用javascript打印XML

Question

我有一个字符串,表示我想要打印的非缩进XML.例如:

<root><node/></root>

应成为:

<root>
  <node/>
</root>

语法突出显示不是必需的.为了解决这个问题,我首先转换XML以添加回车符和空格,然后使用pre标签输出XML.为了添加新行和空格,我编写了以下函数:

function formatXml(xml) {
    var formatted = '';
    var reg = /(>)(<)(\/*)/g;
    xml = xml.replace(reg, '$1\r\n$2$3');
    var pad = 0;
    jQuery.each(xml.split('\r\n'), function(index, node) {
        var indent = 0;
        if (node.match( /.+<\/\w[^>]*>$/ )) {
            indent = 0;
        } else if (node.match( /^<\/\w/ )) {
            if (pad != 0) {
                pad -= 1;
            }
        } else if (node.match( /^<\w[^>]*[^\/]>.*$/ )) {
            indent = 1;
        } else {
            indent = 0;
        }

        var padding = '';
        for (var i = 0; i < pad; i++) {
            padding += '  ';
        }

        formatted += padding + node + '\r\n';
        pad += indent;
    });

    return formatted;
}

然后我调用这个函数:

jQuery('pre.formatted-xml').text(formatXml('<root><node1/></root>'));

这对我来说非常好,但在我写前一个函数时,我认为必须有更好的方法.所以我的问题是,你知道有什么更好的方法给XML字符串在html页面中漂亮打印吗？任何可以完成这项工作的javascript框架和/或插件都是受欢迎的.我唯一的要求就是在客户端完成.

Answer 1

从问题的文本中我得到的结果是预期字符串结果,而不是HTML格式的结果.

如果是这样,最简单的方法是使用标识转换和<xsl:output indent="yes"/>指令处理XML文档:

<xsl:stylesheet version="1.0"
 xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
 <xsl:output omit-xml-declaration="yes" indent="yes"/>

    <xsl:template match="node()|@*">
      <xsl:copy>
        <xsl:apply-templates select="node()|@*"/>
      </xsl:copy>
    </xsl:template>
</xsl:stylesheet>

在提供的XML文档上应用此转换时:

<root><node/></root>

大多数XSLT处理器(.NET XslCompiledTransform,Saxon 6.5.4和Saxon 9.0.0.2,AltovaXML)产生想要的结果:

<root>
  <node />
</root>

Answer 2

轻微修改efnx clckclcks的javascript函数.我将格式从空格更改为制表符,但最重要的是我允许文本保留在一行:

var formatXml = this.formatXml = function (xml) {
        var reg = /(>)\s*(<)(\/*)/g; // updated Mar 30, 2015
        var wsexp = / *(.*) +\n/g;
        var contexp = /(<.+>)(.+\n)/g;
        xml = xml.replace(reg, '$1\n$2$3').replace(wsexp, '$1\n').replace(contexp, '$1\n$2');
        var pad = 0;
        var formatted = '';
        var lines = xml.split('\n');
        var indent = 0;
        var lastType = 'other';
        // 4 types of tags - single, closing, opening, other (text, doctype, comment) - 4*4 = 16 transitions 
        var transitions = {
            'single->single': 0,
            'single->closing': -1,
            'single->opening': 0,
            'single->other': 0,
            'closing->single': 0,
            'closing->closing': -1,
            'closing->opening': 0,
            'closing->other': 0,
            'opening->single': 1,
            'opening->closing': 0,
            'opening->opening': 1,
            'opening->other': 1,
            'other->single': 0,
            'other->closing': -1,
            'other->opening': 0,
            'other->other': 0
        };

        for (var i = 0; i < lines.length; i++) {
            var ln = lines[i];

            // Luca Viggiani 2017-07-03: handle optional <?xml ... ?> declaration
            if (ln.match(/\s*<\?xml/)) {
                formatted += ln + "\n";
                continue;
            }
            // ---

            var single = Boolean(ln.match(/<.+\/>/)); // is this line a single tag? ex. <br />
            var closing = Boolean(ln.match(/<\/.+>/)); // is this a closing tag? ex. </a>
            var opening = Boolean(ln.match(/<[^!].*>/)); // is this even a tag (that's not <!something>)
            var type = single ? 'single' : closing ? 'closing' : opening ? 'opening' : 'other';
            var fromTo = lastType + '->' + type;
            lastType = type;
            var padding = '';

            indent += transitions[fromTo];
            for (var j = 0; j < indent; j++) {
                padding += '\t';
            }
            if (fromTo == 'opening->closing')
                formatted = formatted.substr(0, formatted.length - 1) + ln + '\n'; // substr removes line break (\n) from prev loop
            else
                formatted += padding + ln + '\n';
        }

        return formatted;
    };

Answer 3

这可以使用原生的javascript工具完成,没有第三方库,扩展了@Dimitre Novatchev的答案:

var prettifyXml = function(sourceXml)
{
    var xmlDoc = new DOMParser().parseFromString(sourceXml, 'application/xml');
    var xsltDoc = new DOMParser().parseFromString([
        // describes how we want to modify the XML - indent everything
        '<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform">',
        '  <xsl:strip-space elements="*"/>',
        '  <xsl:template match="para[content-style][not(text())]">', // change to just text() to strip space in text nodes
        '    <xsl:value-of select="normalize-space(.)"/>',
        '  </xsl:template>',
        '  <xsl:template match="node()|@*">',
        '    <xsl:copy><xsl:apply-templates select="node()|@*"/></xsl:copy>',
        '  </xsl:template>',
        '  <xsl:output indent="yes"/>',
        '</xsl:stylesheet>',
    ].join('\n'), 'application/xml');

    var xsltProcessor = new XSLTProcessor();    
    xsltProcessor.importStylesheet(xsltDoc);
    var resultDoc = xsltProcessor.transformToDocument(xmlDoc);
    var resultXml = new XMLSerializer().serializeToString(resultDoc);
    return resultXml;
};

console.log(prettifyXml('<root><node/></root>'));

输出:

<root>
  <node/>
</root>

的jsfiddle

Answer 4

Personnaly,我使​​用google-code-prettify这个函数:

prettyPrintOne('<root><node1><root>', 'xml')

Answer 5

当我有类似的要求时发现这个线程但我简化了OP的代码如下:

function formatXml(xml, tab) { // tab = optional indent value, default is tab (\t)
    var formatted = '', indent= '';
    tab = tab || '\t';
    xml.split(/>\s*</).forEach(function(node) {
        if (node.match( /^\/\w/ )) indent = indent.substring(tab.length); // decrease indent by one 'tab'
        formatted += indent + '<' + node + '>\r\n';
        if (node.match( /^<?\w[^>]*[^\/]$/ )) indent += tab;              // increase indent
    });
    return formatted.substring(1, formatted.length-3);
}

适合我!

Answer 6

或者如果你只是喜欢另一个js函数来做,我已经修改了Darin(很多):

var formatXml = this.formatXml = function (xml) {
    var reg = /(>)(<)(\/*)/g;
    var wsexp = / *(.*) +\n/g;
    var contexp = /(<.+>)(.+\n)/g;
    xml = xml.replace(reg, '$1\n$2$3').replace(wsexp, '$1\n').replace(contexp, '$1\n$2');
    var pad = 0;
    var formatted = '';
    var lines = xml.split('\n');
    var indent = 0;
    var lastType = 'other';
    // 4 types of tags - single, closing, opening, other (text, doctype, comment) - 4*4 = 16 transitions 
    var transitions = {
        'single->single'    : 0,
        'single->closing'   : -1,
        'single->opening'   : 0,
        'single->other'     : 0,
        'closing->single'   : 0,
        'closing->closing'  : -1,
        'closing->opening'  : 0,
        'closing->other'    : 0,
        'opening->single'   : 1,
        'opening->closing'  : 0, 
        'opening->opening'  : 1,
        'opening->other'    : 1,
        'other->single'     : 0,
        'other->closing'    : -1,
        'other->opening'    : 0,
        'other->other'      : 0
    };

    for (var i=0; i < lines.length; i++) {
        var ln = lines[i];
        var single = Boolean(ln.match(/<.+\/>/)); // is this line a single tag? ex. <br />
        var closing = Boolean(ln.match(/<\/.+>/)); // is this a closing tag? ex. </a>
        var opening = Boolean(ln.match(/<[^!].*>/)); // is this even a tag (that's not <!something>)
        var type = single ? 'single' : closing ? 'closing' : opening ? 'opening' : 'other';
        var fromTo = lastType + '->' + type;
        lastType = type;
        var padding = '';

        indent += transitions[fromTo];
        for (var j = 0; j < indent; j++) {
            padding += '    ';
        }

        formatted += padding + ln + '\n';
    }

    return formatted;
};

Answer 7

此处给出的所有javascript函数都不适用于在结束标记">"和开始标记"<"之间具有未指定空格的xml文档.要修复它们,您只需要替换函数中的第一行

var reg = /(>)(<)(\/*)/g;

通过

var reg = /(>)\s*(<)(\/*)/g;

Answer 8

对于当前的项目，我需要在不使用额外库的情况下对 XML 进行美化和着色。下面的自包含代码运行得很好。

function formatXml(xml,colorize,indent) { 
  function esc(s){return s.replace(/[-\/&<> ]/g,function(c){         // Escape special chars
    return c==' '?'&nbsp;':'&#'+c.charCodeAt(0)+';';});}            
  var sm='<div class="xmt">',se='<div class="xel">',sd='<div class="xdt">',
      sa='<div class="xat">',tb='<div class="xtb">',tc='<div class="xtc">',
      ind=indent||'  ',sz='</div>',tz='</div>',re='',is='',ib,ob,at,i;
  if (!colorize) sm=se=sd=sa=sz='';   
  xml.match(/(?<=<).*(?=>)|$/s)[0].split(/>\s*</).forEach(function(nd){
    ob=('<'+nd+'>').match(/^(<[!?\/]?)(.*?)([?\/]?>)$/s);             // Split outer brackets
    ib=ob[2].match(/^(.*?)>(.*)<\/(.*)$/s)||['',ob[2],''];            // Split inner brackets 
    at=ib[1].match(/^--.*--$|=|('|").*?\1|[^\t\n\f \/>"'=]+/g)||['']; // Split attributes
    if (ob[1]=='</') is=is.substring(ind.length);                     // Decrease indent
    re+=tb+tc+esc(is)+tz+tc+sm+esc(ob[1])+sz+se+esc(at[0])+sz;
    for (i=1;i<at.length;i++) re+=(at[i]=="="?sm+"="+sz+sd+esc(at[++i]):sa+' '+at[i])+sz;
    re+=ib[2]?sm+esc('>')+sz+sd+esc(ib[2])+sz+sm+esc('</')+sz+se+ib[3]+sz:'';
    re+=sm+esc(ob[3])+sz+tz+tz;
    if (ob[1]+ob[3]+ib[2]=='<>') is+=ind;                             // Increase indent
  });
  return re;
}

参见https://jsfiddle.net/dkb0La16/