PHP操作字符串详解

<?php  
header("Content-type:text/html;charset=utf-8");  

echo mb_strwidth("6", "UTF-8") . '<br />';//1  
echo mb_strwidth("A", "UTF-8") . '<br />';//1  
echo mb_strwidth("a", "UTF-8") . '<br />';//1  
echo mb_strwidth("月", "UTF-8") . '<br />';//2  

echo mb_strwidth("6月9日OUR系统升级通知", "UTF-8") . '<br />';//21  

echo mb_strimwidth("6月9日OUR系统升级通知", 0, 10, '...') .'<br />';//6月9��...  
echo mb_strimwidth("6月9日OUR系统升级通知", 0, 10, '...', "UTF-8") .'<br />';//6月9日O...  
echo mb_strimwidth("6月9日OUR系统升级通知", 0, 10, '......', "UTF-8") .'<br />';//6月9......  
echo mb_strimwidth("6月9日OUR系统升级通知", 0, 10, '', "UTF-8") .'<br />';//6月9日OUR  

?>

mb_substr($string,'GBK'),
mb_strlen($string,'GBK'),
mb_strwidth($string,'GBK') 
适用于GBK

mb_substr($string,'GBK'),mb_strlen($string,'GBK'),mb_strwidth($string,'GBK')适用于GBK

$test = "123中文测试";

//字符数
$mb_strlen($test, 'GBK');//7
$mb_strlen($test, 'UTF-8');//7

$mb_strlen($test);//11

//字节数
$mb_strwidth($test, 'GBK');//11
$mb_strwidth($test, 'UTF-8');//4
$mb_strwidth($test);//11

mb_substr($test, 0, 4);//乱码
mb_substr($test, 0, 5);//123中


//字符数

mb_substr($test, 0, 4, 'GBK');//123中
mb_substr($test, 0, 5, 'GBK');//123中文

mb_substr($test, 0, 4, 'gb2312');//123中
mb_substr($test, 0, 4, 'UTF-8');//乱码

//截取中文英文字符串：
//方法1：

function str_cut($str, $len)
{
    $str = iconv($str, 'GBK', 'GBK/TRANLIT');
    if (mb_strwidth($str) < $len) {
        return $str;
    }
    for ($i = 0; $i < mb_strlen($str); $i++) {
        $tmp = mb_substr($str, $i, 1, 'GBK');
        if (mb_strwidth($return . $tmp) > $len) {
            break;
        }
        $return .= $tmp;
    }
    return $return;
}

// 方法2:

function str_cut($str, $len)
{
    $str = iconv($str, 'GBK', 'GBK/TRANLIT');
    if (mb_strwidth($str) < $len) {
        return $str;
    }
    for ($i = 0; $i < mb_strlen($str); $i++) {
        $return = mb_substr($str, 0, $i, 'GBK');
        if (mb_strwidth($return) > $len) {

            $return = mb_substr($str, 0, $i - 1, 'GBK');
            break;
        }
    }
    return $return;
}

/*
判断中文和编码有关 gbk是双字节，utf8是三字节，可以根据 中文的范围来判断

编码范围1. GBK (GB2312/GB18030)
x00-xff GBK双字节编码范围
x20-x7f ASCII
xa1-xff 中文
x80-xff 中文
2. UTF-8 (Unicode)
u4e00-u9fa5 (中文)
x3130-x318F (韩文
xAC00-xD7A3 (韩文)
u0800-u4e00 (日文)
ps: 韩文是大于[u9fa5]的字符
*/
//二、代码例子

//截取字符串字串-GBK (PHP)
function gb_substr($str, $len)
{
    $count = 0;
    for ($i = 0; $i < strlen($str); $i++) {
        if ($count == $len) break;
        if (preg_match("/[x80-xff]/", substr($str, $i, 1))) ++$i;
        ++$count;
    }
    return substr($str, 0, $i);
}

function substrGb($str, $len)
{
    $ret = '';
    $i = 0;
    while ($i < $len) {
        $ch = substr($str, $i, 1);
        if (ord($ch) > 0x80) {
            $i++;
        }
        $i++;
    }
    $ret = substr($str, 0, $i);
    return $ret;
}

//截取字符串-UTF8(PHP)
function utf8_substr($str, $position, $length)
{
    $start_position = strlen($str);
    $start_byte = 0;
    $end_position = strlen($str);
    $count = 0;
    for ($i = 0; $i < strlen($str); $i++) {
        if ($count >= $position && $start_position > $i) {
            $start_position = $i;
            $start_byte = $count;
        }
        if (($count - $start_byte) >= $length) {
            $end_position = $i;
            break;
        }
        $value = ord($str[$i]);
        if ($value > 127) {
            $count++;
            if ($value >= 192 && $value <= 223) $i++;
            elseif ($value >= 224 && $value <= 239) $i = $i + 2;
            elseif ($value >= 240 && $value <= 247) $i = $i + 3;
            else die('Not a UTF-8 compatible string');
        }
        $count++;
    }
    return (substr($str, $start_position, $end_position - $start_position));
}

// int ord ( string string )------返回字符的ASCII码
// string chr ( int ascii )-----根据字符的ASCII码返回相应的字符