Changeset 61747

Timestamp:

02/26/2026 10:36:59 AM (7 weeks ago)

Author:

jonsurrell

Message:

HTML API: Preserve newlines when normalizing special elements.

Ensures normalization preserves content in PRE, LISTING, and TEXTAREA elements. These elements ignore a single leading newline during parsing. Normalization now injects a newline after the tag opener to trigger this behavior, preventing significant newlines from being incorrectly stripped.

Developed in ​https://github.com/WordPress/wordpress-develop/pull/10871.

Props jonsurrell, dmsnell, mukesh27.
Fixes #64607.

Location:

trunk

Files:

• src/wp-includes/html-api/class-wp-html-processor.php (modified) (1 diff)
• tests/phpunit/tests/html-api/wpHtmlProcessor-serialize.php (modified) (1 diff)

trunk/src/wp-includes/html-api/class-wp-html-processor.php

@@ -1415 +1415 @@
         $html .= '>';
 
+        /*
+         * The HTML parser strips a leading newline immediately after the start
+         * tag of TEXTAREA, PRE, and LISTING elements. When serializing, prepend
+         * a leading newline to ensure the semantic HTML content is preserved.
+         *
+         * For example, `<pre>\n\nX</pre>` must not become `<pre>\nX</pre>` because its content
+         * has changed. However, `<pre>X</pre>` and `<pre>\nX</pre>` are _equivalent_.
+         *
+         * > A start tag whose tag name is "textarea"
+         * >   …
+         * >   If the next token is a U+000A LINE FEED (LF) character token, then ignore
+         * >   that token and move on to the next one. (Newlines at the start of textarea
+         * >   elements are ignored as an authoring convenience.)
+         *
+         * > A start tag whose tag name is one of: "pre", "listing"
+         * >   …
+         * >   If the next token is a U+000A LINE FEED (LF) character token, then ignore
+         * >   that token and move on to the next one. (Newlines at the start of pre blocks
+         * >   are ignored as an authoring convenience.)
+         *
+         * @see https://html.spec.whatwg.org/multipage/parsing.html
+         */
+        if ( 'TEXTAREA' === $tag_name || 'PRE' === $tag_name || 'LISTING' === $tag_name ) {
+            $html .= "\n";
+        }
+
         // Flush out self-contained elements.
         if ( $in_html && in_array( $tag_name, array( 'IFRAME', 'NOEMBED', 'NOFRAMES', 'SCRIPT', 'STYLE', 'TEXTAREA', 'TITLE', 'XMP' ), true ) ) {

trunk/tests/phpunit/tests/html-api/wpHtmlProcessor-serialize.php

@@ -322 +322 @@
         );
     }
+
+    /**
+     * Ensures that leading newlines in PRE, LISTING, and TEXTAREA elements are preserved upon normalization,
+     * and that normalization is idempotent in these cases.
+     *
+     * @ticket 64607
+     *
+     * @dataProvider data_provider_normalize_special_leading_newline_cases
+     *
+     * @param string $input    HTML input containing leading newlines in PRE, LISTING, or TEXTAREA elements.
+     * @param string $expected Expected output after normalization, which should preserve leading newlines.
+     */
+    public function test_normalize_special_leading_newline_handling( string $input, string $expected ) {
+        $normalized = WP_HTML_Processor::normalize( $input );
+        $this->assertEqualHTML( $expected, $normalized );
+        $normalized_twice = WP_HTML_Processor::normalize( $normalized );
+        $this->assertEqualHTML( $expected, $normalized_twice );
+    }
+
+    /**
+     * Data provider.
+     *
+     * @return array[]
+     */
+    public static function data_provider_normalize_special_leading_newline_cases() {
+        return array(
+            'Leading newline in PRE'             => array(
+                "<pre>\nline 1\nline 2</pre>",
+                "<pre>line 1\nline 2</pre>",
+            ),
+            'Double leading newline in PRE'      => array(
+                "<pre>\n\nline 2\nline 3</pre>",
+                "<pre>\n\nline 2\nline 3</pre>",
+            ),
+            'Multiple text nodes inside PRE'     => array(
+                "<pre>\nline 1<!--comment--> still line 1</pre>",
+                '<pre>line 1<!--comment--> still line 1</pre>',
+            ),
+            'Multiple text nodes inside PRE with leading newlines' => array(
+                "<pre>\n\nline 2<!--comment--> still line 2</pre>",
+                "<pre>\n\nline 2<!--comment--> still line 2</pre>",
+            ),
+            'Leading newline in LISTING'         => array(
+                "<listing>\nline 1\nline 2</listing>",
+                "<listing>line 1\nline 2</listing>",
+            ),
+            'Double leading newline in LISTING'  => array(
+                "<listing>\n\nline 2\nline 3</listing>",
+                "<listing>\n\nline 2\nline 3</listing>",
+            ),
+            'Multiple text nodes inside LISTING' => array(
+                "<listing>\nline 1<!--comment--> still line 1</listing>",
+                '<listing>line 1<!--comment--> still line 1</listing>',
+            ),
+            'Multiple text nodes inside LISTING with leading newlines' => array(
+                "<listing>\n\nline 2<!--comment--> still line 2</listing>",
+                "<listing>\n\nline 2<!--comment--> still line 2</listing>",
+            ),
+            'Leading newline in TEXTAREA'        => array(
+                "<textarea>\nline 1\nline 2</textarea>",
+                "<textarea>line 1\nline 2</textarea>",
+            ),
+            'Double leading newline in TEXTAREA' => array(
+                "<textarea>\n\nline 2\nline 3</textarea>",
+                "<textarea>\n\nline 2\nline 3</textarea>",
+            ),
+        );
+    }
 }