This project does not seem to handle request data directly as such no vulnerable execution paths were found.
include
, or for example
via PHP's auto-loading mechanism.
These results are based on our legacy PHP analysis, consider migrating to our new PHP analysis engine instead. Learn more
1 | <?php |
||
2 | |||
3 | namespace Onoi\Tesa\Tests; |
||
4 | |||
5 | use Onoi\Tesa\Tokenizer\JaTinySegmenterTokenizer; |
||
6 | |||
7 | /** |
||
8 | * @covers \Onoi\Tesa\Tokenizer\JaTinySegmenterTokenizer |
||
9 | * @group onoi-tesa |
||
10 | * |
||
11 | * @license GNU GPL v2+ |
||
12 | * @since 0.1 |
||
13 | * |
||
14 | * @author mwjames |
||
15 | */ |
||
16 | class JaTinySegmenterTokenizerTest extends \PHPUnit_Framework_TestCase { |
||
17 | |||
18 | public function testCanConstruct() { |
||
19 | |||
20 | $tokenizer = $this->getMockBuilder( '\Onoi\Tesa\Tokenizer\Tokenizer' ) |
||
21 | ->disableOriginalConstructor() |
||
22 | ->getMockForAbstractClass(); |
||
23 | |||
24 | $this->assertInstanceOf( |
||
25 | '\Onoi\Tesa\Tokenizer\JaTinySegmenterTokenizer', |
||
26 | new JaTinySegmenterTokenizer( $tokenizer ) |
||
27 | ); |
||
28 | } |
||
29 | |||
30 | /** |
||
31 | * @dataProvider stringProvider |
||
32 | */ |
||
33 | public function testTokenize( $string, $expected ) { |
||
34 | |||
35 | $instance = new JaTinySegmenterTokenizer(); |
||
36 | |||
37 | $this->assertEquals( |
||
38 | $expected, |
||
39 | $instance->tokenize( $string ) |
||
40 | ); |
||
41 | } |
||
42 | |||
43 | public function stringProvider() { |
||
44 | |||
45 | $provider[] = array( |
||
0 ignored issues
–
show
|
|||
46 | '極めてコンパクトな日本語分かち書きソフトウェアです。', |
||
47 | array( |
||
48 | '極め', // should be 極めて |
||
49 | 'て', |
||
50 | 'コンパクト', |
||
51 | 'な', |
||
52 | '日本', |
||
53 | '語分', |
||
54 | 'かち', |
||
55 | '書き', |
||
56 | 'ソフトウェア', |
||
57 | 'です', |
||
58 | '。' |
||
59 | ) |
||
60 | ); |
||
61 | |||
62 | $provider[] = array( |
||
63 | '日本語の新聞記事であれば文字単位で95%程度の精度で分かち書きが行えます。 ', |
||
64 | array( |
||
65 | '日本語', |
||
66 | 'の', |
||
67 | '新聞', |
||
68 | '記事', |
||
69 | 'で', |
||
70 | 'あれ', |
||
71 | 'ば', |
||
72 | '文字', |
||
73 | '単位', |
||
74 | 'で', |
||
75 | '9', |
||
76 | '5', |
||
77 | '%', |
||
78 | '程度', |
||
79 | 'の', |
||
80 | '精度', |
||
81 | 'で', |
||
82 | '分かち', |
||
83 | '書き', |
||
84 | 'が', |
||
85 | '行え', |
||
86 | 'ます', |
||
87 | '。' |
||
88 | |||
89 | ) |
||
90 | ); |
||
91 | |||
92 | $provider[] = array( |
||
93 | '私の名前は中野です', |
||
94 | array( |
||
95 | '私', |
||
96 | 'の', |
||
97 | '名前', |
||
98 | 'は', |
||
99 | '中野', |
||
100 | 'です' |
||
101 | ) |
||
102 | ); |
||
103 | |||
104 | $provider[] = array( |
||
105 | 'TinySegmenterは25kBで書かれています。', |
||
106 | array( |
||
107 | 'TinySegmenter', |
||
108 | 'は', |
||
109 | '2', |
||
110 | '5', |
||
111 | 'kB', |
||
112 | 'で', |
||
113 | '書か', |
||
114 | 'れ', |
||
115 | 'て', |
||
116 | 'い', |
||
117 | 'ます', |
||
118 | '。' |
||
119 | ) |
||
120 | ); |
||
121 | |||
122 | $provider[] = array( |
||
123 | '隣の客はAK47振りかざしてギャアギャアわめきたてる客だ。', |
||
124 | array( |
||
125 | '隣', |
||
126 | 'の', |
||
127 | '客', |
||
128 | 'は', |
||
129 | 'AK', |
||
130 | '4', |
||
131 | '7', |
||
132 | '振り', |
||
133 | 'かざ', // should be かざし |
||
134 | 'し', |
||
135 | 'て', |
||
136 | 'ギャアギャア', |
||
137 | 'わめき', |
||
138 | 'た', |
||
139 | 'てる', |
||
140 | '客', |
||
141 | 'だ', |
||
142 | '。' |
||
143 | ) |
||
144 | ); |
||
145 | |||
146 | // See JaCompoundGroupTokenizerTest for comparison |
||
147 | $provider[] = array( |
||
148 | 'と歓声を上げていました。 十勝農業改良普及センターによりますと', |
||
149 | array( |
||
150 | 'と', |
||
151 | '歓声', |
||
152 | 'を', |
||
153 | '上げ', |
||
154 | 'て', |
||
155 | 'い', |
||
156 | 'まし', |
||
157 | 'た', |
||
158 | '。', |
||
159 | '十勝農業', |
||
160 | '改良', |
||
161 | '普及', |
||
162 | 'センター', |
||
163 | 'により', |
||
164 | 'ます', |
||
165 | 'と' |
||
166 | ) |
||
167 | ); |
||
168 | |||
169 | // See IcuWordBoundaryTokenizerTest |
||
170 | $provider[] = array( |
||
171 | "公明執ようなSNSもストーカー行為の対象に", |
||
172 | array( |
||
173 | '公明執', |
||
174 | 'よう', |
||
175 | 'な', |
||
176 | 'SNS', |
||
177 | 'も', |
||
178 | 'ストーカー', |
||
179 | '行為', |
||
180 | 'の', |
||
181 | '対象', |
||
182 | 'に' |
||
183 | ) |
||
184 | ); |
||
185 | |||
186 | // https://github.com/chezou/TinySegmenter.jl/blob/master/test/timemachineu8j.txt |
||
187 | |||
188 | return $provider; |
||
189 | } |
||
190 | |||
191 | } |
||
192 |
Adding an explicit array definition is generally preferable to implicit array definition as it guarantees a stable state of the code.
Let’s take a look at an example:
As you can see in this example, the array
$myArray
is initialized the first time when the foreach loop is entered. You can also see that the value of thebar
key is only written conditionally; thus, its value might result from a previous iteration.This might or might not be intended. To make your intention clear, your code more readible and to avoid accidental bugs, we recommend to add an explicit initialization $myArray = array() either outside or inside the foreach loop.