C# XMLNodeList Foreach item, group content by module title field from XML

Question

I'm creating a data import from an XML file, to input into our CMS. A course can have up to 9 levels of modules, and each level can have multiple module titles within it.

e.g. XML

<test:modules>
    <test:module>
        <test:title>
           <![CDATA[ Module title 1 ]]>
        </test:title>
        <test:content>
            <![CDATA[ ]]>
        </test:content>
        <test:group>Year 1 Core Modules</lmu:group>
    </test:module>
    <test:module>
        <test:title>
           <![CDATA[ Module title 2 ]]>
        </test:title>
        <test:content>
            <![CDATA[ ]]>
        </test:content>
        <test:group>Year 1 Core Modules</test:group>
    </test:module>
    <test:module>
        <test:title>
           <![CDATA[ Module title 1 ]]>
        </test:title>
        <test:content>
            <![CDATA[ ]]>
        </test:content>
        <test:group>Year 2 Core Modules</test:group>
    </test:module>
    <test:module>
        <test:title>
           <![CDATA[ Module title 2 ]]>
        </test:title>
        <test:content>
            <![CDATA[ ]]>
        </test:content>
        <test:group>Year 2 Core Modules</test:group>
    </test:module>
    <test:module>
        <test:title>
           <![CDATA[ Module title 1 ]]>
        </test:title>
        <test:content>
            <![CDATA[ ]]>
        </test:content>
        <test:group>Year 3 Core Modules</test:group>
    </test:module>

</test:modules>

what i want to do, is to loop through each of the items, and for each group, save a ul li list of modules under each "group".

I'd like to save this to a 9x3 2D array, so i can access this for the import.

so:

modulesArray[0, 0] would be "Year 1 Core Modules"
modulesArray[0, 1] would be "<ul><li>Module title 1<li><li>Module title 2<li></ul>

My code is as follows, but i'm not sure where to go from here:

protected override FeedCourse MapXmlNodeToEntity(XElement p)
    {
        var xmlResult = new XmlDocument();
        xmlResult.LoadXml(p.ToString());
        var test = p.ToString();

        var xmlnsManager = new XmlNamespaceManager(xmlResult.NameTable);
        xmlnsManager.AddNamespace("ns", "http://xcri.org/profiles/1.2/catalog");
        xmlnsManager.AddNamespace("xcriTerms", "http://xcri.org/profiles/catalog/terms");
        xmlnsManager.AddNamespace("xsi", "http://www.w3.org/2001/XMLSchema-instance");
        xmlnsManager.AddNamespace("xhtml", "http://www.w3.org/1999/xhtml");
        xmlnsManager.AddNamespace("dc", "http://purl.org/dc/elements/1.1/");
        xmlnsManager.AddNamespace("dcterms", "http://purl.org/dc/terms/");
        xmlnsManager.AddNamespace("credit", "http://purl.org/net/cm");
        xmlnsManager.AddNamespace("mlo", "http://purl.org/net/mlo");
        xmlnsManager.AddNamespace("courseDataProgramme", "http://xcri.co.uk");
        xmlnsManager.AddNamespace("test", "http://www.test.com");

        var elements = xmlResult.ChildNodes;

        var code =
            xmlResult.DocumentElement.SelectSingleNode(
                "dc:identifier[@xsi:type=\"courseDataProgramme:internalID\"]", xmlnsManager).InnerText;
        var title = xmlResult.DocumentElement.SelectSingleNode("dc:title", xmlnsManager).InnerText;
        var subject = xmlResult.DocumentElement.SelectSingleNode("dc:subject", xmlnsManager).InnerText;



        String[,] modulesArray = new String[6, 3];
        XmlNodeList modList = xmlResult.DocumentElement.SelectNodes("test:modules/test:module", xmlnsManager);
        // var modulestest1 = modList.Item(1).InnerText;
        int modulecount = 0;
        int titlescount = modList.Count;

        var previousModuleGroupTitle = "";
        var modulecontenttitles = "";

        foreach (XmlNode mn in modList)
        {
            var currentmodgroup = mn["test:group"].InnerText;
            if (previousModuleGroupTitle == "")
            {
                modulecontenttitles += "<ul>";
                modulecontenttitles += "<li>" + mn["test:title"].InnerText + "</li>";
            }
            if (previousModuleGroupTitle == mn["test:group"].InnerText)
            {
                modulecontenttitles += "<li>" + mn["test:title"].InnerText + "</li>";
            }
            else
            {
                modulecontenttitles += "</ul>";
                modulecount++;
                modulesArray[modulecount, 0] = modulecontenttitles;
                modulecontenttitles = "";
                modulecontenttitles += "<ul><li>" + mn["test:title"].InnerText + "</li>";
            }

            // modulesArray[modulecount, 0] = mn["test:title"].InnerText;
            //modulesArray[modulecount, 1] = mn["test:content"].InnerText;
            //modulesArray[modulecount, 2] = mn["test:group"].InnerText;
            previousModuleGroupTitle = mn["test:group"].InnerText;
            modulecount++;
        }

        modulesArray[0, 0].ToString();
}

Answer 1

Try this

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Xml;
using System.Xml.Linq;

namespace ConsoleApplication78
{
    class Program
    {
        const string FILENAME = @"c:\temp\test.xml";
        static void Main(string[] args)
        {

            string xml =
            "<Root xmlns:test=\"abc\">" +
              "<test:modules>" +
                "<test:module>" +
                    "<test:title>" +
                       "<![CDATA[ Module title 1 ]]>" +
                    "</test:title>" +
                    "<test:content>" +
                        "<![CDATA[ ]]>" +
                    "</test:content>" +
                    "<test:group>Year 1 Core Modules</test:group>" +
                "</test:module>" +
                "<test:module>" +
                    "<test:title>" +
                       "<![CDATA[ Module title 2 ]]>" +
                    "</test:title>" +
                    "<test:content>" +
                        "<![CDATA[ ]]>" +
                    "</test:content>" +
                    "<test:group>Year 1 Core Modules</test:group>" +
                "</test:module>" +
                "<test:module>" +
                    "<test:title>" +
                       "<![CDATA[ Module title 1 ]]>" +
                    "</test:title>" +
                    "<test:content>" +
                        "<![CDATA[ ]]>" +
                    "</test:content>" +
                    "<test:group>Year 2 Core Modules</test:group>" +
                "</test:module>" +
                "<test:module>" +
                    "<test:title>" +
                       "<![CDATA[ Module title 2 ]]>" +
                    "</test:title>" +
                    "<test:content>" +
                        "<![CDATA[ ]]>" +
                    "</test:content>" +
                    "<test:group>Year 2 Core Modules</test:group>" +
                "</test:module>" +
                "</test:modules>" +
                "</Root>";

            XElement root = XElement.Parse(xml);
            XElement modules = root.Descendants().Where(x => x.Name.LocalName == "modules").FirstOrDefault();
            XNamespace ns = modules.Name.Namespace;

            var results = modules.Descendants(ns + "module")
                .GroupBy(x => x.Element(ns + "title").Value)
                .Select(y => new {
                    title = y.Key,
                    group = y.Select(z => (string)z.Element(ns + "group")).ToList()
                })
                .ToList();

        }
    }
}

Answer 2

Thanks for the answer. I think for other projects that require this, i'll re-work my code to use your methods. Very useful, so thanks for your time and effort.

For this particular project, i've been through the ordering logically, and this does what i need it to do, ready for the input. Hope either of these answers helps someone else out with the same issue.

        String[,] modulesArray = new String[6, 3];
        XmlNodeList modList = xmlResult.DocumentElement.SelectNodes("test:modules/test:module", xmlnsManager);

        int modulecount = 0;
        int maxtitlescount = modList.Count;
        int moduleArrayIndex = 0;
        var previousModuleGroupTitle = "";
        var modulecontenttitles = "";

        foreach (XmlNode mn in modList)
        {
            var currentmodgroup = mn["test:group"].InnerText;

            if (previousModuleGroupTitle == "")
            {
                modulecontenttitles += "<ul>";
                modulecontenttitles += "<li>" + mn["test:title"].InnerText + "</li>";
            }
            else
            {
                if (previousModuleGroupTitle != currentmodgroup)
                {
                    modulecontenttitles += "</ul>";
                    modulesArray[moduleArrayIndex, 0] = previousModuleGroupTitle;
                    modulesArray[moduleArrayIndex, 1] = modulecontenttitles;
                    modulecontenttitles = "";
                    moduleArrayIndex++;
                    modulecontenttitles += "<ul>";
                }
                else
                {
                    modulecontenttitles += "<li>" + mn["test:title"].InnerText + moduleArrayIndex + "</li>";
                    modulecontenttitles += modulecount;
                    modulecontenttitles += maxtitlescount;
                }
            }

            if((modulecount+1) == maxtitlescount)
            {
                modulecontenttitles += "</ul>";
                modulesArray[moduleArrayIndex, 0] = currentmodgroup;
                modulesArray[moduleArrayIndex, 1] = modulecontenttitles;
                modulecontenttitles = "";
            }
            previousModuleGroupTitle = mn["test:group"].InnerText;
            modulecount++;
        }

        var modules1title = (modulesArray[0, 0] != null) ? modulesArray[0, 0].ToString() : "";
        var modules1content = (modulesArray[0, 1] != null) ? modulesArray[0, 1].ToString() : "";
        var modules2title = (modulesArray[1, 0] != null) ? modulesArray[1, 0].ToString() : "";
        var modules2content = (modulesArray[1, 1] != null) ? modulesArray[1, 1].ToString() : "";
        var modules3title = (modulesArray[2, 0] != null) ? modulesArray[2, 0].ToString() : "";
        var modules3content = (modulesArray[2, 1] != null) ? modulesArray[2, 1].ToString() : "";
        var modules4title = (modulesArray[3, 0] != null) ? modulesArray[3, 0].ToString() : "";
        var modules4content = (modulesArray[3, 1] != null) ? modulesArray[3, 1].ToString() : "";
        var modules5title = (modulesArray[4, 0] != null) ? modulesArray[4, 0].ToString() : "";
        var modules5content = (modulesArray[4, 1] != null) ? modulesArray[4, 1].ToString() : "";
        var modules6title = (modulesArray[5, 0] != null) ? modulesArray[5, 0].ToString() : "";
        var modules6content = (modulesArray[5, 1] != null) ? modulesArray[5, 1].ToString() : "";