Changeset 59444 for trunk/tests/phpunit/tests/html-api/wpHtmlProcessor.php

Timestamp:

11/21/2024 01:27:58 PM (18 months ago)

Author:

Bernhard Reiter

Message:

HTML API: Add method to create fragment at node.

HTML Fragment parsing always happens with a context node, which may impact how a fragment of HTML is parsed. HTML Fragment Processors can be instantiated with a BODY context node via WP_HTML_Processor::create_fragment( $html ).

This changeset adds a static method called create_fragment_at_current_node( string $html_fragment ). It can only be called when the processor is paused at a #tag, with some additional constraints:

• The opening and closing tags must appear in the HTML input (no virtual tokens).
• No "self-contained" elements are allowed ( IFRAME, SCRIPT, TITLE, etc.).

If successful, the method will return a WP_HTML_Processor instance whose context is inherited from the node that the method was called from.

Props jonsurrell, bernhard-reiter, gziolo.
Fixes #62357.

File:

• trunk/tests/phpunit/tests/html-api/wpHtmlProcessor.php (modified) (1 diff)

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

@@ -1045 +1045 @@
 
     /**
+     * @ticket 62357
+     */
+    public function test_create_fragment_at_current_node_in_foreign_content() {
+        $processor = WP_HTML_Processor::create_full_parser( '<svg>' );
+        $this->assertTrue( $processor->next_tag( 'SVG' ) );
+
+        $fragment = $processor->create_fragment_at_current_node( "\0preceded-by-nul-byte<rect /><circle></circle><foreignobject><div></div></foreignobject><g>" );
+
+        $this->assertSame( 'svg', $fragment->get_namespace() );
+        $this->assertTrue( $fragment->next_token() );
+
+        /*
+         * In HTML parsing, a nul byte would be ignored.
+         * In SVG it should be replaced with a replacement character.
+         */
+        $this->assertSame( '#text', $fragment->get_token_type() );
+        $this->assertSame( "\u{FFFD}", $fragment->get_modifiable_text() );
+
+        $this->assertTrue( $fragment->next_tag( 'RECT' ) );
+        $this->assertSame( 'svg', $fragment->get_namespace() );
+
+        $this->assertTrue( $fragment->next_tag( 'CIRCLE' ) );
+        $this->assertSame( array( 'HTML', 'SVG', 'CIRCLE' ), $fragment->get_breadcrumbs() );
+        $this->assertTrue( $fragment->next_tag( 'foreignObject' ) );
+        $this->assertSame( 'svg', $fragment->get_namespace() );
+    }
+
+    /**
+     * @ticket 62357
+     */
+    public function test_create_fragment_at_current_node_in_foreign_content_integration_point() {
+        $processor = WP_HTML_Processor::create_full_parser( '<svg><foreignObject>' );
+        $this->assertTrue( $processor->next_tag( 'foreignObject' ) );
+
+        $fragment = $processor->create_fragment_at_current_node( "<image>\0not-preceded-by-nul-byte<rect />" );
+
+        // Nothing has been processed, the html namespace should be used for parsing as an integration point.
+        $this->assertSame( 'html', $fragment->get_namespace() );
+
+        // HTML parsing transforms IMAGE into IMG.
+        $this->assertTrue( $fragment->next_tag( 'IMG' ) );
+
+        $this->assertTrue( $fragment->next_token() );
+
+        // In HTML parsing, the nul byte is ignored and the text is reached.
+        $this->assertSame( '#text', $fragment->get_token_type() );
+        $this->assertSame( 'not-preceded-by-nul-byte', $fragment->get_modifiable_text() );
+
+        /*
+         * svg:foreignObject is an HTML integration point, so the processor should be in the HTML namespace.
+         * RECT is an HTML element here, meaning it may have the self-closing flag but does not self-close.
+         */
+        $this->assertTrue( $fragment->next_tag( 'RECT' ) );
+        $this->assertSame( array( 'HTML', 'FOREIGNOBJECT', 'RECT' ), $fragment->get_breadcrumbs() );
+        $this->assertSame( 'html', $fragment->get_namespace() );
+        $this->assertTrue( $fragment->has_self_closing_flag() );
+        $this->assertTrue( $fragment->expects_closer() );
+    }
+
+    /**
      * Ensure that lowercased tag_name query matches tags case-insensitively.
      *