/** * Copyright 2006 by Know-Center, Graz, Austria * PDF-AS has been contracted by the E-Government Innovation Center EGIZ, a * joint initiative of the Federal Chancellery Austria and Graz University of * Technology. * * Licensed under the EUPL, Version 1.1 or - as soon they will be approved by * the European Commission - subsequent versions of the EUPL (the "Licence"); * You may not use this work except in compliance with the Licence. * You may obtain a copy of the Licence at: * http://www.osor.eu/eupl/ * * Unless required by applicable law or agreed to in writing, software * distributed under the Licence is distributed on an "AS IS" basis, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the Licence for the specific language governing permissions and * limitations under the Licence. * * This product combines work with different licenses. See the "NOTICE" text * file for details on the various modules and licenses. * The "NOTICE" text file is part of the distribution. Any derivative works * that you distribute must include a readable copy of the "NOTICE" text file. */ package demo; import java.io.File; import java.io.IOException; import java.util.Iterator; import java.util.List; import at.gv.egiz.pdfas.api.analyze.NonTextObjectInfo; import at.gv.egiz.pdfas.api.io.DataSource; import at.gv.egiz.pdfas.impl.api.commons.PdfDataSourceAdapter; import at.gv.egiz.pdfas.io.FileBasedDataSource; import at.knowcenter.wag.egov.egiz.PdfAS; public class ExtractNonTextualObjectsDemo { /** * Disable instantiation. */ private ExtractNonTextualObjectsDemo() { } /** * Starts a demo that extracts non-textual elements from a document. * * @param args * The parameter(s). */ public static void main(String[] args) { if (args == null || args.length == 0) { System.err.println("Please provide path of file to be analyzed."); System.exit(1); } File testFile = new File(args[0]); try { // set source DataSource dataSource = new FileBasedDataSource(testFile, "application/pdf"); List nonTextualObjects = PdfAS.extractNonTextualObjects(new PdfDataSourceAdapter(dataSource)); if (nonTextualObjects != null && !nonTextualObjects.isEmpty()) { System.out.println(nonTextualObjects.size() + " non-textual object(s) found."); Iterator noit = nonTextualObjects.iterator(); while (noit.hasNext()) { NonTextObjectInfo info = (NonTextObjectInfo) noit.next(); System.out.println(" -> " + info.toString()); } } else { System.out.println("No non-textual objects found."); } } catch (IOException e) { e.printStackTrace(); } } }