StrObj::calcUtf8CharLength() - Code Metrics - Inspection of "added a bunch of UTF8 stuff but it's not working y..." - garrettw/stringobject - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 66f9bc...5c75e4 )

by Garrett

created 2015-11-22 05:59 UTC

StrObj::calcUtf8CharLength() A

↳ Parent: StrObj

Complexity

Conditions	4
Paths	4

Size

Total Lines	7
Code Lines	5

Duplication

Lines	0
Ratio	0 %

Importance

Changes	1
Bugs	0	Features	1

Metric	Value
c	1
b	0
f	1
dl	0
loc	7
rs	9.2
cc	4
eloc	5
nc	4
nop	1

<?php

namespace StringObject;

class StrObj implements \ArrayAccess, \Countable, \Iterator
{
    // CONSTANTS

    const NORMAL = 0;
    const START = 0;
    const END = 1;
    const BOTH_ENDS = 2;
    const CASE_INSENSITIVE = 4;
    const REVERSE = 8;
    const EXACT_POSITION = 16;
    const CURRENT_LOCALE = 32;
    const NATURAL_ORDER = 64;
    const FIRST_N = 128;
    const C_STYLE = 256;
    const META = 512;
    const LAZY = 1024;
    const GREEDY = 2048;
    const WINDOWS1252 = 4096;
    const UTF8 = 8192;

    // STATIC PROPERTIES

    protected static $asciimap = [
        'a' => ['à', 'á', 'ả', 'ã', 'ạ', 'ă', 'ắ', 'ằ', 'ẳ', 'ẵ', 'ặ', 'â', 'ấ',
                'ầ', 'ẩ', 'ẫ', 'ậ', 'ā', 'ą', 'å', 'α', 'ά', 'ἀ', 'ἁ', 'ἂ', 'ἃ',
                'ἄ', 'ἅ', 'ἆ', 'ἇ', 'ᾀ', 'ᾁ', 'ᾂ', 'ᾃ', 'ᾄ', 'ᾅ', 'ᾆ', 'ᾇ', 'ὰ',
                'ά', 'ᾰ', 'ᾱ', 'ᾲ', 'ᾳ', 'ᾴ', 'ᾶ', 'ᾷ', 'а', 'أ'],
        'b' => ['б', 'β', 'Ъ', 'Ь', 'ب'],
        'c' => ['ç', 'ć', 'č', 'ĉ', 'ċ'],
        'd' => ['ď', 'ð', 'đ', 'ƌ', 'ȡ', 'ɖ', 'ɗ', 'ᵭ', 'ᶁ', 'ᶑ', 'д', 'δ', 'د', 'ض'],
        'e' => ['é', 'è', 'ẻ', 'ẽ', 'ẹ', 'ê', 'ế', 'ề', 'ể', 'ễ', 'ệ', 'ë', 'ē',
                'ę', 'ě', 'ĕ', 'ė', 'ε', 'έ', 'ἐ', 'ἑ', 'ἒ', 'ἓ', 'ἔ', 'ἕ', 'ὲ',
                'έ', 'е', 'ё', 'э', 'є', 'ə'],
        'f' => ['ф', 'φ', 'ف'],
        'g' => ['ĝ', 'ğ', 'ġ', 'ģ', 'г', 'ґ', 'γ', 'ج'],
        'h' => ['ĥ', 'ħ', 'η', 'ή', 'ح', 'ه'],
        'i' => ['í', 'ì', 'ỉ', 'ĩ', 'ị', 'î', 'ï', 'ī', 'ĭ', 'į', 'ı', 'ι', 'ί',
                'ϊ', 'ΐ', 'ἰ', 'ἱ', 'ἲ', 'ἳ', 'ἴ', 'ἵ', 'ἶ', 'ἷ', 'ὶ', 'ί', 'ῐ',
                'ῑ', 'ῒ', 'ΐ', 'ῖ', 'ῗ', 'і', 'ї', 'и'],
        'j' => ['ĵ', 'ј', 'Ј'],
        'k' => ['ķ', 'ĸ', 'к', 'κ', 'Ķ', 'ق', 'ك'],
        'l' => ['ł', 'ľ', 'ĺ', 'ļ', 'ŀ', 'л', 'λ', 'ل'],
        'm' => ['м', 'μ', 'م'],
        'n' => ['ñ', 'ń', 'ň', 'ņ', 'ŉ', 'ŋ', 'ν', 'н', 'ن'],
        'o' => ['ó', 'ò', 'ỏ', 'õ', 'ọ', 'ô', 'ố', 'ồ', 'ổ', 'ỗ', 'ộ', 'ơ', 'ớ',
                'ờ', 'ở', 'ỡ', 'ợ', 'ø', 'ō', 'ő', 'ŏ', 'ο', 'ὀ', 'ὁ', 'ὂ', 'ὃ',
                'ὄ', 'ὅ', 'ὸ', 'ό', 'о', 'و', 'θ'],
        'p' => ['п', 'π'],
        'r' => ['ŕ', 'ř', 'ŗ', 'р', 'ρ', 'ر'],
        's' => ['ś', 'š', 'ş', 'с', 'σ', 'ș', 'ς', 'س', 'ص'],
        't' => ['ť', 'ţ', 'т', 'τ', 'ț', 'ت', 'ط'],
        'u' => ['ú', 'ù', 'ủ', 'ũ', 'ụ', 'ư', 'ứ', 'ừ', 'ử', 'ữ', 'ự', 'û', 'ū',
                'ů', 'ű', 'ŭ', 'ų', 'µ', 'у'],
        'v' => ['в'],
        'w' => ['ŵ', 'ω', 'ώ'],
        'x' => ['χ'],
        'y' => ['ý', 'ỳ', 'ỷ', 'ỹ', 'ỵ', 'ÿ', 'ŷ', 'й', 'ы', 'υ', 'ϋ', 'ύ', 'ΰ', 'ي'],
        'z' => ['ź', 'ž', 'ż', 'з', 'ζ', 'ز'],
        'aa' => ['ع'],
        'ae' => ['ä', 'æ'],
        'ch' => ['ч'],
        'dj' => ['ђ', 'đ'],
        'dz' => ['џ'],
        'gh' => ['غ'],
        'kh' => ['х', 'خ'],
        'lj' => ['љ'],
        'nj' => ['њ'],
        'oe' => ['ö', 'œ'],
        'ps' => ['ψ'],
        'sh' => ['ш'],
        'shch' => ['щ'],
        'ss' => ['ß'],
        'th' => ['þ', 'ث', 'ذ', 'ظ'],
        'ts' => ['ц'],
        'ue' => ['ü'],
        'ya' => ['я'],
        'yu' => ['ю'],
        'zh' => ['ж'],
        '(c]' => ['©'],
        'A' => ['Á', 'À', 'Ả', 'Ã', 'Ạ', 'Ă', 'Ắ', 'Ằ', 'Ẳ', 'Ẵ', 'Ặ', 'Â', 'Ấ',
                'Ầ', 'Ẩ', 'Ẫ', 'Ậ', 'Å', 'Ā', 'Ą', 'Α', 'Ά', 'Ἀ', 'Ἁ', 'Ἂ', 'Ἃ',
                'Ἄ', 'Ἅ', 'Ἆ', 'Ἇ', 'ᾈ', 'ᾉ', 'ᾊ', 'ᾋ', 'ᾌ', 'ᾍ', 'ᾎ', 'ᾏ', 'Ᾰ',
                'Ᾱ', 'Ὰ', 'Ά', 'ᾼ', 'А'],
        'B' => ['Б', 'Β'],
        'C' => ['Ç', 'Ć', 'Č', 'Ĉ', 'Ċ'],
        'D' => ['Ď', 'Ð', 'Đ', 'Ɖ', 'Ɗ', 'Ƌ', 'ᴅ', 'ᴆ', 'Д', 'Δ'],
        'E' => ['É', 'È', 'Ẻ', 'Ẽ', 'Ẹ', 'Ê', 'Ế', 'Ề', 'Ể', 'Ễ', 'Ệ', 'Ë', 'Ē',
                'Ę', 'Ě', 'Ĕ', 'Ė', 'Ε', 'Έ', 'Ἐ', 'Ἑ', 'Ἒ', 'Ἓ', 'Ἔ', 'Ἕ', 'Έ',
                'Ὲ', 'Е', 'Ё', 'Э', 'Є', 'Ə'],
        'F' => ['Ф', 'Φ'],
        'G' => ['Ğ', 'Ġ', 'Ģ', 'Г', 'Ґ', 'Γ'],
        'H' => ['Η', 'Ή'],
        'I' => ['Í', 'Ì', 'Ỉ', 'Ĩ', 'Ị', 'Î', 'Ï', 'Ī', 'Ĭ', 'Į', 'İ', 'Ι', 'Ί',
                'Ϊ', 'Ἰ', 'Ἱ', 'Ἳ', 'Ἴ', 'Ἵ', 'Ἶ', 'Ἷ', 'Ῐ', 'Ῑ', 'Ὶ', 'Ί', 'И',
                'І', 'Ї'],
        'K' => ['К', 'Κ'],
        'L' => ['Ĺ', 'Ł', 'Л', 'Λ', 'Ļ'],
        'M' => ['М', 'Μ'],
        'N' => ['Ń', 'Ñ', 'Ň', 'Ņ', 'Ŋ', 'Н', 'Ν'],
        'O' => ['Ó', 'Ò', 'Ỏ', 'Õ', 'Ọ', 'Ô', 'Ố', 'Ồ', 'Ổ', 'Ỗ', 'Ộ', 'Ơ', 'Ớ',
                'Ờ', 'Ở', 'Ỡ', 'Ợ', 'Ø', 'Ō', 'Ő', 'Ŏ', 'Ο', 'Ό', 'Ὀ', 'Ὁ', 'Ὂ',
                'Ὃ', 'Ὄ', 'Ὅ', 'Ὸ', 'Ό', 'О', 'Θ', 'Ө'],
        'P' => ['П', 'Π'],
        'R' => ['Ř', 'Ŕ', 'Р', 'Ρ'],
        'S' => ['Ş', 'Ŝ', 'Ș', 'Š', 'Ś', 'С', 'Σ'],
        'T' => ['Ť', 'Ţ', 'Ŧ', 'Ț', 'Т', 'Τ'],
        'U' => ['Ú', 'Ù', 'Ủ', 'Ũ', 'Ụ', 'Ư', 'Ứ', 'Ừ', 'Ử', 'Ữ', 'Ự', 'Û', 'Ū',
                'Ů', 'Ű', 'Ŭ', 'Ų', 'У'],
        'V' => ['В'],
        'W' => ['Ω', 'Ώ'],
        'X' => ['Χ'],
        'Y' => ['Ý', 'Ỳ', 'Ỷ', 'Ỹ', 'Ỵ', 'Ÿ', 'Ῠ', 'Ῡ', 'Ὺ', 'Ύ', 'Ы', 'Й', 'Υ', 'Ϋ'],
        'Z' => ['Ź', 'Ž', 'Ż', 'З', 'Ζ'],
        'AE' => ['Ä', 'Æ'],
        'CH' => ['Ч'],
        'DJ' => ['Ђ'],
        'DZ' => ['Џ'],
        'KH' => ['Х'],
        'LJ' => ['Љ'],
        'NJ' => ['Њ'],
        'OE' => ['Ö'],
        'PS' => ['Ψ'],
        'SH' => ['Ш'],
        'SHCH' => ['Щ'],
        'SS' => ['ẞ'],
        'TH' => ['Þ'],
        'TS' => ['Ц'],
        'UE' => ['Ü'],
        'YA' => ['Я'],
        'YU' => ['Ю'],
        'ZH' => ['Ж'],
        ' ' => ["\xC2\xA0", "\xE2\x80\x80", "\xE2\x80\x81", "\xE2\x80\x82",
                "\xE2\x80\x83", "\xE2\x80\x84", "\xE2\x80\x85", "\xE2\x80\x86",
                "\xE2\x80\x87", "\xE2\x80\x88", "\xE2\x80\x89", "\xE2\x80\x8A",
                "\xE2\x80\xAF", "\xE2\x81\x9F", "\xE3\x80\x80"],
    ];
    protected static $winc1umap = [
        128 => 0x20AC,
        130 => 0x201A,
        131 => 0x0192,
        132 => 0x201E,
        133 => 0x2026,
        134 => 0x2020,
        135 => 0x2021,
        136 => 0x02C6,
        137 => 0x2030,
        138 => 0x0160,
        139 => 0x2039,
        140 => 0x0152,
        142 => 0x017D,
        145 => 0x2018,
        146 => 0x2019,
        147 => 0x201C,
        148 => 0x201D,
        149 => 0x2022,
        150 => 0x2013,
        151 => 0x2014,
        152 => 0x02DC,
        153 => 0x2122,
        154 => 0x0161,
        155 => 0x203A,
        156 => 0x0153,
        158 => 0x017E,
        159 => 0x0178,
    ];

    // PROPERTIES

    protected $raw;
    protected $encoding;
    protected $token = false;
    protected $caret = 0;

    // MAGIC METHODS

    public function __construct($thing, $enc = self::WINDOWS1252)
    {
        self::testStringableObject($thing);

        if (\is_array($thing)) {
            throw new \InvalidArgumentException('Unsure of how to convert array to string');
        }

        $this->raw = (string) $thing;
        $this->encoding = $enc;
    }

    /**
     * @return mixed
     */
    public function __get($name)
    {
        return $this->$name;
    }

    /**
     * @return string
     */
    public function __toString()
    {
        return $this->raw;
    }

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

    // INFORMATIONAL METHODS

    public function charAt($offset)
    {
        return new self($this->raw{$offset});
    }

    public function charCodeAt($offset)
    {
        if ($this->encoding === self::WINDOWS1252) {
            return \ord($this->raw{$offset});
        }

        return $this->parseUtf8CharAt($offset);
    }

    public function compareTo($str, $mode = self::NORMAL, $length = 1)
    {
        $modemap = [
            self::NORMAL => 'strcmp',
            self::CASE_INSENSITIVE => 'strcasecmp',
            self::CURRENT_LOCALE => 'strcoll',
            self::NATURAL_ORDER => 'strnatcmp',
            (self::NATURAL_ORDER | self::CASE_INSENSITIVE) => 'strnatcasecmp',
            self::FIRST_N => 'strncmp',
            (self::FIRST_N | self::CASE_INSENSITIVE) => 'strncasecmp',
        ];

        if ($mode & self::FIRST_N) {
            return \call_user_func($modemap[$mode], $this->raw, $str, $length);
        }
        return \call_user_func($modemap[$mode], $this->raw, $str);
    }

    public function indexOf($needle, $offset = 0, $mode = self::NORMAL)
    {
        // strip out bits we don't understand
        $mode &= (self::REVERSE | self::CASE_INSENSITIVE);

        $modemap = [
            self::NORMAL => 'strpos',
            self::CASE_INSENSITIVE => 'stripos',
            self::REVERSE => 'strrpos',
            (self::REVERSE | self::CASE_INSENSITIVE) => 'strripos',
        ];
        return \call_user_func($modemap[$mode], $this->raw, $needle, $offset);
    }

    public function length()
    {
        return \strlen($this->raw);
    }

    // MODIFYING METHODS

    public function append($str)
    {
        return new self($this->raw . $str);
    }

    public function asciify($removeUnsupported = true)
    {
        $str = $this->raw;
        foreach (self::$asciimap as $key => $value) {
            $str = \str_replace($value, $key, $str);
        }
        if ($removeUnsupported) {
            $str = \preg_replace('/[^\x20-\x7E]/u', '', $str);
        }
        return new self($str);
    }

    public function chunk($length = 76, $ending = "\r\n")
    {
        return new self(\chunk_split($this->raw, $length, $ending));
    }

    public function concat($str)
    {
        return $this->append($str);
    }

    public function escape($mode = self::NORMAL, $charlist = '')
    {
        $modemap = [
            self::NORMAL => 'addslashes',
            self::C_STYLE => 'addcslashes',
            self::META => 'quotemeta',
        ];
        if ($mode === self::C_STYLE) {
            return new self(\call_user_func($modemap[$mode], $this->raw, $charlist));
        }
        return new self(\call_user_func($modemap[$mode], $this->raw));
    }

    public function insertAt($str, $offset)
    {
        return $this->replaceSubstr($str, $offset, 0);
    }

    public function nextToken($delim)
    {
        if ($this->token) {
            return new self(\strtok($delim));
        }
        $this->token = true;
        return new self(\strtok($this->raw, $delim));
    }

    public function pad($newlength, $padding = ' ', $mode = self::END)
    {
        return new self(\str_pad($this->raw, $newlength, $padding, $mode));
    }

    public function prepend($str)
    {
        return new self($str . $this->raw);
    }

    public function remove($str, $mode = self::NORMAL)
    {
        return $this->replace($str, '', $mode);
    }

    public function removeSubstr($start, $length = null)
    {
        return $this->replaceSubstr('', $start, $length);
    }

    public function repeat($times)
    {
        return new self(\str_repeat($this->raw, $times));
    }

    public function replace($search, $replace, $mode = self::NORMAL)
    {
        if ($mode & self::CASE_INSENSITIVE) {
            return new self(\str_ireplace($search, $replace, $this->raw));
        }
        return new self(\str_replace($search, $replace, $this->raw));
    }

    public function replaceSubstr($replacement, $start, $length = null)
    {
        if ($length === null) {
            $length = $this->length();
        }
        return new self(\substr_replace($this->raw, $replacement, $start, $length));
    }

    public function resetToken()
    {
        $this->token = false;
    }

    public function reverse()
    {
        return new self(\strrev($this->raw));
    }

    public function shuffle()
    {
        return new self(\str_shuffle($this->raw));
    }

    public function substr($start, $length = 'omitted')
    {
        if ($length === 'omitted') {
            return new self(\substr($this->raw, $start));
        }
        return new self(\substr($this->raw, $start, $length));
    }

    public function times($times)
    {
        return $this->repeat($times);
    }

    public function translate($search, $replace = '')
    {
        if (is_array($search)) {
            return new self(\strtr($this->raw, $search));
        }
        return new self(\strtr($this->raw, $search, $replace));
    }

    public function trim($mask = " \t\n\r\0\x0B", $mode = self::BOTH_ENDS)
    {
        $modemap = [
            self::START => 'ltrim',
            self::END => 'rtrim',
            self::BOTH_ENDS => 'trim',
        ];
        return new self(\call_user_func($modemap[$mode], $this->raw, $mask));
    }

    public function unescape($mode = self::NORMAL)
    {
        $modemap = [
            self::NORMAL => 'stripslashes',
            self::C_STYLE => 'stripcslashes',
            self::META => 'stripslashes',
        ];
        return new self(\call_user_func($modemap[$mode], $this->raw));
    }

    public function uuDecode()
    {
        return new self(\convert_uudecode($this->raw));
    }

    public function uuEncode()
    {
        return new self(\convert_uuencode($this->raw));
    }

    public function wordwrap($width = 75, $break = "\n")
    {
        return new self(\wordwrap($this->raw, $width, $break, false));
    }

    public function wordwrapBreaking($width = 75, $break = "\n")
    {
        return new self(\wordwrap($this->raw, $width, $break, true));
    }

    // TESTING METHODS

    public function contains($needle, $offset = 0, $mode = self::NORMAL)
    {
        if ($mode & self::EXACT_POSITION) {
            return ($this->indexOf($needle, $offset, $mode) === $offset);
        }
        return ($this->indexOf($needle, $offset, $mode) !== false);
    }

    public function countSubstr($needle, $offset = 0, $length = null)
    {
        if ($length === null) {
            return \substr_count($this->raw, $needle, $offset);
        }
        return \substr_count($this->raw, $needle, $offset, $length);
    }

    public function endsWith($str, $mode = self::NORMAL)
    {
        $mode &= self::CASE_INSENSITIVE;
        $offset = $this->length() - \strlen($str);
        return $this->contains($str, $offset, $mode | self::EXACT_POSITION | self::REVERSE);
    }

    public function equals($str)
    {
        self::testStringableObject($str);

        $str = (string) $str;
        return ($str == $this->raw);
    }

    public function isAscii()
    {
        $len = $this->length();

        for ($i = 0; $i < $len; $i++) {
            if ($this->charCodeAt($i) >= 128) {
                return false;
            }
        }
        return true;
    }

    public function isEmpty()
    {
        return empty($this->raw);
    }

    public function startsWith($str, $mode = self::NORMAL)
    {
        $mode &= self::CASE_INSENSITIVE;
        return $this->contains($str, 0, $mode | self::EXACT_POSITION);
    }

    // INTERFACE IMPLEMENTATION METHODS

    public function count()
    {
        return \strlen($this->raw);
    }

    public function current()
    {
        return $this->raw[$this->caret];
    }

    public function key()
    {
        return $this->caret;
    }

    public function next()
    {
        $this->caret++;
    }

    public function rewind()
    {
        $this->caret = 0;
    }

    public function valid()
    {
        return ($this->caret < \strlen($this->raw));
    }

    public function offsetExists($offset)
    {
        $offset = (int) $offset;
        return ($offset >= 0 && $offset < \strlen($this->raw));
    }

    public function offsetGet($offset)
    {
        return $this->raw{$offset};
    }

    public function offsetSet($offset, $value)
    {
        throw new \LogicException('Cannot assign '.$value.' to immutable StrObj instance at index '.$offset);
    }

    public function offsetUnset($offset)
    {
        throw new \LogicException('Cannot unset index '.$offset.' on immutable StrObj instance');
    }

    // PRIVATE STATIC FUNCTIONS

    protected static function testStringableObject($thing)
    {
        if (\is_object($thing) && !\method_exists($thing, '__toString')) {
            throw new \InvalidArgumentException(
                'Parameter is an object that does not implement __toString() method'
            );
        }
    }

    protected function parseUtf8CharAt($offset)
    {
        list($start, $length, $valid, $current) = $this->findUtf8CharAt($offset);

        if ($length === 1) {
            if ($current > 0b01111111 && $current < 0b10100000) {
                return [$start, $length, self::$winc1umap[$current]];
            }
            return [$start, $length, $current];
        }

        $byte = \ord($this->raw{$start});

        if ($valid === false) {
            if ($length === 2 && $byte & 0b11000000) {
                // overlong ascii
                return [$start + 1, 1, ($offset === $start) ? \ord($this->raw{$start + 1}) : $byte];
            }
            return [$offset, 1, $current];
        }

        if ($valid === true) {

            if ($length === 2) {
                $bigcode = $byte & 0b00011111;
            }

            elseif ($length === 3) {
                $bigcode = $byte & 0b00001111;
            }

            elseif ($length === 4) {
                $bigcode = $byte & 0b00000111;
            }

            for ($next = 1; $next < $length; $next++) {
                $bigcode <<= 6;
function myFunction($a) {
    switch ($a) {
        case 'foo':
            $x = 1;
            break;

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

    // $x is potentially undefined here.
    echo $x;
}
                $bigcode += \ord($this->raw{$start + $next}) & 0b00111111;
            }

            if ($bigcode > 0x10FFFF) {
                return [$offset, 1, $current];
            }
            return [$start, $length, $bigcode];
        }
    }

    /**
     * Determines if the byte at the given offset is part of a valid UTF8 char,
     * and returns its actual starting offset, length in bytes, validity,
     * and the byte at the original offset.
     */
    protected function findUtf8CharAt($offset)
    {
        $byte = \ord($this->raw{$offset});

        if ($byte <= 0b01111111) {
            // ASCII passthru, 1 byte long
            return [$offset, 1, true, $byte];
        }

        if ($byte <= 0b10111111) {
            // either part of a UTF8 char, or an invalid UTF8 codepoint.
            // try to find start of UTF8 char
            $original = $offset;
            while ($offset > 0 && $original - $offset < 4) {
                $prev = \ord($this->raw{--$offset});

                if ($prev <= 0b01111111) {
                    // prev is plain ASCII so current char can't be valid
                    return [$original, 1, false, $byte];
                }

                if ($prev <= 0b10111111) {
                    // prev is also part of a UTF8 char, so keep looking
                    continue;
                }

                if ($prev == 0xC0 || $prev == 0xC1) {
                    // prev is an invalid UTF8 starter for overlong ASCII
                    return [$offset, 2, false, $byte];
                }

                if ($prev <= 0b11110100) {
                    // prev is valid start byte, validate length to check this char
                    if ($original < $offset + self::calcUtf8CharLength($prev)) {
                        return [$offset, $length, true, $byte];
function someFunction() {
    $x = 5;
    echo $x;
}
                    }
                }
                return [$original, 1, false, $byte];
            }
            return [$original, 1, false, $byte];
        }

        if ($byte <= 0b11110100) {
            // valid UTF8 start byte, find the rest, determine if length is valid
            $actual = $length = self::calcUtf8CharLength($byte);

            for ($i = 1; $i < $length; $i++) {
                if ($offset + $i >= $this->length()) {
                    $actual = $i - 1;
                    break;
                }
                $last = \ord($this->raw{$offset + $i});
                if ($last < 0b10000000 || $last > 0b10111111) {
                    $actual = $i;
                    break;
                }
            }

            if ($actual !== $length) {
                return [$offset, $actual, false, $byte];
            }
            return [$offset, $length, true, $byte];
        }

        // if 245 to 255, Windows-1252 passthru
        return [$offset, 1, false, $byte];
    }

    protected static function calcUtf8CharLength($byte)
    {
        if (~$byte & 0b00001000) return 4;
        if (~$byte & 0b00010000) return 3;
        if (~$byte & 0b00100000) return 2;
        return 1;
    }
}


1			<?php
2
3			namespace StringObject;
4
5			class StrObj implements \ArrayAccess, \Countable, \Iterator
6			{
7			// CONSTANTS
8
9			const NORMAL = 0;
10			const START = 0;
11			const END = 1;
12			const BOTH_ENDS = 2;
13			const CASE_INSENSITIVE = 4;
14			const REVERSE = 8;
15			const EXACT_POSITION = 16;
16			const CURRENT_LOCALE = 32;
17			const NATURAL_ORDER = 64;
18			const FIRST_N = 128;
19			const C_STYLE = 256;
20			const META = 512;
21			const LAZY = 1024;
22			const GREEDY = 2048;
23			const WINDOWS1252 = 4096;
24			const UTF8 = 8192;
25
26			// STATIC PROPERTIES
27
28			protected static $asciimap = [
29			'a' => ['à', 'á', 'ả', 'ã', 'ạ', 'ă', 'ắ', 'ằ', 'ẳ', 'ẵ', 'ặ', 'â', 'ấ',
30			'ầ', 'ẩ', 'ẫ', 'ậ', 'ā', 'ą', 'å', 'α', 'ά', 'ἀ', 'ἁ', 'ἂ', 'ἃ',
31			'ἄ', 'ἅ', 'ἆ', 'ἇ', 'ᾀ', 'ᾁ', 'ᾂ', 'ᾃ', 'ᾄ', 'ᾅ', 'ᾆ', 'ᾇ', 'ὰ',
32			'ά', 'ᾰ', 'ᾱ', 'ᾲ', 'ᾳ', 'ᾴ', 'ᾶ', 'ᾷ', 'а', 'أ'],
33			'b' => ['б', 'β', 'Ъ', 'Ь', 'ب'],
34			'c' => ['ç', 'ć', 'č', 'ĉ', 'ċ'],
35			'd' => ['ď', 'ð', 'đ', 'ƌ', 'ȡ', 'ɖ', 'ɗ', 'ᵭ', 'ᶁ', 'ᶑ', 'д', 'δ', 'د', 'ض'],
36			'e' => ['é', 'è', 'ẻ', 'ẽ', 'ẹ', 'ê', 'ế', 'ề', 'ể', 'ễ', 'ệ', 'ë', 'ē',
37			'ę', 'ě', 'ĕ', 'ė', 'ε', 'έ', 'ἐ', 'ἑ', 'ἒ', 'ἓ', 'ἔ', 'ἕ', 'ὲ',
38			'έ', 'е', 'ё', 'э', 'є', 'ə'],
39			'f' => ['ф', 'φ', 'ف'],
40			'g' => ['ĝ', 'ğ', 'ġ', 'ģ', 'г', 'ґ', 'γ', 'ج'],
41			'h' => ['ĥ', 'ħ', 'η', 'ή', 'ح', 'ه'],
42			'i' => ['í', 'ì', 'ỉ', 'ĩ', 'ị', 'î', 'ï', 'ī', 'ĭ', 'į', 'ı', 'ι', 'ί',
43			'ϊ', 'ΐ', 'ἰ', 'ἱ', 'ἲ', 'ἳ', 'ἴ', 'ἵ', 'ἶ', 'ἷ', 'ὶ', 'ί', 'ῐ',
44			'ῑ', 'ῒ', 'ΐ', 'ῖ', 'ῗ', 'і', 'ї', 'и'],
45			'j' => ['ĵ', 'ј', 'Ј'],
46			'k' => ['ķ', 'ĸ', 'к', 'κ', 'Ķ', 'ق', 'ك'],
47			'l' => ['ł', 'ľ', 'ĺ', 'ļ', 'ŀ', 'л', 'λ', 'ل'],
48			'm' => ['м', 'μ', 'م'],
49			'n' => ['ñ', 'ń', 'ň', 'ņ', 'ŉ', 'ŋ', 'ν', 'н', 'ن'],
50			'o' => ['ó', 'ò', 'ỏ', 'õ', 'ọ', 'ô', 'ố', 'ồ', 'ổ', 'ỗ', 'ộ', 'ơ', 'ớ',
51			'ờ', 'ở', 'ỡ', 'ợ', 'ø', 'ō', 'ő', 'ŏ', 'ο', 'ὀ', 'ὁ', 'ὂ', 'ὃ',
52			'ὄ', 'ὅ', 'ὸ', 'ό', 'о', 'و', 'θ'],
53			'p' => ['п', 'π'],
54			'r' => ['ŕ', 'ř', 'ŗ', 'р', 'ρ', 'ر'],
55			's' => ['ś', 'š', 'ş', 'с', 'σ', 'ș', 'ς', 'س', 'ص'],
56			't' => ['ť', 'ţ', 'т', 'τ', 'ț', 'ت', 'ط'],
57			'u' => ['ú', 'ù', 'ủ', 'ũ', 'ụ', 'ư', 'ứ', 'ừ', 'ử', 'ữ', 'ự', 'û', 'ū',
58			'ů', 'ű', 'ŭ', 'ų', 'µ', 'у'],
59			'v' => ['в'],
60			'w' => ['ŵ', 'ω', 'ώ'],
61			'x' => ['χ'],
62			'y' => ['ý', 'ỳ', 'ỷ', 'ỹ', 'ỵ', 'ÿ', 'ŷ', 'й', 'ы', 'υ', 'ϋ', 'ύ', 'ΰ', 'ي'],
63			'z' => ['ź', 'ž', 'ż', 'з', 'ζ', 'ز'],
64			'aa' => ['ع'],
65			'ae' => ['ä', 'æ'],
66			'ch' => ['ч'],
67			'dj' => ['ђ', 'đ'],
68			'dz' => ['џ'],
69			'gh' => ['غ'],
70			'kh' => ['х', 'خ'],
71			'lj' => ['љ'],
72			'nj' => ['њ'],
73			'oe' => ['ö', 'œ'],
74			'ps' => ['ψ'],
75			'sh' => ['ш'],
76			'shch' => ['щ'],
77			'ss' => ['ß'],
78			'th' => ['þ', 'ث', 'ذ', 'ظ'],
79			'ts' => ['ц'],
80			'ue' => ['ü'],
81			'ya' => ['я'],
82			'yu' => ['ю'],
83			'zh' => ['ж'],
84			'(c]' => ['©'],
85			'A' => ['Á', 'À', 'Ả', 'Ã', 'Ạ', 'Ă', 'Ắ', 'Ằ', 'Ẳ', 'Ẵ', 'Ặ', 'Â', 'Ấ',
86			'Ầ', 'Ẩ', 'Ẫ', 'Ậ', 'Å', 'Ā', 'Ą', 'Α', 'Ά', 'Ἀ', 'Ἁ', 'Ἂ', 'Ἃ',
87			'Ἄ', 'Ἅ', 'Ἆ', 'Ἇ', 'ᾈ', 'ᾉ', 'ᾊ', 'ᾋ', 'ᾌ', 'ᾍ', 'ᾎ', 'ᾏ', 'Ᾰ',
88			'Ᾱ', 'Ὰ', 'Ά', 'ᾼ', 'А'],
89			'B' => ['Б', 'Β'],
90			'C' => ['Ç', 'Ć', 'Č', 'Ĉ', 'Ċ'],
91			'D' => ['Ď', 'Ð', 'Đ', 'Ɖ', 'Ɗ', 'Ƌ', 'ᴅ', 'ᴆ', 'Д', 'Δ'],
92			'E' => ['É', 'È', 'Ẻ', 'Ẽ', 'Ẹ', 'Ê', 'Ế', 'Ề', 'Ể', 'Ễ', 'Ệ', 'Ë', 'Ē',
93			'Ę', 'Ě', 'Ĕ', 'Ė', 'Ε', 'Έ', 'Ἐ', 'Ἑ', 'Ἒ', 'Ἓ', 'Ἔ', 'Ἕ', 'Έ',
94			'Ὲ', 'Е', 'Ё', 'Э', 'Є', 'Ə'],
95			'F' => ['Ф', 'Φ'],
96			'G' => ['Ğ', 'Ġ', 'Ģ', 'Г', 'Ґ', 'Γ'],
97			'H' => ['Η', 'Ή'],
98			'I' => ['Í', 'Ì', 'Ỉ', 'Ĩ', 'Ị', 'Î', 'Ï', 'Ī', 'Ĭ', 'Į', 'İ', 'Ι', 'Ί',
99			'Ϊ', 'Ἰ', 'Ἱ', 'Ἳ', 'Ἴ', 'Ἵ', 'Ἶ', 'Ἷ', 'Ῐ', 'Ῑ', 'Ὶ', 'Ί', 'И',
100			'І', 'Ї'],
101			'K' => ['К', 'Κ'],
102			'L' => ['Ĺ', 'Ł', 'Л', 'Λ', 'Ļ'],
103			'M' => ['М', 'Μ'],
104			'N' => ['Ń', 'Ñ', 'Ň', 'Ņ', 'Ŋ', 'Н', 'Ν'],
105			'O' => ['Ó', 'Ò', 'Ỏ', 'Õ', 'Ọ', 'Ô', 'Ố', 'Ồ', 'Ổ', 'Ỗ', 'Ộ', 'Ơ', 'Ớ',
106			'Ờ', 'Ở', 'Ỡ', 'Ợ', 'Ø', 'Ō', 'Ő', 'Ŏ', 'Ο', 'Ό', 'Ὀ', 'Ὁ', 'Ὂ',
107			'Ὃ', 'Ὄ', 'Ὅ', 'Ὸ', 'Ό', 'О', 'Θ', 'Ө'],
108			'P' => ['П', 'Π'],
109			'R' => ['Ř', 'Ŕ', 'Р', 'Ρ'],
110			'S' => ['Ş', 'Ŝ', 'Ș', 'Š', 'Ś', 'С', 'Σ'],
111			'T' => ['Ť', 'Ţ', 'Ŧ', 'Ț', 'Т', 'Τ'],
112			'U' => ['Ú', 'Ù', 'Ủ', 'Ũ', 'Ụ', 'Ư', 'Ứ', 'Ừ', 'Ử', 'Ữ', 'Ự', 'Û', 'Ū',
113			'Ů', 'Ű', 'Ŭ', 'Ų', 'У'],
114			'V' => ['В'],
115			'W' => ['Ω', 'Ώ'],
116			'X' => ['Χ'],
117			'Y' => ['Ý', 'Ỳ', 'Ỷ', 'Ỹ', 'Ỵ', 'Ÿ', 'Ῠ', 'Ῡ', 'Ὺ', 'Ύ', 'Ы', 'Й', 'Υ', 'Ϋ'],
118			'Z' => ['Ź', 'Ž', 'Ż', 'З', 'Ζ'],
119			'AE' => ['Ä', 'Æ'],
120			'CH' => ['Ч'],
121			'DJ' => ['Ђ'],
122			'DZ' => ['Џ'],
123			'KH' => ['Х'],
124			'LJ' => ['Љ'],
125			'NJ' => ['Њ'],
126			'OE' => ['Ö'],
127			'PS' => ['Ψ'],
128			'SH' => ['Ш'],
129			'SHCH' => ['Щ'],
130			'SS' => ['ẞ'],
131			'TH' => ['Þ'],
132			'TS' => ['Ц'],
133			'UE' => ['Ü'],
134			'YA' => ['Я'],
135			'YU' => ['Ю'],
136			'ZH' => ['Ж'],
137			' ' => ["\xC2\xA0", "\xE2\x80\x80", "\xE2\x80\x81", "\xE2\x80\x82",
138			"\xE2\x80\x83", "\xE2\x80\x84", "\xE2\x80\x85", "\xE2\x80\x86",
139			"\xE2\x80\x87", "\xE2\x80\x88", "\xE2\x80\x89", "\xE2\x80\x8A",
140			"\xE2\x80\xAF", "\xE2\x81\x9F", "\xE3\x80\x80"],
141			];
142			protected static $winc1umap = [
143			128 => 0x20AC,
144			130 => 0x201A,
145			131 => 0x0192,
146			132 => 0x201E,
147			133 => 0x2026,
148			134 => 0x2020,
149			135 => 0x2021,
150			136 => 0x02C6,
151			137 => 0x2030,
152			138 => 0x0160,
153			139 => 0x2039,
154			140 => 0x0152,
155			142 => 0x017D,
156			145 => 0x2018,
157			146 => 0x2019,
158			147 => 0x201C,
159			148 => 0x201D,
160			149 => 0x2022,
161			150 => 0x2013,
162			151 => 0x2014,
163			152 => 0x02DC,
164			153 => 0x2122,
165			154 => 0x0161,
166			155 => 0x203A,
167			156 => 0x0153,
168			158 => 0x017E,
169			159 => 0x0178,
170			];
171
172			// PROPERTIES
173
174			protected $raw;
175			protected $encoding;
176			protected $token = false;
177			protected $caret = 0;
178
179			// MAGIC METHODS
180
181			public function __construct($thing, $enc = self::WINDOWS1252)
182			{
183			self::testStringableObject($thing);
184
185			if (\is_array($thing)) {
186			throw new \InvalidArgumentException('Unsure of how to convert array to string');
187			}
188
189			$this->raw = (string) $thing;
190			$this->encoding = $enc;
191			}
192
193			/**
194			* @return mixed
195			*/
196			public function __get($name)
197			{
198			return $this->$name;
199			}
200
201			/**
202			* @return string
203			*/
204			public function __toString()
205			{
206			return $this->raw;
207			}
208
209			public function toArray($delim = '', $limit = null)
210			{
211			if (empty($delim)) {
212			return \str_split($this->raw);
213			}
214			if (is_int($delim)) {
215			return \str_split($this->raw, $delim);
216			}
217			if ($limit === null) {
218			return \explode($delim, $this->raw);
219			}
220			return \explode($delim, $this->raw, $limit);
221			}
222
223			// INFORMATIONAL METHODS
224
225			public function charAt($offset)
226			{
227			return new self($this->raw{$offset});
228			}
229
230			public function charCodeAt($offset)
231			{
232			if ($this->encoding === self::WINDOWS1252) {
233			return \ord($this->raw{$offset});
234			}
235
236			return $this->parseUtf8CharAt($offset);
237			}
238
239			public function compareTo($str, $mode = self::NORMAL, $length = 1)
240			{
241			$modemap = [
242			self::NORMAL => 'strcmp',
243			self::CASE_INSENSITIVE => 'strcasecmp',
244			self::CURRENT_LOCALE => 'strcoll',
245			self::NATURAL_ORDER => 'strnatcmp',
246			(self::NATURAL_ORDER \| self::CASE_INSENSITIVE) => 'strnatcasecmp',
247			self::FIRST_N => 'strncmp',
248			(self::FIRST_N \| self::CASE_INSENSITIVE) => 'strncasecmp',
249			];
250
251			if ($mode & self::FIRST_N) {
252			return \call_user_func($modemap[$mode], $this->raw, $str, $length);
253			}
254			return \call_user_func($modemap[$mode], $this->raw, $str);
255			}
256
257			public function indexOf($needle, $offset = 0, $mode = self::NORMAL)
258			{
259			// strip out bits we don't understand
260			$mode &= (self::REVERSE \| self::CASE_INSENSITIVE);
261
262			$modemap = [
263			self::NORMAL => 'strpos',
264			self::CASE_INSENSITIVE => 'stripos',
265			self::REVERSE => 'strrpos',
266			(self::REVERSE \| self::CASE_INSENSITIVE) => 'strripos',
267			];
268			return \call_user_func($modemap[$mode], $this->raw, $needle, $offset);
269			}
270
271			public function length()
272			{
273			return \strlen($this->raw);
274			}
275
276			// MODIFYING METHODS
277
278			public function append($str)
279			{
280			return new self($this->raw . $str);
281			}
282
283			public function asciify($removeUnsupported = true)
284			{
285			$str = $this->raw;
286			foreach (self::$asciimap as $key => $value) {
287			$str = \str_replace($value, $key, $str);
288			}
289			if ($removeUnsupported) {
290			$str = \preg_replace('/[^\x20-\x7E]/u', '', $str);
291			}
292			return new self($str);
293			}
294
295			public function chunk($length = 76, $ending = "\r\n")
296			{
297			return new self(\chunk_split($this->raw, $length, $ending));
298			}
299
300			public function concat($str)
301			{
302			return $this->append($str);
303			}
304
305			public function escape($mode = self::NORMAL, $charlist = '')
306			{
307			$modemap = [
308			self::NORMAL => 'addslashes',
309			self::C_STYLE => 'addcslashes',
310			self::META => 'quotemeta',
311			];
312			if ($mode === self::C_STYLE) {
313			return new self(\call_user_func($modemap[$mode], $this->raw, $charlist));
314			}
315			return new self(\call_user_func($modemap[$mode], $this->raw));
316			}
317
318			public function insertAt($str, $offset)
319			{
320			return $this->replaceSubstr($str, $offset, 0);
321			}
322
323			public function nextToken($delim)
324			{
325			if ($this->token) {
326			return new self(\strtok($delim));
327			}
328			$this->token = true;
329			return new self(\strtok($this->raw, $delim));
330			}
331
332			public function pad($newlength, $padding = ' ', $mode = self::END)
333			{
334			return new self(\str_pad($this->raw, $newlength, $padding, $mode));
335			}
336
337			public function prepend($str)
338			{
339			return new self($str . $this->raw);
340			}
341
342			public function remove($str, $mode = self::NORMAL)
343			{
344			return $this->replace($str, '', $mode);
345			}
346
347			public function removeSubstr($start, $length = null)
348			{
349			return $this->replaceSubstr('', $start, $length);
350			}
351
352			public function repeat($times)
353			{
354			return new self(\str_repeat($this->raw, $times));
355			}
356
357			public function replace($search, $replace, $mode = self::NORMAL)
358			{
359			if ($mode & self::CASE_INSENSITIVE) {
360			return new self(\str_ireplace($search, $replace, $this->raw));
361			}
362			return new self(\str_replace($search, $replace, $this->raw));
363			}
364
365			public function replaceSubstr($replacement, $start, $length = null)
366			{
367			if ($length === null) {
368			$length = $this->length();
369			}
370			return new self(\substr_replace($this->raw, $replacement, $start, $length));
371			}
372
373			public function resetToken()
374			{
375			$this->token = false;
376			}
377
378			public function reverse()
379			{
380			return new self(\strrev($this->raw));
381			}
382
383			public function shuffle()
384			{
385			return new self(\str_shuffle($this->raw));
386			}
387
388			public function substr($start, $length = 'omitted')
389			{
390			if ($length === 'omitted') {
391			return new self(\substr($this->raw, $start));
392			}
393			return new self(\substr($this->raw, $start, $length));
394			}
395
396			public function times($times)
397			{
398			return $this->repeat($times);
399			}
400
401			public function translate($search, $replace = '')
402			{
403			if (is_array($search)) {
404			return new self(\strtr($this->raw, $search));
405			}
406			return new self(\strtr($this->raw, $search, $replace));
407			}
408
409			public function trim($mask = " \t\n\r\0\x0B", $mode = self::BOTH_ENDS)
410			{
411			$modemap = [
412			self::START => 'ltrim',
413			self::END => 'rtrim',
414			self::BOTH_ENDS => 'trim',
415			];
416			return new self(\call_user_func($modemap[$mode], $this->raw, $mask));
417			}
418
419			public function unescape($mode = self::NORMAL)
420			{
421			$modemap = [
422			self::NORMAL => 'stripslashes',
423			self::C_STYLE => 'stripcslashes',
424			self::META => 'stripslashes',
425			];
426			return new self(\call_user_func($modemap[$mode], $this->raw));
427			}
428
429			public function uuDecode()
430			{
431			return new self(\convert_uudecode($this->raw));
432			}
433
434			public function uuEncode()
435			{
436			return new self(\convert_uuencode($this->raw));
437			}
438
439			public function wordwrap($width = 75, $break = "\n")
440			{
441			return new self(\wordwrap($this->raw, $width, $break, false));
442			}
443
444			public function wordwrapBreaking($width = 75, $break = "\n")
445			{
446			return new self(\wordwrap($this->raw, $width, $break, true));
447			}
448
449			// TESTING METHODS
450
451			public function contains($needle, $offset = 0, $mode = self::NORMAL)
452			{
453			if ($mode & self::EXACT_POSITION) {
454			return ($this->indexOf($needle, $offset, $mode) === $offset);
455			}
456			return ($this->indexOf($needle, $offset, $mode) !== false);
457			}
458
459			public function countSubstr($needle, $offset = 0, $length = null)
460			{
461			if ($length === null) {
462			return \substr_count($this->raw, $needle, $offset);
463			}
464			return \substr_count($this->raw, $needle, $offset, $length);
465			}
466
467			public function endsWith($str, $mode = self::NORMAL)
468			{
469			$mode &= self::CASE_INSENSITIVE;
470			$offset = $this->length() - \strlen($str);
471			return $this->contains($str, $offset, $mode \| self::EXACT_POSITION \| self::REVERSE);
472			}
473
474			public function equals($str)
475			{
476			self::testStringableObject($str);
477
478			$str = (string) $str;
479			return ($str == $this->raw);
480			}
481
482			public function isAscii()
483			{
484			$len = $this->length();
485
486			for ($i = 0; $i < $len; $i++) {
487			if ($this->charCodeAt($i) >= 128) {
488			return false;
489			}
490			}
491			return true;
492			}
493
494			public function isEmpty()
495			{
496			return empty($this->raw);
497			}
498
499			public function startsWith($str, $mode = self::NORMAL)
500			{
501			$mode &= self::CASE_INSENSITIVE;
502			return $this->contains($str, 0, $mode \| self::EXACT_POSITION);
503			}
504
505			// INTERFACE IMPLEMENTATION METHODS
506
507			public function count()
508			{
509			return \strlen($this->raw);
510			}
511
512			public function current()
513			{
514			return $this->raw[$this->caret];
515			}
516
517			public function key()
518			{
519			return $this->caret;
520			}
521
522			public function next()
523			{
524			$this->caret++;
525			}
526
527			public function rewind()
528			{
529			$this->caret = 0;
530			}
531
532			public function valid()
533			{
534			return ($this->caret < \strlen($this->raw));
535			}
536
537			public function offsetExists($offset)
538			{
539			$offset = (int) $offset;
540			return ($offset >= 0 && $offset < \strlen($this->raw));
541			}
542
543			public function offsetGet($offset)
544			{
545			return $this->raw{$offset};
546			}
547
548			public function offsetSet($offset, $value)
549			{
550			throw new \LogicException('Cannot assign '.$value.' to immutable StrObj instance at index '.$offset);
551			}
552
553			public function offsetUnset($offset)
554			{
555			throw new \LogicException('Cannot unset index '.$offset.' on immutable StrObj instance');
556			}
557
558			// PRIVATE STATIC FUNCTIONS
559
560			protected static function testStringableObject($thing)
561			{
562			if (\is_object($thing) && !\method_exists($thing, '__toString')) {
563			throw new \InvalidArgumentException(
564			'Parameter is an object that does not implement __toString() method'
565			);
566			}
567			}
568
569			protected function parseUtf8CharAt($offset)
570			{
571			list($start, $length, $valid, $current) = $this->findUtf8CharAt($offset);
572
573			if ($length === 1) {
574			if ($current > 0b01111111 && $current < 0b10100000) {
575			return [$start, $length, self::$winc1umap[$current]];
576			}
577			return [$start, $length, $current];
578			}
579
580			$byte = \ord($this->raw{$start});
581
582			if ($valid === false) {
583			if ($length === 2 && $byte & 0b11000000) {
584			// overlong ascii
585			return [$start + 1, 1, ($offset === $start) ? \ord($this->raw{$start + 1}) : $byte];
586			}
587			return [$offset, 1, $current];
588			}
589
590			if ($valid === true) {
591
592			if ($length === 2) {
593			$bigcode = $byte & 0b00011111;
594			}
595
596			elseif ($length === 3) {
597			$bigcode = $byte & 0b00001111;
598			}
599
600			elseif ($length === 4) {
601			$bigcode = $byte & 0b00000111;
602			}
603
604			for ($next = 1; $next < $length; $next++) {
605			$bigcode <<= 6;
			0 ignored issues – show Bug introduced 2015-11-22 06:01 UTC by Report Bug Copy Issue Report The variable `$bigcode` 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...
606			$bigcode += \ord($this->raw{$start + $next}) & 0b00111111;
607			}
608
609			if ($bigcode > 0x10FFFF) {
610			return [$offset, 1, $current];
611			}
612			return [$start, $length, $bigcode];
613			}
614			}
615
616			/**
617			* Determines if the byte at the given offset is part of a valid UTF8 char,
618			* and returns its actual starting offset, length in bytes, validity,
619			* and the byte at the original offset.
620			*/
621			protected function findUtf8CharAt($offset)
622			{
623			$byte = \ord($this->raw{$offset});
624
625			if ($byte <= 0b01111111) {
626			// ASCII passthru, 1 byte long
627			return [$offset, 1, true, $byte];
628			}
629
630			if ($byte <= 0b10111111) {
631			// either part of a UTF8 char, or an invalid UTF8 codepoint.
632			// try to find start of UTF8 char
633			$original = $offset;
634			while ($offset > 0 && $original - $offset < 4) {
635			$prev = \ord($this->raw{--$offset});
636
637			if ($prev <= 0b01111111) {
638			// prev is plain ASCII so current char can't be valid
639			return [$original, 1, false, $byte];
640			}
641
642			if ($prev <= 0b10111111) {
643			// prev is also part of a UTF8 char, so keep looking
644			continue;
645			}
646
647			if ($prev == 0xC0 \|\| $prev == 0xC1) {
648			// prev is an invalid UTF8 starter for overlong ASCII
649			return [$offset, 2, false, $byte];
650			}
651
652			if ($prev <= 0b11110100) {
653			// prev is valid start byte, validate length to check this char
654			if ($original < $offset + self::calcUtf8CharLength($prev)) {
655			return [$offset, $length, true, $byte];
			0 ignored issues – show Bug introduced 2015-11-22 06:01 UTC by Report Bug Copy Issue Report The variable `$length` seems only to be defined at a later point. Did you maybe move this code here without moving the variable definition? This error can happen if you refactor code and forget to move the variable initialization. Let’s take a look at a simple example: function someFunction() { $x = 5; echo $x; } The above code is perfectly fine. Now imagine that we re-order the statements: function someFunction() { echo $x; $x = 5; } In that case, `$x` would be read before it is initialized. This was a very basic example, however the principle is the same for the found issue. Loading history...
656			}
657			}
658			return [$original, 1, false, $byte];
659			}
660			return [$original, 1, false, $byte];
661			}
662
663			if ($byte <= 0b11110100) {
664			// valid UTF8 start byte, find the rest, determine if length is valid
665			$actual = $length = self::calcUtf8CharLength($byte);
666
667			for ($i = 1; $i < $length; $i++) {
668			if ($offset + $i >= $this->length()) {
669			$actual = $i - 1;
670			break;
671			}
672			$last = \ord($this->raw{$offset + $i});
673			if ($last < 0b10000000 \|\| $last > 0b10111111) {
674			$actual = $i;
675			break;
676			}
677			}
678
679			if ($actual !== $length) {
680			return [$offset, $actual, false, $byte];
681			}
682			return [$offset, $length, true, $byte];
683			}
684
685			// if 245 to 255, Windows-1252 passthru
686			return [$offset, 1, false, $byte];
687			}
688
689			protected static function calcUtf8CharLength($byte)
690			{
691			if (~$byte & 0b00001000) return 4;
692			if (~$byte & 0b00010000) return 3;
693			if (~$byte & 0b00100000) return 2;
694			return 1;
695			}
696			}
697

garrettw / stringobject

Push — master ( 66f9bc...5c75e4 )

StrObj::calcUtf8CharLength() A

Complexity

Size

Duplication

Importance

Available Fixes

Duplication Side-by-Side

Filter issues like