Package org.apache.tika.parser.pdf.image

Class ImageGraphicsEngine

java.lang.Object

org.apache.pdfbox.contentstream.PDFStreamEngine

org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

org.apache.tika.parser.pdf.image.ImageGraphicsEngine

public class ImageGraphicsEngine
extends org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Copied nearly verbatim from PDFBox

Field Summary

Fields

Modifier and Type	Field	Description
protected org.apache.tika.extractor.EmbeddedDocumentExtractor	embeddedDocumentExtractor
protected boolean	extractInlineImageMetadataOnly
protected AtomicInteger	imageCounter
protected static List<String>	JB2
protected static List<String>	JP2
protected static List<String>	JPEG
protected static long	MAX_IMAGE_LENGTH_BYTES
protected int	pageNumber
protected org.apache.tika.metadata.Metadata	parentMetadata
protected org.apache.tika.parser.ParseContext	parseContext
protected PDFParserConfig	pdfParserConfig
protected Map<org.apache.pdfbox.cos.COSStream,Integer>	processedInlineImages
protected boolean	useDirectJPEG
protected org.apache.tika.sax.XHTMLContentHandler	xhtml

Constructor Summary

Constructors

Modifier	Constructor	Description
protected	ImageGraphicsEngine(org.apache.pdfbox.pdmodel.PDPage page, int pageNumber, org.apache.tika.extractor.EmbeddedDocumentExtractor embeddedDocumentExtractor, PDFParserConfig pdfParserConfig, Map<org.apache.pdfbox.cos.COSStream,Integer> processedInlineImages, AtomicInteger imageCounter, org.apache.tika.sax.XHTMLContentHandler xhtml, org.apache.tika.metadata.Metadata parentMetadata, org.apache.tika.parser.ParseContext parseContext)

Method Summary

Modifier and Type	Method	Description
void	appendRectangle(Point2D p0, Point2D p1, Point2D p2, Point2D p3)
void	clip(int windingRule)
void	closePath()
protected static void	copyUpToMaxLength(InputStream is, OutputStream os)
void	curveTo(float x1, float y1, float x2, float y2, float x3, float y3)
void	drawImage(org.apache.pdfbox.pdmodel.graphics.image.PDImage pdImage)
void	endPath()
protected void	extractInlineImageMetadataOnly(org.apache.pdfbox.pdmodel.graphics.image.PDImage pdImage, org.apache.tika.metadata.Metadata metadata)
void	fillAndStrokePath(int windingRule)
void	fillPath(int windingRule)
Point2D	getCurrentPoint()
List<IOException>	getExceptions()
protected String	getSuffix(org.apache.pdfbox.pdmodel.graphics.image.PDImage pdImage, org.apache.tika.metadata.Metadata metadata)
protected void	handleCatchableIOE(IOException e)
protected static boolean	hasMasks(org.apache.pdfbox.pdmodel.graphics.image.PDImage pdImage)
void	lineTo(float x, float y)
void	moveTo(float x, float y)
protected void	processImage(org.apache.pdfbox.pdmodel.graphics.image.PDImage pdImage, int imageNumber)
void	run()
void	shadingFill(org.apache.pdfbox.cos.COSName shadingName)
protected void	showGlyph(org.apache.pdfbox.util.Matrix textRenderingMatrix, org.apache.pdfbox.pdmodel.font.PDFont font, int code, org.apache.pdfbox.util.Vector displacement)
void	strokePath()
protected BufferedImage	writeToBuffer(org.apache.pdfbox.pdmodel.graphics.image.PDImage pdImage, String suffix, boolean directJPEG, OutputStream out)

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

getPage

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, processPage, 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

Field Detail

MAX_IMAGE_LENGTH_BYTES

protected static final long MAX_IMAGE_LENGTH_BYTES

See Also:

Constant Field Values

JPEG

protected static final List<String> JPEG

JP2

protected static final List<String> JP2

JB2

protected static final List<String> JB2

pageNumber

protected final int pageNumber

embeddedDocumentExtractor

protected final org.apache.tika.extractor.EmbeddedDocumentExtractor embeddedDocumentExtractor

pdfParserConfig

protected final PDFParserConfig pdfParserConfig

processedInlineImages

protected final Map<org.apache.pdfbox.cos.COSStream,Integer> processedInlineImages

imageCounter

protected final AtomicInteger imageCounter

parentMetadata

protected final org.apache.tika.metadata.Metadata parentMetadata

xhtml

protected final org.apache.tika.sax.XHTMLContentHandler xhtml

parseContext

protected final org.apache.tika.parser.ParseContext parseContext

extractInlineImageMetadataOnly

protected final boolean extractInlineImageMetadataOnly

useDirectJPEG

protected boolean useDirectJPEG

Constructor Detail

ImageGraphicsEngine

protected ImageGraphicsEngine(org.apache.pdfbox.pdmodel.PDPage page,
                              int pageNumber,
                              org.apache.tika.extractor.EmbeddedDocumentExtractor embeddedDocumentExtractor,
                              PDFParserConfig pdfParserConfig,
                              Map<org.apache.pdfbox.cos.COSStream,Integer> processedInlineImages,
                              AtomicInteger imageCounter,
                              org.apache.tika.sax.XHTMLContentHandler xhtml,
                              org.apache.tika.metadata.Metadata parentMetadata,
                              org.apache.tika.parser.ParseContext parseContext)

Method Detail

writeToBuffer

protected BufferedImage writeToBuffer(org.apache.pdfbox.pdmodel.graphics.image.PDImage pdImage,
                                      String suffix,
                                      boolean directJPEG,
                                      OutputStream out)
                               throws IOException,
                                      org.apache.tika.exception.TikaException

Throws:

IOException

org.apache.tika.exception.TikaException

copyUpToMaxLength

protected static void copyUpToMaxLength(InputStream is,
                                        OutputStream os)
                                 throws IOException,
                                        org.apache.tika.exception.TikaException

Throws:

IOException

org.apache.tika.exception.TikaException

hasMasks

protected static boolean hasMasks(org.apache.pdfbox.pdmodel.graphics.image.PDImage pdImage)
                           throws IOException

Throws:

IOException

run

public void run()
         throws IOException

Throws:

IOException

drawImage

public void drawImage(org.apache.pdfbox.pdmodel.graphics.image.PDImage pdImage)
               throws IOException

Specified by:

drawImage in class org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Throws:

IOException

appendRectangle

public void appendRectangle(Point2D p0,
                            Point2D p1,
                            Point2D p2,
                            Point2D p3)
                     throws IOException

Specified by:

appendRectangle in class org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Throws:

IOException

clip

public void clip(int windingRule)
          throws IOException

Specified by:

clip in class org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Throws:

IOException

moveTo

public void moveTo(float x,
                   float y)
            throws IOException

Specified by:

moveTo in class org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Throws:

IOException

lineTo

public void lineTo(float x,
                   float y)
            throws IOException

Specified by:

lineTo in class org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Throws:

IOException

curveTo

public void curveTo(float x1,
                    float y1,
                    float x2,
                    float y2,
                    float x3,
                    float y3)
             throws IOException

Specified by:

curveTo in class org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Throws:

IOException

getCurrentPoint

public Point2D getCurrentPoint()
                        throws IOException

Specified by:

getCurrentPoint in class org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Throws:

IOException

closePath

public void closePath()
               throws IOException

Specified by:

closePath in class org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Throws:

IOException

endPath

public void endPath()
             throws IOException

Specified by:

endPath in class org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Throws:

IOException

showGlyph

protected void showGlyph(org.apache.pdfbox.util.Matrix textRenderingMatrix,
                         org.apache.pdfbox.pdmodel.font.PDFont font,
                         int code,
                         org.apache.pdfbox.util.Vector displacement)
                  throws IOException

Overrides:

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

Throws:

IOException

strokePath

public void strokePath()
                throws IOException

Specified by:

strokePath in class org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Throws:

IOException

fillPath

public void fillPath(int windingRule)
              throws IOException

Specified by:

fillPath in class org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Throws:

IOException

fillAndStrokePath

public void fillAndStrokePath(int windingRule)
                       throws IOException

Specified by:

fillAndStrokePath in class org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Throws:

IOException

shadingFill

public void shadingFill(org.apache.pdfbox.cos.COSName shadingName)
                 throws IOException

Specified by:

shadingFill in class org.apache.pdfbox.contentstream.PDFGraphicsStreamEngine

Throws:

IOException

processImage

protected void processImage(org.apache.pdfbox.pdmodel.graphics.image.PDImage pdImage,
                            int imageNumber)
                     throws IOException,
                            org.apache.tika.exception.TikaException,
                            SAXException

Throws:

IOException

org.apache.tika.exception.TikaException

SAXException

extractInlineImageMetadataOnly

protected void extractInlineImageMetadataOnly(org.apache.pdfbox.pdmodel.graphics.image.PDImage pdImage,
                                              org.apache.tika.metadata.Metadata metadata)
                                       throws IOException,
                                              SAXException

Throws:

IOException

SAXException

getSuffix

protected String getSuffix(org.apache.pdfbox.pdmodel.graphics.image.PDImage pdImage,
                           org.apache.tika.metadata.Metadata metadata)
                    throws IOException

Throws:

IOException

handleCatchableIOE

protected void handleCatchableIOE(IOException e)
                           throws IOException

Throws:

IOException

getExceptions

public List<IOException> getExceptions()