| | 1 | |
| | 2 | |
| | 3 | {{{ |
| | 4 | #!java |
| | 5 | package org.nchc.hadoop; |
| | 6 | import java.io.IOException; |
| | 7 | |
| | 8 | import org.apache.hadoop.io.LongWritable; |
| | 9 | import org.apache.hadoop.io.Text; |
| | 10 | import org.apache.hadoop.mapreduce.Mapper; |
| | 11 | |
| | 12 | public class HelloMapperV2 extends Mapper<LongWritable, Text, Text, Text> { |
| | 13 | |
| | 14 | public void map(LongWritable key, Text value, Context context) |
| | 15 | throws IOException, InterruptedException { |
| | 16 | context.write(new Text(key.toString()), value); |
| | 17 | } |
| | 18 | |
| | 19 | } |
| | 20 | |
| | 21 | }}} |
| | 22 | |
| | 23 | = HelloReducerV2.java = |
| | 24 | |
| | 25 | {{{ |
| | 26 | #!java |
| | 27 | package org.nchc.hadoop; |
| | 28 | import java.io.IOException; |
| | 29 | |
| | 30 | import org.apache.hadoop.io.Text; |
| | 31 | import org.apache.hadoop.mapreduce.Reducer; |
| | 32 | |
| | 33 | public class HelloReducerV2 extends Reducer<Text, Text, Text, Text> { |
| | 34 | public void reduce(Text key, Iterable<Text> values, Context context) |
| | 35 | throws IOException, InterruptedException { |
| | 36 | |
| | 37 | String str = new String(""); |
| | 38 | Text final_key = new Text(); |
| | 39 | Text final_value = new Text(); |
| | 40 | // 將key值相同的values,透過 && 符號分隔之 |
| | 41 | for (Text tmp : values) { |
| | 42 | str += tmp.toString() + " &&"; |
| | 43 | } |
| | 44 | |
| | 45 | final_key.set(key); |
| | 46 | final_value.set(str); |
| | 47 | |
| | 48 | context.write(final_key, final_value); |
| | 49 | } |
| | 50 | } |
| | 51 | |
| | 52 | }}} |
| | 53 | |
| | 54 | = HelloHadoopV2.java = |
| | 55 | |
| | 56 | {{{ |
| | 57 | #!java |
| | 58 | package org.nchc.hadoop; |
| | 59 | import java.io.IOException; |
| | 60 | |
| | 61 | import org.apache.hadoop.conf.Configuration; |
| | 62 | import org.apache.hadoop.fs.Path; |
| | 63 | import org.apache.hadoop.io.Text; |
| | 64 | import org.apache.hadoop.mapreduce.Job; |
| | 65 | import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; |
| | 66 | import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; |
| | 67 | |
| | 68 | public class HelloHadoopV2 { |
| | 69 | |
| | 70 | |
| | 71 | public static void main(String[] args) throws IOException, |
| | 72 | InterruptedException, ClassNotFoundException { |
| | 73 | |
| | 74 | Configuration conf = new Configuration(); |
| | 75 | Job job = new Job(conf, "Hadoop Hello World 2"); |
| | 76 | job.setJarByClass(HelloHadoopV2.class); |
| | 77 | // 設定 map and reduce 以及 Combiner class |
| | 78 | job.setMapperClass(HelloMapperV2.class); |
| | 79 | job.setCombinerClass(HelloReducerV2.class); |
| | 80 | job.setReducerClass(HelloReducerV2.class); |
| | 81 | |
| | 82 | // 設定map的輸出型態 |
| | 83 | job.setMapOutputKeyClass(Text.class); |
| | 84 | job.setMapOutputValueClass(Text.class); |
| | 85 | // 設定reduce的輸出型態 |
| | 86 | job.setOutputKeyClass(Text.class); |
| | 87 | job.setOutputValueClass(Text.class); |
| | 88 | |
| | 89 | FileInputFormat.addInputPath(job, new Path("/user/hadoop/input")); |
| | 90 | |
| | 91 | FileOutputFormat.setOutputPath(job, new Path("/user/hadoop/output-hh2")); |
| | 92 | |
| | 93 | // 呼叫checkAndDelete函式,檢查是否存在該資料夾,若有則刪除之 |
| | 94 | CheckAndDelete.checkAndDelete("/user/hadoop/output-hh2", conf); |
| | 95 | |
| | 96 | boolean status = job.waitForCompletion(true); |
| | 97 | |
| | 98 | if (status) { |
| | 99 | System.err.println("Integrate Alert Job Finished !"); |
| | 100 | |
| | 101 | } else { |
| | 102 | System.err.println("Integrate Alert Job Failed !"); |
| | 103 | System.exit(1); |
| | 104 | } |
| | 105 | } |
| | 106 | } |
| | 107 | |
| | 108 | }}} |