Package com.hadoop.compression.lzo

Examples of com.hadoop.compression.lzo.LzoIndex

84
85
86
87
88
89
90
91
92
93
94
        if (ignoreNonLzo || LzoInputFormatCommon.isLzoIndexFile(file.toString())) {
          it.remove();
        }
      } else {
        FileSystem fs = file.getFileSystem(conf);
        LzoIndex index = LzoIndex.readIndex(fs, file);
        indexes.put(file, index);
      }
    }

    return files.toArray(new FileStatus[] {});
View Full Code Here
95
96
97
98
99
100
101
102
103
104
105
106
  }

  @Override
  protected boolean isSplitable(FileSystem fs, Path filename) {
    if (LzoInputFormatCommon.isLzoFile(filename.toString())) {
      LzoIndex index = indexes.get(filename);
      return !index.isEmpty();
    } else {
      // Delegate non-LZO files to the TextInputFormat base class.
      return super.isSplitable(fs, filename);
    }
  }
View Full Code Here
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
        result.add(fileSplit);
        continue;
      }

      // LZO file, try to split if the .index file was found
      LzoIndex index = indexes.get(file);
      if (index == null) {
        throw new IOException("Index not found for " + file);
      }
      if (index.isEmpty()) {
        // Empty index, keep it as is.
        result.add(fileSplit);
        continue;
      }

      long start = fileSplit.getStart();
      long end = start + fileSplit.getLength();

      long lzoStart = index.alignSliceStartToIndex(start, end);
      long lzoEnd = index.alignSliceEndToIndex(end, fs.getFileStatus(file).getLen());

      if (lzoStart != LzoIndex.NOT_FOUND  && lzoEnd != LzoIndex.NOT_FOUND) {
        result.add(new FileSplit(file, lzoStart, lzoEnd - lzoStart, fileSplit.getLocations()));
      }
    }
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
        if (ignoreNonLzo || LzoInputFormatCommon.isLzoIndexFile(file.toString())) {
          iterator.remove();
        }
      } else {
        //read the index file
        LzoIndex index = LzoIndex.readIndex(fs, file);
        indexes.put(file, index);
      }
    }

    return files;
View Full Code Here
86
87
88
89
90
91
92
93
94
95
96
97
  }

  @Override
  protected boolean isSplitable(JobContext context, Path filename) {
    if (LzoInputFormatCommon.isLzoFile(filename.toString())) {
      LzoIndex index = indexes.get(filename);
      return !index.isEmpty();
    } else {
      // Delegate non-LZO files to the TextInputFormat base class.
      return super.isSplitable(context, filename);
    }
  }
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
        result.add(fileSplit);
        continue;
      }

      // LZO file, try to split if the .index file was found
      LzoIndex index = indexes.get(file);
      if (index == null) {
        throw new IOException("Index not found for " + file);
      }

      if (index.isEmpty()) {
        // empty index, keep as is
        result.add(fileSplit);
        continue;
      }

      long start = fileSplit.getStart();
      long end = start + fileSplit.getLength();

      long lzoStart = index.alignSliceStartToIndex(start, end);
      long lzoEnd = index.alignSliceEndToIndex(end, fs.getFileStatus(file).getLen());

      if (lzoStart != LzoIndex.NOT_FOUND  && lzoEnd != LzoIndex.NOT_FOUND) {
        result.add(new FileSplit(file, lzoStart, lzoEnd - lzoStart, fileSplit.getLocations()));
      }
    }
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
  /**
   * Make sure the lzo index class works as described.
   */
  public void testLzoIndex() {
    LzoIndex index = new LzoIndex();
    assertTrue(index.isEmpty());
    index = new LzoIndex(4);
    index.set(0, 0);
    index.set(1, 5);
    index.set(2, 10);
    index.set(3, 15);
    assertFalse(index.isEmpty());

    assertEquals(0, index.findNextPosition(-1));
    assertEquals(5, index.findNextPosition(1));
    assertEquals(5, index.findNextPosition(5));
    assertEquals(15, index.findNextPosition(11));
    assertEquals(15, index.findNextPosition(15));
    assertEquals(-1, index.findNextPosition(16));
   
    assertEquals(5, index.alignSliceStartToIndex(3, 20));
    assertEquals(15, index.alignSliceStartToIndex(15, 20));
    assertEquals(10, index.alignSliceEndToIndex(8, 30));
    assertEquals(10, index.alignSliceEndToIndex(10, 30));
    assertEquals(30, index.alignSliceEndToIndex(17, 30));
    assertEquals(LzoIndex.NOT_FOUND, index.alignSliceStartToIndex(16, 20));
  }
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
      if (!file.toString().endsWith(fileExtension)) {
        //get rid of non lzo files
        iterator.remove();
      } else {
        //read the index file
        LzoIndex index = LzoIndex.readIndex(fs, file);
        indexes.put(file, index);
      }
    }

    return files;
View Full Code Here
76
77
78
79
80
81
82
83
    return files;
  }

  @Override
  protected boolean isSplitable(JobContext context, Path filename) {
    LzoIndex index = indexes.get(filename);
    return !index.isEmpty();
  }
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
    for (InputSplit genericSplit : splits) {
      // load the index
      FileSplit fileSplit = (FileSplit) genericSplit;
      Path file = fileSplit.getPath();
      FileSystem fs = file.getFileSystem(conf);
      LzoIndex index = indexes.get(file);
      if (index == null) {
        throw new IOException("Index not found for " + file);
      }

      if (index.isEmpty()) {
        // empty index, keep as is
        result.add(fileSplit);
        continue;
      }

      long start = fileSplit.getStart();
      long end = start + fileSplit.getLength();

      long lzoStart = index.alignSliceStartToIndex(start, end);
      long lzoEnd = index.alignSliceEndToIndex(end, fs.getFileStatus(file).getLen());

      if (lzoStart != LzoIndex.NOT_FOUND  && lzoEnd != LzoIndex.NOT_FOUND) {
        result.add(new FileSplit(file, lzoStart, lzoEnd - lzoStart, fileSplit.getLocations()));
      }
    }
View Full Code Here
TOP

Related Classes of com.hadoop.compression.lzo.LzoIndex

  • com.hadoop.mapred.DeprecatedLzoTextInputFormat
  • com.hadoop.mapreduce.LzoTextInputFormat
  • com.hadoop.mapreduce.TestLzoTextInputFormat
  • com.twitter.elephantbird.mapreduce.input.LzoInputFormat
  • com.twitter.elephantbird.mapreduce.input.TestLzoTextInputFormat
  • com.twitter.elephanttwin.lzo.retrieval.LZOBlockOffsetMapper
  • com.twitter.elephanttwin.lzo.retrieval.TestLzoIndexing
  • org.anarres.lzo.LzopInputStream
  • org.apache.hadoop.conf.Configuration
  • org.apache.hadoop.fs.FSDataInputStream
    • 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.