From: Paul Hänsch <paul@plutz.net>
Date: Tue, 6 Jul 2021 23:26:12 +0000 (+0200)
Subject: md: inline HTML
X-Git-Url: https://git.plutz.net/?p=cgilite;a=commitdiff_plain;h=4f5d122dad9b7a66bafa4fea7c340f3ea1d06fc5

md: inline HTML
---

diff --git a/markdown.awk b/markdown.awk
index d1de2c3..9c548ec 100755
--- a/markdown.awk
+++ b/markdown.awk
@@ -35,7 +35,8 @@
 # - [x] Images / reference style images
 # - [x] <automatic links>
 # - [x] backslash escapes
-# - [ ] Verbatim HTML inline
+# - [x] Verbatim HTML inline
+# - [ ] HTML escaping
 #
 # Extensions - Block elements:
 # ----------------------------
@@ -102,6 +103,11 @@ 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
@@ -235,23 +241,8 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent ) {
   if ( block == "" ) {
     return "";
 
-  # HTML #2
-  } else if ( match( block, /(^|\n) ? ? ?<!--([^-]|-[^-]|--[^>])*(-->|$)/) ) {
-    len = RLENGTH; st = RSTART;
-    return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len));
-
-  # HTML #3
-  } else if ( match( block, /(^|\n) ? ? ?<\?([^\?]|\?[^>])*(\?>|$)/) ) {
-    len = RLENGTH; st = RSTART;
-    return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len));
-
-  # HTML #4
-  } else if ( match( block, /(^|\n) ? ? ?<![A-Z][^>]*(>|$)/) ) {
-    len = RLENGTH; st = RSTART;
-    return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len));
-
-  # HTML #5
-  } else if ( match( block, /(^|\n) ? ? ?<!\[CDATA\[([^\]]|\][^\]]|\]\][^>])*(\]\]>|$)/) ) {
+  # HTML #2 #3 #4 $5
+  } else if ( match( block, /(^|\n) ? ? ?(<!--([^-]|-[^-]|--[^>])*(-->|$)|<\?([^\?]|\?[^>])*(\?>|$)|<![A-Z][^>]*(>|$)|<!\[CDATA\[([^\]]|\][^\]]|\]\][^>])*(\]\]>|$))/) ) {
     len = RLENGTH; st = RSTART;
     return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len));
 
@@ -268,7 +259,7 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent ) {
     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-]* \t]*>|<[A-Za-z][A-Za-z0-9-]*([ \t]+[A-Za-z_:][A-Za-z0-9_\.:-]*[ \t]*=[ \t]*([[:space:]"'=<>`]+|"[^"]*"|'[^']*'))*[ \t]*\/?>)([[:space:]]*\n)([^\n]|\n[[:space:]]*[^\n])*(\n[ \t]*\n|$)/) ) {
+  } else if ( match( block, /^ ? ? ?(<\/[A-Za-z][A-Za-z0-9-]*[[:space:]]*>|<[A-Za-z][A-Za-z0-9-]*([[:space:]]+[A-Za-z_:][A-Za-z0-9_\.:-]*([[:space:]]*=[[:space:]]*([[:space:]"'=<>`]+|"[^"]*"|'[^']*'))?)*[[:space:]]*\/?>)([[:space:]]*\n)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) {
     len = RLENGTH; st = RSTART;
     return substr(block, st, len) _block(substr(block, st + len));