OutputFormat資料輸出
1 OutputFormat介面實現類
2 自定義OutputFormat
3 自定義OutputFormat案例實操
1.需求
過濾輸入的log日誌,包含baidu的網站輸出到e:/baidu.log,不包含baidu的網站輸出到e:/other.log。
(1)輸入資料
http://www.baidu.com
http://www.google.com
http://cn.bing.com
http://www.baidu.com
http://www.sohu.com
http://www.sina.com
http://www.sin2a.com
http://www.sin2desa.com
http://www.sindsafa.com
(2)期望輸出資料
檔案baidu.log
http://www.baidu.com
檔案other.log
http://cn.bing.com
http://www.baidu.com
http://www.google.com
http://www.sin2a.com
http://www.sin2desa.com
http://www.sina.com
http://www.sindsafa.com
http://www.sohu.com
3.案例實操
(1)編寫FilterMapper類
package com.demo.mapreduce.outputformat; import java.io.IOException; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Mapper;
public class FilterMapper extends Mapper<LongWritable, Text, Text, NullWritable>{
@Override protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 寫出 context.write(value, NullWritable.get()); } } |
(2)編寫FilterReducer類
package com.demo.mapreduce.outputformat; import java.io.IOException; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Reducer;
public class FilterReducer extends Reducer<Text, NullWritable, Text, NullWritable> {
Text k = new Text();
@Override protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
// 1 獲取一行 String line = key.toString();
// 2 拼接 line = line + "\r\n";
// 3 設定key k.set(line);
// 4 輸出 context.write(k, NullWritable.get()); } } |
(3)自定義一個OutputFormat類
package com.demo.mapreduce.outputformat; import java.io.IOException; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.RecordWriter; import org.apache.hadoop.mapreduce.TaskAttemptContext; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class FilterOutputFormat extends FileOutputFormat<Text, NullWritable>{
@Override public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException {
// 建立一個RecordWriter return new FilterRecordWriter(job); } } |
(4)編寫RecordWriter類
package com.demo.mapreduce.outputformat; import java.io.IOException; import org.apache.hadoop.fs.FSDataOutputStream; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.RecordWriter; import org.apache.hadoop.mapreduce.TaskAttemptContext;
public class FilterRecordWriter extends RecordWriter<Text, NullWritable> {
FSDataOutputStream atguiguOut = null; FSDataOutputStream otherOut = null;
public FilterRecordWriter(TaskAttemptContext job) {
// 1 獲取檔案系統 FileSystem fs;
try { fs = FileSystem.get(job.getConfiguration());
// 2 建立輸出檔案路徑 Path atguiguPath = new Path("e:/baidu.log"); Path otherPath = new Path("e:/other.log");
// 3 建立輸出流 atguiguOut = fs.create(atguiguPath); otherOut = fs.create(otherPath); } catch (IOException e) { e.printStackTrace(); } }
@Override public void write(Text key, NullWritable value) throws IOException, InterruptedException {
// 判斷是否包含“baidu”輸出到不同檔案 if (key.toString().contains("baidu")) { atguiguOut.write(key.toString().getBytes()); } else { otherOut.write(key.toString().getBytes()); } }
@Override public void close(TaskAttemptContext context) throws IOException, InterruptedException {
// 關閉資源 IOUtils.closeStream(atguiguOut); IOUtils.closeStream(otherOut); } } |
(5)編寫FilterDriver類
package com.demo.mapreduce.outputformat; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class FilterDriver {
public static void main(String[] args) throws Exception {
// 輸入輸出路徑需要根據自己電腦上實際的輸入輸出路徑設定 args = new String[] { "e:/input/inputoutputformat", "e:/output2" };
Configuration conf = new Configuration(); Job job = Job.getInstance(conf);
job.setJarByClass(FilterDriver.class); job.setMapperClass(FilterMapper.class); job.setReducerClass(FilterReducer.class);
job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(NullWritable.class);
job.setOutputKeyClass(Text.class); job.setOutputValueClass(NullWritable.class);
// 要將自定義的輸出格式元件設定到job中 job.setOutputFormatClass(FilterOutputFormat.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
// 雖然我們自定義了outputformat,但是因為我們的outputformat繼承自fileoutputformat // 而fileoutputformat要輸出一個_SUCCESS檔案,所以,在這還得指定一個輸出目錄 FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean result = job.waitForCompletion(true); System.exit(result ? 0 : 1); } } |