Package org.apache.hadoop.io.SequenceFile

Examples of org.apache.hadoop.io.SequenceFile.CompressionType

105
106
107
108
109
110
111
112
113
114
115
    final boolean ignoreExternalLinks = job.getBoolean("db.ignore.external.links", false);
    int maxOutlinksPerPage = job.getInt("db.max.outlinks.per.page", 100);
    final boolean isParsing = job.getBoolean("fetcher.parse", true);
    final int maxOutlinks = (maxOutlinksPerPage < 0) ? Integer.MAX_VALUE
                                                     : maxOutlinksPerPage;
    final CompressionType compType = SequenceFileOutputFormat.getOutputCompressionType(job);
    Path out = FileOutputFormat.getOutputPath(job);
   
    Path text = new Path(new Path(out, ParseText.DIR_NAME), name);
    Path data = new Path(new Path(out, ParseData.DIR_NAME), name);
    Path crawl = new Path(new Path(out, CrawlDatum.PARSE_DIR_NAME), name);
View Full Code Here
276
277
278
279
280
281
282
283
284
285
286
          if (slice == DEFAULT_SLICE) {
            wname = new Path(new Path(new Path(out, segmentName), dirName), name);
          } else {
            wname = new Path(new Path(new Path(out, segmentName + "-" + slice), dirName), name);
          }
          CompressionType compType =
              SequenceFileOutputFormat.getOutputCompressionType(job);
          if (clazz.isAssignableFrom(ParseText.class)) {
            compType = CompressionType.RECORD;
          }
          res = new MapFile.Writer(job, fs, wname.toString(), Text.class, clazz, compType, progress);
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
    public RecordInputStream getInputStream(FileSystem fs, Path path) throws IOException {
        return new SequenceFileInputStream(fs, path);
    }

    public RecordOutputStream getOutputStream(FileSystem fs, Path path) throws IOException {
        CompressionType type = TYPES.get(_typeArg);
        CompressionCodec codec = CODECS.get(_codecArg);

        if(type==null)
            return new SequenceFileOutputStream(fs, path);
        else
View Full Code Here
132
133
134
135
136
137
138
139
140
141
142
    final SequenceFile.Writer[] outs = new SequenceFile.Writer[partitions];
    try {
      Reporter reporter = getReporter(umbilical, getProgress());
      FileSystem localFs = FileSystem.getNamed("local", job);
      CompressionCodec codec = null;
      CompressionType compressionType = CompressionType.NONE;
      if (job.getCompressMapOutput()) {
        // find the kind of compression to do, defaulting to record
        compressionType = job.getMapOutputCompressionType();

        // find the right codec
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
    // get the path of the temporary output file
    Path file = FileOutputFormat.getTaskOutputPath(job, name);
   
    FileSystem fs = file.getFileSystem(job);
    CompressionCodec codec = null;
    CompressionType compressionType = CompressionType.NONE;
    if (getCompressOutput(job)) {
      // find the kind of compression to do
      compressionType = getOutputCompressionType(job);

      // find the right codec
View Full Code Here
132
133
134
135
136
137
138
139
140
141
142
    // get the path of the temporary output file
    Path file = FileOutputFormat.getTaskOutputPath(job, name);
   
    FileSystem fs = file.getFileSystem(job);
    CompressionCodec codec = null;
    CompressionType compressionType = CompressionType.NONE;
    if (getCompressOutput(job)) {
      // find the kind of compression to do
      compressionType = getOutputCompressionType(job);

      // find the right codec
View Full Code Here
356
357
358
359
360
361
362
363
364
365
366
        if (rwonly && (!create || merge || fast)) {
          System.err.println(usage);
          System.exit(-1);
        }

        CompressionType compressionType =
          CompressionType.valueOf(compressType);

        if (rwonly || (create && !merge)) {
            writeTest(fs, count, seed, file, compressionType);
            readTest(fs, count, seed, file);
View Full Code Here
163
164
165
166
167
168
169
170
171
172
173
      Class<?> keyClass, Class<?> valueClass)
      throws IOException {
    Configuration conf = context.getConfiguration();

    CompressionCodec codec = null;
    CompressionType compressionType = CompressionType.NONE;
    if (getCompressOutput(context)) {
      // find the kind of compression to do
      compressionType = getOutputCompressionType(context);
      // find the right codec
      Class<?> codecClass = getOutputCompressorClass(context,
View Full Code Here
694
695
696
697
698
699
700
701
702
703
704
      if (rwonly && (!create || merge || fast)) {
        System.err.println(usage);
        System.exit(-1);
      }

      CompressionType compressionType =
        CompressionType.valueOf(compressType);
      CompressionCodec codec = (CompressionCodec)ReflectionUtils.newInstance(
                                                                             test.conf.getClassByName(compressionCodec),
                                                                             test.conf);
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
    if (!fs.exists(outputPath)) {
      throw new IOException("Output directory doesnt exist");
    }
    Path file = new Path(outputPath, name);
    CompressionCodec codec = null;
    CompressionType compressionType = CompressionType.NONE;
    if (getCompressOutput(job)) {
      // find the kind of compression to do
      compressionType = getOutputCompressionType(job);

      // find the right codec
View Full Code Here
TOP

Related Classes of org.apache.hadoop.io.SequenceFile.CompressionType

  • com.asakusafw.bulkloader.extractor.DfsFileImport
  • com.asakusafw.bulkloader.extractor.DfsFileImportTest
  • com.backtype.hadoop.pail.SequenceFileFormat
  • com.linkedin.camus.etl.kafka.common.SequenceFileRecordWriterProvider
  • com.linkedin.json.JsonSequenceFileOutputFormat
  • com.mozilla.pig.storage.SeqFileMultiStorage$MultiStorageSequenceOutputFormat
  • org.apache.accumulo.server.master.LogSort$LoggerMapFileOutputFormat
  • org.apache.avro.mapreduce.AvroSequenceFileOutputFormat
  • org.apache.flume.sink.hdfs.HDFSCompressedDataStream
  • org.apache.hadoop.hive.ql.exec.FileSinkOperator
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.