Example usage for org.apache.pdfbox.text PDFTextStripper subclass-usage

Introduction

In this page you can find the example usage for org.apache.pdfbox.text PDFTextStripper subclass-usage.

Usage

From source file helper.pdfpreprocessing.pdf.TextHighlight.java

/**
 * This class implements the methods highlight and highlightDefault which will add a highlight to the PDF based on a
 * Pattern or String. The idea is to extend the PDFTextStripper and override the methods that write to the Output to
 * instead write to a TextCache that keeps data on the position of the TextPositions. From this information we can then
 * derive bounding boxes (and quads) that can be used to write the annotations. See the main method for example usage
 *

From source file org.apache.tika.parser.pdf.AbstractPDF2XHTML.java

class AbstractPDF2XHTML extends PDFTextStripper {

    enum ActionTrigger {
        AFTER_DOCUMENT_PRINT, AFTER_DOCUMENT_SAVE, ANNOTATION_CURSOR_ENTERS, ANNOTATION_CURSOR_EXIT, ANNOTATION_LOSE_INPUT_FOCUS, ANNOTATION_MOUSE_CLICK, ANNOTATION_MOUSE_RELEASED, ANNOTATION_PAGE_CLOSED, ANNOTATION_PAGE_NO_LONGER_VISIBLE, ANNOTATION_PAGE_OPENED, ANNOTATION_PAGE_VISIBLE, ANNOTATION_RECEIVES_FOCUS, ANNOTATION_WIDGET, BEFORE_DOCUMENT_CLOSE, BEFORE_DOCUMENT_PRINT, BEFORE_DOCUMENT_SAVE, DOCUMENT_OPEN, FORM_FIELD, FORM_FIELD_FORMATTED, FORM_FIELD_KEYSTROKE, FORM_FIELD_RECALCULATE, FORM_FIELD_VALUE_CHANGE, PAGE_CLOSE, PAGE_OPEN, BOOKMARK,
    };

From source file org.apache.tika.parser.pdf.AbstractPDF2XHTMLPureJava.java

class AbstractPDF2XHTMLPureJava extends PDFTextStripper {

    enum ActionTrigger {
        AFTER_DOCUMENT_PRINT, AFTER_DOCUMENT_SAVE, ANNOTATION_CURSOR_ENTERS, ANNOTATION_CURSOR_EXIT, ANNOTATION_LOSE_INPUT_FOCUS, ANNOTATION_MOUSE_CLICK, ANNOTATION_MOUSE_RELEASED, ANNOTATION_PAGE_CLOSED, ANNOTATION_PAGE_NO_LONGER_VISIBLE, ANNOTATION_PAGE_OPENED, ANNOTATION_PAGE_VISIBLE, ANNOTATION_RECEIVES_FOCUS, ANNOTATION_WIDGET, BEFORE_DOCUMENT_CLOSE, BEFORE_DOCUMENT_PRINT, BEFORE_DOCUMENT_SAVE, DOCUMENT_OPEN, FORM_FIELD, FORM_FIELD_FORMATTED, FORM_FIELD_KEYSTROKE, FORM_FIELD_RECALCULATE, FORM_FIELD_VALUE_CHANGE, PAGE_CLOSE, PAGE_OPEN, BOOKMARK,
    };

From source file org.apache.tika.parser.pdf.EnhancedPDF2XHTML.java

/**
 * <p>Utility class that overrides the {@link PDFTextStripper} functionality
 * to produce a semi-structured XHTML SAX events instead of a plain text
 * stream.</p>
 * 
 * <h2>About this class:</h2>

From source file org.fit.pdfdom.PDFBoxTree.java

/**
 * A generic tree of boxes created from a PDF file. It processes the PDF document and calls
 * the appropriate abstract methods in order to render a page, text box, etc. The particular
 * implementations are expected to implement these actions in order to build the resulting
 * document tree.
 * 

From source file org.mabb.fontverter.pdf.PdfFontExtractor.java

/**
 * Utility to extract all fonts in a given PDF
 */
public class PdfFontExtractor extends PDFTextStripper {
    private static final String[] HELP_CODES = new String[] { "-h", "help", "--help", "/?" };
    private static final String DEFAULT_EXTRACT_PATH = "fonts/";

From source file uk.bl.wa.tika.parser.pdf.pdfbox.PDF2XHTML.java

/**
 * Utility class that overrides the {@link PDFTextStripper} functionality
 * to produce a semi-structured XHTML SAX events instead of a plain text
 * stream.
 */
class PDF2XHTML extends PDFTextStripper {

From source file uk.org.openeyes.PDFFunctions.java

/**
 *
 * @author veta
 */
public class PDFFunctions extends PDFTextStripper {
    private Map<String, Coordinates> CoordMap = new HashMap<String, Coordinates>();

• «
• 1
• 2
• »