List of usage examples for org.apache.hadoop.mapred FileOutputFormat getOutputCompressorClass
public static Class<? extends CompressionCodec> getOutputCompressorClass(JobConf conf, Class<? extends CompressionCodec> defaultValue)
From source file:com.datascience.hadoop.CsvOutputFormat.java
License:Apache License
@Override public RecordWriter<LongWritable, ListWritable<Text>> getRecordWriter(FileSystem fileSystem, JobConf conf, String name, Progressable progress) throws IOException { String charsetName = conf.get(CHARSET); Charset charset = charsetName != null ? Charset.forName(charsetName) : StandardCharsets.UTF_8; Path path;/* ww w. j av a 2 s . c o m*/ if (FileOutputFormat.getCompressOutput(conf)) { Class<? extends CompressionCodec> codecClass = FileOutputFormat.getOutputCompressorClass(conf, GzipCodec.class); CompressionCodec codec = ReflectionUtils.newInstance(codecClass, conf); path = FileOutputFormat.getTaskOutputPath(conf, name + codec.getDefaultExtension()); } else { path = FileOutputFormat.getTaskOutputPath(conf, name); } return new CsvRecordWriter(new OutputStreamWriter(path.getFileSystem(conf).create(path, progress), charset), createFormat(conf)); }
From source file:com.ricemap.spateDB.core.GridRecordWriter.java
License:Apache License
/** * Creates an output stream that will be used to write the final cell file * @param cellFilePath//from w ww . ja v a 2 s . c o m * @return * @throws IOException */ protected OutputStream createFinalCellStream(Path cellFilePath) throws IOException { OutputStream cellStream; boolean isCompressed = jobConf != null && FileOutputFormat.getCompressOutput(jobConf); if (!isCompressed) { // Create new file cellStream = fileSystem.create(cellFilePath, true, fileSystem.getConf().getInt("io.file.buffer.size", 4096), fileSystem.getDefaultReplication(outDir), this.blockSize); } else { Class<? extends CompressionCodec> codecClass = FileOutputFormat.getOutputCompressorClass(jobConf, GzipCodec.class); // create the named codec CompressionCodec codec = ReflectionUtils.newInstance(codecClass, jobConf); // Open a stream to the output file cellStream = fileSystem.create(cellFilePath, true, fileSystem.getConf().getInt("io.file.buffer.size", 4096), fileSystem.getDefaultReplication(outDir), this.blockSize); // Encode the output stream using the codec cellStream = new DataOutputStream(codec.createOutputStream(cellStream)); } return cellStream; }
From source file:com.ricemap.spateDB.core.GridRecordWriter.java
License:Apache License
/** * Returns path to a file in which the final cell will be written. * @param column//from w ww. java 2 s . c om * @param row * @return * @throws IOException */ protected Path getFinalCellPath(int cellIndex) throws IOException { Path path = null; do { String filename = counter == 0 ? String.format("data_%05d", cellIndex) : String.format("data_%05d_%d", cellIndex, counter); boolean isCompressed = jobConf != null && FileOutputFormat.getCompressOutput(jobConf); if (isCompressed) { Class<? extends CompressionCodec> codecClass = FileOutputFormat.getOutputCompressorClass(jobConf, GzipCodec.class); // create the named codec CompressionCodec codec = ReflectionUtils.newInstance(codecClass, jobConf); filename += codec.getDefaultExtension(); } path = getFilePath(filename); counter++; } while (fileSystem.exists(path)); return path; }
From source file:edu.umn.cs.spatialHadoop.core.GridRecordWriter.java
License:Open Source License
/** * Creates an output stream that will be used to write the final cell file * @param cellFilePath/* w ww . j a v a 2 s .co m*/ * @return * @throws IOException */ protected OutputStream createFinalCellStream(Path cellFilePath) throws IOException { OutputStream cellStream; boolean isCompressed = jobConf != null && FileOutputFormat.getCompressOutput(jobConf); if (!isCompressed) { // Create new file cellStream = fileSystem.create(cellFilePath, true, fileSystem.getConf().getInt("io.file.buffer.size", 4096), fileSystem.getDefaultReplication(cellFilePath), this.blockSize); } else { Class<? extends CompressionCodec> codecClass = FileOutputFormat.getOutputCompressorClass(jobConf, GzipCodec.class); // create the named codec CompressionCodec codec = ReflectionUtils.newInstance(codecClass, jobConf); // Open a stream to the output file cellStream = fileSystem.create(cellFilePath, true, fileSystem.getConf().getInt("io.file.buffer.size", 4096), fileSystem.getDefaultReplication(cellFilePath), this.blockSize); // Encode the output stream using the codec cellStream = new DataOutputStream(codec.createOutputStream(cellStream)); } return cellStream; }
From source file:edu.umn.cs.spatialHadoop.core.GridRecordWriter.java
License:Open Source License
/** * Returns path to a file in which the final cell will be written. * @param cellIndex The index of the cell to retrieve its output path. * @return//www . j av a 2s . co m * @throws IOException */ protected Path getFinalCellPath(int cellIndex) throws IOException { Path path; do { String filename = counter == 0 ? String.format("data_%05d", cellIndex) : String.format("data_%05d_%d", cellIndex, counter); boolean isCompressed = jobConf != null && FileOutputFormat.getCompressOutput(jobConf); if (isCompressed) { Class<? extends CompressionCodec> codecClass = FileOutputFormat.getOutputCompressorClass(jobConf, GzipCodec.class); // create the named codec CompressionCodec codec = ReflectionUtils.newInstance(codecClass, jobConf); filename += codec.getDefaultExtension(); } path = getFilePath(filename); counter++; } while (fileSystem.exists(path)); return path; }