Customise for nla.

pom.xml

@@ -1,7 +1,7 @@
 <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
   <modelVersion>4.0.0</modelVersion>
-  <groupId>fr.bnf.digitools</groupId>
-  <artifactId>scannedPdf</artifactId>
+  <groupId>au.gov.nla</groupId>
+  <artifactId>scanned-pdf-detector</artifactId>
   <packaging>jar</packaging>
   <version>1.2</version>
   <name>scannedPdf</name>
@@ -18,11 +18,16 @@
       <distribution>repo</distribution>
     </license>
   </licenses>
-  <scm>
-    <url>https://github.com/tledoux/scannedPdf</url>
-    <connection>scm:git:git://github.com/tledoux/scannedPdf.git</connection>
-    <developerConnection>scm:git:git@github.com:tledoux/scannedPdf.git</developerConnection>
-  </scm>
+  <distributionManagement>
+    <repository>
+      <id>nla-public-releases</id>
+      <url>https://dev.nla.gov.au/nexus/content/repositories/nla-public/</url>
+    </repository>
+    <snapshotRepository>
+      <id>nla-public-snapshots</id>
+      <url>https://dev.nla.gov.au/nexus/content/repositories/nla-public-snapshots/</url>
+    </snapshotRepository>
+  </distributionManagement>
   <properties>
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
   </properties>
@@ -33,13 +38,6 @@
       <artifactId>pdfbox</artifactId>
       <version>2.0.29</version>
     </dependency>
-    <!-- Required by PDFBox to read JPEG2000 images -->
-    <dependency>
-      <groupId>javax.media</groupId>
-      <artifactId>jai_imageio</artifactId>
-      <version>1.1.1</version>
-    </dependency>
-
     <!-- In order to annotate the spotbugs report -->
     <dependency>
       <groupId>com.github.spotbugs</groupId>
@@ -188,13 +186,5 @@
       </plugin>
     </plugins>
   </reporting>
-
-  <repositories>
-    <repository>
-      <id>Geotoolkit</id>
-      <name>Geotoolkit</name>
-      <url>http://maven.geotoolkit.org/</url>
-    </repository>
-  </repositories>
 
 </project>

src/main/java/fr/bnf/toolslab/StrictPdfBoxScanDetector.java

@@ -1,5 +1,6 @@
 package fr.bnf.toolslab;
 
+import java.io.File;
 import java.io.IOException;
 import java.util.ArrayList;
 import java.util.HashMap;
@@ -28,6 +29,15 @@ public class StrictPdfBoxScanDetector extends AbstractScanDetector {
     List<DimensionInfo> imageDimensions;
     private Map<COSStream, Integer> processedInlineImages = new HashMap<>();
     private AtomicInteger inlineImageCounter = new AtomicInteger(0);
+    private final int numSamples; // Number of pages to sample
+
+    public StrictPdfBoxScanDetector(int numSamples) {
+      this.numSamples = numSamples;
+    }
+
+    public StrictPdfBoxScanDetector() {
+      this(MAX_SAMPLES); // Default to 5 samples
+    }
 
     @Override
     public void init(FileDescriptor fd) {
@@ -67,15 +77,14 @@ public void parse() throws IOException {
           return;
         }
 
-        // Second heuristic: pick some pages and look if the image covers
+        // Second heuristic: pick the first x pages and look if the image covers
         // all the page
-        int nbSamples = Math.min(nbPages, MAX_SAMPLES);
-        List<Integer> pagesToTest = pickSamples(nbSamples, nbPages);
+        int nbSamples = Math.min(nbPages, numSamples);
 
         // Classify all the dpiFound (could be 0)
         DpiCounter counter = new DpiCounter();
 
-        for (int pageNum : pagesToTest) {
+        for (int pageNum = 0; pageNum < nbSamples; pageNum++) {
           DimensionInfo dimPage = pageDimensions.get(pageNum);
           DimensionInfo dimImage = imageDimensions.get(pageNum);
           LOGGER.fine("Page [" + pageNum + "] dimension " + dimImage);
@@ -151,5 +160,14 @@ protected int parsePage(PDPage page, int numPage) throws IOException {
       }
       return nbImagesInPage;
     }
+
+    public static boolean isScan(File file, int samples) throws IOException {
+      FileDescriptor fileDescriptor = new FileDescriptor(file);
+
+      StrictPdfBoxScanDetector strictPdfBoxScanDetector = new StrictPdfBoxScanDetector(samples);
+      strictPdfBoxScanDetector.init(fileDescriptor);
+      strictPdfBoxScanDetector.parse();
+      return fileDescriptor.isScan();
+    }
   }