不使用mb_substr函数切割字符串函数

跳至

function cutstr($string, $length, $dot = ' ...') 
{
	global $charset;

	if(strlen($string) <= $length) return $string;

	$string = str_replace(array(&#39;&&#39;, &#39;"&#39;, &#39;<&#39;, &#39;>&#39;), array(&#39;&&#39;, &#39;"&#39;, &#39;<&#39;, &#39;>&#39;), $string);

	$strcut = &#39;&#39;;
	
	if(strtolower($charset) == &#39;utf-8&#39;)
	{
		$n = $tn = $noc = 0;
		
		while($n < strlen($string))
		{
			$t = ord($string[$n]);

			// 特别要注意这部分，utf-8是1--6位不定长表示的，这里就是如何
			// 判断utf-8是1位2位还是3位还是4、5、6位,这对其他语言的编程也有用处
			// 具体可以查看rfc3629或rfc2279
			if($t == 9 || $t == 10 || (32 <= $t && $t <= 126))
			{
				$tn = 1; $n++; $noc++;
			}
			elseif(194 <= $t && $t <= 223)
			{
				$tn = 2; $n += 2; $noc += 2;
			}
			elseif(224 <= $t && $t < 239)
			{
				$tn = 3; $n += 3; $noc += 2;
			}
			elseif(240 <= $t && $t <= 247)
			{
				$tn = 4; $n += 4; $noc += 2;
			}
			elseif(248 <= $t && $t = $length)
			{
				break;
			}

		}
		
		if($noc > $length) $n -= $tn;

		$strcut = substr($string, 0, $n);
	}
	else
	{
		for($i = 0; $i < $length; $i++)
		{
			$strcut .= ord($string[$i]) > 127 ? $string[$i] . $string[++$i] : $string[$i];
		}
	}

	$strcut = str_replace(array(&#39;&&#39;, &#39;"&#39;, &#39;<&#39;, &#39;>&#39;), array(&#39;&&#39;, &#39;"&#39;, &#39;<&#39;, &#39;>&#39;), $strcut);

	return $strcut . $dot;
}

2. [代码]使用方法

$testStr = "好好学习！(good good study)天天向上！(day day up)";     // ^_^! V

// 使用utf文档
echo cutstr($testStr, 10);

// 使用dos文档使用以下代码测试utf-8的效果
//$testStr = iconv('GBK', 'UTF-8', $testStr);
//echo iconv('UTF-8', 'GBK', cutstr($testStr, 10));