Changes between Version 1 and Version 2 of waue/2010/0204-06

Timestamp:

Feb 3, 2010, 9:53:49 PM (14 years ago)

Author:

waue

Comment:

--

waue/2010/0204-06

@@ -7 +7 @@
  == 結果： ==
 {{{
-        $ hbase shell
+$ hbase shell
         > scan 'wordcount'
         ROW             COLUMN+CELL 
         am              column=content:count, timestamp=1264406245488, value=1
-  chen  column=content:count, timestamp=1264406245488, value=1 
+        chen    column=content:count, timestamp=1264406245488, value=1 
         hi,             column=content:count, timestamp=1264406245488, value=2
   ......(略)
@@ -31 +31 @@
 {{{
 #!java
+package tsmc;
 
+import java.io.IOException;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hbase.client.Put;
+import org.apache.hadoop.hbase.mapreduce.TableOutputFormat;
+import org.apache.hadoop.hbase.mapreduce.TableReducer;
+import org.apache.hadoop.hbase.util.Bytes;
+import org.apache.hadoop.io.IntWritable;
+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.lib.input.FileInputFormat;
+import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
+
+public class CountToHBaseReducer {
+        public static class HtMap extends
+                        Mapper<LongWritable, Text, Text, IntWritable> {
+                private IntWritable one = new IntWritable(1);
+
+                public void map(LongWritable key, Text value, Context context)
+                                throws IOException, InterruptedException {
+                        // 輸入的字串先轉換成小寫再用空白區隔
+                        String s[] = value.toString().toLowerCase().trim().split(" ");
+                        for (String m : s) {
+                                // 寫入到輸出串流
+                                context.write(new Text(m), one);
+                        }
+                }
+        }
+
+        // TableReducer<KEYIN,VALUEIN,KEYOUT>
+        // 原本為 TableReducer<Text, IntWritable, NullWritable >
+        // 但在此改成 LongWritable 也可以
+        // 因此證明在此的Class可以很多,org.apache.hadoop.io.* 內有write()的Writable class應該皆可
+        public static class HtReduce extends
+                        TableReducer<Text, IntWritable, LongWritable> {
+
+                public void reduce(Text key, Iterable<IntWritable> values,
+                                Context context) throws IOException, InterruptedException {
+                        int sum = 0;
+                        for (IntWritable i : values) {
+                                sum += i.get();
+                        }
+
+                        // org.apache.hadoop.hbase.client.Put
+                        // Used to perform Put operations for a single row.
+                        // new Put(byte[] row)
+                        Put put = new Put(Bytes.toBytes(key.toString()));
+
+                        // add(byte[] family, byte[] qualifier, byte[] value)
+                        // 在main設定output format class 為 TableOutputFormat
+                        // TableReducer 內有定義 output Key class 必須為 Put 或 Delete
+                        put.add(Bytes.toBytes("content"), Bytes.toBytes("count"), Bytes
+                                        .toBytes(String.valueOf(sum)));
+
+                        // NullWritable.get(): Returns the single instance of this class.
+                        // NullWritable.write(): Serialize the fields of this object to out.
+                        context.write(new LongWritable(), put);
+                        // context.write(NullWritable.get(), put)
+                }
+        }
+
+        public static void main(String args[]) throws Exception {
+                // debug
+                String[] argv = { "/user/waue/input" };
+                args = argv;
+                String input = args[0];
+
+                String tablename = "wordcount";
+                String family = "content";
+
+                Configuration conf = new Configuration();
+                // OUTPUT_TABLE = "hbase.mapred.outputtable"
+                // conf.set 用於設定 如 core-site.xml 的 name 與 value
+                // 告訴程式 hbase.mapred.outputtable --> wordcount
+                conf.set(TableOutputFormat.OUTPUT_TABLE, tablename);
+                // 建立hbase 的table 否則沒先建立會出錯
+                CreateTable.createHBaseTable(tablename, family);
+
+                Job job = new Job(conf, "WordCount table with " + input);
+
+                job.setJarByClass(CountToHBaseReducer.class);
+
+                job.setMapperClass(HtMap.class);
+                job.setReducerClass(HtReduce.class);
+                // 此範例的輸出為 <Text,IntWritable> 因此其實可以省略宣告
+                // set{Map|Reduce}Output{Key|Value}Class()
+                job.setMapOutputKeyClass(Text.class);
+                job.setMapOutputValueClass(IntWritable.class);
+                // InputFormat 只有一個子介面
+                // FileInputFormat <-(SequenceFileInputFormat,TextInputFormat)
+                // 其中TextInputFormat 最常用 ，預設輸入為 LongWritable,Text
+                // 另外HBase 則設計了一個子類別 TableInputFormat
+                job.setInputFormatClass(TextInputFormat.class);
+                // TAbleOutputFormat
+                // 宣告此行則可使 reduce 輸出為 HBase 的table
+                job.setOutputFormatClass(TableOutputFormat.class);
+
+                // 原本設定輸入檔案為 Config.setInputPath(Path) 卻改為
+                // FileInputFormat.addInputPath(Job, Path()) 的設計，
+                // 猜測應該是考慮某些檔案操作並不需要跑mapreduce的Job，因此提到外面
+                FileInputFormat.addInputPath(job, new Path(input));
+
+                System.exit(job.waitForCompletion(true) ? 0 : 1);
+        }
+}
 }}}