From 89cae62dd158755e96acc517b2272dd113a19d8a Mon Sep 17 00:00:00 2001
From: "Kyle J. McKay" <mackyle@gmail.com>
Date: Sun, 14 Feb 2021 11:25:18 -0700
Subject: [PATCH] Markdown.pl: do not sequester top-level unmatched p

When running _HashHTMLBlocks, there's a step where we
"match any empty block tags that should have been paired."

Exclude "p" from that list.  Given a document like this:

  <p>
  text

That isolated "p" was getting sequestered away into its own
blob resulting in an output document like this:

  <p>

  </p><p>text</p>

By removing "p" from the list of "empty block tags that should
have been paired," we get this output instead:

  <p>
  text</p>

A nice improvement.

Signed-off-by: Kyle J. McKay <mackyle@gmail.com>
---
 Markdown.pl | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/Markdown.pl b/Markdown.pl
index f5a9a10..63eff11 100755
--- a/Markdown.pl
+++ b/Markdown.pl
@@ -1205,10 +1205,11 @@ sub _StripLinkDefinitions {
 }
 
 my %ok_tag_name; # initialized later
-my ($block_tags_a, $block_tags_b);
+my ($block_tags_a, $block_tags_b, $block_tags_c);
 BEGIN {
     $block_tags_a = qr/\020|p|div|center|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|ins|del/io;
     $block_tags_b = qr/\020|p|div|center|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math/io;
+    $block_tags_c = qr/div|center|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math/io;
 }
 
 sub _HashHTMLBlocks {
@@ -1284,7 +1285,7 @@ sub _HashHTMLBlocks {
 		(			# save in $1
 		    ^			# start of line (with /m)
 		    (?:\Q$idt\E)?	# optional lead in
-		    <(?:$block_tags_b)	# start tag = $2
+		    <($block_tags_c)	# start tag = $2
 		    \b			# word break
 		    (?:[^<>])*?		#
 		    /?>			# the matching end tag