From 8298f9dad001744c995fe6a0046f88f94e2abcc7 Mon Sep 17 00:00:00 2001
From: Gary Pendergast <pento@git.wordpress.org>
Date: Tue, 2 Jul 2019 01:30:15 +0000
Subject: [PATCH] Clean up stray `<p>` tags added by `wpautop()` inside block
 level tags.

`autop()` can sometimes get confused and not clean up stray `<p>` or `</p>` tags inside block level elements, which produces sub-optimal HTML. While browsers can generally handle it, there's no need to make things harder for them if we don't have to.

Props pento, ayubi, pbearne, jond, azaozz, 1994rstefan, dionysous, MikeHansenMe, jorbin, miqrogroove, niallkennedy.
Fixes #27350.




git-svn-id: https://develop.svn.wordpress.org/trunk@45585 602fd350-edb4-49c9-b593-d223f7449a82
---
 src/wp-includes/formatting.php           | 15 ++++--
 tests/phpunit/tests/formatting/Autop.php | 59 ++++++++++++++++++++++++
 2 files changed, 70 insertions(+), 4 deletions(-)

diff --git a/src/wp-includes/formatting.php b/src/wp-includes/formatting.php
index 00782b1f33..15fef0d851 100644
--- a/src/wp-includes/formatting.php
+++ b/src/wp-includes/formatting.php
@@ -492,7 +492,8 @@ function wpautop( $pee, $br = true ) {
 	// Change multiple <br>s into two line breaks, which will turn into paragraphs.
 	$pee = preg_replace( '|<br\s*/?>\s*<br\s*/?>|', "\n\n", $pee );
 
-	$allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)';
+	$allblocks        = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)\b';
+	$allblocksexceptp = str_replace( '|p|', '|', $allblocks );
 
 	// Add a double line break above block-level opening tags.
 	$pee = preg_replace( '!(<' . $allblocks . '[\s/>])!', "\n\n$1", $pee );
@@ -558,12 +559,12 @@ function wpautop( $pee, $br = true ) {
 	// Under certain strange conditions it could create a P of entirely whitespace.
 	$pee = preg_replace( '|<p>\s*</p>|', '', $pee );
 
-	// Add a closing <p> inside <div>, <address>, or <form> tag if missing.
-	$pee = preg_replace( '!<p>([^<]+)</(div|address|form)>!', '<p>$1</p></$2>', $pee );
-
 	// If an opening or closing block element tag is wrapped in a <p>, unwrap it.
 	$pee = preg_replace( '!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', '$1', $pee );
 
+	// Add a closing <p> inside <div>, <address>, or <form> tag if missing.
+	$pee = preg_replace( '!<p>([^<]+)</(div|address|form)>!', '<p>$1</p></$2>', $pee );
+
 	// In some cases <li> may get wrapped in <p>, fix them.
 	$pee = preg_replace( '|<p>(<li.+?)</p>|', '$1', $pee );
 
@@ -577,6 +578,12 @@ function wpautop( $pee, $br = true ) {
 	// If an opening or closing block element tag is followed by a closing <p> tag, remove it.
 	$pee = preg_replace( '!(</?' . $allblocks . '[^>]*>)\s*</p>!', '$1', $pee );
 
+	// If a closing <p> tag is inside a block element tag, without a preceding opening <p> tag, remove it.
+	$pee = preg_replace( '#(<(' . $allblocksexceptp . ')[^>]*>)(((?!<p>|</\2>).)*)</p>#s', '$1$3', $pee );
+
+	// If an opening <p> tag is inside a block element tag, without a following closing <p> tag, remove it.
+	$pee = preg_replace( '#<p>(((?!</p>).)*</' . $allblocksexceptp . '>)#s', '$1', $pee );
+
 	// Optionally insert line breaks.
 	if ( $br ) {
 		// Replace newlines that shouldn't be touched with a placeholder.
diff --git a/tests/phpunit/tests/formatting/Autop.php b/tests/phpunit/tests/formatting/Autop.php
index e93e826695..bf1675f548 100644
--- a/tests/phpunit/tests/formatting/Autop.php
+++ b/tests/phpunit/tests/formatting/Autop.php
@@ -600,4 +600,63 @@ line 2<br/>
 
 		$this->assertEquals( $expected, trim( wpautop( $content ) ) );
 	}
+
+	/**
+	 * wpautop() should remove stray <p> and </p> tags inside blocks
+	 *
+	 * @ticket 27350
+	 * @dataProvider data_wpautop_removes_stray_p_tags_in_blocks
+	 */
+	function test_wpautop_removes_stray_p_tags_in_blocks( $data, $expected ) {
+		$this->assertEquals( $expected, wpautop( $data ) );
+	}
+
+	function data_wpautop_removes_stray_p_tags_in_blocks() {
+		return array(
+			array(
+				'<div><p>123</p> </div>',
+				"<div>\n<p>123</p>\n</div>\n",
+			),
+			array(
+				'<div><p>123</p></div>',
+				"<div>\n<p>123</p>\n</div>\n",
+			),
+			array(
+				'hello<div>test</div>',
+				"<p>hello</p>\n<div>test</div>\n",
+			),
+			array(
+				'<div><p>Hello world</p><span>WordPress</span></div>',
+				"<div>\n<p>Hello world</p>\n<span>WordPress</span></div>\n",
+			),
+			array(
+				"<div>hello\n<pre>test</pre>\nworld</div>",
+				"<div>hello\n<pre>test</pre>\n<p>world</p></div>\n",
+			),
+			array(
+				'hello<div>test</div>',
+				"<p>hello</p>\n<div>test</div>\n",
+			),
+			array(
+				'<div><img src="/wp-content/uploads/example.jpg" alt="something" /><div>Something</div></div>',
+				"<div><img src=\"/wp-content/uploads/example.jpg\" alt=\"something\" />\n<div>Something</div>\n</div>\n",
+			),
+			array(
+				'<div><span></span><div></div></div>',
+				"<div><span></span>\n<div></div>\n</div>\n",
+			),
+			array(
+				'<div>X<div></div></div>',
+				"<div>X\n<div></div>\n</div>\n",
+			),
+			array(
+				"<div><div></div>\n </div>",
+				"<div>\n<div></div>\n</div>\n",
+			),
+			array(
+				"[banner]\n<h1>Test</h1>",
+				"<p>[banner]</p>\n<h1>Test</h1>\n",
+			),
+		);
+	}
 }