Completed
Push — 5.x ( ef5d14...158fb7 )
by Lars
09:14
created

validateByteSequence()   A

Complexity

Conditions 3
Paths 3

Size

Total Lines 10
Code Lines 5

Duplication

Lines 0
Ratio 0 %

Code Coverage

Tests 4
CRAP Score 3.072

Importance

Changes 0
Metric Value
cc 3
eloc 5
nc 3
nop 2
dl 0
loc 10
ccs 4
cts 5
cp 0.8
crap 3.072
rs 9.4285
c 0
b 0
f 0
1
<?php
2
3
/*
4
 * This file is part of SwiftMailer.
5
 * (c) 2004-2009 Chris Corbyn
6
 *
7
 * For the full copyright and license information, please view the LICENSE
8
 * file that was distributed with this source code.
9
 */
10
11
/**
12
 * Analyzes UTF-8 characters.
13
 *
14
 * @author Chris Corbyn
15
 * @author Xavier De Cock <[email protected]>
16
 */
17
class Swift_CharacterReader_Utf8Reader implements Swift_CharacterReader
0 ignored issues
show
Coding Style Compatibility introduced by
PSR1 recommends that each class must be in a namespace of at least one level to avoid collisions.

You can fix this by adding a namespace to your class:

namespace YourVendor;

class YourClass { }

When choosing a vendor namespace, try to pick something that is not too generic to avoid conflicts with other libraries.

Loading history...
18
{
19
    /** Pre-computed for optimization */
20
    private static $length_map = array(
21
        // N=0,1,2,3,4,5,6,7,8,9,A,B,C,D,E,F,
0 ignored issues
show
Unused Code Comprehensibility introduced by
75% of this comment could be valid code. Did you maybe forget this after debugging?

Sometimes obsolete code just ends up commented out instead of removed. In this case it is better to remove the code once you have checked you do not need it.

The code might also have been commented out for debugging purposes. In this case it is vital that someone uncomments it again or your project may behave in very unexpected ways in production.

This check looks for comments that seem to be mostly valid code and reports them.

Loading history...
22
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x0N
23
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x1N
24
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x2N
25
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x3N
26
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x4N
27
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x5N
28
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x6N
29
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x7N
30
        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0x8N
31
        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0x9N
32
        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xAN
33
        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xBN
34
        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // 0xCN
35
        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // 0xDN
36
        3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, // 0xEN
37
        4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 6, 6, 0, 0, // 0xFN
38
    );
39
40
    private static $s_length_map = array(
41
        "\x00" => 1, "\x01" => 1, "\x02" => 1, "\x03" => 1, "\x04" => 1, "\x05" => 1, "\x06" => 1, "\x07" => 1,
42
        "\x08" => 1, "\x09" => 1, "\x0a" => 1, "\x0b" => 1, "\x0c" => 1, "\x0d" => 1, "\x0e" => 1, "\x0f" => 1,
43
        "\x10" => 1, "\x11" => 1, "\x12" => 1, "\x13" => 1, "\x14" => 1, "\x15" => 1, "\x16" => 1, "\x17" => 1,
44
        "\x18" => 1, "\x19" => 1, "\x1a" => 1, "\x1b" => 1, "\x1c" => 1, "\x1d" => 1, "\x1e" => 1, "\x1f" => 1,
45
        "\x20" => 1, "\x21" => 1, "\x22" => 1, "\x23" => 1, "\x24" => 1, "\x25" => 1, "\x26" => 1, "\x27" => 1,
46
        "\x28" => 1, "\x29" => 1, "\x2a" => 1, "\x2b" => 1, "\x2c" => 1, "\x2d" => 1, "\x2e" => 1, "\x2f" => 1,
47
        "\x30" => 1, "\x31" => 1, "\x32" => 1, "\x33" => 1, "\x34" => 1, "\x35" => 1, "\x36" => 1, "\x37" => 1,
48
        "\x38" => 1, "\x39" => 1, "\x3a" => 1, "\x3b" => 1, "\x3c" => 1, "\x3d" => 1, "\x3e" => 1, "\x3f" => 1,
49
        "\x40" => 1, "\x41" => 1, "\x42" => 1, "\x43" => 1, "\x44" => 1, "\x45" => 1, "\x46" => 1, "\x47" => 1,
50
        "\x48" => 1, "\x49" => 1, "\x4a" => 1, "\x4b" => 1, "\x4c" => 1, "\x4d" => 1, "\x4e" => 1, "\x4f" => 1,
51
        "\x50" => 1, "\x51" => 1, "\x52" => 1, "\x53" => 1, "\x54" => 1, "\x55" => 1, "\x56" => 1, "\x57" => 1,
52
        "\x58" => 1, "\x59" => 1, "\x5a" => 1, "\x5b" => 1, "\x5c" => 1, "\x5d" => 1, "\x5e" => 1, "\x5f" => 1,
53
        "\x60" => 1, "\x61" => 1, "\x62" => 1, "\x63" => 1, "\x64" => 1, "\x65" => 1, "\x66" => 1, "\x67" => 1,
54
        "\x68" => 1, "\x69" => 1, "\x6a" => 1, "\x6b" => 1, "\x6c" => 1, "\x6d" => 1, "\x6e" => 1, "\x6f" => 1,
55
        "\x70" => 1, "\x71" => 1, "\x72" => 1, "\x73" => 1, "\x74" => 1, "\x75" => 1, "\x76" => 1, "\x77" => 1,
56
        "\x78" => 1, "\x79" => 1, "\x7a" => 1, "\x7b" => 1, "\x7c" => 1, "\x7d" => 1, "\x7e" => 1, "\x7f" => 1,
57
        "\x80" => 0, "\x81" => 0, "\x82" => 0, "\x83" => 0, "\x84" => 0, "\x85" => 0, "\x86" => 0, "\x87" => 0,
58
        "\x88" => 0, "\x89" => 0, "\x8a" => 0, "\x8b" => 0, "\x8c" => 0, "\x8d" => 0, "\x8e" => 0, "\x8f" => 0,
59
        "\x90" => 0, "\x91" => 0, "\x92" => 0, "\x93" => 0, "\x94" => 0, "\x95" => 0, "\x96" => 0, "\x97" => 0,
60
        "\x98" => 0, "\x99" => 0, "\x9a" => 0, "\x9b" => 0, "\x9c" => 0, "\x9d" => 0, "\x9e" => 0, "\x9f" => 0,
61
        "\xa0" => 0, "\xa1" => 0, "\xa2" => 0, "\xa3" => 0, "\xa4" => 0, "\xa5" => 0, "\xa6" => 0, "\xa7" => 0,
62
        "\xa8" => 0, "\xa9" => 0, "\xaa" => 0, "\xab" => 0, "\xac" => 0, "\xad" => 0, "\xae" => 0, "\xaf" => 0,
63
        "\xb0" => 0, "\xb1" => 0, "\xb2" => 0, "\xb3" => 0, "\xb4" => 0, "\xb5" => 0, "\xb6" => 0, "\xb7" => 0,
64
        "\xb8" => 0, "\xb9" => 0, "\xba" => 0, "\xbb" => 0, "\xbc" => 0, "\xbd" => 0, "\xbe" => 0, "\xbf" => 0,
65
        "\xc0" => 2, "\xc1" => 2, "\xc2" => 2, "\xc3" => 2, "\xc4" => 2, "\xc5" => 2, "\xc6" => 2, "\xc7" => 2,
66
        "\xc8" => 2, "\xc9" => 2, "\xca" => 2, "\xcb" => 2, "\xcc" => 2, "\xcd" => 2, "\xce" => 2, "\xcf" => 2,
67
        "\xd0" => 2, "\xd1" => 2, "\xd2" => 2, "\xd3" => 2, "\xd4" => 2, "\xd5" => 2, "\xd6" => 2, "\xd7" => 2,
68
        "\xd8" => 2, "\xd9" => 2, "\xda" => 2, "\xdb" => 2, "\xdc" => 2, "\xdd" => 2, "\xde" => 2, "\xdf" => 2,
69
        "\xe0" => 3, "\xe1" => 3, "\xe2" => 3, "\xe3" => 3, "\xe4" => 3, "\xe5" => 3, "\xe6" => 3, "\xe7" => 3,
70
        "\xe8" => 3, "\xe9" => 3, "\xea" => 3, "\xeb" => 3, "\xec" => 3, "\xed" => 3, "\xee" => 3, "\xef" => 3,
71
        "\xf0" => 4, "\xf1" => 4, "\xf2" => 4, "\xf3" => 4, "\xf4" => 4, "\xf5" => 4, "\xf6" => 4, "\xf7" => 4,
72
        "\xf8" => 5, "\xf9" => 5, "\xfa" => 5, "\xfb" => 5, "\xfc" => 6, "\xfd" => 6, "\xfe" => 0, "\xff" => 0,
73
        );
74
75
    /**
76
     * Returns the complete character map.
77
     *
78
     * @param string $string
79
     * @param int    $startOffset
80
     * @param array  $currentMap
81
     * @param mixed  $ignoredChars
82
     *
83
     * @return int
84
     */
85 9
    public function getCharPositions($string, $startOffset, &$currentMap, &$ignoredChars)
86
    {
87 9
        if (!isset($currentMap['i']) || !isset($currentMap['p'])) {
88 9
            $currentMap['p'] = $currentMap['i'] = array();
89 9
        }
90
91 9
        $strlen = strlen($string);
92 9
        $charPos = count($currentMap['p']);
93 9
        $foundChars = 0;
94 9
        $invalid = false;
95
96 9
        for ($i = 0; $i < $strlen; ++$i) {
97 9
            $char = $string[$i];
98 9
            $size = self::$s_length_map[$char];
99
100
            // char is invalid, we must wait for a re-sync
101 9
            if ($size === 0) {
102
                $invalid = true;
103
                continue;
104
            }
105
106 9
            if ($invalid === true) {
107
                // We mark the chars as invalid and start a new char.
108
                $currentMap['p'][$charPos + $foundChars] = $startOffset + $i;
109
                $currentMap['i'][$charPos + $foundChars] = true;
110
                ++$foundChars;
111
                $invalid = false;
112
            }
113
114 9
            if (($i + $size) > $strlen) {
115 1
                $ignoredChars = substr($string, $i);
116 1
                break;
117
            }
118
119 9
            for ($j = 1; $j < $size; ++$j) {
120 7
                $char = $string[$i + $j];
121 7
                if ($char > "\x7F" && $char < "\xC0") {
0 ignored issues
show
Unused Code introduced by
This if statement is empty and can be removed.

This check looks for the bodies of if statements that have no statements or where all statements have been commented out. This may be the result of changes for debugging or the code may simply be obsolete.

These if bodies can be removed. If you have an empty if but statements in the else branch, consider inverting the condition.

if (rand(1, 6) > 3) {
//print "Check failed";
} else {
    print "Check succeeded";
}

could be turned into

if (rand(1, 6) <= 3) {
    print "Check succeeded";
}

This is much more concise to read.

Loading history...
122
                    // valid - continue parsing
123 7
                } else {
124
                    // char is invalid, we must wait for a resync
125
                    $invalid = true;
126
                    continue 2;
127
                }
128 7
            }
129
130
            // Ok we got a complete char here
131 9
            $currentMap['p'][$charPos + $foundChars] = $startOffset + $i + $size;
132 9
            $i += $j - 1;
133 9
            ++$foundChars;
134 9
        }
135
136 9
        return $foundChars;
137
    }
138
139
    /**
140
     * Returns mapType.
141
     *
142
     * @return int mapType
143
     */
144 9
    public function getMapType()
145
    {
146 9
        return self::MAP_TYPE_POSITIONS;
147
    }
148
149
    /**
150
     * Returns an integer which specifies how many more bytes to read.
151
     *
152
     * A positive integer indicates the number of more bytes to fetch before invoking
153
     * this method again.
154
     * A value of zero means this is already a valid character.
155
     * A value of -1 means this cannot possibly be a valid character.
156
     *
157
     * @param string $bytes
158
     * @param int    $size
159
     *
160
     * @return int
161
     */
162 14
    public function validateByteSequence($bytes, $size)
163
    {
164 14
        if ($size < 1) {
165
            return -1;
166
        }
167
168 14
        $needed = self::$length_map[$bytes[0]] - $size;
169
170 14
        return $needed > -1 ? $needed : -1;
171
    }
172
173
    /**
174
     * Returns the number of bytes which should be read to start each character.
175
     *
176
     * @return int
177
     */
178 8
    public function getInitialByteSize()
179
    {
180 8
        return 1;
181
    }
182
}
183