utf_tools.php

这些都是我以前学习是用到的源码

		"\xC4\x9A" => "\xC4\x9B", "\xC4\x9C" => "\xC4\x9D", "\xC4\x9E" => "\xC4\x9F", "\xC4\xA0" => "\xC4\xA1",
		"\xC4\xA2" => "\xC4\xA3", "\xC4\xA4" => "\xC4\xA5", "\xC4\xA6" => "\xC4\xA7", "\xC4\xA8" => "\xC4\xA9",
		"\xC4\xAA" => "\xC4\xAB", "\xC4\xAE" => "\xC4\xAF", "\xC4\xB4" => "\xC4\xB5", "\xC4\xB6" => "\xC4\xB7",
		"\xC4\xB9" => "\xC4\xBA", "\xC4\xBB" => "\xC4\xBC", "\xC4\xBD" => "\xC4\xBE", "\xC5\x81" => "\xC5\x82",
		"\xC5\x83" => "\xC5\x84", "\xC5\x85" => "\xC5\x86", "\xC5\x87" => "\xC5\x88", "\xC5\x8A" => "\xC5\x8B",
		"\xC5\x8C" => "\xC5\x8D", "\xC5\x90" => "\xC5\x91", "\xC5\x94" => "\xC5\x95", "\xC5\x96" => "\xC5\x97",
		"\xC5\x98" => "\xC5\x99", "\xC5\x9A" => "\xC5\x9B", "\xC5\x9C" => "\xC5\x9D", "\xC5\x9E" => "\xC5\x9F",
		"\xC5\xA0" => "\xC5\xA1", "\xC5\xA2" => "\xC5\xA3", "\xC5\xA4" => "\xC5\xA5", "\xC5\xA6" => "\xC5\xA7",
		"\xC5\xA8" => "\xC5\xA9", "\xC5\xAA" => "\xC5\xAB", "\xC5\xAC" => "\xC5\xAD", "\xC5\xAE" => "\xC5\xAF",
		"\xC5\xB0" => "\xC5\xB1", "\xC5\xB2" => "\xC5\xB3", "\xC5\xB4" => "\xC5\xB5", "\xC5\xB6" => "\xC5\xB7",
		"\xC5\xB8" => "\xC3\xBF", "\xC5\xB9" => "\xC5\xBA", "\xC5\xBB" => "\xC5\xBC", "\xC5\xBD" => "\xC5\xBE",
		"\xC6\xA0" => "\xC6\xA1", "\xC6\xAF" => "\xC6\xB0", "\xC8\x98" => "\xC8\x99", "\xC8\x9A" => "\xC8\x9B",
		"\xCE\x86" => "\xCE\xAC", "\xCE\x88" => "\xCE\xAD", "\xCE\x89" => "\xCE\xAE", "\xCE\x8A" => "\xCE\xAF",
		"\xCE\x8C" => "\xCF\x8C", "\xCE\x8E" => "\xCF\x8D", "\xCE\x8F" => "\xCF\x8E", "\xCE\x91" => "\xCE\xB1",
		"\xCE\x92" => "\xCE\xB2", "\xCE\x93" => "\xCE\xB3", "\xCE\x94" => "\xCE\xB4", "\xCE\x95" => "\xCE\xB5",
		"\xCE\x96" => "\xCE\xB6", "\xCE\x97" => "\xCE\xB7", "\xCE\x98" => "\xCE\xB8", "\xCE\x99" => "\xCE\xB9",
		"\xCE\x9A" => "\xCE\xBA", "\xCE\x9B" => "\xCE\xBB", "\xCE\x9C" => "\xCE\xBC", "\xCE\x9D" => "\xCE\xBD",
		"\xCE\x9E" => "\xCE\xBE", "\xCE\x9F" => "\xCE\xBF", "\xCE\xA0" => "\xCF\x80", "\xCE\xA1" => "\xCF\x81",
		"\xCE\xA3" => "\xCF\x83", "\xCE\xA4" => "\xCF\x84", "\xCE\xA5" => "\xCF\x85", "\xCE\xA6" => "\xCF\x86",
		"\xCE\xA7" => "\xCF\x87", "\xCE\xA8" => "\xCF\x88", "\xCE\xA9" => "\xCF\x89", "\xCE\xAA" => "\xCF\x8A",
		"\xCE\xAB" => "\xCF\x8B", "\xD0\x81" => "\xD1\x91", "\xD0\x82" => "\xD1\x92", "\xD0\x83" => "\xD1\x93",
		"\xD0\x84" => "\xD1\x94", "\xD0\x85" => "\xD1\x95", "\xD0\x86" => "\xD1\x96", "\xD0\x87" => "\xD1\x97",
		"\xD0\x88" => "\xD1\x98", "\xD0\x89" => "\xD1\x99", "\xD0\x8A" => "\xD1\x9A", "\xD0\x8B" => "\xD1\x9B",
		"\xD0\x8C" => "\xD1\x9C", "\xD0\x8E" => "\xD1\x9E", "\xD0\x8F" => "\xD1\x9F", "\xD0\x90" => "\xD0\xB0",
		"\xD0\x91" => "\xD0\xB1", "\xD0\x92" => "\xD0\xB2", "\xD0\x93" => "\xD0\xB3", "\xD0\x94" => "\xD0\xB4",
		"\xD0\x95" => "\xD0\xB5", "\xD0\x96" => "\xD0\xB6", "\xD0\x97" => "\xD0\xB7", "\xD0\x98" => "\xD0\xB8",
		"\xD0\x99" => "\xD0\xB9", "\xD0\x9A" => "\xD0\xBA", "\xD0\x9B" => "\xD0\xBB", "\xD0\x9C" => "\xD0\xBC",
		"\xD0\x9D" => "\xD0\xBD", "\xD0\x9E" => "\xD0\xBE", "\xD0\x9F" => "\xD0\xBF", "\xD0\xA0" => "\xD1\x80",
		"\xD0\xA1" => "\xD1\x81", "\xD0\xA2" => "\xD1\x82", "\xD0\xA3" => "\xD1\x83", "\xD0\xA4" => "\xD1\x84",
		"\xD0\xA5" => "\xD1\x85", "\xD0\xA6" => "\xD1\x86", "\xD0\xA7" => "\xD1\x87", "\xD0\xA8" => "\xD1\x88",
		"\xD0\xA9" => "\xD1\x89", "\xD0\xAA" => "\xD1\x8A", "\xD0\xAB" => "\xD1\x8B", "\xD0\xAC" => "\xD1\x8C",
		"\xD0\xAD" => "\xD1\x8D", "\xD0\xAE" => "\xD1\x8E", "\xD0\xAF" => "\xD1\x8F", "\xD2\x90" => "\xD2\x91",
		"\xE1\xB8\x82" => "\xE1\xB8\x83", "\xE1\xB8\x8A" => "\xE1\xB8\x8B", "\xE1\xB8\x9E" => "\xE1\xB8\x9F", "\xE1\xB9\x80" => "\xE1\xB9\x81",
		"\xE1\xB9\x96" => "\xE1\xB9\x97", "\xE1\xB9\xA0" => "\xE1\xB9\xA1", "\xE1\xB9\xAA" => "\xE1\xB9\xAB", "\xE1\xBA\x80" => "\xE1\xBA\x81",
		"\xE1\xBA\x82" => "\xE1\xBA\x83", "\xE1\xBA\x84" => "\xE1\xBA\x85", "\xE1\xBB\xB2" => "\xE1\xBB\xB3"
	);

	$UTF8_LOWER_TO_UPPER = array(
		"\x61" => "\x41", "\x62" => "\x42", "\x63" => "\x43", "\x64" => "\x44",
		"\x65" => "\x45", "\x66" => "\x46", "\x67" => "\x47", "\x68" => "\x48",
		"\x69" => "\x49", "\x6A" => "\x4A", "\x6B" => "\x4B", "\x6C" => "\x4C",
		"\x6D" => "\x4D", "\x6E" => "\x4E", "\x6F" => "\x4F", "\x70" => "\x50",
		"\x71" => "\x51", "\x72" => "\x52", "\x73" => "\x53", "\x74" => "\x54",
		"\x75" => "\x55", "\x76" => "\x56", "\x77" => "\x57", "\x78" => "\x58",
		"\x79" => "\x59", "\x7A" => "\x5A", "\xC3\xA0" => "\xC3\x80", "\xC3\xA1" => "\xC3\x81",
		"\xC3\xA2" => "\xC3\x82", "\xC3\xA3" => "\xC3\x83", "\xC3\xA4" => "\xC3\x84", "\xC3\xA5" => "\xC3\x85",
		"\xC3\xA6" => "\xC3\x86", "\xC3\xA7" => "\xC3\x87", "\xC3\xA8" => "\xC3\x88", "\xC3\xA9" => "\xC3\x89",
		"\xC3\xAA" => "\xC3\x8A", "\xC3\xAB" => "\xC3\x8B", "\xC3\xAC" => "\xC3\x8C", "\xC3\xAD" => "\xC3\x8D",
		"\xC3\xAE" => "\xC3\x8E", "\xC3\xAF" => "\xC3\x8F", "\xC3\xB0" => "\xC3\x90", "\xC3\xB1" => "\xC3\x91",
		"\xC3\xB2" => "\xC3\x92", "\xC3\xB3" => "\xC3\x93", "\xC3\xB4" => "\xC3\x94", "\xC3\xB5" => "\xC3\x95",
		"\xC3\xB6" => "\xC3\x96", "\xC3\xB8" => "\xC3\x98", "\xC3\xB9" => "\xC3\x99", "\xC3\xBA" => "\xC3\x9A",
		"\xC3\xBB" => "\xC3\x9B", "\xC3\xBC" => "\xC3\x9C", "\xC3\xBD" => "\xC3\x9D", "\xC3\xBE" => "\xC3\x9E",
		"\xC3\xBF" => "\xC5\xB8", "\xC4\x81" => "\xC4\x80", "\xC4\x83" => "\xC4\x82", "\xC4\x85" => "\xC4\x84",
		"\xC4\x87" => "\xC4\x86", "\xC4\x89" => "\xC4\x88", "\xC4\x8B" => "\xC4\x8A", "\xC4\x8D" => "\xC4\x8C",
		"\xC4\x8F" => "\xC4\x8E", "\xC4\x91" => "\xC4\x90", "\xC4\x93" => "\xC4\x92", "\xC4\x97" => "\xC4\x96",
		"\xC4\x99" => "\xC4\x98", "\xC4\x9B" => "\xC4\x9A", "\xC4\x9D" => "\xC4\x9C", "\xC4\x9F" => "\xC4\x9E",
		"\xC4\xA1" => "\xC4\xA0", "\xC4\xA3" => "\xC4\xA2", "\xC4\xA5" => "\xC4\xA4", "\xC4\xA7" => "\xC4\xA6",
		"\xC4\xA9" => "\xC4\xA8", "\xC4\xAB" => "\xC4\xAA", "\xC4\xAF" => "\xC4\xAE", "\xC4\xB5" => "\xC4\xB4",
		"\xC4\xB7" => "\xC4\xB6", "\xC4\xBA" => "\xC4\xB9", "\xC4\xBC" => "\xC4\xBB", "\xC4\xBE" => "\xC4\xBD",
		"\xC5\x82" => "\xC5\x81", "\xC5\x84" => "\xC5\x83", "\xC5\x86" => "\xC5\x85", "\xC5\x88" => "\xC5\x87",
		"\xC5\x8B" => "\xC5\x8A", "\xC5\x8D" => "\xC5\x8C", "\xC5\x91" => "\xC5\x90", "\xC5\x95" => "\xC5\x94",
		"\xC5\x97" => "\xC5\x96", "\xC5\x99" => "\xC5\x98", "\xC5\x9B" => "\xC5\x9A", "\xC5\x9D" => "\xC5\x9C",
		"\xC5\x9F" => "\xC5\x9E", "\xC5\xA1" => "\xC5\xA0", "\xC5\xA3" => "\xC5\xA2", "\xC5\xA5" => "\xC5\xA4",
		"\xC5\xA7" => "\xC5\xA6", "\xC5\xA9" => "\xC5\xA8", "\xC5\xAB" => "\xC5\xAA", "\xC5\xAD" => "\xC5\xAC",
		"\xC5\xAF" => "\xC5\xAE", "\xC5\xB1" => "\xC5\xB0", "\xC5\xB3" => "\xC5\xB2", "\xC5\xB5" => "\xC5\xB4",
		"\xC5\xB7" => "\xC5\xB6", "\xC5\xBA" => "\xC5\xB9", "\xC5\xBC" => "\xC5\xBB", "\xC5\xBE" => "\xC5\xBD",
		"\xC6\xA1" => "\xC6\xA0", "\xC6\xB0" => "\xC6\xAF", "\xC8\x99" => "\xC8\x98", "\xC8\x9B" => "\xC8\x9A",
		"\xCE\xAC" => "\xCE\x86", "\xCE\xAD" => "\xCE\x88", "\xCE\xAE" => "\xCE\x89", "\xCE\xAF" => "\xCE\x8A",
		"\xCE\xB1" => "\xCE\x91", "\xCE\xB2" => "\xCE\x92", "\xCE\xB3" => "\xCE\x93", "\xCE\xB4" => "\xCE\x94",
		"\xCE\xB5" => "\xCE\x95", "\xCE\xB6" => "\xCE\x96", "\xCE\xB7" => "\xCE\x97", "\xCE\xB8" => "\xCE\x98",
		"\xCE\xB9" => "\xCE\x99", "\xCE\xBA" => "\xCE\x9A", "\xCE\xBB" => "\xCE\x9B", "\xCE\xBC" => "\xCE\x9C",
		"\xCE\xBD" => "\xCE\x9D", "\xCE\xBE" => "\xCE\x9E", "\xCE\xBF" => "\xCE\x9F", "\xCF\x80" => "\xCE\xA0",
		"\xCF\x81" => "\xCE\xA1", "\xCF\x83" => "\xCE\xA3", "\xCF\x84" => "\xCE\xA4", "\xCF\x85" => "\xCE\xA5",
		"\xCF\x86" => "\xCE\xA6", "\xCF\x87" => "\xCE\xA7", "\xCF\x88" => "\xCE\xA8", "\xCF\x89" => "\xCE\xA9",
		"\xCF\x8A" => "\xCE\xAA", "\xCF\x8B" => "\xCE\xAB", "\xCF\x8C" => "\xCE\x8C", "\xCF\x8D" => "\xCE\x8E",
		"\xCF\x8E" => "\xCE\x8F", "\xD0\xB0" => "\xD0\x90", "\xD0\xB1" => "\xD0\x91", "\xD0\xB2" => "\xD0\x92",
		"\xD0\xB3" => "\xD0\x93", "\xD0\xB4" => "\xD0\x94", "\xD0\xB5" => "\xD0\x95", "\xD0\xB6" => "\xD0\x96",
		"\xD0\xB7" => "\xD0\x97", "\xD0\xB8" => "\xD0\x98", "\xD0\xB9" => "\xD0\x99", "\xD0\xBA" => "\xD0\x9A",
		"\xD0\xBB" => "\xD0\x9B", "\xD0\xBC" => "\xD0\x9C", "\xD0\xBD" => "\xD0\x9D", "\xD0\xBE" => "\xD0\x9E",
		"\xD0\xBF" => "\xD0\x9F", "\xD1\x80" => "\xD0\xA0", "\xD1\x81" => "\xD0\xA1", "\xD1\x82" => "\xD0\xA2",
		"\xD1\x83" => "\xD0\xA3", "\xD1\x84" => "\xD0\xA4", "\xD1\x85" => "\xD0\xA5", "\xD1\x86" => "\xD0\xA6",
		"\xD1\x87" => "\xD0\xA7", "\xD1\x88" => "\xD0\xA8", "\xD1\x89" => "\xD0\xA9", "\xD1\x8A" => "\xD0\xAA",
		"\xD1\x8B" => "\xD0\xAB", "\xD1\x8C" => "\xD0\xAC", "\xD1\x8D" => "\xD0\xAD", "\xD1\x8E" => "\xD0\xAE",
		"\xD1\x8F" => "\xD0\xAF", "\xD1\x91" => "\xD0\x81", "\xD1\x92" => "\xD0\x82", "\xD1\x93" => "\xD0\x83",
		"\xD1\x94" => "\xD0\x84", "\xD1\x95" => "\xD0\x85", "\xD1\x96" => "\xD0\x86", "\xD1\x97" => "\xD0\x87",
		"\xD1\x98" => "\xD0\x88", "\xD1\x99" => "\xD0\x89", "\xD1\x9A" => "\xD0\x8A", "\xD1\x9B" => "\xD0\x8B",
		"\xD1\x9C" => "\xD0\x8C", "\xD1\x9E" => "\xD0\x8E", "\xD1\x9F" => "\xD0\x8F", "\xD2\x91" => "\xD2\x90",
		"\xE1\xB8\x83" => "\xE1\xB8\x82", "\xE1\xB8\x8B" => "\xE1\xB8\x8A", "\xE1\xB8\x9F" => "\xE1\xB8\x9E", "\xE1\xB9\x81" => "\xE1\xB9\x80",
		"\xE1\xB9\x97" => "\xE1\xB9\x96", "\xE1\xB9\xA1" => "\xE1\xB9\xA0", "\xE1\xB9\xAB" => "\xE1\xB9\xAA", "\xE1\xBA\x81" => "\xE1\xBA\x80",
		"\xE1\xBA\x83" => "\xE1\xBA\x82", "\xE1\xBA\x85" => "\xE1\xBA\x84", "\xE1\xBB\xB3" => "\xE1\xBB\xB2"
	);

	/**
	* UTF-8 aware alternative to strtolower
	* Make a string lowercase
	* Note: The concept of a characters "case" only exists is some alphabets
	* such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does
	* not exist in the Chinese alphabet, for example. See Unicode Standard
	* Annex #21: Case Mappings
	* 
	* @param string
	* @return string string in lowercase
	*/
	function utf8_strtolower($string)
	{
		global $UTF8_UPPER_TO_LOWER;

		return strtr($string, $UTF8_UPPER_TO_LOWER);
	}

	/**
	* UTF-8 aware alternative to strtoupper
	* Make a string uppercase
	* Note: The concept of a characters "case" only exists is some alphabets
	* such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does
	* not exist in the Chinese alphabet, for example. See Unicode Standard
	* Annex #21: Case Mappings
	* 
	* @param string
	* @return string string in uppercase
	*/
	function utf8_strtoupper($string)
	{
		global $UTF8_LOWER_TO_UPPER;

		return strtr($string, $UTF8_LOWER_TO_UPPER);
	}

	/**
	* UTF-8 aware alternative to substr
	* Return part of a string given character offset (and optionally length)
	*
	* Note arguments: comparied to substr - if offset or length are
	* not integers, this version will not complain but rather massages them
	* into an integer.
	*
	* Note on returned values: substr documentation states false can be
	* returned in some cases (e.g. offset > string length)
	* mb_substr never returns false, it will return an empty string instead.
	* This adopts the mb_substr approach
	*
	* Note on implementation: PCRE only supports repetitions of less than
	* 65536, in order to accept up to MAXINT values for offset and length,
	* we'll repeat a group of 65535 characters when needed.
	*
	* Note on implementation: calculating the number of characters in the
	* string is a relatively expensive operation, so we only carry it out when
	* necessary. It isn't necessary for +ve offsets and no specified length
	*
	* @author Chris Smith<[e-mail]>
	* @param string $str
	* @param integer $offset number of UTF-8 characters offset (from left)
	* @param integer $length (optional) length in UTF-8 characters from offset
	* @return mixed string or FALSE if failure
	*/
	function utf8_substr($str, $offset, $length = NULL)
	{
		// generates E_NOTICE
		// for PHP4 objects, but not PHP5 objects
		$str = (string) $str;
		$offset = (int) $offset;
		if (!is_null($length))
		{
			$length = (int) $length;
		}

		// handle trivial cases
		if ($length === 0 || ($offset < 0 && $length < 0 && $length < $offset))
		{
			return '';
		}

		// normalise negative offsets (we could use a tail
		// anchored pattern, but they are horribly slow!)
		if ($offset < 0)
		{
			// see notes
			$strlen = utf8_strlen($str);
			$offset = $strlen + $offset;
			if ($offset < 0)
			{
				$offset = 0;
			}
		}

		$op = '';
		$lp = '';

		// establish a pattern for offset, a
		// non-captured group equal in length to offset
		if ($offset > 0)
		{
			$ox = (int) ($offset / 65535);
			$oy = $offset % 65535;

			if ($ox)
			{
				$op = '(?:.{65535}){' . $ox . '}';
			}

			$op = '^(?:' . $op . '.{' . $oy . '})';
		}
		else
		{	
			// offset == 0; just anchor the pattern
			$op = '^';
		}

		// establish a pattern for length
		if (is_null($length))
		{
			// the rest of the string
			$lp = '(.*)$';
		}
		else
		{
			if (!isset($strlen))
			{
				// see notes
				$strlen = utf8_strlen($str);
			}

			// another trivial case
			if ($offset > $strlen)
			{
				return '';
			}

			if ($length > 0)
			{
				// reduce any length that would
				// go passed the end of the string
				$length = min($strlen - $offset, $length);

				$lx = (int) ($length / 65535);
				$ly = $length % 65535;
				
				// negative length requires a captured group
				// of length characters
				if ($lx)
				{
					$lp = '(?:.{65535}){' . $lx . '}';
				}
				$lp = '(' . $lp . '.{'. $ly . '})';
			}
			else if ($length < 0)
			{
				if ($length < ($offset - $strlen))
				{
					return '';
				}

				$lx = (int)((-$length) / 65535);
				$ly = (-$length) % 65535;

				// negative length requires ... capture everything
				// except a group of  -length characters
				// anchored at the tail-end of the string
				if ($lx)
				{
					$lp = '(?:.{65535}){' . $lx . '}';
				}
				$lp = '(.*)(?:' . $lp . '.{' . $ly . '})$';
			}
		}

		if (!preg_match('#' . $op . $lp . '#us', $str, $match))
		{
			return '';
		}

		return $match[1];
	}

	/**
	* Return the length (in characters) of a UTF-8 string
	*
	* @param	string	$text		UTF-8 string
	* @return	integer				Length (in chars) of given string
	*/
	function utf8_strlen($text)
	{
		// Since utf8_decode is replacing multibyte characters to ? strlen works fine
		return strlen(utf8_decode($text));
	}
}

/**
* UTF-8 aware alternative to str_split
* Convert a string to an array
* 
* @author Harry Fuecks
* @param string $str UTF-8 encoded
* @param int $split_len number to characters to split string by
* @return string characters in string reverses
*/
function utf8_str_split($str, $split_len = 1)
{
	if (!preg_match('/^[0-9]+$/', $split_len) || $split_len < 1)
	{
		return false;
	}

	$len = utf8_strlen($str);
	if ($len <= $split_len)
	{
		return array($str);
	}
	
	preg_match_all('/.{' . $split_len . '}|[^\x00]{1,' . $split_len . '}$/us', $str, $ar);
	return $ar[0];
}

/**
* UTF-8 aware alternative to strcspn
* Find length of initial segment not matching mask
* 
* @author Harry Fuecks
*/
function utf8_strspn($str, $mask, $start = null, $length = null)
{
	$mask = preg_replace('!([\\\\\\-\\]\\[/^])!', '\\\${1}', $mask);

	if ($start !== null || $length !== null)
	{
		$str = utf8_substr($str, $start, $length);
	}

	preg_match('/^[' . $mask . ']+/u', $str, $matches);

	if (isset($matches[0]))
	{
		return utf8_strlen($matches[0]);
	}

	return 0;
}

/**
* UTF-8 aware alternative to ucfirst