Package org.apache.hadoop.fs

Examples of org.apache.hadoop.fs.Seekable

136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
    long end = start + length;
    FileSystem fs = file.getFileSystem(conf);
    FSDataInputStream filestream = fs.open(file);
    CompressionCodec codec = (new CompressionCodecFactory(conf)).getCodec(file);
    LineReader filereader;
    Seekable fileseeker = filestream;

    // Hadoop 1.0 does not have support for custom record delimiter and thus
    // we
    // are supporting only default one.
    // We might add another "else if" case for SplittableCompressionCodec once
    // we drop support for Hadoop 1.0.
    if (codec == null) {
      filestream.seek(start);
      filereader = new LineReader(filestream);
    } else {
      filereader = new LineReader(codec.createInputStream(filestream,
          codec.createDecompressor()), conf);
      fileseeker = filestream;
    }
    if (start != 0) {
      // always throw away first record because
      // one extra line is read in previous split
      start += filereader.readLine(new Text(), 0);
    }
    int size;
    LOG.info("Start position: " + String.valueOf(start));
    long next = start;
    while (next <= end) {
      Text line = new Text();
      size = filereader.readLine(line, Integer.MAX_VALUE);
      if (size == 0) {
        break;
      }
      if (codec == null) {
        next += size;
      } else {
        next = fileseeker.getPos();
      }
      rowRead++;
      dataWriter.writeCsvRecord(line.toString());
    }
    LOG.info("Extracting ended on position: " + fileseeker.getPos());
    filestream.close();
  }
View Full Code Here
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
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
    FileSystem fs = file.getFileSystem(conf);
    FSDataInputStream filestream = fs.open(file);
    CompressionCodec codec = (new CompressionCodecFactory(conf)).getCodec(file);
    LineReader filereader;
    Seekable fileseeker = filestream;

    // Hadoop 1.0 does not have support for custom record delimiter and thus we
    // are supporting only default one.
    // We might add another "else if" case for SplittableCompressionCodec once
    // we drop support for Hadoop 1.0.
    if (codec == null) {
      filestream.seek(start);
      filereader = new LineReader(filestream);
    } else {
      filereader = new LineReader(
          codec.createInputStream(filestream, codec.createDecompressor()), conf);
      fileseeker = filestream;
    }

    if (start != 0) {
      // always throw away first record because
      // one extra line is read in previous split
      start += filereader.readLine(new Text(), 0);
    }
    int size;
    LOG.info("Start position: " + String.valueOf(start));
    long next = start;
    while (next <= end) {
      Text line = new Text();
      size = filereader.readLine(line, Integer.MAX_VALUE);
      if (size == 0) {
        break;
      }
      if (codec == null) {
        next += size;
      } else {
        next = fileseeker.getPos();
      }
      datawriter.writeCsvRecord(line.toString());
    }
    LOG.info("Extracting ended on position: " + fileseeker.getPos());
  }
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
    }
    if (input instanceof FileInputStream) {
      return create((FileInputStream) input);
    }
    if (input instanceof Seekable) {
      final Seekable seekable = (Seekable) input;
      return new SeekableInputStream(input) {
        @Override
        public void seek(long pos) throws IOException {
          seekable.seek(pos);
        }

        @Override
        public long getPos() throws IOException {
          return seekable.getPos();
        }

        @Override
        public boolean seekToNewSource(long targetPos) throws IOException {
          return seekable.seekToNewSource(targetPos);
        }
      };
    }

    throw new IOException("Failed to create SeekableInputStream from " + input.getClass());
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
    }
    if (input instanceof FileInputStream) {
      return create((FileInputStream) input);
    }
    if (input instanceof Seekable) {
      final Seekable seekable = (Seekable) input;
      return new SeekableInputStream(input) {
        @Override
        public void seek(long pos) throws IOException {
          seekable.seek(pos);
        }

        @Override
        public long getPos() throws IOException {
          return seekable.getPos();
        }

        @Override
        public boolean seekToNewSource(long targetPos) throws IOException {
          return seekable.seekToNewSource(targetPos);
        }
      };
    }

    throw new IOException("Failed to create SeekableInputStream from " + input.getClass());
View Full Code Here
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
    long end = start + length;
    FileSystem fs = file.getFileSystem(conf);
    FSDataInputStream filestream = fs.open(file);
    CompressionCodec codec = (new CompressionCodecFactory(conf)).getCodec(file);
    LineReader filereader;
    Seekable fileseeker = filestream;

    // Hadoop 1.0 does not have support for custom record delimiter and thus
    // we
    // are supporting only default one.
    // We might add another "else if" case for SplittableCompressionCodec once
    // we drop support for Hadoop 1.0.
    if (codec == null) {
      filestream.seek(start);
      filereader = new LineReader(filestream);
    } else {
      filereader = new LineReader(codec.createInputStream(filestream,
          codec.createDecompressor()), conf);
      fileseeker = filestream;
    }
    if (start != 0) {
      // always throw away first record because
      // one extra line is read in previous split
      start += filereader.readLine(new Text(), 0);
    }
    int size;
    LOG.info("Start position: " + String.valueOf(start));
    long next = start;
    while (next <= end) {
      Text line = new Text();
      size = filereader.readLine(line, Integer.MAX_VALUE);
      if (size == 0) {
        break;
      }
      if (codec == null) {
        next += size;
      } else {
        next = fileseeker.getPos();
      }
      rowRead++;
      dataWriter.writeCsvRecord(line.toString());
    }
    LOG.info("Extracting ended on position: " + fileseeker.getPos());
    filestream.close();
  }
View Full Code Here
TOP

Related Classes of org.apache.hadoop.fs.Seekable

  • co.cask.cdap.common.io.SeekableInputStream
  • co.cask.tigon.io.SeekableInputStream
  • org.apache.sqoop.job.etl.HdfsExportExtractor
  • org.apache.sqoop.job.etl.HdfsTextExportExtractor
    • 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.