Changeset 58281 for trunk/tests/phpunit/tests/html-api/wpHtmlProcessorHtml5lib.php

Timestamp:

06/02/2024 03:14:35 PM (21 months ago)

Author:

dmsnell

Message:

HTML API: Add custom text decoder.

Provides a custom decoder for strings coming from HTML attributes and
markup. This custom decoder is necessary because of deficiencies in
PHP's html_entity_decode() function:

• It isn't aware of 720 of the possible named character references in HTML, leaving many out that should be translated.

• It isn't aware of the ambiguous ampersand rule, which allows conversion of character references in certain contexts when they are missing their closing ;.

• It doesn't draw a distinction for the ambiguous ampersand rule when decoding attribute values instead of markup values.

• Use of html_entity_decode() requires manually passing non-default paramter values to ensure it decodes properly.

This decoder also provides some conveniences, such as making a
single-pass and interruptable decode operation possible. This will
provide a number of opportunities to optimize detection and decoding
of things like value prefixes, and whether a value contains a given
substring.

Developed in ​https://github.com/WordPress/wordpress-develop/pull/6387
Discussed in https://core.trac.wordpress.org/ticket/61072

Props dmsnell, gziolo, jonsurrell, jorbin, westonruter, zieladam.
Fixes #61072.

File:

• trunk/tests/phpunit/tests/html-api/wpHtmlProcessorHtml5lib.php (modified) (2 diffs)

trunk/tests/phpunit/tests/html-api/wpHtmlProcessorHtml5lib.php

@@ -32 +32 @@
      */
     const SKIP_TESTS = array(
-        'adoption01/line0046'        => 'Unimplemented: Reconstruction of active formatting elements.',
-        'adoption01/line0159'        => 'Unimplemented: Reconstruction of active formatting elements.',
-        'adoption01/line0318'        => 'Unimplemented: Reconstruction of active formatting elements.',
-        'entities02/line0100'        => 'Encoded characters without semicolon termination in attribute values are not handled properly',
-        'entities02/line0114'        => 'Encoded characters without semicolon termination in attribute values are not handled properly',
-        'entities02/line0128'        => 'Encoded characters without semicolon termination in attribute values are not handled properly',
-        'entities02/line0142'        => 'Encoded characters without semicolon termination in attribute values are not handled properly',
-        'entities02/line0156'        => 'Encoded characters without semicolon termination in attribute values are not handled properly',
-        'inbody01/line0001'          => 'Bug.',
-        'inbody01/line0014'          => 'Bug.',
-        'inbody01/line0029'          => 'Bug.',
-        'menuitem-element/line0012'  => 'Bug.',
-        'plain-text-unsafe/line0001' => 'HTML entities may be mishandled.',
-        'plain-text-unsafe/line0105' => 'Binary.',
-        'tests1/line0342'            => "Closing P tag implicitly creates opener, which we don't visit.",
-        'tests1/line0720'            => 'Unimplemented: Reconstruction of active formatting elements.',
-        'tests1/line0833'            => 'Bug.',
-        'tests15/line0001'           => 'Unimplemented: Reconstruction of active formatting elements.',
-        'tests15/line0022'           => 'Unimplemented: Reconstruction of active formatting elements.',
-        'tests2/line0317'            => 'HTML entities may be mishandled.',
-        'tests2/line0408'            => 'HTML entities may be mishandled.',
-        'tests2/line0650'            => 'Whitespace only test never enters "in body" parsing mode.',
-        'tests20/line0497'           => "Closing P tag implicitly creates opener, which we don't visit.",
-        'tests23/line0001'           => 'Unimplemented: Reconstruction of active formatting elements.',
-        'tests23/line0041'           => 'Unimplemented: Reconstruction of active formatting elements.',
-        'tests23/line0069'           => 'Unimplemented: Reconstruction of active formatting elements.',
-        'tests23/line0101'           => 'Unimplemented: Reconstruction of active formatting elements.',
-        'tests25/line0169'           => 'Bug.',
-        'tests26/line0263'           => 'Bug: An active formatting element should be created for a trailing text node.',
-        'tests7/line0354'            => 'Bug.',
-        'tests8/line0001'            => 'Bug.',
-        'tests8/line0020'            => 'Bug.',
-        'tests8/line0037'            => 'Bug.',
-        'tests8/line0052'            => 'Bug.',
-        'webkit01/line0174'          => 'Bug.',
+        'adoption01/line0046'       => 'Unimplemented: Reconstruction of active formatting elements.',
+        'adoption01/line0159'       => 'Unimplemented: Reconstruction of active formatting elements.',
+        'adoption01/line0318'       => 'Unimplemented: Reconstruction of active formatting elements.',
+        'inbody01/line0001'         => 'Bug.',
+        'inbody01/line0014'         => 'Bug.',
+        'inbody01/line0029'         => 'Bug.',
+        'menuitem-element/line0012' => 'Bug.',
+        'tests1/line0342'           => "Closing P tag implicitly creates opener, which we don't visit.",
+        'tests1/line0720'           => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests1/line0833'           => 'Bug.',
+        'tests15/line0001'          => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests15/line0022'          => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests2/line0650'           => 'Whitespace only test never enters "in body" parsing mode.',
+        'tests20/line0497'          => "Closing P tag implicitly creates opener, which we don't visit.",
+        'tests23/line0001'          => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests23/line0041'          => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests23/line0069'          => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests23/line0101'          => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests25/line0169'          => 'Bug.',
+        'tests26/line0263'          => 'Bug: An active formatting element should be created for a trailing text node.',
+        'tests7/line0354'           => 'Bug.',
+        'tests8/line0001'           => 'Bug.',
+        'tests8/line0020'           => 'Bug.',
+        'tests8/line0037'           => 'Bug.',
+        'tests8/line0052'           => 'Bug.',
+        'webkit01/line0174'         => 'Bug.',
     );
 
@@ -105 +96 @@
         while ( false !== ( $entry = readdir( $handle ) ) ) {
             if ( ! stripos( $entry, '.dat' ) ) {
-                continue;
-            }
-
-            if ( 'entities01.dat' === $entry || 'entities02.dat' === $entry ) {
                 continue;
             }