Changeset 56685

Timestamp:

09/25/2023 07:13:27 PM (14 months ago)

Author:

Bernhard Reiter

Message:

HTML API: Remove all duplicate copies of an attribute when removing.

When encountering an HTML tag with duplicate copies of an attribute the tag processor ignores the duplicate values, according to the specification. However, when removing an attribute it must remove all copies of that attribute lest one of the duplicates becomes the primary and it appears as if no attributes were removed.

In this patch we're adding tests that will be used to ensure that all attribute copies are removed from a tag when one is request to be removed.

Before

<?php
$p = new WP_HTML_Tag_Processor( '<br id=one id="two" id='three' id>' );
$p->next_tag();
$p->remove_attribute( 'id' );
$p->get_updated_html();
// <br id="two" id='three' id>

After

<?php
$p = new WP_HTML_Tag_Processor( '<br id=one id="two" id='three' id>' );
$p->next_tag();
$p->remove_attribute( 'id' );
$p->get_updated_html();
// <br>

Previously we have been overlooking duplicate attributes since they don't have an impact on what parses into the DOM. However, as one unit test affirmed (asserting the presence of the bug in the tag processor) when removing an attribute where duplicates exist this meant we ended up changing the value of an attribute instead of removing it.

In this patch we're tracking the text spans of the parsed duplicate attributes so that if we attempt to remove them then we'll have the appropriate information necessary to do so. When an attribute isn't removed we'll simply forget about the tracked duplicates. This involves some overhead for normal operation when in fact there are duplicate attributes on a tag, but that overhead is minimal in the form of integer pairs of indices for each duplicated attribute.

Props dmsnell, zieladam.
Merges [56684] to the 6.3 branch.
Fixes #58119.

Location:

branches/6.3

Files:

• src/wp-includes/html-api/class-wp-html-tag-processor.php (modified) (4 diffs)
• tests/phpunit/tests/html-api/wpHtmlTagProcessor.php (modified) (3 diffs)

branches/6.3/src/wp-includes/html-api/class-wp-html-tag-processor.php

@@ -406 +406 @@
      */
     private $attributes = array();
+
+    /**
+     * Tracks spans of duplicate attributes on a given tag, used for removing
+     * all copies of an attribute when calling `remove_attribute()`.
+     *
+     * @since 6.3.2
+     *
+     * @var (WP_HTML_Span[])[]|null
+     */
+    private $duplicate_attributes = null;
 
     /**
@@ -1287 +1297 @@
                 ! $has_value
             );
+
+            return true;
+        }
+
+        /*
+         * Track the duplicate attributes so if we remove it, all disappear together.
+         *
+         * While `$this->duplicated_attributes` could always be stored as an `array()`,
+         * which would simplify the logic here, storing a `null` and only allocating
+         * an array when encountering duplicates avoids needless allocations in the
+         * normative case of parsing tags with no duplicate attributes.
+         */
+        $duplicate_span = new WP_HTML_Span( $attribute_start, $attribute_end );
+        if ( null === $this->duplicate_attributes ) {
+            $this->duplicate_attributes = array( $comparable_name => array( $duplicate_span ) );
+        } elseif ( ! array_key_exists( $comparable_name, $this->duplicate_attributes ) ) {
+            $this->duplicate_attributes[ $comparable_name ] = array( $duplicate_span );
+        } else {
+            $this->duplicate_attributes[ $comparable_name ][] = $duplicate_span;
         }
 
@@ -1308 +1337 @@
     private function after_tag() {
         $this->get_updated_html();
-        $this->tag_name_starts_at = null;
-        $this->tag_name_length    = null;
-        $this->tag_ends_at        = null;
-        $this->is_closing_tag     = null;
-        $this->attributes         = array();
+        $this->tag_name_starts_at   = null;
+        $this->tag_name_length      = null;
+        $this->tag_ends_at          = null;
+        $this->is_closing_tag       = null;
+        $this->attributes           = array();
+        $this->duplicate_attributes = null;
     }
 
@@ -2081 +2111 @@
         );
 
+        // Removes any duplicated attributes if they were also present.
+        if ( null !== $this->duplicate_attributes && array_key_exists( $name, $this->duplicate_attributes ) ) {
+            foreach ( $this->duplicate_attributes[ $name ] as $attribute_token ) {
+                $this->lexical_updates[] = new WP_HTML_Text_Replacement(
+                    $attribute_token->start,
+                    $attribute_token->end,
+                    ''
+                );
+            }
+        }
+
         return true;
     }

branches/6.3/tests/phpunit/tests/html-api/wpHtmlTagProcessor.php

@@ -1050 +1050 @@
      * all its instances and output just `<div />`.
      *
-     * Today, however, WP_HTML_Tag_Processor only removes the first such attribute. It seems like a corner case
-     * and introducing additional complexity to correctly handle this scenario doesn't seem to be worth it.
-     * Let's revisit if and when this becomes a problem.
-     *
-     * This test is in place to confirm this behavior, which while incorrect, is well-defined.
-     * A later fix introduced to the Tag Processor should update this test to reflect the
-     * wanted and correct behavior.
-     *
-     * @ticket 56299
+     * @since 6.3.2 Removes all duplicated attributes as expected.
+     *
+     * @ticket 58119
      *
      * @covers WP_HTML_Tag_Processor::remove_attribute
@@ -1067 +1061 @@
         $p->remove_attribute( 'id' );
 
-        $this->assertSame(
-            '<div  id="ignored-id"><span id="second">Text</span></div>',
+        $this->assertStringNotContainsString(
+            'update-me',
             $p->get_updated_html(),
             'First attribute (when duplicates exist) was not removed'
@@ -1088 +1082 @@
             $p->get_updated_html(),
             'Attribute was not removed'
+        );
+    }
+
+    /**
+     * @ticket 58119
+     *
+     * @since 6.3.2 Removes all duplicated attributes as expected.
+     *
+     * @covers WP_HTML_Tag_Processor::remove_attribute
+     *
+     * @dataProvider data_html_with_duplicated_attributes
+     */
+    public function test_remove_attribute_with_duplicated_attributes_removes_all_of_them( $html_with_duplicate_attributes, $attribute_to_remove ) {
+        $p = new WP_HTML_Tag_Processor( $html_with_duplicate_attributes );
+        $p->next_tag();
+
+        $p->remove_attribute( $attribute_to_remove );
+        $this->assertNull( $p->get_attribute( $attribute_to_remove ), 'Failed to remove all copies of an attribute when duplicated in modified source.' );
+
+        // Recreate a tag processor with the updated HTML after removing the attribute.
+        $p = new WP_HTML_Tag_Processor( $p->get_updated_html() );
+        $p->next_tag();
+        $this->assertNull( $p->get_attribute( $attribute_to_remove ), 'Failed to remove all copies of duplicated attributes when getting updated HTML.' );
+    }
+
+    /**
+     * @ticket 58119
+     *
+     * @since 6.3.2 Removes all duplicated attributes as expected.
+     *
+     * @covers WP_HTML_Tag_Processor::remove_attribute
+     */
+    public function test_previous_duplicated_attributes_are_not_removed_on_successive_tag_removal() {
+        $p = new WP_HTML_Tag_Processor( '<span id=one id=two id=three><span id=four>' );
+        $p->next_tag();
+        $p->next_tag();
+        $p->remove_attribute( 'id' );
+
+        $this->assertSame( '<span id=one id=two id=three><span >', $p->get_updated_html() );
+    }
+
+    /**
+     * Data provider.
+     *
+     * @ticket 58119
+     *
+     * @return array[].
+     */
+    public function data_html_with_duplicated_attributes() {
+        return array(
+            'Double attributes'               => array( '<div id=one id=two>', 'id' ),
+            'Triple attributes'               => array( '<div id=one id=two id=three>', 'id' ),
+            'Duplicates around another'       => array( '<img src="test.png" alt="kites flying in the wind" src="kites.jpg">', 'src' ),
+            'Case-variants of attribute'      => array( '<button disabled inert DISABLED dISaBled INERT DisABleD>', 'disabled' ),
+            'Case-variants of attribute name' => array( '<button disabled inert DISABLED dISaBled INERT DisABleD>', 'DISABLED' ),
         );
     }