public class TEIFormatter
extends java.lang.Object
Modifier and Type | Class and Description |
---|---|
static class |
TEIFormatter.SchemaDeclaration |
Modifier and Type | Field and Description |
---|---|
static java.util.Set<TaggingLabel> |
MARKER_LABELS |
Constructor and Description |
---|
TEIFormatter(Document document,
FullTextParser fullTextParser) |
Modifier and Type | Method and Description |
---|---|
static java.lang.String |
getCoordsAttribute(java.util.List<BoundingBox> boundingBoxes,
boolean generateCoordinates) |
java.util.List<Node> |
markReferencesEquationTEI(java.lang.String text,
java.util.List<LayoutToken> refTokens,
java.util.List<Equation> equations,
boolean generateCoordinates) |
java.util.List<Node> |
markReferencesFigureTEI(java.lang.String text,
java.util.List<LayoutToken> refTokens,
java.util.List<Figure> figures,
boolean generateCoordinates) |
java.util.List<Node> |
markReferencesTableTEI(java.lang.String text,
java.util.List<LayoutToken> refTokens,
java.util.List<Table> tables,
boolean generateCoordinates) |
java.util.List<Node> |
markReferencesTEILuceneBased(java.util.List<LayoutToken> refTokens,
ReferenceMarkerMatcher markerMatcher,
boolean generateCoordinates,
boolean keepUnsolvedCallout)
Mark using TEI annotations the identified references in the text body build with the machine learning model.
|
java.lang.StringBuilder |
toTEIAcknowledgement(java.lang.StringBuilder buffer,
java.lang.String reseAcknowledgement,
java.util.List<LayoutToken> tokenizationsAcknowledgement,
java.util.List<BibDataSet> bds,
GrobidAnalysisConfig config) |
java.lang.StringBuilder |
toTEIAnnex(java.lang.StringBuilder buffer,
java.lang.String result,
BiblioItem biblio,
java.util.List<BibDataSet> bds,
java.util.List<LayoutToken> tokenizations,
Document doc,
GrobidAnalysisConfig config) |
java.lang.StringBuilder |
toTEIBody(java.lang.StringBuilder buffer,
java.lang.String result,
BiblioItem biblio,
java.util.List<BibDataSet> bds,
LayoutTokenization layoutTokenization,
java.util.List<Figure> figures,
java.util.List<Table> tables,
java.util.List<Equation> equations,
Document doc,
GrobidAnalysisConfig config)
TEI formatting of the body where only basic logical document structures are present.
|
java.lang.StringBuilder |
toTEIHeader(BiblioItem biblio,
java.lang.String defaultPublicationStatement,
java.util.List<BibDataSet> bds,
GrobidAnalysisConfig config) |
java.lang.StringBuilder |
toTEIHeader(BiblioItem biblio,
TEIFormatter.SchemaDeclaration schemaDeclaration,
java.lang.String defaultPublicationStatement,
java.util.List<BibDataSet> bds,
GrobidAnalysisConfig config) |
java.lang.StringBuilder |
toTEIReferences(java.lang.StringBuilder tei,
java.util.List<BibDataSet> bds,
GrobidAnalysisConfig config) |
public static final java.util.Set<TaggingLabel> MARKER_LABELS
public TEIFormatter(Document document, FullTextParser fullTextParser)
public java.lang.StringBuilder toTEIHeader(BiblioItem biblio, java.lang.String defaultPublicationStatement, java.util.List<BibDataSet> bds, GrobidAnalysisConfig config)
public java.lang.StringBuilder toTEIHeader(BiblioItem biblio, TEIFormatter.SchemaDeclaration schemaDeclaration, java.lang.String defaultPublicationStatement, java.util.List<BibDataSet> bds, GrobidAnalysisConfig config)
public java.lang.StringBuilder toTEIBody(java.lang.StringBuilder buffer, java.lang.String result, BiblioItem biblio, java.util.List<BibDataSet> bds, LayoutTokenization layoutTokenization, java.util.List<Figure> figures, java.util.List<Table> tables, java.util.List<Equation> equations, Document doc, GrobidAnalysisConfig config) throws java.lang.Exception
java.lang.Exception
public java.lang.StringBuilder toTEIAcknowledgement(java.lang.StringBuilder buffer, java.lang.String reseAcknowledgement, java.util.List<LayoutToken> tokenizationsAcknowledgement, java.util.List<BibDataSet> bds, GrobidAnalysisConfig config) throws java.lang.Exception
java.lang.Exception
public java.lang.StringBuilder toTEIAnnex(java.lang.StringBuilder buffer, java.lang.String result, BiblioItem biblio, java.util.List<BibDataSet> bds, java.util.List<LayoutToken> tokenizations, Document doc, GrobidAnalysisConfig config) throws java.lang.Exception
java.lang.Exception
public java.lang.StringBuilder toTEIReferences(java.lang.StringBuilder tei, java.util.List<BibDataSet> bds, GrobidAnalysisConfig config) throws java.lang.Exception
java.lang.Exception
public static java.lang.String getCoordsAttribute(java.util.List<BoundingBox> boundingBoxes, boolean generateCoordinates)
public java.util.List<Node> markReferencesTEILuceneBased(java.util.List<LayoutToken> refTokens, ReferenceMarkerMatcher markerMatcher, boolean generateCoordinates, boolean keepUnsolvedCallout) throws EntityMatcherException
EntityMatcherException
public java.util.List<Node> markReferencesFigureTEI(java.lang.String text, java.util.List<LayoutToken> refTokens, java.util.List<Figure> figures, boolean generateCoordinates)
public java.util.List<Node> markReferencesTableTEI(java.lang.String text, java.util.List<LayoutToken> refTokens, java.util.List<Table> tables, boolean generateCoordinates)
public java.util.List<Node> markReferencesEquationTEI(java.lang.String text, java.util.List<LayoutToken> refTokens, java.util.List<Equation> equations, boolean generateCoordinates)