Normalizer::normalize() - Code Metrics - Inspection of "Merge branch 'feature/1136-integrate-with-new-plat..." - insideout10/wordlift-plugin - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — develop ( f11ef2...d41b65 )

by David

created 2020-11-17 13:14 UTC

Normalizer::normalize() D

↳ Parent: Normalizer

Complexity

Conditions	17
Paths	199

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	17
nc	199
nop	2
dl	0
loc	52
rs	4.3916
c	0
b	0
f	0

How to fix Long Method Complexity

<?php

/*
 * This file is part of the Symfony package.
 *
 * (c) Fabien Potencier <[email protected]>
 *
 * For the full copyright and license information, please view the LICENSE
 * file that was distributed with this source code.
 */

namespace Symfony\Polyfill\Intl\Normalizer;

/**
 * Normalizer is a PHP fallback implementation of the Normalizer class provided by the intl extension.
 *
 * It has been validated with Unicode 6.3 Normalization Conformance Test.
 * See http://www.unicode.org/reports/tr15/ for detailed info about Unicode normalizations.
 *
 * @author Nicolas Grekas <[email protected]>
 *
 * @internal
 */
class Normalizer
{
    const FORM_D = \Normalizer::FORM_D;
    const FORM_KD = \Normalizer::FORM_KD;
    const FORM_C = \Normalizer::FORM_C;
    const FORM_KC = \Normalizer::FORM_KC;
    const NFD = \Normalizer::NFD;
    const NFKD = \Normalizer::NFKD;
    const NFC = \Normalizer::NFC;
    const NFKC = \Normalizer::NFKC;

    private static $C;
    private static $D;
    private static $KD;
    private static $cC;
    private static $ulenMask = array("\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4);
    private static $ASCII = "\x20\x65\x69\x61\x73\x6E\x74\x72\x6F\x6C\x75\x64\x5D\x5B\x63\x6D\x70\x27\x0A\x67\x7C\x68\x76\x2E\x66\x62\x2C\x3A\x3D\x2D\x71\x31\x30\x43\x32\x2A\x79\x78\x29\x28\x4C\x39\x41\x53\x2F\x50\x22\x45\x6A\x4D\x49\x6B\x33\x3E\x35\x54\x3C\x44\x34\x7D\x42\x7B\x38\x46\x77\x52\x36\x37\x55\x47\x4E\x3B\x4A\x7A\x56\x23\x48\x4F\x57\x5F\x26\x21\x4B\x3F\x58\x51\x25\x59\x5C\x09\x5A\x2B\x7E\x5E\x24\x40\x60\x7F\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0B\x0C\x0D\x0E\x0F\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F";

    public static function isNormalized($s, $form = self::NFC)
    {
        if (!\in_array($form, array(self::NFD, self::NFKD, self::NFC, self::NFKC))) {
            return false;
        }
        $s = (string) $s;
        if (!isset($s[strspn($s, self::$ASCII)])) {
            return true;
        }
        if (self::NFC == $form && preg_match('//u', $s) && !preg_match('/[^\x00-\x{2FF}]/u', $s)) {
            return true;
        }

        return self::normalize($s, $form) === $s;
    }

    public static function normalize($s, $form = self::NFC)
    {
        $s = (string) $s;
        if (!preg_match('//u', $s)) {
            return false;
        }

        switch ($form) {
            case self::NFC: $C = true; $K = false; break;
            case self::NFD: $C = false; $K = false; break;
            case self::NFKC: $C = true; $K = true; break;
            case self::NFKD: $C = false; $K = true; break;
            default:
                if (\defined('Normalizer::NONE') && \Normalizer::NONE == $form) {

                    return $s;
                }

                return false;
        }

        if ('' === $s) {
            return '';
        }

        if ($K && null === self::$KD) {
            self::$KD = self::getData('compatibilityDecomposition');
        }

        if (null === self::$D) {
            self::$D = self::getData('canonicalDecomposition');
            self::$cC = self::getData('combiningClass');
        }

        if (null !== $mbEncoding = (2 /* MB_OVERLOAD_STRING */ & (int) ini_get('mbstring.func_overload')) ? mb_internal_encoding() : null) {
            mb_internal_encoding('8bit');
        }

        $r = self::decompose($s, $K);

        if ($C) {
            if (null === self::$C) {
                self::$C = self::getData('canonicalComposition');
            }

            $r = self::recompose($r);
        }
        if (null !== $mbEncoding) {
            mb_internal_encoding($mbEncoding);
        }

        return $r;
    }

    private static function recompose($s)
    {
        $ASCII = self::$ASCII;
        $compMap = self::$C;
        $combClass = self::$cC;
        $ulenMask = self::$ulenMask;

        $result = $tail = '';

        $i = $s[0] < "\x80" ? 1 : $ulenMask[$s[0] & "\xF0"];
        $len = \strlen($s);

        $lastUchr = substr($s, 0, $i);
        $lastUcls = isset($combClass[$lastUchr]) ? 256 : 0;

        while ($i < $len) {
            if ($s[$i] < "\x80") {
                // ASCII chars

                if ($tail) {
                    $lastUchr .= $tail;
                    $tail = '';
                }

                if ($j = strspn($s, $ASCII, $i + 1)) {
                    $lastUchr .= substr($s, $i, $j);
                    $i += $j;
                }

                $result .= $lastUchr;
                $lastUchr = $s[$i];
                $lastUcls = 0;
                ++$i;
                continue;
            }

            $ulen = $ulenMask[$s[$i] & "\xF0"];
            $uchr = substr($s, $i, $ulen);

            if ($lastUchr < "\xE1\x84\x80" || "\xE1\x84\x92" < $lastUchr
                || $uchr < "\xE1\x85\xA1" || "\xE1\x85\xB5" < $uchr
                || $lastUcls) {
                // Table lookup and combining chars composition

                $ucls = isset($combClass[$uchr]) ? $combClass[$uchr] : 0;

                if (isset($compMap[$lastUchr.$uchr]) && (!$lastUcls || $lastUcls < $ucls)) {
                    $lastUchr = $compMap[$lastUchr.$uchr];
                } elseif ($lastUcls = $ucls) {
                    $tail .= $uchr;
                } else {
                    if ($tail) {
                        $lastUchr .= $tail;
                        $tail = '';
                    }

                    $result .= $lastUchr;
                    $lastUchr = $uchr;
                }
            } else {
                // Hangul chars

                $L = \ord($lastUchr[2]) - 0x80;
                $V = \ord($uchr[2]) - 0xA1;
                $T = 0;

                $uchr = substr($s, $i + $ulen, 3);

                if ("\xE1\x86\xA7" <= $uchr && $uchr <= "\xE1\x87\x82") {
                    $T = \ord($uchr[2]) - 0xA7;
                    0 > $T && $T += 0x40;
                    $ulen += 3;
                }

                $L = 0xAC00 + ($L * 21 + $V) * 28 + $T;
                $lastUchr = \chr(0xE0 | $L >> 12).\chr(0x80 | $L >> 6 & 0x3F).\chr(0x80 | $L & 0x3F);
            }

            $i += $ulen;
        }

        return $result.$lastUchr.$tail;
    }

    private static function decompose($s, $c)
    {
        $result = '';

        $ASCII = self::$ASCII;
        $decompMap = self::$D;
        $combClass = self::$cC;
        $ulenMask = self::$ulenMask;
        if ($c) {
            $compatMap = self::$KD;
        }

        $c = array();
        $i = 0;
        $len = \strlen($s);

        while ($i < $len) {
            if ($s[$i] < "\x80") {
                // ASCII chars

                if ($c) {

                    ksort($c);
                    $result .= implode('', $c);
                    $c = array();
                }

                $j = 1 + strspn($s, $ASCII, $i + 1);
                $result .= substr($s, $i, $j);
                $i += $j;
                continue;
            }

            $ulen = $ulenMask[$s[$i] & "\xF0"];
            $uchr = substr($s, $i, $ulen);
            $i += $ulen;

            if ($uchr < "\xEA\xB0\x80" || "\xED\x9E\xA3" < $uchr) {
                // Table lookup

                if ($uchr !== $j = isset($compatMap[$uchr]) ? $compatMap[$uchr] : (isset($decompMap[$uchr]) ? $decompMap[$uchr] : $uchr)) {
                    $uchr = $j;

                    $j = \strlen($uchr);
                    $ulen = $uchr[0] < "\x80" ? 1 : $ulenMask[$uchr[0] & "\xF0"];

                    if ($ulen != $j) {
                        // Put trailing chars in $s

                        $j -= $ulen;
                        $i -= $j;

                        if (0 > $i) {
                            $s = str_repeat(' ', -$i).$s;
                            $len -= $i;
                            $i = 0;
                        }

                        while ($j--) {
                            $s[$i + $j] = $uchr[$ulen + $j];
                        }

                        $uchr = substr($uchr, 0, $ulen);
                    }
                }
                if (isset($combClass[$uchr])) {
                    // Combining chars, for sorting

                    if (!isset($c[$combClass[$uchr]])) {
                        $c[$combClass[$uchr]] = '';
                    }
                    $c[$combClass[$uchr]] .= $uchr;
                    continue;
                }
            } else {
                // Hangul chars

                $uchr = unpack('C*', $uchr);
                $j = (($uchr[1] - 224) << 12) + (($uchr[2] - 128) << 6) + $uchr[3] - 0xAC80;

                $uchr = "\xE1\x84".\chr(0x80 + (int) ($j / 588))
                       ."\xE1\x85".\chr(0xA1 + (int) (($j % 588) / 28));

                if ($j %= 28) {
                    $uchr .= $j < 25
                        ? ("\xE1\x86".\chr(0xA7 + $j))
                        : ("\xE1\x87".\chr(0x67 + $j));
                }
            }
            if ($c) {

                ksort($c);
                $result .= implode('', $c);
                $c = array();
            }

            $result .= $uchr;
        }

        if ($c) {

            ksort($c);
            $result .= implode('', $c);
        }

        return $result;
    }

    private static function getData($file)

    {
        if (file_exists($file = __DIR__.'/Resources/unidata/'.$file.'.php')) {
            return require $file;
        }

        return false;
    }
}


1		<?php
2
3		/*
4		* This file is part of the Symfony package.
5		*
6		* (c) Fabien Potencier <[email protected]>
7		*
8		* For the full copyright and license information, please view the LICENSE
9		* file that was distributed with this source code.
10		*/
11
12		namespace Symfony\Polyfill\Intl\Normalizer;
13
14		/**
15		* Normalizer is a PHP fallback implementation of the Normalizer class provided by the intl extension.
16		*
17		* It has been validated with Unicode 6.3 Normalization Conformance Test.
18		* See http://www.unicode.org/reports/tr15/ for detailed info about Unicode normalizations.
19		*
20		* @author Nicolas Grekas <[email protected]>
21		*
22		* @internal
23		*/
24		class Normalizer
25		{
26		const FORM_D = \Normalizer::FORM_D;
27		const FORM_KD = \Normalizer::FORM_KD;
28		const FORM_C = \Normalizer::FORM_C;
29		const FORM_KC = \Normalizer::FORM_KC;
30		const NFD = \Normalizer::NFD;
31		const NFKD = \Normalizer::NFKD;
32		const NFC = \Normalizer::NFC;
33		const NFKC = \Normalizer::NFKC;
34
35		private static $C;
36		private static $D;
37		private static $KD;
38		private static $cC;
39		private static $ulenMask = array("\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4);
40		private static $ASCII = "\x20\x65\x69\x61\x73\x6E\x74\x72\x6F\x6C\x75\x64\x5D\x5B\x63\x6D\x70\x27\x0A\x67\x7C\x68\x76\x2E\x66\x62\x2C\x3A\x3D\x2D\x71\x31\x30\x43\x32\x2A\x79\x78\x29\x28\x4C\x39\x41\x53\x2F\x50\x22\x45\x6A\x4D\x49\x6B\x33\x3E\x35\x54\x3C\x44\x34\x7D\x42\x7B\x38\x46\x77\x52\x36\x37\x55\x47\x4E\x3B\x4A\x7A\x56\x23\x48\x4F\x57\x5F\x26\x21\x4B\x3F\x58\x51\x25\x59\x5C\x09\x5A\x2B\x7E\x5E\x24\x40\x60\x7F\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0B\x0C\x0D\x0E\x0F\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F";
41
42		public static function isNormalized($s, $form = self::NFC)
43		{
44		if (!\in_array($form, array(self::NFD, self::NFKD, self::NFC, self::NFKC))) {
45		return false;
46		}
47		$s = (string) $s;
48		if (!isset($s[strspn($s, self::$ASCII)])) {
49		return true;
50		}
51		if (self::NFC == $form && preg_match('//u', $s) && !preg_match('/[^\x00-\x{2FF}]/u', $s)) {
52		return true;
53		}
54
55		return self::normalize($s, $form) === $s;
56		}
57
58		public static function normalize($s, $form = self::NFC)
59		{
60		$s = (string) $s;
61		if (!preg_match('//u', $s)) {
62		return false;
63		}
64
65		switch ($form) {
66		case self::NFC: $C = true; $K = false; break;
67		case self::NFD: $C = false; $K = false; break;
68		case self::NFKC: $C = true; $K = true; break;
69		case self::NFKD: $C = false; $K = true; break;
70		default:
71		if (\defined('Normalizer::NONE') && \Normalizer::NONE == $form) {
		0 ignored issues – show Deprecated Code introduced 2020-11-17 13:20 UTC by Report Bug Copy Issue Report The constant `Normalizer::NONE` has been deprecated with message: since ICU 56 and removed in PHP 8 This class constant has been deprecated. The supplier of the class has supplied an explanatory message. The explanatory message should give you some clue as to whether and when the constant will be removed from the class and what other constant to use instead. Loading history...
72		return $s;
73		}
74
75		return false;
76		}
77
78		if ('' === $s) {
79		return '';
80		}
81
82		if ($K && null === self::$KD) {
83		self::$KD = self::getData('compatibilityDecomposition');
84		}
85
86		if (null === self::$D) {
87		self::$D = self::getData('canonicalDecomposition');
88		self::$cC = self::getData('combiningClass');
89		}
90
91		if (null !== $mbEncoding = (2 /* MB_OVERLOAD_STRING */ & (int) ini_get('mbstring.func_overload')) ? mb_internal_encoding() : null) {
92		mb_internal_encoding('8bit');
93		}
94
95		$r = self::decompose($s, $K);
96
97		if ($C) {
98		if (null === self::$C) {
99		self::$C = self::getData('canonicalComposition');
100		}
101
102		$r = self::recompose($r);
103		}
104		if (null !== $mbEncoding) {
105		mb_internal_encoding($mbEncoding);
106		}
107
108		return $r;
109		}
110
111		private static function recompose($s)
112		{
113		$ASCII = self::$ASCII;
114		$compMap = self::$C;
115		$combClass = self::$cC;
116		$ulenMask = self::$ulenMask;
117
118		$result = $tail = '';
119
120		$i = $s[0] < "\x80" ? 1 : $ulenMask[$s[0] & "\xF0"];
121		$len = \strlen($s);
122
123		$lastUchr = substr($s, 0, $i);
124		$lastUcls = isset($combClass[$lastUchr]) ? 256 : 0;
125
126		while ($i < $len) {
127		if ($s[$i] < "\x80") {
128		// ASCII chars
129
130		if ($tail) {
131		$lastUchr .= $tail;
132		$tail = '';
133		}
134
135		if ($j = strspn($s, $ASCII, $i + 1)) {
136		$lastUchr .= substr($s, $i, $j);
137		$i += $j;
138		}
139
140		$result .= $lastUchr;
141		$lastUchr = $s[$i];
142		$lastUcls = 0;
143		++$i;
144		continue;
145		}
146
147		$ulen = $ulenMask[$s[$i] & "\xF0"];
148		$uchr = substr($s, $i, $ulen);
149
150		if ($lastUchr < "\xE1\x84\x80" \|\| "\xE1\x84\x92" < $lastUchr
151		\|\| $uchr < "\xE1\x85\xA1" \|\| "\xE1\x85\xB5" < $uchr
152		\|\| $lastUcls) {
153		// Table lookup and combining chars composition
154
155		$ucls = isset($combClass[$uchr]) ? $combClass[$uchr] : 0;
156
157		if (isset($compMap[$lastUchr.$uchr]) && (!$lastUcls \|\| $lastUcls < $ucls)) {
158		$lastUchr = $compMap[$lastUchr.$uchr];
159		} elseif ($lastUcls = $ucls) {
160		$tail .= $uchr;
161		} else {
162		if ($tail) {
163		$lastUchr .= $tail;
164		$tail = '';
165		}
166
167		$result .= $lastUchr;
168		$lastUchr = $uchr;
169		}
170		} else {
171		// Hangul chars
172
173		$L = \ord($lastUchr[2]) - 0x80;
174		$V = \ord($uchr[2]) - 0xA1;
175		$T = 0;
176
177		$uchr = substr($s, $i + $ulen, 3);
178
179		if ("\xE1\x86\xA7" <= $uchr && $uchr <= "\xE1\x87\x82") {
180		$T = \ord($uchr[2]) - 0xA7;
181		0 > $T && $T += 0x40;
182		$ulen += 3;
183		}
184
185		$L = 0xAC00 + ($L * 21 + $V) * 28 + $T;
186		$lastUchr = \chr(0xE0 \| $L >> 12).\chr(0x80 \| $L >> 6 & 0x3F).\chr(0x80 \| $L & 0x3F);
187		}
188
189		$i += $ulen;
190		}
191
192		return $result.$lastUchr.$tail;
193		}
194
195		private static function decompose($s, $c)
196		{
197		$result = '';
198
199		$ASCII = self::$ASCII;
200		$decompMap = self::$D;
201		$combClass = self::$cC;
202		$ulenMask = self::$ulenMask;
203		if ($c) {
204		$compatMap = self::$KD;
205		}
206
207		$c = array();
208		$i = 0;
209		$len = \strlen($s);
210
211		while ($i < $len) {
212		if ($s[$i] < "\x80") {
213		// ASCII chars
214
215		if ($c) {
		0 ignored issues – show Bug Best Practice introduced 2020-11-17 13:20 UTC by Report Bug Copy Issue Report The expression `$c` of type `array` is implicitly converted to a boolean; are you sure this is intended? If so, consider using `! empty($expr)` instead to make it clear that you intend to check for an array without elements. This check marks implicit conversions of arrays to boolean values in a comparison. While in PHP an empty array is considered to be equal (but not identical) to false, this is not always apparent. Consider making the comparison explicit by using `empty(..)` or `! empty(...)` instead. Loading history...
216		ksort($c);
217		$result .= implode('', $c);
218		$c = array();
219		}
220
221		$j = 1 + strspn($s, $ASCII, $i + 1);
222		$result .= substr($s, $i, $j);
223		$i += $j;
224		continue;
225		}
226
227		$ulen = $ulenMask[$s[$i] & "\xF0"];
228		$uchr = substr($s, $i, $ulen);
229		$i += $ulen;
230
231		if ($uchr < "\xEA\xB0\x80" \|\| "\xED\x9E\xA3" < $uchr) {
232		// Table lookup
233
234		if ($uchr !== $j = isset($compatMap[$uchr]) ? $compatMap[$uchr] : (isset($decompMap[$uchr]) ? $decompMap[$uchr] : $uchr)) {
235		$uchr = $j;
236
237		$j = \strlen($uchr);
238		$ulen = $uchr[0] < "\x80" ? 1 : $ulenMask[$uchr[0] & "\xF0"];
239
240		if ($ulen != $j) {
241		// Put trailing chars in $s
242
243		$j -= $ulen;
244		$i -= $j;
245
246		if (0 > $i) {
247		$s = str_repeat(' ', -$i).$s;
248		$len -= $i;
249		$i = 0;
250		}
251
252		while ($j--) {
253		$s[$i + $j] = $uchr[$ulen + $j];
254		}
255
256		$uchr = substr($uchr, 0, $ulen);
257		}
258		}
259		if (isset($combClass[$uchr])) {
260		// Combining chars, for sorting
261
262		if (!isset($c[$combClass[$uchr]])) {
263		$c[$combClass[$uchr]] = '';
264		}
265		$c[$combClass[$uchr]] .= $uchr;
266		continue;
267		}
268		} else {
269		// Hangul chars
270
271		$uchr = unpack('C*', $uchr);
272		$j = (($uchr[1] - 224) << 12) + (($uchr[2] - 128) << 6) + $uchr[3] - 0xAC80;
273
274		$uchr = "\xE1\x84".\chr(0x80 + (int) ($j / 588))
275		."\xE1\x85".\chr(0xA1 + (int) (($j % 588) / 28));
276
277		if ($j %= 28) {
278		$uchr .= $j < 25
279		? ("\xE1\x86".\chr(0xA7 + $j))
280		: ("\xE1\x87".\chr(0x67 + $j));
281		}
282		}
283		if ($c) {
		0 ignored issues – show Bug Best Practice introduced 2020-11-17 13:20 UTC by Report Bug Copy Issue Report The expression `$c` of type `array` is implicitly converted to a boolean; are you sure this is intended? If so, consider using `! empty($expr)` instead to make it clear that you intend to check for an array without elements. This check marks implicit conversions of arrays to boolean values in a comparison. While in PHP an empty array is considered to be equal (but not identical) to false, this is not always apparent. Consider making the comparison explicit by using `empty(..)` or `! empty(...)` instead. Loading history...
284		ksort($c);
285		$result .= implode('', $c);
286		$c = array();
287		}
288
289		$result .= $uchr;
290		}
291
292		if ($c) {
		0 ignored issues – show Bug Best Practice introduced 2020-11-17 13:20 UTC by Report Bug Copy Issue Report The expression `$c` of type `array` is implicitly converted to a boolean; are you sure this is intended? If so, consider using `! empty($expr)` instead to make it clear that you intend to check for an array without elements. This check marks implicit conversions of arrays to boolean values in a comparison. While in PHP an empty array is considered to be equal (but not identical) to false, this is not always apparent. Consider making the comparison explicit by using `empty(..)` or `! empty(...)` instead. Loading history...
293		ksort($c);
294		$result .= implode('', $c);
295		}
296
297		return $result;
298		}
299
300	View Code Duplication	private static function getData($file)
		0 ignored issues – show Duplication introduced 2020-11-17 13:20 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...
301		{
302		if (file_exists($file = __DIR__.'/Resources/unidata/'.$file.'.php')) {
303		return require $file;
304		}
305
306		return false;
307		}
308		}
309

insideout10 / wordlift-plugin

Push — develop ( f11ef2...d41b65 )

Normalizer::normalize() D

Complexity

Size

Duplication

Importance

How to fix Long Method Complexity

Long Method

Duplication Side-by-Side

Filter issues like