fr.univnantes.termsuite.uima.readers

Class AbstractTermSuiteCollectionReader

java.lang.Object

org.apache.uima.resource.Resource_ImplBase

org.apache.uima.resource.ConfigurableResource_ImplBase

org.apache.uima.collection.CollectionReader_ImplBase

fr.univnantes.termsuite.uima.readers.AbstractTermSuiteCollectionReader

All Implemented Interfaces:

org.apache.uima.collection.base_cpm.BaseCollectionReader, org.apache.uima.collection.CollectionReader, org.apache.uima.resource.ConfigurableResource, org.apache.uima.resource.Resource

Direct Known Subclasses:

JsonCollectionReader

public abstract class AbstractTermSuiteCollectionReader
extends org.apache.uima.collection.CollectionReader_ImplBase

An abstract CollectionException implementation for TermSuite that recursively load all selected files from an input directory, with customizable file filter and document text parser. of an input

Field Summary

Fields

Modifier and Type	Field and Description
protected TermSuiteCollection	collectionType
protected java.lang.String[]	droppedTags
static java.lang.String	PARAM_COLLECTION_TYPE
static java.lang.String	PARAM_DROPPED_TAGS
static java.lang.String	PARAM_ENCODING
static java.lang.String	PARAM_INPUTDIR
static java.lang.String	PARAM_LANGUAGE
static java.lang.String	PARAM_TXT_TAGS
protected java.lang.String[]	txtTags

Fields inherited from interface org.apache.uima.resource.Resource

PARAM_AGGREGATE_SOFA_MAPPINGS, PARAM_CONFIG_MANAGER, PARAM_CONFIG_PARAM_SETTINGS, PARAM_EXTERNAL_OVERRIDE_SETTINGS, PARAM_PERFORMANCE_TUNING_SETTINGS, PARAM_RESOURCE_MANAGER, PARAM_UIMA_CONTEXT

Constructor Summary

Constructors

Constructor and Description
AbstractTermSuiteCollectionReader()

Method Summary

Modifier and Type	Method and Description
void	close()
protected void	fillCas(org.apache.uima.cas.CAS cas, java.io.File file)
protected abstract java.lang.String	getDocumentText(java.lang.String uri, java.lang.String encoding) Gives the document text to set from the input file URI.
protected java.io.FilenameFilter	getFileFilter() The FilenameFilter for selecting input files to read.
java.util.List<java.io.File>	getFiles()
void	getNext(org.apache.uima.cas.CAS cas)
org.apache.uima.util.Progress[]	getProgress()
boolean	hasNext()
void	initialize()
protected void	lastFileRead() A hook that is executed after the last input files has been read.

Methods inherited from class org.apache.uima.collection.CollectionReader_ImplBase

destroy, getCasInitializer, getProcessingResourceMetaData, initialize, isConsuming, reconfigure, setCasInitializer, typeSystemInit

Methods inherited from class org.apache.uima.resource.ConfigurableResource_ImplBase

getConfigParameterValue, getConfigParameterValue, setConfigParameterValue, setConfigParameterValue

Methods inherited from class org.apache.uima.resource.Resource_ImplBase

getCasManager, getLogger, getMetaData, getResourceManager, getUimaContext, getUimaContextAdmin, setLogger, setMetaData

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.uima.resource.ConfigurableResource

getConfigParameterValue, getConfigParameterValue, setConfigParameterValue, setConfigParameterValue

Methods inherited from interface org.apache.uima.resource.Resource

getLogger, getMetaData, getResourceManager, getUimaContext, getUimaContextAdmin, setLogger

Field Detail

PARAM_INPUTDIR

public static final java.lang.String PARAM_INPUTDIR

See Also:

Constant Field Values

PARAM_ENCODING

public static final java.lang.String PARAM_ENCODING

See Also:

Constant Field Values

PARAM_LANGUAGE

public static final java.lang.String PARAM_LANGUAGE

See Also:

Constant Field Values

PARAM_COLLECTION_TYPE

public static final java.lang.String PARAM_COLLECTION_TYPE

See Also:

Constant Field Values

collectionType

protected TermSuiteCollection collectionType

PARAM_DROPPED_TAGS

public static final java.lang.String PARAM_DROPPED_TAGS

See Also:

Constant Field Values

droppedTags

protected java.lang.String[] droppedTags

PARAM_TXT_TAGS

public static final java.lang.String PARAM_TXT_TAGS

See Also:

Constant Field Values

txtTags

protected java.lang.String[] txtTags

Constructor Detail

AbstractTermSuiteCollectionReader

public AbstractTermSuiteCollectionReader()

Method Detail

initialize

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

Overrides:

initialize in class org.apache.uima.collection.CollectionReader_ImplBase

Throws:

org.apache.uima.resource.ResourceInitializationException

getNext

public void getNext(org.apache.uima.cas.CAS cas)
             throws java.io.IOException,
                    org.apache.uima.collection.CollectionException

Throws:

java.io.IOException

org.apache.uima.collection.CollectionException

fillCas

protected void fillCas(org.apache.uima.cas.CAS cas,
                       java.io.File file)
                throws java.io.IOException,
                       org.apache.uima.collection.CollectionException

Throws:

java.io.IOException

org.apache.uima.collection.CollectionException

hasNext

public boolean hasNext()
                throws java.io.IOException,
                       org.apache.uima.collection.CollectionException

Throws:

java.io.IOException

org.apache.uima.collection.CollectionException

getProgress

public org.apache.uima.util.Progress[] getProgress()

close

public void close()
           throws java.io.IOException

Throws:

java.io.IOException

getFiles

public java.util.List<java.io.File> getFiles()

getFileFilter

protected java.io.FilenameFilter getFileFilter()

The FilenameFilter for selecting input files to read.

Returns:

getDocumentText

protected abstract java.lang.String getDocumentText(java.lang.String uri,
                                                    java.lang.String encoding)
                                             throws java.io.IOException

Gives the document text to set from the input file URI.

Parameters:

uri -

Returns:

Throws:

java.io.IOException

lastFileRead

protected void lastFileRead()

A hook that is executed after the last input files has been read. (Before the last CAS pipeline runs)