List of usage examples for org.apache.hadoop.io.compress CompressionCodec getDefaultExtension
String getDefaultExtension();
From source file:fr.ens.biologie.genomique.eoulsan.bio.io.hadoop.ExpressionOutputFormat.java
License:LGPL
@Override public RecordWriter<Text, LongWritable> getRecordWriter(TaskAttemptContext context) throws IOException, InterruptedException { Configuration conf = context.getConfiguration(); boolean isCompressed = getCompressOutput(context); CompressionCodec codec = null; String extension = ""; if (isCompressed) { Class<? extends CompressionCodec> codecClass = getOutputCompressorClass(context, GzipCodec.class); codec = ReflectionUtils.newInstance(codecClass, conf); extension = codec.getDefaultExtension(); }/*from ww w. j av a 2 s. co m*/ // Get the output file path final Path file = getDefaultWorkFile(context, extension); final FileSystem fs = file.getFileSystem(conf); if (!isCompressed) { FSDataOutputStream fileOut = fs.create(file, false); return new ExpressionRecordWriter(context, fileOut); } else { FSDataOutputStream fileOut = fs.create(file, false); return new ExpressionRecordWriter(context, new DataOutputStream(codec.createOutputStream(fileOut))); } }
From source file:fr.ens.biologie.genomique.eoulsan.bio.io.hadoop.FastqOutputFormat.java
License:LGPL
@Override public RecordWriter<Text, Text> getRecordWriter(TaskAttemptContext context) throws IOException, InterruptedException { Configuration conf = context.getConfiguration(); boolean isCompressed = getCompressOutput(context); CompressionCodec codec = null; String extension = ""; if (isCompressed) { Class<? extends CompressionCodec> codecClass = getOutputCompressorClass(context, GzipCodec.class); codec = ReflectionUtils.newInstance(codecClass, conf); extension = codec.getDefaultExtension(); }/*from w ww . j a va 2 s.c om*/ // Get the output file path final Path file = getDefaultWorkFile(context, extension); final FileSystem fs = file.getFileSystem(conf); if (!isCompressed) { FSDataOutputStream fileOut = fs.create(file, false); return new FastqRecordWriter(context, fileOut); } else { FSDataOutputStream fileOut = fs.create(file, false); return new FastqRecordWriter(context, new DataOutputStream(codec.createOutputStream(fileOut))); } }
From source file:fr.ens.biologie.genomique.eoulsan.bio.io.hadoop.SAMOutputFormat.java
License:LGPL
@Override public RecordWriter<Text, Text> getRecordWriter(TaskAttemptContext context) throws IOException, InterruptedException { Configuration conf = context.getConfiguration(); boolean isCompressed = getCompressOutput(context); CompressionCodec codec = null; String extension = ""; if (isCompressed) { Class<? extends CompressionCodec> codecClass = getOutputCompressorClass(context, GzipCodec.class); codec = ReflectionUtils.newInstance(codecClass, conf); extension = codec.getDefaultExtension(); }// w ww.java 2 s .c o m // Get the output file path final Path file = getDefaultWorkFile(context, extension); final FileSystem fs = file.getFileSystem(conf); if (!isCompressed) { FSDataOutputStream fileOut = fs.create(file, false); return new SAMRecordWriter(context, fileOut); } else { FSDataOutputStream fileOut = fs.create(file, false); return new SAMRecordWriter(context, new DataOutputStream(codec.createOutputStream(fileOut))); } }
From source file:gov.jgi.meta.hadoop.output.FastaOutputFormat.java
License:Open Source License
public RecordWriter<K, V> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException { Configuration conf = job.getConfiguration(); boolean isCompressed = getCompressOutput(job); CompressionCodec codec = null; String extension = ""; if (isCompressed) { Class<? extends CompressionCodec> codecClass = getOutputCompressorClass(job, GzipCodec.class); codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass, conf); extension = codec.getDefaultExtension(); }/*from w ww . ja va 2 s .co m*/ Path file = getDefaultWorkFile(job, extension); FileSystem fs = file.getFileSystem(conf); if (!isCompressed) { FSDataOutputStream fileOut = fs.create(file, false); return (new FastaRecordWriter<K, V>(fileOut)); } else { FSDataOutputStream fileOut = fs.create(file, false); return (new FastaRecordWriter<K, V>(new DataOutputStream(codec.createOutputStream(fileOut)))); } }
From source file:io.aos.hdfs.FileDecompressor.java
License:Apache License
public static void main(String... args) throws Exception { String uri = args[0];/*from w w w .j ava 2s .c om*/ Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(URI.create(uri), conf); Path inputPath = new Path(uri); CompressionCodecFactory factory = new CompressionCodecFactory(conf); CompressionCodec codec = factory.getCodec(inputPath); if (codec == null) { System.err.println("No codec found for " + uri); System.exit(1); } String outputUri = CompressionCodecFactory.removeSuffix(uri, codec.getDefaultExtension()); InputStream in = null; OutputStream out = null; try { in = codec.createInputStream(fs.open(inputPath)); out = fs.create(new Path(outputUri)); IOUtils.copyBytes(in, out, conf); } finally { IOUtils.closeStream(in); IOUtils.closeStream(out); } }
From source file:io.druid.indexer.Utils.java
License:Apache License
public static OutputStream makePathAndOutputStream(JobContext job, Path outputPath, boolean deleteExisting) throws IOException { OutputStream retVal;//from w ww . j a v a 2 s .c o m FileSystem fs = outputPath.getFileSystem(job.getConfiguration()); Class<? extends CompressionCodec> codecClass; CompressionCodec codec = null; if (FileOutputFormat.getCompressOutput(job)) { codecClass = FileOutputFormat.getOutputCompressorClass(job, GzipCodec.class); codec = ReflectionUtils.newInstance(codecClass, job.getConfiguration()); outputPath = new Path(outputPath.toString() + codec.getDefaultExtension()); } if (fs.exists(outputPath)) { if (deleteExisting) { fs.delete(outputPath, false); } else { throw new ISE("outputPath[%s] must not exist.", outputPath); } } if (FileOutputFormat.getCompressOutput(job)) { retVal = codec.createOutputStream(fs.create(outputPath, false)); } else { retVal = fs.create(outputPath, false); } return retVal; }
From source file:io.druid.indexer.Utils.java
License:Apache License
public static boolean exists(JobContext job, FileSystem fs, Path inputPath) throws IOException { if (!FileOutputFormat.getCompressOutput(job)) { return fs.exists(inputPath); } else {//from ww w . j av a 2 s . c o m Class<? extends CompressionCodec> codecClass = FileOutputFormat.getOutputCompressorClass(job, GzipCodec.class); CompressionCodec codec = ReflectionUtils.newInstance(codecClass, job.getConfiguration()); return fs.exists(new Path(inputPath.toString() + codec.getDefaultExtension())); } }
From source file:io.druid.indexer.Utils.java
License:Apache License
public static InputStream openInputStream(JobContext job, Path inputPath, final FileSystem fileSystem) throws IOException { if (!FileOutputFormat.getCompressOutput(job)) { return fileSystem.open(inputPath); } else {/*from ww w .j av a2 s.c o m*/ Class<? extends CompressionCodec> codecClass = FileOutputFormat.getOutputCompressorClass(job, GzipCodec.class); CompressionCodec codec = ReflectionUtils.newInstance(codecClass, job.getConfiguration()); inputPath = new Path(inputPath.toString() + codec.getDefaultExtension()); return codec.createInputStream(fileSystem.open(inputPath)); } }
From source file:it.crs4.pydoop.NoSeparatorTextOutputFormat.java
License:Apache License
public RecordWriter<Text, Text> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException { final String keyValueSeparator = ""; Configuration conf = job.getConfiguration(); boolean isCompressed = getCompressOutput(job); CompressionCodec codec = null; String extension = ""; if (isCompressed) { Class<? extends CompressionCodec> codecClass = getOutputCompressorClass(job, GzipCodec.class); codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass, conf); extension = codec.getDefaultExtension(); }// w w w . j av a 2 s . c om Path file = getDefaultWorkFile(job, extension); FileSystem fs = file.getFileSystem(conf); if (!isCompressed) { FSDataOutputStream fileOut = fs.create(file, false); return new LineRecordWriter<Text, Text>(fileOut, keyValueSeparator); } else { FSDataOutputStream fileOut = fs.create(file, false); return new LineRecordWriter<Text, Text>(new DataOutputStream(codec.createOutputStream(fileOut)), keyValueSeparator); } }
From source file:it.crs4.seal.common.OutputStreamFactory.java
License:Open Source License
public DataOutputStream makeStream(Path path) throws IOException { Configuration conf = context.getConfiguration(); boolean isCompressed = FileOutputFormat.getCompressOutput(context); CompressionCodec codec = null; String extension = ""; if (isCompressed) { Class<? extends CompressionCodec> codecClass = FileOutputFormat.getOutputCompressorClass(context, GzipCodec.class); codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass, conf); extension = codec.getDefaultExtension(); }/*w w w.java2s.com*/ FileSystem fs = path.getFileSystem(conf); DataOutputStream output; if (isCompressed) { FSDataOutputStream fileOut = fs.create(path, false); output = new DataOutputStream(codec.createOutputStream(fileOut)); } else output = fs.create(path, false); return output; }