TIKA-2579 and TIKA-2607: Upgrade PDFBox to 2.0.9 and include new jbi…

…g2-imageio from org.apache.pdfbox
apache · Mar 28, 2018 · ee9e4f4 · ee9e4f4
1 parent 682c38d
commit ee9e4f4
Show file tree

Hide file tree

Showing 4 changed files with 12 additions and 25 deletions.
diff --git a/CHANGES.txt b/CHANGES.txt
@@ -4,7 +4,9 @@ Release 2.0.0 - ???
    * Remove deprecated Metadata keys/properties (TIKA-1974).
 
    Other changes
-
+   * Upgrade PDFBox to 2.0.9 and include new jbig2-imageio
+     from org.apache.pdfbox (TIKA-2579 and TIKA-2607).
+
    * Support for TIFF images in PDF files (TIKA-2338)
 
    * Detection of full encrypted 7z files (TIKA-2568)

diff --git a/tika-parsers/pom.xml b/tika-parsers/pom.xml
@@ -42,7 +42,7 @@
     <tukaani.version>1.8</tukaani.version>
     <mime4j.version>0.8.1</mime4j.version>
     <vorbis.version>0.8</vorbis.version>
-    <pdfbox.version>2.0.8</pdfbox.version>
+    <pdfbox.version>2.0.9</pdfbox.version>
     <jempbox.version>1.8.13</jempbox.version>
     <netcdf-java.version>4.5.5</netcdf-java.version>
     <sis.version>0.8</sis.version>
@@ -679,18 +679,12 @@
       <artifactId>jackson-core</artifactId>
       <version>2.9.4</version>
     </dependency>
-
-    <!-- Java ImageIO plugin for JBIG2 support (often used in PDF)
-         This jbig2 dep is not distributed with Tika due to licensing
-         issue (GPLV3). That's why it is included here as "test".
-         https://github.com/levigo/jbig2-imageio
-      -->
     <dependency>
-      <groupId>com.levigo.jbig2</groupId>
-      <artifactId>levigo-jbig2-imageio</artifactId>
-      <version>1.6.5</version>
-      <scope>test</scope>
+      <groupId>org.apache.pdfbox</groupId>
+      <artifactId>jbig2-imageio</artifactId>
+      <version>3.0.0</version>
     </dependency>
+
     <!-- jai-imageio-core is allowed since LEGAL-304 -->
     <dependency>
       <groupId>com.github.jai-imageio</groupId>

diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/image/ImageParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/image/ImageParser.java
@@ -66,12 +66,10 @@ public class ImageParser extends AbstractParser {
                 MediaType.image("png"),
                 MediaType.image("vnd.wap.wbmp"),
                 MediaType.image("x-icon"),
-                MediaType.image("x-xcf")));
-        try {
-            Class.forName("com.levigo.jbig2.JBIG2ImageReader");
-            TMP_SUPPORTED.add(MediaType.image("x-jbig2"));
-        } catch (ClassNotFoundException e) {
-        }
+                MediaType.image("x-xcf"),
+                MediaType.image("x-jbig2")));
+        //add try/catch class.forName() for image types relying on
+        //provided dependencies
     }
 
     private static final Set<MediaType> SUPPORTED_TYPES =

diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
@@ -765,13 +765,6 @@ public void checkInitialization(InitializableProblemHandler handler) throws Tika
                 return;
             }
             StringBuilder sb = new StringBuilder();
-            try {
-                Class.forName("com.levigo.jbig2.JBIG2ImageReader");
-            } catch (ClassNotFoundException e) {
-                sb.append("JBIG2ImageReader not loaded. jbig2 files will be ignored\n");
-                sb.append("See https://pdfbox.apache.org/2.0/dependencies.html#jai-image-io\n");
-                sb.append("for optional dependencies.\n");
-            }
             try {
                 Class.forName("com.github.jaiimageio.impl.plugins.tiff.TIFFImageWriter");
             } catch (ClassNotFoundException e) {