Package org.apache.hadoop.io.SequenceFile

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

49
50
51
52
53
54
55
56
57
58
59
      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 = SequenceFileOutputFormat.getOutputCompressionType(job);

      // find the right codec
View Full Code Here
275
276
277
278
279
280
281
282
283
284
285
          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
41
42
43
44
45
46
47
48
49
50
51
                                      String name, Progressable progress)
                                      throws IOException {

    Path file = new Path(job.getOutputPath(), name);
    CompressionCodec codec = null;
    CompressionType compressionType = CompressionType.NONE;
    if (getCompressOutput(job)) {
      // find the kind of compression to do
      compressionType = SequenceFile.getCompressionType(job);

      // find the right codec
View Full Code Here
89
90
91
92
93
94
95
96
97
98
99
    final int interval = job.getInt("db.fetch.interval.default", 2592000);
    final boolean ignoreExternalLinks = job.getBoolean("db.ignore.external.links", false);
    int maxOutlinksPerPage = job.getInt("db.max.outlinks.per.page", 100);
    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
59
60
61
62
63
64
65
66
67
68
69
    final Path fetch =
      new Path(new Path(out, CrawlDatum.FETCH_DIR_NAME), name);
    final Path content =
      new Path(new Path(out, Content.DIR_NAME), name);
   
    final CompressionType compType = SequenceFileOutputFormat.getOutputCompressionType(job);

    final MapFile.Writer fetchOut =
      new MapFile.Writer(job, fs, fetch.toString(), Text.class, CrawlDatum.class,
          compType, progress);
   
View Full Code Here
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
   * @return output stream over the created sequencefile
   */
  public static SequenceFile.Writer createSequenceWriter(JobConf jc, FileSystem fs, Path file,
      Class<?> keyClass, Class<?> valClass, boolean isCompressed) throws IOException {
    CompressionCodec codec = null;
    CompressionType compressionType = CompressionType.NONE;
    Class codecClass = null;
    if (isCompressed) {
      compressionType = SequenceFileOutputFormat.getOutputCompressionType(jc);
      codecClass = FileOutputFormat.getOutputCompressorClass(jc, DefaultCodec.class);
      codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass, jc);
View Full Code Here
274
275
276
277
278
279
280
281
282
283
284
              .forName(codecStr);
          FileOutputFormat.setOutputCompressorClass(jc_output, codec);
        }
        String type = conf.getCompressType();
        if (type != null && !type.trim().equals("")) {
          CompressionType style = CompressionType.valueOf(type);
          SequenceFileOutputFormat.setOutputCompressionType(jc, style);
        }
      }
      return getRecordWriter(jc_output, hiveOutputFormat, outputClass,
          isCompressed, tableInfo.getProperties(), outPath, reporter);
View Full Code Here
849
850
851
852
853
854
855
856
857
858
859
   * @return output stream over the created sequencefile
   */
  public static SequenceFile.Writer createSequenceWriter(JobConf jc, FileSystem fs, Path file,
      Class<?> keyClass, Class<?> valClass, boolean isCompressed) throws IOException {
    CompressionCodec codec = null;
    CompressionType compressionType = CompressionType.NONE;
    Class codecClass = null;
    if (isCompressed) {
      compressionType = SequenceFileOutputFormat.getOutputCompressionType(jc);
      codecClass = FileOutputFormat.getOutputCompressorClass(jc, DefaultCodec.class);
      codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass, jc);
View Full Code Here
224
225
226
227
228
229
230
231
232
233
234
              .forName(codecStr);
          FileOutputFormat.setOutputCompressorClass(jc_output, codec);
        }
        String type = conf.getCompressType();
        if (type != null && !type.trim().equals("")) {
          CompressionType style = CompressionType.valueOf(type);
          SequenceFileOutputFormat.setOutputCompressionType(jc, style);
        }
      }
      return getRecordWriter(jc_output, hiveOutputFormat, outputClass,
          isCompressed, tableInfo.getProperties(), outPath);
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
    final Path fetch =
      new Path(new Path(out, CrawlDatum.FETCH_DIR_NAME), name);
    final Path content =
      new Path(new Path(out, Content.DIR_NAME), name);
   
    final CompressionType compType = SequenceFileOutputFormat.getOutputCompressionType(job);

    final MapFile.Writer fetchOut =
      new MapFile.Writer(job, fs, fetch.toString(), Text.class, CrawlDatum.class,
          compType, progress);
   
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.