How to format xml using linq? - c#

Here i am creating a xml using linq and not getting in the required format.Here is my code
List<string> listvalue = new List<string>();
listvalue.Add("http://example.com/sample.html");
listvalue.Add("http://example.com/new.html");
foreach (string url in listvalue)
{
var document = new HtmlWeb().Load(url);
var urls = document.DocumentNode.Descendants("img")
.Select(e => e.GetAttributeValue("src", null))
.Where(s => !String.IsNullOrEmpty(s));
List<string> asList = urls.ToList();
GenerateXml(url, asList);
}
and
protected void GenerateXml(string url, List<string> listitems) //generateXml
{
XNamespace nsSitemap = "http://www.sitemaps.org/schemas/sitemap/0.9";
XNamespace nsImage = "http://www.google.com/schemas/sitemap-image/1.1";
var sitemap = new XDocument(new XDeclaration("1.0", "UTF-8", ""));
var urlSet = new XElement(nsSitemap + "urlset",
new XAttribute("xmlns", nsSitemap),
new XAttribute(XNamespace.Xmlns + "image", nsImage),
new XElement(nsSitemap + "url",
new XElement(nsSitemap + "loc", url),
from urlNode in listitems
select new XElement(nsImage + "image",
new XElement(nsImage + "loc", urlNode)
)));
sitemap.Add(urlSet);
sitemap.Save(System.Web.HttpContext.Current.Server.MapPath("/Static/sitemaps/Sitemap-image.xml"));
}
I need it in the below format
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:image="http://www.google.com/schemas/sitemap-image/1.1">
<url>
<loc>http://example.com/sample.html</loc>
<image:image>
<image:loc>http://example.com/image.jpg</image:loc>
</image:image>
<image:image>
<image:loc>http://example.com/photo.jpg</image:loc>
</image:image>
</url>
<url>
<loc>http://example.com/new.html</loc>
<image:image>
<image:loc>http://example.com/newimage.jpg</image:loc>
</image:image>
<image:image>
<image:loc>http://example.com/newphoto.jpg</image:loc>
</image:image>
</url>
</urlset>
But here i am getting a single url tag. How to achieve this? Any suggestion?

It sounds like this is really just a case of wanting to fetch all the URLs (from all the source documents) before you call GenerateXml at all - and remember where each one came from. That's as simple as:
var sources = new List<string>
{
"http://example.com/sample.html",
"http://example.com/new.html"
};
var imagesBySource = sources
.ToDictionary(source => source,
source => new HtmlWeb().Load(url)
.DocumentNode.Descendants("img")
.Select(e => e.GetAttributeValue("src", null))
.Where(s => !String.IsNullOrEmpty(s))
.ToList());
GenerateXml(imagesBySource);
You'd then need to change GenerateXml to take a Dictionary<string, List<string>>. Something like (untested):
protected void GenerateXml(Dictionary<string, List<string>> imagesByUrl)
{
XNamespace nsSitemap = "http://www.sitemaps.org/schemas/sitemap/0.9";
XNamespace nsImage = "http://www.google.com/schemas/sitemap-image/1.1";
var sitemap = new XDocument(new XDeclaration("1.0", "UTF-8", ""));
var urlSet = new XElement(nsSitemap + "urlset",
new XAttribute("xmlns", nsSitemap),
new XAttribute(XNamespace.Xmlns + "image", nsImage),
imagesByUrl.Select(entry =>
new XElement(nsSitemap + "url",
new XElement(nsSitemap + "loc", entry.Key),
from urlNode in entry.Value
select new XElement(nsImage + "image",
new XElement(nsImage + "loc", urlNode)
)
)
);
sitemap.Add(urlSet);
var path = HttpContext.Current.Server.MapPath("/Static/sitemaps/Sitemap-image.xml");
sitemap.Save(path);
}
Note that this won't guarantee that the order of the sources is preserved. If you need that, you should probably create a class with Url and Images properties, and pass a list of those to GenerateXml instead.

Related

Cannot create XML where the XElement value contains ":"

I have the following code:
private string GetXmlBody()
{
XNamespace ns = "http://schemas.xmlsoap.org/soap/envelope/";
XNamespace xsdNs = "http://www.w3.org/2001/XMLSchema";
XNamespace xsiNs = "http://www.w3.org/2001/XMLSchema-instance";
XNamespace outNs = "http://soap.sforce.com/2005/09/outbound";
XNamespace sfNs = "urn:sobject.enterprise.soap.sforce.com";
XDocument requestXml = new XDocument(
new XElement(ns + "Envelope", new XAttribute(XNamespace.Xmlns + "soapenv", ns), new XAttribute(XNamespace.Xmlns + "xsd", xsdNs), new XAttribute(XNamespace.Xmlns + "xsi", xsiNs),
new XElement(ns + "Body",
new XElement(outNs + "notifications", new XAttribute("xmlns", outNs),
new XElement(outNs + "OrganizationId", runInfo.OrgId),
new XElement(outNs + "SessionId", runInfo.SessionId),
new XElement(outNs + "EnterpriseUrl", runInfo.Location),
new XElement(outNs + "Notification",
new XElement(outNs + "Id", "04l0H000014TY73QAG"),
new XElement(outNs + "sObject", new XAttribute(XNamespace.Xmlns + "sf", sfNs), new XAttribute(xsiNs + "type", "sf:" + runInfo.RecordType),
new XElement(sfNs + "Id", runInfo.RecordId),
new XElement(sfNs + runInfo.Field, runInfo.FieldValue)
)
)
)
)
)
);
return requestXml.ToString();
}
Which will generate XML needed however I'm running into the following error:
System.Xml.XmlException : The ':' character, hexadecimal value 0x3A, cannot be included in a name.
due to the value of runInfo.FieldValue which contains :. For Example the value may look like:
Opportunity:006i000000sidsh;Account:;userId:a016S00000sjsiq;sandbox:true
So far all the solutions or similar problems that I've seen revolve around producing the correct element name, my problem is around the value. If for instance I remove the : from the runInfo.FieldValue variable then the expected XML is produced.
Any thoughts on how to get around this? I've tried URL encoding the string but that just leads to a similar error except it complains about % values.

Error parsing xml syntax error

I have the following code below. I am getting an error "the character ':' hexadecimal value 0x3A cannot be included in a name" Can anyone tell me how to fix this?
Thanks Below is the entire code
public static XDocument GenerateXMLSpreadSheet(DataTable tbl)
{
new XDocument(
new XDeclaration("1.0", "utf-8", "yes"),
new XProcessing**Instruction("mso-application", "Excel.Sheet"),
new XElement("Workbook",
new XAttribute("xmlns", "urn:schemas-microsoft-com:office:spreadsheet"),
new XAttribute("xmlns:ss", "urn:schemas-microsoft-
com:office:spreadsheet"),
new XElement("Worksheet", new XAttribute("ss:Name",
tbl.TableName),
new XElement("Table", GetRows(tbl)
)
)
)
);
return xmlssDoc;
)
public static Object[] GetRows(DataTable tbl)
{
// generate XElement rows for each row in the database.
// generate from the bottom-up.
// start with the cells.
XElement[] rows = new XElement[tbl.Rows.Count];
int r = 0;
foreach (DataRow row in tbl.Rows)
{
// create the array of cells to add to the row:
XElement[] cells = new XElement[tbl.Columns.Count];
int c = 0;
foreach (DataColumn col in tbl.Columns)
{
cells[c++] =
new XElement("Cell",
new XElement("Data", new XAttribute("ss:Type", "String"),
new XText(row[col].ToString())));
}
rows[r++] = new XElement("Row", cells);
}
// return the array of rows.
return rows;
}
Basically, that's not how you handle namespaces in LINQ to XML. You never specify a string with a colon in - instead, you build up an XName from an XNamespace and a string.
The good news is that LINQ to XML handling of namespaces is simple. Here's a complete example:
using System;
using System.Xml.Linq;
public class Test
{
static void Main(string[] args)
{
XNamespace ns = "urn:schemas-microsoft-com:office:spreadsheet";
var doc = new XDocument(
new XDeclaration("1.0", "utf-8", "yes"),
new XProcessingInstruction("mso-application", "Excel.Sheet"),
new XElement(ns + "Workbook",
new XAttribute("xmlns", ns),
new XAttribute(XNamespace.Xmlns + "ss", ns),
new XElement(ns + "Worksheet",
new XAttribute(ns + "Name", "my-table-name"),
new XElement(ns + "Table")
)
)
);
Console.WriteLine(doc);
}
}
Output (reformatted for clarity):
<?mso-application Excel.Sheet?>
<ss:Workbook
xmlns="urn:schemas-microsoft-com:office:spreadsheet"
xmlns:ss="urn:schemas-microsoft-com:office:spreadsheet">
<ss:Worksheet ss:Name="my-table-name">
<ss:Table />
</ss:Worksheet>
</ss:Workbook>
Note how you need to specify the namespace for all the elements and attributes.
Because you've specified an explicit prefix for the namespace, LINQ to XML uses it everywhere. If you remove this part:
new XAttribute(XNamespace.Xmlns + "ss", ns)
... then the namespace for elements will be defaulted, and LINQ to XML will generate a prefix for the attributes that need it explicitly specified (as attributes don't default their namespaces).
Then the output is (for example):
<?mso-application Excel.Sheet?>
<Workbook xmlns="urn:schemas-microsoft-com:office:spreadsheet">
<Worksheet p2:Name="my-table-name" xmlns:p2="urn:schemas-microsoft-com:office:spreadsheet">
<Table />
</Worksheet>
</Workbook>
The problem is how you defined namespaces.
To work with namespaces you may get one by calling XNamespace.Get("the namespace") and using this everywhere you want.
And for xmlns you may use static property XNamespace.Xmlns.
So the final code will look like:
new XDocument(
new XDeclaration("1.0", "utf-8", "yes"),
new XProcessingInstruction("mso-application", "Excel.Sheet"),
new XElement("Workbook",
new XAttribute("xmlns", ns),
new XAttribute(XNamespace.Xmlns + "ss", ns),
new XElement("Worksheet", new XAttribute(ns + "Name",
tbl.TableName),
new XElement("Table", GetRows(tbl)
)
)
)
);

How to add xmlns to xml document?

I'm trying to create a fairly simple XML document that looks like this.
<?xml version="1.0" encoding="UTF-8"?>
<employees xmlns="http://website.com/xsd/MQ">
<employee>
<id>00122731</id>
<first-name>LUIS</first-name>
<last-name>GARCIA</last-name>
<subarea>4100</subarea>
<cost-center>904</cost-center>
<email-address>L.GARCIA#EMAIL.COM</email-address>
</employee>
</employees>
I was able to get the basics by using this code but I need to add the xmlns attribute and I'm not figuring out how to do that.
var xmlDoc = new XElement("employees",
from e in listEmployees
select new XElement("employee",
new XElement("id", e.EmployeeId),
new XElement("first-name", e.FirstName),
new XElement("last-name", e.LastName),
new XElement("subarea", e.SubArea),
new XElement("cost-center", e.CostCenter),
new XElement("email-address", e.EmailAddress)));
This is my attempt to add it but I get an error that this would cause and invalid structure.
XDocument xmlDoc = new XDocument(
new XElement("employees",
new XAttribute("xmlns", "http://website/xsd/MQ")),
from e in listEmployees
select new XElement("employee",
new XElement("id", e.EmployeeId),
new XElement("first-name", e.FirstName),
new XElement("last-name", e.LastName),
new XElement("subarea", e.SubArea),
new XElement("cost-center", e.CostCenter),
new XElement("email-address", e.EmailAddress))
);
UPDATE
Based on the link provided below this is what I came up with that worked.
XNamespace ns = "http://website/xsd/MQ";
var xmlDoc = new XElement(ns + "employees",
from e in listEmployees
select new XElement("employee",
new XElement("id", e.EmployeeId),
new XElement("first-name", e.FirstName),
new XElement("last-name", e.LastName),
new XElement("subarea", e.SubArea),
new XElement("cost-center", e.CostCenter),
new XElement("email-address", e.EmailAddress)));
You need to include the namespace on all of your elements, not just the top one:
XNamespace ns = "http://website/xsd/MQ";
var xmlDoc = new XElement(ns + "employees",
from e in listEmployees
select new XElement(ns + "employee",
new XElement(ns + "id", e.EmployeeId),
new XElement(ns + "first-name", e.FirstName),
new XElement(ns + "last-name", e.LastName),
new XElement(ns + "subarea", e.SubArea),
new XElement(ns + "cost-center", e.CostCenter),
new XElement(ns + "email-address", e.EmailAddress)
)
);
If that's too repetitive for you, you could make a convenience method:
XNamespace ns = "http://website/xsd/MQ";
private static XElement MQElement(string name, object contents)
{
return new XElement(ns + name, contents);
}
then use it:
var xmlDoc = MQElement("employees",
from e in listEmployees
select MQElement("employee",
MQElement("id", e.EmployeeId),
MQElement("first-name", e.FirstName),
MQElement("last-name", e.LastName),
MQElement("subarea", e.SubArea),
MQElement("cost-center", e.CostCenter),
MQElement("email-address", e.EmailAddress)
)
);
One more option to achieve same result is to construct XElement ignoring namespaces completely and then add them in separate code:
foreach (XElement e in xmlDoc.DescendantsAndSelf())
{
if (e.Name.Namespace == "")
{
e.Name = ns + e.Name.LocalName;
}
}

How to generate xml and format it from object in c#?

Here I am trying to format XML from a list and I am not getting the proper format. Here is my code:
protected void GenerateXml(string url, List<string> listitems) //generateXml
{
XNamespace nsXhtml = "http://www.w3.org/1999/xhtml";
XNamespace nsSitemap = "http://www.sitemaps.org/schemas/sitemap/0.9";
XNamespace nsImage = "http://www.google.com/schemas/sitemap-image/1.1";
var sitemap = new XDocument(new XDeclaration("1.0", "UTF-8", ""));
var urlSet =
new XElement(
nsSitemap + "urlset",
new XAttribute("xmlns", nsSitemap),
new XAttribute(XNamespace.Xmlns + "image", nsXhtml),
from urlNode in listitems
select
new XElement(
nsSitemap + "url",
new XElement(nsSitemap + "loc", url),
new XElement(nsSitemap + "image",
new XElement(nsSitemap + "imageloc", urlNode))));
sitemap.Add(urlSet);
sitemap.Save(System.Web.HttpContext.Current.Server.MapPath("/Static/sitemaps/Sitemap-image.xml"));
}
... and getting the format like this:
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:image="http://www.w3.org/1999/xhtml">
<url>
<loc>http://example.com/intl/cars/new-models/the-new-s90</loc>
<image>
<imageloc>http://example.com/static/images/volvo-logo-scaled.png</imageloc>
</image>
</url>
<url>
<loc>http://example.com/intl/cars/new-models/the-new-s90</loc>
<image>
<imageloc>http://assets.example.com/intl/~/media/images/galleries/new-cars/packshots/small/allnew_xc90-side_2.png</imageloc>
</image>
</url>
</urlset>
But I need in this format:
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
xmlns:image="http://www.google.com/schemas/sitemap-image/1.1">
<url>
<loc>http://example.com/sample.html</loc>
<image:image>
<image:loc>http://example.com/image.jpg</image:loc>
</image:image>
<image:image>
<image:loc>http://example.com/photo.jpg</image:loc>
</image:image>
</url>
</urlset>
Any suggestion?
In addition to properly handling the multiple nested elements, you never assigned the image prefix to the elements that are supposed to have them, you continue to use the global namespace:
new XElement(nsSitemap + "image",
new XElement(nsSitemap + "imageloc", urlNode)
nsSitemap should be nsImage, and "imageloc" should be "loc".
A couple minor tweaks to your code will get you what you're looking for:
protected void GenerateXml(string url, List<string> listitems) //generateXml
{
XNamespace nsSitemap = "http://www.sitemaps.org/schemas/sitemap/0.9";
XNamespace nsImage = "http://www.google.com/schemas/sitemap-image/1.1";
var sitemap = new XDocument(new XDeclaration("1.0", "UTF-8", ""));
var urlSet = new XElement(nsSitemap + "urlset",
new XAttribute("xmlns", nsSitemap),
new XAttribute(XNamespace.Xmlns + "image", nsImage),
new XElement(nsSitemap + "url",
new XElement(nsSitemap + "loc", url),
from urlNode in listitems
select new XElement(nsImage + "image",
new XElement(nsImage + "loc", urlNode)
)));
sitemap.Add(urlSet); sitemap.Save(System.Web.HttpContext.Current.Server.MapPath("/Static/sitemaps/Sitemap-image.xml"));
}
Notice the following changes:
new XAttribute(XNamespace.Xmlns + "image", nsImage);
This sets the namespace correctly to mach your expected output.
new XElement(nsImage + "image",
new XElement(nsImage + "loc", urlNode)
This sets the image prefix correctly.
Notice how "loc" and "url" were moved to before the from query.
The above code results in the following output XML:
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:image="http://www.google.com/schemas/sitemap-image/1.1">
<url>
<loc>http://example.com/sample.html</loc>
<image:image>
<image:loc>http://example.com/image.jpg</image:loc>
</image:image>
<image:image>
<image:loc>http://example.com/photo.jpg</image:loc>
</image:image>
</url>
</urlset>

generating KML file using C# and LINQ with a recursive function

I am trying to create a KML file dynamically in C#. I have wrote a recursive function to do this. However the result of output has a bit problem. The problem is the position of closing tags of all placemarks. I am really confused. Please tell me where am I making mistake in the recursive function???
My code:
private void xmlBuild()
{
XDocument doc = new XDocument(
new XDeclaration("1.0", "utf-8", ""),
new XComment("This is comment by me"),
new XElement(ns+"kml",
new XElement(ns+"Document", rec_build())));
doc.Save(Server.MapPath(#"~\App_Data\markers2.xml"));
}
private XElement rec_build()
{
if (iteration != 0)
{
iteration -= 1;
return final_rec = new XElement(ns + "Placemark",
new XAttribute("id", "1"),
new XElement(ns + "title", "something"),
new XElement(ns + "description", "something"),
new XElement(ns + "LookAt",
new XElement(ns + "Longitude", "49.69"),
new XElement(ns + "Latitude", "32.345")), new XElement(ns + "Point", new XElement(ns + "coordinates", "49.69,32.345,0")),rec_build());
}
else
{
return null;
}
}
and this is the output for iteration value of 2: (please notice the closing tags of placemark id=1 at the end of file. It should be before the starting tag of placemark id=2!
<?xml version="1.0" encoding="utf-8"?>
<!--This is comment by me-->
<kml xmlns="http://earth.google.com/kml/2.2">
<Document>
<Placemark id="1">
<title>something</title>
<description>something</description>
<LookAt>
<Longitude>49.69</Longitude>
<Latitude>32.345</Latitude>
</LookAt>
<Point>
<coordinates>49.69,32.345,0</coordinates>
</Point>
<Placemark id="1">
<title>something</title>
<description>something</description>
<LookAt>
<Longitude>49.69</Longitude>
<Latitude>32.345</Latitude>
</LookAt>
<Point>
<coordinates>49.69,32.345,0</coordinates>
</Point>
</Placemark>
</Placemark>
</Document>
</kml>
So the problem is each time you recurse, you are adding the element to the newly created item. It seems that a loop would work better.
Essentially code is doing this:
set up the kml outbody
1st call and add element (element 1) to kml outerboy
2nd call add element (element 2) to (element 1)
3rd call add element (element 3) to (element 2).
If you wanted to do a recursive method rather then the looping mechanism, pass in a reference to the outer kml .
The recursive is more confusing if this is exactly how it works
(Sorry if I have an extra or missing parenthesis, comma, or other item. I don't have VS installed on this)
Looping:
private void xmlBuild()
{
XElement documentElement = new XElement(ns + "Document");
for (int i = 0; i < 2; i++)
{
documentElement.Add(rec_build());
}
XDocument doc = new XDocument(
new XDeclaration("1.0", "utf-8", ""),
new XComment("This is comment by me"),
new XElement(ns + "kml", documentElement));
doc.Save(Server.MapPath(#"~\App_Data\markers2.xml"));
}
private XElement rec_build()
{
return new XElement(ns + "Placemark",
new XAttribute("id", "1"),
new XElement(ns + "title", "something"),
new XElement(ns + "description", "something"),
new XElement(ns + "LookAt",
new XElement(ns + "Longitude", "49.69"),
new XElement(ns + "Latitude", "32.345")),
new XElement(ns + "Point",
new XElement(ns + "coordinates", "49.69,32.345,0")));
}
Recursive:
private void xmlBuild()
{
XElement docElement = new XElement(ns+"Document");
rec_build(docElement);
XDocument doc = new XDocument(
new XDeclaration("1.0", "utf-8", ""),
new XComment("This is comment by me"),
new XElement(ns+"kml", docElement)));
doc.Save(Server.MapPath(#"~\App_Data\markers2.xml"));
}
private XElement rec_build(XElement doc)
{
if (iteration != 0)
{
iteration -= 1;
doc.Add(new XElement(ns + "Placemark",
new XAttribute("id", "1"),
new XElement(ns + "title", "something"),
new XElement(ns + "description", "something"),
new XElement(ns + "LookAt",
new XElement(ns + "Longitude", "49.69"),
new XElement(ns + "Latitude", "32.345")),
new XElement(ns + "Point", new XElement(ns + "coordinates", "49.69,32.345,0")));
return recBuild(doc);
}
else
{
return null;
}
}
You are adding the recursively build elements as children of Placemark and not Document. This should do the trick:
private void xmlBuild()
{
XElement docElement = new XElement(ns + "Document");
XDocument doc = new XDocument(
new XDeclaration("1.0", "utf-8", ""),
new XComment("This is comment by me"),
new XElement(ns + "kml", docElement));
rec_build(docElement);
doc.Save(Server.MapPath(#"~\App_Data\markers2.xml"));
}
private XElement rec_build(XElement docElement)
{
if (iteration != 0)
{
iteration -= 1;
return final_rec = new XElement(ns + "Placemark",
new XAttribute("id", "1"),
new XElement(ns + "title", "something"),
new XElement(ns + "description", "something"),
new XElement(ns + "LookAt",
new XElement(ns + "Longitude", "49.69"),
new XElement(ns + "Latitude", "32.345")),
new XElement(ns + "Point", new XElement(ns + "coordinates", "49.69,32.345,0")));
docElement.Add(final_rec);
rec_build(docElement);
}
else
return null;
}

Categories