This example will count the number of distinct instances of a value in a table and write those summarized counts in another table.
Configuration config = HBaseConfiguration.create();
Job job = new Job(config,"ExampleSummary");
job.setJarByClass(MySummaryJob.class); // class that contains mapper and reducer
Scan scan = new Scan();
scan.setCaching(500); // 1 is the default in Scan, which will be bad for MapReduce jobs
scan.setCacheBlocks(false); // don't set to true for MR jobs// set other scan attrs
TableMapReduceUtil.initTableMapperJob(
sourceTable, // input table
scan, // Scan instance to control CF and attribute selection
MyMapper.class, // mapper class
Text.class, // mapper output key
IntWritable.class, // mapper output value
job);
TableMapReduceUtil.initTableReducerJob(
targetTable, // output table
MyTableReducer.class, // reducer class
job);
job.setNumReduceTasks(1); // at least one, adjust as requiredboolean b = job.waitForCompletion(true);
if (!b) {
thrownewIOException("error with job!");
}
this is using HBase as a MapReduce source but HDFS as the sink.
Configuration config = HBaseConfiguration.create();
Job job = new Job(config,"ExampleSummaryToFile");
job.setJarByClass(MySummaryFileJob.class); // class that contains mapper and reducer
Scan scan = new Scan();
scan.setCaching(500); // 1 is the default in Scan, which will be bad for MapReduce jobs
scan.setCacheBlocks(false); // don't set to true for MR jobs// set other scan attrs
TableMapReduceUtil.initTableMapperJob(
sourceTable, // input table
scan, // Scan instance to control CF and attribute selection
MyMapper.class, // mapper class
Text.class, // mapper output key
IntWritable.class, // mapper output value
job);
job.setReducerClass(MyReducer.class); // reducer class
job.setNumReduceTasks(1); // at least one, adjust as required
FileOutputFormat.setOutputPath(job, new Path("/tmp/mr/mySummaryFile")); // adjust directories as requiredboolean b = job.waitForCompletion(true);
if (!b) {
thrownewIOException("error with job!");
}