We Keep Coding

Adding a new node (taking value from another xml file) inside a certain parent node?

I'm trying to create a program having the following steps:
1) Get all xml files from a user given path
2) Open each of the files (if any) and search for nodes <institution> where it is in the format <funding-source><institution-wrap><institution>...</institution></institution-wrap></funding-source>
3) Get the value of the nodes <institution> and search the exact value in the database xml inside the nodes <skosxl:literalForm xml:lang="...">
4) If found, get the attribute value of its parent node <skos:Concept rdf:about="..."> minus the string http://dx.doi.org/
5) Add a node <institution-id institution-id-type="fundref"> in the xml file after the <institution> node with the value like <funding-source><institution-wrap><institution>...</institution><institution-id institution-id-type="fundref">VALUE of the rdf:about attribute</institution-id></institution-wrap></funding-source>
Here is a sample input file and the desired output for that file.
What I have tried:
string pathToUpdatedFile = #"D:\test\Jobs";
var files=Directory.GetFiles(pathToUpdatedFile,"*.xml");
foreach (var file in files)
{
var fundingDoc = XDocument.Load(#"D:\test\database.xml");
XNamespace rdf=XNamespace.Get("http://www.w3.org/1999/02/22-rdf-syntax-ns#");
XNamespace skosxl = XNamespace.Get("http://www.w3.org/2008/05/skos-xl#");
XNamespace skos=XNamespace.Get("http://www.w3.org/2004/02/skos/core#");
var targetAtt = fundingDoc.Descendants(skos+"Concept").Elements(skosxl+"prefLabel")
.ToLookup(s => (string)s.Element(skosxl+"literalForm"), s => (string)s.Parent.Attribute(rdf+"about"));
XDocument outDoc = XDocument.Parse(File.ReadAllText(file),LoadOptions.PreserveWhitespace);
foreach (var f in outDoc.Descendants("funding-source").Elements("institution-wrap"))
{
if (f.Element("institution-id") == null)
{
var name = (string)f.Element("institution");
var x = targetAtt[name].FirstOrDefault(); // just take the first one
if (x != null)
f.Add(new XElement("institution-id", new XAttribute("institution-id-type","fundref"),x.Substring(#"http://dx.doi.org/".Length)));
}
outDoc.Save(file);
}
Console.ReadLine();
But it is not working...Can somebody help...

See code below :
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Xml;
using System.Xml.Linq;
using System.Data;
using System.Data.OleDb;
namespace ConsoleApplication31
{
class Program
{
const string FILENAME = #"c:\temp\test.xml";
const string DATABASE = #"c:\temp\test1.xml";
static void Main(string[] args)
{
XDocument doc = XDocument.Load(FILENAME);
XElement article = doc.Root;
XNamespace ns = article.GetDefaultNamespace();
XDocument docDatabase = XDocument.Load(DATABASE);
XElement rdf = docDatabase.Root;
XNamespace nsSkosxl = rdf.GetNamespaceOfPrefix("skosxl");
XNamespace nsRdf = rdf.GetNamespaceOfPrefix("rdf");
List<XElement> prefLabels = rdf.Descendants(nsSkosxl + "prefLabel").ToList();
Dictionary<string, List<string>> dictLabels = prefLabels.GroupBy(x => (string)x.Descendants(nsSkosxl + "literalForm").FirstOrDefault(), y => (string)y.Element(nsSkosxl + "Label").Attribute(nsRdf + "about"))
.ToDictionary(x => x.Key, y => y.ToList());
List<XElement> fundingSources = article.Descendants(ns + "funding-source").ToList();
foreach (XElement fundingSource in fundingSources)
{
XElement institutionWrap = fundingSource.Element(ns + "institution-wrap");
string institution = (string)fundingSource;
if (dictLabels.ContainsKey(institution))
{
institutionWrap.Add(new XElement("institution-id", new object[] {
new XAttribute("institution-id-type","fundref"),
dictLabels[institution]
}));
}
else
{
Console.WriteLine("Dictionary doesn't contain : '{0}'", institution);
}
}
Console.ReadLine();
}
}
}

I think this is what you are looking for (MODIFIED jdweng's CODE A LITTLE)
const string FILENAME = #"c:\temp\test.xml";
const string DATABASE = #"c:\temp\test1.xml";
public static void Main(string[] args)
{
XDocument doc = XDocument.Load(FILENAME);
XElement article = doc.Root;
XNamespace ns = article.GetDefaultNamespace();
XDocument docDatabase = XDocument.Load(DATABASE);
XElement rdf = docDatabase.Root;
XNamespace nsSkosxl = rdf.GetNamespaceOfPrefix("skosxl");
XNamespace nsSkos = rdf.GetNamespaceOfPrefix("skos");
XNamespace nsRdf = rdf.GetNamespaceOfPrefix("rdf");
List<XElement> prefLabels = rdf.Descendants(nsSkos + "Concept").ToList();
Dictionary<string, List<string>> dictLabels = prefLabels.GroupBy(x => (string)x.Descendants(nsSkosxl + "literalForm").FirstOrDefault(), y => (string)y.Parent.Element(nsSkos+"Concept").Attribute(nsRdf + "about").Value.Substring(18))
.ToDictionary(x => x.Key, y => y.ToList());
List<XElement> fundingSources = article.Descendants(ns + "funding-source").ToList();
foreach (XElement fundingSource in fundingSources)
{
XElement institutionWrap = fundingSource.Element(ns + "institution-wrap");
string institution = (string)fundingSource;
if (dictLabels.ContainsKey(institution))
{
institutionWrap.Add(new XElement("institution-id", new object[] {
new XAttribute("institution-id-type","fundref"),
dictLabels[institution]
}));
}
}
doc.Save(FILENAME);
Console.WriteLine("Done");
Console.ReadLine();
}

Deleted xml elements are not being removed

In the following snippet the final string "removed" still has the deleted elements. I am converting to byte[] first because the final implementation input will be in that form. I am looping thru the saved nodes and deleting them for element document. What gives? All ideas greatly appreciated.
static void Main(string[] args)
{
var str =
#"
<CustomerCareReport xmlns='http://schemas.datacontract.org/2004/07/Foo.Bar.Frameworks.Reporting.Stack.Infrastructure.DataObjects.FireEms' xmlns:i='http://www.w3.org/2001/XMLSchema-instance'>
<OtherInformation>
<Documents xmlns:a='http://schemas.datacontract.org/2004/07/Foo.Bar.Frameworks.Reporting.Stack.Infrastructure.DataObjects.Documents'>
<a:Document>
<a:Contents>Z2dn</a:Contents>
<a:Description>yoyo</a:Description>
<a:Id>1</a:Id>
</a:Document>
<a:Document>
<a:Contents>ZmhmaA0KZmZmDQpmamZqZmpmDQo=</a:Contents>
<a:Description>test 2</a:Description>
<a:Id>2</a:Id>
</a:Document>
</Documents>
</OtherInformation>
</CustomerCareReport>
";
var element = XElement.Parse(str);
XNamespace ns = element.Name.Namespace;
// convert to bytes firstbecause final implementation input is byte array
byte[] bytes = Encoding.ASCII.GetBytes(str);
using (var stream = new MemoryStream(bytes))
{
var deleteMarked = new List<XElement>();
var xelement = XElement.Load(stream);
var docs = xelement
.Descendants(ns + "Documents");
foreach (XElement doc in docs.Descendants())
{
if (doc.Name.LocalName.Equals("Document"))
{
var delDoc = doc;
deleteMarked.Add(delDoc);
}
}
foreach (var deldoc in deleteMarked)
{
foreach (var node in deldoc.Elements())
{
node.Remove();
}
}
if (deleteMarked.Count > 0)
{
stream.Close();
bytes = stream.ToArray();
}
var removed = System.Text.Encoding.Default.GetString(bytes);
Console.WriteLine(removed);
}
}

Issue with processing an xml file in c#

I have a 5gb xml file which need to be processed. So, I used XMLReader, but I am having hard time with processing files.
I have following part and I want to take the values of levelid,levelUl,primaryCode,primaryPower from sections coming under <ab:pin id="1022">,<ab:pin id="1023">,<ab:pin id="1024"> etc. But the problem I am now facing is there are different sections having the same element names like levelid,levelUl,primaryCode,primaryPower etc. with different values and I am getting incorrect values.
How do I correct to correct my code? Following is part of 5 GB xml file
<ab:pin id="1022">
<ab:attributes>
<ab:levelid>1022</ab:levelid>
<ab:levelUl>9837</ab:levelUl>
<ab:primaryCode>25</ab:primaryCode>
<ab:primaryPower>330</ab:primaryPower>
.
.
.
.
<ab:pin id="1023">
<ab:attributes>
<ab:levelid>1023</ab:levelid>
<ab:levelUl>9833</ab:levelUl>
<ab:primaryCode>35</ab:primaryCode>
<ab:primaryPower>340</ab:primaryPower>
Following is the code what i have done
XmlReader reader = XmlReader.Create(path);
reader.MoveToContent();
string nsUn = reader.LookupNamespace("ab");
while (!reader.EOF)
{
reader.ReadToFollowing("levelid", nsUn);
if (!reader.EOF)
{
XElement cell = (XElement)XElement.ReadFrom(reader);
level_id = cell.Value;
ins3gericson.Add(new TestField("level_id", level_id, 2));
}
reader.ReadToFollowing("levelUl", nsUn);
if (!reader.EOF)
{
XElement cell = (XElement)XElement.ReadFrom(reader);
ins3gericson.Add(new TestField("levelUl", cell.Value, 2));
}
reader.ReadToFollowing("primaryCode", nsUn);
if (!reader.EOF)
{
XElement cell = (XElement)XElement.ReadFrom(reader);
ins3gericson.Add(new TestField("primaryCode", cell.Value, 2));
}
reader.ReadToFollowing("primaryPower", nsUn);
if (!reader.EOF)
{
XElement cell = (XElement)XElement.ReadFrom(reader);
ins3gericson.Add(new TestField("primaryPower", cell.Value, 2));
}

Here is my suggestion:
using (XmlReader xr = XmlReader.Create("input.xml"))
{
xr.MoveToContent();
XNamespace ab = xr.LookupNamespace("ab");
while (xr.Read())
{
if (xr.NodeType == XmlNodeType.Element && xr.NamespaceURI == ab && xr.LocalName == "pin")
{
XElement pin = (XElement)XNode.ReadFrom(xr);
var data = from atts in pin.Elements(ab + "attributes") select new {
levelid = (string)atts.Element(ab + "levelid"),
levelUl = (string)atts.Element(ab + "levelUl"),
primaryCode = (string)atts.Element(ab + "primaryCode"),
primaryPower = (string)atts.Element(ab + "primaryPower")
};
Console.WriteLine("levelId: {0}; levelUl: {1}, ...", data.First().levelid, data.First().levelUl); // store/output values here
}
}
}
Obviously it all depends on how large the ab:pin elements are, but normally with huge XML input the individual elements fit well into memory. And be careful with the XmlReader, if you have adjacent ab:pin elements without any whitespace, then the above might skip an element, so there the code would need some more finetuning, along the lines of
using (XmlReader xr = XmlReader.Create("../../XMLFile1.xml"))
{
xr.MoveToContent();
XNamespace ab = xr.LookupNamespace("ab");
while (xr.Read())
{
while (xr.NodeType == XmlNodeType.Element && xr.NamespaceURI == ab && xr.LocalName == "pin")
{
XElement pin = (XElement)XNode.ReadFrom(xr);
var data = from atts in pin.Elements(ab + "attributes") select new {
levelid = (string)atts.Element(ab + "levelid"),
levelUl = (string)atts.Element(ab + "levelUl"),
primaryCode = (string)atts.Element(ab + "primaryCode"),
primaryPower = (string)atts.Element(ab + "primaryPower")
};
Console.WriteLine("levelId: {0}; levelUl: {1}, ...", data.First().levelid, data.First().levelUl);
}
}
}

Best method for comparing XML with string

I am looking for the best way to compare XML data with a string.
the data is stored in a xml called test.xml, and must be compared with the name descendant, if there is a match more info from the xml must be added to a textbox and picture box.
My ( working ) code:
var xmlDocument = XDocument.Load("test.xml"); // XML koppellen
var key1 = xmlDocument.Descendants("NAME"); // XML filepath
var key2 = xmlDocument.Descendants("TITLE"); // XML titel
var key3 = xmlDocument.Descendants("BRAND"); // XML afbeelding
var key4 = xmlDocument.Descendants("TYPE"); // XML merk
var key5 = xmlDocument.Descendants("SOORT"); // XML type
var key6 = xmlDocument.Descendants("NAAM"); // XML naam
List<string> file = new List<string>();
List<string> title = new List<string>();
List<string> brand = new List<string>();
List<string> type = new List<string>();
List<string> soort = new List<string>();
List<string> naam = new List<string>();
int i = 0;
foreach (var key in key1)
{
file.Add(key.Value.Trim());
}
foreach (var key in key2)
{
title.Add(key.Value.Trim());
}
foreach (var key in key3)
{
brand.Add(key.Value.Trim());
}
foreach (var key in key4)
{
type.Add(key.Value.Trim());
}
foreach (var key in key5)
{
soort.Add(key.Value.Trim());
}
foreach (var key in key6)
{
naam.Add(key.Value.Trim());
}
foreach (var Name in naam)
{
if (textBox3.Text.ToString() == Name.ToString())
{
PDFLocation = file[i].ToString();
pictureBox1.Image = pdfhandler.GetPDFthumbNail(PDFLocation);
textBox4.Text =
title[i].ToString() + "\r\n" +
brand[i].ToString() + "\r\n" +
type[i].ToString() + "\r\n" +
soort[i].ToString() + "\r\n" +
textBox3.Text + "\r\n";
}
i++;
}
]
I think this is not the best way to do it, but cant see a better way....
Update: solution:
foreach (XElement element in xmlDocument.Descendants("PDFDATA"))
{
if (textBox3.Text.ToString() == element.Element("NAAM").Value.Trim())
{
PDFLocation = element.Element("NAME").Value.ToString();
pictureBox1.Image = pdfhandler.GetPDFthumbNail(PDFLocation);
textBox4.Text =
element.Element("TITLE").Value + "\r\n" +
element.Element("BRAND").Value + "\r\n";
break;
}
}

Instead of thinking of the xml and a bunch of individual lists of data, it helps to think of it more as objects. Then you can loop through each element one at a time and don't need to split it up into individual lists. This not only removes duplicate code but more importantly creates a better abstraction of the data you are working with. This makes it easier to read and understand what the code is doing.
foreach (XElement element in xmlDocument.Elements())
{
if (textBox3.Text.ToString() == element.Element("NAAM").Value)
{
PDFLocation = element.Element("NAAM").Value;
pictureBox1.Image = pdfhandler.GetPDFthumbNail(PDFLocation);
textBox4.Text =
element.Element("Title").Value + "\r\n" +
element.Element("Brand").Value + "\r\n" +
element.Element("Type").Value + "\r\n"
// access rest of properties...
}
}

LINQ to read XML file and print results

I got the following XML file (Data.xml):
<root>
<sitecollection name="1A">
<site name="1B">
<maingroup name="1C">
<group name="1D"> </group>
</maingroup>
</site>
</sitecollection>
<sitecollection name="2A">
<site name="2B">
<maingroup name="2C">
<group name="2D"> </group>
</maingroup>
</site>
</sitecollection>
</root>
And I need to print all the all the child elements in this format:
1A
1B
1C
1D
2A
2B
2C
2D
I have the following code so far which needs some adjustment. I could also change it completely if there's an easier method. Thanks for your help
class xmlreader
{
public static void Main()
{
// Xdocument to read XML file
XDocument xdoc = XDocument.Load("Data.xml");
var result = new System.Text.StringBuilder();
var lv1s = from lv1 in xdoc.Descendants("sitecollection")
select new
{
sitecollection = lv1.Attribute("name").Value,
maingroup = lv1.Descendants("group")
};
var lv2s = from lv2 in xdoc.Descendants("site")
select new
{
site = lv2.Attribute("name").Value,
sitetittle = lv2.Descendants()
};
var lv3s = from lv3 in xdoc.Descendants("maingroup")
select new
{
maingroup = lv3.Attribute("name").Value,
};
var lv4s = from lv4 in xdoc.Descendants("group")
select new
{
grouppage = lv4.Attribute("name").Value,
};
// Loop to print results
foreach (var lv1 in lv1s)
{
result.AppendLine(lv1.sitecollection);
foreach (var lv2 in lv2s)
{
result.AppendLine(" " + lv2.Attribute("name").Value);
foreach (var lv3 in lv3s)
{
result.AppendLine(" " + lv3.Attribute("name").Value);
foreach (var lv4 in lv4s)
{
result.AppendLine(" " + lv4.Attribute("name").Value);
}
}
}
}
}
}

With such a uniform hierarchy, recursion can do the job with a lot less code:
void PrintNames(StringBuilder result, string indent, XElement el)
{
var attr = el.Attributes("name");
if (attr != null)
{
result.Append(indent);
result.Append(attr.Value);
result.Append(System.Environment.NewLine);
}
indent = indent + " ";
foreach(var child in el.Elements())
{
PrintNames(result, indent, child);
}
}
...
var sb = new StringBuilder();
PrintNames(sb, String.Empty, xdoc.Root);

How about the following, find all elements with a name attribute, then add spaces based on their depth.
var result = new System.Text.StringBuilder();
var namedElements = doc.Descendants().Where(el => el.Attributes("name")!=null);
foreach(var el in namedElements)
{
int depth = el.Ancestors().Count();
for (int i=0;i<depth;i++)
result.Append(" ");
result.Append(el.Attributes("name").Value);
result.Append(System.Environment.NewLine);
}
NOTE: The above is from memory, so please check the syntax!