You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@pdfbox.apache.org by "Vimal Kumar (JIRA)" <ji...@apache.org> on 2018/01/11 10:21:00 UTC

[jira] [Updated] (PDFBOX-4062) Fetch Color of Text using PDFBox

     [ https://issues.apache.org/jira/browse/PDFBOX-4062?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Vimal Kumar updated PDFBOX-4062:
--------------------------------
    Description: 
I Need to Fetch the Color of Text in a PDF using pdfbox 2.0.0 , for the same i have written java code as 

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.Writer;
import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingColor;
import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingColorN;
import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingColorSpace;
import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingDeviceCMYKColor;
import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingDeviceGrayColor;
import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingDeviceRGBColor;
import org.apache.pdfbox.contentstream.operator.color.SetStrokingColor;
import org.apache.pdfbox.contentstream.operator.color.SetStrokingColorN;
import org.apache.pdfbox.contentstream.operator.color.SetStrokingColorSpace;
import org.apache.pdfbox.contentstream.operator.color.SetStrokingDeviceCMYKColor;
import org.apache.pdfbox.contentstream.operator.color.SetStrokingDeviceGrayColor;
import org.apache.pdfbox.contentstream.operator.color.SetStrokingDeviceRGBColor;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.graphics.color.PDColor;
import org.apache.pdfbox.pdmodel.graphics.state.RenderingMode;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.text.TextPosition;

/**
 * This is an example on how to get the colors of text. Note that this will not tell the background,
 * and will only work properly if the text is not overwritten later, and only if the text rendering
 * modes are 0, 1 or 2. In the PDF 32000 specification, please read 9.3.6 "Text Rendering Mode" to
 * know more. Mode 0 (FILL) is the default. Mode 1 (STROKE) will make glyphs look "hollow". Mode 2
 * (FILL_STROKE) will make glyphs look "fat".
 *
 * @author Ben Litchfield
 * @author Tilman Hausherr
 */
public class PDF_Box_1 extends PDFTextStripper
{
    /**
     * Instantiate a new PDFTextStripper object.
     *
     * @throws IOException If there is an error loading the properties.
     */
    public PDF_Box_1() throws IOException
    {
        addOperator(new SetStrokingColorSpace());
        addOperator(new SetNonStrokingColorSpace());
        addOperator(new SetStrokingDeviceCMYKColor());
        addOperator(new SetNonStrokingDeviceCMYKColor());
        addOperator(new SetNonStrokingDeviceRGBColor());
        addOperator(new SetStrokingDeviceRGBColor());
        addOperator(new SetNonStrokingDeviceGrayColor());
        addOperator(new SetStrokingDeviceGrayColor());
        addOperator(new SetStrokingColor());
        addOperator(new SetStrokingColorN());
        addOperator(new SetNonStrokingColor());
        addOperator(new SetNonStrokingColorN());
    }

    /**
     * This will print the documents data.
     *
     * @param args The command line arguments.
     *
     * @throws IOException If there is an error parsing the document.
     */
    public static void main(String[] args) throws IOException
    {
       
            try (PDDocument document = PDDocument.load(new File("D://Vimal//New folder//ab.pdf")))
            {
                PDFTextStripper stripper = new PDF_Box_1();
                stripper.setSortByPosition(true);
                stripper.setStartPage(0);
                stripper.setEndPage(document.getNumberOfPages());

                stripper.getText(document);
            }
        
    }

    @Override
    protected void processTextPosition(TextPosition text)
    {
        super.processTextPosition(text);

        PDColor strokingColor = getGraphicsState().getStrokingColor();
        PDColor nonStrokingColor = getGraphicsState().getNonStrokingColor();
        String unicode = text.getUnicode();
        RenderingMode renderingMode = getGraphicsState().getTextState().getRenderingMode();
        System.out.println("Unicode:            " + unicode);
        System.out.println("Rendering mode:     " + renderingMode);
        System.out.println("Stroking color:     " + strokingColor);
        System.out.println("Non-Stroking color: " + nonStrokingColor);
        System.out.println("Non-Stroking color: " + nonStrokingColor);
        System.out.println();

        // See the PrintTextLocations for more attributes
    }

    /**
     * This will print the usage for this document.
     */
/*    private static void usage()
    {
        System.err.println("Usage: java " + PDF_Box_1.class.getName() + "D://Vimal//New folder//b1.pdf");
    }*/
}

But by using this I am getting Text of a Byte , but i want it for the word . Can you please help me in how to do this.


  was:
I Need to Fetch the Color of Text in a PDF using pdfbox 2.0.0 , for the same i have written java code as 

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.Writer;
import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingColor;
import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingColorN;
import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingColorSpace;
import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingDeviceCMYKColor;
import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingDeviceGrayColor;
import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingDeviceRGBColor;
import org.apache.pdfbox.contentstream.operator.color.SetStrokingColor;
import org.apache.pdfbox.contentstream.operator.color.SetStrokingColorN;
import org.apache.pdfbox.contentstream.operator.color.SetStrokingColorSpace;
import org.apache.pdfbox.contentstream.operator.color.SetStrokingDeviceCMYKColor;
import org.apache.pdfbox.contentstream.operator.color.SetStrokingDeviceGrayColor;
import org.apache.pdfbox.contentstream.operator.color.SetStrokingDeviceRGBColor;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.graphics.color.PDColor;
import org.apache.pdfbox.pdmodel.graphics.state.RenderingMode;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.text.TextPosition;

/**
 * This is an example on how to get the colors of text. Note that this will not tell the background,
 * and will only work properly if the text is not overwritten later, and only if the text rendering
 * modes are 0, 1 or 2. In the PDF 32000 specification, please read 9.3.6 "Text Rendering Mode" to
 * know more. Mode 0 (FILL) is the default. Mode 1 (STROKE) will make glyphs look "hollow". Mode 2
 * (FILL_STROKE) will make glyphs look "fat".
 *
 * @author Ben Litchfield
 * @author Tilman Hausherr
 */
public class PDF_Box_1 extends PDFTextStripper
{
    /**
     * Instantiate a new PDFTextStripper object.
     *
     * @throws IOException If there is an error loading the properties.
     */
    public PDF_Box_1() throws IOException
    {
        addOperator(new SetStrokingColorSpace());
        addOperator(new SetNonStrokingColorSpace());
        addOperator(new SetStrokingDeviceCMYKColor());
        addOperator(new SetNonStrokingDeviceCMYKColor());
        addOperator(new SetNonStrokingDeviceRGBColor());
        addOperator(new SetStrokingDeviceRGBColor());
        addOperator(new SetNonStrokingDeviceGrayColor());
        addOperator(new SetStrokingDeviceGrayColor());
        addOperator(new SetStrokingColor());
        addOperator(new SetStrokingColorN());
        addOperator(new SetNonStrokingColor());
        addOperator(new SetNonStrokingColorN());
    }

    /**
     * This will print the documents data.
     *
     * @param args The command line arguments.
     *
     * @throws IOException If there is an error parsing the document.
     */
    public static void main(String[] args) throws IOException
    {
       
            try (PDDocument document = PDDocument.load(new File("D://Vimal//New folder//ab.pdf")))
            {
                PDFTextStripper stripper = new PDF_Box_1();
                stripper.setSortByPosition(true);
                stripper.setStartPage(0);
                stripper.setEndPage(document.getNumberOfPages());

                Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
               
                stripper.writeText(document, dummy);
            }
        
    }

    @Override
    protected void processTextPosition(TextPosition text)
    {
        super.processTextPosition(text);

        PDColor strokingColor = getGraphicsState().getStrokingColor();
        PDColor nonStrokingColor = getGraphicsState().getNonStrokingColor();
        String unicode = text.getUnicode();
        RenderingMode renderingMode = getGraphicsState().getTextState().getRenderingMode();
        System.out.println("Unicode:            " + unicode);
        System.out.println("Rendering mode:     " + renderingMode);
        System.out.println("Stroking color:     " + strokingColor);
        System.out.println("Non-Stroking color: " + nonStrokingColor);
        System.out.println("Non-Stroking color: " + nonStrokingColor);
        System.out.println();

        // See the PrintTextLocations for more attributes
    }

    /**
     * This will print the usage for this document.
     */
/*    private static void usage()
    {
        System.err.println("Usage: java " + PDF_Box_1.class.getName() + "D://Vimal//New folder//b1.pdf");
    }*/
}

But by using this I am getting Text of a Byte , but i want it for the word . Can you please help me in how to do this.



> Fetch Color of Text using PDFBox
> --------------------------------
>
>                 Key: PDFBOX-4062
>                 URL: https://issues.apache.org/jira/browse/PDFBOX-4062
>             Project: PDFBox
>          Issue Type: Bug
>            Reporter: Vimal Kumar
>            Priority: Blocker
>
> I Need to Fetch the Color of Text in a PDF using pdfbox 2.0.0 , for the same i have written java code as 
> import java.io.ByteArrayOutputStream;
> import java.io.File;
> import java.io.IOException;
> import java.io.OutputStreamWriter;
> import java.io.Writer;
> import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingColor;
> import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingColorN;
> import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingColorSpace;
> import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingDeviceCMYKColor;
> import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingDeviceGrayColor;
> import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingDeviceRGBColor;
> import org.apache.pdfbox.contentstream.operator.color.SetStrokingColor;
> import org.apache.pdfbox.contentstream.operator.color.SetStrokingColorN;
> import org.apache.pdfbox.contentstream.operator.color.SetStrokingColorSpace;
> import org.apache.pdfbox.contentstream.operator.color.SetStrokingDeviceCMYKColor;
> import org.apache.pdfbox.contentstream.operator.color.SetStrokingDeviceGrayColor;
> import org.apache.pdfbox.contentstream.operator.color.SetStrokingDeviceRGBColor;
> import org.apache.pdfbox.pdmodel.PDDocument;
> import org.apache.pdfbox.pdmodel.graphics.color.PDColor;
> import org.apache.pdfbox.pdmodel.graphics.state.RenderingMode;
> import org.apache.pdfbox.text.PDFTextStripper;
> import org.apache.pdfbox.text.TextPosition;
> /**
>  * This is an example on how to get the colors of text. Note that this will not tell the background,
>  * and will only work properly if the text is not overwritten later, and only if the text rendering
>  * modes are 0, 1 or 2. In the PDF 32000 specification, please read 9.3.6 "Text Rendering Mode" to
>  * know more. Mode 0 (FILL) is the default. Mode 1 (STROKE) will make glyphs look "hollow". Mode 2
>  * (FILL_STROKE) will make glyphs look "fat".
>  *
>  * @author Ben Litchfield
>  * @author Tilman Hausherr
>  */
> public class PDF_Box_1 extends PDFTextStripper
> {
>     /**
>      * Instantiate a new PDFTextStripper object.
>      *
>      * @throws IOException If there is an error loading the properties.
>      */
>     public PDF_Box_1() throws IOException
>     {
>         addOperator(new SetStrokingColorSpace());
>         addOperator(new SetNonStrokingColorSpace());
>         addOperator(new SetStrokingDeviceCMYKColor());
>         addOperator(new SetNonStrokingDeviceCMYKColor());
>         addOperator(new SetNonStrokingDeviceRGBColor());
>         addOperator(new SetStrokingDeviceRGBColor());
>         addOperator(new SetNonStrokingDeviceGrayColor());
>         addOperator(new SetStrokingDeviceGrayColor());
>         addOperator(new SetStrokingColor());
>         addOperator(new SetStrokingColorN());
>         addOperator(new SetNonStrokingColor());
>         addOperator(new SetNonStrokingColorN());
>     }
>     /**
>      * This will print the documents data.
>      *
>      * @param args The command line arguments.
>      *
>      * @throws IOException If there is an error parsing the document.
>      */
>     public static void main(String[] args) throws IOException
>     {
>        
>             try (PDDocument document = PDDocument.load(new File("D://Vimal//New folder//ab.pdf")))
>             {
>                 PDFTextStripper stripper = new PDF_Box_1();
>                 stripper.setSortByPosition(true);
>                 stripper.setStartPage(0);
>                 stripper.setEndPage(document.getNumberOfPages());
>                 stripper.getText(document);
>             }
>         
>     }
>     @Override
>     protected void processTextPosition(TextPosition text)
>     {
>         super.processTextPosition(text);
>         PDColor strokingColor = getGraphicsState().getStrokingColor();
>         PDColor nonStrokingColor = getGraphicsState().getNonStrokingColor();
>         String unicode = text.getUnicode();
>         RenderingMode renderingMode = getGraphicsState().getTextState().getRenderingMode();
>         System.out.println("Unicode:            " + unicode);
>         System.out.println("Rendering mode:     " + renderingMode);
>         System.out.println("Stroking color:     " + strokingColor);
>         System.out.println("Non-Stroking color: " + nonStrokingColor);
>         System.out.println("Non-Stroking color: " + nonStrokingColor);
>         System.out.println();
>         // See the PrintTextLocations for more attributes
>     }
>     /**
>      * This will print the usage for this document.
>      */
> /*    private static void usage()
>     {
>         System.err.println("Usage: java " + PDF_Box_1.class.getName() + "D://Vimal//New folder//b1.pdf");
>     }*/
> }
> But by using this I am getting Text of a Byte , but i want it for the word . Can you please help me in how to do this.



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@pdfbox.apache.org
For additional commands, e-mail: dev-help@pdfbox.apache.org