0x2039, // 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK (‹). 0x0152, // 0x8C -> LATIN CAPITAL LIGATURE OE (Œ). 0x8D, // 0x8D -> (no change). 0x017D, // 0x8E -> LATIN CAPITAL LETTER Z WITH CARON (Ž). 0x8F, // 0x8F -> (no change). 0x90, // 0x90 -> (no change). 0x2018, // 0x91 -> LEFT SINGLE QUOTATION MARK (‘). 0x2019, // 0x92 -> RIGHT SINGLE QUOTATION MARK (’). 0x201C, // 0x93 -> LEFT DOUBLE QUOTATION MARK (“). 0x201D, // 0x94 -> RIGHT DOUBLE QUOTATION MARK (”). 0x2022, // 0x95 -> BULLET (•). 0x2013, // 0x96 -> EN DASH (–). 0x2014, // 0x97 -> EM DASH (—). 0x02DC, // 0x98 -> SMALL TILDE (˜). 0x2122, // 0x99 -> TRADE MARK SIGN (™). 0x0161, // 0x9A -> LATIN SMALL LETTER S WITH CARON (š). 0x203A, // 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK (›). 0x0153, // 0x9C -> LATIN SMALL LIGATURE OE (œ). 0x9D, // 0x9D -> (no change). 0x017E, // 0x9E -> LATIN SMALL LETTER Z WITH CARON (ž). 0x0178, // 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS (Ÿ). ); $code_point = $windows_1252_mapping[ $code_point - 0x80 ]; } $match_byte_length = $end_of_span - $at; return self::code_point_to_utf8_bytes( $code_point ); } /** Tracks inner parsing within the named character reference. */ $name_at = $at + 1; // Minimum named character reference is two characters. E.g. `GT`. if ( $name_at + 2 > $length ) { return null; } $name_length = 0; $replacement = $html5_named_character_references->read_token( $text, $name_at, $name_length ); if ( false === $replacement ) { return null; } $after_name = $name_at + $name_length; // If the match ended with a semicolon then it should always be decoded. if ( ';' === $text[ $name_at + $name_length - 1 ] ) { $match_byte_length = $after_name - $at; return $replacement; } /* * At this point though there's a match for an entry in the named * character reference table but the match doesn't end in `;`. * It may be allowed if it's followed by something unambiguous. */ $ambiguous_follower = ( $after_name < $length && $name_at < $length && ( ctype_alnum( $text[ $after_name ] ) || '=' === $text[ $after_name ] ) ); // It's non-ambiguous, safe to leave it in. if ( ! $ambiguous_follower ) { $match_byte_length = $after_name - $at; return $replacement; } // It's ambiguous, which isn't allowed inside attributes. if ( 'attribute' === $context ) { return null; } $match_byte_length = $after_name - $at; return $replacement; } /** * Encode a code point number into the UTF-8 encoding. * * This encoder implements the UTF-8 encoding algorithm for converting * a code point into a byte sequence. If it receives an invalid code * point it will return the Unicode Replacement Character U+FFFD `�`. * * Example: * * '🅰' === WP_HTML_Decoder::code_point_to_utf8_bytes( 0x1f170 ); * * // Half of a surrogate pair is an invalid code point. * '�' === WP_HTML_Decoder::code_point_to_utf8_bytes( 0xd83c ); * * @since 6.6.0 * * @see https://www.rfc-editor.org/rfc/rfc3629 For the UTF-8 standard. * * @param int $code_point Which code point to convert. * @return string Converted code point, or `�` if invalid. */ public static function code_point_to_utf8_bytes( $code_point ): string { // Pre-check to ensure a valid code point. if ( $code_point <= 0 || ( $code_point >= 0xD800 && $code_point <= 0xDFFF ) || $code_point > 0x10FFFF ) { return '�'; } if ( $code_point <= 0x7F ) { return chr( $code_point ); } if ( $code_point <= 0x7FF ) { $byte1 = chr( ( $code_point >> 6 ) | 0xC0 ); $byte2 = chr( $code_point & 0x3F | 0x80 ); return "{$byte1}{$byte2}"; } if ( $code_point <= 0xFFFF ) { $byte1 = chr( ( $code_point >> 12 ) | 0xE0 ); $byte2 = chr( ( $code_point >> 6 ) & 0x3F | 0x80 ); $byte3 = chr( $code_point & 0x3F | 0x80 ); return "{$byte1}{$byte2}{$byte3}"; } // Any values above U+10FFFF are eliminated above in the pre-check. $byte1 = chr( ( $code_point >> 18 ) | 0xF0 ); $byte2 = chr( ( $code_point >> 12 ) & 0x3F | 0x80 ); $byte3 = chr( ( $code_point >> 6 ) & 0x3F | 0x80 ); $byte4 = chr( $code_point & 0x3F | 0x80 ); return "{$byte1}{$byte2}{$byte3}{$byte4}"; } } Printables Archives - Page 4 of 4 - Keeping Life Sane Skip to Content

Printables