<?php
/* 文字列関連クラス ver 1.5 2009/06/13 poor-script.com */
class str{
	## list_encodings
	private static $list_order = Array("ASCII","UTF-8","SJIS","SJIS-win","EUC-JP","eucJP-win","JIS","ISO-2022-JP");
	## default encoding
	private static $default_encoding = "UTF-8";
	## detect encoding
	// @param string $str
	// @return string (detected encoding or 'auto')
	public static function detect_encoding($str){
		if(self::jis($str) === true){
			return "JIS";
		}
		$encode = mb_detect_encoding($str, self::$list_order, true);
		return (empty($encode) === false) ? $encode : "auto";
	}
	## valid encoding string
	// @param string $str
	// @param string $encoding
	// @param bool   [$strict]
	public static function encoding_valid($str, $encoding, $strict = false){
		$str = self::delete_control($str);
		switch($encoding){
			case "ASCII":
				return self::ascii_valid($str);
			case "UTF-8":
				return self::utf8_valid($str, $strict);
			case "SJIS":
				//Not yet strict supported
				return self::sjis_valid($str);
			case "SJIS-win":
				//Not yet strict supported
				return self::sjis_valid($str);
			case "JIS":
				//Not yet supported
				return false;
			case "ISO-2022-JP":
				//Not yet supported
				return false;
			case "EUC-JP":
				//Not yet supported
				return false;
			case "eucJP-win":
				//Not yet supported
				return false;
			default:
				return false;
		}
	}
	## convert encoding
	// @param string $str
	// @param string $to
	// @param string [$from]
	// @return string
	public static function convert_encoding($str, $to, $from = ""){
		//list_encodings
		$from = (empty($from)) ? self::detect_encoding($str) : $from;
		return mb_convert_encoding($str, $to, $from);
	}
	## delete not common control codes
	// @param mixed $mixed (string or array)
	// @return mixed (string or array)
	public static function delete_control($mixed){
		return preg_replace('%[\x00-\x08\x\x0C\x0E-\x1A\x1C-\x1F\x7F]%sm', '', $mixed);
		//残す制御文字
		// \x09 タブ HT horizon tab
		// \x0A 改行 LF line feed
		// \x0B 垂直タブ VT vertical tab たぶ(tab)んいらないと思う
		// \x0D 復帰 CR 何の略？
		// \x1B エスケープ ESC escape JISのエスケープシーケンスの為に残す
	}
	## replace line feed
	// @param mixed $mixed (string or array)
	// @param string [$linefeed]
	// @return mixed (string or array)
	public static function linefeed($mixed, $linefeed = ""){
		return ($linefeed != "\n") ? str_replace("\n", $linefeed, str_replace(Array("\r\n", "\r"), Array("\r", "\n"), $mixed)) : str_replace(Array("\r\n", "\r"), Array("\r", "\n"), $mixed);
	}
	## split letter
	// @param string $str
	// @param string [$encoding]
	// @return array
	public static function split_letter($str, $encoding = ""){
		$encoding = (empty($encoding) === true) ? self::detect_encoding($str) : $encoding;
		$a = Array();
		for($i = 0; $i < mb_strlen($str, $encoding); $i++){
			$a[] = mb_substr($str, $i, 1, $encoding);
		}
		return $a;
	}
	## length (not byte)
	// @param string $str
	// @param string $encoding
	// @return int
	public static function length($str, $encoding = ""){
		$encoding = (empty($encoding)) ? self::detect_encoding($str) : $encoding;
		//alias
		return mb_strwidth($str, $encoding);
	}
	## byte //alias func strlen()
	// @param string $str
	// @return int
	public static function byte($str){
		return strlen($str);
	}
	## wordwrap (not byte) Multibyte supported
	// @param string $str
	// @param int    $length
	// @param string $break
	// @param string $encoding
	// @return string
	public static function wordwrap($str, $length = 70, $break = "\n", $encoding = ""){
		$encoding = (empty($encoding)) ? self::detect_encoding($str) : $encoding;
		$str = self::linefeed($str, $break);
		$letter = self::split_letter($str, $encoding);
		$cnt = 0;
		$text = "";
		for($i = 0; $i < count($letter); $i++){
			if($letter[$i] == $break){
				$cnt = 0;
				$text .= $break;
				continue;
			}else{
				$width = mb_strwidth($letter[$i], $encoding);
				if($cnt + $width <= $length){
					$text .= $letter[$i];
					$cnt += $width;
				}else{
					$text .= $break . $letter[$i];
					$cnt = $width;
				}
			}
		}
		return $text;
	}
	## cut_length
	// @param string $str
	// @param int    $length
	// @param string $encoding
	// @return string
	public static function cut_length($str, $length, $encoding = ""){
		$encoding = (empty($encoding)) ? self::detect_encoding($str) : $encoding;
		return mb_strimwidth($str, 0, $length, $encoding);
	}
	## cut_byte
	// @param string $str
	// @param int    $byte
	// @param string $encoding
	// @return string
	public static function cut_byte($str, $byte, $encoding = ""){
		$encoding = (empty($encoding)) ? self::detect_encoding($str) : $encoding;
		$letter = self::split_letter($str, $encoding);
		$sumByte = 0;
		$text = "";
		for($i = 0; $i < count($letter); $i++){
			$letterByte = strlen($letter[$i]);
			if($sumByte + $letterByte <= $byte){
				$text .= $letter[$i];
				$sumByte += $letterByte;
			}else{
				break;
			}
		}
		return $text;
	}
	#################### エンコーディング関連 ####################
	## ASCIIかどうか
	public static function ascii($str){
		//\x1B エスケープ も除外
		preg_match_all('%^[\x09\x0A\x0B\x0D\x20-\x7E]+$%s', $str);
		return (count($matches[0]) === 1)?implode("", $matches[0]): false;
	}
	## ASCII不正文字削除
	public static function ascii_valid($str){
		preg_match_all('%[\x09\x0A\x0B\x0D\x20-\x7E]+%s', $str, $matches);
		return implode("", $matches[0]);
	}
	## UTF-8かどうか
	public static function utf8($str, $strict = false){
		if(preg_match('%[\xC0\xC1\xF5-\xFF]%sm', $str) === 1){
			return false;
		}
		if($strict){
			preg_match_all('%^(?:
				[\x00-\x7F] |                        ## 1byte
				[\xC2-\xDF][\x80-\xBF] |             ## 2byte
				\xE0[\xA0-\xBF][\x80-\xBF] |         ## 3byte 1
				[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} |  ## 3byte 2
				\xED[\x80-\x9F][\x80-\xBF] |         ## 3byte 3
				\xF0[\x90-\xBF][\x80-\xBF]{2} |      ## 4byte 1
				[\xF1-\xF3][\x80-\xBF]{3} |          ## 4byte 2
				\xF4[\x80-\x8F][\x80-\xBF]{2}        ## 4byte 3
				)+$%xs', $str, $matches);
			return (count($matches[0]) === 1)?implode("", $matches[0]): false;
		}else{
			preg_match_all('%^(?:
				[\x00-\x7F] |                        ## 1byte
				[\xC2-\xDF][\x80-\xBF] |             ## 2byte
				\xE0[\xA0-\xBF][\x80-\xBF] |         ## 3byte 1
				[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} |  ## 3byte 2
				\xED[\x80-\x9F][\x80-\xBF]           ## 3byte 3
				)+$%xs', $str, $matches);
			return (count($matches[0]) === 1)?implode("", $matches[0]): false;
		}
	}
	## UTF-8不正文字削除
	public static function utf8_valid($str, $strict = false){
		if($strict){
			preg_match_all('%(?:
				[\x00-\x7F] |                        ## 1byte
				[\xC2-\xDF][\x80-\xBF] |             ## 2byte
				\xE0[\xA0-\xBF][\x80-\xBF] |         ## 3byte 1
				[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} |  ## 3byte 2
				\xED[\x80-\x9F][\x80-\xBF] |         ## 3byte 3
				\xF0[\x90-\xBF][\x80-\xBF]{2} |      ## 4byte 1
				[\xF1-\xF3][\x80-\xBF]{3} |          ## 4byte 2
				\xF4[\x80-\x8F][\x80-\xBF]{2}        ## 4byte 3
				)+%xs', $str, $matches);
			return implode("", $matches[0]);
		}else{
			preg_match_all('%(?:
				[\x09\x0A\x0B\x0D\x20-\x7E] |        ## 1byte
				[\xC2-\xDF][\x80-\xBF] |             ## 2byte
				\xE0[\xA0-\xBF][\x80-\xBF] |         ## 3byte 1
				[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} |  ## 3byte 2
				\xED[\x80-\x9F][\x80-\xBF]           ## 3byte 3
				)+%xs', $str, $matches);
			return implode("", $matches[0]);
		}
	}
	## Shift JISかどうか
	public static function sjis($str){
		if(preg_match('%[\xFD-\xFF]%sm', $str) === 1){
			return false;
		}
		preg_match_all('%^(?:
			[\x00-\x7F] |
			[\xA1-\xDF] |
			[\x81-\x9F\xE0-\xFC][\x40-\x7E\x80-\xFC]
			)+$%xs', $str, $matches);
		return (count($matches[0]) === 1)?implode("", $matches[0]): false;
	}
	## Shift JIS不正文字削除
	public static function sjis_valid($str){
		preg_match_all('%(?:
			[\x00-\x7F] |
			[\xA1-\xDF] |
			[\x81-\x9F\xE0-\xFC][\x40-\x7E\x80-\xFC]
			)+%xs', $str, $matches);
		return implode("", $matches[0]);
	}
	## JIS(ISO-2002-JP-?)かどうか
	public static function jis($str){
		if(preg_match('%[\x99-\xFF]%sm', $str) === 1){
			return false;
		}
		//エスケープシーケンスの検索
		return (
			preg_match('%(?:
			\x1B\x28\x42 |       ## Esc ( B  -> ASCII 【ISO-2022-JP】
			\x1B\x28\x4A |       ## Esc ( J  -> JIS X 0201-1976のラテン文字集合 【ISO-2022-JP】
			\x1B\x28\x49 |       ## Esc ( I  -> 半角カタカナ【JIS?】
			\x1B\x24\x40 |       ## Esc $ @  -> JIS C 6226-1978 【ISO-2022-JP】
			\x1B\x24\x42 |       ## Esc $ B  -> JIS X 0208-1983 JIS X 0208:1990 【ISO-2022-JP】
			\x1B\x24\x28\x44 |   ## Esc $ ( D -> JIS X 0212-1990 【ISO-2022-JP-1】
			\x1B\x24\x28\x4F |   ## Esc $ ( O -> JIS X 0213:2000の1面 【ISO-2022-JP-3】
			\x1B\x24\x28\x50 |   ## Esc $ ( P -> JIS X 0213:2000の2面 【ISO-2022-JP-3】
			\x1B\x24\x28\x51     ## Esc $ ( Q -> JIS X 0213:2004の1面 【ISO-2022-JP-2004】
			)%xs', $str) === 1
		) ? true : false ;
	}
	
}
?>