Top Description Fields Constructors Methods

org.jabref.logic.search.sqlbased.indexing

public final Class DocumentReader

Class Inheritance

extends Object

java.lang.Object
org.jabref.logic.search.sqlbased.indexing.DocumentReader

Imports

java.io.IOException, java.nio.file.Files, .Path, java.util.ArrayList, .List, .Objects, java.util.concurrent.TimeUnit, java.util.regex.Pattern, org.jabref.logic.util.strings.StringUtil, org.apache.lucene.document.Document, org.apache.lucene.document.Field, org.apache.lucene.document.StringField, org.apache.lucene.document.TextField, org.apache.pdfbox.Loader, org.apache.pdfbox.pdmodel.PDDocument, .PDPage, org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotation, org.apache.pdfbox.text.PDFTextStripper, org.slf4j.Logger, .LoggerFactory, .MDC

Utility class for reading the data from LinkedFiles of a BibEntry for Lucene.

Field Summary

Modifier and Type	Field and Description
private static final Pattern	HYPHEN_LINEBREAK_PATTERN
private static final Pattern	LINEBREAK_WITHOUT_PERIOD_PATTERN
private static final Logger	LOGGER

Constructor Summary

Access	Constructor and Description
public	DocumentReader()

Method Summary

Modifier and Type	Method and Description
private void	addContentIfNotEmpty(PDDocument pdfDocument, org.apache.lucene.document.Document newDocument, Path resolvedPath, int pageNumber)
private void	addIdentifiers(org.apache.lucene.document.Document newDocument, String path)
private void	addMetaData(org.apache.lucene.document.Document newDocument, Path resolvedPdfPath, int pageNumber)
private void	addStringField(org.apache.lucene.document.Document newDocument, String field, String value)
private boolean	isValidField(String value)
public static String	mergeLines(String text)
public List<org.apache.lucene.document.Document>	readPdfContents(String fileLink, Path resolvedPdfPath)

Inherited from java.lang.Object:: clone equals finalize getClass hashCode notify notifyAll toString wait wait wait

Field Detail

HYPHEN_LINEBREAK_PATTERN	back to summary
private static final Pattern HYPHEN_LINEBREAK_PATTERN

LINEBREAK_WITHOUT_PERIOD_PATTERN	back to summary
private static final Pattern LINEBREAK_WITHOUT_PERIOD_PATTERN

LOGGER	back to summary
private static final Logger LOGGER

Constructor Detail

DocumentReader	back to summary
public DocumentReader()

Method Detail

addContentIfNotEmpty	back to summary
private void addContentIfNotEmpty(PDDocument pdfDocument, org.apache.lucene.document.Document newDocument, Path resolvedPath, int pageNumber)

addIdentifiers	back to summary
private void addIdentifiers(org.apache.lucene.document.Document newDocument, String path)

addMetaData	back to summary
private void addMetaData(org.apache.lucene.document.Document newDocument, Path resolvedPdfPath, int pageNumber)

addStringField	back to summary
private void addStringField(org.apache.lucene.document.Document newDocument, String field, String value)

isValidField	back to summary
private boolean isValidField(String value)

mergeLines	back to summary
public static String mergeLines(String text)

readPdfContents	back to summary
public List<org.apache.lucene.document.Document> readPdfContents(String fileLink, Path resolvedPdfPath)