oracle.spatial.hadoop.vector.mapred.job

Class BaseJob<K,V>

java.lang.Object

org.apache.hadoop.conf.Configured

oracle.spatial.hadoop.vector.mapred.job.BaseJob<K,V>

Type Parameters:

K - the type of the input keys

V - the type of the input values

All Implemented Interfaces:

org.apache.hadoop.conf.Configurable, org.apache.hadoop.util.Tool

Direct Known Subclasses:

IndexedInputBaseJob, KMeansClustering, MultipleInputsJob, SpatialIndexing, SuggestService

public abstract class BaseJob<K,V>
extends org.apache.hadoop.conf.Configured
implements org.apache.hadoop.util.Tool

Defines the basic parameters and validations for vector jobs

Field Summary

Fields

Modifier and Type	Field and Description
protected CmdArgsParser	argsp
protected AbstractInputDataSet	inputDataSet
protected java.lang.Class<?>	jarClass
protected org.apache.hadoop.fs.Path	jobRegEntryPath
protected FileInputDataSet	proxyIDS

Constructor Summary

Constructors

Constructor and Description
BaseJob()

Method Summary

Methods

Modifier and Type	Method and Description
protected org.apache.hadoop.fs.Path	addJobRegistryEntry(org.apache.hadoop.fs.Path jobRegEntryPath, org.apache.hadoop.mapreduce.Job job)
protected org.apache.hadoop.fs.Path	addJobRegistryEntry(org.apache.hadoop.fs.Path jobRegEntryPath, oracle.spatial.hadoop.commons.logging.registry.JobRegistryEntry jobRegEntry, org.apache.hadoop.conf.Configuration conf)
protected org.apache.hadoop.fs.Path	addJobRegistryEntry(org.apache.hadoop.fs.Path jobRegEntryPath, org.apache.hadoop.mapred.RunningJob runningJob)
void	configure(org.apache.hadoop.mapreduce.Job job) Validates and adds the current parameters to the job configuration
void	configure(org.apache.hadoop.mapred.JobConf jobConf) Validates and adds the current parameters to the job configuration
protected org.apache.hadoop.mapreduce.Job	createJob()
protected org.apache.hadoop.mapreduce.Job	createJob(org.apache.hadoop.conf.Configuration conf)
protected org.apache.hadoop.mapreduce.Job	createJob(org.apache.hadoop.conf.Configuration conf, java.lang.String jobName)
protected org.apache.hadoop.mapreduce.Job	createJob(org.apache.hadoop.conf.Configuration conf, java.lang.String jobName, java.lang.String jar)
protected org.apache.hadoop.mapred.JobConf	createJobConf() Creates a job configuration
protected org.apache.hadoop.mapred.JobConf	createJobConf(org.apache.hadoop.mapred.JobConf baseConf)
protected org.apache.hadoop.mapred.JobConf	createJobConf(org.apache.hadoop.mapred.JobConf baseConf, java.lang.String jobName)
java.lang.String	getCmdOptions() Gets a description of the arguments expected from command line.
java.lang.String	getCmdOptionsWithInputDataSets() Gets a descriptive text about the parameters expected by the job plus a description of the supported input data set types
protected java.lang.String	getCmdOptionsWithInputDataSets(InputDataSetCmdArgsParserHandler parserHandler)
java.util.Map<java.lang.String,java.lang.Object>	getCurrentCmdArgs(org.apache.hadoop.conf.Configuration conf) Returns the current driver properties in a map where each key-value is a name and value of a command line argument.
java.lang.String	getCurrentCmdArgsAsString(org.apache.hadoop.conf.Configuration conf) Returns the current driver properties as a space-separated list of name=value elements.
protected void	getCurrentCmdArgsAsString(java.util.Map<java.lang.String,java.lang.Object> cmdArgs, java.lang.StringBuilder buff)
java.lang.String	getInput() Gets the job input string
AbstractInputDataSet	getInputDataSet() Gets the current input data set
protected abstract InputDataSetCmdArgsParserHandler	getInputDataSetCmdParserHandler(org.apache.hadoop.conf.Configuration conf) Gets the current instance of InputDataSetCmdArgsParserHandler used to parse command line parameters for the input data set
protected abstract InputDataSetConfiguratorHandler	getInputDataSetConfiguratorHandler(org.apache.hadoop.conf.Configuration conf) Returns the current instance of InputDataSetConfiguratorHandler used to configure the input data set
java.lang.Class<?>	getInputFormatClass() Gets the input format used to read the input data
java.lang.Class<?>	getJarClass()
java.lang.String	getOutput() Gets the job output path
java.lang.Class<? extends RecordInfoProvider<K,V>>	getRecordInfoProviderClass() Gets the RecordInfoProvider class used to interpret input records.
SpatialConfig	getSpatialConfig() Gets the spatial configuration that describes the geometries in the input data.
void	processArgs(java.lang.String[] args, org.apache.hadoop.conf.Configuration conf) Extracts and validates arguments from the command line
protected boolean	runJob(org.apache.hadoop.mapreduce.Job job)
protected org.apache.hadoop.mapred.RunningJob	runJob(org.apache.hadoop.mapred.JobConf jobConf)
void	setInput(java.lang.String input) Sets the job input string
void	setInputDataSet(AbstractInputDataSet inputDataSet)
void	setInputFormatClass(java.lang.Class<?> inputFormatClass) Sets the input format used to read the input data
void	setJarClass(java.lang.Class<?> jarClass)
void	setOutput(java.lang.String output) Sets the job output
void	setRecordInfoProviderClass(java.lang.Class<? extends RecordInfoProvider<K,V>> recordInfoProviderClass) Sets the RecordInfoProvider class used to interpret input records.
void	setSpatialConfig(SpatialConfig spatialConfig) Sets the spatial configuration that describes the geometries in the input data.
protected void	updateInputDataSet()

Methods inherited from class org.apache.hadoop.conf.Configured

getConf, setConf

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.hadoop.util.Tool

run

Methods inherited from interface org.apache.hadoop.conf.Configurable

getConf, setConf

Field Detail

argsp

protected CmdArgsParser argsp

jarClass

protected java.lang.Class<?> jarClass

inputDataSet

protected AbstractInputDataSet inputDataSet

proxyIDS

protected FileInputDataSet proxyIDS

jobRegEntryPath

protected org.apache.hadoop.fs.Path jobRegEntryPath

Constructor Detail

BaseJob

public BaseJob()

Method Detail

getInputDataSetConfiguratorHandler

protected abstract InputDataSetConfiguratorHandler getInputDataSetConfiguratorHandler(org.apache.hadoop.conf.Configuration conf)

Returns the current instance of InputDataSetConfiguratorHandler used to configure the input data set

Parameters:

conf - a job configuration

Returns:

an instance of InputDataSetConfiguratorHandler

getInputDataSetCmdParserHandler

protected abstract InputDataSetCmdArgsParserHandler getInputDataSetCmdParserHandler(org.apache.hadoop.conf.Configuration conf)

Gets the current instance of InputDataSetCmdArgsParserHandler used to parse command line parameters for the input data set

Parameters:

conf - a job configuration

Returns:

an instance of InputDataSetCmdArgsParserHandler

setInputDataSet

public void setInputDataSet(AbstractInputDataSet inputDataSet)

getInputDataSet

public AbstractInputDataSet getInputDataSet()

Gets the current input data set

Returns:

an instance of AbstractInputDataSet

getInput

public java.lang.String getInput()

Gets the job input string

Returns:

a path, comma-separated paths or a path pattern

setInput

public void setInput(java.lang.String input)

Sets the job input string

Parameters:

input - a path, comma-separated paths or a path pattern

getOutput

public java.lang.String getOutput()

Gets the job output path

Returns:

a path

setOutput

public void setOutput(java.lang.String output)

Sets the job output

Parameters:

output - a path

getInputFormatClass

public java.lang.Class<?> getInputFormatClass()

Gets the input format used to read the input data

Returns:

an InputFormat subclass

setInputFormatClass

public void setInputFormatClass(java.lang.Class<?> inputFormatClass)

Sets the input format used to read the input data

Parameters:

inputFormatClass - an InputFormat subclass

getRecordInfoProviderClass

public java.lang.Class<? extends RecordInfoProvider<K,V>> getRecordInfoProviderClass()

Gets the RecordInfoProvider class used to interpret input records.

Returns:

a RecordInfoProvider subclass

setRecordInfoProviderClass

public void setRecordInfoProviderClass(java.lang.Class<? extends RecordInfoProvider<K,V>> recordInfoProviderClass)

Sets the RecordInfoProvider class used to interpret input records.

Parameters:

recordInfoProviderClass - a RecordInfoProvider subclass

setSpatialConfig

public void setSpatialConfig(SpatialConfig spatialConfig)

Sets the spatial configuration that describes the geometries in the input data.

Parameters:

spatialConfig - the spatial configuration

getSpatialConfig

public SpatialConfig getSpatialConfig()

Gets the spatial configuration that describes the geometries in the input data.

Returns:

the spatial configuration

setJarClass

public void setJarClass(java.lang.Class<?> jarClass)

getJarClass

public java.lang.Class<?> getJarClass()

processArgs

public void processArgs(java.lang.String[] args,
               org.apache.hadoop.conf.Configuration conf)
                 throws java.lang.Exception

Extracts and validates arguments from the command line

Parameters:

args - arguments from the command line

conf - the job configuration

Throws:

java.lang.Exception

getCurrentCmdArgs

public java.util.Map<java.lang.String,java.lang.Object> getCurrentCmdArgs(org.apache.hadoop.conf.Configuration conf)

Returns the current driver properties in a map where each key-value is a name and value of a command line argument. By printing this information it is possible to know how to execute a similar job from command line

Parameters:

conf - a job configuration

Returns:

a map which entries are of type <String,String> or <String, Map<String, Object>> for multiple input data sets. For nested maps, the entry types are the same than the enclosing map

getCurrentCmdArgsAsString

public java.lang.String getCurrentCmdArgsAsString(org.apache.hadoop.conf.Configuration conf)

Returns the current driver properties as a space-separated list of name=value elements. By printing this information it is possible to know how to execute a similar job from command line

Parameters:

conf - a job configuration

Returns:

a string containing command line arguments

getCurrentCmdArgsAsString

protected void getCurrentCmdArgsAsString(java.util.Map<java.lang.String,java.lang.Object> cmdArgs,
                             java.lang.StringBuilder buff)

getCmdOptionsWithInputDataSets

public java.lang.String getCmdOptionsWithInputDataSets()

Gets a descriptive text about the parameters expected by the job plus a description of the supported input data set types

Returns:

a string

getCmdOptionsWithInputDataSets

protected java.lang.String getCmdOptionsWithInputDataSets(InputDataSetCmdArgsParserHandler parserHandler)

getCmdOptions

public java.lang.String getCmdOptions()

Gets a description of the arguments expected from command line.

Returns:

a text description

configure

public void configure(org.apache.hadoop.mapred.JobConf jobConf)
               throws java.lang.Exception

Validates and adds the current parameters to the job configuration

Parameters:

jobConf - the job configuration

Throws:

java.lang.Exception

configure

public void configure(org.apache.hadoop.mapreduce.Job job)
               throws java.lang.Exception

Validates and adds the current parameters to the job configuration

Parameters:

job - a job instance

Throws:

java.lang.Exception

createJobConf

protected org.apache.hadoop.mapred.JobConf createJobConf()

Creates a job configuration

Returns:

a job configuration

createJobConf

protected org.apache.hadoop.mapred.JobConf createJobConf(org.apache.hadoop.mapred.JobConf baseConf)

createJobConf

protected org.apache.hadoop.mapred.JobConf createJobConf(org.apache.hadoop.mapred.JobConf baseConf,
                                             java.lang.String jobName)

createJob

protected org.apache.hadoop.mapreduce.Job createJob()
                                             throws java.io.IOException

Throws:

java.io.IOException

createJob

protected org.apache.hadoop.mapreduce.Job createJob(org.apache.hadoop.conf.Configuration conf)
                                             throws java.io.IOException

Throws:

java.io.IOException

createJob

protected org.apache.hadoop.mapreduce.Job createJob(org.apache.hadoop.conf.Configuration conf,
                                        java.lang.String jobName)
                                             throws java.io.IOException

Throws:

java.io.IOException

createJob

protected org.apache.hadoop.mapreduce.Job createJob(org.apache.hadoop.conf.Configuration conf,
                                        java.lang.String jobName,
                                        java.lang.String jar)
                                             throws java.io.IOException

Throws:

java.io.IOException

updateInputDataSet

protected void updateInputDataSet()

addJobRegistryEntry

protected org.apache.hadoop.fs.Path addJobRegistryEntry(org.apache.hadoop.fs.Path jobRegEntryPath,
                                            org.apache.hadoop.mapred.RunningJob runningJob)

addJobRegistryEntry

protected org.apache.hadoop.fs.Path addJobRegistryEntry(org.apache.hadoop.fs.Path jobRegEntryPath,
                                            org.apache.hadoop.mapreduce.Job job)

addJobRegistryEntry

protected org.apache.hadoop.fs.Path addJobRegistryEntry(org.apache.hadoop.fs.Path jobRegEntryPath,
                                            oracle.spatial.hadoop.commons.logging.registry.JobRegistryEntry jobRegEntry,
                                            org.apache.hadoop.conf.Configuration conf)

runJob

protected org.apache.hadoop.mapred.RunningJob runJob(org.apache.hadoop.mapred.JobConf jobConf)
                                              throws java.lang.Exception

Throws:

java.lang.Exception

runJob

protected boolean runJob(org.apache.hadoop.mapreduce.Job job)
                  throws java.lang.Exception

Throws:

java.lang.Exception