List of usage examples for org.apache.hadoop.mapreduce TaskAttemptContext getConfiguration
public Configuration getConfiguration();
From source file:com.linkedin.whiteelephant.mapreduce.MyAvroMultipleOutputs.java
License:Apache License
@SuppressWarnings("unchecked") private synchronized RecordWriter getRecordWriter(TaskAttemptContext taskContext, String baseFileName) throws IOException, InterruptedException { // look for record-writer in the cache RecordWriter writer = recordWriters.get(baseFileName); // If not in cache, create a new one if (writer == null) { // get the record writer from context output format //FileOutputFormat.setOutputName(taskContext, baseFileName); // (mhayes) Fix so can write to different baseFileName // * Bug reported here: https://issues.apache.org/jira/browse/AVRO-1215 // * Original code submitted here: https://issues.apache.org/jira/browse/AVRO-1106 taskContext.getConfiguration().set("avro.mo.config.namedOutput", baseFileName); try {/*from w w w . ja v a2s. c o m*/ writer = ((OutputFormat) ReflectionUtils.newInstance(taskContext.getOutputFormatClass(), taskContext.getConfiguration())).getRecordWriter(taskContext); } catch (ClassNotFoundException e) { throw new IOException(e); } // if counters are enabled, wrap the writer with context // to increment counters if (countersEnabled) { writer = new RecordWriterWithCounter(writer, baseFileName, context); } // add the record-writer to the cache recordWriters.put(baseFileName, writer); } return writer; }
From source file:com.mapred.EmplRecordReader.java
@Override public void initialize(InputSplit is, TaskAttemptContext tac) throws IOException, InterruptedException { FileSplit split = (FileSplit) is;//from w ww .j a v a 2 s.c om position = 0L; end = split.getLength(); Configuration job = tac.getConfiguration(); final Path file = split.getPath(); FileSystem fs = file.getFileSystem(job); FSDataInputStream fileIn = fs.open(split.getPath()); in = new LineRecordReader(); in.initialize(is, tac); }
From source file:com.marcolotz.lung.io.inputFormat.MultipleFilesRecordReader.java
License:Creative Commons License
/** * Implementation detail: This constructor is built to be called via * reflection from within CombineFileRecordReader. * //ww w . ja v a 2 s.c om * @param fileSplit * The CombineFileSplit that this will read from. * @param context * The context for this task. * @param pathToProcess * The path index from the CombineFileSplit to process in this * record. */ public MultipleFilesRecordReader(CombineFileSplit fileSplit, TaskAttemptContext context, Integer pathToProcess) { isProcessed = false; mFileToRead = fileSplit.getPath(pathToProcess); mFileLength = fileSplit.getLength(pathToProcess); mConf = context.getConfiguration(); /* never used in production, just for code integrity */ assert 0 == fileSplit.getOffset(pathToProcess); if (LOG.isDebugEnabled()) { LOG.debug("FileToRead is: " + mFileToRead.toString()); LOG.debug("Processing path " + pathToProcess + " out of " + fileSplit.getNumPaths()); try { FileSystem fs = FileSystem.get(mConf); /* never used in production, just for code integrity */ assert fs.getFileStatus(mFileToRead).getLen() == mFileLength; } catch (IOException ioe) { LOG.debug("Problem in file length"); } } fileContent = new BytesWritable(); }
From source file:com.marcolotz.lung.io.inputFormat.WholeFileRecordReader.java
License:Creative Commons License
@Override public void initialize(InputSplit split, TaskAttemptContext context) throws IOException, InterruptedException { this.fileSplit = (FileSplit) split; this.conf = context.getConfiguration(); }
From source file:com.marklogic.contentpump.AggregateXMLReader.java
License:Apache License
@Override public void initialize(InputSplit inSplit, TaskAttemptContext context) throws IOException, InterruptedException { initConfig(context);// w w w .j a v a2 s. co m initAggConf(context); f = XMLInputFactory.newInstance(); setFile(((FileSplit) inSplit).getPath()); fs = file.getFileSystem(context.getConfiguration()); FileStatus status = fs.getFileStatus(file); if (status.isDirectory()) { iterator = new FileIterator((FileSplit) inSplit, context); inSplit = iterator.next(); } initStreamReader(inSplit); }
From source file:com.marklogic.contentpump.AggregateXMLReader.java
License:Apache License
protected void initAggConf(TaskAttemptContext context) { Configuration conf = context.getConfiguration(); idName = conf.get(ConfigConstants.CONF_INPUT_URI_ID); if (idName == null) { useAutomaticId = true;/*w w w .jav a2s.c om*/ } recordName = conf.get(ConfigConstants.CONF_AGGREGATE_RECORD_ELEMENT); recordNamespace = conf.get(ConfigConstants.CONF_AGGREGATE_RECORD_NAMESPACE); }
From source file:com.marklogic.contentpump.ArchiveOutputFormat.java
License:Apache License
@Override public RecordWriter<DocumentURI, MarkLogicDocument> getRecordWriter(TaskAttemptContext context) throws IOException, InterruptedException { Configuration conf = context.getConfiguration(); Path path = new Path(conf.get(ConfigConstants.CONF_OUTPUT_FILEPATH)); return new ArchiveWriter(path, context); }
From source file:com.marklogic.contentpump.ArchiveRecordReader.java
License:Apache License
@Override public void initialize(InputSplit inSplit, TaskAttemptContext context) throws IOException, InterruptedException { initConfig(context);//ww w .j a v a 2s . c o m allowEmptyMeta = conf.getBoolean(CONF_INPUT_ARCHIVE_METADATA_OPTIONAL, false); setFile(((FileSplit) inSplit).getPath()); fs = file.getFileSystem(context.getConfiguration()); FileStatus status = fs.getFileStatus(file); if (status.isDirectory()) { iterator = new FileIterator((FileSplit) inSplit, context); inSplit = iterator.next(); } initStream(inSplit); }
From source file:com.marklogic.contentpump.ArchiveWriter.java
License:Apache License
public ArchiveWriter(Path path, TaskAttemptContext context) { dir = path.toString();/*from ww w. ja v a 2 s . co m*/ this.context = context; Configuration conf = context.getConfiguration(); encoding = conf.get(OUTPUT_CONTENT_ENCODING, DEFAULT_ENCODING); String type = conf.get(CONF_OUTPUT_TYPE, DEFAULT_OUTPUT_TYPE); ExportOutputType outputType = ExportOutputType.valueOf(type.toUpperCase()); if (outputType.equals(ExportOutputType.DOCUMENT)) { isExportDoc = true; } else { //archive uses DatabaseContentReader isExportDoc = false; } }
From source file:com.marklogic.contentpump.CompressedAggXMLReader.java
License:Apache License
@Override public void initialize(InputSplit inSplit, TaskAttemptContext context) throws IOException, InterruptedException { initConfig(context);/*w w w. ja va 2 s. c o m*/ initAggConf(context); f = XMLInputFactory.newInstance(); setFile(((FileSplit) inSplit).getPath()); fs = file.getFileSystem(context.getConfiguration()); FileStatus status = fs.getFileStatus(file); if (status.isDirectory()) { iterator = new FileIterator((FileSplit) inSplit, context); inSplit = iterator.next(); } initStreamReader(inSplit); }