com.itextpdf.text.pdf.parser.LocationTextExtractionStrategy Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of itextpdf Show documentation
Show all versions of itextpdf Show documentation
iText, a free Java-PDF library
/*
* $Id: LocationTextExtractionStrategy.java 4784 2011-03-15 08:33:00Z blowagie $
*
* This file is part of the iText (R) project.
* Copyright (c) 1998-2011 1T3XT BVBA
* Authors: Kevin Day, Bruno Lowagie, Paulo Soares, et al.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License version 3
* as published by the Free Software Foundation with the addition of the
* following permission added to Section 15 as permitted in Section 7(a):
* FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY 1T3XT,
* 1T3XT DISCLAIMS THE WARRANTY OF NON INFRINGEMENT OF THIRD PARTY RIGHTS.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
* or FITNESS FOR A PARTICULAR PURPOSE.
* See the GNU Affero General Public License for more details.
* You should have received a copy of the GNU Affero General Public License
* along with this program; if not, see http://www.gnu.org/licenses or write to
* the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
* Boston, MA, 02110-1301 USA, or download the license from the following URL:
* http://itextpdf.com/terms-of-use/
*
* The interactive user interfaces in modified source and object code versions
* of this program must display Appropriate Legal Notices, as required under
* Section 5 of the GNU Affero General Public License.
*
* In accordance with Section 7(b) of the GNU Affero General Public License,
* a covered work must retain the producer line in every PDF that is created
* or manipulated using iText.
*
* You can be released from the requirements of the license by purchasing
* a commercial license. Buying such a license is mandatory as soon as you
* develop commercial activities involving the iText software without
* disclosing the source code of your own applications.
* These activities include: offering paid services to customers as an ASP,
* serving PDFs on the fly in a web application, shipping iText with a closed
* source product.
*
* For more information, please contact iText Software Corp. at this
* address: [email protected]
*/
package com.itextpdf.text.pdf.parser;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Iterator;
import java.util.List;
/**
* Development preview - this class (and all of the parser classes) are still experiencing
* heavy development, and are subject to change both behavior and interface.
*
* A text extraction renderer that keeps track of relative position of text on page
* The resultant text will be relatively consistent with the physical layout that most
* PDF files have on screen.
*
* This renderer keeps track of the orientation and distance (both perpendicular
* and parallel) to the unit vector of the orientation. Text is ordered by
* orientation, then perpendicular, then parallel distance. Text with the same
* perpendicular distance, but different parallel distance is treated as being on
* the same line.
*
* This renderer also uses a simple strategy based on the font metrics to determine if
* a blank space should be inserted into the output.
*
* @since 5.0.2
*/
public class LocationTextExtractionStrategy implements TextExtractionStrategy {
/** set to true for debugging */
static boolean DUMP_STATE = false;
/** a summary of all found text */
private final List locationalResult = new ArrayList();
/**
* Creates a new text extraction renderer.
*/
public LocationTextExtractionStrategy() {
}
/**
* @see com.itextpdf.text.pdf.parser.RenderListener#beginTextBlock()
*/
public void beginTextBlock(){
}
/**
* @see com.itextpdf.text.pdf.parser.RenderListener#endTextBlock()
*/
public void endTextBlock(){
}
/**
* Returns the result so far.
* @return a String with the resulting text.
*/
public String getResultantText(){
if (DUMP_STATE) dumpState();
Collections.sort(locationalResult);
StringBuffer sb = new StringBuffer();
TextChunk lastChunk = null;
for (TextChunk chunk : locationalResult) {
if (lastChunk == null){
sb.append(chunk.text);
} else {
if (chunk.sameLine(lastChunk)){
float dist = chunk.distanceFromEndOf(lastChunk);
if (dist < -chunk.charSpaceWidth)
sb.append(' ');
// we only insert a blank space if the trailing character of the previous string wasn't a space, and the leading character of the current string isn't a space
else if (dist > chunk.charSpaceWidth/2.0f && chunk.text.charAt(0) != ' ' && lastChunk.text.charAt(lastChunk.text.length()-1) != ' ')
sb.append(' ');
sb.append(chunk.text);
} else {
sb.append('\n');
sb.append(chunk.text);
}
}
lastChunk = chunk;
}
return sb.toString();
}
/** Used for debugging only */
private void dumpState(){
for (Iterator iterator = locationalResult.iterator(); iterator.hasNext(); ) {
TextChunk location = (TextChunk) iterator.next();
location.printDiagnostics();
System.out.println();
}
}
/**
*
* @see com.itextpdf.text.pdf.parser.RenderListener#renderText(com.itextpdf.text.pdf.parser.TextRenderInfo)
*/
public void renderText(TextRenderInfo renderInfo) {
LineSegment segment = renderInfo.getBaseline();
TextChunk location = new TextChunk(renderInfo.getText(), segment.getStartPoint(), segment.getEndPoint(), renderInfo.getSingleSpaceWidth());
locationalResult.add(location);
}
/**
* Represents a chunk of text, it's orientation, and location relative to the orientation vector
*/
private static class TextChunk implements Comparable{
/** the text of the chunk */
final String text;
/** the starting location of the chunk */
final Vector startLocation;
/** the ending location of the chunk */
final Vector endLocation;
/** unit vector in the orientation of the chunk */
final Vector orientationVector;
/** the orientation as a scalar for quick sorting */
final int orientationMagnitude;
/** perpendicular distance to the orientation unit vector (i.e. the Y position in an unrotated coordinate system)
* we round to the nearest integer to handle the fuzziness of comparing floats */
final int distPerpendicular;
/** distance of the start of the chunk parallel to the orientation unit vector (i.e. the X position in an unrotated coordinate system) */
final float distParallelStart;
/** distance of the end of the chunk parallel to the orientation unit vector (i.e. the X position in an unrotated coordinate system) */
final float distParallelEnd;
/** the width of a single space character in the font of the chunk */
final float charSpaceWidth;
public TextChunk(String string, Vector startLocation, Vector endLocation, float charSpaceWidth) {
this.text = string;
this.startLocation = startLocation;
this.endLocation = endLocation;
this.charSpaceWidth = charSpaceWidth;
orientationVector = endLocation.subtract(startLocation).normalize();
orientationMagnitude = (int)(Math.atan2(orientationVector.get(Vector.I2), orientationVector.get(Vector.I1))*1000);
// see http://mathworld.wolfram.com/Point-LineDistance2-Dimensional.html
// the two vectors we are crossing are in the same plane, so the result will be purely
// in the z-axis (out of plane) direction, so we just take the I3 component of the result
Vector origin = new Vector(0,0,1);
distPerpendicular = (int)(startLocation.subtract(origin)).cross(orientationVector).get(Vector.I3);
distParallelStart = orientationVector.dot(startLocation);
distParallelEnd = orientationVector.dot(endLocation);
}
private void printDiagnostics(){
System.out.println("Text (@" + startLocation + " -> " + endLocation + "): " + text);
System.out.println("orientationMagnitude: " + orientationMagnitude);
System.out.println("distPerpendicular: " + distPerpendicular);
System.out.println("distParallel: " + distParallelStart);
}
/**
* @param as the location to compare to
* @return true is this location is on the the same line as the other
*/
public boolean sameLine(TextChunk as){
if (orientationMagnitude != as.orientationMagnitude) return false;
if (distPerpendicular != as.distPerpendicular) return false;
return true;
}
/**
* Computes the distance between the end of 'other' and the beginning of this chunk
* in the direction of this chunk's orientation vector. Note that it's a bad idea
* to call this for chunks that aren't on the same line and orientation, but we don't
* explicitly check for that condition for performance reasons.
* @param other
* @return the number of spaces between the end of 'other' and the beginning of this chunk
*/
public float distanceFromEndOf(TextChunk other){
float distance = distParallelStart - other.distParallelEnd;
return distance;
}
/**
* Compares based on orientation, perpendicular distance, then parallel distance
* @see java.lang.Comparable#compareTo(java.lang.Object)
*/
public int compareTo(TextChunk rhs) {
if (this == rhs) return 0; // not really needed, but just in case
int rslt;
rslt = compareInts(orientationMagnitude, rhs.orientationMagnitude);
if (rslt != 0) return rslt;
rslt = compareInts(distPerpendicular, rhs.distPerpendicular);
if (rslt != 0) return rslt;
// note: it's never safe to check floating point numbers for equality, and if two chunks
// are truly right on top of each other, which one comes first or second just doesn't matter
// so we arbitrarily choose this way.
rslt = distParallelStart < rhs.distParallelStart ? -1 : 1;
return rslt;
}
/**
*
* @param int1
* @param int2
* @return comparison of the two integers
*/
private static int compareInts(int int1, int int2){
return int1 == int2 ? 0 : int1 < int2 ? -1 : 1;
}
}
/**
* no-op method - this renderer isn't interested in image events
* @see com.itextpdf.text.pdf.parser.RenderListener#renderImage(com.itextpdf.text.pdf.parser.ImageRenderInfo)
* @since 5.0.1
*/
public void renderImage(ImageRenderInfo renderInfo) {
// do nothing
}
}