List of usage examples for org.apache.hadoop.mapreduce TaskAttemptContext getConfiguration
public Configuration getConfiguration();
From source file:com.cloudera.science.avro2parquet.CombinedAvroKeyInputFormat.java
License:Apache License
@SuppressWarnings("unchecked") @Override/*from w ww.j a va 2 s . c o m*/ public RecordReader<AvroKey<T>, NullWritable> createRecordReader(InputSplit inputSplit, TaskAttemptContext context) throws IOException { Schema readerSchema = AvroJob.getInputKeySchema(context.getConfiguration()); if (null == readerSchema) { LOG.warn("Reader schema was not set. Use AvroJob.setInputKeySchema() if desired."); LOG.info("Using a reader schema equal to the writer schema."); } Object c = CombinedAvroKeyRecordReader.class; return new CombineFileRecordReader<AvroKey<T>, NullWritable>((CombineFileSplit) inputSplit, context, (Class<? extends RecordReader<AvroKey<T>, NullWritable>>) c); }
From source file:com.cloudera.sqoop.mapreduce.AvroOutputFormat.java
License:Apache License
@Override public RecordWriter<AvroWrapper<T>, NullWritable> getRecordWriter(TaskAttemptContext context) throws IOException, InterruptedException { Schema schema = AvroJob.getMapOutputSchema(context.getConfiguration()); final DataFileWriter<T> WRITER = new DataFileWriter<T>(new GenericDatumWriter<T>()); Path path = getDefaultWorkFile(context, org.apache.avro.mapred.AvroOutputFormat.EXT); WRITER.create(schema, path.getFileSystem(context.getConfiguration()).create(path)); return new RecordWriter<AvroWrapper<T>, NullWritable>() { @Override/*from w w w . jav a 2 s .com*/ public void write(AvroWrapper<T> wrapper, NullWritable ignore) throws IOException { WRITER.append(wrapper.datum()); } @Override public void close(TaskAttemptContext context) throws IOException, InterruptedException { WRITER.close(); } }; }
From source file:com.cloudera.sqoop.mapreduce.db.DBInputFormat.java
License:Apache License
@Override /** {@inheritDoc} */ public RecordReader<LongWritable, T> createRecordReader(InputSplit split, TaskAttemptContext context) throws IOException, InterruptedException { return createDBRecordReader((DBInputSplit) split, context.getConfiguration()); }
From source file:com.cloudera.sqoop.mapreduce.db.DBOutputFormat.java
License:Apache License
@Override /** {@inheritDoc} */ public RecordWriter<K, V> getRecordWriter(TaskAttemptContext context) throws IOException { DBConfiguration dbConf = new DBConfiguration(context.getConfiguration()); String tableName = dbConf.getOutputTableName(); String[] fieldNames = dbConf.getOutputFieldNames(); if (fieldNames == null) { fieldNames = new String[dbConf.getOutputFieldCount()]; }/*w w w. ja v a2 s .c o m*/ try { Connection connection = dbConf.getConnection(); PreparedStatement statement = null; statement = connection.prepareStatement(constructQuery(tableName, fieldNames)); return new DBRecordWriter(connection, statement); } catch (Exception ex) { throw new IOException(ex.getMessage()); } }
From source file:com.cloudera.sqoop.mapreduce.RawKeyTextOutputFormat.java
License:Apache License
public RecordWriter<K, V> getRecordWriter(TaskAttemptContext context) throws IOException { boolean isCompressed = getCompressOutput(context); Configuration conf = context.getConfiguration(); String ext = ""; CompressionCodec codec = null;// ww w.j a v a2s .c om if (isCompressed) { // create the named codec Class<? extends CompressionCodec> codecClass = getOutputCompressorClass(context, GzipCodec.class); codec = ReflectionUtils.newInstance(codecClass, conf); ext = codec.getDefaultExtension(); } Path file = getDefaultWorkFile(context, ext); FileSystem fs = file.getFileSystem(conf); FSDataOutputStream fileOut = fs.create(file, false); DataOutputStream ostream = fileOut; if (isCompressed) { ostream = new DataOutputStream(codec.createOutputStream(fileOut)); } return new RawKeyRecordWriter<K, V>(ostream); }
From source file:com.conductor.kafka.hadoop.KafkaRecordReader.java
License:Apache License
/** * {@inheritDoc}//from w w w .ja v a 2s .c om */ @Override public void initialize(final InputSplit split, final TaskAttemptContext context) throws IOException, InterruptedException { if (!(split instanceof KafkaInputSplit)) { throw new IllegalArgumentException( "Expected an InputSplit of type KafkaInputSplit but got " + split.getClass()); } final KafkaInputSplit inputSplit = (KafkaInputSplit) split; this.conf = context.getConfiguration(); this.split = inputSplit; this.start = inputSplit.getStartOffset(); this.pos = inputSplit.getStartOffset(); this.currentOffset = inputSplit.getStartOffset(); this.end = inputSplit.getEndOffset(); this.fetchSize = KafkaInputFormat.getKafkaFetchSizeBytes(conf); this.consumer = getConsumer(inputSplit, conf); }
From source file:com.conductor.s3.S3TextInputFormat.java
License:Apache License
@Override public RecordReader<LongWritable, Text> createRecordReader(InputSplit split, TaskAttemptContext context) { final String delimiter = context.getConfiguration().get("textinputformat.record.delimiter"); return new LineRecordReader(delimiter != null ? delimiter.getBytes() : null); }
From source file:com.conversantmedia.mapreduce.output.BloomFilterOutputFormat.java
License:Apache License
public BloomFilterOutputFormat(TaskAttemptContext context, int size) { this.context = context; this.insertionSize = size; context.getConfiguration().set(BASE_OUTPUT_NAME, BLOOM_FILTER); }
From source file:com.conversantmedia.mapreduce.output.BloomFilterOutputFormat.java
License:Apache License
public BloomFilterOutputFormat(TaskAttemptContext context, int size, String fileNamePrefix) { this.context = context; this.insertionSize = size; context.getConfiguration().set(BASE_OUTPUT_NAME, fileNamePrefix); }
From source file:com.conversantmedia.mapreduce.output.BloomFilterOutputFormat.java
License:Apache License
@Override public RecordWriter<K, V> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException { if (writer == null) { int size = getExpectedInsertions(job); checkState(size > 0, "Expected insertion insertionSize not set."); Configuration conf = job.getConfiguration(); String extension = ""; Path file = getDefaultWorkFile(job, extension); FileSystem fs = file.getFileSystem(conf); FSDataOutputStream fileOut = fs.create(file, false); writer = new BloomFilterRecordWriter<>(fileOut, size); }/* www . j a va 2 s. c o m*/ return writer; }