Parsing Properties From Certain Nodes In Xml Using Javascript?

Suppose, I have an XML with descriptions of files and directories (where XML nodes of files that belong to some directory are nested into that directory's corresponding XML node):

Solution 1:

Using XPath e.g. //file[type = 'file']/data/offset with either browser APIs like the DOM Level 3 XPath API evaluate method on document nodes

const xml = `<list>
<signature>
hash...
</signature>
  <file id="44">
   <data>
    <length>1759</length>
    <offset>36491175</offset>
    <size>1018</size>
    <encoding style="application/x-gzip"/>
    <extracted-checksum style="sha1">91e4e9a81d6b8abb07fd6009afe72178997c512b</extracted-checksum>
    <archived-checksum style="sha1">f141cb115e21de3320c1afccd2dc115b78f83661</archived-checksum>
   </data>
   <type>file</type>
   <name>dist.dat</name>
  </file>
  <file id="6">
   <ctime>1970-01-01T00:00:00Z</ctime>
   <mtime>1970-01-01T00:00:00Z</mtime>
   <atime>1970-01-01T00:00:00Z</atime>
   <group>wheel</group>
   <gid>0</gid>
   <user>root</user>
   <uid>0</uid>
   <mode>0700</mode>
   <deviceno>0</deviceno>
   <inode>0</inode>
   <type>directory</type>
   <name>src</name>
   <file id="7">
    <ctime>1970-01-01T00:00:00Z</ctime>
    <mtime>1970-01-01T00:00:00Z</mtime>
    <atime>1970-01-01T00:00:00Z</atime>
    <group>wheel</group>
    <gid>0</gid>
    <user>root</user>
    <uid>0</uid>
    <mode>0700</mode>
    <deviceno>0</deviceno>
    <inode>0</inode>
    <type>directory</type>
    <name>Dede</name>          
    <file id="8">
     <data>
      <length>514</length>
      <offset>36357051</offset>
      <size>859</size>
      <encoding style="application/x-gzip"/>
      <extracted-checksum style="sha1">b13b86984f1ceeb698e879ad4a0c4174804529c3</extracted-checksum>
      <archived-checksum style="sha1">414b16e24dbbbbf864d68bcde726d52d69a4dc04</archived-checksum>
     </data>
     <type>file</type>
     <name>Hello.txt</name>
    </file>
    <file id="9">
     <data>
      <length>776</length>
      <offset>36357665</offset>
      <size>1630</size>
      <encoding style="application/x-gzip"/>
      <extracted-checksum style="sha1">318eec584b12f2333133d8d07bf6b2d883fa7070</extracted-checksum>
      <archived-checksum style="sha1">c1d196e28e7a8ec0444f7d16f205bd67667f5eec</archived-checksum>
     </data>
     <type>file</type>
     <name>Local_st.txt</name>
    </file>
   </file>                         
   ... More File Nodes
  </file>
</list>`;
   
const domParser = newDOMParser();

const xmlDoc = domParser.parseFromString(xml, 'application/xml');

const result = xmlDoc.evaluate('//file[type = "file"]/data/offset', xmlDoc, null, XPathResult.ORDERED_NODE_SNAPSHOT_TYPE, null);

console.log(result.snapshotLength);

const offsets = [];
for (let i = 0; i < result.snapshotLength; i++) {
  offsets.push(result.snapshotItem(i).textContent);
}

console.log(offsets);

//alternativeconst offsetNumbers = [];
for (let i = 0; i < result.snapshotLength; i++) {
  offsetNumbers.push(xmlDoc.evaluate('number()', result.snapshotItem(i), null, XPathResult.NUMBER_TYPE, null).numberValue);
}

console.log(offsetNumbers);

or using Saxon-JS 2 as a library you can use //file[type = 'file']/data/offset/number():

const xml = `<list>
<signature>
hash...
</signature>
  <file id="44">
   <data>
    <length>1759</length>
    <offset>36491175</offset>
    <size>1018</size>
    <encoding style="application/x-gzip"/>
    <extracted-checksum style="sha1">91e4e9a81d6b8abb07fd6009afe72178997c512b</extracted-checksum>
    <archived-checksum style="sha1">f141cb115e21de3320c1afccd2dc115b78f83661</archived-checksum>
   </data>
   <type>file</type>
   <name>dist.dat</name>
  </file>
  <file id="6">
   <ctime>1970-01-01T00:00:00Z</ctime>
   <mtime>1970-01-01T00:00:00Z</mtime>
   <atime>1970-01-01T00:00:00Z</atime>
   <group>wheel</group>
   <gid>0</gid>
   <user>root</user>
   <uid>0</uid>
   <mode>0700</mode>
   <deviceno>0</deviceno>
   <inode>0</inode>
   <type>directory</type>
   <name>src</name>
   <file id="7">
    <ctime>1970-01-01T00:00:00Z</ctime>
    <mtime>1970-01-01T00:00:00Z</mtime>
    <atime>1970-01-01T00:00:00Z</atime>
    <group>wheel</group>
    <gid>0</gid>
    <user>root</user>
    <uid>0</uid>
    <mode>0700</mode>
    <deviceno>0</deviceno>
    <inode>0</inode>
    <type>directory</type>
    <name>Dede</name>          
    <file id="8">
     <data>
      <length>514</length>
      <offset>36357051</offset>
      <size>859</size>
      <encoding style="application/x-gzip"/>
      <extracted-checksum style="sha1">b13b86984f1ceeb698e879ad4a0c4174804529c3</extracted-checksum>
      <archived-checksum style="sha1">414b16e24dbbbbf864d68bcde726d52d69a4dc04</archived-checksum>
     </data>
     <type>file</type>
     <name>Hello.txt</name>
    </file>
    <file id="9">
     <data>
      <length>776</length>
      <offset>36357665</offset>
      <size>1630</size>
      <encoding style="application/x-gzip"/>
      <extracted-checksum style="sha1">318eec584b12f2333133d8d07bf6b2d883fa7070</extracted-checksum>
      <archived-checksum style="sha1">c1d196e28e7a8ec0444f7d16f205bd67667f5eec</archived-checksum>
     </data>
     <type>file</type>
     <name>Local_st.txt</name>
    </file>
   </file>                         
   ... More File Nodes
  </file>
</list>`;
   
const offsets = SaxonJS.XPath.evaluate(`parse-xml($xml)//file[type = 'file']/data/offset/number()`, [], { params : { xml : xml }});

console.log(offsets);

<scriptsrc="https://www.saxonica.com/saxon-js/documentation/SaxonJS/SaxonJS2.rt.js"></script>