Use American English spelling for behavior

[lhc/web/wiklou.git] / includes / StringUtils.php

diff --git a/includes/StringUtils.php b/includes/StringUtils.php
index fba31ea..9543d1f 100644 (file)
--- a/includes/StringUtils.php
+++ b/includes/StringUtils.php
@@ -24,6 +24,51 @@
  * A collection of static methods to play with strings.
  */
 class StringUtils {
+
+       /**
+        * Test whether a string is valid UTF-8.
+        *
+        * The function check for invalid byte sequences, overlong encoding but
+        * not for different normalisations.
+        *
+        * This relies internally on the mbstring function mb_check_encoding()
+        * hardcoded to check against UTF-8. Whenever the function is not available
+        * we fallback to a pure PHP implementation. Setting $disableMbstring to
+        * true will skip the use of mb_check_encoding, this is mostly intended for
+        * unit testing our internal implementation.
+        *
+        * @since 1.21
+        *
+        * @param string $value String to check
+        * @param boolean $disableMbstring Whether to use the pure PHP
+        * implementation instead of trying mb_check_encoding. Intended for unit
+        * testing. Default: false
+        *
+        * @return boolean Whether the given $value is a valid UTF-8 encoded string
+        */
+       static function isUtf8( $value, $disableMbstring = false ) {
+
+               if ( preg_match( '/[\x80-\xff]/', $value ) === 0 ) {
+                       # no high bit set, this is pure ASCII which is defacto
+                       # valid UTF-8
+                       return true;
+               }
+
+               if ( !$disableMbstring && function_exists( 'mb_check_encoding' ) ) {
+                       return mb_check_encoding( $value, 'UTF-8' );
+               } else {
+                       $hasUtf8 = preg_match( '/^(?>
+                                 [\x00-\x7f]
+                               | [\xc0-\xdf][\x80-\xbf]
+                               | [\xe0-\xef][\x80-\xbf]{2}
+                               | [\xf0-\xf7][\x80-\xbf]{3}
+                               | [\xf8-\xfb][\x80-\xbf]{4}
+                               | \xfc[\x84-\xbf][\x80-\xbf]{4}
+                       )+$/x', $value );
+                       return ($hasUtf8 > 0 );
+               }
+       }
+
        /**
         * Perform an operation equivalent to
         *
@@ -65,7 +110,7 @@ class StringUtils {
         * memory. The delimiters are literal strings, not regular expressions.
         *
         * If the start delimiter ends with an initial substring of the end delimiter,
-        * e.g. in the case of C-style comments, the behaviour differs from the model
+        * e.g. in the case of C-style comments, the behavior differs from the model
         * regex. In this implementation, the end must share no characters with the
         * start, so e.g. /*\/ is not considered to be both the start and end of a
         * comment. /*\/xy/*\/ is considered to be a single comment with contents /xy/.
@@ -90,12 +135,12 @@ class StringUtils {
                $m = array();
 
                while ( $inputPos < strlen( $subject ) &&
-                 preg_match( "!($encStart)|($encEnd)!S$flags", $subject, $m, PREG_OFFSET_CAPTURE, $inputPos ) )
+                       preg_match( "!($encStart)|($encEnd)!S$flags", $subject, $m, PREG_OFFSET_CAPTURE, $inputPos ) )
                {
                        $tokenOffset = $m[0][1];
                        if ( $m[1][0] != '' ) {
                                if ( $foundStart &&
-                                 $strcmp( $endDelim, substr( $subject, $tokenOffset, $endLength ) ) == 0 )
+                                       $strcmp( $endDelim, substr( $subject, $tokenOffset, $endLength ) ) == 0 )
                                {
                                        # An end match is present at the same location
                                        $tokenType = 'end';
@@ -387,7 +432,7 @@ class ReplacementArray {
         * @param $from string
         */
        function removePair( $from ) {
-               unset($this->data[$from]);
+               unset( $this->data[$from] );
                $this->fss = false;
        }