eclipse 运行hadoop wordcount
程序员文章站
2022-05-25 14:51:07
...
给大家 一个建议 如果使用1.XX的版本hadoop 建议大家严格按照 以下的 第一条 中的博文的版本安装，可以是单机或者伪分布式，主要是因为，hadoop版本和 eclipse插件版本如果不一致会带来很多问题，解决起来比较麻烦，
先说明一下 此次搭建 hadoop 运行示例 ，过程中参考的文章：
1. eclipse 搭建 hadoop环境：
http://www.cnblogs.com/xia520pi/archive/2012/05/20/2510723.html
2.运行hadoop是遇到的问题：
第一个问题：XX.XX.XXX.WordCount$TokenizerMapper 这个主要是因为 插件版本不一致的问题，但是目前我没有解决，我用的还是1.2.1的 有源码 ，查了一些资料 也手工打了一个 eclipse-plugin 但是最终还是不好使，打eclipse-plugins 的 可以参考 利用hadoop源码 打plugins的文章（我打了包但是还是不好用），绕过这个问题的方法可以参考 （http://www.cnblogs.com/spork/archive/2010/04/21/1717592.html 文章有几篇 写的不错，可以都看看也算都hadoop执行过程的一个了解） ，这个最终解决办法是模拟了 hadoop将本地文件打成jar 的过程
以上问题解决 按照网上的文章应该是已经可以运行了 ，但是我这又遇到了 其他问题：
问题二：
eclipse 中运行 org.apache.hadoop.mapreduce.lib.input.InvalidInputException
执行 wordount 的时候，配置input文件找不到：明明就在那里防止相对路径绝对路径都试过了 还是不行，最后想着 hadoop在命令行执行 的话，是 将本地文件上传到 hadoop中的，但是我运行时候每次都报的的是本地文件找不到，所以应该写远程文件地址，参开 执行成功的hadoop文件发现文件地址为：
mapred.output.dirhdfs://172.16.236.11:9000/user/libin/output/wordcount-ec
所以就修改了本地代码程序：
FileInputFormat.addInputPath(job, new Path("hdfs://172.16.236.11:9000"
+ File.separator + otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(
"hdfs://172.16.236.11:9000" + File.separator + otherArgs[1]));
这样 本地执行的代码就可以 在hadoop服务端执行了。
这里还有一个问题 就是，如果每次测试都需要将本地文件上传到 hadoop服务端 ，好像有点麻烦，所以 可以考虑，每次addInputPath 的时候，在这个之前，先执行以下 类型 hadoop fs -put 的 代码，将本地文件上传到 hadoop服务端，这样就不用每次手工上传文件到 服务器 参考
http://younglibin.iteye.com/admin/blogs/1925109
贴一个完整的 示例程序吧：
package com.younglibin.hadoop.test;
import java.io.File;
import java.io.IOException;
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.mapred.JobConf;
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 com.younglibin.hadoop.EJob;
public class WordCount {
public static class TokenizerMapper extends
Mapper<Object, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}
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 {
File jarFile = EJob.createTempJar("bin");
EJob.addClasspath("/home/libin/software/hadoop/hadoop-1.2.1/conf");
ClassLoader classLoader = EJob.getClassLoader();
Thread.currentThread().setContextClassLoader(classLoader);
Configuration conf = new Configuration();
conf.set("mapred.job.tracker", "172.16.236.11:9001");
args = new String[] { "/user/libin/input/libin", "/user/libin/output/wordcount-ec" };
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(WordCount.class);
((JobConf) job.getConfiguration()).setJar(jarFile.toString());
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path("hdfs://172.16.236.11:9000"
+ File.separator + otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(
"hdfs://172.16.236.11:9000" + File.separator + otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
/**
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package com.younglibin.hadoop;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.lang.reflect.Array;
import java.lang.reflect.InvocationTargetException;
import java.lang.reflect.Method;
import java.net.URL;
import java.net.URLClassLoader;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Enumeration;
import java.util.jar.JarEntry;
import java.util.jar.JarFile;
import java.util.jar.JarOutputStream;
import java.util.jar.Manifest;
public class EJob {
private static ArrayList<URL> classPath = new ArrayList<URL>();
/** Unpack a jar file into a directory. */
public static void unJar(File jarFile, File toDir) throws IOException {
JarFile jar = new JarFile(jarFile);
try {
Enumeration entries = jar.entries();
while (entries.hasMoreElements()) {
JarEntry entry = (JarEntry) entries.nextElement();
if (!entry.isDirectory()) {
InputStream in = jar.getInputStream(entry);
try {
File file = new File(toDir, entry.getName());
if (!file.getParentFile().mkdirs()) {
if (!file.getParentFile().isDirectory()) {
throw new IOException("Mkdirs failed to create "
+ file.getParentFile().toString());
}
}
OutputStream out = new FileOutputStream(file);
try {
byte[] buffer = new byte[8192];
int i;
while ((i = in.read(buffer)) != -1) {
out.write(buffer, 0, i);
}
} finally {
out.close();
}
} finally {
in.close();
}
}
}
} finally {
jar.close();
}
}
/**
* Run a Hadoop job jar. If the main class is not in the jar's manifest, then
* it must be provided on the command line.
*/
public static void runJar(String[] args) throws Throwable {
String usage = "jarFile [mainClass] args...";
if (args.length < 1) {
System.err.println(usage);
System.exit(-1);
}
int firstArg = 0;
String fileName = args[firstArg++];
File file = new File(fileName);
String mainClassName = null;
JarFile jarFile;
try {
jarFile = new JarFile(fileName);
} catch (IOException io) {
throw new IOException("Error opening job jar: " + fileName).initCause(io);
}
Manifest manifest = jarFile.getManifest();
if (manifest != null) {
mainClassName = manifest.getMainAttributes().getValue("Main-Class");
}
jarFile.close();
if (mainClassName == null) {
if (args.length < 2) {
System.err.println(usage);
System.exit(-1);
}
mainClassName = args[firstArg++];
}
mainClassName = mainClassName.replaceAll("/", ".");
File tmpDir = new File(System.getProperty("java.io.tmpdir"));
tmpDir.mkdirs();
if (!tmpDir.isDirectory()) {
System.err.println("Mkdirs failed to create " + tmpDir);
System.exit(-1);
}
final File workDir = File.createTempFile("hadoop-unjar", "", tmpDir);
workDir.delete();
workDir.mkdirs();
if (!workDir.isDirectory()) {
System.err.println("Mkdirs failed to create " + workDir);
System.exit(-1);
}
Runtime.getRuntime().addShutdownHook(new Thread() {
public void run() {
try {
fullyDelete(workDir);
} catch (IOException e) {
}
}
});
unJar(file, workDir);
classPath.add(new File(workDir + "/").toURL());
classPath.add(file.toURL());
classPath.add(new File(workDir, "classes/").toURL());
File[] libs = new File(workDir, "lib").listFiles();
if (libs != null) {
for (int i = 0; i < libs.length; i++) {
classPath.add(libs[i].toURL());
}
}
ClassLoader loader = new URLClassLoader(classPath.toArray(new URL[0]));
Thread.currentThread().setContextClassLoader(loader);
Class<?> mainClass = Class.forName(mainClassName, true, loader);
Method main = mainClass.getMethod("main", new Class[] { Array.newInstance(
String.class, 0).getClass() });
String[] newArgs = Arrays.asList(args).subList(firstArg, args.length)
.toArray(new String[0]);
try {
main.invoke(null, new Object[] { newArgs });
} catch (InvocationTargetException e) {
throw e.getTargetException();
}
}
/**
* Delete a directory and all its contents. If we return false, the directory
* may be partially-deleted.
*/
public static boolean fullyDelete(File dir) throws IOException {
File contents[] = dir.listFiles();
if (contents != null) {
for (int i = 0; i < contents.length; i++) {
if (contents[i].isFile()) {
if (!contents[i].delete()) {
return false;
}
} else {
// try deleting the directory
// this might be a symlink
boolean b = false;
b = contents[i].delete();
if (b) {
// this was indeed a symlink or an empty directory
continue;
}
// if not an empty directory or symlink let
// fullydelete handle it.
if (!fullyDelete(contents[i])) {
return false;
}
}
}
}
return dir.delete();
}
/**
* Add a directory or file to classpath.
*
* @param component
*/
public static void addClasspath(String component) {
if ((component != null) && (component.length() > 0)) {
try {
File f = new File(component);
if (f.exists()) {
URL key = f.getCanonicalFile().toURL();
if (!classPath.contains(key)) {
classPath.add(key);
}
}
} catch (IOException e) {
}
}
}
/**
* Add default classpath listed in bin/hadoop bash.
*
* @param hadoopHome
*/
public static void addDefaultClasspath(String hadoopHome) {
// Classpath initially contains conf dir.
addClasspath(hadoopHome + "/conf");
// For developers, add Hadoop classes to classpath.
addClasspath(hadoopHome + "/build/classes");
if (new File(hadoopHome + "/build/webapps").exists()) {
addClasspath(hadoopHome + "/build");
}
addClasspath(hadoopHome + "/build/test/classes");
addClasspath(hadoopHome + "/build/tools");
// For releases, add core hadoop jar & webapps to classpath.
if (new File(hadoopHome + "/webapps").exists()) {
addClasspath(hadoopHome);
}
addJarsInDir(hadoopHome);
addJarsInDir(hadoopHome + "/build");
// Add libs to classpath.
addJarsInDir(hadoopHome + "/lib");
addJarsInDir(hadoopHome + "/lib/jsp-2.1");
addJarsInDir(hadoopHome + "/build/ivy/lib/Hadoop/common");
}
/**
* Add all jars in directory to classpath, sub-directory is excluded.
*
* @param dirPath
*/
public static void addJarsInDir(String dirPath) {
File dir = new File(dirPath);
if (!dir.exists()) {
return;
}
File[] files = dir.listFiles();
if (files == null) {
return;
}
for (int i = 0; i < files.length; i++) {
if (files[i].isDirectory()) {
continue;
} else {
addClasspath(files[i].getAbsolutePath());
}
}
}
/**
* Create a temp jar file in "java.io.tmpdir".
*
* @param root
* @return
* @throws IOException
*/
public static File createTempJar(String root) throws IOException {
if (!new File(root).exists()) {
return null;
}
Manifest manifest = new Manifest();
manifest.getMainAttributes().putValue("Manifest-Version", "1.0");
final File jarFile = File.createTempFile("EJob-", ".jar", new File(System
.getProperty("java.io.tmpdir")));
Runtime.getRuntime().addShutdownHook(new Thread() {
public void run() {
jarFile.delete();
}
});
JarOutputStream out = new JarOutputStream(new FileOutputStream(jarFile),
manifest);
createTempJarInner(out, new File(root), "");
out.flush();
out.close();
return jarFile;
}
private static void createTempJarInner(JarOutputStream out, File f,
String base) throws IOException {
if (f.isDirectory()) {
File[] fl = f.listFiles();
if (base.length() > 0) {
base = base + "/";
}
for (int i = 0; i < fl.length; i++) {
createTempJarInner(out, fl[i], base + fl[i].getName());
}
} else {
out.putNextEntry(new JarEntry(base));
FileInputStream in = new FileInputStream(f);
byte[] buffer = new byte[1024];
int n = in.read(buffer);
while (n != -1) {
out.write(buffer, 0, n);
n = in.read(buffer);
}
in.close();
}
}
/**
* Return a classloader based on user-specified classpath and parent
* classloader.
*
* @return
*/
public static ClassLoader getClassLoader() {
ClassLoader parent = Thread.currentThread().getContextClassLoader();
if (parent == null) {
parent = EJob.class.getClassLoader();
}
if (parent == null) {
parent = ClassLoader.getSystemClassLoader();
}
return new URLClassLoader(classPath.toArray(new URL[0]), parent);
}
}
看这个比较迷茫的是参数的传递：
简单说明一下,这里map参数传递 在 FileInputFormat 指定的 ，所以在map方法中，中的value
就是经过FileInputFormat 处理的 ，在处理 createRecordReader 的时候，根据参数来判断使用哪一个子类处理，这里使用了TextInputFormat