Example usage for org.apache.hadoop.mapred JobConf setInputFormat

List of usage examples for org.apache.hadoop.mapred JobConf setInputFormat

  1. HOME
  2. Java
  3. org.apache.hadoop
  4. org.apache.hadoop.mapred.*
  5. JobConf
  6. setInputFormat

Introduction

In this page you can find the example usage for org.apache.hadoop.mapred JobConf setInputFormat.

Prototype

public void setInputFormat(Class<? extends InputFormat> theClass)

Source Link

Document

Set the InputFormat implementation for the map-reduce job.

Usage

From source file:IndexService.IndexMergeMR.java

License:Open Source License

public static RunningJob run(String inputfiles, String outputdir, Configuration conf) {
    if (inputfiles == null || outputdir == null)
        return null;

    JobConf job = new JobConf(conf);
    job.setJobName("MergeIndexMR");
    job.setJarByClass(IndexMergeMR.class);
    job.setNumReduceTasks(1);/*from   ww w .  j av a2  s.  com*/
    FileSystem fs = null;
    try {
        fs = FileSystem.get(job);
        fs.delete(new Path(outputdir), true);

        String[] ifs = inputfiles.split(",");
        TreeSet<String> files = new TreeSet<String>();
        for (int i = 0; i < ifs.length; i++) {
            IFormatDataFile ifdf = new IFormatDataFile(job);
            ifdf.open(ifs[i]);
            Collection<String> strs = ifdf.fileInfo().head().getUdi().infos().values();
            for (String str : strs) {
                files.add(str);
            }
            ifdf.close();
        }
        StringBuffer sb = new StringBuffer();
        for (String str : files) {
            sb.append(str + ",");
        }
        job.set(ConstVar.HD_index_filemap, sb.substring(0, sb.length() - 1));

        IFormatDataFile ifdf = new IFormatDataFile(job);
        ifdf.open(ifs[0]);

        HashMap<Integer, IRecord.IFType> map = ifdf.fileInfo().head().fieldMap().fieldtypes();
        ArrayList<String> fieldStrings = new ArrayList<String>();

        for (int i = 0; i < map.size(); i++) {
            IRecord.IFType type = map.get(i);
            fieldStrings.add(type.type() + ConstVar.RecordSplit + type.idx());
        }

        job.setStrings(ConstVar.HD_fieldMap, fieldStrings.toArray(new String[fieldStrings.size()]));
        job.set("datafiletype", ifdf.fileInfo().head().getUdi().infos().get(123456));
        ifdf.close();
    } catch (Exception e2) {
        e2.printStackTrace();
    }

    FileInputFormat.setInputPaths(job, inputfiles);
    FileOutputFormat.setOutputPath(job, new Path(outputdir));

    job.setOutputKeyClass(IndexKey.class);
    job.setOutputValueClass(IndexValue.class);

    job.setPartitionerClass(IndexMergePartitioner.class);

    job.setMapperClass(MergeIndexMap.class);
    job.setCombinerClass(MergeIndexReduce.class);
    job.setReducerClass(MergeIndexReduce.class);

    job.setInputFormat(IndexMergeIFormatInputFormat.class);
    job.setOutputFormat(IndexMergeIFormatOutputFormat.class);

    try {
        JobClient jc = new JobClient(job);
        return jc.submitJob(job);
    } catch (IOException e) {
        e.printStackTrace();
        return null;
    }
}

From source file:IndexService.IndexMR.java

License:Open Source License

public static RunningJob run(Configuration conf2, String inputfiles, boolean column, String ids,
        String outputdir) {//w  w w. java2  s.c  o m
    if (inputfiles == null || outputdir == null)
        return null;

    JobConf conf = new JobConf(conf2);
    conf.setJobName("IndexMR:\t" + ids);
    conf.setJarByClass(IndexMR.class);
    FileSystem fs = null;
    try {
        fs = FileSystem.get(conf);
        fs.delete(new Path(outputdir), true);
    } catch (IOException e3) {
        e3.printStackTrace();
    }

    conf.set("index.ids", ids);
    if (column) {
        conf.set("datafiletype", "column");
    } else {
        conf.set("datafiletype", "format");
    }

    String[] ifs = inputfiles.split(",");
    long wholerecnum = 0;

    String[] idxs = ids.split(",");
    String[] fieldStrings = new String[idxs.length + 2];

    if (!column) {
        IFormatDataFile ifdf;
        try {
            ifdf = new IFormatDataFile(conf);
            ifdf.open(ifs[0]);
            for (int i = 0; i < idxs.length; i++) {
                int id = Integer.parseInt(idxs[i]);
                byte type = ifdf.fileInfo().head().fieldMap().fieldtypes().get(id).type();
                fieldStrings[i] = type + ConstVar.RecordSplit + i;
            }
            ifdf.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    } else {
        try {
            IColumnDataFile icdf = new IColumnDataFile(conf);
            icdf.open(ifs[0]);
            for (int i = 0; i < idxs.length; i++) {
                int id = Integer.parseInt(idxs[i]);
                byte type = icdf.fieldtypes().get(id).type();
                fieldStrings[i] = type + ConstVar.RecordSplit + i;
            }
            icdf.close();
        } catch (IOException e) {
            e.printStackTrace();
        }

    }

    fieldStrings[fieldStrings.length - 2] = ConstVar.FieldType_Short + ConstVar.RecordSplit
            + (fieldStrings.length - 2);
    fieldStrings[fieldStrings.length - 1] = ConstVar.FieldType_Int + ConstVar.RecordSplit
            + (fieldStrings.length - 1);

    conf.setStrings(ConstVar.HD_fieldMap, fieldStrings);

    if (!column) {
        conf.set(ConstVar.HD_index_filemap, inputfiles);
        for (String file : ifs) {
            IFormatDataFile fff;
            try {
                fff = new IFormatDataFile(conf);
                fff.open(file);
                wholerecnum += fff.segIndex().recnum();
                fff.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    } else {
        HashSet<String> files = new HashSet<String>();
        for (String file : ifs) {
            files.add(file);
        }
        StringBuffer sb = new StringBuffer();
        for (String str : files) {
            sb.append(str).append(",");
        }
        conf.set(ConstVar.HD_index_filemap, sb.substring(0, sb.length() - 1));

        for (String file : files) {
            Path parent = new Path(file).getParent();
            try {
                FileStatus[] fss = fs.listStatus(parent);
                String openfile = "";
                for (FileStatus status : fss) {
                    if (status.getPath().toString().contains(file)) {
                        openfile = status.getPath().toString();
                        break;
                    }
                }
                IFormatDataFile fff = new IFormatDataFile(conf);
                fff.open(openfile);
                wholerecnum += fff.segIndex().recnum();
                fff.close();

            } catch (IOException e) {
                e.printStackTrace();
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
    }

    conf.setNumReduceTasks((int) ((wholerecnum - 1) / (100000000) + 1));

    FileInputFormat.setInputPaths(conf, inputfiles);
    Path outputPath = new Path(outputdir);
    FileOutputFormat.setOutputPath(conf, outputPath);

    conf.setOutputKeyClass(IndexKey.class);
    conf.setOutputValueClass(IndexValue.class);

    conf.setPartitionerClass(IndexPartitioner.class);

    conf.setMapperClass(IndexMap.class);
    conf.setCombinerClass(IndexReduce.class);
    conf.setReducerClass(IndexReduce.class);

    if (column) {
        conf.setInputFormat(IColumnInputFormat.class);
    } else {
        conf.setInputFormat(IFormatInputFormat.class);
    }
    conf.setOutputFormat(IndexIFormatOutputFormat.class);

    try {
        JobClient jc = new JobClient(conf);
        return jc.submitJob(conf);
    } catch (IOException e) {
        e.printStackTrace();
        return null;
    }
}

From source file:infinidb.hadoop.db.InfiniDBInputFormat.java

License:Apache License

/**
 * @InfiniDB//from w w w.ja  v a 2  s.co m
 * Initializes the map-part of the job with the appropriate input settings.
 * 
 * @param job The job
 * @param inputClass the class object implementing DBWritable, which is the 
 * Java object holding tuple fields.
 * @param tableName The table to read data from
 * @param conditions The condition which to select data with, eg. '(updated >
 * 20070101 AND length > 0)'
 * @param key the field name used for split key.
 * @param fieldNames The field names in the table
 * @see #setInput(JobConf, Class, String, String)
 */
public static void setInput(JobConf job, Class<? extends DBWritable> inputClass, String tableName,
        String conditions, String key, String... fieldNames) {

    job.setInputFormat(InfiniDBInputFormat.class);
    InfiniDBConfiguration dbConf = new InfiniDBConfiguration(job);
    dbConf.setInputClass(inputClass);
    dbConf.setInputTableName(tableName);
    dbConf.setInputFieldNames(fieldNames);
    dbConf.setInputConditions(conditions);
    dbConf.setSplitKey(key);
}

From source file:infinidb.hadoop.db.InfiniDBInputFormat.java

License:Apache License

/**
 * @InfiniDB//  ww w  . j a va2s. c o m
 * Initializes the map-part of the job with the appropriate input settings.
 * 
 * @param job The job
 * @param inputClass the class object implementing DBWritable, which is the 
 * Java object holding tuple fields.
 * @param inputQuery the input query to select fields. Example : 
 * "SELECT f1, f2, f3 FROM Mytable ORDER BY f1"
 * @param inputCountQuery the input query that returns the number of records in
 * the table. 
 * Example : "SELECT COUNT(f1) FROM Mytable"
 * @see #setInput(JobConf, Class, String, String, String, String...)
 */
public static void setInput(JobConf job, Class<? extends DBWritable> inputClass, String inputQuery,
        String inputCountQuery) {
    job.setInputFormat(InfiniDBInputFormat.class);

    InfiniDBConfiguration dbConf = new InfiniDBConfiguration(job);
    dbConf.setInputClass(inputClass);
    dbConf.setInputQuery(inputQuery);
    dbConf.setInputCountQuery(inputCountQuery);

}

From source file:infinidb.hadoop.example.InfiniDBOutputDriver.java

License:Apache License

public int run(String[] args) throws Exception {
    Configuration conf = new Configuration();
    JobConf jobconf = new JobConf(conf, InfiniDoopDriver.class);
    DBConfiguration.configureDB(jobconf, "com.mysql.jdbc.Driver", "jdbc:mysql://srvswint4/tpch1", "root", "");
    String[] fields = { "n_nationkey", "n_name" };
    String[] outFields = { "id", "name" };
    jobconf.setInputFormat(IDBFileInputFormat.class);
    jobconf.setOutputFormat(InfiniDBOutputFormat.class);
    jobconf.setOutputKeyClass(NullWritable.class);
    jobconf.setOutputValueClass(Text.class);
    InfiniDBOutputFormat.setOutput(jobconf, "db", outFields);
    InfiniDBConfiguration idbconf = new InfiniDBConfiguration(jobconf);
    idbconf.setInputPath("input");
    idbconf.setOutputPath("output");
    idbconf.setInfiniDBHome("/usr/local/Calpont");

    jobconf.setMapperClass(InfiniDoopMapper.class);
    jobconf.setNumMapTasks(1);// w  w  w .j ava  2 s.  com
    jobconf.setNumReduceTasks(2);
    JobClient client = new JobClient();
    client.setConf(jobconf);
    try {
        JobClient.runJob(jobconf);
    } catch (Exception e) {
        e.printStackTrace();
    }

    return 0;
}

From source file:infinidb.hadoop.example.InfiniDoopDriver.java

License:Apache License

public int run(String[] args) throws Exception {
    Configuration conf = new Configuration();
    JobConf jobconf = new JobConf(conf, InfiniDoopDriver.class);
    DBConfiguration.configureDB(jobconf, "com.mysql.jdbc.Driver", "jdbc:mysql://srvswint4/tpch1", "root", "");
    String[] fields = { "n_nationkey", "n_name" };
    jobconf.setInputFormat(InfiniDBInputFormat.class);

    jobconf.setOutputKeyClass(LongWritable.class);
    jobconf.setOutputValueClass(Text.class);

    InfiniDBInputFormat.setInput(jobconf, InfiniDoopRecord.class, "nation", null, "n_nationkey", fields);

    InfiniDBConfiguration idbconf = new InfiniDBConfiguration(jobconf);
    idbconf.setOutputPath("output2");
    jobconf.setMapperClass(InfiniDoopInputMapper.class);
    jobconf.setNumMapTasks(4);//from   ww w .  jav  a2  s. co m
    jobconf.setNumReduceTasks(1);
    jobconf.set("mapred.textoutputformat.separator", "|");
    JobClient client = new JobClient();

    client.setConf(jobconf);
    try {
        JobClient.runJob(jobconf);
    } catch (Exception e) {
        e.printStackTrace();
    }

    return 0;
}

From source file:invertedIndex.startJob.java

public static void start(String[] args) {
    try {/*from w w  w .  j  a  v a 2s  .c  om*/
        JobConf conf = new JobConf(WordCount.class);
        conf.setJobName("wordcount");

        conf.setOutputKeyClass(Text.class);
        conf.setOutputValueClass(IntWritable.class);

        lineIndexMapper Map = new lineIndexMapper();
        conf.setMapperClass(Map.getClass());

        lineIndexReducer Reduce = new lineIndexReducer();
        conf.setCombinerClass(Reduce.getClass());
        conf.setReducerClass(Reduce.getClass());

        conf.setInputFormat(TextInputFormat.class);
        conf.setOutputFormat(TextOutputFormat.class);

        FileInputFormat.setInputPaths(conf, new Path(args[1]));

        Path outputDir = new Path(args[2]);

        outputDir.getFileSystem(conf).delete(outputDir, true);
        FileSystem fs = FileSystem.get(conf);
        fs.delete(outputDir, true);

        FileOutputFormat.setOutputPath(conf, outputDir);

        JobClient.runJob(conf);

    } catch (Exception Exp) {

        Exp.printStackTrace();
    }
}

From source file:io.aos.t4f.hadoop.mapred.WordCountTest.java

License:Apache License

private JobConf createJobConf() {
    JobConf conf = mrCluster.createJobConf();
    conf.setJobName("wordcount test");

    conf.setMapperClass(WordCountMapper.class);
    conf.setReducerClass(WordCountReducer.class);

    conf.setInputFormat(TextInputFormat.class);
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(IntWritable.class);
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);
    conf.setNumMapTasks(1);/*  www . ja  v a2s  . c  o m*/
    conf.setNumReduceTasks(1);
    FileInputFormat.setInputPaths(conf, input);
    FileOutputFormat.setOutputPath(conf, output);
    return conf;
}

From source file:io.bfscan.clueweb12.DumpWarcRecordsToPlainText.java

License:Apache License

/**
 * Runs this tool.//w  w  w.j a v a 2  s.  c  o  m
 */
@SuppressWarnings("static-access")
public int run(String[] args) throws Exception {
    Options options = new Options();

    options.addOption(
            OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT_OPTION));
    options.addOption(
            OptionBuilder.withArgName("path").hasArg().withDescription("output path").create(OUTPUT_OPTION));

    CommandLine cmdline;
    CommandLineParser parser = new GnuParser();
    try {
        cmdline = parser.parse(options, args);
    } catch (ParseException exp) {
        HelpFormatter formatter = new HelpFormatter();
        formatter.printHelp(this.getClass().getName(), options);
        ToolRunner.printGenericCommandUsage(System.out);
        System.err.println("Error parsing command line: " + exp.getMessage());
        return -1;
    }

    if (!cmdline.hasOption(INPUT_OPTION) || !cmdline.hasOption(OUTPUT_OPTION)) {
        HelpFormatter formatter = new HelpFormatter();
        formatter.printHelp(this.getClass().getName(), options);
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }

    String input = cmdline.getOptionValue(INPUT_OPTION);
    String output = cmdline.getOptionValue(OUTPUT_OPTION);

    LOG.info("Tool name: " + DumpWarcRecordsToPlainText.class.getSimpleName());
    LOG.info(" - input: " + input);
    LOG.info(" - output: " + output);

    JobConf conf = new JobConf(getConf(), DumpWarcRecordsToPlainText.class);
    conf.setJobName(DumpWarcRecordsToPlainText.class.getSimpleName() + ":" + input);

    conf.setNumReduceTasks(0);

    FileInputFormat.addInputPaths(conf, input);
    FileOutputFormat.setOutputPath(conf, new Path(output));

    conf.setInputFormat(ClueWeb12InputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);
    conf.setMapperClass(MyMapper.class);

    RunningJob job = JobClient.runJob(conf);
    Counters counters = job.getCounters();
    int numDocs = (int) counters.findCounter(Records.PAGES).getCounter();

    LOG.info("Read " + numDocs + " docs.");

    return 0;
}

From source file:io.fluo.stress.trie.Generate.java

License:Apache License

@Override
public int run(String[] args) throws Exception {

    if (args.length != 4) {
        log.error("Usage: " + this.getClass().getSimpleName()
                + " <numMappers> <numbersPerMapper> <max> <output dir>");
        System.exit(-1);//from w  w  w .  j a  v  a 2  s.  c  o  m
    }

    int numMappers = Integer.parseInt(args[0]);
    int numPerMapper = Integer.parseInt(args[1]);
    long max = Long.parseLong(args[2]);
    Path out = new Path(args[3]);

    Preconditions.checkArgument(numMappers > 0, "numMappers <= 0");
    Preconditions.checkArgument(numPerMapper > 0, "numPerMapper <= 0");
    Preconditions.checkArgument(max > 0, "max <= 0");

    JobConf job = new JobConf(getConf());

    job.setJobName(this.getClass().getName());

    job.setJarByClass(Generate.class);

    job.setInt(TRIE_GEN_NUM_PER_MAPPER_PROP, numPerMapper);
    job.setInt(TRIE_GEN_NUM_MAPPERS_PROP, numMappers);
    job.setLong(TRIE_GEN_MAX_PROP, max);

    job.setInputFormat(RandomLongInputFormat.class);

    job.setNumReduceTasks(0);

    job.setOutputKeyClass(LongWritable.class);
    job.setOutputValueClass(NullWritable.class);

    job.setOutputFormat(SequenceFileOutputFormat.class);
    SequenceFileOutputFormat.setOutputPath(job, out);

    RunningJob runningJob = JobClient.runJob(job);
    runningJob.waitForCompletion();
    return runningJob.isSuccessful() ? 0 : -1;
}