void |
Document.cleanUp() |
Call this method only WHEN YOU ARE SURE YOU WILL NOT USE THE DOCUMENT NO MORE IN YOUR DATA.
|
void |
DocumentImpl.cleanUp() |
|
List<Citation> |
Document.extractCitations() |
Get the list of citations extracted from the document.
|
List<Citation> |
DocumentImpl.extractCitations() |
|
Header |
Document.extractHeader() |
Extract the information retrieved by parsing the header of the paper
|
Header |
DocumentImpl.extractHeader() |
|
List<Section> |
Document.extractSections(Boolean onlyRoot) |
Get the sections (or a subset of the sections) of the document
|
List<Section> |
DocumentImpl.extractSections(Boolean onlyRoot) |
|
Sentence |
Document.extractSentenceById(int sentenceId) |
Get one of the sentences of the document by id
|
Sentence |
DocumentImpl.extractSentenceById(int sentenceId) |
|
List<Sentence> |
Document.extractSentences(SentenceSelectorENUM sentenceSel) |
Load the list of sentences of the document, ordered by their occurrence in the document.
|
List<Sentence> |
DocumentImpl.extractSentences(SentenceSelectorENUM sentenceSel) |
|
List<Sentence> |
Document.extractSummary(int sentNumber,
SummaryTypeENUM summaryType) |
Generate a summary of the paper by selecting a relevant set of sentences.
|
List<Sentence> |
DocumentImpl.extractSummary(int sentNumber,
SummaryTypeENUM summaryType) |
|
String |
Document.getName() |
Get the name of the document
|
String |
DocumentImpl.getName() |
|
String |
Document.getRawText() |
Get the raw text of the document (UTF-8 encoded)
|
String |
DocumentImpl.getRawText() |
|
SourceENUM |
Document.getSourceDocumentType() |
Get the original document type from which the Document instance has been created.
|
SourceENUM |
DocumentImpl.getSourceDocumentType() |
|
Document |
Document.getXMLDocument() |
Get the contents of the document as an instance of org.w3c.dom.Document
|
Document |
DocumentImpl.getXMLDocument() |
|
String |
Document.getXMLString() |
Get the XML string-serialized contents of the document, as a string (UTF-8 char encoding)
|
String |
DocumentImpl.getXMLString() |
|
boolean |
Document.isCleanUp() |
Check if the document data structures has been cleaned by calling the cleanUp() method.
|
boolean |
DocumentImpl.isCleanUp() |
|
void |
DocumentImpl.parsingBabelNet(boolean force) |
|
void |
DocumentImpl.parsingCausality(boolean force) |
|
void |
DocumentImpl.parsingCitations_Enrich(boolean force) |
|
void |
DocumentImpl.parsingCitations_Link(boolean force) |
|
void |
DocumentImpl.parsingCitations_Spot(boolean force) |
|
void |
DocumentImpl.parsingCoref(boolean force) |
|
void |
DocumentImpl.parsingDep(boolean force) |
|
void |
DocumentImpl.parsingHeader(boolean force) |
|
void |
DocumentImpl.parsingMetaAnnotations(boolean force) |
|
void |
DocumentImpl.parsingRhetoricalClass(boolean force) |
|
void |
DocumentImpl.parsingSentences(boolean force) |
|
void |
DocumentImpl.parsingSummary(boolean force) |
|
void |
DocumentImpl.parsingTerminology(boolean force) |
|
void |
Document.preprocess() |
Pre-compute the text analysis of the document in order to speed-up the execution of
the extract-methods.
|
void |
DocumentImpl.preprocess() |
|
void |
DocumentImpl.resetBabelNet() |
|
void |
DocumentImpl.resetCausality() |
|
void |
DocumentImpl.resetCitations_Enrich() |
|
void |
DocumentImpl.resetCitations_Link() |
|
void |
DocumentImpl.resetCitations_Spot() |
|
void |
DocumentImpl.resetCoref() |
|
void |
DocumentImpl.resetDep() |
|
void |
Document.resetDocumentExtractionData() |
This method deletes all the data extracted from the original document including sentences, terminology, citations, etc.
|
void |
DocumentImpl.resetDocumentExtractionData() |
|
void |
DocumentImpl.resetHeader() |
|
void |
DocumentImpl.resetMetaAnnotations() |
|
void |
DocumentImpl.resetRhetoricalClass() |
|
void |
DocumentImpl.resetSummary() |
|
void |
DocumentImpl.resetTerminology() |
|