org.apache.giraph.io.hcatalog

Class GiraphHCatInputFormat

java.lang.Object

org.apache.hadoop.mapreduce.InputFormat<org.apache.hadoop.io.WritableComparable,org.apache.hcatalog.data.HCatRecord>

org.apache.hcatalog.mapreduce.HCatBaseInputFormat

org.apache.giraph.io.hcatalog.GiraphHCatInputFormat

public class GiraphHCatInputFormat
extends org.apache.hcatalog.mapreduce.HCatBaseInputFormat

Provides functionality similar to HCatInputFormat, but allows for different data sources (vertex and edge data).

Field Summary

Fields

Modifier and Type	Field and Description
static String	EDGE_INPUT_JOB_INFO Edge input job info for HCatalog.
static String	VERTEX_INPUT_JOB_INFO Vertex input job info for HCatalog.

Constructor Summary

Constructors

Constructor and Description
GiraphHCatInputFormat()

Method Summary

Modifier and Type	Method and Description
org.apache.hadoop.mapreduce.RecordReader<org.apache.hadoop.io.WritableComparable,org.apache.hcatalog.data.HCatRecord>	createEdgeRecordReader(org.apache.hadoop.mapreduce.InputSplit split, org.apache.hadoop.mapreduce.TaskAttemptContext taskContext) Create a RecordReader for edges.
org.apache.hadoop.mapreduce.RecordReader<org.apache.hadoop.io.WritableComparable,org.apache.hcatalog.data.HCatRecord>	createVertexRecordReader(org.apache.hadoop.mapreduce.InputSplit split, org.apache.hadoop.mapreduce.TaskAttemptContext taskContext) Create a RecordReader for vertices.
List<org.apache.hadoop.mapreduce.InputSplit>	getEdgeSplits(org.apache.hadoop.mapreduce.JobContext jobContext) Get edge input splits.
static org.apache.hcatalog.data.schema.HCatSchema	getEdgeTableSchema(org.apache.hadoop.conf.Configuration conf) Get edge input table schema.
List<org.apache.hadoop.mapreduce.InputSplit>	getVertexSplits(org.apache.hadoop.mapreduce.JobContext jobContext) Get vertex input splits.
static org.apache.hcatalog.data.schema.HCatSchema	getVertexTableSchema(org.apache.hadoop.conf.Configuration conf) Get vertex input table schema.
static void	setEdgeInput(org.apache.hadoop.mapreduce.Job job, org.apache.hcatalog.mapreduce.InputJobInfo inputJobInfo) Set edge InputJobInfo.
static void	setVertexInput(org.apache.hadoop.mapreduce.Job job, org.apache.hcatalog.mapreduce.InputJobInfo inputJobInfo) Set vertex InputJobInfo.

Methods inherited from class org.apache.hcatalog.mapreduce.HCatBaseInputFormat

createRecordReader, getMapRedInputFormat, getSplits, getTableSchema, getTableSchema, setOutputSchema

Methods inherited from class java.lang.Object

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

Field Detail

VERTEX_INPUT_JOB_INFO

public static final String VERTEX_INPUT_JOB_INFO

Vertex input job info for HCatalog.

See Also:

Constant Field Values

EDGE_INPUT_JOB_INFO

public static final String EDGE_INPUT_JOB_INFO

Edge input job info for HCatalog.

See Also:

Constant Field Values

Constructor Detail

GiraphHCatInputFormat

public GiraphHCatInputFormat()

Method Detail

setVertexInput

public static void setVertexInput(org.apache.hadoop.mapreduce.Job job,
                                  org.apache.hcatalog.mapreduce.InputJobInfo inputJobInfo)
                           throws IOException

Set vertex InputJobInfo.

Parameters:

job - The job

inputJobInfo - Vertex input job info

Throws:

IOException

setEdgeInput

public static void setEdgeInput(org.apache.hadoop.mapreduce.Job job,
                                org.apache.hcatalog.mapreduce.InputJobInfo inputJobInfo)
                         throws IOException

Set edge InputJobInfo.

Parameters:

job - The job

inputJobInfo - Edge input job info

Throws:

IOException

getVertexTableSchema

public static org.apache.hcatalog.data.schema.HCatSchema getVertexTableSchema(org.apache.hadoop.conf.Configuration conf)
                                                                       throws IOException

Get vertex input table schema.

Parameters:

conf - Job configuration

Returns:

Vertex input table schema

Throws:

IOException

getEdgeTableSchema

public static org.apache.hcatalog.data.schema.HCatSchema getEdgeTableSchema(org.apache.hadoop.conf.Configuration conf)
                                                                     throws IOException

Get edge input table schema.

Parameters:

conf - Job configuration

Returns:

Edge input table schema

Throws:

IOException

getVertexSplits

public List<org.apache.hadoop.mapreduce.InputSplit> getVertexSplits(org.apache.hadoop.mapreduce.JobContext jobContext)
                                                             throws IOException,
                                                                    InterruptedException

Get vertex input splits.

Parameters:

jobContext - Job context

Returns:

List of vertex InputSplits

Throws:

IOException

InterruptedException

getEdgeSplits

public List<org.apache.hadoop.mapreduce.InputSplit> getEdgeSplits(org.apache.hadoop.mapreduce.JobContext jobContext)
                                                           throws IOException,
                                                                  InterruptedException

Get edge input splits.

Parameters:

jobContext - Job context

Returns:

List of edge InputSplits

Throws:

IOException

InterruptedException

createVertexRecordReader

public org.apache.hadoop.mapreduce.RecordReader<org.apache.hadoop.io.WritableComparable,org.apache.hcatalog.data.HCatRecord> createVertexRecordReader(org.apache.hadoop.mapreduce.InputSplit split,
                                                                                                                                                      org.apache.hadoop.mapreduce.TaskAttemptContext taskContext)
                                                                                                                                               throws IOException,
                                                                                                                                                      InterruptedException

Create a RecordReader for vertices.

Parameters:

split - Input split

taskContext - Context

Returns:

Record reader

Throws:

IOException

InterruptedException

createEdgeRecordReader

public org.apache.hadoop.mapreduce.RecordReader<org.apache.hadoop.io.WritableComparable,org.apache.hcatalog.data.HCatRecord> createEdgeRecordReader(org.apache.hadoop.mapreduce.InputSplit split,
                                                                                                                                                    org.apache.hadoop.mapreduce.TaskAttemptContext taskContext)
                                                                                                                                             throws IOException,
                                                                                                                                                    InterruptedException

Create a RecordReader for edges.

Parameters:

split - Input split

taskContext - Context

Returns:

Record reader

Throws:

IOException

InterruptedException