Reputation: 450
I have an XML file for a government document and a XSD file that it references. I'm trying to extract information from the XML (chemical name, UN, and hazard classification) and store it into a table in SQL Server 2014. However, whenever I perform an ETL with an XML source, using SSIS, I get the error: The XML Source Adapter does not support mixed content model on Complex Types
. How can I work around this? Some ideas I thought about and tried to understand better were: using an XSLT transform on the XML to only retain the pertinent information or use C# and XPath to select only the nodes I want. But this has turned into something a bit harder than I originally thought. Any help or direction is appreciated.
http://www.gpo.gov/fdsys/bulkdata/CFR/2014/title-49/CFR-2014-title49-vol2.xml http://www.gpo.gov/fdsys/bulkdata/CFR/resources/CFRMergedXML.xsd
Upvotes: 0
Views: 2742
Reputation: 34421
Try this
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Xml;
using System.Xml.Linq;
namespace ConsoleApplication1
{
class Program
{
const string FILENAME = @"c:\temp\CFR-2014-title49-vol2.xml";
static void Main(string[] args)
{
XDocument doc = XDocument.Load(FILENAME);
XElement chapter = doc.Descendants("GPOTABLE").Where(x => x.Element("TTITLE") != null && x.Element("TTITLE").Value == "§ 172.101 Hazardous Materials Table").FirstOrDefault();
var results = chapter.Elements().Where(x => x.Name == "ROW" && x.Attribute("RUL") == null && (x.Elements("ENT").Count() == 14 || x.Elements("ENT").Count() == 2)).Select(y => new
{
chemical_name = y.Elements("ENT").Count() == 14 ? y.Elements("ENT").Skip(1).FirstOrDefault().Value
: y.Elements("ENT").Skip(1).FirstOrDefault().Value == ""
? string.Join("", y.Elements("ENT").Skip(1).FirstOrDefault().Descendants().Select(z => z.NextNode == null ? z.Value : z.Value + z.NextNode.ToString()).ToArray())
: string.Join("", y.Elements("ENT").Skip(1).FirstOrDefault().Value),
classification = y.Elements("ENT").Count() == 14 ? y.Elements("ENT").Skip(2).FirstOrDefault().Value : null,
UN = y.Elements("ENT").Count() == 14 ? y.Elements("ENT").Skip(3).FirstOrDefault().Value : null
}).Where(a => a.chemical_name.Length > 0).ToList();
}
}
}
Upvotes: 1