Java FileInputFormat.addInputPaths方法代码示例

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
public int run(String[] args) throws Exception {

    if(args.length < 2) {
      printUsage();
      return 2;
    }

    Job job = Job.getInstance(getConf());
    job.setJobName("MultiFileWordCount");
    job.setJarByClass(MultiFileWordCount.class);

    //set the InputFormat of the job to our InputFormat
    job.setInputFormatClass(MyInputFormat.class);
    
    // the keys are words (strings)
    job.setOutputKeyClass(Text.class);
    // the values are counts (ints)
    job.setOutputValueClass(IntWritable.class);

    //use the defined mapper
    job.setMapperClass(MapClass.class);
    //use the WordCount Reducer
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);

    FileInputFormat.addInputPaths(job, args[0]);
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    return job.waitForCompletion(true) ? 0 : 1;
  }
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
@Override
public int run(String[] args)
        throws Exception
{
    Job job = Job.getInstance(getConf());

    job.setJarByClass(WordDistributionStatisticsCollector.class);
    job.setJobName(WordDistributionStatisticsCollector.class.getName());

    // mapper
    job.setMapperClass(getMapperClass());
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    // reducer
    job.setReducerClass(SumReducer.class);
    job.setInputFormatClass(getInputFormatClass());
    job.setOutputFormatClass(TextOutputFormat.class);

    // paths
    String commaSeparatedInputFiles = args[0];
    String outputPath = args[1];

    FileInputFormat.addInputPaths(job, commaSeparatedInputFiles);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job.waitForCompletion(true) ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
@Override
public int run(String[] args)
        throws Exception
{
    Configuration conf = getConf();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    Job job = Job.getInstance();
    job.setJarByClass(TopDomainCounter.class);

    job.setJobName(TopDomainCounter.class.getName());

    // mapper
    job.setMapperClass(DomainMapper.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);

    // combiner + reducer
    job.setCombinerClass(TextLongCountingReducer.class);
    job.setReducerClass(TextLongCountingReducer.class);

    job.setInputFormatClass(WARCInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    // paths
    String commaSeparatedInputFiles = otherArgs[0];
    String outputPath = otherArgs[1];

    FileInputFormat.addInputPaths(job, commaSeparatedInputFiles);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job.waitForCompletion(true) ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
@Override
public int run(String[] args)
        throws Exception
{
    org.apache.hadoop.conf.Configuration conf = getConf();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    System.out.println("Other args: " + Arrays.toString(otherArgs));

    Job job = Job.getInstance();
    job.setJarByClass(OriginalURLGrep.class);

    job.setJobName(OriginalURLGrep.class.getName());
    job.setMapperClass(OrigURLGrepMapper.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(NullWritable.class);

    // cache file - IDs for index
    String idFile = args[2];
    System.err.println("idFile: " + idFile);
    job.addCacheFile(new URI(idFile + "#" + NODE_IDS));

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    String commaSeparatedInputFiles = otherArgs[0];
    String outputPath = otherArgs[1];
    System.err.println("commaSeparatedInputFiles: " + commaSeparatedInputFiles);
    System.err.println("outputPath: " + outputPath);

    FileInputFormat.addInputPaths(job, commaSeparatedInputFiles);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job.waitForCompletion(true) ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
@Override
public int run(String[] args)
        throws Exception
{
    Job job = Job.getInstance(getConf());

    for (Map.Entry<String, String> next : job.getConfiguration()) {
        System.out.println(next.getKey() + ": " + next.getValue());
    }

    job.setJarByClass(ClueWebTRECIdFileExtractor.class);
    job.setJobName(ClueWebTRECIdFileExtractor.class.getName());

    // mapper
    job.setMapperClass(MapperClass.class);

    // input
    job.setInputFormatClass(WARCInputFormat.class);

    // output
    job.setOutputFormatClass(WARCOutputFormat.class);
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(WARCWritable.class);
    FileOutputFormat.setCompressOutput(job, true);

    // paths
    String commaSeparatedInputFiles = args[0];
    String outputPath = args[1];

    // load IDs to be searched for
    job.getConfiguration().set(MAPREDUCE_MAPPER_TREC_IDS, loadTrecIds(args[2]));

    FileInputFormat.addInputPaths(job, commaSeparatedInputFiles);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job.waitForCompletion(true) ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
@Override
public int run(String[] args)
        throws Exception
{
    Configuration conf = getConf();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    Job job = Job.getInstance();
    job.setJarByClass(SimpleTextSearch.class);

    job.setJobName(SimpleTextSearch.class.getName());

    // mapper
    job.setMapperClass(TextSearchMapper.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);

    // combiner + reducer
    job.setCombinerClass(TextLongCountingReducer.class);
    job.setReducerClass(TextLongCountingReducer.class);

    job.setInputFormatClass(WARCInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    // paths
    String commaSeparatedInputFiles = otherArgs[0];
    String outputPath = otherArgs[1];

    // regex with a phrase to be searched for
    String regex = otherArgs[2];
    job.getConfiguration().set(MAPREDUCE_MAP_REGEX, regex);

    FileInputFormat.addInputPaths(job, commaSeparatedInputFiles);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job.waitForCompletion(true) ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
@Override
public int run(String[] args)
        throws Exception
{
    Configuration conf = getConf();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    Job job = Job.getInstance();
    job.setJarByClass(WordCounterExample.class);

    job.setJobName(WordCounterExample.class.getName());

    // mapper
    job.setMapperClass(WordCounterMapper.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);

    // combiner + reducer
    job.setCombinerClass(TextLongCountingReducer.class);
    job.setReducerClass(TextLongCountingReducer.class);

    job.setInputFormatClass(WARCInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    // paths
    String commaSeparatedInputFiles = otherArgs[0];
    String outputPath = otherArgs[1];

    FileInputFormat.addInputPaths(job, commaSeparatedInputFiles);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job.waitForCompletion(true) ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
/**
 * Job configurator
 *
 * @param job                      job instance
 * @param jarByClass               class of the jar
 * @param mapperClass              mapper
 * @param reducerClass             reducer
 * @param commaSeparatedInputFiles input paths
 * @param outputPath               output
 * @throws IOException I/O exception
 */
public static void configureJob(Job job, Class<?> jarByClass,
        Class<? extends Mapper> mapperClass, Class<? extends Reducer> reducerClass,
        String commaSeparatedInputFiles, String outputPath)
        throws IOException
{
    job.setJarByClass(jarByClass);
    job.setJobName(jarByClass.getName());

    // mapper
    job.setMapperClass(mapperClass);

    // reducer
    job.setReducerClass(reducerClass);

    // input-output is warc
    job.setInputFormatClass(WARCInputFormat.class);
    // prevent producing empty files
    LazyOutputFormat.setOutputFormatClass(job, WARCOutputFormat.class);

    // intermediate data
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(WARCWritable.class);

    // output data
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(WARCWritable.class);

    // set output compression to GZip
    FileOutputFormat.setCompressOutput(job, true);
    FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);

    FileInputFormat.addInputPaths(job, commaSeparatedInputFiles);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));
}
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
@Override
public int run(String[] args)
        throws Exception
{
    Job job = Job.getInstance(getConf());

    job.setJarByClass(Phase3Step1ExtractNearDupInfo.class);
    job.setJobName(Phase3Step1ExtractNearDupInfo.class.getName());

    // mapper
    job.setMapperClass(MapperClass.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(DocumentInfo.class);

    // reducer
    job.setReducerClass(DeDuplicationTextOutputReducer.class);
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(List.class);

    job.setInputFormatClass(WARCInputFormat.class);
    LazyOutputFormat.setOutputFormatClass(job, DocumentInfoOutputFormat.class);

    // paths
    String commaSeparatedInputFiles = args[0];
    String outputPath = args[1];

    FileInputFormat.addInputPaths(job, commaSeparatedInputFiles);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job.waitForCompletion(true) ? 0 : 1;

}
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
@Override
public int run(String[] args)
        throws Exception
{
    Job job = Job.getInstance(getConf());
    //set from the command line

    job.setJarByClass(Phase2ExactMatchDeDuplication.class);
    job.setJobName(Phase2ExactMatchDeDuplication.class.getName());

    // mapper
    job.setMapperClass(ExactMatchDetectionMapper.class);

    // we will compress the mapper's output (use fast Snappy compressor)
    job.getConfiguration().setBoolean(Job.MAP_OUTPUT_COMPRESS, true);
    job.getConfiguration()
            .setClass(Job.MAP_OUTPUT_COMPRESS_CODEC, SnappyCodec.class, CompressionCodec.class);

    // reducer
    job.setReducerClass(UniqueWarcWriterReducer.class);
    // no combiner, as the output classes in mapper and reducer are different!

    // input-output is warc
    job.setInputFormatClass(WARCInputFormat.class);
    job.setOutputFormatClass(WARCOutputFormat.class);

    // mapper output data
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(WARCWritable.class);

    // set output compression to GZip
    FileOutputFormat.setCompressOutput(job, true);
    FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);

    FileInputFormat.addInputPaths(job, args[0]);
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    return job.waitForCompletion(true) ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
@Override
public int run(String[] args)
        throws Exception
{
    Job job = Job.getInstance(getConf());

    job.setJarByClass(Phase3Step3NearDupTuplesCreation.class);
    job.setJobName(Phase3Step3NearDupTuplesCreation.class.getName());

    // mapper
    job.setMapperClass(CreateTuplesMapper.class);
    job.setMapOutputKeyClass(NullWritable.class);
    job.setMapOutputValueClass(TreeSet.class);

    job.setInputFormatClass(TextInputFormat.class);
    LazyOutputFormat.setOutputFormatClass(job, TextOutputFormat.class);

    // paths
    String commaSeparatedInputFiles = args[0];
    String outputPath = args[1];

    FileInputFormat.addInputPaths(job, commaSeparatedInputFiles);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    job.setNumReduceTasks(0); //must be added or the mapper wont be called

    return job.waitForCompletion(true) ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
@Override
public int run(String[] args)
        throws Exception
{
    Job job = Job.getInstance(getConf());
    // set from the command line

    job.setJarByClass(Phase1FullJob.class);
    job.setJobName(Phase1FullJob.class.getName());

    // mapper
    job.setMapperClass(MapperClass.class);

    // we will compress the mapper's output (use fast Snappy compressor)
    job.getConfiguration().setBoolean(Job.MAP_OUTPUT_COMPRESS, true);
    job.getConfiguration()
            .setClass(Job.MAP_OUTPUT_COMPRESS_CODEC, SnappyCodec.class, CompressionCodec.class);

    // reducer
    job.setReducerClass(SimpleWarcWriterReducer.class);

    // input-output is warc
    job.setInputFormatClass(WARCInputFormat.class);
    job.setOutputFormatClass(WARCOutputFormat.class);

    // mapper output data
    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(WARCWritable.class);

    // set output compression to GZip
    FileOutputFormat.setCompressOutput(job, true);
    FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);

    FileInputFormat.addInputPaths(job, args[0]);
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    return job.waitForCompletion(true) ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
@Override
public int run(String[] args)
        throws Exception
{
    Configuration conf = getConf();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    Job job = Job.getInstance(conf);
    job.setJarByClass(TextToSentencesSplitter.class);

    job.setJobName(TextToSentencesSplitter.class.getName());

    // mapper
    job.setMapperClass(TextToSentencesSplitter.MapperClass.class);
    job.setInputFormatClass(WARCInputFormat.class);

    // reducer
    job.setReducerClass(ReducerClass.class);
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(Text.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    // paths
    String commaSeparatedInputFiles = otherArgs[0];
    String outputPath = otherArgs[1];

    FileInputFormat.addInputPaths(job, commaSeparatedInputFiles);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job.waitForCompletion(true) ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
/**
 * {@inheritDoc}
 */
@Override
public int run(String[] args)
        throws Exception
{

    Job job = Job.getInstance(getConf());
    // set from the command line
    job.setJarByClass(URIExtractor.class);
    job.setJobName(URIExtractor.class.getName());

    // mapper
    job.setMapperClass(URIExtractorMapper.class);
    job.setReducerClass(URIExtractorReducer.class);

    // input-output is warc
    job.setInputFormatClass(WARCInputFormat.class);
    // is necessary, so that Hadoop does not mix the map input format up.
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(NullWritable.class);

    // set output compression to GZip
    FileOutputFormat.setCompressOutput(job, true);
    FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);

    FileInputFormat.addInputPaths(job, args[0]);
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    return job.waitForCompletion(true) ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; //导入方法依赖的package包/类
@Override
public int run(String[] args)
        throws Exception
{
    Job job = Job.getInstance(getConf());

    for (Map.Entry<String, String> next : job.getConfiguration()) {
        System.out.println(next.getKey() + ": " + next.getValue());
    }

    job.setJarByClass(PagesByURLExtractor.class);
    job.setJobName(PagesByURLExtractor.class.getName());

    // mapper
    job.setMapperClass(MapperClass.class);

    // input
    job.setInputFormatClass(WARCInputFormat.class);

    // output
    job.setOutputFormatClass(WARCOutputFormat.class);
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(WARCWritable.class);
    FileOutputFormat.setCompressOutput(job, true);

    // paths
    String commaSeparatedInputFiles = args[0];
    String outputPath = args[1];

    // load IDs to be searched for
    job.getConfiguration().set(MAPREDUCE_MAPPER_URLS, loadURLs(args[2]));

    FileInputFormat.addInputPaths(job, commaSeparatedInputFiles);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job.waitForCompletion(true) ? 0 : 1;
}