[MAPREDUCE-5664] java.lang.RuntimeException: javax.xml.parsers.ParserConfigurationException:

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Duplicate
• Affects Version/s: 0.21.0

Environment

Java 1.6

• Assignee: Unassigned
• Reporter: ranjini
• Created: 03/Dec/13 10:11
• Updated: 04/Dec/13 09:06
• Resolved: 04/Dec/13 09:05

Description

Hi,

I am using hadoop 0.21 vesrsion and java 1.6. Please help me to fix the issue. What version jar should i put.

The sample code with xml i have attached here.

<?xml version="1.0"?>
<Company>
<Employee>
<id>100</id>
<ename>ranjini</ename>
<dept>IT</dept>
<sal>123456</sal>
<location>nextlevel</location>
</Employee>
</Company>

import java.io.IOException;
import java.util.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;
import java.io.*;
import org.apache.hadoop.mapred.lib.*;

import java.io.Reader;
import java.io.StringReader;
import org.jdom.Document;
import org.jdom.Element;
import org.jdom.JDOMException;
import org.jdom.input.SAXBuilder;

public class ParseXml {
	public static class Map extends MapReduceBase implements
			Mapper<LongWritable, Text, Text, Text> {
		
		public void map(LongWritable key, Text value,
				OutputCollector<Text, Text> output, Reporter reporter) 
				throws IOException {
			
			String s="";
			FileSystem fs=null;
			Configuration conf=new Configuration();
			conf.set("fs.default.name","hdfs://localhost:4440/");
			Path srcpath=new Path("/user/hduser/Ran/");
try {
	
					String xmlString = value.toString();
             
             		SAXBuilder builder = new SAXBuilder();
            		Reader in = new StringReader(xmlString);
 					Document doc = builder.build(in);
           			 Element root = doc.getRootElement();
	

  s =root.getChild("Employee").getChild("id").getChild("ename").getChild("dept").getChild("sal").getChild("location").getTextTrim();
 output.collect(new Text(""),new Text(s));
		
    } catch (Exception e) {
	e.printStackTrace();
    }

}
}
			
	public static void main(String[] args) throws Exception {
		
		String input="/user/hduser/Ran/";
		String fileoutput="/user/task/Sales/";
		JobConf conf = new JobConf(ParseXml.class);
		conf.setJobName("file");
		conf.setOutputKeyClass(Text.class);
		conf.setOutputValueClass(Text.class);
		conf.setNumReduceTasks(1);
		conf.setMapperClass(Map.class);
		conf.setInputFormat(TextInputFormat.class);
		conf.setOutputFormat(TextOutputFormat.class);
		FileInputFormat.setInputPaths(conf,input);
		Path outPath = new Path(fileoutput);
		FileOutputFormat.setOutputPath(conf, outPath);
		FileSystem dfs = FileSystem.get(outPath.toUri(), conf);
			if (dfs.exists(outPath)) {
				dfs.delete(outPath, true);
			}
		//conf.setOutputFormat(MultiFileOutput.class);

		JobClient.runJob(conf);
	}
}

When processing xml file as input via map reduce, the error occurred is

conf.Configuration: error parsing conf file: javax.xml.parsers.ParserConfigurationException: Feature 'http://apache.org/xml/features/xinclude' is not recognized.
Exception in thread "main" java.lang.RuntimeException: javax.xml.parsers.ParserConfigurationException: Feature 'http://apache.org/xml/features/xinclude' is not recognized.
	at org.apache.hadoop.conf.Configuration.loadResource(Configuration.java:1171)
	at org.apache.hadoop.conf.Configuration.loadResources(Configuration.java:1030)
	at org.apache.hadoop.conf.Configuration.getProps(Configuration.java:980)
	at org.apache.hadoop.conf.Configuration.get(Configuration.java:382)
	at org.apache.hadoop.util.RunJar.main(RunJar.java:109)
Caused by: javax.xml.parsers.ParserConfigurationException: Feature 'http://apache.org/xml/features/xinclude' is not recognized.
	at org.apache.xerces.jaxp.DocumentBuilderFactoryImpl.newDocumentBuilder(Unknown Source)
	at org.apache.hadoop.conf.Configuration.loadResource(Configuration.java:1061)
	... 4 more

Please help to fix the issue

Issue Links

• duplicates: HADOOP-5254 Xinclude setup results in a stack trace
• is duplicated by: MAPREDUCE-5667 Error in runtime in mapreduce code
• relates to: HADOOP-5254 Xinclude setup results in a stack trace