org.nuxeo.ecm.core.convert.plugins.text.extractors

Class PDF2TextConverter.PatchedPDFTextStripper

java.lang.Object

org.apache.pdfbox.util.PDFStreamEngine

org.apache.pdfbox.util.PDFTextStripper

org.nuxeo.ecm.core.convert.plugins.text.extractors.PDF2TextConverter.PatchedPDFTextStripper

Enclosing class:

PDF2TextConverter

public static class PDF2TextConverter.PatchedPDFTextStripper
extends org.apache.pdfbox.util.PDFTextStripper

Field Summary

Fields inherited from class org.apache.pdfbox.util.PDFTextStripper

charactersByArticle, document, output, outputEncoding, systemLineSeparator

Constructor Summary

Constructors

Constructor and Description
PatchedPDFTextStripper()

Method Summary

Modifier and Type	Method and Description
protected Map<String,org.apache.pdfbox.util.operator.OperatorProcessor>	operators()
protected void	processOperator(org.apache.pdfbox.util.PDFOperator operator, List<org.apache.pdfbox.cos.COSBase> arguments)
protected Object	unrestrictedAccess(String name)
protected Set<String>	unsupportedOperators()

Methods inherited from class org.apache.pdfbox.util.PDFTextStripper

endArticle, endDocument, endPage, getAddMoreFormatting, getArticleEnd, getArticleStart, getAverageCharTolerance, getCharactersByArticle, getCurrentPageNo, getDropThreshold, getEndBookmark, getEndPage, getIndentThreshold, getLineSeparator, getListItemPatterns, getOutput, getPageEnd, getPageSeparator, getPageStart, getParagraphEnd, getParagraphStart, getSeparateByBeads, getSortByPosition, getSpacingTolerance, getStartBookmark, getStartPage, getSuppressDuplicateOverlappingText, getText, getText, getWordSeparator, handleLineSeparation, inspectFontEncoding, isParagraphSeparation, matchListItemPattern, matchPattern, processPage, processPages, processTextPosition, resetEngine, setAddMoreFormatting, setArticleEnd, setArticleStart, setAverageCharTolerance, setDropThreshold, setEndBookmark, setEndPage, setIndentThreshold, setLineSeparator, setListItemPatterns, setPageEnd, setPageSeparator, setPageStart, setParagraphEnd, setParagraphStart, setShouldSeparateByBeads, setSortByPosition, setSpacingTolerance, setStartBookmark, setStartPage, setSuppressDuplicateOverlappingText, setWordSeparator, startArticle, startArticle, startDocument, startPage, writeCharacters, writeLineSeparator, writePage, writePageEnd, writePageSeperator, writePageStart, writeParagraphEnd, writeParagraphSeparator, writeParagraphStart, writeString, writeString, writeText, writeText, writeWordSeparator

Methods inherited from class org.apache.pdfbox.util.PDFStreamEngine

getColorSpaces, getCurrentPage, getFonts, getGraphicsStack, getGraphicsState, getGraphicsStates, getResources, getTextLineMatrix, getTextMatrix, getTotalCharCnt, getValidCharCnt, getXObjects, isForceParsing, processEncodedText, processOperator, processStream, processSubStream, registerOperatorProcessor, setColorSpaces, setFonts, setForceParsing, setGraphicsStack, setGraphicsState, setGraphicsStates, setTextLineMatrix, setTextMatrix

Methods inherited from class java.lang.Object

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

Constructor Detail

PatchedPDFTextStripper

public PatchedPDFTextStripper()
                       throws IOException

Throws:

IOException

Method Detail

unrestrictedAccess

protected Object unrestrictedAccess(String name)

unsupportedOperators

protected Set<String> unsupportedOperators()

operators

protected Map<String,org.apache.pdfbox.util.operator.OperatorProcessor> operators()

processOperator

protected void processOperator(org.apache.pdfbox.util.PDFOperator operator,
                               List<org.apache.pdfbox.cos.COSBase> arguments)
                        throws IOException

Overrides:

processOperator in class org.apache.pdfbox.util.PDFStreamEngine

Throws:

IOException