以指定编码对字符串进行截取
假设有字符串“朱元璋”，截取限定的长度为7字节
截取编码为utf-8 结果为“朱”
截取编码为gb2312时 结果为“朱”
字符串为“hello朱元璋”，截取限定的长度为13字节
截取编码为utf-8 结果为“hello朱元”
这里的问题就是gbk编码占位2个字节，而utf-8占位3个字节，完整的示例代码：
1: 2: <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd"> 3: <html> 4: <head> 5: <title> new document </title> 6: <meta name="generator" content="editplus" /> 7: <meta name="author" content="" /> 8: <meta name="keywords" content="" /> 9: <meta name="description" content="" /> 10: <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 11: </head> 12: 13: <body> 14: <script type="text/javascript"> 15: function getRealLen(str, isUTF8) { 16: if (typeof str != 'string') { 17: return 0; 18: } 19: 20: if (!isUTF8) { 21: return str.replace(/[^\x00-\xFF]/g, 'xx').length; 22: } else { 23: var tempStr = str.replace(/[\x00-\xFF]/g, ''); 24: return (str.length - tempStr.length) + Math.floor(encodeURI(tempStr).length / 3); 25: } 26: } 27: 28: function uniLeft(str, isUTF8, len, suffix) { 29: var str = str.toString(); 30: var len = len * 1; 31: var suffix = suffix || ""; 32: 33: if (isNaN(len)) { 34: return str; 35: } 36: 37: var uniLen = getRealLen(str, isUTF8),tempStr = ''; 38: 39: if (uniLen <= len) { 40: return str.substr(0); 41: } 42: 43: for (var i = Math.floor(len / 2); i< uniLen; i++) { 44: tempStr = str.substr(0, i); 45: 46: if (getRealLen(tempStr, isUTF8) >= len || getRealLen(str.substr(0, i+1), isUTF8) > len) { 47: return tempStr; 48: } 49: } 50: } 51: 52: var str_1 = '朱元璋'; 53: var str_2 = 'hello朱元璋'; 54: 55: document.write( uniLeft(str_1, false, 3) + "<br/>");//gb2312 56: document.write( uniLeft(str_2, true, 13) );//utf-8 57: </script> 58: </body> 59: </html>这里从len/2开始试着截取字符串，截取后调用getRealLen方法获取真实长度，判断是否超出限定的长度
本文参与 腾讯云自媒体分享计划，分享自作者个人站点/博客。
原始发表：2011-03-21 ，如有侵权请联系 cloudcommunity@tencent.com 删除
评论
登录后参与评论
推荐阅读