MediaWiki  REL1_31
StringUtilsTest.php
Go to the documentation of this file.
1 <?php
2 
3 class StringUtilsTest extends PHPUnit\Framework\TestCase {
4 
5  use MediaWikiCoversValidator;
6 
11  public function testIsUtf8( $expected, $string ) {
12  $this->assertEquals( $expected, StringUtils::isUtf8( $string ),
13  'Testing string "' . $this->escaped( $string ) . '"' );
14  }
15 
21  function escaped( $string ) {
22  $escaped = '';
23  $length = strlen( $string );
24  for ( $i = 0; $i < $length; $i++ ) {
25  $char = $string[$i];
26  $val = ord( $char );
27  if ( $val > 127 ) {
28  $escaped .= '\x' . dechex( $val );
29  } else {
30  $escaped .= $char;
31  }
32  }
33 
34  return $escaped;
35  }
36 
42  public static function provideStringsForIsUtf8Check() {
43  // Expected return values for StringUtils::isUtf8()
44  $PASS = true;
45  $FAIL = false;
46 
47  return [
48  'some ASCII' => [ $PASS, 'Some ASCII' ],
49  'euro sign' => [ $PASS, "Euro sign €" ],
50 
51  'first possible sequence 1 byte' => [ $PASS, "\x00" ],
52  'first possible sequence 2 bytes' => [ $PASS, "\xc2\x80" ],
53  'first possible sequence 3 bytes' => [ $PASS, "\xe0\xa0\x80" ],
54  'first possible sequence 4 bytes' => [ $PASS, "\xf0\x90\x80\x80" ],
55  'first possible sequence 5 bytes' => [ $FAIL, "\xf8\x88\x80\x80\x80" ],
56  'first possible sequence 6 bytes' => [ $FAIL, "\xfc\x84\x80\x80\x80\x80" ],
57 
58  'last possible sequence 1 byte' => [ $PASS, "\x7f" ],
59  'last possible sequence 2 bytes' => [ $PASS, "\xdf\xbf" ],
60  'last possible sequence 3 bytes' => [ $PASS, "\xef\xbf\xbf" ],
61  'last possible sequence 4 bytes (U+1FFFFF)' => [ $FAIL, "\xf7\xbf\xbf\xbf" ],
62  'last possible sequence 5 bytes' => [ $FAIL, "\xfb\xbf\xbf\xbf\xbf" ],
63  'last possible sequence 6 bytes' => [ $FAIL, "\xfd\xbf\xbf\xbf\xbf\xbf" ],
64 
65  'boundary 1' => [ $PASS, "\xed\x9f\xbf" ],
66  'boundary 2' => [ $PASS, "\xee\x80\x80" ],
67  'boundary 3' => [ $PASS, "\xef\xbf\xbd" ],
68  'boundary 4' => [ $PASS, "\xf2\x80\x80\x80" ],
69  'boundary 5 (U+FFFFF)' => [ $PASS, "\xf3\xbf\xbf\xbf" ],
70  'boundary 6 (U+100000)' => [ $PASS, "\xf4\x80\x80\x80" ],
71  'boundary 7 (U+10FFFF)' => [ $PASS, "\xf4\x8f\xbf\xbf" ],
72  'boundary 8 (U+110000)' => [ $FAIL, "\xf4\x90\x80\x80" ],
73 
74  'malformed 1' => [ $FAIL, "\x80" ],
75  'malformed 2' => [ $FAIL, "\xbf" ],
76  'malformed 3' => [ $FAIL, "\x80\xbf" ],
77  'malformed 4' => [ $FAIL, "\x80\xbf\x80" ],
78  'malformed 5' => [ $FAIL, "\x80\xbf\x80\xbf" ],
79  'malformed 6' => [ $FAIL, "\x80\xbf\x80\xbf\x80" ],
80  'malformed 7' => [ $FAIL, "\x80\xbf\x80\xbf\x80\xbf" ],
81  'malformed 8' => [ $FAIL, "\x80\xbf\x80\xbf\x80\xbf\x80" ],
82 
83  'last byte missing 1' => [ $FAIL, "\xc0" ],
84  'last byte missing 2' => [ $FAIL, "\xe0\x80" ],
85  'last byte missing 3' => [ $FAIL, "\xf0\x80\x80" ],
86  'last byte missing 4' => [ $FAIL, "\xf8\x80\x80\x80" ],
87  'last byte missing 5' => [ $FAIL, "\xfc\x80\x80\x80\x80" ],
88  'last byte missing 6' => [ $FAIL, "\xdf" ],
89  'last byte missing 7' => [ $FAIL, "\xef\xbf" ],
90  'last byte missing 8' => [ $FAIL, "\xf7\xbf\xbf" ],
91  'last byte missing 9' => [ $FAIL, "\xfb\xbf\xbf\xbf" ],
92  'last byte missing 10' => [ $FAIL, "\xfd\xbf\xbf\xbf\xbf" ],
93 
94  'extra continuation byte 1' => [ $FAIL, "e\xaf" ],
95  'extra continuation byte 2' => [ $FAIL, "\xc3\x89\xaf" ],
96  'extra continuation byte 3' => [ $FAIL, "\xef\xbc\xa5\xaf" ],
97  'extra continuation byte 4' => [ $FAIL, "\xf0\x9d\x99\xb4\xaf" ],
98 
99  'impossible bytes 1' => [ $FAIL, "\xfe" ],
100  'impossible bytes 2' => [ $FAIL, "\xff" ],
101  'impossible bytes 3' => [ $FAIL, "\xfe\xfe\xff\xff" ],
102 
103  'overlong sequences 1' => [ $FAIL, "\xc0\xaf" ],
104  'overlong sequences 2' => [ $FAIL, "\xc1\xaf" ],
105  'overlong sequences 3' => [ $FAIL, "\xe0\x80\xaf" ],
106  'overlong sequences 4' => [ $FAIL, "\xf0\x80\x80\xaf" ],
107  'overlong sequences 5' => [ $FAIL, "\xf8\x80\x80\x80\xaf" ],
108  'overlong sequences 6' => [ $FAIL, "\xfc\x80\x80\x80\x80\xaf" ],
109 
110  'maximum overlong sequences 1' => [ $FAIL, "\xc1\xbf" ],
111  'maximum overlong sequences 2' => [ $FAIL, "\xe0\x9f\xbf" ],
112  'maximum overlong sequences 3' => [ $FAIL, "\xf0\x8f\xbf\xbf" ],
113  'maximum overlong sequences 4' => [ $FAIL, "\xf8\x87\xbf\xbf" ],
114  'maximum overlong sequences 5' => [ $FAIL, "\xfc\x83\xbf\xbf\xbf\xbf" ],
115 
116  'surrogates 1 (U+D799)' => [ $PASS, "\xed\x9f\xbf" ],
117  'surrogates 2 (U+E000)' => [ $PASS, "\xee\x80\x80" ],
118  'surrogates 3 (U+D800)' => [ $FAIL, "\xed\xa0\x80" ],
119  'surrogates 4 (U+DBFF)' => [ $FAIL, "\xed\xaf\xbf" ],
120  'surrogates 5 (U+DC00)' => [ $FAIL, "\xed\xb0\x80" ],
121  'surrogates 6 (U+DFFF)' => [ $FAIL, "\xed\xbf\xbf" ],
122  'surrogates 7 (U+D800 U+DC00)' => [ $FAIL, "\xed\xa0\x80\xed\xb0\x80" ],
123 
124  'noncharacters 1' => [ $PASS, "\xef\xbf\xbe" ],
125  'noncharacters 2' => [ $PASS, "\xef\xbf\xbf" ],
126  ];
127  }
128 }
StringUtils\isUtf8
static isUtf8( $value)
Test whether a string is valid UTF-8.
Definition: StringUtils.php:41
use
Apache License January AND DISTRIBUTION Definitions License shall mean the terms and conditions for use
Definition: APACHE-LICENSE-2.0.txt:10
StringUtilsTest\escaped
escaped( $string)
Print high range characters as a hexadecimal.
Definition: StringUtilsTest.php:21
StringUtilsTest\testIsUtf8
testIsUtf8( $expected, $string)
StringUtils::isUtf8 provideStringsForIsUtf8Check.
Definition: StringUtilsTest.php:11
php
injection txt This is an overview of how MediaWiki makes use of dependency injection The design described here grew from the discussion of RFC T384 The term dependency this means that anything an object needs to operate should be injected from the the object itself should only know narrow no concrete implementation of the logic it relies on The requirement to inject everything typically results in an architecture that based on two main types of and essentially stateless service objects that use other service objects to operate on the value objects As of the beginning MediaWiki is only starting to use the DI approach Much of the code still relies on global state or direct resulting in a highly cyclical dependency which acts as the top level factory for services in MediaWiki which can be used to gain access to default instances of various services MediaWikiServices however also allows new services to be defined and default services to be redefined Services are defined or redefined by providing a callback the instantiator that will return a new instance of the service When it will create an instance of MediaWikiServices and populate it with the services defined in the files listed by thereby bootstrapping the DI framework Per $wgServiceWiringFiles lists includes ServiceWiring php
Definition: injection.txt:37
StringUtilsTest
Definition: StringUtilsTest.php:3
StringUtilsTest\provideStringsForIsUtf8Check
static provideStringsForIsUtf8Check()
See also "UTF-8 decoder capability and stress test" by Markus Kuhn: http://www.cl....
Definition: StringUtilsTest.php:42