Package org.apache.hop.execution.sampler.plugins.dataprof

Class BasicDataProfilingDataSampler

java.lang.Object

org.apache.hop.execution.sampler.plugins.dataprof.BasicDataProfilingDataSampler

All Implemented Interfaces:

Cloneable, IExecutionDataSampler<BasicDataProfilingDataSamplerStore>

@GuiPlugin
@ExecutionDataSamplerPlugin(id="BasicDataProfilingRowsExecutionDataSampler",
                            name="Data profile output rows",
                            description="Allow for some basic data profiling to be performed on transform output rows")
public class BasicDataProfilingDataSampler
extends Object
implements IExecutionDataSampler<BasicDataProfilingDataSamplerStore>

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	BasicDataProfilingDataSampler.ProfilingType

Nested classes/interfaces inherited from interface org.apache.hop.execution.sampler.IExecutionDataSampler

IExecutionDataSampler.ExecutionDataSamplerObjectFactory

Field Summary

Fields

Modifier and Type	Field	Description
protected boolean	onlyProfilingLastTransforms
protected boolean	profilingMaximum
protected boolean	profilingMaxLength
protected boolean	profilingMinimum
protected boolean	profilingMinLength
protected boolean	profilingNrNonNull
protected boolean	profilingNrNull
protected String	sampleSize	The number of rows to sample for each field and each profiling result.

Constructor Summary

Constructors

Constructor	Description
BasicDataProfilingDataSampler()
BasicDataProfilingDataSampler(BasicDataProfilingDataSampler sampler)

Method Summary

Modifier and Type	Method	Description
BasicDataProfilingDataSampler	clone()
BasicDataProfilingDataSamplerStore	createSamplerStore(ExecutionDataSamplerMeta samplerMeta)	Create a sampler store to match the sampler.
String	getPluginId()	Gets pluginId
String	getPluginName()	Gets pluginName
String	getSampleSize()	Gets sampleSize
boolean	isOnlyProfilingLastTransforms()	Gets onlyProfilingLastTransforms
boolean	isProfilingMaximum()	Gets profilingMaximum
boolean	isProfilingMaxLength()	Gets profilingMaxLength
boolean	isProfilingMinimum()	Gets profilingMinimum
boolean	isProfilingMinLength()	Gets profilingMinLength
boolean	isProfilingNrNonNull()	Gets profilingNrNonNull
boolean	isProfilingNrNull()	Gets profilingNrNull
void	sampleRow(BasicDataProfilingDataSamplerStore store, IStream.StreamType streamType, IRowMeta rowMeta, Object[] row)	Sample one row in a stream or rows.
void	setOnlyProfilingLastTransforms(boolean onlyProfilingLastTransforms)	Sets onlyProfilingLastTransforms
void	setPluginId(String pluginId)	Sets pluginId
void	setPluginName(String pluginName)	Sets pluginName
void	setProfilingMaximum(boolean profilingMaximum)	Sets profilingMaximum
void	setProfilingMaxLength(boolean profilingMaxLength)	Sets profilingMaxLength
void	setProfilingMinimum(boolean profilingMinimum)	Sets profilingMinimum
void	setProfilingMinLength(boolean profilingMinLength)	Sets profilingMinLength
void	setProfilingNrNonNull(boolean profilingNrNonNull)	Sets profilingNrNonNull
void	setProfilingNrNull(boolean profilingNrNull)	Sets profilingNrNull
void	setSampleSize(String sampleSize)	Sets sampleSize

Methods inherited from class java.lang.Object

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

Field Detail

sampleSize

@GuiWidgetElement(order="100",
                  type=TEXT,
                  parentId="ExecutionDataSamplerParent",
                  label="i18n::BasicDataProfilingDataSampler.Label.SampleSize",
                  toolTip="i18n::BasicDataProfilingDataSampler.Tooltip.SampleSize")
protected String sampleSize

The number of rows to sample for each field and each profiling result.

onlyProfilingLastTransforms

@GuiWidgetElement(order="105",
                  type=CHECKBOX,
                  parentId="ExecutionDataSamplerParent",
                  label="i18n::BasicDataProfilingDataSampler.Label.LastTransforms")
protected boolean onlyProfilingLastTransforms

profilingMinimum

@GuiWidgetElement(order="110",
                  type=CHECKBOX,
                  parentId="ExecutionDataSamplerParent",
                  label="i18n::BasicDataProfilingDataSampler.Label.ProfilingMinimum")
protected boolean profilingMinimum

profilingMaximum

@GuiWidgetElement(order="120",
                  type=CHECKBOX,
                  parentId="ExecutionDataSamplerParent",
                  label="i18n::BasicDataProfilingDataSampler.Label.ProfilingMaximum")
protected boolean profilingMaximum

profilingNrNull

@GuiWidgetElement(order="140",
                  type=CHECKBOX,
                  parentId="ExecutionDataSamplerParent",
                  label="i18n::BasicDataProfilingDataSampler.Label.ProfilingNrNull")
protected boolean profilingNrNull

profilingNrNonNull

@GuiWidgetElement(order="150",
                  type=CHECKBOX,
                  parentId="ExecutionDataSamplerParent",
                  label="i18n::BasicDataProfilingDataSampler.Label.ProfilingNrNonNull")
protected boolean profilingNrNonNull

profilingMinLength

@GuiWidgetElement(order="160",
                  type=CHECKBOX,
                  parentId="ExecutionDataSamplerParent",
                  label="i18n::BasicDataProfilingDataSampler.Label.ProfilingMinimumLength")
protected boolean profilingMinLength

profilingMaxLength

@GuiWidgetElement(order="170",
                  type=CHECKBOX,
                  parentId="ExecutionDataSamplerParent",
                  label="i18n::BasicDataProfilingDataSampler.Label.ProfilingMaximumLength")
protected boolean profilingMaxLength

Constructor Detail

BasicDataProfilingDataSampler

public BasicDataProfilingDataSampler()

BasicDataProfilingDataSampler

public BasicDataProfilingDataSampler(BasicDataProfilingDataSampler sampler)

Method Detail

clone

public BasicDataProfilingDataSampler clone()

Specified by:

clone in interface IExecutionDataSampler<BasicDataProfilingDataSamplerStore>

Overrides:

clone in class Object

createSamplerStore

public BasicDataProfilingDataSamplerStore createSamplerStore(ExecutionDataSamplerMeta samplerMeta)

Description copied from interface: IExecutionDataSampler

Create a sampler store to match the sampler. It will allow you to store your intermediate sampler results.

Specified by:

createSamplerStore in interface IExecutionDataSampler<BasicDataProfilingDataSamplerStore>

Parameters:

samplerMeta - Metadata about the transform we're sampling for.

Returns:

A new sampler store instance.

sampleRow

public void sampleRow(BasicDataProfilingDataSamplerStore store,
                      IStream.StreamType streamType,
                      IRowMeta rowMeta,
                      Object[] row)
               throws HopException

Description copied from interface: IExecutionDataSampler

Sample one row in a stream or rows. It's up to the plugin to know what to do with it.

Specified by:

sampleRow in interface IExecutionDataSampler<BasicDataProfilingDataSamplerStore>

Parameters:

store - A place to store the samples and intermediate results

streamType - The type of stream we're sampling from. (INPUT, OUTPUT, READ, WRITTEN, ...)

rowMeta - The row metadata

row - The row data itself

Throws:

HopException

getPluginId

public String getPluginId()

Gets pluginId

Specified by:

getPluginId in interface IExecutionDataSampler<BasicDataProfilingDataSamplerStore>

Returns:

value of pluginId

setPluginId

public void setPluginId(String pluginId)

Sets pluginId

Specified by:

setPluginId in interface IExecutionDataSampler<BasicDataProfilingDataSamplerStore>

Parameters:

pluginId - value of pluginId

getPluginName

public String getPluginName()

Gets pluginName

Specified by:

getPluginName in interface IExecutionDataSampler<BasicDataProfilingDataSamplerStore>

Returns:

value of pluginName

setPluginName

public void setPluginName(String pluginName)

Sets pluginName

Specified by:

setPluginName in interface IExecutionDataSampler<BasicDataProfilingDataSamplerStore>

Parameters:

pluginName - value of pluginName

getSampleSize

public String getSampleSize()

Gets sampleSize

Returns:

value of sampleSize

setSampleSize

public void setSampleSize(String sampleSize)

Sets sampleSize

Parameters:

sampleSize - value of sampleSize

isOnlyProfilingLastTransforms

public boolean isOnlyProfilingLastTransforms()

Gets onlyProfilingLastTransforms

Returns:

value of onlyProfilingLastTransforms

setOnlyProfilingLastTransforms

public void setOnlyProfilingLastTransforms(boolean onlyProfilingLastTransforms)

Sets onlyProfilingLastTransforms

Parameters:

onlyProfilingLastTransforms - value of onlyProfilingLastTransforms

isProfilingMinimum

public boolean isProfilingMinimum()

Gets profilingMinimum

Returns:

value of profilingMinimum

setProfilingMinimum

public void setProfilingMinimum(boolean profilingMinimum)

Sets profilingMinimum

Parameters:

profilingMinimum - value of profilingMinimum

isProfilingMaximum

public boolean isProfilingMaximum()

Gets profilingMaximum

Returns:

value of profilingMaximum

setProfilingMaximum

public void setProfilingMaximum(boolean profilingMaximum)

Sets profilingMaximum

Parameters:

profilingMaximum - value of profilingMaximum

isProfilingNrNull

public boolean isProfilingNrNull()

Gets profilingNrNull

Returns:

value of profilingNrNull

setProfilingNrNull

public void setProfilingNrNull(boolean profilingNrNull)

Sets profilingNrNull

Parameters:

profilingNrNull - value of profilingNrNull

isProfilingNrNonNull

public boolean isProfilingNrNonNull()

Gets profilingNrNonNull

Returns:

value of profilingNrNonNull

setProfilingNrNonNull

public void setProfilingNrNonNull(boolean profilingNrNonNull)

Sets profilingNrNonNull

Parameters:

profilingNrNonNull - value of profilingNrNonNull

isProfilingMinLength

public boolean isProfilingMinLength()

Gets profilingMinLength

Returns:

value of profilingMinLength

setProfilingMinLength

public void setProfilingMinLength(boolean profilingMinLength)

Sets profilingMinLength

Parameters:

profilingMinLength - value of profilingMinLength

isProfilingMaxLength

public boolean isProfilingMaxLength()

Gets profilingMaxLength

Returns:

value of profilingMaxLength

setProfilingMaxLength

public void setProfilingMaxLength(boolean profilingMaxLength)

Sets profilingMaxLength

Parameters:

profilingMaxLength - value of profilingMaxLength