You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2014/02/11 01:42:21 UTC

svn commit: r1566910 - /tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java

Author: tallison
Date: Tue Feb 11 00:42:21 2014
New Revision: 1566910

URL: http://svn.apache.org/r1566910
Log:
temporary fix to TIKA-1233. Added extra catch clause to catch PDFBOX-1803 related StringIndexOutOfBoundsException.  When PDFBOX-1803 is fixed, we should be able to remove these catches

Modified:
    tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java

Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java?rev=1566910&r1=1566909&r2=1566910&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java Tue Feb 11 00:42:21 2014
@@ -171,6 +171,9 @@ public class PDFParser extends AbstractP
             addMetadata(metadata, TikaCoreProperties.CREATED, info.getCreationDate());
         } catch (IOException e) {
             // Invalid date format, just ignore
+        } catch (StringIndexOutOfBoundsException e){
+            //remove after PDFBOX-1803 is fixed (TIKA-1233)
+            // Invalid date format, just ignore
         }
         try {
             Calendar modified = info.getModificationDate(); 
@@ -178,6 +181,9 @@ public class PDFParser extends AbstractP
             addMetadata(metadata, TikaCoreProperties.MODIFIED, modified);
         } catch (IOException e) {
             // Invalid date format, just ignore
+        } catch (StringIndexOutOfBoundsException e){
+            //remove after PDFBOX-1803 is fixed (TIKA-1233)
+            // Invalid date format, just ignore
         }
         
         // All remaining metadata is custom