| 1 | // Jomic - a viewer for comic book archives. |
| 2 | // Copyright (C) 2004-2011 Thomas Aglassinger |
| 3 | // |
| 4 | // This program is free software: you can redistribute it and/or modify |
| 5 | // it under the terms of the GNU General Public License as published by |
| 6 | // the Free Software Foundation, either version 3 of the License, or |
| 7 | // (at your option) any later version. |
| 8 | // |
| 9 | // This program is distributed in the hope that it will be useful, |
| 10 | // but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 11 | // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 12 | // GNU General Public License for more details. |
| 13 | // |
| 14 | // You should have received a copy of the GNU General Public License |
| 15 | // along with this program. If not, see <http://www.gnu.org/licenses/>. |
| 16 | package net.sf.jomic.tools; |
| 17 | |
| 18 | import java.io.File; |
| 19 | import java.io.IOException; |
| 20 | import java.text.DecimalFormat; |
| 21 | import java.util.ArrayList; |
| 22 | import java.util.Iterator; |
| 23 | import java.util.List; |
| 24 | import java.util.Map; |
| 25 | |
| 26 | import org.apache.commons.logging.Log; |
| 27 | import org.apache.commons.logging.LogFactory; |
| 28 | import org.apache.pdfbox.pdmodel.PDDocument; |
| 29 | import org.apache.pdfbox.pdmodel.PDPage; |
| 30 | import org.apache.pdfbox.pdmodel.PDResources; |
| 31 | import org.apache.pdfbox.pdmodel.graphics.xobject.PDXObjectImage; |
| 32 | |
| 33 | /** |
| 34 | * Task to extract all images from a PDF file to a specified target folder. The images will be |
| 35 | * named "00.jpg", "01.jpg" and so on, with the actual number of digits depending on the number of |
| 36 | * images in the PDF. |
| 37 | * |
| 38 | * @author Thomas Aglassinger |
| 39 | */ |
| 40 | public class ExtractPdfImagesTask extends AbstractTask |
| 41 | { |
| 42 | private static final double WEIGHT_IMAGE_NAMES = 0.10; |
| 43 | private static final double WEIGHT_LOAD = 0.10; |
| 44 | private FileTools fileTools; |
| 45 | |
| 46 | private Log logger; |
| 47 | private File pdfFile; |
| 48 | private StringTools stringTools; |
| 49 | private File targetFolder; |
| 50 | |
| 51 | public ExtractPdfImagesTask(File newPdfFile, File newTargetFolder) { |
| 52 | this(); |
| 53 | pdfFile = newPdfFile; |
| 54 | targetFolder = newTargetFolder; |
| 55 | setMaxProgress(pdfFile.length() + 1); |
| 56 | } |
| 57 | |
| 58 | private ExtractPdfImagesTask() { |
| 59 | super(); |
| 60 | logger = LogFactory.getLog(ExtractPdfImagesTask.class); |
| 61 | fileTools = FileTools.instance(); |
| 62 | stringTools = StringTools.instance(); |
| 63 | } |
| 64 | |
| 65 | private List getTargetImageNames(List pages) |
| 66 | throws IOException { |
| 67 | List result = new ArrayList(); |
| 68 | Iterator pageRider = pages.iterator(); |
| 69 | |
| 70 | while (pageRider.hasNext()) { |
| 71 | PDPage page = (PDPage) pageRider.next(); |
| 72 | PDResources resources = page.getResources(); |
| 73 | Map images = resources.getImages(); |
| 74 | |
| 75 | if (images != null) { |
| 76 | Iterator imageRider = images.values().iterator(); |
| 77 | |
| 78 | while (imageRider.hasNext()) { |
| 79 | PDXObjectImage image = (PDXObjectImage) imageRider.next(); |
| 80 | String suffix = image.getSuffix(); |
| 81 | |
| 82 | result.add(suffix); |
| 83 | } |
| 84 | } |
| 85 | } |
| 86 | |
| 87 | // Assign numeric names to all images, but preserve the original suffix. |
| 88 | int imageCount = result.size(); |
| 89 | |
| 90 | if (imageCount > 0) { |
| 91 | DecimalFormat format = stringTools.getLeadingZeroFormat(imageCount); |
| 92 | |
| 93 | for (int i = 0; i < imageCount; i += 1) { |
| 94 | String name = format.format(i) + "." + result.get(i); |
| 95 | |
| 96 | result.set(i, name); |
| 97 | } |
| 98 | } |
| 99 | return result; |
| 100 | } |
| 101 | |
| 102 | public void start() |
| 103 | throws Exception { |
| 104 | setProgress(0); |
| 105 | |
| 106 | boolean allFilesExtracted = false; |
| 107 | List targetImageNames = null; |
| 108 | PDDocument pdf = PDDocument.load(pdfFile); |
| 109 | |
| 110 | setProgress(Math.round(WEIGHT_LOAD * getMaxProgress())); |
| 111 | |
| 112 | try { |
| 113 | List pages = pdf.getDocumentCatalog().getAllPages(); |
| 114 | |
| 115 | targetImageNames = getTargetImageNames(pages); |
| 116 | |
| 117 | int imageCount = targetImageNames.size(); |
| 118 | |
| 119 | setProgress(Math.round((WEIGHT_LOAD + WEIGHT_IMAGE_NAMES) * getMaxProgress())); |
| 120 | |
| 121 | long progressWhenStartingToExtract = getProgress(); |
| 122 | long maxExtractProgress = (getMaxProgress() - progressWhenStartingToExtract); |
| 123 | int imageIndex = 0; |
| 124 | Iterator pageRider = pages.iterator(); |
| 125 | |
| 126 | fileTools.mkdirs(targetFolder); |
| 127 | while (pageRider.hasNext()) { |
| 128 | PDPage page = (PDPage) pageRider.next(); |
| 129 | PDResources resources = page.getResources(); |
| 130 | Map images = resources.getImages(); |
| 131 | |
| 132 | if (images != null) { |
| 133 | Iterator imageRider = images.values().iterator(); |
| 134 | |
| 135 | while (imageRider.hasNext()) { |
| 136 | PDXObjectImage image = (PDXObjectImage) imageRider.next(); |
| 137 | File imageFile = new File(targetFolder, (String) targetImageNames.get(imageIndex)); |
| 138 | String name = imageFile.getAbsolutePath(); |
| 139 | |
| 140 | if (logger.isInfoEnabled()) { |
| 141 | logger.info("extracting image: " + stringTools.sourced(name)); |
| 142 | } |
| 143 | image.write2file(fileTools.getWithoutLastSuffix(name)); |
| 144 | imageIndex += 1; |
| 145 | |
| 146 | double imagesProcessedRatio = ((double) imageIndex) / imageCount; |
| 147 | |
| 148 | setProgress(progressWhenStartingToExtract |
| 149 | + Math.round(imagesProcessedRatio * maxExtractProgress)); |
| 150 | } |
| 151 | } |
| 152 | allFilesExtracted = !isInterrupted(); |
| 153 | } |
| 154 | } finally { |
| 155 | pdf.close(); |
| 156 | if (!allFilesExtracted && (targetImageNames != null)) { |
| 157 | if (logger.isInfoEnabled()) { |
| 158 | logger.info("removing files extracted so far"); |
| 159 | } |
| 160 | Iterator fileRider = targetImageNames.iterator(); |
| 161 | |
| 162 | // TODO: Also remove folder structure generated by extracted files. |
| 163 | while (fileRider.hasNext()) { |
| 164 | String fileNameToDelete = (String) fileRider.next(); |
| 165 | File fileToDelete = new File(targetFolder, fileNameToDelete); |
| 166 | |
| 167 | fileToDelete.delete(); |
| 168 | } |
| 169 | |
| 170 | } |
| 171 | } |
| 172 | setProgress(getMaxProgress()); |
| 173 | } |
| 174 | } |