com.github.jlangch.venice.util.pdf

Class PdfLayoutTextStripper

java.lang.Object

org.apache.pdfbox.contentstream.PDFStreamEngine

org.apache.pdfbox.text.PDFTextStripper

com.github.jlangch.venice.util.pdf.PdfLayoutTextStripper

public class PdfLayoutTextStripper
extends org.apache.pdfbox.text.PDFTextStripper

Java doc to be completed

Field Summary

Fields

Modifier and Type	Field and Description
static boolean	DEBUG
static int	OUTPUT_SPACE_CHARACTER_WIDTH_IN_PT

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

charactersByArticle, document, LINE_SEPARATOR, output

Constructor Summary

Constructors

Constructor and Description
PdfLayoutTextStripper()

Method Summary

Modifier and Type	Method and Description
protected float	computeFontHeight(org.apache.pdfbox.pdmodel.font.PDFont arg0)
void	processPage(org.apache.pdfbox.pdmodel.PDPage page)
protected void	showGlyph(org.apache.pdfbox.util.Matrix arg0, org.apache.pdfbox.pdmodel.font.PDFont arg1, int arg2, org.apache.pdfbox.util.Vector arg3)
protected void	writePage()

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, 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, 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, operatorException, processAnnotation, processChildStream, processOperator, processOperator, processSoftMask, processTilingPattern, processTilingPattern, processTransparencyGroup, processType3Stream, restoreGraphicsStack, restoreGraphicsState, saveGraphicsStack, saveGraphicsState, setLineDashPattern, setTextLineMatrix, setTextMatrix, showAnnotation, showFontGlyph, showForm, showText, showTextString, showTextStrings, showTransparencyGroup, showType3Glyph, transformedPoint, transformWidth, unsupportedOperator

Methods inherited from class java.lang.Object

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

Field Detail

DEBUG

public static final boolean DEBUG

See Also:

Constant Field Values

OUTPUT_SPACE_CHARACTER_WIDTH_IN_PT

public static final int OUTPUT_SPACE_CHARACTER_WIDTH_IN_PT

See Also:

Constant Field Values

Constructor Detail

PdfLayoutTextStripper

public PdfLayoutTextStripper()
                      throws java.io.IOException

Throws:

java.io.IOException

Method Detail

processPage

public void processPage(org.apache.pdfbox.pdmodel.PDPage page)
                 throws java.io.IOException

Overrides:

processPage in class org.apache.pdfbox.text.PDFTextStripper

Throws:

java.io.IOException

writePage

protected void writePage()
                  throws java.io.IOException

Overrides:

writePage in class org.apache.pdfbox.text.PDFTextStripper

Throws:

java.io.IOException

showGlyph

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

Overrides:

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

Throws:

java.io.IOException

computeFontHeight

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

Throws:

java.io.IOException