Edit File by line

[500] Fix | Delete

* Example:

[501] Fix | Delete

[502] Fix | Delete

* while ( $at < strlen( $input ) ) {

[503] Fix | Delete

* $next_at = strpos( $input, ':', $at );

[504] Fix | Delete

* if ( false === $next_at ) {

[505] Fix | Delete

* break;

[506] Fix | Delete

* }

[507] Fix | Delete

[508] Fix | Delete

* $smily = $smilies->read_token( $input, $next_at, $token_byte_length );

[509] Fix | Delete

* if ( false === $next_at ) {

[510] Fix | Delete

* ++$at;

[511] Fix | Delete

* continue;

[512] Fix | Delete

* }

[513] Fix | Delete

[514] Fix | Delete

* $prefix = substr( $input, $at, $next_at - $at );

[515] Fix | Delete

* $at += $token_byte_length;

[516] Fix | Delete

* $output .= "{$prefix}{$smily}";

[517] Fix | Delete

* }

[518] Fix | Delete

[519] Fix | Delete

* @since 6.6.0

[520] Fix | Delete

[521] Fix | Delete

* @param string $text String in which to search for a lookup key.

[522] Fix | Delete

* @param int $offset Optional. How many bytes into the string where the lookup key ought to start. Default 0.

[523] Fix | Delete

* @param ?int &$matched_token_byte_length Optional. Holds byte-length of found token matched, otherwise not set. Default null.

[524] Fix | Delete

* @param string $case_sensitivity Optional. Pass 'ascii-case-insensitive' to ignore ASCII case when matching. Default 'case-sensitive'.

[525] Fix | Delete

* @return string|null Mapped value of lookup key if found, otherwise `null`.

[526] Fix | Delete

[527] Fix | Delete

public function read_token( $text, $offset = 0, &$matched_token_byte_length = null, $case_sensitivity = 'case-sensitive' ) {

[528] Fix | Delete

$ignore_case = 'ascii-case-insensitive' === $case_sensitivity;

[529] Fix | Delete

$text_length = strlen( $text );

[530] Fix | Delete

[531] Fix | Delete

// Search for a long word first, if the text is long enough, and if that fails, a short one.

[532] Fix | Delete

if ( $text_length > $this->key_length ) {

[533] Fix | Delete

$group_key = substr( $text, $offset, $this->key_length );

[534] Fix | Delete

[535] Fix | Delete

$group_at = $ignore_case ? stripos( $this->groups, $group_key ) : strpos( $this->groups, $group_key );

[536] Fix | Delete

if ( false === $group_at ) {

[537] Fix | Delete

// Perhaps a short word then.

[538] Fix | Delete

return strlen( $this->small_words ) > 0

[539] Fix | Delete

? $this->read_small_token( $text, $offset, $matched_token_byte_length, $case_sensitivity )

[540] Fix | Delete

: null;

[541] Fix | Delete

}

[542] Fix | Delete

[543] Fix | Delete

$group = $this->large_words[ $group_at / ( $this->key_length + 1 ) ];

[544] Fix | Delete

$group_length = strlen( $group );

[545] Fix | Delete

$at = 0;

[546] Fix | Delete

while ( $at < $group_length ) {

[547] Fix | Delete

$token_length = unpack( 'C', $group[ $at++ ] )[1];

[548] Fix | Delete

$token = substr( $group, $at, $token_length );

[549] Fix | Delete

$at += $token_length;

[550] Fix | Delete

$mapping_length = unpack( 'C', $group[ $at++ ] )[1];

[551] Fix | Delete

$mapping_at = $at;

[552] Fix | Delete

[553] Fix | Delete

if ( 0 === substr_compare( $text, $token, $offset + $this->key_length, $token_length, $ignore_case ) ) {

[554] Fix | Delete

$matched_token_byte_length = $this->key_length + $token_length;

[555] Fix | Delete

return substr( $group, $mapping_at, $mapping_length );

[556] Fix | Delete

}

[557] Fix | Delete

[558] Fix | Delete

$at = $mapping_at + $mapping_length;

[559] Fix | Delete

}

[560] Fix | Delete

}

[561] Fix | Delete

[562] Fix | Delete

// Perhaps a short word then.

[563] Fix | Delete

return strlen( $this->small_words ) > 0

[564] Fix | Delete

? $this->read_small_token( $text, $offset, $matched_token_byte_length, $case_sensitivity )

[565] Fix | Delete

: null;

[566] Fix | Delete

}

[567] Fix | Delete

[568] Fix | Delete

/**

[569] Fix | Delete

* Finds a match for a short word at the index.

[570] Fix | Delete

[571] Fix | Delete

* @since 6.6.0.

[572] Fix | Delete

[573] Fix | Delete

* @param string $text String in which to search for a lookup key.

[574] Fix | Delete

* @param int $offset Optional. How many bytes into the string where the lookup key ought to start. Default 0.

[575] Fix | Delete

* @param ?int &$matched_token_byte_length Optional. Holds byte-length of found lookup key if matched, otherwise not set. Default null.

[576] Fix | Delete

* @param string $case_sensitivity Optional. Pass 'ascii-case-insensitive' to ignore ASCII case when matching. Default 'case-sensitive'.

[577] Fix | Delete

* @return string|null Mapped value of lookup key if found, otherwise `null`.

[578] Fix | Delete

[579] Fix | Delete

private function read_small_token( $text, $offset, &$matched_token_byte_length, $case_sensitivity = 'case-sensitive' ) {

[580] Fix | Delete

$ignore_case = 'ascii-case-insensitive' === $case_sensitivity;

[581] Fix | Delete

$small_length = strlen( $this->small_words );

[582] Fix | Delete

$search_text = substr( $text, $offset, $this->key_length );

[583] Fix | Delete

if ( $ignore_case ) {

[584] Fix | Delete

$search_text = strtoupper( $search_text );

[585] Fix | Delete

}

[586] Fix | Delete

$starting_char = $search_text[0];

[587] Fix | Delete

[588] Fix | Delete

$at = 0;

[589] Fix | Delete

while ( $at < $small_length ) {

[590] Fix | Delete

if (

[591] Fix | Delete

$starting_char !== $this->small_words[ $at ] &&

[592] Fix | Delete

( ! $ignore_case || strtoupper( $this->small_words[ $at ] ) !== $starting_char )

[593] Fix | Delete

) {

[594] Fix | Delete

$at += $this->key_length + 1;

[595] Fix | Delete

continue;

[596] Fix | Delete

}

[597] Fix | Delete

[598] Fix | Delete

for ( $adjust = 1; $adjust < $this->key_length; $adjust++ ) {

[599] Fix | Delete

if ( "\x00" === $this->small_words[ $at + $adjust ] ) {

[600] Fix | Delete

$matched_token_byte_length = $adjust;

[601] Fix | Delete

return $this->small_mappings[ $at / ( $this->key_length + 1 ) ];

[602] Fix | Delete

}

[603] Fix | Delete

[604] Fix | Delete

if (

[605] Fix | Delete

$search_text[ $adjust ] !== $this->small_words[ $at + $adjust ] &&

[606] Fix | Delete

( ! $ignore_case || strtoupper( $this->small_words[ $at + $adjust ] !== $search_text[ $adjust ] ) )

[607] Fix | Delete

) {

[608] Fix | Delete

$at += $this->key_length + 1;

[609] Fix | Delete

continue 2;

[610] Fix | Delete

}

[611] Fix | Delete

}

[612] Fix | Delete

[613] Fix | Delete

$matched_token_byte_length = $adjust;

[614] Fix | Delete

return $this->small_mappings[ $at / ( $this->key_length + 1 ) ];

[615] Fix | Delete

}

[616] Fix | Delete

[617] Fix | Delete

return null;

[618] Fix | Delete

}

[619] Fix | Delete

[620] Fix | Delete

/**

[621] Fix | Delete

* Exports the token map into an associate array of key/value pairs.

[622] Fix | Delete

[623] Fix | Delete

* Example:

[624] Fix | Delete

[625] Fix | Delete

* $smilies->to_array() === array(

[626] Fix | Delete

* '8O' => '😯',

[627] Fix | Delete

* ':(' => '🙁',

[628] Fix | Delete

* ':)' => '🙂',

[629] Fix | Delete

* ':?' => '😕',

[630] Fix | Delete

* );

[631] Fix | Delete

[632] Fix | Delete

* @return array The lookup key/substitution values as an associate array.

[633] Fix | Delete

[634] Fix | Delete

public function to_array() {

[635] Fix | Delete

$tokens = array();

[636] Fix | Delete

[637] Fix | Delete

$at = 0;

[638] Fix | Delete

$small_mapping = 0;

[639] Fix | Delete

$small_length = strlen( $this->small_words );

[640] Fix | Delete

while ( $at < $small_length ) {

[641] Fix | Delete

$key = rtrim( substr( $this->small_words, $at, $this->key_length + 1 ), "\x00" );

[642] Fix | Delete

$value = $this->small_mappings[ $small_mapping++ ];

[643] Fix | Delete

$tokens[ $key ] = $value;

[644] Fix | Delete

[645] Fix | Delete

$at += $this->key_length + 1;

[646] Fix | Delete

}

[647] Fix | Delete

[648] Fix | Delete

foreach ( $this->large_words as $index => $group ) {

[649] Fix | Delete

$prefix = substr( $this->groups, $index * ( $this->key_length + 1 ), 2 );

[650] Fix | Delete

$group_length = strlen( $group );

[651] Fix | Delete

$at = 0;

[652] Fix | Delete

while ( $at < $group_length ) {

[653] Fix | Delete

$length = unpack( 'C', $group[ $at++ ] )[1];

[654] Fix | Delete

$key = $prefix . substr( $group, $at, $length );

[655] Fix | Delete

[656] Fix | Delete

$at += $length;

[657] Fix | Delete

$length = unpack( 'C', $group[ $at++ ] )[1];

[658] Fix | Delete

$value = substr( $group, $at, $length );

[659] Fix | Delete

[660] Fix | Delete

$tokens[ $key ] = $value;

[661] Fix | Delete

$at += $length;

[662] Fix | Delete

}

[663] Fix | Delete

}

[664] Fix | Delete

[665] Fix | Delete

return $tokens;

[666] Fix | Delete

}

[667] Fix | Delete

[668] Fix | Delete

/**

[669] Fix | Delete

* Export the token map for quick loading in PHP source code.

[670] Fix | Delete

[671] Fix | Delete

* This function has a specific purpose, to make loading of static token maps fast.

[672] Fix | Delete

* It's used to ensure that the HTML character reference lookups add a minimal cost

[673] Fix | Delete

* to initializing the PHP process.

[674] Fix | Delete

[675] Fix | Delete

* Example:

[676] Fix | Delete

[677] Fix | Delete

* echo $smilies->precomputed_php_source_table();

[678] Fix | Delete

[679] Fix | Delete

* // Output.

[680] Fix | Delete

* WP_Token_Map::from_precomputed_table(

[681] Fix | Delete

* array(

[682] Fix | Delete

* "storage_version" => "6.6.0",

[683] Fix | Delete

* "key_length" => 2,

[684] Fix | Delete

* "groups" => "",

[685] Fix | Delete

* "long_words" => array(),

[686] Fix | Delete

* "small_words" => "8O\x00:)\x00:(\x00:?\x00",

[687] Fix | Delete

* "small_mappings" => array( "😯", "🙂", "🙁", "😕" )

[688] Fix | Delete

* )

[689] Fix | Delete

* );

[690] Fix | Delete

[691] Fix | Delete

* @since 6.6.0

[692] Fix | Delete

[693] Fix | Delete

* @param string $indent Optional. Use this string for indentation, or rely on the default horizontal tab character. Default "\t".

[694] Fix | Delete

* @return string Value which can be pasted into a PHP source file for quick loading of table.

[695] Fix | Delete

[696] Fix | Delete

public function precomputed_php_source_table( $indent = "\t" ) {

[697] Fix | Delete

$i1 = $indent;

[698] Fix | Delete

$i2 = $i1 . $indent;

[699] Fix | Delete

$i3 = $i2 . $indent;

[700] Fix | Delete

[701] Fix | Delete

$class_version = self::STORAGE_VERSION;

[702] Fix | Delete

[703] Fix | Delete

$output = self::class . "::from_precomputed_table(\n";

[704] Fix | Delete

$output .= "{$i1}array(\n";

[705] Fix | Delete

$output .= "{$i2}\"storage_version\" => \"{$class_version}\",\n";

[706] Fix | Delete

$output .= "{$i2}\"key_length\" => {$this->key_length},\n";

[707] Fix | Delete

[708] Fix | Delete

$group_line = str_replace( "\x00", "\\x00", $this->groups );

[709] Fix | Delete

$output .= "{$i2}\"groups\" => \"{$group_line}\",\n";

[710] Fix | Delete

[711] Fix | Delete

$output .= "{$i2}\"large_words\" => array(\n";

[712] Fix | Delete

[713] Fix | Delete

$prefixes = explode( "\x00", $this->groups );

[714] Fix | Delete

foreach ( $prefixes as $index => $prefix ) {

[715] Fix | Delete

if ( '' === $prefix ) {

[716] Fix | Delete

break;

[717] Fix | Delete

}

[718] Fix | Delete

$group = $this->large_words[ $index ];

[719] Fix | Delete

$group_length = strlen( $group );

[720] Fix | Delete

$comment_line = "{$i3}//";

[721] Fix | Delete

$data_line = "{$i3}\"";

[722] Fix | Delete

$at = 0;

[723] Fix | Delete

while ( $at < $group_length ) {

[724] Fix | Delete

$token_length = unpack( 'C', $group[ $at++ ] )[1];

[725] Fix | Delete

$token = substr( $group, $at, $token_length );

[726] Fix | Delete

$at += $token_length;

[727] Fix | Delete

$mapping_length = unpack( 'C', $group[ $at++ ] )[1];

[728] Fix | Delete

$mapping = substr( $group, $at, $mapping_length );

[729] Fix | Delete

$at += $mapping_length;

[730] Fix | Delete

[731] Fix | Delete

$token_digits = str_pad( dechex( $token_length ), 2, '0', STR_PAD_LEFT );

[732] Fix | Delete

$mapping_digits = str_pad( dechex( $mapping_length ), 2, '0', STR_PAD_LEFT );

[733] Fix | Delete

[734] Fix | Delete

$mapping = preg_replace_callback(

[735] Fix | Delete

"~[\\x00-\\x1f\\x22\\x5c]~",

[736] Fix | Delete

static function ( $match_result ) {

[737] Fix | Delete

switch ( $match_result[0] ) {

[738] Fix | Delete

case '"':

[739] Fix | Delete

return '\\"';

[740] Fix | Delete

[741] Fix | Delete

case '\\':

[742] Fix | Delete

return '\\\\';

[743] Fix | Delete

[744] Fix | Delete

default:

[745] Fix | Delete

$hex = dechex( ord( $match_result[0] ) );

[746] Fix | Delete

return "\\x{$hex}";

[747] Fix | Delete

}

[748] Fix | Delete

[749] Fix | Delete

$mapping

[750] Fix | Delete

);

[751] Fix | Delete

[752] Fix | Delete

$comment_line .= " {$prefix}{$token}[{$mapping}]";

[753] Fix | Delete

$data_line .= "\\x{$token_digits}{$token}\\x{$mapping_digits}{$mapping}";

[754] Fix | Delete

}

[755] Fix | Delete

$comment_line .= ".\n";

[756] Fix | Delete

$data_line .= "\",\n";

[757] Fix | Delete

[758] Fix | Delete

$output .= $comment_line;

[759] Fix | Delete

$output .= $data_line;

[760] Fix | Delete

}

[761] Fix | Delete

[762] Fix | Delete

$output .= "{$i2}),\n";

[763] Fix | Delete

[764] Fix | Delete

$small_words = array();

[765] Fix | Delete

$small_length = strlen( $this->small_words );

[766] Fix | Delete

$at = 0;

[767] Fix | Delete

while ( $at < $small_length ) {

[768] Fix | Delete

$small_words[] = substr( $this->small_words, $at, $this->key_length + 1 );

[769] Fix | Delete

$at += $this->key_length + 1;

[770] Fix | Delete

}

[771] Fix | Delete

[772] Fix | Delete

$small_text = str_replace( "\x00", '\x00', implode( '', $small_words ) );

[773] Fix | Delete

$output .= "{$i2}\"small_words\" => \"{$small_text}\",\n";

[774] Fix | Delete

[775] Fix | Delete

$output .= "{$i2}\"small_mappings\" => array(\n";

[776] Fix | Delete

foreach ( $this->small_mappings as $mapping ) {

[777] Fix | Delete

$output .= "{$i3}\"{$mapping}\",\n";

[778] Fix | Delete

}

[779] Fix | Delete

$output .= "{$i2})\n";

[780] Fix | Delete

$output .= "{$i1})\n";

[781] Fix | Delete

$output .= ')';

[782] Fix | Delete

[783] Fix | Delete

return $output;

[784] Fix | Delete

}

[785] Fix | Delete

[786] Fix | Delete

/**

[787] Fix | Delete

* Compares two strings, returning the longest, or whichever

[788] Fix | Delete

* is first alphabetically if they are the same length.

[789] Fix | Delete

[790] Fix | Delete

* This is an important sort when building the token map because

[791] Fix | Delete

* it should not form a match on a substring of a longer potential

[792] Fix | Delete

* match. For example, it should not detect `Cap` when matching

[793] Fix | Delete

* against the string `CapitalDifferentialD`.

[794] Fix | Delete

[795] Fix | Delete

* @since 6.6.0

[796] Fix | Delete

[797] Fix | Delete

* @param string $a First string to compare.

[798] Fix | Delete

* @param string $b Second string to compare.

[799] Fix | Delete

* @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.

[800] Fix | Delete

[801] Fix | Delete

private static function longest_first_then_alphabetical( $a, $b ) {

[802] Fix | Delete

if ( $a === $b ) {

[803] Fix | Delete

return 0;

[804] Fix | Delete

}

[805] Fix | Delete

[806] Fix | Delete

$length_a = strlen( $a );

[807] Fix | Delete

$length_b = strlen( $b );

[808] Fix | Delete

[809] Fix | Delete

// Longer strings are less-than for comparison's sake.

[810] Fix | Delete

if ( $length_a !== $length_b ) {

[811] Fix | Delete

return $length_b - $length_a;

[812] Fix | Delete

}

[813] Fix | Delete

[814] Fix | Delete

return strcmp( $a, $b );

[815] Fix | Delete

}

[816] Fix | Delete

}

[817] Fix | Delete

[818] Fix | Delete