Hadoop2.5.2+ubuntu14.04+eclispe+hadoop2x-eclipse-plugin-master搭建开发环境
Hadoop2.5.2+ubuntu14.04+eclispe(Version:Luna Service Release 2 (4.4.2))
+hadoop2x-eclipse-plugin-master搭建开发环境
环境：
ubuntu14.04(或者linux系统）
hadoop2.5.2(hadoop2.x.y应该都可以）
eclipse
hadoop2x-eclipse-plugin-master
ant
linux系统的安装就不说了，假设您已经安装好了
hadoop2.5.2安装参考http://www.powerxing.com/install-hadoop/
我的eclipse版本是Version:Luna Service Release 2 (4.4.2)，网上的教程都是较低版本的，但是低版本应该也同样适用
下载hadoop2x-eclipse-plugin-master，网址：https://github.com/winghc/hadoop2x-eclipse-plugin，可以直接使用git
[email protected]:winghc/hadoop2x-eclipse-plugin.git或者下载zip压缩包
ant是java项目的一个构建工具，安装很简单，下载压缩包之后解压到相应目录，之后设置环境变量即可exportANT_HOME=你的
ant目录，exportPATH=$PATH:$ANT_HOME/bin，可以参考其他教程，本教程主要是搭建。
以上任务完成之后，需要先编译hadoop2x-eclipse-plugin-master，得到eclipse的hadoop插件hadoop-eclipse-plugin-
2.5.2.jar。不同版本的hadoop编译参数会不同，hadoop2.x.y对应hadoop-eclipse-plugin-2.x.y.jar。因此，如果您不
是hadoop2.5.2,那么设置的参数以及编译依赖的包也不一样。我编译的时候下载下来的hadoop2x-eclipse-plugin-master里已经
有编译好的2.6.0版本和2.4.1版本和2.2.0的插件了,可以直接使用
编译hadoop2x-eclipse-plugin-master。
打开文件hadoop2x-eclipse-plugin-master/ivy/libraries.properties
# Licensed 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 orimplied.
# See the License for the specific language governing permissions and
# limitations under the License.
#Thisproperties file lists the versions of the various artifacts used byhadoop and components.
#Itdrives ivy and the generation of a maven POM
#This is the version of hadoop we are generating
hadoop.version=2.6.0
hadoop-gpl-compression.version=0.1.0
#Theseare the versions of our dependencies (in alphabetical order)
apacheant.version=1.7.0
ant-task.version=2.0.10
asm.version=3.2
aspectj.version=1.6.5
aspectj.version=1.6.11
checkstyle.version=4.2
commons-cli.version=1.2
commons-codec.version=1.4
commons-collections.version=3.2.1
commons-configuration.version=1.6
commons-daemon.version=1.0.13
commons-httpclient.version=3.0.1
commons-lang.version=2.6
commons-logging.version=1.0.4
commons-logging-api.version=1.0.4
commons-math.version=2.1
commons-el.version=1.0
commons-fileupload.version=1.2
commons-io.version=2.1
commons-net.version=3.1
core.version=3.1.1
coreplugin.version=1.3.2
hsqldb.version=1.8.0.10
htrace.version=3.0.4
ivy.version=2.1.0
jasper.version=5.5.12
jackson.version=1.9.13
#notable to figureout the version of jsp & jsp-api version to get itresolved throught ivy
#but still declared here as we are going to have a local copy from thelib folder
jsp.version=2.1
jsp-api.version=5.5.12
jsp-api-2.1.version=6.1.14
jsp-2.1.version=6.1.14
jets3t.version=0.6.1
jetty.version=6.1.26
jetty-util.version=6.1.26
jersey-core.version=1.8
jersey-json.version=1.8
jersey-server.version=1.8
junit.version=4.5
jdeb.version=0.8
jdiff.version=1.0.9
json.version=1.0
kfs.version=0.1
log4j.version=1.2.17
lucene-core.version=2.3.1
mockito-all.version=1.8.5
jsch.version=0.1.42
oro.version=2.0.8
rats-lib.version=0.5.1
servlet.version=4.0.6
servlet-api.version=2.5
slf4j-api.version=1.7.5
slf4j-log4j12.version=1.7.5
wagon-http.version=1.0-beta-2
xmlenc.version=0.52
xerces.version=1.4.4
protobuf.version=2.5.0
guava.version=11.0.2
netty.version=3.6.2.Final
以上文件有几处是需要修改的，修改过的部分如下：
hadoop.version=2.5.2
commons-collections.version=3.2.1
commons-httpclient.version=3.1
commons-lang.version=2.6
commons-logging.version=1.1.3
commons-math.version=3.1.1
commons-io.version=2.4
jackson.version=1.9.13
jersey-core.version=1.9
jersey-json.version=1.9
jersey-server.version=1.9
junit.version=4.11
仔细比对每一项参数，然后做相应的修改。然后将该文件复制到hadoop2x-eclipse-plugin-master/src/ivy目录和hadoop2x-
eclipse-plugin-master/src/contrib/eclipse-plugin/ivy目录下，覆盖里面的libraries.properties
进入hadoop2x-eclipse-plugin-master/src/contrib/eclipse-plugin/目录，修改makePlus.sh
ant jar -Dversion=hadoop版本 -Declipse.home=你的eclipse根目录 -Dhadoop.home=hadoop根目录
我的是：
ant jar -Dversion=2.5.2 -Declipse.home=/usr/local/eclipse -Dhadoop.home=/usr/local/hadoop
然后chmod
777 makePlus.sh,执行./makePlus.sh
编译过程中可能会遇到找不到/usr/local/hadoop/share/hadoop/common/lib/htrace-core-3.0.4.jar文件，可以从网上下载一个htrace-core-3.0.4.jar包，然后放入HADOOP_HOME/share/hadoop/common/lib/目录下，重新编译即可
编译成功后，会在hadoop2x-eclipse-plugin-master/build/contrib/eclipse-plugin/目录下生成
hadoop-eclipse-plugin-2.5.2.jar包，放入/usr/local/eclipse/plugins/目录下，重新启动eclipse即可。
进入Window->Show View->other,在MapReduce Tools文件夹下选择Map/Reduce Locations即可加入视图。
然后右键，新建一个new hadoop location，进入下面的界面
然后配置，这里的配置需要和core-site.xmlhdfs-site.xml一致，找到对应的参数，修改成一样的值。
完成之后，注意要启动hadoop！！可以从Dfs Location看到hdfs的文件目录
File->New->project新建一个map/reduce项目wordcount
并将core-site.xml和hdfs-site.xml log4j.properties从$HADOOP_HOME/etc/hadoop/目录拷贝到工程源代码src目录下
最后新建一个WordCount类，代码如下：
package org.apache.hadoop.examples;
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.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;
public class WordCount {
public static class TokenizerMapper
extends Mapper{
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 {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable 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();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount ");
System.exit(2);
}
Job job = new Job(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);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
} 
最后运行，右键原则Run On Hadoop即可。