org.apache.beam.sdk.io.tika

Interface TikaOptions

All Superinterfaces:

HasDisplayData, PipelineOptions

public interface TikaOptions
extends PipelineOptions

TikaInput Options to support the command-line applications.

Nested Class Summary

Nested classes/interfaces inherited from interface org.apache.beam.sdk.options.PipelineOptions

PipelineOptions.AtomicLongFactory, PipelineOptions.CheckEnabled, PipelineOptions.DirectRunner, PipelineOptions.JobNameFactory, PipelineOptions.UserAgentFactory

Method Summary

Modifier and Type	Method and Description
java.lang.String	getContentTypeHint()
java.lang.String	getInput()
java.lang.Integer	getMinimumTextLength()
java.lang.String	getOutput()
java.lang.Boolean	getParseSynchronously()
java.lang.String	getPipelineName()
java.lang.Long	getQueueMaxPollTime()
java.lang.Long	getQueuePollTime()
java.lang.Boolean	getReadOutputMetadata()
java.lang.String	getTikaConfigPath()
void	setContentTypeHint(java.lang.String value)
void	setInput(java.lang.String value)
void	setMinimumTextLength(java.lang.Integer value)
void	setOutput(java.lang.String value)
void	setParseSynchronously(java.lang.Boolean value)
void	setPipelineName(java.lang.String value)
void	setQueueMaxPollTime(java.lang.Long value)
void	setQueuePollTime(java.lang.Long value)
void	setReadOutputMetadata(java.lang.Boolean value)
void	setTikaConfigPath(java.lang.String value)

Methods inherited from interface org.apache.beam.sdk.options.PipelineOptions

as, getJobName, getOptionsId, getRunner, getStableUniqueNames, getTempLocation, getUserAgent, outputRuntimeOptions, setJobName, setOptionsId, setRunner, setStableUniqueNames, setTempLocation, setUserAgent

Methods inherited from interface org.apache.beam.sdk.transforms.display.HasDisplayData

populateDisplayData

Method Detail

getInput

@Validation.Required
java.lang.String getInput()

setInput

void setInput(java.lang.String value)

getTikaConfigPath

java.lang.String getTikaConfigPath()

setTikaConfigPath

void setTikaConfigPath(java.lang.String value)

getContentTypeHint

java.lang.String getContentTypeHint()

setContentTypeHint

void setContentTypeHint(java.lang.String value)

getReadOutputMetadata

@Default.Boolean(value=false)
java.lang.Boolean getReadOutputMetadata()

setReadOutputMetadata

void setReadOutputMetadata(java.lang.Boolean value)

getParseSynchronously

@Default.Boolean(value=false)
java.lang.Boolean getParseSynchronously()

setParseSynchronously

void setParseSynchronously(java.lang.Boolean value)

getQueuePollTime

@Default.Long(value=50L)
java.lang.Long getQueuePollTime()

setQueuePollTime

void setQueuePollTime(java.lang.Long value)

getQueueMaxPollTime

@Default.Long(value=3000L)
java.lang.Long getQueueMaxPollTime()

setQueueMaxPollTime

void setQueueMaxPollTime(java.lang.Long value)

getMinimumTextLength

@Default.Integer(value=0)
java.lang.Integer getMinimumTextLength()

setMinimumTextLength

void setMinimumTextLength(java.lang.Integer value)

getPipelineName

@Default.String(value="TikaRead")
java.lang.String getPipelineName()

setPipelineName

void setPipelineName(java.lang.String value)

getOutput

@Default.String(value="/tmp/tika/out")
java.lang.String getOutput()

setOutput

void setOutput(java.lang.String value)