hadoop MMSEG4 分词实例

pom.xml

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>

  <groupId>com.nxcjh.iktest</groupId>
  <artifactId>iktest</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <packaging>jar</packaging>

  <name>iktest</name>
  <url>http://maven.apache.org</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
  </properties>

  <dependencies>
<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-hdfs</artifactId>
    <version>2.4.0</version>
</dependency>
<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
    <version>2.4.0</version>
</dependency>
<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-common</artifactId>
    <version>2.4.0</version>
</dependency>
<!-- https://mvnrepository.com/artifact/commons-cli/commons-cli -->
<dependency>
    <groupId>commons-cli</groupId>
    <artifactId>commons-cli</artifactId>
    <version>1.3.1</version>
</dependency>
<dependency>
    <groupId>com.nxcjh.ikanalyzer</groupId>
    <artifactId>ikanalyzer</artifactId>
    <version>1.1.0</version>
</dependency>
<!-- https://mvnrepository.com/artifact/com.chenlb.mmseg4j/mmseg4j-core -->
<dependency>
    <groupId>com.chenlb.mmseg4j</groupId>
    <artifactId>mmseg4j-core</artifactId>
    <version>1.10.0</version>
</dependency>


  </dependencies>
  <!-- 打依赖包 -->
 <build>
     <plugins>
          <plugin>
               <artifactId>maven-assembly-plugin</artifactId>
               <configuration>
                    <archive>
                         <manifest>
                              <mainClass>com.nxcjh.iktest.IKJob</mainClass>
                         </manifest>
                    </archive>
                    <descriptorRefs>
                         <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
               </configuration>
               <executions>
                    <execution>
                         <id>make-assembly</id>
                         <phase>package</phase>
                         <goals>
                              <goal>single</goal>
                         </goals>
                    </execution>
               </executions>
          </plugin>
     </plugins>
</build>
</project>

Mapper

package com.nxcjh.mmseg;

import java.io.File;
import java.io.IOException;
import java.io.StringReader;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import com.chenlb.mmseg4j.ComplexSeg;
import com.chenlb.mmseg4j.Dictionary;
import com.chenlb.mmseg4j.MMSeg;
import com.chenlb.mmseg4j.Seg;
import com.chenlb.mmseg4j.Word;


public class MmsegMapper extends Mapper<Object, Text, Text, IntWritable> {

	private final static IntWritable one = new IntWritable(1);
	private Text word = new Text();
	File file = new File("/home/jianglu/下载/mmseg4j/data");//词典的目录
	Dictionary dic = Dictionary.getInstance(file);//建立词典实例，与比较老的版本中不相同。不能直接new。
	Seg seg = new ComplexSeg(dic); 
	
	public void map(Object key, Text value, Context context) throws IOException, InterruptedException{
		MMSeg mmSeg = new MMSeg(new StringReader(value.toString()), seg);
		Word iks = null;
		while((iks = mmSeg.next())!=null) {
			word.set(iks.getString());
			context.write(word, one);
		}
	}
}

Reducer

package com.nxcjh.mmseg;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class IKReducer extends
Reducer<Text, IntWritable, Text, IntWritable> {

private IntWritable result = new IntWritable();

public void reduce(Text key, Iterable<IntWritable> values, Context context)
	throws IOException, InterruptedException {
	int sum = 0;
	for (IntWritable val : values) {
		sum += val.get();
	}
	result.set(sum);
	context.write(key, result);
	}
}

Job

package com.nxcjh.mmseg;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;


public class IKJob {
	public static void main(String[] args) throws Exception {
	    Configuration conf = new Configuration();
	    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
	    if (otherArgs.length != 2) {
	      System.err.println("Usage: wordcount <in> <out>");
	      System.exit(2);
	    }
	    Job job = new Job(conf, "word count");
	    job.setJarByClass(IKJob.class);
	    job.setMapperClass(MmsegMapper.class);
	    job.setCombinerClass(IKReducer.class);
	    job.setReducerClass(IKReducer.class);
	    job.setOutputKeyClass(Text.class);
	    job.setOutputValueClass(IntWritable.class);
	    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
	    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
	    System.exit(job.waitForCompletion(true) ? 0 : 1);
	  }
}