You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ma...@apache.org on 2013/03/23 02:45:58 UTC

svn commit: r1460073 - in /tika/trunk: CHANGES.txt tika-parsers/pom.xml tika-parsers/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java

Author: mattmann
Date: Sat Mar 23 01:45:57 2013
New Revision: 1460073

URL: http://svn.apache.org/r1460073
Log:
Patch for TIKA-1096 CompressorParser: Add support for handling concatenated InputStreams contributed by Gregory Canan.

Modified:
    tika/trunk/CHANGES.txt
    tika/trunk/tika-parsers/pom.xml
    tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java

Modified: tika/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/tika/trunk/CHANGES.txt?rev=1460073&r1=1460072&r2=1460073&view=diff
==============================================================================
--- tika/trunk/CHANGES.txt (original)
+++ tika/trunk/CHANGES.txt Sat Mar 23 01:45:57 2013
@@ -1,5 +1,8 @@
 Release 1.4 Current Development
 
+  * Improvements were made to the Compressor Parser to handle g'zipped files
+    that require the decompressConcatenated option set to true (TIKA-1096).
+
   * Addressed a typographic error that was preventing from detection of 
     awk files (TIKA-1081).
 

Modified: tika/trunk/tika-parsers/pom.xml
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/pom.xml?rev=1460073&r1=1460072&r2=1460073&view=diff
==============================================================================
--- tika/trunk/tika-parsers/pom.xml (original)
+++ tika/trunk/tika-parsers/pom.xml Sat Mar 23 01:45:57 2013
@@ -90,7 +90,7 @@
     <dependency>
       <groupId>org.apache.commons</groupId>
       <artifactId>commons-compress</artifactId>
-      <version>1.4.1</version>
+      <version>1.5</version>
     </dependency>
     <dependency>
       <groupId>commons-codec</groupId>

Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java?rev=1460073&r1=1460072&r2=1460073&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java Sat Mar 23 01:45:57 2013
@@ -93,6 +93,13 @@ public class CompressorParser extends Ab
         CompressorInputStream cis;
         try {
             CompressorStreamFactory factory = new CompressorStreamFactory();
+            CompressorParserOptions options =
+                 context.get(CompressorParserOptions.class, new CompressorParserOptions() {
+                     public boolean decompressConcatenated(Metadata metadata) {
+                         return false;
+                     }
+                 });
+            factory.setDecompressConcatenated(options.decompressConcatenated(metadata));
             cis = factory.createCompressorInputStream(stream);
         } catch (CompressorException e) {
             throw new TikaException("Unable to uncompress document stream", e);