Java Code Examples for org.apache.hadoop.io.file.tfile.TFile.Reader#createScanner()

The following examples show how to use org.apache.hadoop.io.file.tfile.TFile.Reader#createScanner() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: TestTFileStreams.java    From hadoop-gpu with Apache License 2.0 6 votes vote down vote up 
public void testFailureNegativeOffset() throws IOException {
  if (skip)
    return;
  writeRecords(2, true, true);

  Reader reader = new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Scanner scanner = reader.createScanner();
  byte[] buf = new byte[K];
  try {
    scanner.entry().getKey(buf, -1);
    Assert.fail("Failed to handle key negative offset.");
  }
  catch (Exception e) {
    // noop, expecting exceptions
  }
  finally {
  }
  scanner.close();
  reader.close();
}
Example 2
Source File: TestTFileByteArrays.java    From big-c with Apache License 2.0 6 votes vote down vote up 
@Test
public void testFailureNegativeOffset_2() throws IOException {
  if (skip)
    return;
  closeOutput();

  Reader reader = new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Scanner scanner = reader.createScanner();
  try {
    scanner.lowerBound("keyX".getBytes(), -1, 4);
    Assert.fail("Error on handling negative offset.");
  } catch (Exception e) {
    // noop, expecting exceptions
  } finally {
    reader.close();
    scanner.close();
  }
  closeOutput();
}
Example 3
Source File: TestTFile.java    From hadoop-gpu with Apache License 2.0 6 votes vote down vote up 
void unsortedWithSomeCodec(String codec) throws IOException {
  Path uTfile = new Path(ROOT, "unsorted.tfile");
  FSDataOutputStream fout = createFSOutput(uTfile);
  Writer writer = new Writer(fout, minBlockSize, codec, null, conf);
  writeRecords(writer);
  writer.close();
  fout.close();
  FSDataInputStream fin = fs.open(uTfile);
  Reader reader =
      new Reader(fs.open(uTfile), fs.getFileStatus(uTfile).getLen(), conf);

  Scanner scanner = reader.createScanner();
  readAllRecords(scanner);
  scanner.close();
  reader.close();
  fin.close();
  fs.delete(uTfile, true);
}
Example 4
Source File: TestTFile.java    From big-c with Apache License 2.0 6 votes vote down vote up 
void unsortedWithSomeCodec(String codec) throws IOException {
  Path uTfile = new Path(ROOT, "unsorted.tfile");
  FSDataOutputStream fout = createFSOutput(uTfile);
  Writer writer = new Writer(fout, minBlockSize, codec, null, conf);
  writeRecords(writer);
  writer.close();
  fout.close();
  FSDataInputStream fin = fs.open(uTfile);
  Reader reader =
      new Reader(fs.open(uTfile), fs.getFileStatus(uTfile).getLen(), conf);

  Scanner scanner = reader.createScanner();
  readAllRecords(scanner);
  scanner.close();
  reader.close();
  fin.close();
  fs.delete(uTfile, true);
}
Example 5
Source File: TestTFileByteArrays.java    From hadoop-gpu with Apache License 2.0 6 votes vote down vote up 
public void testFailureNegativeLength_2() throws IOException {
  if (skip)
    return;
  closeOutput();

  Reader reader = new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Scanner scanner = reader.createScanner();
  try {
    scanner.lowerBound("keyX".getBytes(), 0, -1);
    Assert.fail("Error on handling negative length.");
  }
  catch (Exception e) {
    // noop, expecting exceptions
  }
  finally {
    scanner.close();
    reader.close();
  }
  closeOutput();
}
Example 6
Source File: TestTFileByteArrays.java    From hadoop with Apache License 2.0 6 votes vote down vote up 
@Test
public void testFailureNegativeLength_2() throws IOException {
  if (skip)
    return;
  closeOutput();

  Reader reader = new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Scanner scanner = reader.createScanner();
  try {
    scanner.lowerBound("keyX".getBytes(), 0, -1);
    Assert.fail("Error on handling negative length.");
  } catch (Exception e) {
    // noop, expecting exceptions
  } finally {
    scanner.close();
    reader.close();
  }
  closeOutput();
}
Example 7
Source File: TestTFileByteArrays.java    From big-c with Apache License 2.0 6 votes vote down vote up 
@Test
public void testFailureNegativeLength_2() throws IOException {
  if (skip)
    return;
  closeOutput();

  Reader reader = new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Scanner scanner = reader.createScanner();
  try {
    scanner.lowerBound("keyX".getBytes(), 0, -1);
    Assert.fail("Error on handling negative length.");
  } catch (Exception e) {
    // noop, expecting exceptions
  } finally {
    scanner.close();
    reader.close();
  }
  closeOutput();
}
Example 8
Source File: TestTFileByteArrays.java    From hadoop-gpu with Apache License 2.0 6 votes vote down vote up 
public void testFailureNegativeOffset_2() throws IOException {
  if (skip)
    return;
  closeOutput();

  Reader reader = new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Scanner scanner = reader.createScanner();
  try {
    scanner.lowerBound("keyX".getBytes(), -1, 4);
    Assert.fail("Error on handling negative offset.");
  }
  catch (Exception e) {
    // noop, expecting exceptions
  }
  finally {
    reader.close();
    scanner.close();
  }
  closeOutput();
}
Example 9
Source File: TestTFileStreams.java    From RDFS with Apache License 2.0 6 votes vote down vote up 
public void testFailureNegativeOffset() throws IOException {
  if (skip)
    return;
  writeRecords(2, true, true);

  Reader reader = new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Scanner scanner = reader.createScanner();
  byte[] buf = new byte[K];
  try {
    scanner.entry().getKey(buf, -1);
    Assert.fail("Failed to handle key negative offset.");
  }
  catch (Exception e) {
    // noop, expecting exceptions
  }
  finally {
  }
  scanner.close();
  reader.close();
}
Example 10
Source File: TestTFile.java    From hadoop with Apache License 2.0 6 votes vote down vote up 
void unsortedWithSomeCodec(String codec) throws IOException {
  Path uTfile = new Path(ROOT, "unsorted.tfile");
  FSDataOutputStream fout = createFSOutput(uTfile);
  Writer writer = new Writer(fout, minBlockSize, codec, null, conf);
  writeRecords(writer);
  writer.close();
  fout.close();
  FSDataInputStream fin = fs.open(uTfile);
  Reader reader =
      new Reader(fs.open(uTfile), fs.getFileStatus(uTfile).getLen(), conf);

  Scanner scanner = reader.createScanner();
  readAllRecords(scanner);
  scanner.close();
  reader.close();
  fin.close();
  fs.delete(uTfile, true);
}
Example 11
Source File: TestTFileByteArrays.java    From hadoop-gpu with Apache License 2.0 6 votes vote down vote up 
public void testLocate() throws IOException {
  if (skip)
    return;
  writeRecords(3 * records1stBlock);
  Reader reader = new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Scanner scanner = reader.createScanner();
  Location loc2 =
      locate(scanner, composeSortedKey(KEY, 3 * records1stBlock, 2)
          .getBytes());
  Location locLastIn1stBlock =
      locate(scanner, composeSortedKey(KEY, 3 * records1stBlock,
          records1stBlock - 1).getBytes());
  Location locFirstIn2ndBlock =
      locate(scanner, composeSortedKey(KEY, 3 * records1stBlock,
          records1stBlock).getBytes());
  Location locX = locate(scanner, "keyX".getBytes());
  Assert.assertEquals(scanner.endLocation, locX);
  scanner.close();
  reader.close();
}
Example 12
Source File: TestTFileByteArrays.java    From hadoop-gpu with Apache License 2.0 5 votes vote down vote up 
public void testNoDataEntry() throws IOException {
  if (skip) 
    return;
  closeOutput();

  Reader reader = new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Assert.assertTrue(reader.isSorted());
  Scanner scanner = reader.createScanner();
  Assert.assertTrue(scanner.atEnd());
  scanner.close();
  reader.close();
}
Example 13
Source File: TestTFileByteArrays.java    From RDFS with Apache License 2.0 5 votes vote down vote up 
private void checkBlockIndex(int recordIndex, int blockIndexExpected) throws IOException {
  Reader reader = new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Scanner scanner = reader.createScanner();
  scanner.seekTo(composeSortedKey(KEY, recordIndex).getBytes());
  Assert.assertEquals(blockIndexExpected, scanner.currentLocation
      .getBlockIndex());
  scanner.close();
  reader.close();
}
Example 14
Source File: TestTFileByteArrays.java    From hadoop with Apache License 2.0 5 votes vote down vote up 
private void checkBlockIndex(int recordIndex, int blockIndexExpected) throws IOException {
  Reader reader = new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Scanner scanner = reader.createScanner();
  scanner.seekTo(composeSortedKey(KEY, recordIndex).getBytes());
  Assert.assertEquals(blockIndexExpected, scanner.currentLocation
      .getBlockIndex());
  scanner.close();
  reader.close();
}
Example 15
Source File: TestTFileUnsortedByteArrays.java    From hadoop with Apache License 2.0 5 votes vote down vote up 
public void testScanRange() throws IOException {
  Reader reader =
      new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Assert.assertFalse(reader.isSorted());
  Assert.assertEquals((int) reader.getEntryCount(), 4);

  Scanner scanner = reader.createScanner();

  try {

    // read key and value
    byte[] kbuf = new byte[BUF_SIZE];
    int klen = scanner.entry().getKeyLength();
    scanner.entry().getKey(kbuf);
    Assert.assertEquals(new String(kbuf, 0, klen), "keyZ");

    byte[] vbuf = new byte[BUF_SIZE];
    int vlen = scanner.entry().getValueLength();
    scanner.entry().getValue(vbuf);
    Assert.assertEquals(new String(vbuf, 0, vlen), "valueZ");

    scanner.advance();

    // now try get value first
    vbuf = new byte[BUF_SIZE];
    vlen = scanner.entry().getValueLength();
    scanner.entry().getValue(vbuf);
    Assert.assertEquals(new String(vbuf, 0, vlen), "valueM");

    kbuf = new byte[BUF_SIZE];
    klen = scanner.entry().getKeyLength();
    scanner.entry().getKey(kbuf);
    Assert.assertEquals(new String(kbuf, 0, klen), "keyM");
  }
  finally {
    scanner.close();
    reader.close();
  }
}
Example 16
Source File: TestTFileSeek.java    From big-c with Apache License 2.0 5 votes vote down vote up 
public void seekTFile() throws IOException {
  int miss = 0;
  long totalBytes = 0;
  FSDataInputStream fsdis = fs.open(path);
  Reader reader =
    new Reader(fsdis, fs.getFileStatus(path).getLen(), conf);
  KeySampler kSampler =
      new KeySampler(rng, reader.getFirstKey(), reader.getLastKey(),
          keyLenGen);
  Scanner scanner = reader.createScanner();
  BytesWritable key = new BytesWritable();
  BytesWritable val = new BytesWritable();
  timer.reset();
  timer.start();
  for (int i = 0; i < options.seekCount; ++i) {
    kSampler.next(key);
    scanner.lowerBound(key.get(), 0, key.getSize());
    if (!scanner.atEnd()) {
      scanner.entry().get(key, val);
      totalBytes += key.getSize();
      totalBytes += val.getSize();
    }
    else {
      ++miss;
    }
  }
  timer.stop();
  double duration = (double) timer.read() / 1000; // in us.
  System.out.printf(
      "time: %s...avg seek: %s...%d hit...%d miss...avg I/O size: %.2fKB\n",
      timer.toString(), NanoTimer.nanoTimeToString(timer.read()
          / options.seekCount), options.seekCount - miss, miss,
      (double) totalBytes / 1024 / (options.seekCount - miss));

}
Example 17
Source File: TestTFileByteArrays.java    From big-c with Apache License 2.0 5 votes vote down vote up 
static void readRecords(FileSystem fs, Path path, int count,
    Configuration conf) throws IOException {
  Reader reader =
      new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Scanner scanner = reader.createScanner();

  try {
    for (int nx = 0; nx < count; nx++, scanner.advance()) {
      Assert.assertFalse(scanner.atEnd());
      // Assert.assertTrue(scanner.next());

      byte[] kbuf = new byte[BUF_SIZE];
      int klen = scanner.entry().getKeyLength();
      scanner.entry().getKey(kbuf);
      Assert.assertEquals(new String(kbuf, 0, klen), composeSortedKey(KEY,
          nx));

      byte[] vbuf = new byte[BUF_SIZE];
      int vlen = scanner.entry().getValueLength();
      scanner.entry().getValue(vbuf);
      Assert.assertEquals(new String(vbuf, 0, vlen), VALUE + nx);
    }

    Assert.assertTrue(scanner.atEnd());
    Assert.assertFalse(scanner.advance());
  } finally {
    scanner.close();
    reader.close();
  }
}
Example 18
Source File: TestTFileByteArrays.java    From hadoop-gpu with Apache License 2.0 5 votes vote down vote up 
static void readRecords(FileSystem fs, Path path, int count,
    Configuration conf) throws IOException {
  Reader reader =
      new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Scanner scanner = reader.createScanner();

  try {
    for (int nx = 0; nx < count; nx++, scanner.advance()) {
      Assert.assertFalse(scanner.atEnd());
      // Assert.assertTrue(scanner.next());

      byte[] kbuf = new byte[BUF_SIZE];
      int klen = scanner.entry().getKeyLength();
      scanner.entry().getKey(kbuf);
      Assert.assertEquals(new String(kbuf, 0, klen), composeSortedKey(KEY,
          count, nx));

      byte[] vbuf = new byte[BUF_SIZE];
      int vlen = scanner.entry().getValueLength();
      scanner.entry().getValue(vbuf);
      Assert.assertEquals(new String(vbuf, 0, vlen), VALUE + nx);
    }

    Assert.assertTrue(scanner.atEnd());
    Assert.assertFalse(scanner.advance());
  }
  finally {
    scanner.close();
    reader.close();
  }
}
Example 19
Source File: TestTFileSeek.java    From RDFS with Apache License 2.0 5 votes vote down vote up 
public void seekTFile() throws IOException {
  int miss = 0;
  long totalBytes = 0;
  FSDataInputStream fsdis = fs.open(path);
  Reader reader =
    new Reader(fsdis, fs.getFileStatus(path).getLen(), conf);
  KeySampler kSampler =
      new KeySampler(rng, reader.getFirstKey(), reader.getLastKey(),
          keyLenGen);
  Scanner scanner = reader.createScanner();
  BytesWritable key = new BytesWritable();
  BytesWritable val = new BytesWritable();
  timer.reset();
  timer.start();
  for (int i = 0; i < options.seekCount; ++i) {
    kSampler.next(key);
    scanner.lowerBound(key.get(), 0, key.getSize());
    if (!scanner.atEnd()) {
      scanner.entry().get(key, val);
      totalBytes += key.getSize();
      totalBytes += val.getSize();
    }
    else {
      ++miss;
    }
  }
  timer.stop();
  double duration = (double) timer.read() / 1000; // in us.
  System.out.printf(
      "time: %s...avg seek: %s...%d hit...%d miss...avg I/O size: %.2fKB\n",
      timer.toString(), NanoTimer.nanoTimeToString(timer.read()
          / options.seekCount), options.seekCount - miss, miss,
      (double) totalBytes / 1024 / (options.seekCount - miss));

}
Example 20
Source File: TestTFileByteArrays.java    From big-c with Apache License 2.0 5 votes vote down vote up 
@Test
public void testNoDataEntry() throws IOException {
  if (skip) 
    return;
  closeOutput();

  Reader reader = new Reader(fs.open(path), fs.getFileStatus(path).getLen(), conf);
  Assert.assertTrue(reader.isSorted());
  Scanner scanner = reader.createScanner();
  Assert.assertTrue(scanner.atEnd());
  scanner.close();
  reader.close();
}