Mbstring::mb_get_info() - Code Metrics - Inspection of "composer install" - gctools-outilsgc/gcconnex - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — composer-installed ( c4bac5 )

by Ilia

created 2019-11-10 18:36 UTC

Mbstring::mb_get_info() A

↳ Parent: Mbstring

Complexity

Conditions	3
Paths	3

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	3
nc	3
nop	1
dl	0
loc	28
rs	9.472
c	0
b	0
f	0

<?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\Mbstring;

/**
 * Partial mbstring implementation in PHP, iconv based, UTF-8 centric.
 *
 * Implemented:
 * - mb_chr                  - Returns a specific character from its Unicode code point
 * - mb_convert_encoding     - Convert character encoding
 * - mb_convert_variables    - Convert character code in variable(s)
 * - mb_decode_mimeheader    - Decode string in MIME header field
 * - mb_encode_mimeheader    - Encode string for MIME header XXX NATIVE IMPLEMENTATION IS REALLY BUGGED
 * - mb_convert_case         - Perform case folding on a string
 * - mb_get_info             - Get internal settings of mbstring
 * - mb_http_input           - Detect HTTP input character encoding
 * - mb_http_output          - Set/Get HTTP output character encoding
 * - mb_internal_encoding    - Set/Get internal character encoding
 * - mb_list_encodings       - Returns an array of all supported encodings
 * - mb_ord                  - Returns the Unicode code point of a character
 * - mb_output_handler       - Callback function converts character encoding in output buffer
 * - mb_scrub                - Replaces ill-formed byte sequences with substitute characters
 * - mb_strlen               - Get string length
 * - mb_strpos               - Find position of first occurrence of string in a string
 * - mb_strrpos              - Find position of last occurrence of a string in a string
 * - mb_strtolower           - Make a string lowercase
 * - mb_strtoupper           - Make a string uppercase
 * - mb_substitute_character - Set/Get substitution character
 * - mb_substr               - Get part of string
 * - mb_stripos              - Finds position of first occurrence of a string within another, case insensitive
 * - mb_stristr              - Finds first occurrence of a string within another, case insensitive
 * - mb_strrchr              - Finds the last occurrence of a character in a string within another
 * - mb_strrichr             - Finds the last occurrence of a character in a string within another, case insensitive
 * - mb_strripos             - Finds position of last occurrence of a string within another, case insensitive
 * - mb_strstr               - Finds first occurrence of a string within anothers
 * - mb_strwidth             - Return width of string
 * - mb_substr_count         - Count the number of substring occurrences
 *
 * Not implemented:
 * - mb_convert_kana         - Convert "kana" one from another ("zen-kaku", "han-kaku" and more)
 * - mb_decode_numericentity - Decode HTML numeric string reference to character
 * - mb_encode_numericentity - Encode character to HTML numeric string reference
 * - mb_ereg_*               - Regular expression with multibyte support
 * - mb_parse_str            - Parse GET/POST/COOKIE data and set global variable
 * - mb_preferred_mime_name  - Get MIME charset string
 * - mb_regex_encoding       - Returns current encoding for multibyte regex as string
 * - mb_regex_set_options    - Set/Get the default options for mbregex functions
 * - mb_send_mail            - Send encoded mail
 * - mb_split                - Split multibyte string using regular expression
 * - mb_strcut               - Get part of string
 * - mb_strimwidth           - Get truncated string with specified width
 *
 * @author Nicolas Grekas <[email protected]>
 *
 * @internal
 */
final class Mbstring
{
    const MB_CASE_FOLD = PHP_INT_MAX;

    private static $encodingList = array('ASCII', 'UTF-8');
    private static $language = 'neutral';
    private static $internalEncoding = 'UTF-8';
    private static $caseFold = array(
        array('µ','ſ',"\xCD\x85",'ς',"\xCF\x90","\xCF\x91","\xCF\x95","\xCF\x96","\xCF\xB0","\xCF\xB1","\xCF\xB5","\xE1\xBA\x9B","\xE1\xBE\xBE"),
        array('μ','s','ι',       'σ','β',       'θ',       'φ',       'π',       'κ',       'ρ',       'ε',       "\xE1\xB9\xA1",'ι'),
    );

    public static function mb_convert_encoding($s, $toEncoding, $fromEncoding = null)
    {
        if (is_array($fromEncoding) || false !== strpos($fromEncoding, ',')) {
            $fromEncoding = self::mb_detect_encoding($s, $fromEncoding);
        } else {
            $fromEncoding = self::getEncoding($fromEncoding);
        }

        $toEncoding = self::getEncoding($toEncoding);

        if ('BASE64' === $fromEncoding) {
            $s = base64_decode($s);
            $fromEncoding = $toEncoding;
        }

        if ('BASE64' === $toEncoding) {
            return base64_encode($s);
        }

        if ('HTML-ENTITIES' === $toEncoding || 'HTML' === $toEncoding) {
            if ('HTML-ENTITIES' === $fromEncoding || 'HTML' === $fromEncoding) {
                $fromEncoding = 'Windows-1252';
            }
            if ('UTF-8' !== $fromEncoding) {
                $s = iconv($fromEncoding, 'UTF-8//IGNORE', $s);
            }

            return preg_replace_callback('/[\x80-\xFF]+/', array(__CLASS__, 'html_encoding_callback'), $s);
        }

        if ('HTML-ENTITIES' === $fromEncoding) {
            $s = html_entity_decode($s, ENT_COMPAT, 'UTF-8');
            $fromEncoding = 'UTF-8';
        }

        return iconv($fromEncoding, $toEncoding.'//IGNORE', $s);
    }

    public static function mb_convert_variables($toEncoding, $fromEncoding, &$a = null, &$b = null, &$c = null, &$d = null, &$e = null, &$f = null)
    {
        $vars = array(&$a, &$b, &$c, &$d, &$e, &$f);

        $ok = true;
        array_walk_recursive($vars, function (&$v) use (&$ok, $toEncoding, $fromEncoding) {
            if (false === $v = Mbstring::mb_convert_encoding($v, $toEncoding, $fromEncoding)) {
                $ok = false;
            }
        });

        return $ok ? $fromEncoding : false;
    }

    public static function mb_decode_mimeheader($s)
    {
        return iconv_mime_decode($s, 2, self::$internalEncoding);
    }

    public static function mb_encode_mimeheader($s, $charset = null, $transferEncoding = null, $linefeed = null, $indent = null)
    {
        trigger_error('mb_encode_mimeheader() is bugged. Please use iconv_mime_encode() instead', E_USER_WARNING);
    }

    public static function mb_convert_case($s, $mode, $encoding = null)
    {
        if ('' === $s .= '') {
            return '';
        }

        $encoding = self::getEncoding($encoding);

        if ('UTF-8' === $encoding) {
            $encoding = null;
            if (!preg_match('//u', $s)) {
                $s = @iconv('UTF-8', 'UTF-8//IGNORE', $s);
            }
        } else {
            $s = iconv($encoding, 'UTF-8//IGNORE', $s);
        }

        if (MB_CASE_TITLE == $mode) {
            $s = preg_replace_callback('/\b\p{Ll}/u', array(__CLASS__, 'title_case_upper'), $s);
            $s = preg_replace_callback('/\B[\p{Lu}\p{Lt}]+/u', array(__CLASS__, 'title_case_lower'), $s);
        } else {
            if (MB_CASE_UPPER == $mode) {
                static $upper = null;
                if (null === $upper) {
                    $upper = self::getData('upperCase');
                }
                $map = $upper;
            } else {
                if (self::MB_CASE_FOLD === $mode) {
                    $s = str_replace(self::$caseFold[0], self::$caseFold[1], $s);
                }

                static $lower = null;
                if (null === $lower) {
                    $lower = self::getData('lowerCase');
                }
                $map = $lower;
            }

            static $ulenMask = array("\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4);

            $i = 0;
            $len = strlen($s);

            while ($i < $len) {
                $ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"];
                $uchr = substr($s, $i, $ulen);
                $i += $ulen;

                if (isset($map[$uchr])) {
                    $uchr = $map[$uchr];
                    $nlen = strlen($uchr);

                    if ($nlen == $ulen) {
                        $nlen = $i;
                        do {
                            $s[--$nlen] = $uchr[--$ulen];
                        } while ($ulen);
                    } else {
                        $s = substr_replace($s, $uchr, $i - $ulen, $ulen);
                        $len += $nlen - $ulen;
                        $i   += $nlen - $ulen;
                    }
                }
            }
        }

        if (null === $encoding) {
            return $s;
        }

        return iconv('UTF-8', $encoding.'//IGNORE', $s);
    }

    public static function mb_internal_encoding($encoding = null)
    {
        if (null === $encoding) {
            return self::$internalEncoding;
        }

        $encoding = self::getEncoding($encoding);

        if ('UTF-8' === $encoding || false !== @iconv($encoding, $encoding, ' ')) {
            self::$internalEncoding = $encoding;

            return true;
        }

        return false;
    }

    public static function mb_language($lang = null)
    {
        if (null === $lang) {
            return self::$language;
        }

        switch ($lang = strtolower($lang)) {
            case 'uni':
            case 'neutral':
                self::$language = $lang;

                return true;
        }

        return false;
    }

    public static function mb_list_encodings()
    {
        return array('UTF-8');
    }

    public static function mb_encoding_aliases($encoding)
    {
        switch (strtoupper($encoding)) {
            case 'UTF8':
            case 'UTF-8':
                return array('utf8');
        }

        return false;
    }

    public static function mb_check_encoding($var = null, $encoding = null)
    {
        if (null === $encoding) {
            if (null === $var) {
                return false;
            }
            $encoding = self::$internalEncoding;
        }

        return self::mb_detect_encoding($var, array($encoding)) || false !== @iconv($encoding, $encoding, $var);
    }

    public static function mb_detect_encoding($str, $encodingList = null, $strict = false)
    {
        if (null === $encodingList) {
            $encodingList = self::$encodingList;
        } else {
            if (!is_array($encodingList)) {
                $encodingList = array_map('trim', explode(',', $encodingList));
            }
            $encodingList = array_map('strtoupper', $encodingList);
        }

        foreach ($encodingList as $enc) {
            switch ($enc) {
                case 'ASCII':
                    if (!preg_match('/[\x80-\xFF]/', $str)) {
                        return $enc;
                    }
                    break;

                case 'UTF8':
                case 'UTF-8':
                    if (preg_match('//u', $str)) {
                        return 'UTF-8';
                    }
                    break;

                default:
                    if (0 === strncmp($enc, 'ISO-8859-', 9)) {
                        return $enc;
                    }
            }
        }

        return false;
    }

    public static function mb_detect_order($encodingList = null)
    {
        if (null === $encodingList) {
            return self::$encodingList;
        }

        if (!is_array($encodingList)) {
            $encodingList = array_map('trim', explode(',', $encodingList));
        }
        $encodingList = array_map('strtoupper', $encodingList);

        foreach ($encodingList as $enc) {
            switch ($enc) {
                default:
                    if (strncmp($enc, 'ISO-8859-', 9)) {
                        return false;
                    }
                case 'ASCII':
                case 'UTF8':
                case 'UTF-8':
            }
        }

        self::$encodingList = $encodingList;

        return true;
    }

    public static function mb_strlen($s, $encoding = null)
    {
        $encoding = self::getEncoding($encoding);
        if ('CP850' === $encoding || 'ASCII' === $encoding) {
            return strlen($s);
        }

        return @iconv_strlen($s, $encoding);
    }

    public static function mb_strpos($haystack, $needle, $offset = 0, $encoding = null)
    {
        $encoding = self::getEncoding($encoding);
        if ('CP850' === $encoding || 'ASCII' === $encoding) {
            return strpos($haystack, $needle, $offset);
        }

        if ('' === $needle .= '') {
            trigger_error(__METHOD__.': Empty delimiter', E_USER_WARNING);

            return false;
        }

        return iconv_strpos($haystack, $needle, $offset, $encoding);
    }

    public static function mb_strrpos($haystack, $needle, $offset = 0, $encoding = null)
    {
        $encoding = self::getEncoding($encoding);
        if ('CP850' === $encoding || 'ASCII' === $encoding) {
            return strrpos($haystack, $needle, $offset);
        }

        if ($offset != (int) $offset) {
            $offset = 0;
        } elseif ($offset = (int) $offset) {
            if ($offset < 0) {
                $haystack = self::mb_substr($haystack, 0, $offset, $encoding);
                $offset = 0;
            } else {
                $haystack = self::mb_substr($haystack, $offset, 2147483647, $encoding);
            }
        }

        $pos = iconv_strrpos($haystack, $needle, $encoding);

        return false !== $pos ? $offset + $pos : false;
    }

    public static function mb_strtolower($s, $encoding = null)
    {
        return self::mb_convert_case($s, MB_CASE_LOWER, $encoding);
    }

    public static function mb_strtoupper($s, $encoding = null)
    {
        return self::mb_convert_case($s, MB_CASE_UPPER, $encoding);
    }

    public static function mb_substitute_character($c = null)
    {
        if (0 === strcasecmp($c, 'none')) {
            return true;
        }

        return null !== $c ? false : 'none';
    }

    public static function mb_substr($s, $start, $length = null, $encoding = null)
    {
        $encoding = self::getEncoding($encoding);
        if ('CP850' === $encoding || 'ASCII' === $encoding) {
            return substr($s, $start, null === $length ? 2147483647 : $length);
        }

        if ($start < 0) {
            $start = iconv_strlen($s, $encoding) + $start;
            if ($start < 0) {
                $start = 0;
            }
        }

        if (null === $length) {
            $length = 2147483647;
        } elseif ($length < 0) {
            $length = iconv_strlen($s, $encoding) + $length - $start;
            if ($length < 0) {
                return '';
            }
        }

        return iconv_substr($s, $start, $length, $encoding).'';
    }

    public static function mb_stripos($haystack, $needle, $offset = 0, $encoding = null)

    {
        $haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding);
        $needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding);

        return self::mb_strpos($haystack, $needle, $offset, $encoding);
    }

    public static function mb_stristr($haystack, $needle, $part = false, $encoding = null)
    {
        $pos = self::mb_stripos($haystack, $needle, 0, $encoding);

        return self::getSubpart($pos, $part, $haystack, $encoding);
    }

    public static function mb_strrchr($haystack, $needle, $part = false, $encoding = null)
    {
        $encoding = self::getEncoding($encoding);
        if ('CP850' === $encoding || 'ASCII' === $encoding) {
            return strrchr($haystack, $needle, $part);
        }
        $needle = self::mb_substr($needle, 0, 1, $encoding);
        $pos = iconv_strrpos($haystack, $needle, $encoding);

        return self::getSubpart($pos, $part, $haystack, $encoding);
    }

    public static function mb_strrichr($haystack, $needle, $part = false, $encoding = null)
    {
        $needle = self::mb_substr($needle, 0, 1, $encoding);
        $pos = self::mb_strripos($haystack, $needle, $encoding);

        return self::getSubpart($pos, $part, $haystack, $encoding);
    }

    public static function mb_strripos($haystack, $needle, $offset = 0, $encoding = null)

    {
        $haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding);
        $needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding);

        return self::mb_strrpos($haystack, $needle, $offset, $encoding);
    }

    public static function mb_strstr($haystack, $needle, $part = false, $encoding = null)
    {
        $pos = strpos($haystack, $needle);
        if (false === $pos) {
            return false;
        }
        if ($part) {
            return substr($haystack, 0, $pos);
        }

        return substr($haystack, $pos);
    }

    public static function mb_get_info($type = 'all')
    {
        $info = array(
            'internal_encoding' => self::$internalEncoding,
            'http_output' => 'pass',
            'http_output_conv_mimetypes' => '^(text/|application/xhtml\+xml)',
            'func_overload' => 0,
            'func_overload_list' => 'no overload',
            'mail_charset' => 'UTF-8',
            'mail_header_encoding' => 'BASE64',
            'mail_body_encoding' => 'BASE64',
            'illegal_chars' => 0,
            'encoding_translation' => 'Off',
            'language' => self::$language,
            'detect_order' => self::$encodingList,
            'substitute_character' => 'none',
            'strict_detection' => 'Off',
        );

        if ('all' === $type) {
            return $info;
        }
        if (isset($info[$type])) {
            return $info[$type];
        }

        return false;
    }

    public static function mb_http_input($type = '')
    {
        return false;
    }

    public static function mb_http_output($encoding = null)
    {
        return null !== $encoding ? 'pass' === $encoding : 'pass';
    }

    public static function mb_strwidth($s, $encoding = null)
    {
        $encoding = self::getEncoding($encoding);

        if ('UTF-8' !== $encoding) {
            $s = iconv($encoding, 'UTF-8//IGNORE', $s);
        }

        $s = preg_replace('/[\x{1100}-\x{115F}\x{2329}\x{232A}\x{2E80}-\x{303E}\x{3040}-\x{A4CF}\x{AC00}-\x{D7A3}\x{F900}-\x{FAFF}\x{FE10}-\x{FE19}\x{FE30}-\x{FE6F}\x{FF00}-\x{FF60}\x{FFE0}-\x{FFE6}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}]/u', '', $s, -1, $wide);

        return ($wide << 1) + iconv_strlen($s, 'UTF-8');
    }

    public static function mb_substr_count($haystack, $needle, $encoding = null)
    {
        return substr_count($haystack, $needle);
    }

    public static function mb_output_handler($contents, $status)
    {
        return $contents;
    }

    public static function mb_chr($code, $encoding = null)
    {
        if (0x80 > $code %= 0x200000) {
            $s = chr($code);
        } elseif (0x800 > $code) {
            $s = chr(0xC0 | $code >> 6).chr(0x80 | $code & 0x3F);
        } elseif (0x10000 > $code) {
            $s = chr(0xE0 | $code >> 12).chr(0x80 | $code >> 6 & 0x3F).chr(0x80 | $code & 0x3F);
        } else {
            $s = chr(0xF0 | $code >> 18).chr(0x80 | $code >> 12 & 0x3F).chr(0x80 | $code >> 6 & 0x3F).chr(0x80 | $code & 0x3F);
        }

        if ('UTF-8' !== $encoding = self::getEncoding($encoding)) {
            $s = mb_convert_encoding($s, $encoding, 'UTF-8');
        }

        return $s;
    }

    public static function mb_ord($s, $encoding = null)
    {
        if ('UTF-8' !== $encoding = self::getEncoding($encoding)) {
            $s = mb_convert_encoding($s, 'UTF-8', $encoding);
        }

        $code = ($s = unpack('C*', substr($s, 0, 4))) ? $s[1] : 0;
        if (0xF0 <= $code) {
            return (($code - 0xF0) << 18) + (($s[2] - 0x80) << 12) + (($s[3] - 0x80) << 6) + $s[4] - 0x80;
        }
        if (0xE0 <= $code) {
            return (($code - 0xE0) << 12) + (($s[2] - 0x80) << 6) + $s[3] - 0x80;
        }
        if (0xC0 <= $code) {
            return (($code - 0xC0) << 6) + $s[2] - 0x80;
        }

        return $code;
    }

    private static function getSubpart($pos, $part, $haystack, $encoding)
    {
        if (false === $pos) {
            return false;
        }
        if ($part) {
            return self::mb_substr($haystack, 0, $pos, $encoding);
        }

        return self::mb_substr($haystack, $pos, null, $encoding);
    }

    private static function html_encoding_callback($m)
    {
        $i = 1;
        $entities = '';
        $m = unpack('C*', htmlentities($m[0], ENT_COMPAT, 'UTF-8'));

        while (isset($m[$i])) {
            if (0x80 > $m[$i]) {
                $entities .= chr($m[$i++]);
                continue;
            }
            if (0xF0 <= $m[$i]) {
                $c = (($m[$i++] - 0xF0) << 18) + (($m[$i++] - 0x80) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80;
            } elseif (0xE0 <= $m[$i]) {
                $c = (($m[$i++] - 0xE0) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80;
            } else {
                $c = (($m[$i++] - 0xC0) << 6) + $m[$i++] - 0x80;
            }

            $entities .= '&#'.$c.';';
        }

        return $entities;
    }

    private static function title_case_lower($s)
    {
        return self::mb_convert_case($s[0], MB_CASE_LOWER, 'UTF-8');
    }

    private static function title_case_upper($s)
    {
        return self::mb_convert_case($s[0], MB_CASE_UPPER, 'UTF-8');
    }

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

        return false;
    }

    private static function getEncoding($encoding)
    {
        if (null === $encoding) {
            return self::$internalEncoding;
        }

        $encoding = strtoupper($encoding);

        if ('8BIT' === $encoding || 'BINARY' === $encoding) {
            return 'CP850';
        }
        if ('UTF8' === $encoding) {
            return 'UTF-8';
        }

        return $encoding;
    }
}


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\Mbstring;
13
14		/**
15		* Partial mbstring implementation in PHP, iconv based, UTF-8 centric.
16		*
17		* Implemented:
18		* - mb_chr - Returns a specific character from its Unicode code point
19		* - mb_convert_encoding - Convert character encoding
20		* - mb_convert_variables - Convert character code in variable(s)
21		* - mb_decode_mimeheader - Decode string in MIME header field
22		* - mb_encode_mimeheader - Encode string for MIME header XXX NATIVE IMPLEMENTATION IS REALLY BUGGED
23		* - mb_convert_case - Perform case folding on a string
24		* - mb_get_info - Get internal settings of mbstring
25		* - mb_http_input - Detect HTTP input character encoding
26		* - mb_http_output - Set/Get HTTP output character encoding
27		* - mb_internal_encoding - Set/Get internal character encoding
28		* - mb_list_encodings - Returns an array of all supported encodings
29		* - mb_ord - Returns the Unicode code point of a character
30		* - mb_output_handler - Callback function converts character encoding in output buffer
31		* - mb_scrub - Replaces ill-formed byte sequences with substitute characters
32		* - mb_strlen - Get string length
33		* - mb_strpos - Find position of first occurrence of string in a string
34		* - mb_strrpos - Find position of last occurrence of a string in a string
35		* - mb_strtolower - Make a string lowercase
36		* - mb_strtoupper - Make a string uppercase
37		* - mb_substitute_character - Set/Get substitution character
38		* - mb_substr - Get part of string
39		* - mb_stripos - Finds position of first occurrence of a string within another, case insensitive
40		* - mb_stristr - Finds first occurrence of a string within another, case insensitive
41		* - mb_strrchr - Finds the last occurrence of a character in a string within another
42		* - mb_strrichr - Finds the last occurrence of a character in a string within another, case insensitive
43		* - mb_strripos - Finds position of last occurrence of a string within another, case insensitive
44		* - mb_strstr - Finds first occurrence of a string within anothers
45		* - mb_strwidth - Return width of string
46		* - mb_substr_count - Count the number of substring occurrences
47		*
48		* Not implemented:
49		* - mb_convert_kana - Convert "kana" one from another ("zen-kaku", "han-kaku" and more)
50		* - mb_decode_numericentity - Decode HTML numeric string reference to character
51		* - mb_encode_numericentity - Encode character to HTML numeric string reference
52		* - mb_ereg_* - Regular expression with multibyte support
53		* - mb_parse_str - Parse GET/POST/COOKIE data and set global variable
54		* - mb_preferred_mime_name - Get MIME charset string
55		* - mb_regex_encoding - Returns current encoding for multibyte regex as string
56		* - mb_regex_set_options - Set/Get the default options for mbregex functions
57		* - mb_send_mail - Send encoded mail
58		* - mb_split - Split multibyte string using regular expression
59		* - mb_strcut - Get part of string
60		* - mb_strimwidth - Get truncated string with specified width
61		*
62		* @author Nicolas Grekas <[email protected]>
63		*
64		* @internal
65		*/
66		final class Mbstring
67		{
68		const MB_CASE_FOLD = PHP_INT_MAX;
69
70		private static $encodingList = array('ASCII', 'UTF-8');
71		private static $language = 'neutral';
72		private static $internalEncoding = 'UTF-8';
73		private static $caseFold = array(
74		array('µ','ſ',"\xCD\x85",'ς',"\xCF\x90","\xCF\x91","\xCF\x95","\xCF\x96","\xCF\xB0","\xCF\xB1","\xCF\xB5","\xE1\xBA\x9B","\xE1\xBE\xBE"),
75		array('μ','s','ι', 'σ','β', 'θ', 'φ', 'π', 'κ', 'ρ', 'ε', "\xE1\xB9\xA1",'ι'),
76		);
77
78		public static function mb_convert_encoding($s, $toEncoding, $fromEncoding = null)
79		{
80		if (is_array($fromEncoding) \|\| false !== strpos($fromEncoding, ',')) {
81		$fromEncoding = self::mb_detect_encoding($s, $fromEncoding);
82		} else {
83		$fromEncoding = self::getEncoding($fromEncoding);
84		}
85
86		$toEncoding = self::getEncoding($toEncoding);
87
88		if ('BASE64' === $fromEncoding) {
89		$s = base64_decode($s);
90		$fromEncoding = $toEncoding;
91		}
92
93		if ('BASE64' === $toEncoding) {
94		return base64_encode($s);
95		}
96
97		if ('HTML-ENTITIES' === $toEncoding \|\| 'HTML' === $toEncoding) {
98		if ('HTML-ENTITIES' === $fromEncoding \|\| 'HTML' === $fromEncoding) {
99		$fromEncoding = 'Windows-1252';
100		}
101		if ('UTF-8' !== $fromEncoding) {
102		$s = iconv($fromEncoding, 'UTF-8//IGNORE', $s);
103		}
104
105		return preg_replace_callback('/[\x80-\xFF]+/', array(__CLASS__, 'html_encoding_callback'), $s);
106		}
107
108		if ('HTML-ENTITIES' === $fromEncoding) {
109		$s = html_entity_decode($s, ENT_COMPAT, 'UTF-8');
110		$fromEncoding = 'UTF-8';
111		}
112
113		return iconv($fromEncoding, $toEncoding.'//IGNORE', $s);
114		}
115
116		public static function mb_convert_variables($toEncoding, $fromEncoding, &$a = null, &$b = null, &$c = null, &$d = null, &$e = null, &$f = null)
117		{
118		$vars = array(&$a, &$b, &$c, &$d, &$e, &$f);
119
120		$ok = true;
121		array_walk_recursive($vars, function (&$v) use (&$ok, $toEncoding, $fromEncoding) {
122		if (false === $v = Mbstring::mb_convert_encoding($v, $toEncoding, $fromEncoding)) {
123		$ok = false;
124		}
125		});
126
127		return $ok ? $fromEncoding : false;
128		}
129
130		public static function mb_decode_mimeheader($s)
131		{
132		return iconv_mime_decode($s, 2, self::$internalEncoding);
133		}
134
135		public static function mb_encode_mimeheader($s, $charset = null, $transferEncoding = null, $linefeed = null, $indent = null)
136		{
137		trigger_error('mb_encode_mimeheader() is bugged. Please use iconv_mime_encode() instead', E_USER_WARNING);
138		}
139
140		public static function mb_convert_case($s, $mode, $encoding = null)
141		{
142		if ('' === $s .= '') {
143		return '';
144		}
145
146		$encoding = self::getEncoding($encoding);
147
148		if ('UTF-8' === $encoding) {
149		$encoding = null;
150		if (!preg_match('//u', $s)) {
151		$s = @iconv('UTF-8', 'UTF-8//IGNORE', $s);
152		}
153		} else {
154		$s = iconv($encoding, 'UTF-8//IGNORE', $s);
155		}
156
157		if (MB_CASE_TITLE == $mode) {
158		$s = preg_replace_callback('/\b\p{Ll}/u', array(__CLASS__, 'title_case_upper'), $s);
159		$s = preg_replace_callback('/\B[\p{Lu}\p{Lt}]+/u', array(__CLASS__, 'title_case_lower'), $s);
160		} else {
161		if (MB_CASE_UPPER == $mode) {
162		static $upper = null;
163		if (null === $upper) {
164		$upper = self::getData('upperCase');
165		}
166		$map = $upper;
167		} else {
168		if (self::MB_CASE_FOLD === $mode) {
169		$s = str_replace(self::$caseFold[0], self::$caseFold[1], $s);
170		}
171
172		static $lower = null;
173		if (null === $lower) {
174		$lower = self::getData('lowerCase');
175		}
176		$map = $lower;
177		}
178
179		static $ulenMask = array("\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4);
180
181		$i = 0;
182		$len = strlen($s);
183
184		while ($i < $len) {
185		$ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"];
186		$uchr = substr($s, $i, $ulen);
187		$i += $ulen;
188
189		if (isset($map[$uchr])) {
190		$uchr = $map[$uchr];
191		$nlen = strlen($uchr);
192
193		if ($nlen == $ulen) {
194		$nlen = $i;
195		do {
196		$s[--$nlen] = $uchr[--$ulen];
197		} while ($ulen);
198		} else {
199		$s = substr_replace($s, $uchr, $i - $ulen, $ulen);
200		$len += $nlen - $ulen;
201		$i += $nlen - $ulen;
202		}
203		}
204		}
205		}
206
207		if (null === $encoding) {
208		return $s;
209		}
210
211		return iconv('UTF-8', $encoding.'//IGNORE', $s);
212		}
213
214		public static function mb_internal_encoding($encoding = null)
215		{
216		if (null === $encoding) {
217		return self::$internalEncoding;
218		}
219
220		$encoding = self::getEncoding($encoding);
221
222		if ('UTF-8' === $encoding \|\| false !== @iconv($encoding, $encoding, ' ')) {
223		self::$internalEncoding = $encoding;
224
225		return true;
226		}
227
228		return false;
229		}
230
231		public static function mb_language($lang = null)
232		{
233		if (null === $lang) {
234		return self::$language;
235		}
236
237		switch ($lang = strtolower($lang)) {
238		case 'uni':
239		case 'neutral':
240		self::$language = $lang;
241
242		return true;
243		}
244
245		return false;
246		}
247
248		public static function mb_list_encodings()
249		{
250		return array('UTF-8');
251		}
252
253		public static function mb_encoding_aliases($encoding)
254		{
255		switch (strtoupper($encoding)) {
256		case 'UTF8':
257		case 'UTF-8':
258		return array('utf8');
259		}
260
261		return false;
262		}
263
264		public static function mb_check_encoding($var = null, $encoding = null)
265		{
266		if (null === $encoding) {
267		if (null === $var) {
268		return false;
269		}
270		$encoding = self::$internalEncoding;
271		}
272
273		return self::mb_detect_encoding($var, array($encoding)) \|\| false !== @iconv($encoding, $encoding, $var);
274		}
275
276		public static function mb_detect_encoding($str, $encodingList = null, $strict = false)
277		{
278		if (null === $encodingList) {
279		$encodingList = self::$encodingList;
280		} else {
281		if (!is_array($encodingList)) {
282		$encodingList = array_map('trim', explode(',', $encodingList));
283		}
284		$encodingList = array_map('strtoupper', $encodingList);
285		}
286
287		foreach ($encodingList as $enc) {
288		switch ($enc) {
289		case 'ASCII':
290		if (!preg_match('/[\x80-\xFF]/', $str)) {
291		return $enc;
292		}
293		break;
294
295		case 'UTF8':
296		case 'UTF-8':
297		if (preg_match('//u', $str)) {
298		return 'UTF-8';
299		}
300		break;
301
302		default:
303		if (0 === strncmp($enc, 'ISO-8859-', 9)) {
304		return $enc;
305		}
306		}
307		}
308
309		return false;
310		}
311
312		public static function mb_detect_order($encodingList = null)
313		{
314		if (null === $encodingList) {
315		return self::$encodingList;
316		}
317
318		if (!is_array($encodingList)) {
319		$encodingList = array_map('trim', explode(',', $encodingList));
320		}
321		$encodingList = array_map('strtoupper', $encodingList);
322
323		foreach ($encodingList as $enc) {
324		switch ($enc) {
325		default:
326		if (strncmp($enc, 'ISO-8859-', 9)) {
327		return false;
328		}
329		case 'ASCII':
330		case 'UTF8':
331		case 'UTF-8':
332		}
333		}
334
335		self::$encodingList = $encodingList;
336
337		return true;
338		}
339
340		public static function mb_strlen($s, $encoding = null)
341		{
342		$encoding = self::getEncoding($encoding);
343		if ('CP850' === $encoding \|\| 'ASCII' === $encoding) {
344		return strlen($s);
345		}
346
347		return @iconv_strlen($s, $encoding);
348		}
349
350		public static function mb_strpos($haystack, $needle, $offset = 0, $encoding = null)
351		{
352		$encoding = self::getEncoding($encoding);
353		if ('CP850' === $encoding \|\| 'ASCII' === $encoding) {
354		return strpos($haystack, $needle, $offset);
355		}
356
357		if ('' === $needle .= '') {
358		trigger_error(__METHOD__.': Empty delimiter', E_USER_WARNING);
359
360		return false;
361		}
362
363		return iconv_strpos($haystack, $needle, $offset, $encoding);
364		}
365
366		public static function mb_strrpos($haystack, $needle, $offset = 0, $encoding = null)
367		{
368		$encoding = self::getEncoding($encoding);
369		if ('CP850' === $encoding \|\| 'ASCII' === $encoding) {
370		return strrpos($haystack, $needle, $offset);
371		}
372
373		if ($offset != (int) $offset) {
374		$offset = 0;
375		} elseif ($offset = (int) $offset) {
376		if ($offset < 0) {
377		$haystack = self::mb_substr($haystack, 0, $offset, $encoding);
378		$offset = 0;
379		} else {
380		$haystack = self::mb_substr($haystack, $offset, 2147483647, $encoding);
381		}
382		}
383
384		$pos = iconv_strrpos($haystack, $needle, $encoding);
385
386		return false !== $pos ? $offset + $pos : false;
387		}
388
389		public static function mb_strtolower($s, $encoding = null)
390		{
391		return self::mb_convert_case($s, MB_CASE_LOWER, $encoding);
392		}
393
394		public static function mb_strtoupper($s, $encoding = null)
395		{
396		return self::mb_convert_case($s, MB_CASE_UPPER, $encoding);
397		}
398
399		public static function mb_substitute_character($c = null)
400		{
401		if (0 === strcasecmp($c, 'none')) {
402		return true;
403		}
404
405		return null !== $c ? false : 'none';
406		}
407
408		public static function mb_substr($s, $start, $length = null, $encoding = null)
409		{
410		$encoding = self::getEncoding($encoding);
411		if ('CP850' === $encoding \|\| 'ASCII' === $encoding) {
412		return substr($s, $start, null === $length ? 2147483647 : $length);
413		}
414
415	View Code Duplication	if ($start < 0) {
416		$start = iconv_strlen($s, $encoding) + $start;
417		if ($start < 0) {
418		$start = 0;
419		}
420		}
421
422		if (null === $length) {
423		$length = 2147483647;
424	View Code Duplication	} elseif ($length < 0) {
425		$length = iconv_strlen($s, $encoding) + $length - $start;
426		if ($length < 0) {
427		return '';
428		}
429		}
430
431		return iconv_substr($s, $start, $length, $encoding).'';
432		}
433
434	View Code Duplication	public static function mb_stripos($haystack, $needle, $offset = 0, $encoding = null)
		0 ignored issues – show Duplication introduced 2017-09-27 16:16 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...
435		{
436		$haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding);
437		$needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding);
438
439		return self::mb_strpos($haystack, $needle, $offset, $encoding);
440		}
441
442		public static function mb_stristr($haystack, $needle, $part = false, $encoding = null)
443		{
444		$pos = self::mb_stripos($haystack, $needle, 0, $encoding);
445
446		return self::getSubpart($pos, $part, $haystack, $encoding);
447		}
448
449		public static function mb_strrchr($haystack, $needle, $part = false, $encoding = null)
450		{
451		$encoding = self::getEncoding($encoding);
452		if ('CP850' === $encoding \|\| 'ASCII' === $encoding) {
453		return strrchr($haystack, $needle, $part);
454		}
455		$needle = self::mb_substr($needle, 0, 1, $encoding);
456		$pos = iconv_strrpos($haystack, $needle, $encoding);
457
458		return self::getSubpart($pos, $part, $haystack, $encoding);
459		}
460
461		public static function mb_strrichr($haystack, $needle, $part = false, $encoding = null)
462		{
463		$needle = self::mb_substr($needle, 0, 1, $encoding);
464		$pos = self::mb_strripos($haystack, $needle, $encoding);
465
466		return self::getSubpart($pos, $part, $haystack, $encoding);
467		}
468
469	View Code Duplication	public static function mb_strripos($haystack, $needle, $offset = 0, $encoding = null)
		0 ignored issues – show Duplication introduced 2017-09-27 16:16 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...
470		{
471		$haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding);
472		$needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding);
473
474		return self::mb_strrpos($haystack, $needle, $offset, $encoding);
475		}
476
477		public static function mb_strstr($haystack, $needle, $part = false, $encoding = null)
478		{
479		$pos = strpos($haystack, $needle);
480		if (false === $pos) {
481		return false;
482		}
483		if ($part) {
484		return substr($haystack, 0, $pos);
485		}
486
487		return substr($haystack, $pos);
488		}
489
490		public static function mb_get_info($type = 'all')
491		{
492		$info = array(
493		'internal_encoding' => self::$internalEncoding,
494		'http_output' => 'pass',
495		'http_output_conv_mimetypes' => '^(text/\|application/xhtml\+xml)',
496		'func_overload' => 0,
497		'func_overload_list' => 'no overload',
498		'mail_charset' => 'UTF-8',
499		'mail_header_encoding' => 'BASE64',
500		'mail_body_encoding' => 'BASE64',
501		'illegal_chars' => 0,
502		'encoding_translation' => 'Off',
503		'language' => self::$language,
504		'detect_order' => self::$encodingList,
505		'substitute_character' => 'none',
506		'strict_detection' => 'Off',
507		);
508
509		if ('all' === $type) {
510		return $info;
511		}
512		if (isset($info[$type])) {
513		return $info[$type];
514		}
515
516		return false;
517		}
518
519		public static function mb_http_input($type = '')
520		{
521		return false;
522		}
523
524		public static function mb_http_output($encoding = null)
525		{
526		return null !== $encoding ? 'pass' === $encoding : 'pass';
527		}
528
529		public static function mb_strwidth($s, $encoding = null)
530		{
531		$encoding = self::getEncoding($encoding);
532
533		if ('UTF-8' !== $encoding) {
534		$s = iconv($encoding, 'UTF-8//IGNORE', $s);
535		}
536
537		$s = preg_replace('/[\x{1100}-\x{115F}\x{2329}\x{232A}\x{2E80}-\x{303E}\x{3040}-\x{A4CF}\x{AC00}-\x{D7A3}\x{F900}-\x{FAFF}\x{FE10}-\x{FE19}\x{FE30}-\x{FE6F}\x{FF00}-\x{FF60}\x{FFE0}-\x{FFE6}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}]/u', '', $s, -1, $wide);
538
539		return ($wide << 1) + iconv_strlen($s, 'UTF-8');
540		}
541
542		public static function mb_substr_count($haystack, $needle, $encoding = null)
543		{
544		return substr_count($haystack, $needle);
545		}
546
547		public static function mb_output_handler($contents, $status)
548		{
549		return $contents;
550		}
551
552		public static function mb_chr($code, $encoding = null)
553		{
554		if (0x80 > $code %= 0x200000) {
555		$s = chr($code);
556		} elseif (0x800 > $code) {
557		$s = chr(0xC0 \| $code >> 6).chr(0x80 \| $code & 0x3F);
558		} elseif (0x10000 > $code) {
559		$s = chr(0xE0 \| $code >> 12).chr(0x80 \| $code >> 6 & 0x3F).chr(0x80 \| $code & 0x3F);
560		} else {
561		$s = chr(0xF0 \| $code >> 18).chr(0x80 \| $code >> 12 & 0x3F).chr(0x80 \| $code >> 6 & 0x3F).chr(0x80 \| $code & 0x3F);
562		}
563
564		if ('UTF-8' !== $encoding = self::getEncoding($encoding)) {
565		$s = mb_convert_encoding($s, $encoding, 'UTF-8');
566		}
567
568		return $s;
569		}
570
571		public static function mb_ord($s, $encoding = null)
572		{
573		if ('UTF-8' !== $encoding = self::getEncoding($encoding)) {
574		$s = mb_convert_encoding($s, 'UTF-8', $encoding);
575		}
576
577		$code = ($s = unpack('C*', substr($s, 0, 4))) ? $s[1] : 0;
578		if (0xF0 <= $code) {
579		return (($code - 0xF0) << 18) + (($s[2] - 0x80) << 12) + (($s[3] - 0x80) << 6) + $s[4] - 0x80;
580		}
581		if (0xE0 <= $code) {
582		return (($code - 0xE0) << 12) + (($s[2] - 0x80) << 6) + $s[3] - 0x80;
583		}
584		if (0xC0 <= $code) {
585		return (($code - 0xC0) << 6) + $s[2] - 0x80;
586		}
587
588		return $code;
589		}
590
591		private static function getSubpart($pos, $part, $haystack, $encoding)
592		{
593		if (false === $pos) {
594		return false;
595		}
596		if ($part) {
597		return self::mb_substr($haystack, 0, $pos, $encoding);
598		}
599
600		return self::mb_substr($haystack, $pos, null, $encoding);
601		}
602
603		private static function html_encoding_callback($m)
604		{
605		$i = 1;
606		$entities = '';
607		$m = unpack('C*', htmlentities($m[0], ENT_COMPAT, 'UTF-8'));
608
609		while (isset($m[$i])) {
610		if (0x80 > $m[$i]) {
611		$entities .= chr($m[$i++]);
612		continue;
613		}
614		if (0xF0 <= $m[$i]) {
615		$c = (($m[$i++] - 0xF0) << 18) + (($m[$i++] - 0x80) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80;
616		} elseif (0xE0 <= $m[$i]) {
617		$c = (($m[$i++] - 0xE0) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80;
618		} else {
619		$c = (($m[$i++] - 0xC0) << 6) + $m[$i++] - 0x80;
620		}
621
622		$entities .= '&#'.$c.';';
623		}
624
625		return $entities;
626		}
627
628		private static function title_case_lower($s)
629		{
630		return self::mb_convert_case($s[0], MB_CASE_LOWER, 'UTF-8');
631		}
632
633		private static function title_case_upper($s)
634		{
635		return self::mb_convert_case($s[0], MB_CASE_UPPER, 'UTF-8');
636		}
637
638		private static function getData($file)
639		{
640		if (file_exists($file = __DIR__.'/Resources/unidata/'.$file.'.php')) {
641		return require $file;
642		}
643
644		return false;
645		}
646
647		private static function getEncoding($encoding)
648		{
649		if (null === $encoding) {
650		return self::$internalEncoding;
651		}
652
653		$encoding = strtoupper($encoding);
654
655		if ('8BIT' === $encoding \|\| 'BINARY' === $encoding) {
656		return 'CP850';
657		}
658		if ('UTF8' === $encoding) {
659		return 'UTF-8';
660		}
661
662		return $encoding;
663		}
664		}
665

gctools-outilsgc / gcconnex

Push — composer-installed ( c4bac5 )

Mbstring::mb_get_info() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like