package hip.ch3.json; import hip.util.Cli; import hip.util.CliCommonOpts; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configured; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.MapWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.Writable; 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.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; import org.apache.hadoop.util.Tool; import org.apache.hadoop.util.ToolRunner; import org.slf4j.Logger; import org.slf4j.LoggerFactory; import java.io.IOException; public final class JsonMapReduce extends Configured implements Tool { private static final Logger log = LoggerFactory.getLogger (JsonMapReduce.class); public static class Map extends Mapper<LongWritable, MapWritable, Text, Text> { @Override protected void map(LongWritable key, MapWritable value, Context context) throws IOException, InterruptedException { for (java.util.Map.Entry<Writable, Writable> entry : value .entrySet()) { context.write((Text) entry.getKey(), (Text) entry.getValue()); } } } /** * Main entry point for the example. * * @param args arguments * @throws Exception when something goes wrong */ public static void main(final String[] args) throws Exception { int res = ToolRunner.run(new Configuration(), new JsonMapReduce(), args); System.exit(res); } /** * The MapReduce driver - setup and launch the job. * * @param args the command-line arguments * @return the process exit code * @throws Exception if something goes wrong */ public int run(final String[] args) throws Exception { Cli cli = Cli.builder().setArgs(args).addOptions(CliCommonOpts.MrIoOpts.values()).build(); int result = cli.runCmd(); if (result != 0) { return result; } Path inputPath = new Path(cli.getArgValueAsString(CliCommonOpts.MrIoOpts.INPUT)); Path outputPath = new Path(cli.getArgValueAsString(CliCommonOpts.MrIoOpts.OUTPUT)); Configuration conf = super.getConf(); Job job = new Job(conf); job.setJarByClass(JsonMapReduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setMapperClass(Map.class); job.setInputFormatClass(JsonInputFormat.class); job.setNumReduceTasks(0); job.setOutputFormatClass(TextOutputFormat.class); FileInputFormat.setInputPaths(job, inputPath); FileOutputFormat.setOutputPath(job, outputPath); if (job.waitForCompletion(true)) { return 0; } return 1; } }