From: Paul Hänsch <paul@plutz.net>
Date: Wed, 23 Feb 2022 15:46:01 +0000 (+0100)
Subject: First Macro: toc
X-Git-Url: https://git.plutz.net/?a=commitdiff_plain;h=9362e386b7134e97e63858b7d59e2f6dd3cb1ca6;p=shellwiki

First Macro: toc
---

diff --git a/macros/toc b/macros/toc
new file mode 100755
index 0000000..0d708a4
--- /dev/null
+++ b/macros/toc
@@ -0,0 +1,299 @@
+#!/bin/awk -f
+#!/opt/busybox/awk -f
+
+# Table of Content generator
+# For finding Headlines within a markdown document one needs to be context
+# aware. I.e. Headlines within verbatim blocks must be ignored, etc.
+#
+# Basically this program is a slightly stripped down version onf the main
+# markdown parser.
+# Most of the inline parser is also included to allow stylig of headlines.
+
+# TODO: Accept Arguments for controlling toc depth
+# TODO Maybe: Somehow enable section TOCs
+
+function debug(text) { printf "\n---\n%s\n---\n", text > "/dev/stderr"; }
+
+function HTML ( text ) {
+  gsub( /&/,  "\\&amp;",  text );
+  gsub( /</,  "\\&lt;",   text );
+  gsub( />/,  "\\&gt;",   text );
+  gsub( /"/,  "\\&quot;", text );
+  gsub( /'/,  "\\&#x27;", text );
+  gsub( /\\/, "\\&#x5C;", text );
+  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 <TOC MODIFIED>
+  } else if ( match(line, /^  \n/) ) {
+    return 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( /&/, "\\&amp;", code ); gsub( /</, "\\&lt;", code ); gsub( />/, "\\&gt;", code );
+      return "<code>" code "</code>" inline( substr( line, len + 1 ) )
+    }
+
+  #  quick links ("automatic links" in md doc) <TOC MODIFIED>
+  } else if ( match( line, /^<[a-zA-Z]+:\/\/([-\.[:alnum:]]+)(:[0-9]*)?(\/[^>]*)?>/ ) ) {
+    len = RLENGTH;
+    href = HTML( substr( line, 2, len - 2) );
+    return "<span class=\"a\">" href "</span>" inline( substr( line, len + 1) );
+
+  # inline links <TOC MODIFIED>
+  } else if ( match(line, /^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/) ) {
+    len = RLENGTH;
+    text  = gensub(/^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\1", "g", line);
+    return "<span class=\"a\">" inline( text ) "</span>" inline( substr( line, len + 1) );
+
+  # reference style links <TOC MODIFIED>
+  } else if ( match(line, /^\[([^]]+)\] ?\[([^]]*)\]/ ) ) {
+    len = RLENGTH;
+    text = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\1", 1, line);
+    #   id = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\2", 1, line);
+    return "<span class=\"a\">" inline(text) "</span>" inline( substr( line, len + 1) );
+
+  # inline images <TOC MODIFIED>
+  } else if ( match(line, /^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/) ) {
+    len = RLENGTH;
+    text  = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\1", "g", line);
+    # href  = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\2", "g", line);
+    title = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\4", "g", line);
+    if ( title ) {
+      return "<span class=\"img\">" HTML(title) "</span>" inline( substr( line, len + 1) );
+    } else {
+      return "<span class=\"img\">" HTML(text) "</span>" inline( substr( line, len + 1) );
+    }
+
+  # reference style images <TOC MODIFIED>
+  } else if ( match(line, /^!\[([^]]+)\] ?\[([^]]*)\]/ ) ) {
+    len = RLENGTH;
+    text = gensub(/^!\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\1", 1, line);
+    #  id = gensub(/^!\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\2", 1, line);
+    return "<span class=\"img\">" HTML(text) "</span>" inline( substr( line, len + 1) );
+
+  #  ~~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 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  <TOC MODIFIED: never allow recursion>
+  # } 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) );
+  }
+}
+
+function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent ) {
+  gsub( /^\n+|\n+$/, "", block );
+
+  if ( block == "" ) {
+    return "";
+
+  # HTML #2 #3 #4 $5
+  } else if ( AllowHTML && match( block, /(^|\n) ? ? ?(<!--([^-]|-[^-]|--[^>])*(-->|$)|<\?([^\?]|\?[^>])*(\?>|$)|<![A-Z][^>]*(>|$)|<!\[CDATA\[([^\]]|\][^\]]|\]\][^>])*(\]\]>|$))/) ) {
+    len = RLENGTH; st = RSTART;
+    return _block(substr(block, 1, st - 1)) _block(substr(block, st + len));
+
+  # HTML #6
+  } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<\/?(address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset|h[123456]|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul)([[:space:]\n>]|\/>)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) {
+    len = RLENGTH; st = RSTART;
+    return _block(substr(block, 1, st - 1)) _block(substr(block, st + len));
+
+  # HTML #1
+  } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<(script|pre|style)([[:space:]\n>]).*(<\/script>|<\/pre>|<\/style>|$)/) ) {
+    len = RLENGTH; st = RSTART;
+    match( tolower(substr(block, st, len)), /(<\/script>|<\/pre>|<\/style>)/);
+    len = RSTART + RLENGTH;
+    return _block(substr(block, 1, st - 1)) _block(substr(block, st + len));
+
+  # HTML #7
+  } else if ( AllowHTML && match( block, /^ ? ? ?(<\/[A-Za-z][A-Za-z0-9-]*[[:space:]]*>|<[A-Za-z][A-Za-z0-9-]*([[:space:]]+[A-Za-z_:][A-Za-z0-9_\.:-]*([[:space:]]*=[[:space:]]*([[:space:]"'=<>`]+|"[^"]*"|'[^']*'))?)*[[:space:]]*\/?>)([[:space:]]*\n)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) {
+    len = RLENGTH; st = RSTART;
+    return _block(substr(block, st + len));
+ 
+  # Blockquote (leading >)
+  } else if ( match( block, /^> /) ) {
+    match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match(block, /$/);
+    len = RLENGTH; st = RSTART;
+    return _block( substr(block, st + len) );
+
+  # Line Blocks (pandoc)
+  } else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\n]*(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) {
+    len = RLENGTH; st = RSTART;
+    return _block( substr( block, len + 1) );
+
+  # Indented Code Block
+  } else if ( match(block, /^(    |\t)[^\n]+(\n|$)((    |\t)[^\n]+(\n|$)|[ \t]*(\n|$))*/) ) {
+    len = RLENGTH; st = RSTART;
+    return _block( substr( block, len + 1 ) );
+
+  # Fenced Code Block (pandoc)
+  } else if ( match( block, /^(~~~+|```+)/ ) ) {
+    guard = substr( block, 1, RLENGTH );
+    code = gensub(/^[^\n]+\n/, "", 1, block);
+    if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) {
+      len = RLENGTH; st = RSTART;
+      return _block( substr( code, st + len ) );
+    } else {
+      match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ );
+      len = RLENGTH; st = RSTART;
+      return _block( substr(block, st + len) );
+    }
+
+  # Unordered list
+  } else if ( match( block, "^ ? ? ?[-+*][ \t]+[^\n]+(\n|$)" \
+                            "(([ \t]*\n)* ? ? ?[-+*][ \t]+[^\n]+(\n|$)" \
+                            "|([ \t]*\n)*( ? ? ?\t|  +)[^\n]+(\n|$)" \
+                            "|[^\n]+(\n|$))*" ) ) {
+  block = substr( block, RLENGTH + 1);
+  return _block( block );
+
+  # Ordered list
+  } else if ( match( block, "^ ? ? ?([0-9]+|#)\\.[ \t]+[^\n]+(\n|$)" \
+                            "(([ \t]*\n)* ? ? ?([0-9]+|#)\\.[ \t]+[^\n]+(\n|$)" \
+                            "|([ \t]*\n)*( ? ? ?\t|  +)[^\n]+(\n|$)" \
+                            "|[^\n]+(\n|$))*" ) ) {
+  block = substr( block, RLENGTH + 1);
+  return _block( block );
+
+  # First Order Heading
+  } else if ( match( block, /^[^\n]+\n===+(\n|$)/ ) ) {
+    len = RLENGTH;
+    HL[1]++; HL[2] = 0; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
+    return "<a class=\"toc h1\" href=\"#" HL[1] " - " HTML(gensub( /\n.*$/, "", "g", block )) "\">" inline( gensub( /\n.*$/, "", "g", block ) ) "</a>\n" \
+           _block( substr( block, len + 1 ) );
+
+  # Second Order Heading
+  } else if ( match( block, /^[^\n]+\n---+(\n|$)/ ) ) {
+    len = RLENGTH;
+    HL[2]++; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
+    return "<a class=\"toc h2\" href=\"#" HL[1] "." HL[2] " - " HTML(gensub( /\n.*$/, "", "g", block )) "\">" inline( gensub( /\n.*$/, "", "g", block ) ) "</a>\n" \
+           _block( substr( block, len + 1) );
+
+  # Nth Order Heading
+  } else if ( match( block, /^#{1,6}[ \t]*[^\n]+([ \t]*#*)(\n|$)/ ) ) {
+    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 "<a class=\"toc h" hlvl  "\" href=\"#" hid " - " HTML(htxt) "\">" inline( htxt ) "</a>\n" \
+           _block( substr( block, len + 1) );
+
+  # Horizontal rule
+  } else if ( match( block, /(^|\n) ? ? ?((\* *){3,}|(- *){3,}|(_ *){3,})($|\n)/) ) {
+    len = RLENGTH; st = RSTART;
+    return _block(substr(block, 1, st - 1)) _block(substr(block, st + len));
+
+  # Plain paragraph
+  } else {
+    match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ );
+    len = RLENGTH; st = RSTART;
+    return _block( substr(block, st + len) );
+  }
+}
+
+BEGIN {
+  # Global Vars
+  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;
+
+  # Buffering of full file ist necessary, e.g. to find reference links
+  while (getline) { file = file $0 "\n"; }
+  # Clean up MS-DOS line breaks
+  gsub(/\r\n/, "\n", file);
+
+  # Clear reflinks from File
+  re_reflink = "(^|\n) ? ? ?\\[([^]\n]+)\\]: ([^ \t\n]+)(\n?[ \t]+(\"([^\"]+)\"|'([^']+)'|\\(([^)]+)\\)))?(\n|$)";
+  while( gsub(re_reflink, "\n", file ) );
+
+  # Run Block Processing -> The Actual Markdown!
+  printf "%s", "<div class=\"macro toc\">\n" _block( file ) "</div>";
+}