar*em*qua**' '<p><strong>foo<em>em</em>bar<em>em</em>qua</strong></p>' 'strong em asterisk'
+
+assert '_foo__str__bar__str__qua_' '<p><em>foo__str__bar__str__qua</em></p>' 'em embedded underscore'
+assert '__foo_em_bar_em_qua__' '<p><strong>foo_em_bar_em_qua</strong></p>' 'strong embedded underscore'
+assert '_**str**foo**str**_' '<p><em><strong>str</strong>foo<strong>str</strong></em></p>' 'em strong mixed'
+
+assert '_foo_-> bar' '<p><em>foo</em>→ bar</p>' 'arrow'
+assert '`_foo_-> bar`' '<p><code>_foo_-> bar</code></p>' 'arrow'
+assert '<!-- comment --> <- comment' '<p><!-- comment --> ← comment</p>' 'arrow'
+
+# Escaping
+assert '©' "<p>©</p>" "escape"
+assert '\©' "<p>&copy;</p>" "escape"
+assert 'AT&T' "<p>AT&T</p>" "escape"
+assert '`©`' "<p><code>&copy;</code></p>" "code span escape"
+
+# Wiki Links
+assert '[[Link/]]' '<p><a href="Link/">Link/</a></p>' "Wiki Link"
+assert '[[Link/|Linked Page]]' '<p><a href="Link/">Linked Page</a></p>' "Wiki Link"
+
+# Automatic Links
+assert '<https://de.wikipedia.org>' "<p><a href=\"https://de.wikipedia.org\">https://de.wikipedia.org</a></p>" "automatic link"
+assert '<http://de.wikipedia.org>' "<p><a href=\"http://de.wikipedia.org\">http://de.wikipedia.org</a></p>" "automatic link"
+# assert '<//de.wikipedia.org>' "<p><a href=\"//de.wikipedia.org\">http://de.wikipedia.org</a></p>" "automatic link"
+
+assert '<hello&goodbye@sub-test.example.com>' "<p><a href=\"mailto:hello&goodbye@sub-test.example.com\">hello&goodbye@sub-test.example.com</a></p>" "automatic link, email"
+# assert '<hällö&guttbei@sub-test.example.com>' "<p><a href=\"mailto:hällö&guttbei@sub-test.example.com\">hällö&guttbei@sub-test.example.com</a></p>" "automatic link, email"
+
+# Inline Links
+assert '[Wikipedia](http://de.wikipedia.org)' "<p><a href=\"http://de.wikipedia.org\">Wikipedia</a></p>" "inline link"
+assert '[Wikipedia](http://de.wikipedia.org "Online Encyclopedia")' "<p><a href=\"http://de.wikipedia.org\" title=\"Online Encyclopedia\">Wikipedia</a></p>" "inline link"
+assert '[Wikipedia](<http://de.wikipedia.org> "Online Encyclopedia")' "<p><a href=\"http://de.wikipedia.org\" title=\"Online Encyclopedia\">Wikipedia</a></p>" "inline link"
+
+# Inline Images (note leading white space)
+assert ' ' '<p> <img src="Test Bild.jpg" alt="Testbild"></p>' "inline image"
+assert ' ' '<p> <img src="Test Bild.jpg" alt="Testbild" title="German Television *test* image ca. 1994"></p>' "inline image"
+assert ' {tv ard function-check}' '<p> <img src="Test Bild.jpg" alt="Testbild *ARD*" class="tv ard function-check"></p>' "inline image"
+# assert ' {#tv .ard .function-check}' '<p> <img src="Test Bild.jpg" alt="Testbild *ARD*" class="tv ard check"></p>' "inline image id/classes"
+
+assert '[](<http://de.wikipedia.org>)'\
+ '<p><a href="http://de.wikipedia.org"><img src="wikilogo.png" alt="Wikipedia"></a></p>'\
+ "Image Link"
+
+assert ' <<macro /test -- "* weird <args>" _foo_>>' '<p> <code class="macro">macro /test -- "* weird <args>" _foo_</code></p>' "Macros"
+
+# Block checks
+printf '\n## Testing Block markup ##\n'
+
+assert \
+'foo
+
+bar' \
+'<p>foo</p>
+
+<p>bar</p>' \
+'paragraphs'
+
+assert '%meta *data block*
+ ignored `no` __formatting__
+regular *data*' \
+'<p>regular <em>data</em></p>' \
+"meta data block"
+
+assert '> text in a block
+> quote can be *emphasized*
+and quotes continued
+
+until they end' \
+'<blockquote><p>text in a block
+quote can be <em>emphasized</em>
+and quotes continued</p></blockquote>
+
+<p>until they end</p>' \
+'block quote'
+
+assert '| text in a line
+| block can be *emphasized*
+but not continued
+
+until they end' \
+'<div class="line-block">text in a line<br>
+block can be <em>emphasized</em></div>
+<p>but not continued</p>
+
+<p>until they end</p>' \
+'pandoc line block'
+
+assert ' indented code will
+ not be
+ *formatted*
+ but ­ <escaped>' \
+'<pre><code>indented code will
+not be
+*formatted*
+but &shy; <escaped></code></pre>' \
+"indented code block"
+
+assert ' indented code will
+ not be
+
+ *formatted*
+ but ­ <escaped>' \
+'<pre><code>indented code will
+not be
+
+*formatted*
+but &shy; <escaped></code></pre>' \
+"indented code block"
+
+assert ':::: tag
+fenced _divs_ are regular text
+
+:::
+and can contain another div
+:::
+::::' \
+'<div class="tag"><p>fenced <em>divs</em> are regular text</p>
+
+<div><p>and can contain another div</p>
+</div>
+</div>' \
+"pandoc fenced divs"
+
+assert '``` tag,code
+fenced code will
+not be
+*formatted*
+but ­ <escaped>
+```' \
+'<pre><code class="tag code">fenced code will
+not be
+*formatted*
+but &shy; <escaped></code></pre>' \
+"fenced code block"
+
+assert 'foobar
+````
+foobar' \
+'<p>foobar
+````
+foobar</p>' \
+"Open Fence"
+
+# Block Images
+assert '' \
+'<figure data-src="Test Bild.jpg"><img src="Test Bild.jpg" alt="Testbild"></figure>' \
+"block image"
+
+assert '' \
+'<figure data-src="Test Bild.jpg"><img src="Test Bild.jpg" alt="Testbild"><figcaption>German Television <em>test</em> image ca. 1994</figcaption></figure>' \
+"block image"
+
+assert '{tv ard function-check}' \
+'<figure data-src="Test Bild.jpg" class="tv ard function-check"><img src="Test Bild.jpg" alt="Testbild *ARD*" class="tv ard function-check"></figure>' \
+"block image tagged"
+
+# assert '{#tv .ard .function-check}' \
+# '<figure data-src="Test Bild.jpg" class="tv ard function-check"><img src="Test Bild.jpg" alt="Testbild *ARD*" class="tv ard function-check"></figure>' \
+# "block image tagged"
+
+# Headings
+assert 'Heading first Order
+============' \
+'<section class="h1" id="1:Heading%20first%20Order"><h1>Heading first Order<a class="anchor" href="#1:Heading%20first%20Order"></a></h1>
+</section>' \
+'Heading h1'
+
+assert 'Heading first Order {.foo #bar}
+============' \
+'<section class="h1 foo bar" id="1:Heading%20first%20Order"><h1 class="foo bar">Heading first Order<a class="anchor" href="#1:Heading%20first%20Order"></a></h1>
+</section>' \
+'Heading h1 + attributes'
+
+assert 'Heading second Order
+------------' \
+'<section class="h2" id="0.1:Heading%20second%20Order"><h2>Heading second Order<a class="anchor" href="#0.1:Heading%20second%20Order"></a></h2>
+</section>' \
+'Heading h2'
+
+assert 'Heading second Order {.foo #bar}
+------------' \
+'<section class="h2 foo bar" id="0.1:Heading%20second%20Order"><h2 class="foo bar">Heading second Order<a class="anchor" href="#0.1:Heading%20second%20Order"></a></h2>
+</section>' \
+'Heading h2 + attributes'
+
+assert '#### Heading four' \
+'<section class="h4" id="0.0.0.1:Heading%20four"><h4>Heading four<a class="anchor" href="#0.0.0.1:Heading%20four"></a></h4>
+</section>' \
+'Heading arbitrary'
+
+assert '###Heading three ######' \
+'<section class="h3" id="0.0.1:Heading%20three"><h3>Heading three<a class="anchor" href="#0.0.1:Heading%20three"></a></h3>
+</section>' \
+'Heading arbitrary'
+
+assert '### Heading three ## {foo bar}' \
+'<section class="h3 foo bar" id="0.0.1:Heading%20three"><h3 class="foo bar">Heading three<a class="anchor" href="#0.0.1:Heading%20three"></a></h3>
+</section>' \
+'Heading arbitrary + attributes'
+
+assert '# Heading \# # {foo bar}' \
+'<section class="h1 foo bar" id="1:Heading%20%5C%23"><h1 class="foo bar">Heading #<a class="anchor" href="#1:Heading%20%5C%23"></a></h1>
+</section>' \
+'Heading arbitrary + attributes'
+
+assert 'Definition
+: term
+with line continuation
+
+: second term
+
+foo
+: bar' \
+'<dl>
+<dt>Definition</dt>
+<dd>term
+with line continuation</dd>
+<dd>second term</dd>
+<dt>foo</dt>
+<dd>bar</dd>
+</dl>' \
+'Definition List'
+
+assert ' * list
+* item
+ 1. sub list
+* three
+- new list' \
+'<ul>
+<li>list</li>
+<li><p>item</p>
+<ol>
+<li>sub list</li>
+</ol>
+</li>
+<li>three</li>
+</ul>
+<ul>
+<li>new list</li>
+</ul>' \
+'Lists'
+
+assert '::: outer div
+Nesting paragraph
+
+-------
+
+> ```
+> quoted code
+> ```
+>
+> > quoted quote
+:::
+' \
+'<div class="outer div"><p>Nesting paragraph</p>
+
+<hr>
+
+<blockquote><pre><code>quoted code</code></pre>
+<blockquote><p>quoted quote</p></blockquote>
+</blockquote>
+
+</div>' \
+"Nesting"
+
+assert '
+| Col 1 | Col 2| Col 3 |
+|-------|-------|------:|
+| foo | *bar* | `qua` |
+| 23 | 47 | 11 |
+' \
+'<table><thead>
+<tr><th align=""> Col 1 </th><th align=""> Col 2</th><th align="right"> Col 3 </th></tr>
+</thead><tbody>
+<tr><td align=""> foo </td><td align=""> <em>bar</em> </td><td align="right"> <code>qua</code> </td></tr>
+<tr><td align=""> 23 </td><td align=""> 47 </td><td align="right"> 11 </td></tr>
+</tbody></table>' \
+'Pipe Tables'
+
+# assert '
+# Col 1 | Col 2| Col 3
+# :-----:|-------|------:
+# foo | *bar* | `qua`
+# 23 | 47 | 11 |
+# ' \
+# '<table><thead>
+# <tr><th align="center"> Col 1 </th><th align=""> Col 2</th><th align="right"> Col 3 </th></tr>
+# </thead><tbody>
+# <tr><td align="center"> foo </td><td align=""> <em>bar</em> </td><td align="right"> <code>qua</code> </td></tr>
+# <tr><td align="center"> 23 </td><td align=""> 47 </td><td align="right"> 11 </td></tr>
+# </tbody></table>' \
+# 'Pipe Tables'
+
+assert '+---+---+---+
+|Col 1\\| Col\|2 | Col 3|
++===+:==:+===+
+| * foo1 | *bar* |```|
+| * foo2 | **qua** |code |
+| - foo3 | `quux` |```|
++-------+-----+----+
+| 23 | 47 | 11 |
++-------+-----+----+
+' \
+'<table><thead>
+<tr><th align=""><p>Col 1\</p>
+</th><th align="center"><p> Col|2 </p>
+</th><th align=""><p> Col 3</p>
+</th></tr>
+</thead><tbody>
+<tr><td align=""><ul>
+<li>foo1 </li>
+<li>foo2 </li>
+</ul>
+<ul>
+<li>foo3 </li>
+</ul>
+</td><td align="center"><p> <em>bar</em>
+ <strong>qua</strong>
+ <code>quux</code> </p>
+</td><td align=""><pre><code>code </code></pre>
+</td></tr>
+<tr><td align=""><p> 23 </p>
+</td><td align="center"><p> 47 </p>
+</td><td align=""><p> 11 </p>
+</td></tr>
+</tbody></table>' \
+'Grid Tables'
+
+assert '## foo
+
+# bar
+
+sub bar
+-------
+
+### sub sub sub ###
+
+##sub2 bar {x}
+' \
+'<section class="h2" id="0.1:foo"><h2>foo<a class="anchor" href="#0.1:foo"></a></h2>
+</section><section class="h1" id="1:bar"><h1>bar<a class="anchor" href="#1:bar"></a></h1>
+<section class="h2" id="1.1:sub%20bar"><h2>sub bar<a class="anchor" href="#1.1:sub%20bar"></a></h2>
+<section class="h3" id="1.1.1:sub%20sub%20sub"><h3>sub sub sub<a class="anchor" href="#1.1.1:sub%20sub%20sub"></a></h3>
+</section></section><section class="h2 x" id="1.2:sub2%20bar"><h2 class="x">sub2 bar<a class="anchor" href="#1.2:sub2%20bar"></a></h2>
+</section></section>' \
+'Headline Nesting'
+
+# Reference syntax checks
+printf '\n## Testing reference syntax ##\n'
+
+assert 'Foo bar [Link] [1] for show
+
+The same in [en][]
+
+[en]: <http://en.wikipedia.org>
+[1]: http://de.wikipedia.org "Online Encyclopedia"' \
+'<p>Foo bar <a href="http://de.wikipedia.org" title="Online Encyclopedia">Link</a> for show</p>
+
+<p>The same in <a href="http://en.wikipedia.org">en</a></p>' \
+"Reference Links"
+
+assert 'Foo bar [Link] [1] for show
+
+[en]: <http://en.wikipedia.org>
+[1]: http://de.wikipedia.org
+ "Online Encyclopedia"' \
+'<p>Foo bar <a href="http://de.wikipedia.org" title="Online Encyclopedia">Link</a> for show</p>' \
+"Reference Links"
+
+assert 'Foo bar ![Image] [1] for show
+
+The same as ![PNG][]
+
+[PNG]: <mage/path/i.png>
+[1]: http://de.wikipedia.org/logo.jpg "Online Encyclopedia"' \
+'<p>Foo bar <img src="http://de.wikipedia.org/logo.jpg" alt="Image" title="Online Encyclopedia"> for show</p>
+
+<p>The same as <img src="mage/path/i.png" alt="PNG"></p>' \
+"Reference images"
+
+assert '![Image] [1]
+
+[PNG]: <mage/path/i.png>
+[1]: http://de.wikipedia.org/logo.jpg "Online Encyclopedia"' \
+'<figure data-src="http://de.wikipedia.org/logo.jpg"><img src="http://de.wikipedia.org/logo.jpg" alt="Image"><figcaption>Online Encyclopedia</figcaption></figure>' \
+"Reference images (block)"
+
+assert '<<macro /test -- "* weird <args>" _foo_>>' '<code class="macro">macro /test -- "* weird <args>" _foo_</code>' "Macros/Block"
+
+
+printf '\n## Testing example pages ##\n'
+
+assert 'Markdown.awk
+============
+
+Supported Features / TODO:
+--------------------------
+- [x] done
+- [ ] todo
+- [-] not planned
+- ? unsure (whether to implement)
+- [/] partial
+
+### Basic Markdown - Block elements: ###
+- [x] Paragraphs
+ - [x] Double space line breaks
+- [x] Proper block element nesting
+- [x] Headings
+- [x] ATX-Style Headings
+- [x] Blockquotes
+- [x] Lists (ordered, unordered)
+- [x] Code blocks (using indention)
+- [x] Horizontal rules
+- [x] Verbatim HTML block (disabled by default)
+
+### Basic Markdown - Inline elements: ###
+- [x] Links
+- [x] Reference style links
+- [x] Emphasis *em*/**strong** (*Asterisk*, _Underscore_)
+- [x] `code`, also ``code containing `backticks` ``
+- [x] Images / reference style images
+- [x] <automatic links>
+- [x] backslash escapes
+- [x] Verbatim HTML inline (disabled by default)
+- [x] HTML escaping
+
+NOTE: Set the environment variable `MD_HTML=true` to enable verbatim HTML
+
+### Extensions - Block elements: ###
+- [x] Automatic <section>-wrapping (custom)
+- ? Heading identifiers (php md, pandoc)
+ - [x] Heading attributes (custom)
+- [x] Automatic heading identifiers (custom)
+- [x] Fenced code blocks (php md, pandoc)
+ - [x] Fenced code attributes
+- [x] Images (as block elements, <figure>-wrapped) (custom)
+ - [x] reference style block images
+- [/] Tables
+ - ? Simple table (pandoc)
+ - ? Multiline table (pandoc)
+ - [x] Grid table (pandoc)
+ - [x] Headerless
+ - [x] Pipe table (php md, pandoc)
+- [x] Line blocks (pandoc)
+- [x] Task lists (pandoc, custom)
+- [x] Definition lists (php md, pandoc)
+- [-] Numbered example lists (pandoc)
+- [-] Metadata blocks (pandoc)
+- [x] Metadata blocks (custom)
+- [x] Fenced Divs (pandoc)
+
+### Extensions - Inline elements: ###
+- [x] Ignore embedded_underscores (php md, pandoc)
+- [x] ~~strikeout~~ (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)
+- ? "Curly quotes" (smartypants)
+- [ ] em-dashes (--) (smartypants old)
+- ? ... three-dot ellipsis (smartypants)
+- [-] en-dash (smartypants)
+- [ ] Automatic em-dash / en-dash
+- [x] Automatic -> Arrows <- (custom)
+
+Compatibility
+-------------
+Markdown.awk can run in GNU awk (`gawk`) and in Busybox awk. It is _not_ fully POSIX compliant and does not run in `mawk` or `nawk`. In particular it makes heavy use of the `gensub()` function and its ability to use paranthesized subexpressions in the replacement text. This feature is not available in the POSIX specified `sub()` and `gsub()` functions. Hence it cannot be replaced without effort.
+
+Tests
+-----
+[Link with Title](https://en.wikipedia.org/wiki/Markdown "Markdown in Wikipedia"), *emphasis*, **strong**, **strong containing *emphasis***, `inline code`, `` code with `backticks` ``. See more tests [here](./tests/).' \
+'<section class="h1" id="1:Markdown.awk"><h1>Markdown.awk<a class="anchor" href="#1:Markdown.awk"></a></h1>
+<section class="h2" id="1.1:Supported%20Features%20/%20TODO:"><h2>Supported Features / TODO:<a class="anchor" href="#1.1:Supported%20Features%20/%20TODO:"></a></h2>
+<ul>
+<li class="task done"><input type=checkbox disabled checked> done</li>
+<li class="task pending"><input type=checkbox disabled> todo</li>
+<li class="task negative"><input type=checkbox disabled> not planned</li>
+<li>? unsure (whether to implement)</li>
+<li class="task partial"><input type=checkbox disabled> partial</li>
+</ul>
+<section class="h3" id="1.1.1:Basic%20Markdown%20-%20Block%20elements:"><h3>Basic Markdown - Block elements:<a class="anchor" href="#1.1.1:Basic%20Markdown%20-%20Block%20elements:"></a></h3>
+<ul>
+<li class="task done"><input type=checkbox disabled checked><p> Paragraphs</p>
+<ul>
+<li class="task done"><input type=checkbox disabled checked> Double space line breaks</li>
+</ul>
+</li>
+<li class="task done"><input type=checkbox disabled checked> Proper block element nesting</li>
+<li class="task done"><input type=checkbox disabled checked> Headings</li>
+<li class="task done"><input type=checkbox disabled checked> ATX-Style Headings</li>
+<li class="task done"><input type=checkbox disabled checked> Blockquotes</li>
+<li class="task done"><input type=checkbox disabled checked> Lists (ordered, unordered)</li>
+<li class="task done"><input type=checkbox disabled checked> Code blocks (using indention)</li>
+<li class="task done"><input type=checkbox disabled checked> Horizontal rules</li>
+<li class="task done"><input type=checkbox disabled checked> Verbatim HTML block (disabled by default)</li>
+</ul>
+</section><section class="h3" id="1.1.2:Basic%20Markdown%20-%20Inline%20elements:"><h3>Basic Markdown - Inline elements:<a class="anchor" href="#1.1.2:Basic%20Markdown%20-%20Inline%20elements:"></a></h3>
+<ul>
+<li class="task done"><input type=checkbox disabled checked> Links</li>
+<li class="task done"><input type=checkbox disabled checked> Reference style links</li>
+<li class="task done"><input type=checkbox disabled checked> Emphasis <em>em</em>/<strong>strong</strong> (<em>Asterisk</em>, <em>Underscore</em>)</li>
+<li class="task done"><input type=checkbox disabled checked> <code>code</code>, also <code>code containing `backticks`</code></li>
+<li class="task done"><input type=checkbox disabled checked> Images / reference style images</li>
+<li class="task done"><input type=checkbox disabled checked> <automatic links></li>
+<li class="task done"><input type=checkbox disabled checked> backslash escapes</li>
+<li class="task done"><input type=checkbox disabled checked> Verbatim HTML inline (disabled by default)</li>
+<li class="task done"><input type=checkbox disabled checked> HTML escaping</li>
+</ul>
+<p>NOTE: Set the environment variable <code>MD_HTML=true</code> to enable verbatim HTML</p>
+
+</section><section class="h3" id="1.1.3:Extensions%20-%20Block%20elements:"><h3>Extensions - Block elements:<a class="anchor" href="#1.1.3:Extensions%20-%20Block%20elements:"></a></h3>
+<ul>
+<li class="task done"><input type=checkbox disabled checked> Automatic <section>-wrapping (custom)</li>
+<li><p> ? Heading identifiers (php md, pandoc)</p>
+<ul>
+<li class="task done"><input type=checkbox disabled checked> Heading attributes (custom)</li>
+</ul>
+</li>
+<li class="task done"><input type=checkbox disabled checked> Automatic heading identifiers (custom)</li>
+<li class="task done"><input type=checkbox disabled checked><p> Fenced code blocks (php md, pandoc)</p>
+<ul>
+<li class="task done"><input type=checkbox disabled checked> Fenced code attributes</li>
+</ul>
+</li>
+<li class="task done"><input type=checkbox disabled checked><p> Images (as block elements, <figure>-wrapped) (custom)</p>
+<ul>
+<li class="task done"><input type=checkbox disabled checked> reference style block images</li>
+</ul>
+</li>
+<li class="task partial"><input type=checkbox disabled><p> Tables</p>
+<ul>
+<li> ? Simple table (pandoc)</li>
+<li> ? Multiline table (pandoc)</li>
+<li class="task done"><input type=checkbox disabled checked><p> Grid table (pandoc)</p>
+<ul>
+<li class="task done"><input type=checkbox disabled checked> Headerless</li>
+</ul>
+</li>
+<li class="task done"><input type=checkbox disabled checked> Pipe table (php md, pandoc)</li>
+</ul>
+</li>
+<li class="task done"><input type=checkbox disabled checked> Line blocks (pandoc)</li>
+<li class="task done"><input type=checkbox disabled checked> Task lists (pandoc, custom)</li>
+<li class="task done"><input type=checkbox disabled checked> Definition lists (php md, pandoc)</li>
+<li class="task negative"><input type=checkbox disabled> Numbered example lists (pandoc)</li>
+<li class="task negative"><input type=checkbox disabled> Metadata blocks (pandoc)</li>
+<li class="task done"><input type=checkbox disabled checked> Metadata blocks (custom)</li>
+<li class="task done"><input type=checkbox disabled checked> Fenced Divs (pandoc)</li>
+</ul>
+</section><section class="h3" id="1.1.4:Extensions%20-%20Inline%20elements:"><h3>Extensions - Inline elements:<a class="anchor" href="#1.1.4:Extensions%20-%20Inline%20elements:"></a></h3>
+<ul>
+<li class="task done"><input type=checkbox disabled checked> Ignore embedded_underscores (php md, pandoc)</li>
+<li class="task done"><input type=checkbox disabled checked> <del>strikeout</del> (pandoc)</li>
+<li class="task done"><input type=checkbox disabled checked> <sup>Superscript</sup> <sub>Subscript</sub> (pandoc)</li>
+<li class="task negative"><input type=checkbox disabled><p> Bracketed spans (pandoc)</p>
+<ul>
+<li class="task negative"><input type=checkbox disabled> Inline attributes (pandoc)</li>
+</ul>
+</li>
+<li class="task done"><input type=checkbox disabled checked> Image attributes (custom, pandoc inspired, not for reference style)</li>
+<li class="task done"><input type=checkbox disabled checked> Wiki style links <a href="PageName">PageName</a> / <a href="PageName">Link Text</a></li>
+<li class="task negative"><input type=checkbox disabled> TEX-Math (pandoc)</li>
+<li> ? Footnotes (php md)</li>
+<li> ? Abbreviations (php md)</li>
+<li> ? "Curly quotes" (smartypants)</li>
+<li class="task pending"><input type=checkbox disabled> em-dashes (--) (smartypants old)</li>
+<li> ? ... three-dot ellipsis (smartypants)</li>
+<li class="task negative"><input type=checkbox disabled> en-dash (smartypants)</li>
+<li class="task pending"><input type=checkbox disabled> Automatic em-dash / en-dash</li>
+<li class="task done"><input type=checkbox disabled checked> Automatic → Arrows ← (custom)</li>
+</ul>
+</section></section><section class="h2" id="1.2:Compatibility"><h2>Compatibility<a class="anchor" href="#1.2:Compatibility"></a></h2>
+<p>Markdown.awk can run in GNU awk (<code>gawk</code>) and in Busybox awk. It is <em>not</em> fully POSIX compliant and does not run in <code>mawk</code> or <code>nawk</code>. In particular it makes heavy use of the <code>gensub()</code> function and its ability to use paranthesized subexpressions in the replacement text. This feature is not available in the POSIX specified <code>sub()</code> and <code>gsub()</code> functions. Hence it cannot be replaced without effort.</p>
+
+</section><section class="h2" id="1.3:Tests"><h2>Tests<a class="anchor" href="#1.3:Tests"></a></h2>
+<p><a href="https://en.wikipedia.org/wiki/Markdown" title="Markdown in Wikipedia">Link with Title</a>, <em>emphasis</em>, <strong>strong</strong>, <strong>strong containing <em>emphasis</em></strong>, <code>inline code</code>, <code>code with `backticks`</code>. See more tests <a href="./tests/">here</a>.</p>
+</section></section>' \
+'Full Page (cgilite markdown)'
+
+assert 'Headline First Order
+====================
+
+Headline Second Order
+---------------------
+
+ Code Block
+ with indentation
+
+> Blockquote
+> ----------
+> like in an email
+
+### Headline 3rd order
+
+- unordered List
+1. with sub points
+
+ sometimes longer ones
+
+2. which are ordered
+3. [ ] and have a Todo item
+- more list points
+ - and a sublist
+- [x] some of which ae done
+
+----------
++ A lazy, lazy, list
+item.
+
++ Another one; this looks
+bad but is legal.
+
+ Second paragraph of second
+list item.
+
+---------
+
+~~~ {.blue}
+Fenced Code Block
+# with verbatim Text
+`and an attribute`
+~~~
+
+| The limerick packs laughs anatomical
+| In space that is quite economical.
+| But the *good* ones I'\''ve seen
+| So seldom are *clean*
+| And the clean ones so seldom are comical
+
+| The Right Honorable Most Venerable and Righteous Samuel L.
+ Constable, Jr.
+| 200 Main St.
+| Berkeley, CA 94718
+
+Term 1
+
+: This is a definition with two paragraphs. Lorem ipsum
+ dolor sit amet, consectetuer adipiscing elit. Aliquam
+ hendrerit mi posuere lectus.
+
+ Vestibulum enim wisi, viverra nec, fringilla in, laoreet
+ vitae, risus.
+
+: Second definition for term 1, also wrapped in a paragraph
+ because of the blank line preceding it.
+
+Term 2
+
+: This definition has a code block, a blockquote and a list.
+
+ code block.
+
+ > block quote
+ > on two lines.
+
+ 1. first list item
+ 2. second list item' \
+'<section class="h1" id="1:Headline%20First%20Order"><h1>Headline First Order<a class="anchor" href="#1:Headline%20First%20Order"></a></h1>
+<section class="h2" id="1.1:Headline%20Second%20Order"><h2>Headline Second Order<a class="anchor" href="#1.1:Headline%20Second%20Order"></a></h2>
+<pre><code>Code Block
+with indentation</code></pre>
+<blockquote><section class="h2" id="1/0.1:Blockquote"><h2>Blockquote<a class="anchor" href="#1/0.1:Blockquote"></a></h2>
+<p>like in an email</p>
+</section></blockquote>
+
+<section class="h3" id="1.1.1:Headline%203rd%20order"><h3>Headline 3rd order<a class="anchor" href="#1.1.1:Headline%203rd%20order"></a></h3>
+<ul>
+<li>unordered List</li>
+</ul>
+<ol>
+<li><p>with sub points</p>
+
+<p>sometimes longer ones</p>
+</li>
+<li><p>which are ordered</p>
+</li>
+<li class="task pending"><input type=checkbox disabled><p> and have a Todo item</p>
+</li>
+</ol>
+<ul>
+<li><p>more list points</p>
+<ul>
+<li>and a sublist</li>
+</ul>
+</li>
+<li class="task done"><input type=checkbox disabled checked> some of which ae done</li>
+</ul>
+<hr>
+<ul>
+<li><p>A lazy, lazy, list
+item.</p>
+</li>
+<li><p>Another one; this looks
+bad but is legal.</p>
+
+<p> Second paragraph of second
+list item.</p>
+</li>
+</ul>
+<hr>
+
+<pre><code class="blue">Fenced Code Block
+# with verbatim Text
+`and an attribute`</code></pre>
+<div class="line-block">The limerick packs laughs anatomical<br>
+In space that is quite economical.<br>
+ But the <em>good</em> ones I've seen<br>
+ So seldom are <em>clean</em><br>
+And the clean ones so seldom are comical</div>
+<div class="line-block">The Right Honorable Most Venerable and Righteous Samuel L. Constable, Jr.<br>
+200 Main St.<br>
+Berkeley, CA 94718</div>
+<dl>
+<dt>Term 1</dt>
+<dd><p>This is a definition with two paragraphs. Lorem ipsum
+dolor sit amet, consectetuer adipiscing elit. Aliquam
+hendrerit mi posuere lectus.</p>
+
+<p>Vestibulum enim wisi, viverra nec, fringilla in, laoreet
+vitae, risus.</p>
+</dd>
+<dd>Second definition for term 1, also wrapped in a paragraph
+because of the blank line preceding it.</dd>
+<dt>Term 2</dt>
+<dd><p>This definition has a code block, a blockquote and a list.</p>
+
+<pre><code>code block.</code></pre>
+<blockquote><p>block quote
+on two lines.</p></blockquote>
+
+<ol>
+<li> first list item</li>
+<li> second list item</li>
+</ol>
+</dd>
+</dl>
+</section></section></section>' \
+'Full Page (MD Tests)'
+
+assert '%css shellwiki.css
+
+Shellwiki
+=========
+Shellwiki is a Wiki and Content Management System with minimal dependencies. It can run on embedded devices, as well as full size web servers. Its goals are:
+
+ - **easy deployment**
+
+ *ShellWiki* can run on any Unix-Like web server. It requires no
+ scripting languages beyound the regular (Bourne style) Unix
+ shell, `awk`, and `sed`, all of which can be providede by
+ `busybox`. It can be launched via `netcat`, `inetd`, `systemd`,
+ or any cgi capable webserver like `apache` or `lighttpd`.
+ *ShellWiki* can run easily on embedded systems like OpenWRT or
+ RaspberryPi, and just as easily on internet web servers
+ providing multisite setups.
+
+ - **accessibility**
+
+ *ShellWiki* requires no browserside scripting. It aims to be rendered
+ in all web browsers including `w3m` and `links` besides graphical
+ browsers like `chromium` or `firefox`. It is as accessible on mobile
+ screens as on desktop computers.
+ *ShellWiki* uses the well known `markdown` syntax for formatting and
+ aims to provide consistent UI controls for various use cases.
+
+ - **adaptability**
+
+ *ShellWiki* is extensible through plugins and provides theming and
+ styling capabilities that make it suitable not only as a wiki, but
+ also as a CMS, including access scopes for different authors and
+ stylisticly distinct subpages.
+
+ - **simplicity**
+
+ *ShellWiki* avoids complexity in both software design and user
+ interface. It aims to be secure and predictable. Extensions can
+ be written and modified by system administrators.
+
+<<toc 2 2>>
+
+Features
+--------
+ - **Markdown Wiki Syntax**
+
+ The wiki syntax is based on [John Grubers Markdown](https://daringfireball.net/projects/markdown/)
+ with extensions inspired by [Pandoc](https://pandoc.org/MANUAL.html#pandocs-markdown),
+ [PHP Markdown Extra](https://michelf.ca/projects/php-markdown/extra/), and
+ [Github Flavored Markdown](https://github.github.com/gfm/).
+ Additional Macros are provided to enable functions like an automatic table of contents, listing of
+ sub pages, etc.
+
+ See [Markdown](/software/cgilite/markdown/)
+ and [Macros](macros/)
+
+ - **Plain file Storage**
+
+ Pages and attachments are stored as plain files on disk. There is no need for a separate database
+ system.
+
+ - **Git revisioning**
+
+ If `git` is available on the web server, pages can be revisioned so that past versions can be
+ revisited. Optionally attachments can be revisioned too. Server administrators may use the git
+ archives to synchronise sites across servers by adding their own mechanics.
+
+ - **Multisite Installation**
+
+ Code and data directories are stricly separate on the server. Directory pathes are obtained from
+ environment variables, so that multiple sites can be served from the same installation directory.
+
+ See also: [Installation](installation/)
+
+ - **Semantic HTML5**
+
+ for accessible rendering of pages
+
+ - **Descriptive Page Names**
+
+ URLs of pages can be freely provided by the user. User access can be constrained to specific sub
+ pages. Within their access permissions users can move and rename pages as they like.
+
+ - **File Upload / Attachment**
+
+ While pages are merely text documents themselves, users can upload additional attachments and
+ link to them in a page. Images and media files can be embedded directly into a page.
+
+ - **Image scaling**
+
+ If `ImageMagick` is available on the web server, huge attachment images are automatically compressed
+ and scaled to HD resolution when referred to in a page.
+ Of course the original version can still be linked to.
+
+ - **Permissions via ACL**
+
+ Grant read/write access for pages and sub-pages
+
+ - **User provided CSS**
+
+ Aside from full theming in the installation directory, pages can be styled using CSS files
+ uploaded as attachments.
+
+ - **No reliance on Javascript**
+
+ Authors and visitors can use the site without being forced to run untrusted code.
+ The main theme still provides collapsible menus and a responsive layout.
+
+ - **Complete GDPR Compliance** without consent walls
+
+ Because shellwiki does not track page visitors and does not
+ serve cookies to visitors by default it does not need to coerce
+ visitors into handling GDPR "consent" forms.
+
+ (Login for authors still requires a session cookie)
+
+ - **True multilanguage capability**
+
+ - Pages can be translated
+ - Switching language does not require a cookie
+ - Fallback language for missing translations
+ - Users stay on a translated version, even if single page translations are missing
+
+ - **Full text indexing and search**
+
+ Shellwiki contains its own basic text indexer without external dependencies.
+
+ - **Extensibility** through
+
+ - [Themes](themes/)
+ - [Macros](macros/)
+ - [URL Handlers](handlers/)
+ - [Custom Syntax parsers](parsers/)
+
+Dependencies
+------------
+Shellwiki is based on [cgilite](/software/cgilite/), which is included in the installation. It is written in posix compliant shell script, and the markdown renderer is written in ~~posix compliant~~ AWK. The entire wiki system can run with nothing more than a busybox. In fact it can be served from the rescue shell in a Debian initrd, or from an OpenWRT router.
+
+**Its precise requirements are:**
+
+ - A Posix Shell (as provided by busybox, but bash is OK)
+ - An AWK interpreter (as provided by busybox, but GNU AWK is OK)
+ - `mawk` and `nawk` will currently not work
+ - inetd (as provided by busybox)
+
+ **or** any CGI-Capable web server
+
+ - _Optional:_ GIT for revisioning
+ - _Optional:_ ImageMagick for image compression
+ - _Optional:_ Sendmail for sending password reminders, etc.
+
+Installation
+------------
+Also see -> [[installation/]]
+
+You can try out shellwiki right now using busybox:
+
+ ~$ git clone https://git.plutz.net/git/shellwiki ~/shellwiki
+ ~$ _DATA=~/wikidata busybox nc -llp 1080 -e ~/shellwiki/index.cgi
+
+For additional examples, regarding permanent installation and configuration in webservers see [[installation/]].
+
+Syntax
+------
+The wiki syntax is based on John Grubers [Markdown](https://daringfireball.net/projects/markdown/) with extensions borrowed from [Pandoc](https://pandoc.org/MANUAL%202.html#pandocs-markdown) and [PHP Markdown Extra](https://michelf.ca/projects/php-markdown/extra/). The Markdown parser is provided by [Cgilite](/software/cgilite/) and its full documentation can be looked at [here](/software/cgilite/markdown/).
+
+<<include --nolink /[wiki]/editorhelp/>>
+
+Macros
+------
+Also see -> [[macros/]]
+
+In addition to the Markdown syntax, wiki pages can include Macros, which perform additional functions on a page, like generating an image gallery, including parts of other pages, etc. Macros make Shellwiki truly dynamic and flexible.
+
+For example you can include a table of content for the current page by including the line
+
+ <<toc>>
+
+in your page. Macros can receive additional parameters, which modify their behaviour.
+
+Macros are the most easy to write type of extension. See [Macros](macros/) for a full list of available macros.
+
+Themes
+------
+Also see -> [[theming/]]
+
+While Shellwiki supports plugins for [theming](dev-theming/), it'\''s apearance can mostly be configured by the user. Pages can be configured to use custom CSS files. In addition page headers and footers are themselves wiki pages which can be modified to add menus, custom logos, links, etc. The same goes for error pages.
+
+For an example, see the [technical pages](/[wiki]/) for this wiki.
+
+Multiple Languages
+------------------
+To enable a multilingual setup you must set a default language in your configuration environment:
+
+```
+export LANGUAGE_DEFAULT=en
+```
+
+Once this is the case, pagenames starting with a colon (`:`) will be considered translated versions of their parent pages. I.e. the pages `/`, `/:de`, and `/:fr` will serve as the default, german, and french home page respectively.
+
+The names of the languages can be arbitrary, but I recommend using [ISO-639](https://en.wikipedia.org/wiki/ISO_639-1) codes, because the code is used in the `lang=""` attribute of the pages top level html element. You can however make up non-standardised or fantastic language names as well.
+
+Links on each page will automatically be suffixed with the same language tag, so a visitor keeps browsing the same language without needing a cookie. Attachments should only be uploaded to the default language page, and attachment links in the translated pages will correctly point to the main page attachments. You can create a language menu on the header page, simply by linking to `./:en`, `./:es` , `./:fr`, etc.
+
+Header, footer, and error pages will be included from their respective language version, as will all macro includes, etc. Should a page not exist in a given language, the default page will be displayed instead. However, included elements will still be taken from the respective language version, possibly mixing languages between the selected user language and the default.
+
+### Constraints of the current implementation
+ - There can be only one default language, with no priority of different fallback languages
+ - Page URLs can currently not be translated. Doing so would require a model for manually assigning translated page names and would not be trivial to use.
+
+Developer Documentation
+-----------------------
+How to write:
+
+ - [Themes](dev-theming/)
+ - [Macros](dev-macros/)
+ - [Handlers](dev-handlers/)
+ - [Parsers](dev-parsers/)' \
+'<section class="h1" id="1:Shellwiki"><h1>Shellwiki<a class="anchor" href="#1:Shellwiki"></a></h1>
+<p>Shellwiki is a Wiki and Content Management System with minimal dependencies. It can run on embedded devices, as well as full size web servers. Its goals are:</p>
+<ul>
+<li><p><strong>easy deployment</strong></p>
+
+<p><em>ShellWiki</em> can run on any Unix-Like web server. It requires no
+scripting languages beyound the regular (Bourne style) Unix
+shell, <code>awk</code>, and <code>sed</code>, all of which can be providede by
+<code>busybox</code>. It can be launched via <code>netcat</code>, <code>inetd</code>, <code>systemd</code>,
+or any cgi capable webserver like <code>apache</code> or <code>lighttpd</code>.<br>
+<em>ShellWiki</em> can run easily on embedded systems like OpenWRT or
+RaspberryPi, and just as easily on internet web servers
+providing multisite setups.</p>
+</li>
+<li><p><strong>accessibility</strong></p>
+
+<p><em>ShellWiki</em> requires no browserside scripting. It aims to be rendered
+in all web browsers including <code>w3m</code> and <code>links</code> besides graphical
+browsers like <code>chromium</code> or <code>firefox</code>. It is as accessible on mobile
+screens as on desktop computers.<br>
+<em>ShellWiki</em> uses the well known <code>markdown</code> syntax for formatting and
+aims to provide consistent UI controls for various use cases.</p>
+</li>
+<li><p><strong>adaptability</strong></p>
+
+<p><em>ShellWiki</em> is extensible through plugins and provides theming and
+styling capabilities that make it suitable not only as a wiki, but
+also as a CMS, including access scopes for different authors and
+stylisticly distinct subpages.</p>
+</li>
+<li><p><strong>simplicity</strong></p>
+
+<p><em>ShellWiki</em> avoids complexity in both software design and user
+interface. It aims to be secure and predictable. Extensions can
+be written and modified by system administrators. </p>
+</li>
+</ul>
+<code class="macro">toc 2 2</code><section class="h2" id="1.1:Features"><h2>Features<a class="anchor" href="#1.1:Features"></a></h2>
+<ul>
+<li><p><strong>Markdown Wiki Syntax</strong></p>
+
+<p>The wiki syntax is based on <a href="https://daringfireball.net/projects/markdown/">John Grubers Markdown</a>
+with extensions inspired by <a href="https://pandoc.org/MANUAL.html#pandocs-markdown">Pandoc</a>,
+<a href="https://michelf.ca/projects/php-markdown/extra/">PHP Markdown Extra</a>, and
+<a href="https://github.github.com/gfm/">Github Flavored Markdown</a>.
+Additional Macros are provided to enable functions like an automatic table of contents, listing of
+sub pages, etc.</p>
+
+<p>See <a href="/software/cgilite/markdown/">Markdown</a><br>
+and <a href="macros/">Macros</a></p>
+</li>
+<li><p><strong>Plain file Storage</strong></p>
+
+<p>Pages and attachments are stored as plain files on disk. There is no need for a separate database
+system.</p>
+</li>
+<li><p><strong>Git revisioning</strong></p>
+
+<p>If <code>git</code> is available on the web server, pages can be revisioned so that past versions can be
+revisited. Optionally attachments can be revisioned too. Server administrators may use the git
+archives to synchronise sites across servers by adding their own mechanics.</p>
+</li>
+<li><p><strong>Multisite Installation</strong></p>
+
+<p>Code and data directories are stricly separate on the server. Directory pathes are obtained from
+environment variables, so that multiple sites can be served from the same installation directory.</p>
+
+<p>See also: <a href="installation/">Installation</a></p>
+</li>
+<li><p><strong>Semantic HTML5</strong></p>
+
+<p>for accessible rendering of pages</p>
+</li>
+<li><p><strong>Descriptive Page Names</strong></p>
+
+<p>URLs of pages can be freely provided by the user. User access can be constrained to specific sub
+pages. Within their access permissions users can move and rename pages as they like.</p>
+</li>
+<li><p><strong>File Upload / Attachment</strong></p>
+
+<p>While pages are merely text documents themselves, users can upload additional attachments and
+link to them in a page. Images and media files can be embedded directly into a page.</p>
+</li>
+<li><p><strong>Image scaling</strong></p>
+
+<p>If <code>ImageMagick</code> is available on the web server, huge attachment images are automatically compressed
+and scaled to HD resolution when referred to in a page.
+Of course the original version can still be linked to.</p>
+</li>
+<li><p><strong>Permissions via ACL</strong></p>
+
+<p>Grant read/write access for pages and sub-pages</p>
+</li>
+<li><p><strong>User provided CSS</strong></p>
+
+<p>Aside from full theming in the installation directory, pages can be styled using CSS files
+uploaded as attachments.</p>
+</li>
+<li><p><strong>No reliance on Javascript</strong></p>
+
+<p>Authors and visitors can use the site without being forced to run untrusted code.
+The main theme still provides collapsible menus and a responsive layout.</p>
+</li>
+<li><p><strong>Complete GDPR Compliance</strong> without consent walls</p>
+
+<p>Because shellwiki does not track page visitors and does not
+serve cookies to visitors by default it does not need to coerce
+visitors into handling GDPR "consent" forms.</p>
+
+<p>(Login for authors still requires a session cookie)</p>
+</li>
+<li><p><strong>True multilanguage capability</strong></p>
+<ul>
+<li>Pages can be translated</li>
+<li>Switching language does not require a cookie</li>
+<li>Fallback language for missing translations</li>
+<li>Users stay on a translated version, even if single page translations are missing</li>
+</ul>
+</li>
+<li><p><strong>Full text indexing and search</strong></p>
+
+<p>Shellwiki contains its own basic text indexer without external dependencies.</p>
+</li>
+<li><p><strong>Extensibility</strong> through</p>
+<ul>
+<li><a href="themes/">Themes</a></li>
+<li><a href="macros/">Macros</a></li>
+<li><a href="handlers/">URL Handlers</a></li>
+<li><a href="parsers/">Custom Syntax parsers</a></li>
+</ul>
+</li>
+</ul>
+</section><section class="h2" id="1.2:Dependencies"><h2>Dependencies<a class="anchor" href="#1.2:Dependencies"></a></h2>
+<p>Shellwiki is based on <a href="/software/cgilite/">cgilite</a>, which is included in the installation. It is written in posix compliant shell script, and the markdown renderer is written in <del>posix compliant</del> AWK. The entire wiki system can run with nothing more than a busybox. In fact it can be served from the rescue shell in a Debian initrd, or from an OpenWRT router.</p>
+
+<p><strong>Its precise requirements are:</strong></p>
+<ul>
+<li><p>A Posix Shell (as provided by busybox, but bash is OK)</p>
+</li>
+<li><p>An AWK interpreter (as provided by busybox, but GNU AWK is OK)</p>
+<ul>
+<li><code>mawk</code> and <code>nawk</code> will currently not work</li>
+</ul>
+</li>
+<li><p>inetd (as provided by busybox)</p>
+
+<p><strong>or</strong> any CGI-Capable web server</p>
+</li>
+<li><p><em>Optional:</em> GIT for revisioning</p>
+</li>
+<li><p><em>Optional:</em> ImageMagick for image compression</p>
+</li>
+<li><p><em>Optional:</em> Sendmail for sending password reminders, etc.</p>
+</li>
+</ul>
+</section><section class="h2" id="1.3:Installation"><h2>Installation<a class="anchor" href="#1.3:Installation"></a></h2>
+<p>Also see → <a href="installation/">installation/</a></p>
+
+<p>You can try out shellwiki right now using busybox:</p>
+
+<pre><code>~$ git clone https://git.plutz.net/git/shellwiki ~/shellwiki
+~$ _DATA=~/wikidata busybox nc -llp 1080 -e ~/shellwiki/index.cgi</code></pre>
+<p>For additional examples, regarding permanent installation and configuration in webservers see <a href="installation/">installation/</a>.</p>
+
+</section><section class="h2" id="1.4:Syntax"><h2>Syntax<a class="anchor" href="#1.4:Syntax"></a></h2>
+<p>The wiki syntax is based on John Grubers <a href="https://daringfireball.net/projects/markdown/">Markdown</a> with extensions borrowed from <a href="https://pandoc.org/MANUAL%202.html#pandocs-markdown">Pandoc</a> and <a href="https://michelf.ca/projects/php-markdown/extra/">PHP Markdown Extra</a>. The Markdown parser is provided by <a href="/software/cgilite/">Cgilite</a> and its full documentation can be looked at <a href="/software/cgilite/markdown/">here</a>.</p>
+
+<code class="macro">include --nolink /[wiki]/editorhelp/</code></section><section class="h2" id="1.5:Macros"><h2>Macros<a class="anchor" href="#1.5:Macros"></a></h2>
+<p>Also see → <a href="macros/">macros/</a></p>
+
+<p>In addition to the Markdown syntax, wiki pages can include Macros, which perform additional functions on a page, like generating an image gallery, including parts of other pages, etc. Macros make Shellwiki truly dynamic and flexible.</p>
+
+<p>For example you can include a table of content for the current page by including the line</p>
+
+<pre><code><<toc>></code></pre>
+<p>in your page. Macros can receive additional parameters, which modify their behaviour.</p>
+
+<p>Macros are the most easy to write type of extension. See <a href="macros/">Macros</a> for a full list of available macros.</p>
+
+</section><section class="h2" id="1.6:Themes"><h2>Themes<a class="anchor" href="#1.6:Themes"></a></h2>
+<p>Also see → <a href="theming/">theming/</a></p>
+
+<p>While Shellwiki supports plugins for <a href="dev-theming/">theming</a>, it's apearance can mostly be configured by the user. Pages can be configured to use custom CSS files. In addition page headers and footers are themselves wiki pages which can be modified to add menus, custom logos, links, etc. The same goes for error pages.</p>
+
+<p>For an example, see the <a href="/[wiki]/">technical pages</a> for this wiki.</p>
+
+</section><section class="h2" id="1.7:Multiple%20Languages"><h2>Multiple Languages<a class="anchor" href="#1.7:Multiple%20Languages"></a></h2>
+<p>To enable a multilingual setup you must set a default language in your configuration environment:</p>
+
+<pre><code>export LANGUAGE_DEFAULT=en</code></pre>
+<p>Once this is the case, pagenames starting with a colon (<code>:</code>) will be considered translated versions of their parent pages. I.e. the pages <code>/</code>, <code>/:de</code>, and <code>/:fr</code> will serve as the default, german, and french home page respectively.</p>
+
+<p>The names of the languages can be arbitrary, but I recommend using <a href="https://en.wikipedia.org/wiki/ISO_639-1">ISO-639</a> codes, because the code is used in the <code>lang=""</code> attribute of the pages top level html element. You can however make up non-standardised or fantastic language names as well.</p>
+
+<p>Links on each page will automatically be suffixed with the same language tag, so a visitor keeps browsing the same language without needing a cookie. Attachments should only be uploaded to the default language page, and attachment links in the translated pages will correctly point to the main page attachments. You can create a language menu on the header page, simply by linking to <code>./:en</code>, <code>./:es</code> , <code>./:fr</code>, etc.</p>
+
+<p>Header, footer, and error pages will be included from their respective language version, as will all macro includes, etc. Should a page not exist in a given language, the default page will be displayed instead. However, included elements will still be taken from the respective language version, possibly mixing languages between the selected user language and the default.</p>
+
+<section class="h3" id="1.7.1:Constraints%20of%20the%20current%20implementation"><h3>Constraints of the current implementation<a class="anchor" href="#1.7.1:Constraints%20of%20the%20current%20implementation"></a></h3>
+<ul>
+<li>There can be only one default language, with no priority of different fallback languages</li>
+<li>Page URLs can currently not be translated. Doing so would require a model for manually assigning translated page names and would not be trivial to use.</li>
+</ul>
+</section></section><section class="h2" id="1.8:Developer%20Documentation"><h2>Developer Documentation<a class="anchor" href="#1.8:Developer%20Documentation"></a></h2>
+<p>How to write:</p>
+<ul>
+<li><a href="dev-theming/">Themes</a></li>
+<li><a href="dev-macros/">Macros</a></li>
+<li><a href="dev-handlers/">Handlers</a></li>
+<li><a href="dev-parsers/">Parsers</a></li>
+</ul>
+</section></section>' \
+'Full Page (ShellWiki)'
+
+printf '\nAll tests passed!\n'
projects / invoices / commitdiff