add some comments for the mapreduce example code

Author: Qianxi Zhang

hadoop/src/main/java/cn/chinahadoop/mapreduce/Grep.java

@@ -29,18 +29,19 @@ public int run(String[] args) throws Exception {
 			ToolRunner.printGenericCommandUsage(System.out);
 			return 2;
 		}
-
+        // the temp dir between two mapreduce jobs
 		Path tempDir = new Path("grep-temp-" + Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));
 
 		Configuration conf = getConf();
 		conf.set(RegexMapper.PATTERN, args[2]);
 		if (args.length == 4)
 			conf.set(RegexMapper.GROUP, args[3]);
-
+         //the first job
+		// word count
 		Job grepJob = new Job(conf);
 
 		try {
-
+            //define the first job
 			grepJob.setJobName("grep-search");
 
 			FileInputFormat.setInputPaths(grepJob, args[0]);
@@ -49,22 +50,23 @@ public int run(String[] args) throws Exception {
 
 			grepJob.setCombinerClass(LongSumReducer.class);
 			grepJob.setReducerClass(LongSumReducer.class);
-
+            // output to tempDir
 			FileOutputFormat.setOutputPath(grepJob, tempDir);
 			grepJob.setOutputFormatClass(SequenceFileOutputFormat.class);
 			grepJob.setOutputKeyClass(Text.class);
 			grepJob.setOutputValueClass(LongWritable.class);
-
+            // result: word + count
 			grepJob.waitForCompletion(true);
-
+            //the second job
+			//sort
 			Job sortJob = new Job(conf);
 			sortJob.setJobName("grep-sort");
-
+            //tempDir to input
 			FileInputFormat.setInputPaths(sortJob, tempDir);
 			sortJob.setInputFormatClass(SequenceFileInputFormat.class);
 
 			sortJob.setMapperClass(InverseMapper.class);
-
+            //just write the sort data out
 			sortJob.setNumReduceTasks(1); // write a single file
 			FileOutputFormat.setOutputPath(sortJob, new Path(args[1]));
 			sortJob.setSortComparatorClass( // sort by decreasing freq

hadoop/src/main/java/cn/chinahadoop/mapreduce/InvertedIndex.java

@@ -80,10 +80,10 @@ public static void main(String[] args) throws Exception {
 		job.setInputFormatClass(TextInputFormat.class);
 		job.setOutputFormatClass(TextOutputFormat.class);
 
-		FileInputFormat.addInputPath(job, new Path(args[0]));
-		FileOutputFormat.setOutputPath(job, new Path(args[1]));
+		FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
+		FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
 
-		Path outputPath = new Path(args[1]);
+		Path outputPath = new Path(otherArgs[1]);
 
 		outputPath.getFileSystem(conf).delete(outputPath);
 

hadoop/src/main/java/cn/chinahadoop/mapreduce/JobFailureTest.java

@@ -25,6 +25,8 @@ public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritab
 		private Text word = new Text();
 
 		public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
+			//get the task id from context
+			//for the first map task(task id=0), the task always fails
 			int id = context.getTaskAttemptID().getTaskID().getId();
 			System.out.println("id:" + id);
 			if (id == 0)

hadoop/src/main/java/cn/chinahadoop/mapreduce/TaskAttemptTest.java

@@ -25,6 +25,8 @@ public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritab
 		private Text word = new Text();
 
 		public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
+			//get the task attempt id
+			//for the 4 previous attempt for the task, the attempt always fails.   
 			int id = context.getTaskAttemptID().getId();
 			System.out.println("id:" + id);
 			if (id < 4)