protected SequenceFile.Writer getSequenceWriter(TaskAttemptContext context,
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,
DefaultCodec.class);
codec = (CompressionCodec)
ReflectionUtils.newInstance(codecClass, conf);
}
// get the path of the temporary output file
Path file = getDefaultWorkFile(context, "");
FileSystem fs = file.getFileSystem(conf);
return SequenceFile.createWriter(fs, conf, file,
keyClass,
valueClass,
compressionType,
codec,
context);
}
java类org.apache.hadoop.io.compress.DefaultCodec的实例源码
SequenceFileOutputFormat.java 文件源码
项目:FlexMap
阅读 23
收藏 0
点赞 0
评论 0
MrUtil.java 文件源码
项目:cloudera-framework
阅读 22
收藏 0
点赞 0
评论 0
/**
* Get the codec string associated with this <code>configuration</code>
*
* @param configuration the {@link Configuration}
* @return the codec {@link String}
*/
public static String getCodecString(Configuration configuration) {
boolean compress = configuration.getBoolean(FileOutputFormat.COMPRESS, false);
String codecType = configuration.get(FileOutputFormat.COMPRESS_TYPE, null);
if (compress && (codecType == null || !codecType.equals(CompressionType.NONE.toString()))) {
Class<?> codecClass = configuration.getClass(FileOutputFormat.COMPRESS_CODEC, DefaultCodec.class);
if (codecClass == null) {
return CODEC_NONE;
} else {
try {
return ((CompressionCodec) codecClass.newInstance()).getDefaultExtension().replace(".", "");
} catch (Exception exception) {
throw new RuntimeException("Could not determine codec", exception);
}
}
}
return CODEC_NONE;
}
TestMrUtil.java 文件源码
项目:cloudera-framework
阅读 21
收藏 0
点赞 0
评论 0
@Test
public void testGetCodecString() {
Configuration configuration = dfsServer.getConf();
assertEquals(MrUtil.CODEC_NONE, MrUtil.getCodecString(configuration));
configuration.setBoolean(FileOutputFormat.COMPRESS, false);
assertEquals(MrUtil.CODEC_NONE, MrUtil.getCodecString(configuration));
configuration.setBoolean(FileOutputFormat.COMPRESS, true);
assertEquals(new DefaultCodec().getDefaultExtension().substring(1, new DefaultCodec().getDefaultExtension().length()),
MrUtil.getCodecString(configuration));
configuration.set(FileOutputFormat.COMPRESS_CODEC, SnappyCodec.class.getName());
assertEquals(new SnappyCodec().getDefaultExtension().substring(1, new SnappyCodec().getDefaultExtension().length()),
MrUtil.getCodecString(configuration));
configuration.set(FileOutputFormat.COMPRESS_TYPE, CompressionType.BLOCK.toString());
assertEquals(new SnappyCodec().getDefaultExtension().substring(1, new SnappyCodec().getDefaultExtension().length()),
MrUtil.getCodecString(configuration));
configuration.set(FileOutputFormat.COMPRESS_TYPE, CompressionType.NONE.toString());
assertEquals(MrUtil.CODEC_NONE, MrUtil.getCodecString(configuration));
configuration.set(FileOutputFormat.COMPRESS_TYPE, CompressionType.BLOCK.toString());
configuration.setBoolean(FileOutputFormat.COMPRESS, false);
assertEquals(MrUtil.CODEC_NONE, MrUtil.getCodecString(configuration));
}
TestIPCUtil.java 文件源码
项目:HIndex
阅读 34
收藏 0
点赞 0
评论 0
/**
* For running a few tests of methods herein.
* @param args
* @throws IOException
*/
public static void main(String[] args) throws IOException {
int count = 1024;
int size = 10240;
for (String arg: args) {
if (arg.startsWith(COUNT)) {
count = Integer.parseInt(arg.replace(COUNT, ""));
} else if (arg.startsWith(SIZE)) {
size = Integer.parseInt(arg.replace(SIZE, ""));
} else {
usage(1);
}
}
IPCUtil util = new IPCUtil(HBaseConfiguration.create());
((Log4JLogger)IPCUtil.LOG).getLogger().setLevel(Level.ALL);
timerTests(util, count, size, new KeyValueCodec(), null);
timerTests(util, count, size, new KeyValueCodec(), new DefaultCodec());
timerTests(util, count, size, new KeyValueCodec(), new GzipCodec());
}
HadoopFileOutputFormat.java 文件源码
项目:titan0.5.4-hbase1.1.1-custom
阅读 17
收藏 0
点赞 0
评论 0
public DataOutputStream getDataOuputStream(final TaskAttemptContext job) throws IOException, InterruptedException {
org.apache.hadoop.conf.Configuration hadoopConf = DEFAULT_COMPAT.getContextConfiguration(job);
this.faunusConf = ModifiableHadoopConfiguration.of(hadoopConf);
boolean isCompressed = getCompressOutput(job);
CompressionCodec codec = null;
String extension = "";
if (isCompressed) {
final Class<? extends CompressionCodec> codecClass = getOutputCompressorClass(job, DefaultCodec.class);
codec = ReflectionUtils.newInstance(codecClass, hadoopConf);
extension = codec.getDefaultExtension();
}
final Path file = super.getDefaultWorkFile(job, extension);
final FileSystem fs = file.getFileSystem(hadoopConf);
if (!isCompressed) {
return new DataOutputStream(fs.create(file, false));
} else {
return new DataOutputStream(codec.createOutputStream(fs.create(file, false)));
}
}
TestIFile.java 文件源码
项目:hops
阅读 25
收藏 0
点赞 0
评论 0
@Test
/**
* Create an IFile.Writer using GzipCodec since this code does not
* have a compressor when run via the tests (ie no native libraries).
*/
public void testIFileWriterWithCodec() throws Exception {
Configuration conf = new Configuration();
FileSystem localFs = FileSystem.getLocal(conf);
FileSystem rfs = ((LocalFileSystem)localFs).getRaw();
Path path = new Path(new Path("build/test.ifile"), "data");
DefaultCodec codec = new GzipCodec();
codec.setConf(conf);
IFile.Writer<Text, Text> writer =
new IFile.Writer<Text, Text>(conf, rfs.create(path), Text.class, Text.class,
codec, null);
writer.close();
}
TestIFile.java 文件源码
项目:hops
阅读 24
收藏 0
点赞 0
评论 0
@Test
/** Same as above but create a reader. */
public void testIFileReaderWithCodec() throws Exception {
Configuration conf = new Configuration();
FileSystem localFs = FileSystem.getLocal(conf);
FileSystem rfs = ((LocalFileSystem)localFs).getRaw();
Path path = new Path(new Path("build/test.ifile"), "data");
DefaultCodec codec = new GzipCodec();
codec.setConf(conf);
FSDataOutputStream out = rfs.create(path);
IFile.Writer<Text, Text> writer =
new IFile.Writer<Text, Text>(conf, out, Text.class, Text.class,
codec, null);
writer.close();
FSDataInputStream in = rfs.open(path);
IFile.Reader<Text, Text> reader =
new IFile.Reader<Text, Text>(conf, in, rfs.getFileStatus(path).getLen(),
codec, null);
reader.close();
// test check sum
byte[] ab= new byte[100];
int readed= reader.checksumIn.readWithChecksum(ab, 0, ab.length);
assertEquals( readed,reader.checksumIn.getChecksum().length);
}
TextBytesJobUtil.java 文件源码
项目:openimaj
阅读 21
收藏 0
点赞 0
评论 0
public static Job createJob(Path[] inputPaths, Path outputPath, Map<String, String> metadata, Configuration config)
throws IOException
{
final Job job = new Job(config);
job.setInputFormatClass(SequenceFileInputFormat.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(BytesWritable.class);
job.setOutputFormatClass(MetadataSequenceFileOutputFormat.class);
SequenceFileInputFormat.setInputPaths(job, inputPaths);
SequenceFileOutputFormat.setOutputPath(job, outputPath);
SequenceFileOutputFormat.setCompressOutput(job, true);
SequenceFileOutputFormat.setOutputCompressorClass(job, DefaultCodec.class);
SequenceFileOutputFormat.setOutputCompressionType(job, CompressionType.BLOCK);
if (metadata != null)
MetadataConfiguration.setMetadata(metadata, job.getConfiguration());
return job;
}
TestSequenceFile.java 文件源码
项目:hadoop-oss
阅读 27
收藏 0
点赞 0
评论 0
/** Unit tests for SequenceFile. */
@Test
public void testZlibSequenceFile() throws Exception {
LOG.info("Testing SequenceFile with DefaultCodec");
compressedSeqFileTest(new DefaultCodec());
LOG.info("Successfully tested SequenceFile with DefaultCodec");
}
TestReduceTask.java 文件源码
项目:hadoop
阅读 14
收藏 0
点赞 0
评论 0
public void testValueIteratorWithCompression() throws Exception {
Path tmpDir = new Path("build/test/test.reduce.task.compression");
Configuration conf = new Configuration();
DefaultCodec codec = new DefaultCodec();
codec.setConf(conf);
for (Pair[] testCase: testCases) {
runValueIterator(tmpDir, testCase, conf, codec);
}
}