Index: src/main/java/org/apache/hadoop/hbase/mapreduce/CellCounter.java =================================================================== --- src/main/java/org/apache/hadoop/hbase/mapreduce/CellCounter.java (revision ) +++ src/main/java/org/apache/hadoop/hbase/mapreduce/CellCounter.java (revision ) @@ -0,0 +1,187 @@ +/** + * Copyright 2008 The Apache Software Foundation + * + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.hadoop.hbase.mapreduce; + +import java.io.IOException; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.hbase.HBaseConfiguration; +import org.apache.hadoop.hbase.KeyValue; +import org.apache.hadoop.hbase.client.Result; +import org.apache.hadoop.hbase.client.Scan; +import org.apache.hadoop.hbase.filter.FirstKeyOnlyFilter; +import org.apache.hadoop.hbase.io.ImmutableBytesWritable; +import org.apache.hadoop.hbase.util.Bytes; +import org.apache.hadoop.mapreduce.Job; +import org.apache.hadoop.mapreduce.lib.output.NullOutputFormat; +import org.apache.hadoop.util.GenericOptionsParser; +import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; +import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.mapreduce.lib.reduce.IntSumReducer; +import org.apache.hadoop.io.IntWritable; +import org.apache.hadoop.mapreduce.Reducer; +import org.apache.hadoop.io.Text; + + +/** + * A job with a just a map phase to count rows. Map outputs table rows IF the + * input row has columns that have content. + */ +public class CellCounter { + + /** + * Name of this 'program'. + */ + static final String NAME = "CellCounter"; + + /** + * Mapper that runs the count. + */ + static class CellCounterMapper + extends TableMapper { + + /** + * Counter enumeration to count the actual rows. + */ + public static enum Counters { + ROWS + } + + /** + * Maps the data. + * + * @param row The current table row key. + * @param values The columns. + * @param context The current context. + * @throws IOException When something is broken with the data. + * @see org.apache.hadoop.mapreduce.Mapper#map(KEYIN, VALUEIN, + * org.apache.hadoop.mapreduce.Mapper.Context) + */ + + @Override + public void map(ImmutableBytesWritable row, Result values, + Context context) + throws IOException { + String currentFamilyName = null; + String currentQualifierName = null; + String currentRowKey = null; + + try { + if (values != null) { + context.getCounter(Counters.ROWS).increment(1); + context.write(new Text("Total ROWS"), new IntWritable(1)); + } + + for (KeyValue value : values.list()) { + currentRowKey = Bytes.toString(value.getRow()); + String thisRowFamilyName = Bytes.toString(value.getFamily()); + if (thisRowFamilyName != null && !thisRowFamilyName.equals(currentFamilyName)) { + currentFamilyName = thisRowFamilyName; + context.getCounter("CF", thisRowFamilyName).increment(1); + context.write(new Text("Total Families Across all Rows"), new IntWritable(1)); + context.write(new Text(thisRowFamilyName), new IntWritable(1)); + } + String thisRowQualifierName = thisRowFamilyName + ":" + Bytes.toString(value.getQualifier()); + if (thisRowQualifierName != null && !thisRowQualifierName.equals(currentQualifierName)) { + currentQualifierName = thisRowQualifierName; + context.getCounter("CFQL", thisRowQualifierName).increment(1); + context.write(new Text("Total Qualifiers across all Rows"), new IntWritable(1)); + context.write(new Text(thisRowQualifierName), new IntWritable(1)); + // Intialize versions + context.getCounter("QL_VERSIONS", currentRowKey + ":" + thisRowQualifierName).increment(1); + context.write(new Text(currentRowKey + ":" + thisRowQualifierName + "_Versions"), new IntWritable(1)); + + } else { + // Increment versions + currentQualifierName = thisRowQualifierName; + context.getCounter("QL_VERSIONS", currentRowKey + ":" + thisRowQualifierName).increment(1); + context.write(new Text(currentRowKey + ":" + thisRowQualifierName + "_Versions"), new IntWritable(1)); + } + } + } catch (InterruptedException e) { + e.printStackTrace(); + } + } + } + + static class IntSumReducer extends Reducer { + + private IntWritable result = new IntWritable(); + public void reduce(Key key, Iterable values, + Context context) throws IOException, InterruptedException { + int sum = 0; + for (IntWritable val : values) { + sum += val.get(); + } + result.set(sum); + context.write(key, result); + } + + } + + /** + * Sets up the actual job. + * + * @param conf The current configuration. + * @param args The command line parameters. + * @return The newly created job. + * @throws IOException When setting up the job fails. + */ + public static Job createSubmittableJob(Configuration conf, String[] args) + throws IOException { + String tableName = args[0]; + Path outputDir = new Path(args[1]); + Job job = new Job(conf, NAME + "_" + tableName); + job.setJarByClass(CellCounter.class); + Scan scan = new Scan(); + scan.setMaxVersions(Integer.MAX_VALUE); + TableMapReduceUtil.initTableMapperJob(tableName, scan, + CellCounterMapper.class, ImmutableBytesWritable.class, Result.class, job); + job.setNumReduceTasks(1); + job.setMapOutputKeyClass(Text.class); + job.setMapOutputValueClass(IntWritable.class); + job.setOutputFormatClass(TextOutputFormat.class); + job.setOutputKeyClass(Text.class); + job.setOutputValueClass(IntWritable.class); + FileOutputFormat.setOutputPath(job, outputDir); + job.setReducerClass(IntSumReducer.class); + return job; + } + + /** + * Main entry point. + * + * @param args The command line parameters. + * @throws Exception When running the job fails. + */ + public static void main(String[] args) throws Exception { + Configuration conf = HBaseConfiguration.create(); + String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); + if (otherArgs.length < 1) { + System.err.println("ERROR: Wrong number of parameters: " + args.length); + System.err.println("Usage: CellCounter "); + System.exit(-1); + } + Job job = createSubmittableJob(conf, otherArgs); + System.exit(job.waitForCompletion(true) ? 0 : 1); + } +}