6.6.0 * * @param string $indent Optional. Use this string for indentation, or rely on the default horizontal tab character. Default "\t". * @return string Value which can be pasted into a PHP source file for quick loading of table. */ public function precomputed_php_source_table( $indent = "\t" ) { $i1 = $indent; $i2 = $i1 . $indent; $i3 = $i2 . $indent; $class_version = self::STORAGE_VERSION; $output = self::class . "::from_precomputed_table(\n"; $output .= "{$i1}array(\n"; $output .= "{$i2}\"storage_version\" => \"{$class_version}\",\n"; $output .= "{$i2}\"key_length\" => {$this->key_length},\n"; $group_line = str_replace( "\x00", "\\x00", $this->groups ); $output .= "{$i2}\"groups\" => \"{$group_line}\",\n"; $output .= "{$i2}\"large_words\" => array(\n"; $prefixes = explode( "\x00", $this->groups ); foreach ( $prefixes as $index => $prefix ) { if ( '' === $prefix ) { break; } $group = $this->large_words[ $index ]; $group_length = strlen( $group ); $comment_line = "{$i3}//"; $data_line = "{$i3}\""; $at = 0; while ( $at < $group_length ) { $token_length = unpack( 'C', $group[ $at++ ] )[1]; $token = substr( $group, $at, $token_length ); $at += $token_length; $mapping_length = unpack( 'C', $group[ $at++ ] )[1]; $mapping = substr( $group, $at, $mapping_length ); $at += $mapping_length; $token_digits = str_pad( dechex( $token_length ), 2, '0', STR_PAD_LEFT ); $mapping_digits = str_pad( dechex( $mapping_length ), 2, '0', STR_PAD_LEFT ); $mapping = preg_replace_callback( "~[\\x00-\\x1f\\x22\\x5c]~", static function ( $match_result ) { switch ( $match_result[0] ) { case '"': return '\\"'; case '\\': return '\\\\'; default: $hex = dechex( ord( $match_result[0] ) ); return "\\x{$hex}"; } }, $mapping ); $comment_line .= " {$prefix}{$token}[{$mapping}]"; $data_line .= "\\x{$token_digits}{$token}\\x{$mapping_digits}{$mapping}"; } $comment_line .= ".\n"; $data_line .= "\",\n"; $output .= $comment_line; $output .= $data_line; } $output .= "{$i2}),\n"; $small_words = array(); $small_length = strlen( $this->small_words ); $at = 0; while ( $at < $small_length ) { $small_words[] = substr( $this->small_words, $at, $this->key_length + 1 ); $at += $this->key_length + 1; } $small_text = str_replace( "\x00", '\x00', implode( '', $small_words ) ); $output .= "{$i2}\"small_words\" => \"{$small_text}\",\n"; $output .= "{$i2}\"small_mappings\" => array(\n"; foreach ( $this->small_mappings as $mapping ) { $output .= "{$i3}\"{$mapping}\",\n"; } $output .= "{$i2})\n"; $output .= "{$i1})\n"; $output .= ')'; return $output; } /** * Compares two strings, returning the longest, or whichever * is first alphabetically if they are the same length. * * This is an important sort when building the token map because * it should not form a match on a substring of a longer potential * match. For example, it should not detect `Cap` when matching * against the string `CapitalDifferentialD`. * * @since 6.6.0 * * @param string $a First string to compare. * @param string $b Second string to compare. * @return int -1 or lower if `$a` is less than `$b`; 1 or greater if `$a` is greater than `$b`, and 0 if they are equal. */ private static function longest_first_then_alphabetical( $a, $b ) { if ( $a === $b ) { return 0; } $length_a = strlen( $a ); $length_b = strlen( $b ); // Longer strings are less-than for comparison's sake. if ( $length_a !== $length_b ) { return $length_b - $length_a; } return strcmp( $a, $b ); } }