Context Navigation

← Previous Change
Next Change →

canonicalCharset.php

Timestamp:

05/14/2024 06:03:43 PM (2 years ago)

Author:

dmsnell

Message:

Normalize UTF-8 charset slug detection.

There are several exist places in Core that attempt to detect if a blog charset
is UTF-8. Each place attempts to perform the same check, except the logic is
spread throughout and there's no single method provided to make this
determination in a consistent way. The _canonical_charset() method exists,
but is marked private for use.

In this patch the new unicode module provides is_utf8_charset() as a method
taking an optional charset slug and indicating if it represents UTF-8,
examining all of the allowable variants of that slug. Associated code is
updated to use this new function, including _canonical_charset(). If no slug
is provided, it will look up the current get_option( 'blog_charset' ).

Finally, the test functions governing _canonical_charset() have been
rewritten as a single test with a data provider instead of as separate test
functions.

Developed in https://github.com/WordPress/wordpress-develop/pull/6535
Discussed in https://core.trac.wordpress.org/ticket/61182

Fixes #61182.
Props dmsnell, jonsurrell.

File:

: 1 edited

trunk/tests/phpunit/tests/functions/canonicalCharset.php (modified) (1 diff)

Legend:

: Unmodified
: Added
: Removed

trunk/tests/phpunit/tests/functions/canonicalCharset.php

-              r56971
+              r58147
  */
 class Tests_Functions_CanonicalCharset extends WP_UnitTestCase {
+        public function test_utf_8_lower() {
+                $this->assertSame( 'UTF-8', _canonical_charset( 'utf-8' ) );
+        /**
+         * Ensures that charset variants for common encodings normalize to the expected form.
+         *
+         * @ticket 61182
+         *
+         * @dataProvider data_charset_normalizations
+         *
+         * @param string $given_charset      Potential charset provided by user.
+         * @param string $normalized_charset Expected normalized form of charset.
+         */
+        public function test_properly_normalizes_charset_variants( $given_charset, $normalized_charset ) {
+                $this->assertSame(
+                        $normalized_charset,
+                        _canonical_charset( $given_charset ),
+                        'Did not properly transform the provided charset into its normalized form.'
+                );
+        }
+        public function test_utf_8_upper() {
+                $this->assertSame( 'UTF-8', _canonical_charset( 'UTF-8' ) );
+        }
+        /**
+         * Data provider.
+         *
+         * @return array[].
+         */
+        public static function data_charset_normalizations() {
+                return array(
+                        // UTF-8 family.
+                        array( 'UTF-8', 'UTF-8' ),
+                        array( 'Utf-8', 'UTF-8' ),
+                        array( 'Utf-8', 'UTF-8' ),
+                        array( 'UTF8', 'UTF-8' ),
+        public function test_utf_8_mixxed() {
+                $this->assertSame( 'UTF-8', _canonical_charset( 'Utf-8' ) );
+        }
+                        // Almost UTF-8.
+                        array( 'UTF-8*', 'UTF-8*' ),
+                        array( 'UTF.8', 'UTF.8' ),
+                        array( 'UTF88', 'UTF88' ),
+                        array( 'UTF-7', 'UTF-7' ),
+                        array( 'X-UTF-8', 'X-UTF-8' ),
+        public function test_utf_8() {
+                $this->assertSame( 'UTF-8', _canonical_charset( 'UTF8' ) );
+        }
+                        // ISO-8859-1 family.
+                        array( 'iso-8859-1', 'ISO-8859-1' ),
+                        array( 'ISO-8859-1', 'ISO-8859-1' ),
+                        array( 'Iso-8859-1', 'ISO-8859-1' ),
+                        array( 'ISO8859-1', 'ISO-8859-1' ),
+        public function test_iso_lower() {
+                $this->assertSame( 'ISO-8859-1', _canonical_charset( 'iso-8859-1' ) );
+        }
+        public function test_iso_upper() {
+                $this->assertSame( 'ISO-8859-1', _canonical_charset( 'ISO-8859-1' ) );
+        }
+        public function test_iso_mixxed() {
+                $this->assertSame( 'ISO-8859-1', _canonical_charset( 'Iso8859-1' ) );
+        }
+        public function test_iso() {
+                $this->assertSame( 'ISO-8859-1', _canonical_charset( 'ISO8859-1' ) );
+        }
+        public function test_random() {
+                $this->assertSame( 'random', _canonical_charset( 'random' ) );
+        }
+        public function test_empty() {
+                $this->assertSame( '', _canonical_charset( '' ) );
+                        // Other charset slugs should not be adjusted.
+                        array( 'random', 'random' ),
+                        array( '', '' ),
+                );
+        }

Note: See TracChangeset for help on using the changeset viewer.

Make WordPress Core

Context Navigation

Changeset 58147 for trunk/tests/phpunit/tests/functions/canonicalCharset.php

Legend:

trunk/tests/phpunit/tests/functions/canonicalCharset.php

Download in other formats: