开发
在windows下开发,通过eclipse连接到hadoop集群,并且远程运行
参考代码为wordcount代码
package mapreduce; import java.net.URI; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.LongWritable; 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; public class WordCountApp { static final String INPUT_PATH = "hdfs://192.168.7.12:9000/hello"; static final String OUT_PATH = "hdfs://192.168.7.12:9000/helloout"; public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); conf.set("mapred.job.tracker", "192.168.7.12:9001"); final FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), conf); final Path outPath = new Path(OUT_PATH); if(fileSystem.exists(outPath)){ fileSystem.delete(outPath, true); } final Job job = new Job(conf , WordCountApp.class.getSimpleName()); //1.1指定读取的文件位于哪里 FileInputFormat.setInputPaths(job, INPUT_PATH); //指定如何对输入文件进行格式化,把输入文件每一行解析成键值对 //job.setInputFormatClass(TextInputFormat.class); //1.2 指定自定义的map类 job.setMapperClass(MyMapper.class); //map输出的<k,v>类型。如果<k3,v3>的类型与<k2,v2>类型一致,则可以省略 //job.setMapOutputKeyClass(Text.class); //job.setMapOutputValueClass(LongWritable.class); //1.3 分区 //job.setPartitionerClass(HashPartitioner.class); //有一个reduce任务运行 //job.setNumReduceTasks(1); //1.4 TODO 排序、分组 //1.5 TODO 规约 //2.2 指定自定义reduce类 job.setReducerClass(MyReducer.class); //指定reduce的输出类型 job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); //2.3 指定写出到哪里 FileOutputFormat.setOutputPath(job, outPath); //指定输出文件的格式化类 //job.setOutputFormatClass(TextOutputFormat.class); //把job提交给JobTracker运行 job.waitForCompletion(true); } /** * KEYIN 即k1 表示行的偏移量 * VALUEIN 即v1 表示行文本内容 * KEYOUT 即k2 表示行中出现的单词 * VALUEOUT 即v2 表示行中出现的单词的次数,固定值1 */ static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable>{ protected void map(LongWritable k1, Text v1, Context context) throws java.io.IOException ,InterruptedException { final String[] splited = v1.toString().split("\t"); for (String word : splited) { context.write(new Text(word), new LongWritable(1)); } }; } /** * KEYIN 即k2 表示行中出现的单词 * VALUEIN 即v2 表示行中出现的单词的次数 * KEYOUT 即k3 表示文本中出现的不同单词 * VALUEOUT 即v3 表示文本中出现的不同单词的总次数 * */ static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable>{ protected void reduce(Text k2, java.lang.Iterable<LongWritable> v2s, Context ctx) throws java.io.IOException ,InterruptedException { long times = 0L; for (LongWritable count : v2s) { times += count.get(); } ctx.write(k2, new LongWritable(times)); }; } }
调试
直接在eclipse运行即可
1、 Exception in thread "main" java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Ljava/lang/String;I)Z
hadoop2.2.0配置eclipse运行wordcount程序问题及解决方法:解决方法 :从https://github.com/srccodes/hadoop-common-2.2.0-bin上下载bin包,然后将bin目录下的wiutils.exe放在hadoop/bin目录下或者将hadoop/bin目录文件全部替换为bin包,并且配置hadoop环境变量HADOOP_HOME="*****",在path中配置%HADOOP_HOME%\bin
问题2:文件IO异常
将第一步问题解决后继续运行程序,会出现如下问题:
Exception in thread "main" java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Ljava/lang/String;I)Z原因:缺少hadoop.dll文件解决方案:
将bin包下的hadoop文件放在C:\Windows\System32目录下。
即可解决上面问题!!!Happy一把!!!