Changeset 45585

Timestamp:

07/02/2019 01:30:15 AM (5 years ago)

Author:

pento

Message:

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.

Location:

trunk

Files:

• src/wp-includes/formatting.php (modified) (3 diffs)
• tests/phpunit/tests/formatting/Autop.php (modified) (1 diff)

trunk/src/wp-includes/formatting.php

@@ -493 +493 @@
     $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.
@@ -559 +560 @@
     $pee = preg_replace( '|<p>\s*</p>|', '', $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 );
-
-    // 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 );
 
     // In some cases <li> may get wrapped in <p>, fix them.
@@ -577 +578 @@
     // 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.

trunk/tests/phpunit/tests/formatting/Autop.php

@@ -601 +601 @@
         $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",
+            ),
+        );
+    }
 }