如何使用Javascript正则表达式来格式化XML内容

207 阅读 0 评论 137 点赞

我是靠谱客的博主幽默花生，最近开发中收集的这篇文章主要介绍如何使用Javascript正则表达式来格式化XML内容，觉得挺不错的，现在分享给大家，希望可以做个参考。

概述

使用得是Emeditor ，在看XML文档时，总是因为格式混乱而看不清。这个是一个Emeditor宏来自动格式化XML。下载：formatXml.rar (1,021.00 bytes)
下面这段是这个网页版的javascript格式化XML的代码。

复制代码代码如下:

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<html>
<head>
    <meta http-equiv=content-type content="text/html; charset=UTF-8">
    <title>Xml格式化工具</title>
    <script type="text/javascript">
    String.prototype.removeLineEnd = function()
    {
        return this.replace(/(<.+?s+?)(?:ns*?(.+?=".*?"))/g,'$1 $2')
    }
    function formatXml(text)
    {
        //去掉多余的空格
        text = 'n' + text.replace(/(<w+)(s.*?>)/g,function($0, name, props)
        {
            return name + ' ' + props.replace(/s+(w+=)/g," $1");
        }).replace(/>s*?</g,">n<");

        //把注释编码
        text = text.replace(/n/g,'r').replace(/<!--(.+?)-->/g,function($0, text)
        {
            var ret = '<!--' + escape(text) + '-->';
            //alert(ret);
            return ret;
        }).replace(/r/g,'n');

        //调整格式
        var rgx = /n(<(([^?]).+?)(?:s|s*?>|s*?(/)>)(?:.*?(?:(?:(/)>)|(?:<(/)2>)))?)/mg;
        var nodeStack = [];
        var output = text.replace(rgx,function($0,all,name,isBegin,isCloseFull1,isCloseFull2 ,isFull1,isFull2){
            var isClosed = (isCloseFull1 == '/') || (isCloseFull2 == '/' ) || (isFull1 == '/') || (isFull2 == '/');
            //alert([all,isClosed].join('='));
            var prefix = '';
            if(isBegin == '!')
            {
                prefix = getPrefix(nodeStack.length);
            }
            else 
            {
                if(isBegin != '/')
                {
                    prefix = getPrefix(nodeStack.length);
                    if(!isClosed)
                    {
                        nodeStack.push(name);
                    }
                }
                else
                {
                    nodeStack.pop();
                    prefix = getPrefix(nodeStack.length);
                }

            }
                var ret =  'n' + prefix + all;
                return ret;
        });

        var prefixSpace = -1;
        var outputText = output.substring(1);
        //alert(outputText);

        //把注释还原并解码，调格式
        outputText = outputText.replace(/n/g,'r').replace(/(s*)<!--(.+?)-->/g,function($0, prefix,  text)
        {
            //alert(['[',prefix,']=',prefix.length].join(''));
            if(prefix.charAt(0) == 'r')
                prefix = prefix.substring(1);
            text = unescape(text).replace(/r/g,'n');
            var ret = 'n' + prefix + '<!--' + text.replace(/^s*/mg, prefix ) + '-->';
            //alert(ret);
            return ret;
        });

        return outputText.replace(/s+$/g,'').replace(/r/g,'rn');
    }
    function getPrefix(prefixIndex)
    {
        var span = '    ';
        var output = [];
        for(var i = 0 ; i < prefixIndex; ++i)
        {
            output.push(span);
        }

        return output.join('');
    }        
        function btnFormat_click()
        {
            var $ = document.getElementById;
            $('output').value = formatXml($('input').value);
        }

    </script>

    
</head>
<body>
    <textarea id="input" style="width:100%;height:45%;"></textarea>
    <div style="margin:0px auto;"><input type="button" id="btnFormat" onclick="btnFormat_click()" value="格式化" style="width:50%;height:10%;"/></div>
    <textarea id="output" style="width:100%;height:45%;"></textarea>
</body>
</html>