UStrObj::loadToArray() - Code Metrics - Inspection of "method cleanup on loadToArray" - garrettw/stringobject - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 891408...d32ecd )

by Garrett

created 2015-12-17 22:36 UTC

UStrObj::loadToArray() C

↳ Parent: UStrObj

Complexity

Conditions	16
Paths	12

Size

Total Lines	78
Code Lines	44

Duplication

Lines	0
Ratio	0 %

Importance

Changes	3
Bugs	0	Features	0

Metric	Value
c	3
b	0
f	0
dl	0
loc	78
rs	5.142
cc	16
eloc	44
nc	12
nop	0

How to fix Long Method Complexity

<?php

namespace StringObject;

class UStrObj extends StrObj
{
    protected $chars = [];
    protected $uhandler;

    protected static $spec = [
        2 => ['datamask' => 0b00011111, 'threshold' => 0x80],
        3 => ['datamask' => 0b00001111, 'threshold' => 0x800],
        4 => ['datamask' => 0b00000111, 'threshold' => 0x10000],
        5 => ['datamask' => 0b00000011, 'threshold' => 0x200000],
        6 => ['datamask' => 0b00000001, 'threshold' => 0x4000000],
    ];
    protected static $winc1umap = [
        0x80 => 0x20AC,
        0x81 => 0xFFFD, // invalid
        0x82 => 0x201A,
        0x83 => 0x0192,
        0x84 => 0x201E,
        0x85 => 0x2026,
        0x86 => 0x2020,
        0x87 => 0x2021,
        0x88 => 0x02C6,
        0x89 => 0x2030,
        0x8A => 0x0160,
        0x8B => 0x2039,
        0x8C => 0x0152,
        0x8D => 0xFFFD, // invalid
        0x8E => 0x017D,
        0x8F => 0xFFFD, // invalid
        0x90 => 0xFFFD, // invalid
        0x91 => 0x2018,
        0x92 => 0x2019,
        0x93 => 0x201C,
        0x94 => 0x201D,
        0x95 => 0x2022,
        0x96 => 0x2013,
        0x97 => 0x2014,
        0x98 => 0x02DC,
        0x99 => 0x2122,
        0x9A => 0x0161,
        0x9B => 0x203A,
        0x9C => 0x0153,
        0x9D => 0xFFFD, // invalid
        0x9E => 0x017E,
        0x9F => 0x0178,
    ];

    public function __construct($thing)
    {
        parent::__construct($thing);
    }

    public function toArray($delim = '', $limit = null)

    {
        $this->loadToArray();

        if (empty($delim)) {
            return $this->chars;
        }
        if (is_int($delim)) {
            return \str_split($this->raw, $delim);
        }
        if ($limit === null) {
            return \explode($delim, $this->raw);
        }
        return \explode($delim, $this->raw, $limit);
    }

    public function charAt($index)

    {
        $this->loadToArray();
        return $this->chars[$index][0];
    }

    public function charCodeAt($index)

    {
        $this->loadToArray();
        return $this->chars[$index][1];
    }

    private function loadToArray()
    {
        if (!empty($this->chars)) {
            return;
        }

        $len = \strlen($this->raw);
        $inside = false;
        $invalid = false;

        for ($offset = 0; $offset < $len; $offset++) {
            $char = $this->raw{$offset};
            $ord = \ord($char);

            if ($inside === false) {
                $bytes = self::charLength($ord);

                if ($bytes > 1 && $offset + $bytes <= $len && $invalid === false) {
                    // valid UTF-8 multibyte start
                    $inside = true;
                    $cache = $char;
                    $ordcache = ($ord & self::$spec[$bytes]['datamask']) << (6 * ($bytes - 1));
                    $originOffset = $offset;
                } elseif ($ord < 0x80) {
                    // ASCII 7-bit char
                    $this->chars[] = [$char, $ord];
                } else {
                    // either C0/C1 block or higher; map from cp1252 to utf8 or just convert
                    $ord = (isset(self::$winc1umap[$ord])) ? self::$winc1umap[$ord] : $ord;
                    $this->chars[] = [self::cpToUtf8Char($ord), $ord];
                    $invalid = false;
                }
                continue;
            }

            // $inside === true, i.e. *should be* continuation character
            if (($ord & 0b11000000) !== 0b10000000) {
                // actually, it's not one, so now the whole UTF-8 char is invalid
                // go back and force it to parse as ISO or 1252
                $inside = false;
                $invalid = true;
                $offset = $originOffset - 1;
function myFunction($a) {
    switch ($a) {
        case 'foo':
            $x = 1;
            break;

        case 'bar':
            $x = 2;
            break;
    }

    // $x is potentially undefined here.
    echo $x;
}
                continue;
            }

            // put this byte's data where it needs to go
            $ordcache |= ($ord & 0b00111111) << (6 * ($bytes - 1 - ($offset - $originOffset)));
function myFunction($a) {
    switch ($a) {
        case 'foo':
            $x = 1;
            break;

        case 'bar':
            $x = 2;
            break;
    }

    // $x is potentially undefined here.
    echo $x;
}
            $cache .= $char;
function myFunction($a) {
    switch ($a) {
        case 'foo':
            $x = 1;
            break;

        case 'bar':
            $x = 2;
            break;
    }

    // $x is potentially undefined here.
    echo $x;
}

            if ($originOffset + ($bytes - 1) === $offset) {
                // we're done parsing this char, now let's verify
                $inside = false;

                // check for overlong, surrogate, too large, BOM, or C0/C1
                $overlong = ($ordcache < self::$spec[$bytes]['threshold']);
                $surrogate = ($ordcache & 0xFFFFF800 === 0xD800);
                $toobig = ($ordcache > 0x10FFFF);

                if ($overlong || $surrogate || $toobig) {
                    $invalid = true;
                    $offset = $originOffset - 1;
                    continue;
                }

                if ($ordcache === 0xFEFF) { // BOM
                    if ($originOffset !== 0) {
                        // if not at beginning, store as word joiner U+2060
                        $this->chars[] = [\chr(0xE2) . \chr(0x81) . \chr(0xA0), 0x2060];
                    }
                    // otherwise discard
                    continue;
                }

                // verification passed, now store it
                $this->chars[] = [$cache, $ordcache];
            }
        }
    }

    /**
     *
     */
    protected static function cpToUtf8Char($cpt)
    {
        if ($cpt < 0x80) {
            return \chr($cpt);
        }

        $data = [];
$myVar = 'Value';
$higher = false;

if (rand(1, 6) > 3) {
    $higher = true;
} else {
    $higher = false;
}
        if ($cpt < 0x800) {
            $data = [
                0b11000000 | ($cpt >> 6),
                0b10000000 | ($cpt & 0b00111111)
            ];
        } elseif ($cpt < 0x10000) {
            $data = [
                0b11100000 | ($cpt >> 12),
                0b10000000 | (($cpt >> 6) & 0b00111111),
                0b10000000 | ($cpt & 0b00111111),
            ];
        } elseif ($cpt < 0x10FFFF) {
            $data = [
                0b11110100,
                0b10000000 | (($cpt >> 12) & 0b00111111),
                0b10000000 | (($cpt >> 6) & 0b00111111),
                0b10000000 | ($cpt & 0b00111111),
            ];
        } else {
            $data = [0xEF, 0xBF, 0xBD]; // U+FFFD
        }

        return implode(array_map('chr', $data));
    }
    /**
     * @param integer $byte
     */
    protected static function charLength($byte)
    {
        if (($byte & 0b11111110) === 0b11111100) {
            return 6;
        }
        if (($byte & 0b11111100) === 0b11111000) {
            return 5;
        }
        if (($byte & 0b11111000) === 0b11110000) {
            return 4;
        }
        if (($byte & 0b11110000) === 0b11100000) {
            return 3;
        }
        if (($byte & 0b11100000) === 0b11000000) {
            return 2;
        }
        return 1;
    }
}


Push — master ( 891408...d32ecd )

UStrObj::loadToArray() C

Complexity

Size

Duplication

Importance

How to fix Long Method Complexity

Long Method

Available Fixes

Available Fixes

Available Fixes

Available Fixes

1		<?php
2
3		namespace StringObject;
4
5		class UStrObj extends StrObj
6		{
7		protected $chars = [];
8		protected $uhandler;
9
10		protected static $spec = [
11		2 => ['datamask' => 0b00011111, 'threshold' => 0x80],
12		3 => ['datamask' => 0b00001111, 'threshold' => 0x800],
13		4 => ['datamask' => 0b00000111, 'threshold' => 0x10000],
14		5 => ['datamask' => 0b00000011, 'threshold' => 0x200000],
15		6 => ['datamask' => 0b00000001, 'threshold' => 0x4000000],
16		];
17		protected static $winc1umap = [
18		0x80 => 0x20AC,
19		0x81 => 0xFFFD, // invalid
20		0x82 => 0x201A,
21		0x83 => 0x0192,
22		0x84 => 0x201E,
23		0x85 => 0x2026,
24		0x86 => 0x2020,
25		0x87 => 0x2021,
26		0x88 => 0x02C6,
27		0x89 => 0x2030,
28		0x8A => 0x0160,
29		0x8B => 0x2039,
30		0x8C => 0x0152,
31		0x8D => 0xFFFD, // invalid
32		0x8E => 0x017D,
33		0x8F => 0xFFFD, // invalid
34		0x90 => 0xFFFD, // invalid
35		0x91 => 0x2018,
36		0x92 => 0x2019,
37		0x93 => 0x201C,
38		0x94 => 0x201D,
39		0x95 => 0x2022,
40		0x96 => 0x2013,
41		0x97 => 0x2014,
42		0x98 => 0x02DC,
43		0x99 => 0x2122,
44		0x9A => 0x0161,
45		0x9B => 0x203A,
46		0x9C => 0x0153,
47		0x9D => 0xFFFD, // invalid
48		0x9E => 0x017E,
49		0x9F => 0x0178,
50		];
51
52		public function __construct($thing)
53		{
54		parent::__construct($thing);
55		}
56
57	View Code Duplication	public function toArray($delim = '', $limit = null)
		0 ignored issues – show Duplication introduced 2015-12-04 23:19 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...
58		{
59		$this->loadToArray();
60
61		if (empty($delim)) {
62		return $this->chars;
63		}
64		if (is_int($delim)) {
65		return \str_split($this->raw, $delim);
66		}
67		if ($limit === null) {
68		return \explode($delim, $this->raw);
69		}
70		return \explode($delim, $this->raw, $limit);
71		}
72
73		public function charAt($index)
		0 ignored issues – show Documentation introduced 2015-12-04 23:19 UTC by Report Bug Copy Issue Report The return type could not be reliably inferred; please add a `@return` annotation. Our type inference engine in quite powerful, but sometimes the code does not provide enough clues to go by. In these cases we request you to add a `@return` annotation as described here. Loading history...
74		{
75		$this->loadToArray();
76		return $this->chars[$index][0];
77		}
78
79		public function charCodeAt($index)
		0 ignored issues – show Documentation introduced 2015-12-04 23:19 UTC by Report Bug Copy Issue Report The return type could not be reliably inferred; please add a `@return` annotation. Our type inference engine in quite powerful, but sometimes the code does not provide enough clues to go by. In these cases we request you to add a `@return` annotation as described here. Loading history...
80		{
81		$this->loadToArray();
82		return $this->chars[$index][1];
83		}
84
85		private function loadToArray()
86		{
87		if (!empty($this->chars)) {
88		return;
89		}
90
91		$len = \strlen($this->raw);
92		$inside = false;
93		$invalid = false;
94
95		for ($offset = 0; $offset < $len; $offset++) {
96		$char = $this->raw{$offset};
97		$ord = \ord($char);
98
99		if ($inside === false) {
100		$bytes = self::charLength($ord);
101
102		if ($bytes > 1 && $offset + $bytes <= $len && $invalid === false) {
103		// valid UTF-8 multibyte start
104		$inside = true;
105		$cache = $char;
106		$ordcache = ($ord & self::$spec[$bytes]['datamask']) << (6 * ($bytes - 1));
107		$originOffset = $offset;
108		} elseif ($ord < 0x80) {
109		// ASCII 7-bit char
110		$this->chars[] = [$char, $ord];
111		} else {
112		// either C0/C1 block or higher; map from cp1252 to utf8 or just convert
113		$ord = (isset(self::$winc1umap[$ord])) ? self::$winc1umap[$ord] : $ord;
114		$this->chars[] = [self::cpToUtf8Char($ord), $ord];
115		$invalid = false;
116		}
117		continue;
118		}
119
120		// $inside === true, i.e. should be continuation character
121		if (($ord & 0b11000000) !== 0b10000000) {
122		// actually, it's not one, so now the whole UTF-8 char is invalid
123		// go back and force it to parse as ISO or 1252
124		$inside = false;
125		$invalid = true;
126		$offset = $originOffset - 1;
		1 ignored issue – show Bug introduced 2015-12-17 22:39 UTC by Report Bug Copy Issue Report The variable `$originOffset` does not seem to be defined for all execution paths leading up to this point. If you define a variable conditionally, it can happen that it is not defined for all execution paths. Let’s take a look at an example: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } // $x is potentially undefined here. echo $x; } In the above example, the variable `$x` is defined if you pass “foo” or “bar” as argument for `$a`. However, since the `switch` statement has no default case statement, if you pass any other value, the variable `$x` would be undefined. Available Fixes Check for existence of the variable explicitly: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } if (isset($x)) { // Make sure it's always set. echo $x; } } Define a default value for the variable: function myFunction($a) { $x = ''; // Set a default which gets overridden for certain paths. switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } echo $x; } Add a value for the missing path: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; // We add support for the missing case. default: $x = ''; break; } echo $x; } Loading history...
127		continue;
128		}
129
130		// put this byte's data where it needs to go
131		$ordcache \|= ($ord & 0b00111111) << (6 * ($bytes - 1 - ($offset - $originOffset)));
		2 ignored issues – show Bug introduced 2015-12-17 22:39 UTC by Report Bug Copy Issue Report The variable `$ordcache` does not seem to be defined for all execution paths leading up to this point. If you define a variable conditionally, it can happen that it is not defined for all execution paths. Let’s take a look at an example: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } // $x is potentially undefined here. echo $x; } In the above example, the variable `$x` is defined if you pass “foo” or “bar” as argument for `$a`. However, since the `switch` statement has no default case statement, if you pass any other value, the variable `$x` would be undefined. Available Fixes Check for existence of the variable explicitly: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } if (isset($x)) { // Make sure it's always set. echo $x; } } Define a default value for the variable: function myFunction($a) { $x = ''; // Set a default which gets overridden for certain paths. switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } echo $x; } Add a value for the missing path: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; // We add support for the missing case. default: $x = ''; break; } echo $x; } Loading history... Bug introduced 2015-12-17 22:39 UTC by Report Bug Copy Issue Report The variable `$bytes` does not seem to be defined for all execution paths leading up to this point. If you define a variable conditionally, it can happen that it is not defined for all execution paths. Let’s take a look at an example: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } // $x is potentially undefined here. echo $x; } In the above example, the variable `$x` is defined if you pass “foo” or “bar” as argument for `$a`. However, since the `switch` statement has no default case statement, if you pass any other value, the variable `$x` would be undefined. Available Fixes Check for existence of the variable explicitly: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } if (isset($x)) { // Make sure it's always set. echo $x; } } Define a default value for the variable: function myFunction($a) { $x = ''; // Set a default which gets overridden for certain paths. switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } echo $x; } Add a value for the missing path: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; // We add support for the missing case. default: $x = ''; break; } echo $x; } Loading history...
132		$cache .= $char;
		1 ignored issue – show Bug introduced 2015-12-17 22:39 UTC by Report Bug Copy Issue Report The variable `$cache` does not seem to be defined for all execution paths leading up to this point. If you define a variable conditionally, it can happen that it is not defined for all execution paths. Let’s take a look at an example: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } // $x is potentially undefined here. echo $x; } In the above example, the variable `$x` is defined if you pass “foo” or “bar” as argument for `$a`. However, since the `switch` statement has no default case statement, if you pass any other value, the variable `$x` would be undefined. Available Fixes Check for existence of the variable explicitly: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } if (isset($x)) { // Make sure it's always set. echo $x; } } Define a default value for the variable: function myFunction($a) { $x = ''; // Set a default which gets overridden for certain paths. switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } echo $x; } Add a value for the missing path: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; // We add support for the missing case. default: $x = ''; break; } echo $x; } Loading history...
133
134		if ($originOffset + ($bytes - 1) === $offset) {
135		// we're done parsing this char, now let's verify
136		$inside = false;
137
138		// check for overlong, surrogate, too large, BOM, or C0/C1
139		$overlong = ($ordcache < self::$spec[$bytes]['threshold']);
140		$surrogate = ($ordcache & 0xFFFFF800 === 0xD800);
141		$toobig = ($ordcache > 0x10FFFF);
142
143		if ($overlong \|\| $surrogate \|\| $toobig) {
144		$invalid = true;
145		$offset = $originOffset - 1;
146		continue;
147		}
148
149		if ($ordcache === 0xFEFF) { // BOM
150		if ($originOffset !== 0) {
151		// if not at beginning, store as word joiner U+2060
152		$this->chars[] = [\chr(0xE2) . \chr(0x81) . \chr(0xA0), 0x2060];
153		}
154		// otherwise discard
155		continue;
156		}
157
158		// verification passed, now store it
159		$this->chars[] = [$cache, $ordcache];
160		}
161		}
162		}
163
164		/**
165		*
166		*/
167		protected static function cpToUtf8Char($cpt)
168		{
169		if ($cpt < 0x80) {
170		return \chr($cpt);
171		}
172
173		$data = [];
		0 ignored issues – show Unused Code introduced 2015-12-16 21:29 UTC by Report Bug Copy Issue Report `$data` is not used, you could remove the assignment. This check looks for variable assignements that are either overwritten by other assignments or where the variable is not used subsequently. $myVar = 'Value'; $higher = false; if (rand(1, 6) > 3) { $higher = true; } else { $higher = false; } Both the `$myVar` assignment in line 1 and the `$higher` assignment in line 2 are dead. The first because `$myVar` is never used and the second because `$higher` is always overwritten for every possible time line. Loading history...
174		if ($cpt < 0x800) {
175		$data = [
176		0b11000000 \| ($cpt >> 6),
177		0b10000000 \| ($cpt & 0b00111111)
178		];
179		} elseif ($cpt < 0x10000) {
180		$data = [
181		0b11100000 \| ($cpt >> 12),
182		0b10000000 \| (($cpt >> 6) & 0b00111111),
183		0b10000000 \| ($cpt & 0b00111111),
184		];
185		} elseif ($cpt < 0x10FFFF) {
186		$data = [
187		0b11110100,
188		0b10000000 \| (($cpt >> 12) & 0b00111111),
189		0b10000000 \| (($cpt >> 6) & 0b00111111),
190		0b10000000 \| ($cpt & 0b00111111),
191		];
192		} else {
193		$data = [0xEF, 0xBF, 0xBD]; // U+FFFD
194		}
195
196		return implode(array_map('chr', $data));
197		}
198		/**
199		* @param integer $byte
200		*/
201		protected static function charLength($byte)
202		{
203		if (($byte & 0b11111110) === 0b11111100) {
204		return 6;
205		}
206		if (($byte & 0b11111100) === 0b11111000) {
207		return 5;
208		}
209		if (($byte & 0b11111000) === 0b11110000) {
210		return 4;
211		}
212		if (($byte & 0b11110000) === 0b11100000) {
213		return 3;
214		}
215		if (($byte & 0b11100000) === 0b11000000) {
216		return 2;
217		}
218		return 1;
219		}
220		}
221

garrettw / stringobject

Push — master ( 891408...d32ecd )

UStrObj::loadToArray() C

Complexity

Size

Duplication

Importance

How to fix Long Method Complexity

Long Method

Available Fixes

Available Fixes

Available Fixes

Available Fixes

Duplication Side-by-Side

Filter issues like