summaryrefslogtreecommitdiff
path: root/includes/StringUtils.php
diff options
context:
space:
mode:
authorLuke Shumaker <LukeShu@sbcglobal.net>2014-01-28 09:50:25 -0500
committerLuke Shumaker <LukeShu@sbcglobal.net>2014-01-28 09:50:25 -0500
commit5744df39e15f85c6cc8a9faf8924d77e76d2b216 (patch)
treea8c8dd40a94d1fa0d5377566aa5548ae55a163da /includes/StringUtils.php
parent4bb2aeca1d198391ca856aa16c40b8559c68daec (diff)
parent224b22a051051f6c2e494c3a2fb4adb42898e2d1 (diff)
Merge branch 'archwiki'
Conflicts: extensions/FluxBBAuthPlugin.php extensions/SyntaxHighlight_GeSHi/README extensions/SyntaxHighlight_GeSHi/SyntaxHighlight_GeSHi.class.php extensions/SyntaxHighlight_GeSHi/SyntaxHighlight_GeSHi.i18n.php extensions/SyntaxHighlight_GeSHi/SyntaxHighlight_GeSHi.php extensions/SyntaxHighlight_GeSHi/geshi/docs/CHANGES extensions/SyntaxHighlight_GeSHi/geshi/docs/THANKS extensions/SyntaxHighlight_GeSHi/geshi/docs/TODO extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/AbstractClass.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/AbstractClass_logo.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/AbstractMethod.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/AbstractPrivateClass.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/AbstractPrivateClass_logo.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/AbstractPrivateMethod.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Class.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Class_logo.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Constant.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Constructor.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Destructor.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Function.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Global.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/I.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Index.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Interface.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Interface_logo.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/L.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Lminus.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Lplus.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Method.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Page.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Page_logo.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/PrivateClass.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/PrivateClass_logo.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/PrivateMethod.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/PrivateVariable.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/StaticMethod.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/StaticVariable.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/T.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Tminus.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Tplus.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/Variable.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/blank.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/class_folder.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/file.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/folder.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/function_folder.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/next_button.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/next_button_disabled.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/package.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/package_folder.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/previous_button.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/previous_button_disabled.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/private_class_logo.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/tutorial.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/tutorial_folder.png extensions/SyntaxHighlight_GeSHi/geshi/docs/api/media/images/up_button.png extensions/SyntaxHighlight_GeSHi/geshi/docs/geshi-doc.html extensions/SyntaxHighlight_GeSHi/geshi/docs/geshi-doc.txt extensions/SyntaxHighlight_GeSHi/geshi/geshi.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/4cs.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/6502acme.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/6502kickass.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/6502tasm.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/68000devpac.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/abap.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/actionscript.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/actionscript3.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/ada.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/algol68.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/apache.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/applescript.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/apt_sources.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/asm.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/asp.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/autoconf.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/autohotkey.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/autoit.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/avisynth.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/awk.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/bascomavr.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/bash.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/basic4gl.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/bf.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/bibtex.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/blitzbasic.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/bnf.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/boo.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/c.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/c_loadrunner.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/c_mac.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/caddcl.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/cadlisp.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/cfdg.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/cfm.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/chaiscript.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/cil.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/clojure.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/cmake.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/cobol.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/coffeescript.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/cpp-qt.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/cpp.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/csharp.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/css.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/cuesheet.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/d.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/dcs.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/delphi.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/diff.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/div.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/dos.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/dot.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/e.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/ecmascript.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/eiffel.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/email.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/epc.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/erlang.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/euphoria.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/f1.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/falcon.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/fo.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/fortran.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/freebasic.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/fsharp.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/gambas.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/gdb.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/genero.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/genie.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/gettext.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/glsl.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/gml.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/gnuplot.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/go.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/groovy.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/gwbasic.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/haskell.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/hicest.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/hq9plus.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/html4strict.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/html5.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/icon.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/idl.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/ini.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/inno.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/intercal.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/io.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/j.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/java.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/java5.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/javascript.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/jquery.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/kixtart.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/klonec.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/klonecpp.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/latex.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/lb.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/lisp.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/llvm.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/locobasic.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/logtalk.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/lolcode.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/lotusformulas.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/lotusscript.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/lscript.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/lsl2.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/lua.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/m68k.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/magiksf.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/make.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/mapbasic.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/matlab.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/mirc.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/mmix.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/modula2.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/modula3.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/mpasm.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/mxml.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/mysql.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/newlisp.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/nsis.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/oberon2.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/objc.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/objeck.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/ocaml-brief.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/ocaml.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/oobas.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/oracle11.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/oracle8.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/oxygene.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/oz.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/pascal.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/pcre.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/per.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/perl.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/perl6.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/pf.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/php-brief.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/php.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/pic16.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/pike.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/pixelbender.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/pli.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/plsql.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/postgresql.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/povray.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/powerbuilder.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/powershell.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/proftpd.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/progress.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/prolog.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/properties.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/providex.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/purebasic.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/pycon.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/python.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/q.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/qbasic.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/rails.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/rebol.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/reg.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/robots.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/rpmspec.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/rsplus.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/ruby.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/sas.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/scala.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/scheme.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/scilab.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/sdlbasic.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/smalltalk.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/smarty.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/sql.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/systemverilog.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/tcl.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/teraterm.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/text.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/thinbasic.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/tsql.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/typoscript.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/unicon.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/uscript.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/vala.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/vb.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/vbnet.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/verilog.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/vhdl.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/vim.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/visualfoxpro.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/visualprolog.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/whitespace.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/whois.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/winbatch.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/xbasic.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/xml.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/xorg_conf.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/xpp.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/yaml.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/z80.php extensions/SyntaxHighlight_GeSHi/geshi/geshi/zxbasic.php
Diffstat (limited to 'includes/StringUtils.php')
-rw-r--r--includes/StringUtils.php176
1 files changed, 133 insertions, 43 deletions
diff --git a/includes/StringUtils.php b/includes/StringUtils.php
index 43275a66..c1545e6e 100644
--- a/includes/StringUtils.php
+++ b/includes/StringUtils.php
@@ -24,6 +24,92 @@
* 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
+ * @note In MediaWiki 1.21, this function did not provide proper UTF-8 validation.
+ * In particular, the pure PHP code path did not in fact check for overlong forms.
+ * Beware of this when backporting code to that version of MediaWiki.
+ *
+ * @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 ) {
+ $value = (string)$value;
+
+ // If the mbstring extension is loaded, use it. However, before PHP 5.4, values above
+ // U+10FFFF are incorrectly allowed, so we have to check for them separately.
+ if ( !$disableMbstring && function_exists( 'mb_check_encoding' ) ) {
+ static $newPHP;
+ if ( $newPHP === null ) {
+ $newPHP = !mb_check_encoding( "\xf4\x90\x80\x80", 'UTF-8' );
+ }
+
+ return mb_check_encoding( $value, 'UTF-8' ) &&
+ ( $newPHP || preg_match( "/\xf4[\x90-\xbf]|[\xf5-\xff]/S", $value ) === 0 );
+ }
+
+ if ( preg_match( "/[\x80-\xff]/S", $value ) === 0 ) {
+ // String contains only ASCII characters, has to be valid
+ return true;
+ }
+
+ // PCRE implements repetition using recursion; to avoid a stack overflow (and segfault)
+ // for large input, we check for invalid sequences (<= 5 bytes) rather than valid
+ // sequences, which can be as long as the input string is. Multiple short regexes are
+ // used rather than a single long regex for performance.
+ static $regexes;
+ if ( $regexes === null ) {
+ $cont = "[\x80-\xbf]";
+ $after = "(?!$cont)"; // "(?:[^\x80-\xbf]|$)" would work here
+ $regexes = array(
+ // Continuation byte at the start
+ "/^$cont/",
+
+ // ASCII byte followed by a continuation byte
+ "/[\\x00-\x7f]$cont/S",
+
+ // Illegal byte
+ "/[\xc0\xc1\xf5-\xff]/S",
+
+ // Invalid 2-byte sequence, or valid one then an extra continuation byte
+ "/[\xc2-\xdf](?!$cont$after)/S",
+
+ // Invalid 3-byte sequence, or valid one then an extra continuation byte
+ "/\xe0(?![\xa0-\xbf]$cont$after)/",
+ "/[\xe1-\xec\xee\xef](?!$cont{2}$after)/S",
+ "/\xed(?![\x80-\x9f]$cont$after)/",
+
+ // Invalid 4-byte sequence, or valid one then an extra continuation byte
+ "/\xf0(?![\x90-\xbf]$cont{2}$after)/",
+ "/[\xf1-\xf3](?!$cont{3}$after)/S",
+ "/\xf4(?![\x80-\x8f]$cont{2}$after)/",
+ );
+ }
+
+ foreach ( $regexes as $regex ) {
+ if ( preg_match( $regex, $value ) !== 0 ) {
+ return false;
+ }
+ }
+ return true;
+ }
+
/**
* Perform an operation equivalent to
*
@@ -65,16 +151,16 @@ 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 +176,12 @@ 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
$tokenType = 'end';
@@ -155,12 +241,12 @@ class StringUtils {
*
* preg_replace( "!$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 = '' ) {
@@ -172,8 +258,8 @@ class StringUtils {
/**
* More or less "markup-safe" explode()
* Ignores any instances of the separator inside <...>
- * @param $separator String
- * @param $text String
+ * @param string $separator
+ * @param string $text
* @return array
*/
static function explodeMarkup( $separator, $text ) {
@@ -188,7 +274,7 @@ class StringUtils {
// Explode, then put the replaced separators back in
$items = explode( $separator, $cleaned );
- foreach( $items as $i => $str ) {
+ foreach ( $items as $i => $str ) {
$items[$i] = str_replace( $placeholder, $separator, $str );
}
@@ -199,8 +285,8 @@ class StringUtils {
* Escape a string to make it suitable for inclusion in a preg_replace()
* replacement parameter.
*
- * @param $string String
- * @return String
+ * @param string $string
+ * @return string
*/
static function escapeRegexReplacement( $string ) {
$string = str_replace( '\\', '\\\\', $string );
@@ -211,8 +297,8 @@ class StringUtils {
/**
* Workalike for explode() with limited memory usage.
* Returns an Iterator
- * @param $separator
- * @param $subject
+ * @param string $separator
+ * @param string $subject
* @return ArrayIterator|ExplodeIterator
*/
static function explode( $separator, $subject ) {
@@ -245,14 +331,14 @@ class RegexlikeReplacer extends Replacer {
var $r;
/**
- * @param $r string
+ * @param string $r
*/
function __construct( $r ) {
$this->r = $r;
}
/**
- * @param $matches array
+ * @param array $matches
* @return string
*/
function replace( $matches ) {
@@ -273,7 +359,7 @@ class DoubleReplacer extends Replacer {
/**
* @param $from
* @param $to
- * @param $index int
+ * @param int $index
*/
function __construct( $from, $to, $index = 0 ) {
$this->from = $from;
@@ -282,7 +368,7 @@ class DoubleReplacer extends Replacer {
}
/**
- * @param $matches array
+ * @param array $matches
* @return mixed
*/
function replace( $matches ) {
@@ -298,7 +384,7 @@ class HashtableReplacer extends Replacer {
/**
* @param $table
- * @param $index int
+ * @param int $index
*/
function __construct( $table, $index = 0 ) {
$this->table = $table;
@@ -306,7 +392,7 @@ class HashtableReplacer extends Replacer {
}
/**
- * @param $matches array
+ * @param array $matches
* @return mixed
*/
function replace( $matches ) {
@@ -344,6 +430,7 @@ class ReplacementArray {
/**
* Set the whole replacement array at once
+ * @param array $data
*/
function setArray( $data ) {
$this->data = $data;
@@ -359,8 +446,8 @@ class ReplacementArray {
/**
* Set an element of the replacement array
- * @param $from string
- * @param $to stromg
+ * @param string $from
+ * @param string $to
*/
function setPair( $from, $to ) {
$this->data[$from] = $to;
@@ -368,7 +455,7 @@ class ReplacementArray {
}
/**
- * @param $data array
+ * @param array $data
*/
function mergeArray( $data ) {
$this->data = array_merge( $this->data, $data );
@@ -376,7 +463,7 @@ class ReplacementArray {
}
/**
- * @param $other
+ * @param ReplacementArray $other
*/
function merge( $other ) {
$this->data = array_merge( $this->data, $other->data );
@@ -384,39 +471,39 @@ class ReplacementArray {
}
/**
- * @param $from string
+ * @param string $from
*/
function removePair( $from ) {
- unset($this->data[$from]);
+ unset( $this->data[$from] );
$this->fss = false;
}
/**
- * @param $data array
+ * @param array $data
*/
function removeArray( $data ) {
- foreach( $data as $from => $to ) {
+ foreach ( $data as $from => $to ) {
$this->removePair( $from );
}
$this->fss = false;
}
/**
- * @param $subject string
+ * @param string $subject
* @return string
*/
function replace( $subject ) {
if ( function_exists( 'fss_prep_replace' ) ) {
- wfProfileIn( __METHOD__.'-fss' );
+ wfProfileIn( __METHOD__ . '-fss' );
if ( $this->fss === false ) {
$this->fss = fss_prep_replace( $this->data );
}
$result = fss_exec_replace( $this->fss, $subject );
- wfProfileOut( __METHOD__.'-fss' );
+ wfProfileOut( __METHOD__ . '-fss' );
} else {
- wfProfileIn( __METHOD__.'-strtr' );
+ wfProfileIn( __METHOD__ . '-strtr' );
$result = strtr( $subject, $this->data );
- wfProfileOut( __METHOD__.'-strtr' );
+ wfProfileOut( __METHOD__ . '-strtr' );
}
return $result;
}
@@ -424,7 +511,7 @@ class ReplacementArray {
/**
* An iterator which works exactly like:
- *
+ *
* foreach ( explode( $delim, $s ) as $element ) {
* ...
* }
@@ -449,15 +536,15 @@ class ExplodeIterator implements Iterator {
/**
* Construct a DelimIterator
- * @param $delim string
- * @param $s string
+ * @param string $delim
+ * @param string $subject
*/
- function __construct( $delim, $s ) {
- $this->subject = $s;
+ function __construct( $delim, $subject ) {
+ $this->subject = $subject;
$this->delim = $delim;
// Micro-optimisation (theoretical)
- $this->subjectLength = strlen( $s );
+ $this->subjectLength = strlen( $subject );
$this->delimLength = strlen( $delim );
$this->rewind();
@@ -485,6 +572,9 @@ class ExplodeIterator implements Iterator {
return $this->current;
}
+ /**
+ * @return int|bool Current position or boolean false if invalid
+ */
function key() {
return $this->curPos;
}