summaryrefslogtreecommitdiff
path: root/includes/StringUtils.php
diff options
context:
space:
mode:
authorPierre Schmitz <pierre@archlinux.de>2013-08-12 09:28:15 +0200
committerPierre Schmitz <pierre@archlinux.de>2013-08-12 09:28:15 +0200
commit08aa4418c30cfc18ccc69a0f0f9cb9e17be6c196 (patch)
tree577a29fb579188d16003a209ce2a2e9c5b0aa2bd /includes/StringUtils.php
parentcacc939b34e315b85e2d72997811eb6677996cc1 (diff)
Update to MediaWiki 1.21.1
Diffstat (limited to 'includes/StringUtils.php')
-rw-r--r--includes/StringUtils.php73
1 files changed, 59 insertions, 14 deletions
diff --git a/includes/StringUtils.php b/includes/StringUtils.php
index 43275a66..f4c98f1d 100644
--- 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]/', $value ) === 0 ) {
+ # no high bit set, this is pure ASCII which is de facto
+ # valid UTF-8
+ return true;
+ }
+
+ if ( !$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
*
@@ -65,16 +110,16 @@ 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/.
*
- * @param $startDelim String: start delimiter
- * @param $endDelim String: end delimiter
+ * @param string $startDelim start delimiter
+ * @param string $endDelim end delimiter
* @param $callback Callback: function to call on each match
* @param $subject String
- * @param $flags String: regular expression flags
+ * @param string $flags regular expression flags
* @throws MWException
* @return string
*/
@@ -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
$tokenType = 'end';
@@ -155,12 +200,12 @@ class StringUtils {
*
* preg_replace( "!$startDelim(.*)$endDelim!$flags", $replace, $subject )
*
- * @param $startDelim String: start delimiter regular expression
- * @param $endDelim String: end delimiter regular expression
- * @param $replace String: replacement string. May contain $1, which will be
+ * @param string $startDelim start delimiter regular expression
+ * @param string $endDelim end delimiter regular expression
+ * @param string $replace replacement string. May contain $1, which will be
* replaced by the text between the delimiters
- * @param $subject String to search
- * @param $flags String: regular expression flags
+ * @param string $subject to search
+ * @param string $flags regular expression flags
* @return String: The string with the matches replaced
*/
static function delimiterReplace( $startDelim, $endDelim, $replace, $subject, $flags = '' ) {
@@ -360,7 +405,7 @@ class ReplacementArray {
/**
* Set an element of the replacement array
* @param $from string
- * @param $to stromg
+ * @param $to string
*/
function setPair( $from, $to ) {
$this->data[$from] = $to;
@@ -387,7 +432,7 @@ class ReplacementArray {
* @param $from string
*/
function removePair( $from ) {
- unset($this->data[$from]);
+ unset( $this->data[$from] );
$this->fss = false;
}
@@ -424,7 +469,7 @@ class ReplacementArray {
/**
* An iterator which works exactly like:
- *
+ *
* foreach ( explode( $delim, $s ) as $element ) {
* ...
* }