Merge pull request #467 from support-project/feature/issue172_pdf_to_…

…image

#172 Change the library "com-sun-pdfview" to "pdfbox" for pdf to png

src/main/java/org/support/project/knowledge/parser/SlideShowParserFactory.java

@@ -3,7 +3,7 @@
 import java.io.IOException;
 
 import org.support.project.common.util.StringUtils;
-import org.support.project.knowledge.parser.impl.PdfSlideShowParser;
+import org.support.project.knowledge.parser.impl.PdfSlideShowParserOnPdfbox;
 import org.support.project.knowledge.parser.impl.PptxSlideShowParser;
 
 public class SlideShowParserFactory {
@@ -19,7 +19,7 @@ public static SlideShowParser getParser(String filename) throws IOException {
         if (extension.toLowerCase().equals(".pptx")) {
             return new PptxSlideShowParser();
         } else if (extension.toLowerCase().equals(".pdf")) {
-            return new PdfSlideShowParser();
+            return new PdfSlideShowParserOnPdfbox();
         } else {
             return null;
         }

src/main/java/org/support/project/knowledge/parser/impl/PdfSlideShowParserOnPdfbox.java

@@ -0,0 +1,51 @@
+package org.support.project.knowledge.parser.impl;
+
+import java.awt.image.BufferedImage;
+import java.io.File;
+import java.io.IOException;
+import java.util.List;
+
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.pdmodel.PDPage;
+import org.apache.pdfbox.util.ImageIOUtil;
+import org.support.project.common.exception.ParseException;
+import org.support.project.knowledge.parser.SlideShowParser;
+
+public class PdfSlideShowParserOnPdfbox implements SlideShowParser {
+
+    @Override
+    public void parse(File inputFile, File outputDir) throws ParseException {
+        try {
+            /*
+             * Solution for the 1.8 version:
+             */
+            PDDocument document = PDDocument.loadNonSeq(inputFile, null);
+            List<PDPage> pdPages = document.getDocumentCatalog().getAllPages();
+            int page = 0;
+            for (PDPage pdPage : pdPages) {
+                ++page;
+                BufferedImage bim = pdPage.convertToImage(BufferedImage.TYPE_INT_RGB, 300);
+                ImageIOUtil.writeImage(bim, outputDir.getAbsolutePath() + "/" + page + ".png", 300);
+            }
+            document.close();
+
+            /*
+             * Solution for the 2.0 version:
+            PDDocument document = PDDocument.load(inputFile);
+            PDFRenderer pdfRenderer = new PDFRenderer(document);
+            for (int page = 0; page < document.getNumberOfPages(); ++page) {
+                BufferedImage bim = pdfRenderer.renderImageWithDPI(page, 300, ImageType.RGB);
+
+                // suffix in filename will be used as the file format
+                ImageIOUtil.writeImage(bim, outputDir.getAbsolutePath() + "/" + (page + 1) + ".png", 300);
+            }
+            document.close();
+            */
+
+        } catch (IOException e) {
+            throw new ParseException(e);
+        }
+    }
+
+}
+

src/test/java/org/support/project/knowledge/parser/PdfSlideShowParserTest.java

@@ -8,11 +8,11 @@
 import org.support.project.common.exception.ParseException;
 import org.support.project.common.util.FileUtil;
 import org.support.project.knowledge.config.AppConfig;
-import org.support.project.knowledge.parser.impl.PdfSlideShowParser;
+import org.support.project.knowledge.parser.impl.PdfSlideShowParserOnPdfbox;
 
 public class PdfSlideShowParserTest {
 
-    public static final String SAMPLE = "sample2";
+    public static final String SAMPLE = "sample4";
 
     public static void main(String[] args) throws FileNotFoundException, IOException, ParseException {
         File tempDir = new File(AppConfig.get().getTmpPath());
@@ -24,7 +24,7 @@ public static void main(String[] args) throws FileNotFoundException, IOException
         FileUtil.copy(PdfSlideShowParserTest.class.getResourceAsStream("/org/support/project/knowledge/paeser/" + SAMPLE + ".pdf"),
                 new FileOutputStream(sample));
 
-        PdfSlideShowParser parser = new PdfSlideShowParser();
+        SlideShowParser parser = new PdfSlideShowParserOnPdfbox();
         parser.parse(sample, output);
     }