/home/techb158/primomovers.ca/wp-includes
Edit: /home/techb158/primomovers.ca/wp-includes/utf8.php (6977B)
=' )
) :
/**
* Replaces ill-formed UTF-8 byte sequences with the Unicode Replacement Character.
*
* Knowing what to do in the presence of text encoding issues can be complicated.
* This function replaces invalid spans of bytes to neutralize any corruption that
* may be there and prevent it from causing further problems downstream.
*
* However, it’s not always ideal to replace those bytes. In some settings it may
* be best to leave the invalid bytes in the string so that downstream code can handle
* them in a specific way. Replacing the bytes too early, like escaping for HTML too
* early, can introduce other forms of corruption and data loss.
*
* When in doubt, use this function to replace spans of invalid bytes.
*
* Replacement follows the “maximal subpart” algorithm for secure and interoperable
* strings. This can lead to sequences of multiple replacement characters in a row.
*
* Example:
*
* // Valid strings come through unchanged.
* 'test' === wp_scrub_utf8( 'test' );
*
* // Invalid sequences of bytes are replaced.
* $invalid = "the byte \xC0 is never allowed in a UTF-8 string.";
* "the byte \u{FFFD} is never allowed in a UTF-8 string." === wp_scrub_utf8( $invalid, true );
* 'the byte � is never allowed in a UTF-8 string.' === wp_scrub_utf8( $invalid, true );
*
* // Maximal subparts are replaced individually.
* '.�.' === wp_scrub_utf8( ".\xC0." ); // C0 is never valid.
* '.�.' === wp_scrub_utf8( ".\xE2\x8C." ); // Missing A3 at end.
* '.��.' === wp_scrub_utf8( ".\xE2\x8C\xE2\x8C." ); // Maximal subparts replaced separately.
* '.��.' === wp_scrub_utf8( ".\xC1\xBF." ); // Overlong sequence.
* '.���.' === wp_scrub_utf8( ".\xED\xA0\x80." ); // Surrogate half.
*
* Note! The Unicode Replacement Character is itself a Unicode character (U+FFFD).
* Once a span of invalid bytes has been replaced by one, it will not be possible
* to know whether the replacement character was originally intended to be there
* or if it is the result of scrubbing bytes. It is ideal to leave replacement for
* display only, but some contexts (e.g. generating XML or passing data into a
* large language model) require valid input strings.
*
* @since 6.9.0
*
* @see https://www.unicode.org/versions/Unicode16.0.0/core-spec/chapter-5/#G40630
*
* @param string $text String which is assumed to be UTF-8 but may contain invalid sequences of bytes.
* @return string Input text with invalid sequences of bytes replaced with the Unicode replacement character.
*/
function wp_scrub_utf8( $text ) {
/*
* While it looks like setting the substitute character could fail,
* the internal PHP code will never fail when provided a valid
* code point as a number. In this case, there’s no need to check
* its return value to see if it succeeded.
*/
$prev_replacement_character = mb_substitute_character();
mb_substitute_character( 0xFFFD );
$scrubbed = mb_scrub( $text, 'UTF-8' );
mb_substitute_character( $prev_replacement_character );
return $scrubbed;
}
else :
/**
* Fallback function for scrubbing UTF-8.
*
* @ignore
* @private
*
* @since 6.9.0
*/
function wp_scrub_utf8( $text ) {
return _wp_scrub_utf8_fallback( $text );
}
endif;
/**
* Returns whether the given string contains Unicode noncharacters.
*
* XML recommends against using noncharacters and HTML forbids their
* use in attribute names. Unicode recommends that they not be used
* in open exchange of data.
*
* Noncharacters are code points within the following ranges:
* - U+FDD0–U+FDEF
* - U+FFFE–U+FFFF
* - U+1FFFE, U+1FFFF, U+2FFFE, U+2FFFF, …, U+10FFFE, U+10FFFF
*
* @see https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-23/#G12612
* @see https://www.w3.org/TR/xml/#charsets
* @see https://html.spec.whatwg.org/#attributes-2
*
* @since 6.9.0
*
* @param string $text Are there noncharacters in this string?
* @return bool Whether noncharacters were found in the string.
*/
function wp_has_noncharacters( string $text ): bool {
/*
* Match the UTF-8 byte sequences directly so malformed UTF-8 elsewhere
* in the subject does not cause PCRE's Unicode mode to reject the string.
*/
return 1 === preg_match(
'~
# U+FDD0-U+FDEF, U+FFFE-U+FFFF
\xEF(?:\xB7[\x90-\xAF]|\xBF[\xBE\xBF])
|
# U+nFFFE/U+nFFFF
(?:\xF0[\x9F\xAF\xBF]|[\xF1-\xF3][\x8F\x9F\xAF\xBF]|\xF4\x8F)\xBF[\xBE\xBF]
~x',
$text
);
}