Skip to content

Instantly share code, notes, and snippets.

@sente

sente/formatXML.js

Last active April 4, 2024 12:20
Show Gist options
  • Save sente/1083506 to your computer and use it in GitHub Desktop.
Save sente/1083506 to your computer and use it in GitHub Desktop.
Download ZIP
javascript to format/pretty-print XML
Raw
formatXML.js
The MIT License (MIT)
Copyright (c) 2016 Stuart Powers
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
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;
}
xml_raw = '<foo><bar><baz>blahblah</baz><baz>tralala</baz></bar></foo>';
xml_formatted = formatXml(xml_raw);
xml_escaped = xml_formatted.replace(/&/g,'&amp;').replace(/</g,'&lt;').replace(/>/g,'&gt;').replace(/ /g, '&nbsp;').replace(/\n/g,'<br />');
var mydiv = document.createElement('div');
mydiv.innerHTML = xml_escaped;
document.body.appendChild(mydiv);
Raw
javascript_xml_pretty_print.html
<html>
<head>
<title>Javascript xml pretty print - Stuart Powers</title>
<script src="http://bit.ly/jqymin"></script>
<style>
textarea {
width: 80%;
height: 50%;
overflow-x: scroll;
overflow-y: scroll;
display: block;
border: 1px solid black;
padding: 5px;
margin: 5px;
}
</style>
<script>
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;
}
$(function(){
var url = "http://careers.stackoverflow.com/jobs/feed?searchTerm=python&location=02144&range=30";
$.ajax({
url: url,
dataType:"text",
beforeSend:function(){$('.info').append($('<p>requesting: '+url+'</p>'));},
error:function(){$('.info').append($('<p>error! '+url+'</p>'));},
success: function(data) {
$('.unformatted').text(data);
}
});
$.ajax({
url: url,
dataType:"text",
beforeSend:function(){
$('.info2').append($('<p>requesting '+url+'</p>'));
$('.info2').append($('<p>and formatting the response!'));
},
error:function(){$('.info2').append($('<p>error! '+url+'</p>'));},
success: function(data) {
xml_neat = formatXml(data);
$('.formatted').text(xml_neat);
}
});
});
</script>
</head>
<body>
<code>
Also available <a href="http://sente.cc/misc/javascript_xml_pretty_print.html">
http://sente.cc/misc/javascript_xml_pretty_print.html
</a>
</code>
<pre class="info"></pre>
<h3>unformatted</h3>
<textarea class="unformatted"></textarea>
<h3>formatted</h3>
<textarea class="formatted"></textarea>
<body>
</html>
@ianbale
Copy link

ianbale commented Jun 2, 2015

I've just come across a small issue with CDATA sections. If these contain tags then this puts then on new lines introducing white space which can break the content of the CDATA section where white space may already be deliberately encoded.

eg. Here the CDATA section is protecting carriage returns contained in the string:

<!{CDATA[line 1
line 2
line 3
]]>

But after "pretty printing" it ends up as:

line 2 line 3 ]]>

which has changed the meaning of the text the CDATA section was enclosing.

Cool function in all other cases though! :-)

@mjswan
Copy link

mjswan commented Oct 30, 2015

Thank you. Works perfectly!

@Risord
Copy link

Risord commented Mar 18, 2016

node.match(/^<\w[^>][^\/]>.$/) seems not to match single letter elements like

@vishumertiya
Copy link

Thank u so much .. It helps a lot

@edemaine
Copy link

@Risord Indeed, that regular expression should be /^<\w([^>]*[^\/])?>.*$/

@sente
Copy link
Author

sente commented Dec 16, 2016

@edemaine, @Risord -- thank you. I've updated the regular expression.

@grubersjoe
Copy link

grubersjoe commented Nov 10, 2017 •
edited
Loading

Thanks for the code.

Here's an adapted ES6 variant:

formatXml(xml) {
    const PADDING = ' '.repeat(2); // set desired indent size here
    const reg = /(>)(<)(\/*)/g;
    let pad = 0;

    xml = xml.replace(reg, '$1\r\n$2$3');

    return xml.split('\r\n').map((node, index) => {
        let indent = 0;
        if (node.match(/.+<\/\w[^>]*>$/)) {
            indent = 0;
        } else if (node.match(/^<\/\w/) && pad > 0) {
            pad -= 1;
        } else if (node.match(/^<\w[^>]*[^\/]>.*$/)) {
            indent = 1;
        } else {
            indent = 0;
        }

        pad += indent;

        return PADDING.repeat(pad - indent) + node;
    }).join('\r\n');
}

@theo-armour
Copy link

@grubersjoe

ES6 variant works for me. Thanks!

@nasermirzaei89
Copy link

nasermirzaei89 commented Mar 25, 2018 •
edited
Loading

@grubersjoe
js lint fails with this message:

Unnecessary escape character: \/ no-useless-escape

so I used [^/] in last node.match function

@MagedSaeed
Copy link

MagedSaeed commented Apr 21, 2018 •
edited
Loading

Many Thanks,, works perfect!!

@vsix27
Copy link

vsix27 commented Jun 11, 2018

did you try script on bad formed xml like

      <feed xmlns="http://www.w3.org/2005/Atom"
need="urgent">   <title type="general" sub="sample">Example Feed</title>
<subtitle><![CDATA[minor subtitle <<< ]]></subtitle>
<author nn="1" order="2" case="now"><name>John Doe</name><email>johndoe@example.com</email>
 </author>    <entry><title>Atom-Powered Robots Run Amok</title>
    <link href="http://example.org/2003/12/13/atom03" />
   <id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
  <updated>2003-12-13T18:30:02Z</updated><summary>Some text.</summary>
 </entry>      </feed>

? it does not work for me

@JoaoPortella
Copy link

@grubersjoe
Many thanks!

@ezhov-da
Copy link

@ sente
Wow, so cool, thanks!

@huangwei16800
Copy link 

<simple-value><![CDATA[部门

Dept]]>

after format xml, it will be follow result, have many space char before <![CDATA

@huangwei16800
Copy link

i had try, modify ,

var reg = /(>)(<)([^!])(/*)/g;

@brunolkatz
Copy link

thanks \o

@brennanyoung
Copy link

Good work - although I must point out that it doesn't touch existing whitespace indentation, with hilarious consequences.

@nishant-dutta
Copy link

Thanks for the code.

Here's an adapted ES6 variant:

formatXml(xml) {
    const PADDING = ' '.repeat(2); // set desired indent size here
    const reg = /(>)(<)(\/*)/g;
    let pad = 0;

    xml = xml.replace(reg, '$1\r\n$2$3');

    return xml.split('\r\n').map((node, index) => {
        let indent = 0;
        if (node.match(/.+<\/\w[^>]*>$/)) {
            indent = 0;
        } else if (node.match(/^<\/\w/) && pad > 0) {
            pad -= 1;
        } else if (node.match(/^<\w[^>]*[^\/]>.*$/)) {
            indent = 1;
        } else {
            indent = 0;
        }

        pad += indent;

        return PADDING.repeat(pad - indent) + node;
    }).join('\r\n');
}

Thanks for the ES6 version @grubersjoe ,a small addition though for handling newlines and existing whitespace between tags(as pointed out by @brennanyoung):

formatXml(xml) {
// Remove all the newlines and then remove all the spaces between tags
xml = xml.replace(/(\r\n|\n|\r)/gm, " ").replace(/>\s+</g,'><');

  const PADDING = ' '.repeat(4); // set desired indent size here
  const reg = /(>)(<)(\/*)/g;
  let pad = 0;

  xml = xml.replace(reg, '$1\r\n$2$3');

  return xml.split('\r\n').map((node, index) => {
      let indent = 0;
      if (node.match(/.+<\/\w[^>]*>$/)) {
          indent = 0;
      } else if (node.match(/^<\/\w/) && pad > 0) {
          pad -= 1;
      } else if (node.match(/^<\w[^>]*[^\/]>.*$/)) {
          indent = 1;
      } else {
          indent = 0;
      }

      pad += indent;

      return PADDING.repeat(pad - indent) + node;
  }).join('\r\n');

}

@ppazos
Copy link

ppazos commented Jul 27, 2020

I'm not sure if the latest versions of FF added more constraints, I'm getting "Toot much recursion" from formatXml()

@davidgolding
Copy link

davidgolding commented Nov 13, 2023 •
edited
Loading

A slight mismatch in one of the regular expressions needs to be: node.match(/^<[\w^>]*[^\/]>.*$/)). Merging everyone's updates, here's what I've been using:

/**
 * Prettifies the tab indentation of given XML string
 *
 * @param xml string - The XML to clean
 * @return string - Prettified XML string
 */
static prettify(xml: String) {
    let pad = 0;
    const padding = '\u0020'.repeat(4); // set desired indent size here
    
    xml = xml.replace(/(\r\n|\n|\r)/gm, '\u0020').replace(/>\s+</g,'><');
    xml = xml.replace(/(>)(<)(\/*)/g, '$1\r\n$2$3');
    
    return xml.split('\r\n').map((node, index) => { //XML elements now split into lines
        let indent = 0;
        if (node.match(/.+<\/\w[^>]*>$/)) {
            indent = 0;
        } else if (node.match(/^<\/\w/) && pad > 0) {
            pad -= 1;
        } else if (node.match(/^<[\w^>]*[^\/]>.*$/)) {
            indent = 1;
        } else {
            indent = 0;
        }
        pad += indent;
        return padding.repeat(pad - indent) + node;
    }).join('\r\n');
}

@thetilliwilli
Copy link

jlyk: if (node.match(/.+<\/\w[^>]*>$/)) { - this is extremely slow on big rows.
not for production use for sure ;) - DannyDainton/newman-reporter-htmlextra#428 (comment)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment