com.marklogic.mapreduce
Class MarkLogicRecordReader<KEYIN,VALUEIN>

java.lang.Object
  org.apache.hadoop.mapreduce.RecordReader<KEYIN,VALUEIN>
      com.marklogic.mapreduce.MarkLogicRecordReader<KEYIN,VALUEIN>

All Implemented Interfaces:

MarkLogicConstants, Closeable

Direct Known Subclasses:

DocumentReader, KeyValueReader, NodeReader, ValueReader

public abstract class MarkLogicRecordReader<KEYIN,VALUEIN>
extends org.apache.hadoop.mapreduce.RecordReader<KEYIN,VALUEIN>
implements MarkLogicConstants

A RecordReader that fetches data from MarkLogic server and generates key value pairs.

Field Summary

protected org.apache.hadoop.conf.Configuration	conf Job configuration.
protected long	count Count of records fetched
protected float	length Total expected count of the records in a split.
static org.apache.commons.logging.Log	LOG
protected MarkLogicInputSplit	mlSplit Input split for this record reader
protected com.marklogic.xcc.ResultSequence	result ResultSequence from the MarkLogic server.
protected com.marklogic.xcc.Session	session Session to the MarkLogic server.

Fields inherited from interface com.marklogic.mapreduce.MarkLogicConstants

ADVANCED_MODE, BASIC_MODE, BATCH_SIZE, BIND_SPLIT_RANGE, CONTENT_TYPE, DEFAULT_BATCH_SIZE, DEFAULT_CONTENT_TYPE, DEFAULT_MAX_SPLIT_SIZE, DEFAULT_OUTPUT_CONTENT_ENCODING, DEFAULT_OUTPUT_XML_REPAIR_LEVEL, DEFAULT_PROPERTY_OPERATION_TYPE, DOCUMENT_SELECTOR, INDENTED, INPUT_DATABASE_NAME, INPUT_HOST, INPUT_KEY_CLASS, INPUT_LEXICON_FUNCTION_CLASS, INPUT_MODE, INPUT_PASSWORD, INPUT_PORT, INPUT_QUERY, INPUT_SSL_OPTIONS_CLASS, INPUT_USE_SSL, INPUT_USERNAME, INPUT_VALUE_CLASS, MAX_SPLIT_SIZE, MR_NAMESPACE, NODE_OPERATION_TYPE, OUTPUT_CLEAN_DIR, OUTPUT_COLLECTION, OUTPUT_CONTENT_ENCODING, OUTPUT_CONTENT_LANGUAGE, OUTPUT_CONTENT_NAMESPACE, OUTPUT_DIRECTORY, OUTPUT_FAST_LOAD, OUTPUT_FOREST_HOST, OUTPUT_HOST, OUTPUT_KEY_TYPE, OUTPUT_KEY_VARNAME, OUTPUT_NAMESPACE, OUTPUT_PASSWORD, OUTPUT_PERMISSION, OUTPUT_PORT, OUTPUT_PROPERTY_ALWAYS_CREATE, OUTPUT_QUALITY, OUTPUT_QUERY, OUTPUT_SSL_OPTIONS_CLASS, OUTPUT_STREAMING, OUTPUT_TOLERATE_ERRORS, OUTPUT_USE_SSL, OUTPUT_USERNAME, OUTPUT_VALUE_TYPE, OUTPUT_VALUE_VARNAME, OUTPUT_XML_REPAIR_LEVEL, PATH_NAMESPACE, PROPERTY_OPERATION_TYPE, RECORD_TO_FRAGMENT_RATIO, SPLIT_END_VARNAME, SPLIT_QUERY, SPLIT_START_VARNAME, SUBDOCUMENT_EXPRESSION, TXN_SIZE

Constructor Summary

MarkLogicRecordReader(org.apache.hadoop.conf.Configuration conf)

Method Summary

void	close()
protected abstract void	endOfResult()
org.apache.hadoop.conf.Configuration	getConf()
long	getCount()
protected abstract float	getDefaultRatio()
float	getProgress()
void	initialize(org.apache.hadoop.mapreduce.InputSplit split, org.apache.hadoop.mapreduce.TaskAttemptContext context)
boolean	nextKeyValue()
protected abstract boolean	nextResult(com.marklogic.xcc.ResultItem result)

Methods inherited from class org.apache.hadoop.mapreduce.RecordReader

getCurrentKey, getCurrentValue

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

LOG

public static final org.apache.commons.logging.Log LOG

mlSplit

protected MarkLogicInputSplit mlSplit

Input split for this record reader

count

protected long count

Count of records fetched

session

protected com.marklogic.xcc.Session session

Session to the MarkLogic server.

result

protected com.marklogic.xcc.ResultSequence result

ResultSequence from the MarkLogic server.

conf

protected org.apache.hadoop.conf.Configuration conf

Job configuration.

length

protected float length

Total expected count of the records in a split.

Constructor Detail

MarkLogicRecordReader

public MarkLogicRecordReader(org.apache.hadoop.conf.Configuration conf)

Method Detail

close

public void close()
           throws IOException

Specified by:

close in interface Closeable

Specified by:

close in class org.apache.hadoop.mapreduce.RecordReader<KEYIN,VALUEIN>

Throws:

IOException

getConf

public org.apache.hadoop.conf.Configuration getConf()

getProgress

public float getProgress()
                  throws IOException,
                         InterruptedException

Specified by:

getProgress in class org.apache.hadoop.mapreduce.RecordReader<KEYIN,VALUEIN>

Throws:

IOException

InterruptedException

initialize

public void initialize(org.apache.hadoop.mapreduce.InputSplit split,
                       org.apache.hadoop.mapreduce.TaskAttemptContext context)
                throws IOException,
                       InterruptedException

Specified by:

initialize in class org.apache.hadoop.mapreduce.RecordReader<KEYIN,VALUEIN>

Throws:

IOException

InterruptedException

nextKeyValue

public boolean nextKeyValue()
                     throws IOException,
                            InterruptedException

Specified by:

nextKeyValue in class org.apache.hadoop.mapreduce.RecordReader<KEYIN,VALUEIN>

Throws:

IOException

InterruptedException

endOfResult

protected abstract void endOfResult()

nextResult

protected abstract boolean nextResult(com.marklogic.xcc.ResultItem result)

getDefaultRatio

protected abstract float getDefaultRatio()

getCount

public long getCount()