org.dice_research.topicmodeling.io.xml

Class AbstractDocumentXmlReader

java.lang.Object

org.dice_research.topicmodeling.io.xml.AbstractDocumentXmlReader

All Implemented Interfaces:

XMLParserObserver

Direct Known Subclasses:

CorpusXmlReader, StreamBasedXmlDocumentSupplier

public abstract class AbstractDocumentXmlReader
extends Object
implements XMLParserObserver

Field Summary

Fields

Modifier and Type	Field and Description
private List<String>	categories
private org.dice_research.topicmodeling.utils.doc.Document	currentDocument
private org.dice_research.topicmodeling.utils.doc.ner.NamedEntityInText	currentNamedEntity
private String	data
private static org.slf4j.Logger	LOGGER
private List<org.dice_research.topicmodeling.utils.doc.ner.NamedEntityInText>	namedEntities
private StringBuilder	textBuffer

Constructor Summary

Constructors

Constructor and Description
AbstractDocumentXmlReader()

Method Summary

Modifier and Type	Method and Description
protected abstract void	finishedDocument(org.dice_research.topicmodeling.utils.doc.Document document)
void	handleClosingTag(String tagString)
void	handleData(String data)
void	handleEmptyTag(String tagString)
void	handleOpeningTag(String tagString)
protected org.dice_research.topicmodeling.utils.doc.ner.NamedEntityInText	parseNamedEntityInText(String tag)
static void	registerParseableDocumentProperty(Class<? extends org.dice_research.topicmodeling.utils.doc.ParseableDocumentProperty> clazz)

Methods inherited from class java.lang.Object

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

Field Detail

LOGGER

private static final org.slf4j.Logger LOGGER

currentDocument

private org.dice_research.topicmodeling.utils.doc.Document currentDocument

currentNamedEntity

private org.dice_research.topicmodeling.utils.doc.ner.NamedEntityInText currentNamedEntity

namedEntities

private List<org.dice_research.topicmodeling.utils.doc.ner.NamedEntityInText> namedEntities

categories

private List<String> categories

textBuffer

private StringBuilder textBuffer

data

private String data

Constructor Detail

AbstractDocumentXmlReader

public AbstractDocumentXmlReader()

Method Detail

handleOpeningTag

public void handleOpeningTag(String tagString)

Specified by:

handleOpeningTag in interface XMLParserObserver

handleClosingTag

public void handleClosingTag(String tagString)

Specified by:

handleClosingTag in interface XMLParserObserver

handleData

public void handleData(String data)

Specified by:

handleData in interface XMLParserObserver

handleEmptyTag

public void handleEmptyTag(String tagString)

Specified by:

handleEmptyTag in interface XMLParserObserver

parseNamedEntityInText

protected org.dice_research.topicmodeling.utils.doc.ner.NamedEntityInText parseNamedEntityInText(String tag)

registerParseableDocumentProperty

public static void registerParseableDocumentProperty(Class<? extends org.dice_research.topicmodeling.utils.doc.ParseableDocumentProperty> clazz)

finishedDocument

protected abstract void finishedDocument(org.dice_research.topicmodeling.utils.doc.Document document)