Changes between Initial Version and Version 1 of waue/2010/0115-WordCountV1

Timestamp:

Jan 19, 2010, 7:49:29 PM (15 years ago)

Author:

waue

Comment:

--

waue/2010/0115-WordCountV1

@@ +1 @@
+ = Word Count V1 =
+
+{{{
+#!java
+
+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;
+//WordCount
+//說明： 
+//      用於字數統計
+//
+//測試方法：
+//      將此程式運作在hadoop 0.20 平台上，執行：
+//      ---------------------------
+//      hadoop jar WordCount.jar <input> <output>
+//      ---------------------------
+//
+//注意：
+//1.    在hdfs 上來源檔案的路徑為 你所指定的 <input>
+//請注意必須先放資料到此hdfs上的資料夾內，且此資料夾內只能放檔案，不可再放資料夾
+//2.    運算完後，程式將執行結果放在hdfs 的輸出路徑為 你所指定的 <output>
+//      
+public class WordCount {
+
+        public static class TokenizerMapper extends
+                        Mapper<Object, Text, Text, IntWritable> {
+
+                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<Text, IntWritable, Text, IntWritable> {
+                private IntWritable result = new IntWritable();
+
+                public void reduce(Text key, Iterable<IntWritable> 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 {
+                // debug using
+//              String[] argv = { "input", "output-wc" };
+//              args = argv;
+                
+                Configuration conf = new Configuration();
+                
+                String[] otherArgs = new GenericOptionsParser(conf, args)
+                                .getRemainingArgs();
+                if (otherArgs.length != 2) {
+                        System.err
+                                        .println("Usage: hadoop jar WordCount.jar <input> <output>");
+                        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(args[0]));
+                FileOutputFormat.setOutputPath(job, new Path(args[1]));
+                CheckAndDelete.checkAndDelete(args[1], conf);
+                System.exit(job.waitForCompletion(true) ? 0 : 1);
+        }
+}
+
+}}}