opennlp.uima.tokenize

Class AbstractTokenizer

java.lang.Object

org.apache.uima.analysis_component.AnalysisComponent_ImplBase

org.apache.uima.analysis_component.Annotator_ImplBase

org.apache.uima.analysis_component.CasAnnotator_ImplBase

opennlp.uima.tokenize.AbstractTokenizer

All Implemented Interfaces:

org.apache.uima.analysis_component.AnalysisComponent

Direct Known Subclasses:

SimpleTokenizer, Tokenizer, WhitespaceTokenizer

public abstract class AbstractTokenizer
extends org.apache.uima.analysis_component.CasAnnotator_ImplBase

Field Summary

Fields

Modifier and Type	Field and Description
protected org.apache.uima.UimaContext	context
protected org.apache.uima.util.Logger	logger
protected String	name
protected org.apache.uima.cas.Type	sentenceType Type of the sentence containing the tokens.
protected org.apache.uima.cas.Type	tokenType Type of the tokens to be created.

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	AbstractTokenizer(String name)

Method Summary

Modifier and Type	Method and Description
void	initialize(org.apache.uima.UimaContext context)
protected void	postProcessAnnotations(Span[] tokens, org.apache.uima.cas.text.AnnotationFS[] tokenAnnotations)
void	process(org.apache.uima.cas.CAS cas)
protected abstract Span[]	tokenize(org.apache.uima.cas.CAS cas, org.apache.uima.cas.text.AnnotationFS sentence)
void	typeSystemInit(org.apache.uima.cas.TypeSystem typeSystem)

Methods inherited from class org.apache.uima.analysis_component.CasAnnotator_ImplBase

getRequiredCasInterface, process

Methods inherited from class org.apache.uima.analysis_component.Annotator_ImplBase

getCasInstancesRequired, hasNext, next

Methods inherited from class org.apache.uima.analysis_component.AnalysisComponent_ImplBase

batchProcessComplete, collectionProcessComplete, destroy, getContext, getResultSpecification, reconfigure, setResultSpecification

Methods inherited from class java.lang.Object

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

Field Detail

name

protected final String name

context

protected org.apache.uima.UimaContext context

logger

protected org.apache.uima.util.Logger logger

sentenceType

protected org.apache.uima.cas.Type sentenceType

Type of the sentence containing the tokens.

tokenType

protected org.apache.uima.cas.Type tokenType

Type of the tokens to be created.

Constructor Detail

AbstractTokenizer

protected AbstractTokenizer(String name)

Method Detail

initialize

public void initialize(org.apache.uima.UimaContext context)
                throws org.apache.uima.resource.ResourceInitializationException

Specified by:

initialize in interface org.apache.uima.analysis_component.AnalysisComponent

Overrides:

initialize in class org.apache.uima.analysis_component.AnalysisComponent_ImplBase

Throws:

org.apache.uima.resource.ResourceInitializationException

typeSystemInit

public void typeSystemInit(org.apache.uima.cas.TypeSystem typeSystem)
                    throws org.apache.uima.analysis_engine.AnalysisEngineProcessException

Overrides:

typeSystemInit in class org.apache.uima.analysis_component.CasAnnotator_ImplBase

Throws:

org.apache.uima.analysis_engine.AnalysisEngineProcessException

postProcessAnnotations

protected void postProcessAnnotations(Span[] tokens,
                                      org.apache.uima.cas.text.AnnotationFS[] tokenAnnotations)

tokenize

protected abstract Span[] tokenize(org.apache.uima.cas.CAS cas,
                                   org.apache.uima.cas.text.AnnotationFS sentence)

process

public void process(org.apache.uima.cas.CAS cas)
             throws org.apache.uima.analysis_engine.AnalysisEngineProcessException

Specified by:

process in class org.apache.uima.analysis_component.CasAnnotator_ImplBase

Throws:

org.apache.uima.analysis_engine.AnalysisEngineProcessException