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

Class PDF2TextConverter.PatchedPDFTextStripper

java.lang.Object

org.apache.pdfbox.contentstream.PDFStreamEngine

org.apache.pdfbox.text.PDFTextStripper

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

Enclosing class:

PDF2TextConverter

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

Field Summary

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

charactersByArticle, document, LINE_SEPARATOR, output

Constructor Summary

Constructors

Constructor	Description
PatchedPDFTextStripper()

Method Summary

Modifier and Type	Method	Description
protected float	computeFontHeight(org.apache.pdfbox.pdmodel.font.PDFont arg0)
protected void	operatorException(org.apache.pdfbox.contentstream.operator.Operator operator, List<org.apache.pdfbox.cos.COSBase> operands, IOException e)
protected void	showGlyph(org.apache.pdfbox.util.Matrix arg0, org.apache.pdfbox.pdmodel.font.PDFont arg1, int arg2, String arg3, org.apache.pdfbox.util.Vector arg4)

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

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

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

addOperator, applyTextAdjustment, beginMarkedContentSequence, beginText, decreaseLevel, endMarkedContentSequence, endText, getAppearance, getCurrentPage, getGraphicsStackSize, getGraphicsState, getInitialMatrix, getLevel, getResources, getTextLineMatrix, getTextMatrix, increaseLevel, processAnnotation, processChildStream, processOperator, processOperator, processSoftMask, processTilingPattern, processTilingPattern, processTransparencyGroup, processType3Stream, registerOperatorProcessor, restoreGraphicsStack, restoreGraphicsState, saveGraphicsStack, saveGraphicsState, setLineDashPattern, setTextLineMatrix, setTextMatrix, showAnnotation, showFontGlyph, showFontGlyph, showForm, showGlyph, showText, showTextString, showTextStrings, showTransparencyGroup, showType3Glyph, showType3Glyph, transformedPoint, transformWidth, unsupportedOperator

Methods inherited from class java.lang.Object

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

Constructor Details

PatchedPDFTextStripper

public PatchedPDFTextStripper()
                       throws IOException

Throws:

IOException

Method Details

operatorException

protected void operatorException(org.apache.pdfbox.contentstream.operator.Operator operator,
 List<org.apache.pdfbox.cos.COSBase> operands,
 IOException e)
                          throws IOException

Overrides:

operatorException in class org.apache.pdfbox.contentstream.PDFStreamEngine

Throws:

IOException

showGlyph

protected void showGlyph(org.apache.pdfbox.util.Matrix arg0,
 org.apache.pdfbox.pdmodel.font.PDFont arg1,
 int arg2,
 String arg3,
 org.apache.pdfbox.util.Vector arg4)
                  throws IOException

Overrides:

showGlyph in class org.apache.pdfbox.contentstream.PDFStreamEngine

Throws:

IOException

computeFontHeight

protected float computeFontHeight(org.apache.pdfbox.pdmodel.font.PDFont arg0)
                           throws IOException

Throws:

IOException