<?php




class WP_Token_Map {
	
	const STORAGE_VERSION = '6.6.0-trunk';

	
	const MAX_LENGTH = 256;

	
	private $key_length = 2;

	
	private $large_words = array();

	
	private $groups = '';

	
	private $small_words = '';

	
	private $small_mappings = array();

	
	public static function from_array( array $mappings, int $key_length = 2 ): ?WP_Token_Map {
		$map             = new WP_Token_Map();
		$map->key_length = $key_length;

		// Start by grouping words.

		$groups = array();
		$shorts = array();
		foreach ( $mappings as $word => $mapping ) {
			if (
				self::MAX_LENGTH <= strlen( $word ) ||
				self::MAX_LENGTH <= strlen( $mapping )
			) {
				_doing_it_wrong(
					__METHOD__,
					sprintf(
						/* translators: 1: maximum byte length (a count) */
						__( 'Token Map tokens and substitutions must all be shorter than %1$d bytes.' ),
						self::MAX_LENGTH
					),
					'6.6.0'
				);
				return null;
			}

			$length = strlen( $word );

			if ( $key_length >= $length ) {
				$shorts[] = $word;
			} else {
				$group = substr( $word, 0, $key_length );

				if ( ! isset( $groups[ $group ] ) ) {
					$groups[ $group ] = array();
				}

				$groups[ $group ][] = array( substr( $word, $key_length ), $mapping );
			}
		}

		/*
		 * Sort the words to ensure that no smaller substring of a match masks the full match.
		 * For example, `Cap` should not match before `CapitalDifferentialD`.
		 */
		usort( $shorts, 'WP_Token_Map::longest_first_then_alphabetical' );
		foreach ( $groups as $group_key => $group ) {
			usort(
				$groups[ $group_key ],
				static function ( array $a, array $b ): int {
					return self::longest_first_then_alphabetical( $a[0], $b[0] );
				}
			);
		}

		// Finally construct the optimized lookups.

		foreach ( $shorts as $word ) {
			$map->small_words     .= str_pad( $word, $key_length + 1, "\x00", STR_PAD_RIGHT );
			$map->small_mappings[] = $mappings[ $word ];
		}

		$group_keys = array_keys( $groups );
		sort( $group_keys );

		foreach ( $group_keys as $group ) {
			$map->groups .= "{$group}\x00";

			$group_string = '';

			foreach ( $groups[ $group ] as $group_word ) {
				list( $word, $mapping ) = $group_word;

				$word_length    = pack( 'C', strlen( $word ) );
				$mapping_length = pack( 'C', strlen( $mapping ) );
				$group_string  .= "{$word_length}{$word}{$mapping_length}{$mapping}";
			}

			$map->large_words[] = $group_string;
		}

		return $map;
	}

	
	public static function from_precomputed_table( $state ): ?WP_Token_Map {
		$has_necessary_state = isset(
			$state['storage_version'],
			$state['key_length'],
			$state['groups'],
			$state['large_words'],
			$state['small_words'],
			$state['small_mappings']
		);

		if ( ! $has_necessary_state ) {
			_doing_it_wrong(
				__METHOD__,
				__( 'Missing required inputs to pre-computed WP_Token_Map.' ),
				'6.6.0'
			);
			return null;
		}

		if ( self::STORAGE_VERSION !== $state['storage_version'] ) {
			_doing_it_wrong(
				__METHOD__,
				/* translators: 1: version string, 2: version string. */
				sprintf( __( 'Loaded version \'%1$s\' incompatible with expected version \'%2$s\'.' ), $state['storage_version'], self::STORAGE_VERSION ),
				'6.6.0'
			);
			return null;
		}

		$map = new WP_Token_Map();

		$map->key_length     = $state['key_length'];
		$map->groups         = $state['groups'];
		$map->large_words    = $state['large_words'];
		$map->small_words    = $state['small_words'];
		$map->small_mappings = $state['small_mappings'];

		return $map;
	}

	
	public function contains( string $word, string $case_sensitivity = 'case-sensitive' ): bool {
		$ignore_case = 'ascii-case-insensitive' === $case_sensitivity;

		if ( $this->key_length >= strlen( $word ) ) {
			if ( 0 === strlen( $this->small_words ) ) {
				return false;
			}

			$term    = str_pad( $word, $this->key_length + 1, "\x00", STR_PAD_RIGHT );
			$word_at = $ignore_case ? stripos( $this->small_words, $term ) : strpos( $this->small_words, $term );
			if ( false === $word_at ) {
				return false;
			}

			return true;
		}

		$group_key = substr( $word, 0, $this->key_length );
		$group_at  = $ignore_case ? stripos( $this->groups, $group_key ) : strpos( $this->groups, $group_key );
		if ( false === $group_at ) {
			return false;
		}
		$group        = $this->large_words[ $group_at / ( $this->key_length + 1 ) ];
		$group_length = strlen( $group );
		$slug         = substr( $word, $this->key_length );
		$length       = strlen( $slug );
		$at           = 0;

		while ( $at < $group_length ) {
			$token_length   = unpack( 'C', $group[ $at++ ] )[1];
			$token_at       = $at;
			$at            += $token_length;
			$mapping_length = unpack( 'C', $group[ $at++ ] )[1];
			$mapping_at     = $at;

			if ( $token_length === $length && 0 === substr_compare( $group, $slug, $token_at, $token_length, $ignore_case ) ) {
				return true;
			}

			$at = $mapping_at + $mapping_length;
		}

		return false;
	}

	
	public function read_token( string $text, int $offset = 0, &$matched_token_byte_length = null, $case_sensitivity = 'case-sensitive' ): ?string {
		$ignore_case = 'ascii-case-insensitive' === $case_sensitivity;
		$text_length = strlen( $text );

		// Search for a long word first, if the text is long enough, and if that fails, a short one.
		if ( $text_length > $this->key_length ) {
			$group_key = substr( $text, $offset, $this->key_length );

			$group_at = $ignore_case ? stripos( $this->groups, $group_key ) : strpos( $this->groups, $group_key );
			if ( false === $group_at ) {
				// Perhaps a short word then.
				return strlen( $this->small_words ) > 0
					? $this->read_small_token( $text, $offset, $matched_token_byte_length, $case_sensitivity )
					: null;
			}

			$group        = $this->large_words[ $group_at / ( $this->key_length + 1 ) ];
			$group_length = strlen( $group );
			$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_at     = $at;

				if ( 0 === substr_compare( $text, $token, $offset + $this->key_length, $token_length, $ignore_case ) ) {
					$matched_token_byte_length = $this->key_length + $token_length;
					return substr( $group, $mapping_at, $mapping_length );
				}

				$at = $mapping_at + $mapping_length;
			}
		}

		// Perhaps a short word then.
		return strlen( $this->small_words ) > 0
			? $this->read_small_token( $text, $offset, $matched_token_byte_length, $case_sensitivity )
			: null;
	}

	
	private function read_small_token( string $text, int $offset = 0, &$matched_token_byte_length = null, $case_sensitivity = 'case-sensitive' ): ?string {
		$ignore_case  = 'ascii-case-insensitive' === $case_sensitivity;
		$small_length = strlen( $this->small_words );
		$search_text  = substr( $text, $offset, $this->key_length );
		if ( $ignore_case ) {
			$search_text = strtoupper( $search_text );
		}
		$starting_char = $search_text[0];

		$at = 0;
		while ( $at < $small_length ) {
			if (
				$starting_char !== $this->small_words[ $at ] &&
				( ! $ignore_case || strtoupper( $this->small_words[ $at ] ) !== $starting_char )
			) {
				$at += $this->key_length + 1;
				continue;
			}

			for ( $adjust = 1; $adjust < $this->key_length; $adjust++ ) {
				if ( "\x00" === $this->small_words[ $at + $adjust ] ) {
					$matched_token_byte_length = $adjust;
					return $this->small_mappings[ $at / ( $this->key_length + 1 ) ];
				}

				if (
					$search_text[ $adjust ] !== $this->small_words[ $at + $adjust ] &&
					( ! $ignore_case || strtoupper( $this->small_words[ $at + $adjust ] !== $search_text[ $adjust ] ) )
				) {
					$at += $this->key_length + 1;
					continue 2;
				}
			}

			$matched_token_byte_length = $adjust;
			return $this->small_mappings[ $at / ( $this->key_length + 1 ) ];
		}

		return null;
	}

	
	public function to_array(): array {
		$tokens = array();

		$at            = 0;
		$small_mapping = 0;
		$small_length  = strlen( $this->small_words );
		while ( $at < $small_length ) {
			$key            = rtrim( substr( $this->small_words, $at, $this->key_length + 1 ), "\x00" );
			$value          = $this->small_mappings[ $small_mapping++ ];
			$tokens[ $key ] = $value;

			$at += $this->key_length + 1;
		}

		foreach ( $this->large_words as $index => $group ) {
			$prefix       = substr( $this->groups, $index * ( $this->key_length + 1 ), 2 );
			$group_length = strlen( $group );
			$at           = 0;
			while ( $at < $group_length ) {
				$length = unpack( 'C', $group[ $at++ ] )[1];
				$key    = $prefix . substr( $group, $at, $length );

				$at    += $length;
				$length = unpack( 'C', $group[ $at++ ] )[1];
				$value  = substr( $group, $at, $length );

				$tokens[ $key ] = $value;
				$at            += $length;
			}
		}

		return $tokens;
	}

	
	public function precomputed_php_source_table( string $indent = "\t" ): string {
		$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;
	}

	
	private static function longest_first_then_alphabetical( string $a, string $b ): int {
		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 );
	}
}