Windows下使用 IntelliJ IDEA搭建hadoop开发环境调试MapReduce（二）
准备
准备前一篇的涉及到的内容
这里额外新增一快，在idea的安装目录下，也就是idea.exe的目录下新建一个idea.bat，使用txt文本文件改下后缀名即可，编辑输入以下信息：
runas /user:root /savecred idea.exe
相当于使用前面新建的windows账号为root的用户，使用root身份执行idea.exe程序，此时会提示输入root账号的密码，如果idea在root账号下曾经开发过其他的内容，IDEA会使用root下的配置。
搭建
前面已经新建了Test的测试类，这里新建WordCount2测试类
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
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;
import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStream;
import java.net.URI;
import java.util.*;
public class WordCount2 {
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", false);
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[] args0) throws Exception {
//String[] args1=args0;
//这里两个参数本来在执行main方法的args里面配置，这里写死在这里方便调试
String[] args1={"hdfs://192.168.145.128:9000/tmp/input", "hdfs://192.168.145.128:9000/tmp/output"};
Configuration conf = new Configuration();
// 每个人的maven仓库的路径不一样，这里使用你的MAVEN仓库路径，比如我的MAVEN就暴露出了盘很多，报名为me.j360.hadoop，F:\\Maven\\repo
// 如果缺少这一句，会提示ClassNotFound
conf.set("mapred.jar", "F:\\Maven\\repo\\me\\j360\\hadoop\\1.0-SNAPSHOT\\hadoop-1.0-SNAPSHOT.jar");
// 以下都是默认配置，端口号和hadoop集群的配置必须要一致
conf.setBoolean("mapreduce.app-submission.cross-platform", true); // 配置使用跨平台提交任务
String flag=conf.get("mapreduce.app-submission.cross-platform");
System.out.println(flag);
conf.set("fs.defaultFS", "hdfs://192.168.145.128:9000"); //指定namenode
conf.set("mapreduce.framework.name", "yarn"); // 指定使用yarn框架
conf.set("yarn.resourcemanager.address", "192.168.145.128:8032"); // 指定resourcemanager
conf.set("yarn.resourcemanager.scheduler.address", "192.168.145.128:8030"); // 指定资源分配器
conf.set("mapreduce.jobhistory.address","192.168.145.128:10020");
GenericOptionsParser optionParser = new GenericOptionsParser(conf, args1);
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(WordCount2.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)));
if(job.waitForCompletion(true)){
System.out.println("执行完成...");
//使用hdfs的api打印出结果
FileSystem fs = FileSystem.get(URI.create("hdfs://192.168.145.128:9000"), conf);
// 列出hdfs上/tmp/output/目录下的所有文件和目录
FileStatus[] statuses = fs.listStatus(new Path("/tmp/output"));
for (FileStatus status : statuses) {
System.out.println(status);
System.out.println(status.getPath());
}
// 显示在hdfs的/tmp/output下指定文件的内容
InputStream is = fs.open(new Path("/tmp/output/part-r-00000"));
IOUtils.copyBytes(is, System.out, 1024, true);
}
}
}
调试
执行main方法，等待几秒钟，如果提示file已经存在，则修改下输出的路径，如果file找不到，根据hdfs的api调试
FileStatus{path=hdfs://192.168.145.128:9000/tmp/output/_SUCCESS; isDirectory=false; length=0; replication=3; blocksize=134217728; modification_time=1429001943525; access_time=1429001943504; owner=root; group=supergroup; permission=rw-r--r--; isSymlink=false}
FileStatus{path=hdfs://192.168.145.128:9000/tmp/output/part-r-00000; isDirectory=false; length=45; replication=3; blocksize=134217728; modification_time=1429001943215; access_time=1429001942602; owner=root; group=supergroup; permission=rw-r--r--; isSymlink=false}
bye 2
hadoop 2
hello 3
jj 1
world 1
world! 1