EmailLexerTests::testLexerTokens() - Code Metrics - Inspection of "small code improvement" - egulias/EmailValidator - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Branch — moving_tests_around (1c37ee)

by Eduardo Gulias

created 2016-05-14 23:02 UTC

EmailLexerTests::testLexerTokens() A

↳ Parent: EmailLexerTests

Complexity

Conditions	1
Paths	1

Size

Total Lines	8
Code Lines	6

Duplication

Lines	8
Ratio	100 %

Importance

Changes	1
Bugs	1	Features	0

Metric	Value
c	1
b	1
f	0
dl	8
loc	8
rs	9.4285
cc	1
eloc	6
nc	1
nop	2

<?php

namespace Egulias\Tests\EmailValidator;

use Egulias\EmailValidator\EmailLexer;

class EmailLexerTests extends \PHPUnit_Framework_TestCase
{

    public function testLexerExtendsLib()
    {
        $lexer = new EmailLexer();
        $this->assertInstanceOf('Doctrine\Common\Lexer\AbstractLexer', $lexer);
    }

    /**
     *  @dataProvider getTokens
     *
     */
    public function testLexerTokens($str, $token)

    {
        $lexer = new EmailLexer();
        $lexer->setInput($str);
        $lexer->moveNext();
        $lexer->moveNext();
        $this->assertEquals($token, $lexer->token['type']);
    }

    public function testLexerParsesMultipleSpaces()

    {
        $lexer = new EmailLexer();
        $lexer->setInput('  ');
        $lexer->moveNext();
        $lexer->moveNext();
        $this->assertEquals(EmailLexer::S_SP, $lexer->token['type']);
        $lexer->moveNext();
        $this->assertEquals(EmailLexer::S_SP, $lexer->token['type']);
    }

    /**
     * @dataProvider invalidUTF8CharsProvider
     */
    public function testLexerParsesInvalidUTF8($char)

    {
        $lexer = new EmailLexer();
        $lexer->setInput($char);
        $lexer->moveNext();
        $lexer->moveNext();

        $this->assertEquals(EmailLexer::INVALID, $lexer->token['type']);
    }

    public function invalidUTF8CharsProvider()
    {
        $chars = array();
        for ($i = 0; $i < 0x100; ++$i) {
            $c = $this->utf8Chr($i);
            if (preg_match('/(?=\p{Cc})(?=[^\t\n\n\r])/u', $c) && !preg_match('/\x{0000}/u', $c)) {
                $chars[] = array($c);
            }
        }

        return $chars;
    }

    protected function utf8Chr($code_point)
    {

        if ($code_point < 0 || 0x10FFFF < $code_point || (0xD800 <= $code_point && $code_point <= 0xDFFF)) {
            return '';
        }

        if ($code_point < 0x80) {
            $hex[0] = $code_point;
foreach ($collection as $item) {
    $myArray['foo'] = $item->getFoo();

    if ($item->hasBar()) {
        $myArray['bar'] = $item->getBar();
    }

    // do something with $myArray
}
            $ret = chr($hex[0]);
        } elseif ($code_point < 0x800) {
            $hex[0] = 0x1C0 | $code_point >> 6;
foreach ($collection as $item) {
    $myArray['foo'] = $item->getFoo();

    if ($item->hasBar()) {
        $myArray['bar'] = $item->getBar();
    }

    // do something with $myArray
}
            $hex[1] = 0x80  | $code_point & 0x3F;
            $ret = chr($hex[0]).chr($hex[1]);
        } elseif ($code_point < 0x10000) {
            $hex[0] = 0xE0 | $code_point >> 12;
foreach ($collection as $item) {
    $myArray['foo'] = $item->getFoo();

    if ($item->hasBar()) {
        $myArray['bar'] = $item->getBar();
    }

    // do something with $myArray
}
            $hex[1] = 0x80 | $code_point >> 6 & 0x3F;
            $hex[2] = 0x80 | $code_point & 0x3F;
            $ret = chr($hex[0]).chr($hex[1]).chr($hex[2]);
        } else {
            $hex[0] = 0xF0 | $code_point >> 18;
foreach ($collection as $item) {
    $myArray['foo'] = $item->getFoo();

    if ($item->hasBar()) {
        $myArray['bar'] = $item->getBar();
    }

    // do something with $myArray
}
            $hex[1] = 0x80 | $code_point >> 12 & 0x3F;
            $hex[2] = 0x80 | $code_point >> 6 & 0x3F;
            $hex[3] = 0x80 | $code_point  & 0x3F;
            $ret = chr($hex[0]).chr($hex[1]).chr($hex[2]).chr($hex[3]);
        }

        return $ret;
    }

    public function testLexerForTab()

    {
        $lexer = new EmailLexer();
        $lexer->setInput("foo\tbar");
        $lexer->moveNext();
        $lexer->skipUntil(EmailLexer::S_HTAB);
        $lexer->moveNext();
        $this->assertEquals(EmailLexer::S_HTAB, $lexer->token['type']);
    }

    public function testLexerForUTF8()

    {
        $lexer = new EmailLexer();
        $lexer->setInput("áÇ@bar.com");
        $lexer->moveNext();
        $lexer->moveNext();
        $this->assertEquals(EmailLexer::GENERIC, $lexer->token['type']);
        $lexer->moveNext();
        $this->assertEquals(EmailLexer::GENERIC, $lexer->token['type']);
    }

    public function testLexerSearchToken()
    {
        $lexer = new EmailLexer();
        $lexer->setInput("foo\tbar");
        $lexer->moveNext();
        $this->assertTrue($lexer->find(EmailLexer::S_HTAB));
    }

    public function getTokens()
    {
        return array(
            array("foo", EmailLexer::GENERIC),
            array("\r", EmailLexer::S_CR),
            array("\t", EmailLexer::S_HTAB),
            array("\r\n", EmailLexer::CRLF),
            array("\n", EmailLexer::S_LF),
            array(" ", EmailLexer::S_SP),
            array("@", EmailLexer::S_AT),
            array("IPv6", EmailLexer::S_IPV6TAG),
            array("::", EmailLexer::S_DOUBLECOLON),
            array(":", EmailLexer::S_COLON),
            array(".", EmailLexer::S_DOT),
            array("\"", EmailLexer::S_DQUOTE),
            array("-", EmailLexer::S_HYPHEN),
            array("\\", EmailLexer::S_BACKSLASH),
            array("/", EmailLexer::S_SLASH),
            array("(", EmailLexer::S_OPENPARENTHESIS),
            array(")", EmailLexer::S_CLOSEPARENTHESIS),
            array('<', EmailLexer::S_LOWERTHAN),
            array('>', EmailLexer::S_GREATERTHAN),
            array('[', EmailLexer::S_OPENBRACKET),
            array(']', EmailLexer::S_CLOSEBRACKET),
            array(';', EmailLexer::S_SEMICOLON),
            array(',', EmailLexer::S_COMMA),
            array('<', EmailLexer::S_LOWERTHAN),
            array('>', EmailLexer::S_GREATERTHAN),
            array('{', EmailLexer::S_OPENQBRACKET),
            array('}', EmailLexer::S_CLOSEQBRACKET),
            array('',  EmailLexer::S_EMPTY),
            array(chr(31),  EmailLexer::INVALID),
            array(chr(226),  EmailLexer::GENERIC),
            array(chr(0),  EmailLexer::C_NUL)
        );
    }
}


1		<?php
2
3		namespace Egulias\Tests\EmailValidator;
4
5		use Egulias\EmailValidator\EmailLexer;
6
7		class EmailLexerTests extends \PHPUnit_Framework_TestCase
8		{
9
10		public function testLexerExtendsLib()
11		{
12		$lexer = new EmailLexer();
13		$this->assertInstanceOf('Doctrine\Common\Lexer\AbstractLexer', $lexer);
14		}
15
16		/**
17		* @dataProvider getTokens
18		*
19		*/
20	View Code Duplication	public function testLexerTokens($str, $token)
		0 ignored issues – show Duplication introduced 2016-05-09 22:37 UTC by Report Bug Copy Issue Report This method seems to be duplicated in your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
21		{
22		$lexer = new EmailLexer();
23		$lexer->setInput($str);
24		$lexer->moveNext();
25		$lexer->moveNext();
26		$this->assertEquals($token, $lexer->token['type']);
27		}
28
29	View Code Duplication	public function testLexerParsesMultipleSpaces()
		0 ignored issues – show Duplication introduced 2016-05-09 22:37 UTC by Report Bug Copy Issue Report This method seems to be duplicated in your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
30		{
31		$lexer = new EmailLexer();
32		$lexer->setInput(' ');
33		$lexer->moveNext();
34		$lexer->moveNext();
35		$this->assertEquals(EmailLexer::S_SP, $lexer->token['type']);
36		$lexer->moveNext();
37		$this->assertEquals(EmailLexer::S_SP, $lexer->token['type']);
38		}
39
40		/**
41		* @dataProvider invalidUTF8CharsProvider
42		*/
43	View Code Duplication	public function testLexerParsesInvalidUTF8($char)
		0 ignored issues – show Duplication introduced 2016-05-09 22:37 UTC by Report Bug Copy Issue Report This method seems to be duplicated in your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
44		{
45		$lexer = new EmailLexer();
46		$lexer->setInput($char);
47		$lexer->moveNext();
48		$lexer->moveNext();
49
50		$this->assertEquals(EmailLexer::INVALID, $lexer->token['type']);
51		}
52
53		public function invalidUTF8CharsProvider()
54		{
55		$chars = array();
56		for ($i = 0; $i < 0x100; ++$i) {
57		$c = $this->utf8Chr($i);
58		if (preg_match('/(?=\p{Cc})(?=[^\t\n\n\r])/u', $c) && !preg_match('/\x{0000}/u', $c)) {
59		$chars[] = array($c);
60		}
61		}
62
63		return $chars;
64		}
65
66		protected function utf8Chr($code_point)
67		{
68
69		if ($code_point < 0 \|\| 0x10FFFF < $code_point \|\| (0xD800 <= $code_point && $code_point <= 0xDFFF)) {
70		return '';
71		}
72
73		if ($code_point < 0x80) {
74		$hex[0] = $code_point;
		0 ignored issues – show Coding Style Comprehensibility introduced 2016-05-09 22:37 UTC by Report Bug Copy Issue Report `$hex` was never initialized. Although not strictly required by PHP, it is generally a good practice to add `$hex = array();` before regardless. Adding an explicit array definition is generally preferable to implicit array definition as it guarantees a stable state of the code. Let’s take a look at an example: foreach ($collection as $item) { $myArray['foo'] = $item->getFoo(); if ($item->hasBar()) { $myArray['bar'] = $item->getBar(); } // do something with $myArray } As you can see in this example, the array `$myArray` is initialized the first time when the foreach loop is entered. You can also see that the value of the `bar` 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. Loading history...
75		$ret = chr($hex[0]);
76		} elseif ($code_point < 0x800) {
77		$hex[0] = 0x1C0 \| $code_point >> 6;
		0 ignored issues – show Coding Style Comprehensibility introduced 2016-05-09 22:37 UTC by Report Bug Copy Issue Report `$hex` was never initialized. Although not strictly required by PHP, it is generally a good practice to add `$hex = array();` before regardless. Adding an explicit array definition is generally preferable to implicit array definition as it guarantees a stable state of the code. Let’s take a look at an example: foreach ($collection as $item) { $myArray['foo'] = $item->getFoo(); if ($item->hasBar()) { $myArray['bar'] = $item->getBar(); } // do something with $myArray } As you can see in this example, the array `$myArray` is initialized the first time when the foreach loop is entered. You can also see that the value of the `bar` 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. Loading history...
78		$hex[1] = 0x80 \| $code_point & 0x3F;
79		$ret = chr($hex[0]).chr($hex[1]);
80		} elseif ($code_point < 0x10000) {
81		$hex[0] = 0xE0 \| $code_point >> 12;
		0 ignored issues – show Coding Style Comprehensibility introduced 2016-05-09 22:37 UTC by Report Bug Copy Issue Report `$hex` was never initialized. Although not strictly required by PHP, it is generally a good practice to add `$hex = array();` before regardless. Adding an explicit array definition is generally preferable to implicit array definition as it guarantees a stable state of the code. Let’s take a look at an example: foreach ($collection as $item) { $myArray['foo'] = $item->getFoo(); if ($item->hasBar()) { $myArray['bar'] = $item->getBar(); } // do something with $myArray } As you can see in this example, the array `$myArray` is initialized the first time when the foreach loop is entered. You can also see that the value of the `bar` 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. Loading history...
82		$hex[1] = 0x80 \| $code_point >> 6 & 0x3F;
83		$hex[2] = 0x80 \| $code_point & 0x3F;
84		$ret = chr($hex[0]).chr($hex[1]).chr($hex[2]);
85		} else {
86		$hex[0] = 0xF0 \| $code_point >> 18;
		0 ignored issues – show Coding Style Comprehensibility introduced 2016-05-09 22:37 UTC by Report Bug Copy Issue Report `$hex` was never initialized. Although not strictly required by PHP, it is generally a good practice to add `$hex = array();` before regardless. Adding an explicit array definition is generally preferable to implicit array definition as it guarantees a stable state of the code. Let’s take a look at an example: foreach ($collection as $item) { $myArray['foo'] = $item->getFoo(); if ($item->hasBar()) { $myArray['bar'] = $item->getBar(); } // do something with $myArray } As you can see in this example, the array `$myArray` is initialized the first time when the foreach loop is entered. You can also see that the value of the `bar` 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. Loading history...
87		$hex[1] = 0x80 \| $code_point >> 12 & 0x3F;
88		$hex[2] = 0x80 \| $code_point >> 6 & 0x3F;
89		$hex[3] = 0x80 \| $code_point & 0x3F;
90		$ret = chr($hex[0]).chr($hex[1]).chr($hex[2]).chr($hex[3]);
91		}
92
93		return $ret;
94		}
95
96	View Code Duplication	public function testLexerForTab()
		0 ignored issues – show Duplication introduced 2016-05-09 22:37 UTC by Report Bug Copy Issue Report This method seems to be duplicated in your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
97		{
98		$lexer = new EmailLexer();
99		$lexer->setInput("foo\tbar");
100		$lexer->moveNext();
101		$lexer->skipUntil(EmailLexer::S_HTAB);
102		$lexer->moveNext();
103		$this->assertEquals(EmailLexer::S_HTAB, $lexer->token['type']);
104		}
105
106	View Code Duplication	public function testLexerForUTF8()
		0 ignored issues – show Duplication introduced 2016-05-09 22:37 UTC by Report Bug Copy Issue Report This method seems to be duplicated in your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
107		{
108		$lexer = new EmailLexer();
109		$lexer->setInput("áÇ@bar.com");
110		$lexer->moveNext();
111		$lexer->moveNext();
112		$this->assertEquals(EmailLexer::GENERIC, $lexer->token['type']);
113		$lexer->moveNext();
114		$this->assertEquals(EmailLexer::GENERIC, $lexer->token['type']);
115		}
116
117		public function testLexerSearchToken()
118		{
119		$lexer = new EmailLexer();
120		$lexer->setInput("foo\tbar");
121		$lexer->moveNext();
122		$this->assertTrue($lexer->find(EmailLexer::S_HTAB));
123		}
124
125		public function getTokens()
126		{
127		return array(
128		array("foo", EmailLexer::GENERIC),
129		array("\r", EmailLexer::S_CR),
130		array("\t", EmailLexer::S_HTAB),
131		array("\r\n", EmailLexer::CRLF),
132		array("\n", EmailLexer::S_LF),
133		array(" ", EmailLexer::S_SP),
134		array("@", EmailLexer::S_AT),
135		array("IPv6", EmailLexer::S_IPV6TAG),
136		array("::", EmailLexer::S_DOUBLECOLON),
137		array(":", EmailLexer::S_COLON),
138		array(".", EmailLexer::S_DOT),
139		array("\"", EmailLexer::S_DQUOTE),
140		array("-", EmailLexer::S_HYPHEN),
141		array("\\", EmailLexer::S_BACKSLASH),
142		array("/", EmailLexer::S_SLASH),
143		array("(", EmailLexer::S_OPENPARENTHESIS),
144		array(")", EmailLexer::S_CLOSEPARENTHESIS),
145		array('<', EmailLexer::S_LOWERTHAN),
146		array('>', EmailLexer::S_GREATERTHAN),
147		array('[', EmailLexer::S_OPENBRACKET),
148		array(']', EmailLexer::S_CLOSEBRACKET),
149		array(';', EmailLexer::S_SEMICOLON),
150		array(',', EmailLexer::S_COMMA),
151		array('<', EmailLexer::S_LOWERTHAN),
152		array('>', EmailLexer::S_GREATERTHAN),
153		array('{', EmailLexer::S_OPENQBRACKET),
154		array('}', EmailLexer::S_CLOSEQBRACKET),
155		array('', EmailLexer::S_EMPTY),
156		array(chr(31), EmailLexer::INVALID),
157		array(chr(226), EmailLexer::GENERIC),
158		array(chr(0), EmailLexer::C_NUL)
159		);
160		}
161		}
162

egulias / EmailValidator

Branch — moving_tests_around (1c37ee)

EmailLexerTests::testLexerTokens() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like