Develop Reference

Deserialize XML document, keeping track of order

I am parsing an XML document using the XMLSerialization tool. The sample XML file consists of paragraphs (string) and tables, which are a complex XML type. Tables consist of a series of row, which consists of a series of entry (string)
I need to keep track of the position of each table, relative to each paragraph. Is there a way of catching the position of each table as it is being parsed by the XMLSerialization tool? Or do I need to use a construct like [XMLAnyElement] and parse each paragraph and table sequentially in order to track the table position? I would prefer to avoid that approach, because my real XML files have many levels that would need manual parsing. I have a feeling that I am missing something really obvious here, but I've been scouring SO and trying multiple approaches, but with no straightforward solution.
Here is my basic code:
using System.Xml;
using System.Xml.Serialization;
using System.IO;
namespace XMLDeserializeTest
{
class Program
{
static void Main(string[] args)
{
string file = Environment.CurrentDirectory + #"\test.xml";
test testClass = Deserialize(file);
}
static test Deserialize(string url)
{
XmlSerializer reader =
new XmlSerializer(typeof(test));
StreamReader stream = new StreamReader(url);
return reader.Deserialize(stream) as test;
}
}
public class test
{
[XmlElement("paragraph")]
public List<string> paragraphs { get; set; }
[XmlElement("table")]
public List<Table> tables { get; set; }
public test()
{
}
}
public class Table
{
[XmlElement("row")]
public List<Row> rows { get; set; }
public int nodeNumber { get; set; } // This is what needs to be tracked
public Table()
{
}
}
public class Row
{
[XmlElement("entry")]
public List<string> entries { get; set; }
public Row()
{
}
}
My sample XML:
<?xml version="1.0" encoding="utf-8" ?>
<test>
<paragraph>Here is some text.</paragraph>
<paragraph>Here is some more text. The table follows this paragraph.</paragraph>
<table>
<row>
<entry>1</entry>
<entry>2</entry>
<entry>3</entry>
</row>
<row>
<entry>4</entry>
<entry>5</entry>
<entry>6</entry>
</row>
</table>
<paragraph>This is the last paragraph. This comes after the table.</paragraph>
</test>
I came up with one solution, using XDocument, but it seems pretty clumsy:
XDocument Xdoc = XDocument.Load(file);
int numParagraphs = 0;
int tableNumber = 0;
foreach(XElement item in Xdoc.Root.Descendants())
{
if (item.Name.LocalName.Equals("paragraph"))
{
numParagraphs++;
}
else if (item.Name.LocalName.Equals("table"))
{
testClass.tables[tableNumber].nodeNumber = numParagraphs;
tableNumber++;
}
}

One option would just be to serialize the paragraph "index" of the table into your XML at the time of serialization. That way you wouldn't have to do anything custom.
However, to do what you are looking for with the XmlSerializer you could handle the deserialization yourself for certain element types using the UnknownElement event. Notice that the XmlElement attributes have been removed from the test class in order for the table and paragraph elements to be handled.
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Xml;
using System.Xml.Serialization;
using System.IO;
namespace XMLDeserializeTest
{
class Program
{
static int paragraphCount = 0;
static void Main(string[] args)
{
string file = Environment.CurrentDirectory + #"\test.xml";
paragraphCount = 0;
test testClass = Deserialize(file);
}
static test Deserialize(string url)
{
XmlSerializer serializer = new XmlSerializer(typeof(test));
serializer.UnknownElement += serializer_UnknownElement;
StreamReader stream = new StreamReader(url);
return serializer.Deserialize(stream) as test;
}
static void serializer_UnknownElement(object sender, XmlElementEventArgs e)
{
test t = (test)e.ObjectBeingDeserialized;
if (e.Element.Name == "table")
{
var s = new XmlSerializer(typeof(Table));
var sr = new StringReader(e.Element.OuterXml);
Table newTable = s.Deserialize(sr) as Table;
newTable.nodeNumber = paragraphCount;
t.tables.Add(newTable);
}
else if (e.Element.Name == "paragraph")
{
String paragraphText = e.Element.InnerText;
t.paragraphs.Add(paragraphText);
paragraphCount++;
}
}
}
public class test
{
public List<string> paragraphs { get; set; }
public List<Table> tables { get; set; }
public test()
{
}
}
[Serializable, XmlRoot("table")]
public class Table
{
[XmlElement("row")]
public List<Row> rows { get; set; }
public int nodeNumber { get; set; } // This is what needs to be tracked
public Table()
{
}
}
[Serializable, XmlRoot("row")]
public class Row
{
[XmlElement("entry")]
public List<string> entries { get; set; }
public Row()
{
}
}
}

Deserialize portion of XmlDocument into object

I see this question often enough, but nobody's title really seems to depict their question. I get a large response object back from a Web API that contains general response information, along with the data object I want to deserialize.
Full XML:
<?xml version="1.0"?>
<root>
<status>
<apiErrorCode>0</apiErrorCode>
<apiErrorMessage/>
<dbErrorCode>0</dbErrorCode>
<dbErrorMessage/>
<dbErrorList/>
</status>
<data>
<modelName>ReportXDTO</modelName>
<modelData>
<id>1780</id>
<reportTitle>Access Level (select) with Door Assignment</reportTitle>
<hasParameters>true</hasParameters>
<parameters>
<dataType>STRING</dataType>
<title>Access Level:</title>
<index>1</index>
<allowMulti>true</allowMulti>
<selectSql>SELECT DISTINCT [Name] FROM dbo.[Levels] WHERE [PrecisionFlag] = '0' ORDER BY [Name] </selectSql>
<values>
<value>Door 1</value>
<used>1</used>
</values>
<values>
<value>Door 2</value>
<used>1</used>
</values>
<values>
<value>Door 3</value>
<used>1</used>
</values>
</parameters>
<sourceSql>SELECT [Name], [SData] FROM [Schedules]</sourceSql>
<report/>
</modelData>
<itemReturned>1</itemReturned>
<itemTotal>1</itemTotal>
</data>
<listInfo>
<pageIdRequested>1</pageIdRequested>
<pageIdCurrent>1</pageIdCurrent>
<pageIdFirst>1</pageIdFirst>
<pageIdPrev>1</pageIdPrev>
<pageIdNext>1</pageIdNext>
<pageIdLast>1</pageIdLast>
<itemRequested>1</itemRequested>
<itemReturned>1</itemReturned>
<itemStart>1</itemStart>
<itemEnd>1</itemEnd>
<itemTotal>1</itemTotal>
</listInfo>
</root>
I only want to deserialize the modelData element. The modelData object type is dynamic, depending on the API call.
I deserialize xml in other applications, and created the following method, but don't know how to specifically ONLY get the modelData element:
public static T ConvertXmltoClass<T>(HttpResponseMessage http, string elementName) where T : new()
{
var newClass = new T();
try
{
var doc = JsonConvert.DeserializeXmlNode(http.Content.ReadAsStringAsync().Result, "root");
XmlReader reader = new XmlNodeReader(doc);
reader.ReadToFollowing(elementName);
//The xml needs to show the proper object name
var xml = reader.ReadOuterXml().Replace(elementName, newClass.GetType().Name);
using (var stream = new MemoryStream(Encoding.UTF8.GetBytes(xml)))
{
var serializer = new XmlSerializer(typeof(T));
newClass = (T)serializer.Deserialize(stream);
}
}
catch (Exception e)
{
AppLog.LogException(System.Reflection.MethodBase.GetCurrentMethod().Name, e);
}
return newClass;
}
I have updated this thread multiple times now, to stay current. I started updating it with the first solution. But that solution by itself didn't solve the problem. With the code how it is right now, I get no exceptions, but don't get the xml deserialized to my object. Instead I get a new, blank object. Thoughts?
THOUGH the object type can change, here is my current object I am dealing with: (PLEASE NOTE, that I deserialize the exact xml in modelData, in the Web API)
namespace WebApiCommon.DataObjects
{
[Serializable]
public class ReportXDto
{
public ReportXDto()
{
Parameters = new List<ReportParameterXDto>();
}
public int Id { get; set; }
public string ReportTitle { get; set; }
public bool HasParameters { get; set; } = false;
public List<ReportParameterXDto> Parameters { get; set; }
public string SourceSql { get; set; }
public DataTable Report { get; set; }
}
[Serializable]
public class ReportXDto
{
public ReportXDto()
{
Parameters = new List<ReportParameterXDto>();
}
public int Id { get; set; }
public string ReportTitle { get; set; }
public bool HasParameters { get; set; } = false;
public List<ReportParameterXDto> Parameters { get; set; }
public string SourceSql { get; set; }
public DataTable Report { get; set; }
}
[Serializable]
public class ReportParameterValuesXDto
{
public string Value { get; set; } = "";
public bool Used { get; set; } = false;
}
}

Firstly, XmlSerializer is case sensitive. Thus your property names need to match the XML element names exactly -- unless overridden with an attribute that controls XML serialization such as [XmlElement(ElementName="id")]. To generate a data model with the correct casing I used http://xmltocsharp.azurewebsites.net/ which resulted in:
public class ReportParameterValuesXDto
{
[XmlElement(ElementName="value")]
public string Value { get; set; }
[XmlElement(ElementName="used")]
public string Used { get; set; }
}
public class ReportParametersXDto
{
[XmlElement(ElementName="dataType")]
public string DataType { get; set; }
[XmlElement(ElementName="title")]
public string Title { get; set; }
[XmlElement(ElementName="index")]
public string Index { get; set; }
[XmlElement(ElementName="allowMulti")]
public string AllowMulti { get; set; }
[XmlElement(ElementName="selectSql")]
public string SelectSql { get; set; }
[XmlElement(ElementName="values")]
public List<ReportParameterValuesXDto> Values { get; set; }
}
public class ReportXDto
{
[XmlElement(ElementName="id")]
public string Id { get; set; }
[XmlElement(ElementName="reportTitle")]
public string ReportTitle { get; set; }
[XmlElement(ElementName="hasParameters")]
public string HasParameters { get; set; }
[XmlElement(ElementName="parameters")]
public ReportParametersXDto Parameters { get; set; }
[XmlElement(ElementName="sourceSql")]
public string SourceSql { get; set; }
[XmlElement(ElementName="report")]
public string Report { get; set; }
}
(After generating the model, I modified the class names to match your naming convention.)
Given the correct data model, you can deserialize directly from a selected XmlNode using an XmlNodeReader as shown in How to deserialize a node in a large document using XmlSerializer without having to re-serialize to an intermediate XML string. The following extension method does the trick:
public static partial class XmlExtensions
{
public static IEnumerable<T> DeserializeElements<T>(this XmlNode root, string localName, string namespaceUri)
{
return new XmlNodeReader(root).DeserializeElements<T>(localName, namespaceUri);
}
public static IEnumerable<T> DeserializeElements<T>(this XmlReader reader, string localName, string namespaceUri)
{
var serializer = XmlSerializerFactory.Create(typeof(T), localName, namespaceUri);
while (!reader.EOF)
{
if (!(reader.NodeType == XmlNodeType.Element && reader.LocalName == localName && reader.NamespaceURI == namespaceUri))
reader.ReadToFollowing(localName, namespaceUri);
if (!reader.EOF)
{
yield return (T)serializer.Deserialize(reader);
// Note that the serializer will advance the reader past the end of the node
}
}
}
}
public static class XmlSerializerFactory
{
// To avoid a memory leak the serializer must be cached.
// https://stackoverflow.com/questions/23897145/memory-leak-using-streamreader-and-xmlserializer
// This factory taken from
// https://stackoverflow.com/questions/34128757/wrap-properties-with-cdata-section-xml-serialization-c-sharp/34138648#34138648
readonly static Dictionary<Tuple<Type, string, string>, XmlSerializer> cache;
readonly static object padlock;
static XmlSerializerFactory()
{
padlock = new object();
cache = new Dictionary<Tuple<Type, string, string>, XmlSerializer>();
}
public static XmlSerializer Create(Type serializedType, string rootName, string rootNamespace)
{
if (serializedType == null)
throw new ArgumentNullException();
if (rootName == null && rootNamespace == null)
return new XmlSerializer(serializedType);
lock (padlock)
{
XmlSerializer serializer;
var key = Tuple.Create(serializedType, rootName, rootNamespace);
if (!cache.TryGetValue(key, out serializer))
cache[key] = serializer = new XmlSerializer(serializedType, new XmlRootAttribute { ElementName = rootName, Namespace = rootNamespace });
return serializer;
}
}
}
Then you would deserialize as follows:
var modelData = doc.DeserializeElements<ReportXDto>("modelData", "").FirstOrDefault();
Working sample .Net fiddle here.

For Huge xml files always use XmlReader so you do not get an out of memory issue. See code below to get the element as a string :
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Xml;
namespace ConsoleApplication1
{
class Program
{
const string FILENAME = #"c:\temp\test.xml";
static void Main(string[] args)
{
//or Create(Stream)
XmlReader reader = XmlReader.Create(FILENAME);
reader.ReadToFollowing("modelData");
if (!reader.EOF)
{
string modelDataStr = reader.ReadOuterXml();
}
}
}
}

C# XML parsing - Get attribute of child node

So, I have XML like this:
<tileset firstgid="1" name="simple_tiles" tilewidth="32" tileheight="32" tilecount="16" columns="8">
<image source="../Users/mkkek/Pictures/rpg/default_tiles_x.png" width="256" height="64"/>
</tileset>
When I'm at the tileset node, how can I access the image node and its source attribute? My code is as follows:
public void LoadMaps(ContentManager content)
{
Dictionary<string, string> mapsToLoad = InitMapsToLoad();
foreach (KeyValuePair<string, string> mapToLoad in mapsToLoad)
{
Map map = new Map();
map.Name = Path.GetFileNameWithoutExtension(mapToLoad.Value);
reader = XmlReader.Create("Content/" + mapToLoad.Value);
while(reader.Read())
{
if(reader.NodeType == XmlNodeType.Element)
{
switch(reader.Name)
{
case "tileset":
if(!Tilesets.Any(ts => ts.Name == reader.GetAttribute("name")))
{
// handling the image node here
}
break;
}
}
}
}
}

I usually prefer to use LINQ to XML because I find it's API to be much easier to use than XmlReader, a comparison between the technologies here.
If all you need is getting source attribute value from image element this can be achieved easily:
var doc = XDocument.Load("something.xml");
var root = doc.DocumentElement;
var imageElements = root.Elements("image").ToList();
foreach (var imageElement in imageElements)
{
var sourceAttribute = imageElement.Attribute("source");
var sourceValue = sourceAttribute.Value;
//do something with the source value...
}
More about basic queries in LINQ to XML here.

I will suggest to create some classes that represents the Xml structure, something like this :
[XmlRoot(ElementName = "image")]
public class Image
{
[XmlAttribute(AttributeName = "source")]
public string Source { get; set; }
[XmlAttribute(AttributeName = "width")]
public string Width { get; set; }
[XmlAttribute(AttributeName = "height")]
public string Height { get; set; }
}
[XmlRoot(ElementName = "tileset")]
public class Tileset
{
[XmlElement(ElementName = "image")]
public Image Image { get; set; }
[XmlAttribute(AttributeName = "firstgid")]
public string Firstgid { get; set; }
[XmlAttribute(AttributeName = "name")]
public string Name { get; set; }
[XmlAttribute(AttributeName = "tilewidth")]
public string Tilewidth { get; set; }
[XmlAttribute(AttributeName = "tileheight")]
public string Tileheight { get; set; }
[XmlAttribute(AttributeName = "tilecount")]
public string Tilecount { get; set; }
[XmlAttribute(AttributeName = "columns")]
public string Columns { get; set; }
}
Then In some Utility class add the following method:
public static T DeserializeFromXml<T>(string xml)
{
if (string.IsNullOrEmpty(xml))
{
return default(T);
}
var serializer = new XmlSerializer(typeof(T));
T entity;
using (XmlReader reader = XmlReader.Create(new StringReader(xml)))
{
entity = (T)serializer.Deserialize(reader);
}
return entity;
}
Now you will be able to access to the Image object using the following code:
Tileset tileset=DeserializeFromXml<Tileset>(yourXmlContent);
// now you can access the image from the tileset instance 'tileset.Image.Source'

You are almost done. Add this to your code.
// handling the image node here
if (reader.ReadToDescendant("image"))
{
string source = reader.GetAttribute("source");
}

How to get value inside XML tag?

I have the follow XML structure:
<Document>
<Sectors>
<Sector>
SectorName1
<Subsectors>
<Subsector>Subsector1</Subsector>
<Subsector>Subsector2</Subsector>
</Subsectors>
</Sector>
<Sector>
SectorName2
<Subsectors>
<Subsector>Subsector1</Subsector>
<Subsector>Subsector2</Subsector>
</Subsectors>
</Sector>
</Sectors>
</Document>
Also I have classes for deserialize:
public class MetaDataXML
{
public class SectorXML
{
[XmlArrayItem(ElementName = "Sector")]
string SectorName { get; set; }
[XmlArray]
[XmlArrayItem(ElementName = "Subsector")]
public List<string> Subsectors { get; set; }
}
public List<SectorXML> Sectors { get; set; }
}
And part of code which do deserialize:
var xRoot = new XmlRootAttribute { ElementName = "Document", IsNullable = true };
var reader = new XmlSerializer(typeof(MetaDataXML), xRoot);
var data = (MetaDataXML)reader.Deserialize(streamXML);
After deserialization I successfully get subsectors velues, but I didn't get values for SectorName. How I need to organize my structure of class that I'll get values "SectorName1" and "SectorName2" for my string SectorName property?
I found that that this case it's a "Mixed Content". How we can parse this text values?

Whilst I am not entirely sure what it is you're trying to achieve here, I've made a few modifications to your XML class and provided some sample code below that is able to retrieve all of the information about a sector, including its name and the name of all the subsectors inside it.
XML Class:
namespace DocumentXml
{
[XmlRoot("Document")]
public class Document
{
[XmlArray("Sectors")]
[XmlArrayItem("Sector")]
public Sector[] Sectors { get; set; }
}
[XmlRoot("Sector")]
public class Sector
{
[XmlAttribute("SectorName")]
public string SectorName { get; set; }
[XmlArray("Subsectors")]
[XmlArrayItem("Subsector")]
public string[] Subsectors { get; set; }
}
}
Main Program Class:
namespace DocumentXml
{
class Program
{
static void Main(string[] args)
{
var path = #"D:\sandbox\DocumentXml\DocumentXml\Sample.xml";
var serializer = new XmlSerializer(typeof(Document));
var document = serializer.Deserialize(File.OpenRead(path)) as Document;
var sectors = document.Sectors;
foreach (var s in sectors)
{
Console.WriteLine($"Sector Name: {s.SectorName}");
foreach (var ss in s.Subsectors)
{
Console.WriteLine($"Subsector Name: {ss}");
}
Console.WriteLine();
}
Console.ReadKey();
}
}
}
Sample XML:
<Document>
<Sectors>
<Sector SectorName="SectorName1">
<Subsectors>
<Subsector>Subsector1</Subsector>
<Subsector>Subsector2</Subsector>
</Subsectors>
</Sector>
<Sector SectorName="SectorName2">
<Subsectors>
<Subsector>Subsector1</Subsector>
<Subsector>Subsector2</Subsector>
</Subsectors>
</Sector>
</Sectors>
</Document>
Output:
EDIT
Since the XML structure cannot be changed, this new class will preserve the structure and also allow you to get the value in question. XmlText returns everything inside the value so a custom set had to be used to ensure that the whitespace was correctly trimmed from it.
[XmlRoot("Document")]
public class MetaDataXml
{
[XmlArray("Sectors")]
[XmlArrayItem("Sector")]
public Sector[] Sectors { get; set; }
}
[XmlRoot("Sector")]
public class Sector
{
[XmlIgnore]
private string _sectorName;
[XmlText]
public string SectorName
{
get
{
return _sectorName;
}
set
{
_sectorName = value.Trim();
}
}
[XmlArray]
[XmlArrayItem(ElementName = "Subsector")]
public List<string> Subsectors { get; set; }
}
Sample Program:
class Program
{
static void Main(string[] args)
{
var path = #"D:\sandbox\DocumentXml\DocumentXml\Sample.xml";
using (var stream = File.OpenRead(path))
{
var deserializer = new XmlSerializer(typeof(MetaDataXml));
var data = (MetaDataXml)deserializer.Deserialize(stream);
foreach (var s in data.Sectors)
{
Console.WriteLine($"Sector Name: {s.SectorName}");
foreach (var ss in s.Subsectors)
{
Console.WriteLine($"Subsector Name: {ss}");
}
Console.WriteLine();
}
}
Console.ReadKey();
}
}

XML Parser Error in C#

I am trying to create a function to parse an XML file like this:
<?xml version="1.0" encoding="utf-8"?>
<list name="Grocery List" author="Ian" desc="Saturday grocery list">
<item color="black" done="false">Milk</item>
<item color="black" done="false">Eggs</item>
<item color="blue" done="false">Water</item>
</list>
It parses the attributes correctly, but it fails to return the values of the list items. Here is the function and class it uses:
class List
{
public string[] listItems;
public string[] colorArray;
public string[] doneArray;
public string listName;
public string listAuthor;
public string listDesc;
public string err;
}
Reader definition:
class ListReader
{
public List doListParse(string filename)
{
List l = new List();
int arrayCount = 0;
try
{
XmlReader r = XmlReader.Create(filename);
while (r.Read())
{
if (r.NodeType == XmlNodeType.Element && r.Name == "list")
{
//Get the attributes of the list
l.listName = r.GetAttribute("name");
l.listAuthor = r.GetAttribute("author");
l.listDesc = r.GetAttribute("desc");
while (r.NodeType != XmlNodeType.EndElement)
{
r.Read();
if (r.Name == "item")
{
r.Read();
if (r.NodeType == XmlNodeType.Text)
{
//Get The Attributes
l.colorArray[arrayCount] = r.GetAttribute("color");
l.doneArray[arrayCount] = r.GetAttribute("done");
//Get The Content
l.listItems[arrayCount] = r.Value.ToString();
arrayCount++;
}
r.Read();
}
}
}
}
}
catch (Exception e)
{
l.err = e.ToString();
}
return l;
}
}
When I execute the program, it gives this exception:
System.NullReferenceException: Object reference not set to an instance of an object.
What is going on here?

I'd recommend you using a serializer. The XmlSerializer class is pretty decent. It will simplify your code.
So start by defining the models that will map to this XML structure:
[XmlRoot("list")]
public class GroceryList
{
[XmlAttribute("name")]
public string Name { get; set; }
[XmlAttribute("author")]
public string Author { get; set; }
[XmlAttribute("desc")]
public string Description { get; set; }
[XmlElement("item")]
public Item[] Items { get; set; }
}
public class Item
{
[XmlAttribute("color")]
public string Color { get; set; }
[XmlAttribute("done")]
public bool Done { get; set; }
[XmlText]
public string Value { get; set; }
}
and then simply deserialize the XML:
class Program
{
static void Main()
{
var serializer = new XmlSerializer(typeof(GroceryList));
using (var reader = XmlReader.Create("groceriesList.xml"))
{
var list = (GroceryList)serializer.Deserialize(reader);
// you could access the list items here
}
}
}

You can use Linq To Xml.
var xElem = XDocument.Parse(xml).Element("list"); //or XDocument.Load(filename)
var list = new
{
Name = xElem.Attribute("name").Value,
Author = xElem.Attribute("author").Value,
Desc = xElem.Attribute("desc").Value,
Items = xElem.Elements("item")
.Select(e => new{
Color = e.Attribute("color").Value,
Done = (bool)e.Attribute("done"),
Value = e.Value,
})
.ToList()
};