我在代码项目上遵循Anoop Madhusudanan的article，以构建不是在集群上而是在我的系统上的推荐引擎。
问题是当我尝试解析posts.xml时，其结构如下:
<row Id="99" PostTypeId="2" ParentId="88" CreationDate="2008-08-01T14:55:08.477" Score="2" Body="<blockquote>
 <p>The actual resolution of gettimeofday() depends on the hardware architecture. Intel processors as well as SPARC machines offer high resolution timers that measure microseconds. Other hardware architectures fall back to the system’s timer, which is typically set to 100 Hz. In such cases, the time resolution will be less accurate. </p>
</blockquote>

<p>I obtained this answer from <a href="http://www.informit.com/guides/content.aspx?g=cplusplus&amp;seqNum=272" rel="nofollow">High Resolution Time Measurement and Timers, Part I</a></p>" OwnerUserId="25" LastActivityDate="2008-08-01T14:55:08.477" />
Java类如下:
import java.io.IOException;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.DocumentBuilder;
import org.w3c.dom.Document;
import org.w3c.dom.NodeList;
import org.w3c.dom.Node;
import org.w3c.dom.Element;
import java.io.File;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;
public class Recommend {
static class Map extends Mapper<Text, Text, Text, Text> {
Path path;
String fXmlFile;
DocumentBuilderFactory dbFactory;
DocumentBuilder dBuilder;
Document doc;
/**
* Given an output filename, write a bunch of random records to it.
*/
public void map(LongWritable key, Text value,
OutputCollector<Text, Text> output, Reporter reporter) throws IOException {
try{
fXmlFile=value.toString();
dbFactory = DocumentBuilderFactory.newInstance();
dBuilder= dbFactory.newDocumentBuilder();
doc= dBuilder.parse(fXmlFile);
doc.getDocumentElement().normalize();
NodeList nList = doc.getElementsByTagName("row");
for (int temp = 0; temp < nList.getLength(); temp++) {
Node nNode = nList.item(temp);
Element eElement = (Element) nNode;
Text keyWords =new Text(eElement.getAttribute("OwnerUserId"));
Text valueWords = new Text(eElement.getAttribute("ParentId"));
String val=keyWords.toString()+" "+valueWords.toString();
// Write the sentence
if(keyWords != null && valueWords != null){
output.collect(keyWords, new Text(val));
}
}
}catch (Exception e) {
e.printStackTrace();
}
}
}
/**
*
* @throws IOException
*/
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
//String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
/*if (args.length != 2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}*/
// FileSystem fs = FileSystem.get(conf);
Job job = new Job(conf, "Recommend");
job.setJarByClass(Recommend.class);
// the keys are words (strings)
job.setOutputKeyClass(Text.class);
job.setMapOutputKeyClass(LongWritable.class);
job.setMapOutputValueClass(Text.class);
// the values are counts (ints)
job.setOutputValueClass(Text.class);
job.setMapperClass(Map.class);
//conf.setReducerClass(Reduce.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
Path outPath = new Path(args[1]);
FileSystem dfs = FileSystem.get(outPath.toUri(), conf);
if (dfs.exists(outPath)) {
dfs.delete(outPath, true);
}
}
}
OwnerUserId ParentId的输出但相反，我得到的输出为:
1599788 <row Id="2292" PostTypeId="2" ParentId="2284" CreationDate="2008-08-05T13:28:06.700" Score="0" ViewCount="0" Body="<p>The first thing you should do is contact the main people who run the open source project. Ask them if it is ok to contribute to the code and go from there.</p>

<p>Simply writing your improved code and then giving it to them may result in your code being rejected.</p>" OwnerUserId="383" LastActivityDate="2008-08-05T13:28:06.700" />
1599788的起源是来自mapper的键值。我对为hadoop编写映射器类了解不多，我需要帮助来修改我的代码以获得所需的输出。
提前致谢。
最佳答案
经过大量的研究和实验，终于学会了为parsin xml文件编写映射的方法，该语法具有我提供的语法。我改变了方法，这是我的新映射器代码。它适用于我的用例。
希望它可以帮助某人，他们可以节省时间:)
import java.io.IOException;
import java.util.StringTokenizer;
import javax.xml.parsers.ParserConfigurationException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.xml.sax.SAXException;
public class Map extends Mapper<LongWritable, Text, NullWritable, Text> {
NullWritable obj;
@Override
public void map(LongWritable key, Text value, Context context) throws InterruptedException {
StringTokenizer tok= new StringTokenizer(value.toString());
String pa=null,ow=null,pi=null,v;
while (tok.hasMoreTokens()) {
String[] arr;
String val = (String) tok.nextToken();
if(val.contains("PostTypeId")){
arr= val.split("[\"]");
pi=arr[arr.length-1];
if(pi.equals("2")){
continue;
}
else break;
}
if(val.contains("ParentId")){
arr= val.split("[\"]");
pa=arr[arr.length-1];
}
else if(val.contains("OwnerUserId") ){
arr= val.split("[\"]");
ow=arr[arr.length-1];
try {
if(pa!=null && ow != null){
v=String.format("{0},{1}", ow,pa);
context.write(obj,new Text(v));
}
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
}
}