public class StreamBasedXmlDocumentSupplier extends AbstractDocumentXmlReader implements org.dice_research.topicmodeling.preprocessing.docsupplier.DocumentSupplier
| Modifier and Type | Field and Description |
|---|---|
private org.dice_research.topicmodeling.utils.doc.Document |
document |
private int |
documentCount |
private static org.slf4j.Logger |
LOGGER |
private int |
nextDocumentId |
private static boolean |
USE_DOCUMENT_IDS_FROM_FILE_DEFAULT |
private boolean |
useDocumentIdsFromFile |
private FileReader |
xmlFileReader |
private SimpleReaderBasedXMLParser |
xmlParser |
| Modifier | Constructor and Description |
|---|---|
private |
StreamBasedXmlDocumentSupplier(FileReader reader,
boolean useDocumentIdsFromFile) |
| Modifier and Type | Method and Description |
|---|---|
static StreamBasedXmlDocumentSupplier |
createReader(File file) |
static StreamBasedXmlDocumentSupplier |
createReader(File file,
boolean useDocumentIdsFromFile) |
static StreamBasedXmlDocumentSupplier |
createReader(String filename) |
static StreamBasedXmlDocumentSupplier |
createReader(String filename,
boolean useDocumentIdsFromFile) |
protected void |
finishedDocument(org.dice_research.topicmodeling.utils.doc.Document document) |
org.dice_research.topicmodeling.utils.doc.Document |
getNextDocument() |
protected int |
getNextDocumentId() |
void |
setDocumentStartId(int documentStartId) |
handleClosingTag, handleData, handleEmptyTag, handleOpeningTag, parseNamedEntityInText, registerParseableDocumentPropertyprivate static final org.slf4j.Logger LOGGER
private static final boolean USE_DOCUMENT_IDS_FROM_FILE_DEFAULT
private boolean useDocumentIdsFromFile
private FileReader xmlFileReader
private SimpleReaderBasedXMLParser xmlParser
private org.dice_research.topicmodeling.utils.doc.Document document
private int documentCount
private int nextDocumentId
private StreamBasedXmlDocumentSupplier(FileReader reader, boolean useDocumentIdsFromFile)
public static StreamBasedXmlDocumentSupplier createReader(String filename) throws FileNotFoundException
FileNotFoundExceptionpublic static StreamBasedXmlDocumentSupplier createReader(String filename, boolean useDocumentIdsFromFile) throws FileNotFoundException
FileNotFoundExceptionpublic static StreamBasedXmlDocumentSupplier createReader(File file)
public static StreamBasedXmlDocumentSupplier createReader(File file, boolean useDocumentIdsFromFile)
public org.dice_research.topicmodeling.utils.doc.Document getNextDocument()
getNextDocument in interface org.dice_research.topicmodeling.preprocessing.docsupplier.DocumentSupplierpublic void setDocumentStartId(int documentStartId)
setDocumentStartId in interface org.dice_research.topicmodeling.preprocessing.docsupplier.DocumentSupplierprotected int getNextDocumentId()
protected void finishedDocument(org.dice_research.topicmodeling.utils.doc.Document document)
finishedDocument in class AbstractDocumentXmlReaderCopyright © 2015–2020. All rights reserved.