Java Code Examples for org.apache.pdfbox.text.PDFTextStripper#setSortByPosition()

public static void main(String[] args) throws IOException {
	PDDocument document = null;
	try {
		document = PDDocument.load(new File("/home/lili/data/test.pdf"));

		PDFTextStripper stripper = new PrintTextLocations();
		stripper.setSortByPosition(true);
		stripper.setStartPage(0);
		stripper.setEndPage(document.getNumberOfPages());

		Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
		stripper.writeText(document, dummy);
	} finally {
		if (document != null) {
			document.close();
		}
	}
}
 

/**
 * @throws IOException If there is an error parsing the document.
 */
public static void main( String[] args ) throws IOException {
    PDDocument document = null;
    String fileName = "/home/lili/data/test.pdf";
    try {
        document = PDDocument.load( new File(fileName) );
        PDFTextStripper stripper = new GetLinesFromPDF();
        stripper.setSortByPosition( true );
        stripper.setStartPage( 0 );
        stripper.setEndPage( document.getNumberOfPages() );
        Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
        stripper.writeText(document, dummy);
        
        // print lines
        for(String line:lines){
            System.out.println(line); 
        }
    }
    finally {
        if( document != null ) {
            document.close();
        }
    }
}
 

/**
     * <a href="https://stackoverflow.com/questions/53773479/java-rotated-file-extraction">
     * java- rotated file extraction?
     * </a>
     * <br/>
     * <a href="https://www.dropbox.com/s/g1pe8zb9m5kajif/lol.pdf?dl=0">
     * lol.pdf
     * </a>
     * <p>
     * Indeed, regular text extraction results on many lines, essentially
     * one for each text chunk. One can improve this in two ways, either
     * one activates sorting or one removes the Rotate entries from the
     * page dictionaries.
     * </p>
     */
    @Test
    public void testLol() throws IOException
    {
        try (   InputStream resource = getClass().getResourceAsStream("lol.pdf")    )
        {
            PDDocument document = Loader.loadPDF(resource);
// Option 1: Remove Rotate entries
//            for (PDPage page : document.getPages()) {
//                page.setRotation(0);
//            }

            PDFTextStripper stripper = new PDFTextStripper();
// Option 2: Sort by position
            stripper.setSortByPosition(true);
            String text = stripper.getText(document);

            System.out.printf("\n*\n* lol.pdf\n*\n%s\n", text);
            Files.write(new File(RESULT_FOLDER, "lol.txt").toPath(), Collections.singleton(text));
        }
    }
 

List<TextPositionSequence> findSubwords(PDDocument document, int page, String searchTerm) throws IOException
{
    final List<TextPositionSequence> hits = new ArrayList<TextPositionSequence>();
    PDFTextStripper stripper = new PDFTextStripper()
    {
        @Override
        protected void writeString(String text, List<TextPosition> textPositions) throws IOException
        {
            System.out.printf("  -- %s\n", text);

            TextPositionSequence word = new TextPositionSequence(textPositions);
            String string = word.toString();

            int fromIndex = 0;
            int index;
            while ((index = string.indexOf(searchTerm, fromIndex)) > -1)
            {
                hits.add(word.subSequence(index, index + searchTerm.length()));
                fromIndex = index + 1;
            }
            super.writeString(text, textPositions);
        }
    };
    
    stripper.setSortByPosition(true);
    stripper.setStartPage(page);
    stripper.setEndPage(page);
    stripper.getText(document);
    return hits;
}
 

/**
 * <a href="https://stackoverflow.com/questions/50330484/could-someone-give-me-an-example-of-how-to-extract-coordinates-for-a-word-usin">
 * Could someone give me an example of how to extract coordinates for a 'word' using PDFBox
 * </a>
 * <br/>
 * <a href="https://www.tutorialkart.com/pdfbox/how-to-get-location-and-size-of-images-in-pdf/attachment/apache-pdf/">
 * apache.pdf
 * </a>
 * <p>
 * This test shows how to extract word coordinates combining the ideas of
 * the two tutorials referenced by the OP.
 * </p>
 */
@Test
public void testExtractWordsForGoodJuJu() throws IOException {
    try (   InputStream resource = getClass().getResourceAsStream("apache.pdf")) {
        PDDocument document = Loader.loadPDF(resource);
        PDFTextStripper stripper = new GetWordLocationAndSize();
        stripper.setSortByPosition( true );
        stripper.setStartPage( 0 );
        stripper.setEndPage( document.getNumberOfPages() );
 
        Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
        stripper.writeText(document, dummy);
    }
}
 

/**
     * <a href="https://stackoverflow.com/questions/54822124/pdftextstripperbyarea-and-pdftextstripper-parsing-different-text-output-for-tabl">
     * PDFTextStripperByArea and PDFTextStripper parsing different Text Output for Table with Merged Cell or Table cell with multi-line text content
     * </a>
     * <br/>
     * <a href="https://www4.esc13.net/uploads/webccat/docs/PDFTables_12142005.pdf">
     * PDFTables_12142005.pdf
     * </a>
     * <p>
     * Cannot reproduce the problem, and the OP does not react to clarification requests.
     * </p>
     */
    @Test
    public void testPDFTables_12142005() throws IOException {
        try (   InputStream resource = getClass().getResourceAsStream("PDFTables_12142005.pdf")    )
        {
            PDDocument document =  Loader.loadPDF(resource);

            PDFTextStripper textStripper = new PDFTextStripper();
            textStripper.setSortByPosition(true);
            textStripper.setAddMoreFormatting(false);
            // textStripper.setSpacingTolerance(1.5F);
            //textStripper.setAverageCharTolerance(averageCharToleranceValue);

            textStripper.setStartPage(2);
            textStripper.setEndPage(2);

            textStripper.getCurrentPage();
            String text = textStripper.getText(document).trim();
            System.out.println("PDF text is: " + "\n" + text.trim());

            System.out.println("----------------------------------------------------------------");

            PDFTextStripperByArea stripper = new PDFTextStripperByArea();
            stripper.setSortByPosition(true);
            stripper.setAddMoreFormatting(false);
            // stripper.setSpacingTolerance(1.5F);

            Dimension dimension = new Dimension();
            dimension.setSize(document.getPage(1).getMediaBox().getWidth(),
                    document.getPage(1).getMediaBox().getHeight());
//            Rectangle2D rect = toJavaRect(document.getBleedBox(), dimension);
//            Rectangle2D rect1 = toJavaRect(document.getArtBox(), dimension);
            PDRectangle mediaBox = document.getPage(1).getMediaBox();
            Rectangle2D rect = new Rectangle2D.Float(mediaBox.getLowerLeftX(), mediaBox.getLowerLeftY(), mediaBox.getWidth(), mediaBox.getHeight());
            Rectangle2D rect1 = rect;

            /*
             * Rectangle2D rect = new
             * Rectangle2D.Float(document.getBleedBox().getLowerLeftX(),
             * document.getBleedBox().getLowerLeftY(), document.getBleedBox().getWidth(),
             * document.getBleedBox().getHeight());
             */

            /*
             * Rectangle2D rect1 = new
             * Rectangle2D.Float(document.getArtBox().getLowerLeftX(),
             * document.getArtBox().getLowerLeftY(), document.getArtBox().getWidth(),
             * document.getArtBox().getHeight());
             */

            /*
             * Rectangle2D rect = new
             * Rectangle2D.Float(document.getBleedBox().getLowerLeftX(),
             * document.getBleedBox().getUpperRightY(), document.getBleedBox().getWidth(),
             * document.getBleedBox().getHeight());
             */

            System.out.println("Rectangle bleedBox Content : " + "\n" + rect);
            System.out.println("----------------------------------------------------------------");
            System.out.println("Rectangle artBox Content : " + "\n" + rect1);
            System.out.println("----------------------------------------------------------------");
            stripper.addRegion("Test1", rect);
            stripper.addRegion("Test2", rect1);
            stripper.extractRegions(document.getPage(1));

            System.out.println("Text in the area-BleedBox : " + "\n" + stripper.getTextForRegion("Test1").trim());
            System.out.println("----------------------------------------------------------------");
            System.out.println("Text in the area1-ArtBox : " + "\n" + stripper.getTextForRegion("Test2").trim());
            System.out.println("----------------------------------------------------------------");

            StringBuilder artPlusBleedBox = new StringBuilder();
            artPlusBleedBox.append(stripper.getTextForRegion("Test2").trim());
            artPlusBleedBox.append("\r\n");
            artPlusBleedBox.append(stripper.getTextForRegion("Test1").trim());

            System.out.println("Whole Page Text : " + artPlusBleedBox);
            System.out.println("----------------------------------------------------------------");
            text = new String(text.trim().getBytes(), "UTF-8");
            String text2 = new String(artPlusBleedBox.toString().trim().getBytes(), "UTF-8");
            System.out.println(" Matches equals with Both Content : " + text.equals(artPlusBleedBox.toString()));
            System.out.println(" String Matches equals with Both Content : " + text.equalsIgnoreCase(text2));
        }
    }
 

/**
 * <a href="https://stackoverflow.com/questions/47908124/pdfbox-removing-invisible-text-by-clip-filling-paths-issue">
 * PDFBox - Removing invisible text (by clip/filling paths issue)
 * </a>
 * <br/>
 * <a href="https://drive.google.com/open?id=1xcZOusx3cEdZX4AT8QAVDqZe33YWla0H">
 * test.pdf
 * </a> as testDmitryK.pdf
 * <p>
 * Indeed, using the original {@link PDFVisibleTextStripper} implementation
 * a lot of visible characters where dropped. This was due to the incorrect
 * calculation of the <code>end</code> of the character baseline in the methods
 * {@link PDFVisibleTextStripper#processTextPosition(org.apache.pdfbox.text.TextPosition)}
 * and {@link PDFVisibleTextStripper#deleteCharsInPath()}.
 * </p>
 * <p>
 * After patching those {@link PDFVisibleTextStripper} methods to make use of
 * <code>end</code> only optionally, running the test with that option results
 * in a decent extraction of visible text.
 * </p>
 */
@Test
public void testTestDmitryK() throws IOException {
    try (   InputStream resource = getClass().getResourceAsStream("testDmitryK.pdf")  ) {
        PDDocument document = Loader.loadPDF(resource);
        PDFTextStripper stripper = new PDFVisibleTextStripper();
        stripper.setSortByPosition(true);
        String text = stripper.getText(document);

        System.out.printf("\n*\n* testDmitryK.pdf\n*\n%s\n", text);
        Files.write(new File(RESULT_FOLDER, "testDmitryK.txt").toPath(), Collections.singleton(text));
    }
}
 

/**
 * <a href="https://stackoverflow.com/questions/47908124/pdfbox-removing-invisible-text-by-clip-filling-paths-issue">
 * PDFBox - Removing invisible text (by clip/filling paths issue)
 * </a>
 * <br/>
 * <a href="https://drive.google.com/open?id=1l0Yt9BJXs09bXcBD7pDbxFiZQQqnuaan">
 * test2.pdf
 * </a> as test2DmitryK.pdf
 * <p>
 * Indeed, even the {@link PDFVisibleTextStripper} implementation as originally
 * improved for {@link #testTestDmitryK()} failed for this document. The cause
 * is another normalization by PDFBox text stripping moving the origin into the
 * lower left corner of the crop box.
 * </p>
 * <p>
 * Patching the {@link PDFVisibleTextStripper} methods to add the lower left
 * crop box coordinate values again results in a decent extraction of visible
 * text.
 * </p>
 */
@Test
public void testTest2DmitryK() throws IOException {
    try (   InputStream resource = getClass().getResourceAsStream("test2DmitryK.pdf")  ) {
        PDDocument document = Loader.loadPDF(resource);
        PDFTextStripper stripper = new PDFVisibleTextStripper();
        stripper.setSortByPosition(true);
        String text = stripper.getText(document);

        System.out.printf("\n*\n* test2DmitryK.pdf\n*\n%s\n", text);
        Files.write(new File(RESULT_FOLDER, "test2DmitryK.txt").toPath(), Collections.singleton(text));
    }
}
 

/**
 * <a href="https://github.com/mkl-public/testarea-pdfbox2/issues/3">
 * One case fails to remove invisible texts or symbols
 * </a>
 * <br/>
 * <a href="https://github.com/mkl-public/testarea-pdfbox2/files/2481423/00000000000005fw6q.pdf">
 * 00000000000005fw6q.pdf
 * </a>
 * <p>
 * The "hidden text" recognized by Adobe here is only "hidden"
 * because it uses a glyph (page 1, Font F9, code 0000) for which
 * the embedded font draws nothing but which ToUnicode maps to
 * U+DBD0, a High Private Use Surrogate which by itself in general
 * makes no sense.
 * </p>
 */
@Test
public void test00000000000005fw6q() throws IOException {
    try (   InputStream resource = getClass().getResourceAsStream("00000000000005fw6q.pdf")  ) {
        PDDocument document = Loader.loadPDF(resource);
        PDFTextStripper stripper = new PDFVisibleTextStripper();
        stripper.setSortByPosition(true);
        String text = stripper.getText(document);

        System.out.printf("\n*\n* 00000000000005fw6q.pdf\n*\n%s\n", text);
        Files.write(new File(RESULT_FOLDER, "00000000000005fw6q.txt").toPath(), Collections.singleton(text));
    }
}
 

/**
 * <a href="https://stackoverflow.com/questions/59920280/pdfbox-2-0-invisible-lines-on-rotated-page-clip-path-issue">
 * PDFBox 2.0: invisible lines on rotated page - clip path issue
 * </a>
 * <br/>
 * <a href="https://drive.google.com/open?id=1Ex03HhDz17xQlsiTIY1cxaT_cb3nyTf3">
 * 1.pdf
 * </a>
 * <p>
 * Indeed, a number of lines get dropped. An analysis turns out that a glyph
 * origin positioned right on the clip path border has chances of being dropped.
 * This is due to different processing of those data with different errors.
 * </p>
 * @see #testFat1()
 */
@Test
public void test1() throws IOException {
    try (   InputStream resource = getClass().getResourceAsStream("1.pdf")  ) {
        PDDocument document = Loader.loadPDF(resource);
        PDFTextStripper stripper = new PDFVisibleTextStripper(false, new PrintStream(new File(RESULT_FOLDER, "1-drops.txt")));
        stripper.setSortByPosition(true);
        String text = stripper.getText(document);

        System.out.printf("\n*\n* 1.pdf\n*\n%s\n", text);
        Files.write(new File(RESULT_FOLDER, "1.txt").toPath(), Collections.singleton(text));
    }
}