Hadoop实战-MapReduce之WordCount(五)
环境介绍：
主服务器ip：192.168.80.128(master) NameNode SecondaryNameNode ResourceManager
从服务器ip：192.168.80.129(slave1) DataNode NodeManager
从服务器ip: 192.168.80.130(slave2) DataNode NodeManager
1.文件准备
1）在HDFS上创建文件夹
hadoop fs -mkdir /user/joe/wordcount/input
2）在本地创建文件夹
mkdir /home/chenyun/data/mapreduce
3）创建file01
cd /home/chenyun/data/mapreduce
touch file01
vi file01
往file01写入内容：
Hello World, Bye World!
4)创建file02
cd /home/chenyun/data/mapreduce touch file02 vi file02
往file02写入内容：
Hello Hadoop, Goodbye to hadoop.
5）把本地文件file01、file02上传到hdfs的/user/joe/wordcount/input目录
hadoop fs -put /home/chenyun/data/mapreduce/file01 /user/joe/wordcount/input hadoop fs -put /home/chenyun/data/mapreduce/file02 /user/joe/wordcount/input
2.编写mapreduce程序
1）在Eclipse编写Mapreduce程序
import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.net.URI;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
import java.util.StringTokenizer;
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.Counter;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.util.StringUtils;
public class WordCount {
public static class TokenizerMapper extends
Mapper<Object, Text, Text, IntWritable> {
static enum CountersEnum {
INPUT_WORDS
}
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
private boolean caseSensitive;
private Set<String> patternsToSkip = new HashSet<String>();
private Configuration conf;
private BufferedReader fis;
@Override
public void setup(Context context) throws IOException,
InterruptedException {
conf = context.getConfiguration();
caseSensitive = conf.getBoolean("wordcount.case.sensitive", true);
if (conf.getBoolean("wordcount.skip.patterns", false)) {
URI[] patternsURIs = Job.getInstance(conf).getCacheFiles();
for (URI patternsURI : patternsURIs) {
Path patternsPath = new Path(patternsURI.getPath());
String patternsFileName = patternsPath.getName().toString();
parseSkipFile(patternsFileName);
}
}
}
private void parseSkipFile(String fileName) {
try {
fis = new BufferedReader(new FileReader(fileName));
String pattern = null;
while ((pattern = fis.readLine()) != null) {
patternsToSkip.add(pattern);
}
} catch (IOException ioe) {
System.err
.println("Caught exception while parsing the cached file '"
+ StringUtils.stringifyException(ioe));
}
}
@Override
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
String line = (caseSensitive) ? value.toString() : value.toString()
.toLowerCase();
for (String pattern : patternsToSkip) {
line = line.replaceAll(pattern, "");
}
StringTokenizer itr = new StringTokenizer(line);
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
Counter counter = context.getCounter(
CountersEnum.class.getName(),
CountersEnum.INPUT_WORDS.toString());
counter.increment(1);
}
}
}
public static class IntSumReducer 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);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
GenericOptionsParser optionParser = new GenericOptionsParser(conf, args);
String[] remainingArgs = optionParser.getRemainingArgs();
if ((remainingArgs.length != 2) && (remainingArgs.length != 4)) {
System.err
.println("Usage: wordcount <in> <out> [-skip skipPatternFile]");
System.exit(2);
}
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
List<String> otherArgs = new ArrayList<String>();
for (int i = 0; i < remainingArgs.length; ++i) {
if ("-skip".equals(remainingArgs[i])) {
job.addCacheFile(new Path(remainingArgs[++i]).toUri());
job.getConfiguration().setBoolean("wordcount.skip.patterns",
true);
} else {
otherArgs.add(remainingArgs[i]);
}
}
FileInputFormat.addInputPath(job, new Path(otherArgs.get(0)));
FileOutputFormat.setOutputPath(job, new Path(otherArgs.get(1)));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
2）导出mapreduce.jar
3) 上传到master的目录
/home/chenyun/project/mapreduce
3.运行wordCount
hadoop jar /home/chenyun/project/mapreduce/mapreduce.jar com.accp.mapreduce.WordCount /user/joe/wordcount/input /user/joe/wordcount/output
4)查看运行结果
hadoop fs -cat /user/joe/wordcount/output/part-r-00000
=======================================================================================================================
4.过滤不需要统计的字符
1）在本地创建/home/chenyun/data/mapreduce/patterns.txt ,在文件里加入
\. \, \! to
2)把文件上传到hdfs上
hadoop fs -put /home/chenyun/data/mapreduce/patterns.txt /user/joe/wordcount
3)运行
hadoop jar /home/chenyun/project/mapreduce/mapreduce.jar com.accp.mapreduce.WordCount -Dwordcount.case.sensitive=true /user/joe/wordcount/input /user/joe/wordcount/output1 -skip /user/joe/wordcount/patterns.txt
4)查看运行结果
hadoop fs -cat /user/joe/wordcount/output1/part-r-00000
======================================================================================================================
5.忽略大小写，进行统计
1)运行
hadoop jar /home/chenyun/project/mapreduce/mapreduce.jar com.accp.mapreduce.WordCount -Dwordcount.case.sensitive=false /user/joe/wordcount/input /user/joe/wordcount/output5 -skip /user/joe/wordcount/patterns.txt
2)查看运行结果
hadoop fs -cat /user/joe/wordcount/output5/part-r-00000
