From: Paul Hänsch <paul@plutz.net>
Date: Wed, 7 Jul 2021 11:55:31 +0000 (+0200)
Subject: HTML escaping, switchable HTML processing
X-Git-Url: https://git.plutz.net/?p=cgilite;a=commitdiff_plain;h=cd49a5ce71b79c56477dc351607484b0718fa594

HTML escaping, switchable HTML processing
---

diff --git a/markdown.awk b/markdown.awk
index 9c548ec..785ece8 100755
--- a/markdown.awk
+++ b/markdown.awk
@@ -24,7 +24,7 @@
 # - [x] Lists (ordered, unordered)
 # - [x] Code blocks (using indention)
 # - [x] Horizontal rules
-# - [x] Verbatim HTML block (gfm)
+# - [x] Verbatim HTML block (disabled by default)
 #
 # Basic Markdown - Inline elements:
 # ---------------------------------
@@ -35,8 +35,10 @@
 # - [x] Images / reference style images
 # - [x] <automatic links>
 # - [x] backslash escapes
-# - [x] Verbatim HTML inline
-# - [ ] HTML escaping
+# - [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:
 # ----------------------------
@@ -103,11 +105,6 @@ function inline( line, LOCAL, len, code, href, guard ) {
   } else if ( match(line, /^  \n/) ) {
     return "<br />\n" inline( substr(line, RLENGTH + 1) );
 
-  # Verbatim inline HTML
-  } else if ( 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));
-
   #  ``code spans``
   } else if ( match( line, /^`+/) ) {
     len = RLENGTH
@@ -229,6 +226,20 @@ function inline( line, LOCAL, len, code, href, guard ) {
     len = RLENGTH;
     return "<em>" inline( substr( line, 2, len - 2 ) ) "</em>" 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) );
@@ -242,24 +253,24 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent ) {
     return "";
 
   # HTML #2 #3 #4 $5
-  } else if ( match( block, /(^|\n) ? ? ?(<!--([^-]|-[^-]|--[^>])*(-->|$)|<\?([^\?]|\?[^>])*(\?>|$)|<![A-Z][^>]*(>|$)|<!\[CDATA\[([^\]]|\][^\]]|\]\][^>])*(\]\]>|$))/) ) {
+  } else if ( AllowHTML && match( block, /(^|\n) ? ? ?(<!--([^-]|-[^-]|--[^>])*(-->|$)|<\?([^\?]|\?[^>])*(\?>|$)|<![A-Z][^>]*(>|$)|<!\[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 ( 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|$)/) ) {
+  } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<\/?(address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset|h[123456]|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul)([[:space:]\n>]|\/>)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) {
     len = RLENGTH; st = RSTART;
     return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len));
 
   # HTML #1
-  } else if ( match( tolower(block), /(^|\n) ? ? ?<(script|pre|style)([[:space:]\n>]).*(<\/script>|<\/pre>|<\/style>|$)/) ) {
+  } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<(script|pre|style)([[:space:]\n>]).*(<\/script>|<\/pre>|<\/style>|$)/) ) {
     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 ( 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|$)/) ) {
+  } else if ( AllowHTML && match( block, /^ ? ? ?(<\/[A-Za-z][A-Za-z0-9-]*[[:space:]]*>|<[A-Za-z][A-Za-z0-9-]*([[:space:]]+[A-Za-z_:][A-Za-z0-9_\.:-]*([[:space:]]*=[[:space:]]*([[:space:]"'=<>`]+|"[^"]*"|'[^']*'))?)*[[:space:]]*\/?>)([[:space:]]*\n)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) {
     len = RLENGTH; st = RSTART;
     return substr(block, st, len) _block(substr(block, st + len));
 
@@ -391,6 +402,7 @@ function _list( block, last, LOCAL, p) {
 BEGIN {
   # Global Vars
   file = ""; rl_href[""] = ""; rl_title[""] = "";
+  if (ENVIRON["MD_HTML"] == "true") { AllowHTML = "true"; }
 
   # Buffering of full file ist necessary, e.g. to find reference links
   while (getline) { file = file $0 "\n"; }