iconv_strlen - PHP code example

The php Function Iconv_Strlen

PHP has a wide array of built-in functions that simplify string-related operations for developers. One of these functions is iconv_strlen, which takes a string and its encoding into consideration when counting its characters. This makes it an alternative to strlen, which does not take into account multibyte character sequences and can sometimes result in incorrect byte counts.

Unlike the ASCII character set, where each byte represents a single character, other languages such as Chinese and Japanese require more than 256 different values per byte. As a result, these strings need to be encoded into multiple bytes, and when determining their character count, iconv_strlen takes this into account. The resulting value may differ from the byte string’s length, which is why some programs need to make a separate, more accurate byte count.

The php function iconv_strlen() can be used to get an accurate character count for any string based on its encoding. It takes two parameters, the string and its encoding, as well as an optional offset. If the encoding is omitted, the string will be assumed to be encoded in the internal iconv charset.

If the encoding is not set, iconv_strlen will return an Integer representing the string’s length in characters. If the encoding is set to UTF-8, it will also take into account htmlspecialchars and htmlentities, which allow for the direct representation of multibyte characters in a string. It is important to note that this function is not compatible with all systems, and if it fails to convert the string to the requested encoding, it will return false.

iconv_strlen example

        } else {
            // seperate negative format pattern when available             $format  = self::_seperateFormat($format, $value, $options['precision']);
            if (strpos($format, '.')) {
                if (is_numeric($options['precision'])) {
                    $value = Zend_Locale_Math::round($value, $options['precision']);
                } else {
                    if (substr($format, iconv_strpos($format, '.') + 1, 3) == '###') {
                        $options['precision'] = null;
                    } else {
                        $options['precision'] = iconv_strlen(iconv_substr($format, iconv_strpos($format, '.') + 1,
                                                             iconv_strrpos($format, '0') - iconv_strpos($format, '.')));
                        $format = iconv_substr($format, 0, iconv_strpos($format, '.') + 1) . '###'
                                . iconv_substr($format, iconv_strrpos($format, '0') + 1);
                    }
                }
            } else {
                $value = Zend_Locale_Math::round($value, 0);
                $options['precision'] = 0;
            }
            $value = Zend_Locale_Math::normalize($value);
        }

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

        switch ($token[0]) {
            case 'y' :
                if ((strlen($token) == 4) && (abs($this->getUnixTimestamp()) <= 0x7FFFFFFF)) {
                    return 'Y';
                }

                $length = iconv_strlen($token, 'UTF-8');
                return $this->_toComment(str_pad($this->date('Y', $this->getUnixTimestamp(), false), $length, '0', STR_PAD_LEFT));
                break;

            case 'Y' :
                if ((strlen($token) == 4) && (abs($this->getUnixTimestamp()) <= 0x7FFFFFFF)) {
                    return 'o';
                }

                $length = iconv_strlen($token, 'UTF-8');
                return $this->_toComment(str_pad($this->date('o', $this->getUnixTimestamp(), false), $length, '0', STR_PAD_LEFT));
                break;

'line-break-chars' => $this->CRLF,
                ]);

                // There are reports that iconv_mime_encode() might fail and return FALSE                 if ($output !== false) {
                    // iconv_mime_encode() will always put a header field name.                     // We've passed it an empty one, but it still prepends our                     // encoded string with ': ', so we need to strip it.                     return static::substr($output, 2);
                }

                $chars = iconv_strlen($str, 'UTF-8');
            } elseif (extension_loaded('mbstring')) {
                $chars = mb_strlen($str, 'UTF-8');
            }
        }

        // We might already have this set for UTF-8         if (! isset($chars)) {
            $chars = static::strlen($str);
        }

        $output = '=?' . $this->charset . '?Q?';

    public function isValid($value)
    {
        if (!is_string($value)) {
            $this->_error(self::INVALID);
            return false;
        }

        $this->_setValue($value);
        if ($this->_encoding !== null) {
            $length = iconv_strlen($value, $this->_encoding);
        } else {
            $length = iconv_strlen($value);
        }

        if ($length < $this->_min) {
            $this->_error(self::TOO_SHORT);
        }

        if (null !== $this->_max && $this->_max < $length) {
            $this->_error(self::TOO_LONG);
        }

// Check each domain part                         $checked = false;
                        foreach($regexChars as $regexKey => $regexChar) {
                            $status = @preg_match($regexChar, $domainPart);
                            if ($status > 0) {
                                $length = 63;
                                if (array_key_exists(strtoupper($this->_tld), $this->_idnLength)
                                    && (array_key_exists($regexKey, $this->_idnLength[strtoupper($this->_tld)]))) {
                                    $length = $this->_idnLength[strtoupper($this->_tld)];
                                }

                                if (iconv_strlen($domainPart, 'UTF-8') > $length) {
                                    $this->_error(self::INVALID_HOSTNAME);
                                } else {
                                    $checked = true;
                                    break;
                                }
                            }
                        }

                        if ($checked) {
                            ++$check;
                        }
                    }

            if (false === $needle = self::iconv($encoding, 'utf-8', $needle)) {
                return false;
            }
        }

        if ($offset = (int) $offset) {
            $haystack = self::iconv_substr($haystack, $offset, 2147483647, 'utf-8');
        }
        $pos = strpos($haystack, $needle);

        return false === $pos ? false : ($offset + ($pos ? self::iconv_strlen(substr($haystack, 0, $pos), 'utf-8') : 0));
    }

    public static function iconv_strrpos($haystack, $needle, $encoding = null)
    {
        if (null === $encoding) {
            $encoding = self::$internalEncoding;
        }

        if (0 !== stripos($encoding, 'utf-8')) {
            if (false === $haystack = self::iconv($encoding, 'utf-8', $haystack)) {
                return false;
            }

    public static function countChars($string)
    {
        // Get the length for the string we need.         if (function_exists('mb_strlen')) {
            return mb_strlen($string, 'utf-8');
        }

        if (function_exists('iconv_strlen')) {
            return iconv_strlen($string, 'utf-8');
        }

        $count = count_chars($string);

        // 0x80 = 0x7F - 0 + 1 (one added to get inclusive range)         // 0x33 = 0xF4 - 0x2C + 1 (one added to get inclusive range)         return array_sum(array_slice($count, 0, 0x80)) + array_sum(array_slice($count, 0xC2, 0x33));
    }

    /** * Convert data from the given encoding to UTF-8. * * This has not yet been tested with charactersets other than UTF-8. * It should work with ISO-8859-1/-13 and standard Latin Win charsets. * * @param string $data The data to convert * @param string $encoding A valid encoding. Examples: http://www.php.net/manual/en/mbstring.supported-encodings.php * * @return string */

        $i = 1;
        $ret = '';

        do {
            if (\GRAPHEME_EXTR_COUNT === $type) {
                --$size;
            } elseif (\GRAPHEME_EXTR_MAXBYTES === $type) {
                $size -= \strlen($s[$i]);
            } else {
                $size -= iconv_strlen($s[$i], 'UTF-8//IGNORE');
            }

            if ($size >= 0) {
                $ret .= $s[$i];
            }
        } while (isset($s[++$i]) && $size > 0);

        $next += \strlen($ret);

        return $ret;
    }

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);
        }

        $needle = (string) $needle;
        if ('' === $needle) {