Ticket #21212: 21212-emoji.diff

src/wp-admin/includes/post.php

@@ -325 +325 @@
 
                 foreach( $fields as $field ) {
                         if ( isset( $post_data[ $field ] ) ) {
+                                $charset = $wpdb->get_col_charset( $wpdb->posts, $field );
+                                if ( 'utf8' === $charset ) {
+                                        $post_data[ $field ] = wp_encode_emoji( $post_data[ $field ] );
+                                }
                                 $post_data[ $field ] = $wpdb->strip_invalid_text_for_column( $wpdb->posts, $field, $post_data[ $field ] );
                         }
                 }

src/wp-includes/formatting.php

@@ -3318 +3318 @@
 
                 case 'blogdescription':
                 case 'blogname':
+                        $charset = $wpdb->get_col_charset( $wpdb->options, 'option_value' );
+                        if ( 'utf8' === $charset ) {
+                                $value = wp_encode_emoji( $value );
+                        }
                         $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
                         $value = wp_kses_post( $value );
                         $value = esc_html( $value );
@@ -4015 +4019 @@
 
         return $spaces;
 }
+
+/**
+ * Convert any 4 byte emoji in a string to their equivalent HTML entitiy.
+ *
+ * This allows us to store emoji in a DB using the utf8 character set.
+ *
+ * @since 4.2.0
+ * @param  string $content The content to encode
+ * @return string The encoded content
+ */
+function wp_encode_emoji( $content ) {
+        if ( function_exists( 'mb_convert_encoding' ) ) {
+                $regex = '/(
+                          \x23\xE2\x83\xA3               # Digits
+                          [\x30-\x39]\xE2\x83\xA3
+                        | \xF0\x9F[\x85-\x88][\xB0-\xBF] # Enclosed characters
+                        | \xF0\x9F[\x8C-\x97][\x80-\xBF] # Misc
+                        | \xF0\x9F\x98[\x80-\xBF]        # Smilies
+                        | \xF0\x9F\x99[\x80-\x8F]
+                        | \xF0\x9F\x9A[\x80-\xBF]        # Transport and map symbols
+                        | \xF0\x9F\x99[\x80-\x85]
+                )/x';
+                $matches = array();
+                if ( preg_match_all( $regex, $content, $matches ) ) {
+                        if ( ! empty( $matches[1] ) ) {
+                                foreach( $matches[1] as $emoji ) {
+                                        $unpacked = unpack( 'H*', mb_convert_encoding( $emoji, 'UTF-32', 'UTF-8' ) );
+                                        if ( isset( $unpacked[1] ) ) {
+                                                $entity = '&#x' . trim( $unpacked[1], '0' ) . ';';
+                                                $content = str_replace( $emoji, $entity, $content );
+                                        }
+                                }
+                        }
+                }
+        }
+
+        return $content;
+}
+ No newline at end of file

tests/phpunit/tests/formatting/Emoji.php

@@ +1 @@
+<?php
+
+/**
+ * @group formatting
+ * @group emoji
+ */
+class Tests_Formatting_Emoji extends WP_UnitTestCase {
+        public function test_emoji_encoding() {
+                $content = "foo\xf0\x9f\x98\x89bar";
+                $expected = "foo&#x1f609;bar";
+                $encoded = wp_encode_emoji( $content );
+                $this->assertEquals( $expected, $encoded );
+        }
+
+        public function test_non_emoji_encoding() {
+                $content = "foo\xe5\x85\xb1bar";
+                $encoded = wp_encode_emoji( $content );
+                $this->assertEquals( $content, $encoded );
+        }
+}