You are viewing a plain text version of this content. The canonical link for it is here.
Posted to solr-commits@lucene.apache.org by gs...@apache.org on 2009/11/22 17:18:52 UTC

svn commit: r883095 - in /lucene/solr/trunk/contrib/extraction: ./ lib/ src/main/java/org/apache/solr/handler/extraction/

Author: gsingers
Date: Sun Nov 22 16:18:49 2009
New Revision: 883095

URL: http://svn.apache.org/viewvc?rev=883095&view=rev
Log:
SOLR-1567: Upgrade to Tika 0.5

Added:
    lucene/solr/trunk/contrib/extraction/lib/asm-3.1.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/commons-compress-1.0.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/commons-logging-1.1.1.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/dom4j-1.6.1.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/fontbox-0.8.0-incubator.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/geronimo-stax-api_1.0_spec-1.0.1.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/jempbox-0.8.0-incubator.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/log4j-1.2.14.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/metadata-extractor-2.4.0-beta-1.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/ooxml-schemas-1.0.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/pdfbox-0.8.0-incubating.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/poi-3.5-FINAL.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/poi-ooxml-3.5-FINAL.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/poi-scratchpad-3.5-FINAL.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/tagsoup-1.2.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/tika-core-0.5.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/tika-parsers-0.5.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/xml-apis-1.0.b2.jar   (with props)
    lucene/solr/trunk/contrib/extraction/lib/xmlbeans-2.3.0.jar   (with props)
Removed:
    lucene/solr/trunk/contrib/extraction/lib/bcmail-jdk14-136.jar
    lucene/solr/trunk/contrib/extraction/lib/bcprov-jdk14-136.jar
    lucene/solr/trunk/contrib/extraction/lib/commons-codec-1.3.jar
    lucene/solr/trunk/contrib/extraction/lib/commons-io-1.4.jar
    lucene/solr/trunk/contrib/extraction/lib/commons-lang-2.1.jar
    lucene/solr/trunk/contrib/extraction/lib/fontbox-0.1.0.jar
    lucene/solr/trunk/contrib/extraction/lib/geronimo-stax-api_1.0_spec-1.0.jar
    lucene/solr/trunk/contrib/extraction/lib/icu4j-3.8.jar
    lucene/solr/trunk/contrib/extraction/lib/jempbox-0.2.0.jar
    lucene/solr/trunk/contrib/extraction/lib/nekohtml-1.9.9.jar
    lucene/solr/trunk/contrib/extraction/lib/pdfbox-0.7.3.jar
    lucene/solr/trunk/contrib/extraction/lib/poi-3.5-beta6.jar
    lucene/solr/trunk/contrib/extraction/lib/poi-ooxml-3.5-beta6.jar
    lucene/solr/trunk/contrib/extraction/lib/poi-scratchpad-3.5-beta6.jar
    lucene/solr/trunk/contrib/extraction/lib/tika-core-0.4.jar
    lucene/solr/trunk/contrib/extraction/lib/tika-parsers-0.4.jar
Modified:
    lucene/solr/trunk/contrib/extraction/CHANGES.txt
    lucene/solr/trunk/contrib/extraction/src/main/java/org/apache/solr/handler/extraction/ExtractingRequestHandler.java

Modified: lucene/solr/trunk/contrib/extraction/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/CHANGES.txt?rev=883095&r1=883094&r2=883095&view=diff
==============================================================================
--- lucene/solr/trunk/contrib/extraction/CHANGES.txt (original)
+++ lucene/solr/trunk/contrib/extraction/CHANGES.txt Sun Nov 22 16:18:49 2009
@@ -17,8 +17,12 @@
 to your Solr Home lib directory.  See http://wiki.apache.org/solr/ExtractingRequestHandler for more details on hooking it in
  and configuring.
 
-
 $Id:$
+
+================== Release 1.5-dev ==================
+
+* SOLR-1567: Upgrade to Tika 0.5, which upgrades many of the underlying libraries (PDFBox, for example) too (gsingers)
+
 ================== Release 1.4.0 ==================
 
 1. SOLR-284:  Added in support for extraction. (Eric Pugh, Chris Harris, gsingers)
@@ -34,4 +38,4 @@
     for discussion on language detection.
     See http://www.apache.org/dist/lucene/tika/CHANGES-0.4.txt. (gsingers)
 
-6. SOLR-1274: Added text serialization output for extractOnly (Peter Wolanin, gsingers)    
\ No newline at end of file
+6. SOLR-1274: Added text serialization output for extractOnly (Peter Wolanin, gsingers)    

Added: lucene/solr/trunk/contrib/extraction/lib/asm-3.1.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/asm-3.1.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/asm-3.1.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/commons-compress-1.0.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/commons-compress-1.0.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/commons-compress-1.0.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/commons-logging-1.1.1.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/commons-logging-1.1.1.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/commons-logging-1.1.1.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/dom4j-1.6.1.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/dom4j-1.6.1.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/dom4j-1.6.1.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/fontbox-0.8.0-incubator.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/fontbox-0.8.0-incubator.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/fontbox-0.8.0-incubator.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/geronimo-stax-api_1.0_spec-1.0.1.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/geronimo-stax-api_1.0_spec-1.0.1.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/geronimo-stax-api_1.0_spec-1.0.1.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/jempbox-0.8.0-incubator.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/jempbox-0.8.0-incubator.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/jempbox-0.8.0-incubator.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/log4j-1.2.14.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/log4j-1.2.14.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/log4j-1.2.14.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/metadata-extractor-2.4.0-beta-1.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/metadata-extractor-2.4.0-beta-1.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/metadata-extractor-2.4.0-beta-1.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/ooxml-schemas-1.0.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/ooxml-schemas-1.0.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/ooxml-schemas-1.0.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/pdfbox-0.8.0-incubating.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/pdfbox-0.8.0-incubating.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/pdfbox-0.8.0-incubating.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/poi-3.5-FINAL.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/poi-3.5-FINAL.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/poi-3.5-FINAL.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/poi-ooxml-3.5-FINAL.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/poi-ooxml-3.5-FINAL.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/poi-ooxml-3.5-FINAL.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/poi-scratchpad-3.5-FINAL.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/poi-scratchpad-3.5-FINAL.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/poi-scratchpad-3.5-FINAL.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/tagsoup-1.2.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/tagsoup-1.2.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/tagsoup-1.2.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/tika-core-0.5.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/tika-core-0.5.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/tika-core-0.5.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/tika-parsers-0.5.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/tika-parsers-0.5.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/tika-parsers-0.5.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/xml-apis-1.0.b2.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/xml-apis-1.0.b2.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/xml-apis-1.0.b2.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: lucene/solr/trunk/contrib/extraction/lib/xmlbeans-2.3.0.jar
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/lib/xmlbeans-2.3.0.jar?rev=883095&view=auto
==============================================================================
Binary file - no diff available.

Propchange: lucene/solr/trunk/contrib/extraction/lib/xmlbeans-2.3.0.jar
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Modified: lucene/solr/trunk/contrib/extraction/src/main/java/org/apache/solr/handler/extraction/ExtractingRequestHandler.java
URL: http://svn.apache.org/viewvc/lucene/solr/trunk/contrib/extraction/src/main/java/org/apache/solr/handler/extraction/ExtractingRequestHandler.java?rev=883095&r1=883094&r2=883095&view=diff
==============================================================================
--- lucene/solr/trunk/contrib/extraction/src/main/java/org/apache/solr/handler/extraction/ExtractingRequestHandler.java (original)
+++ lucene/solr/trunk/contrib/extraction/src/main/java/org/apache/solr/handler/extraction/ExtractingRequestHandler.java Sun Nov 22 16:18:49 2009
@@ -76,11 +76,7 @@
           throw new SolrException(ErrorCode.SERVER_ERROR, e);
         }
       } else {
-        try {
-          config = TikaConfig.getDefaultConfig();
-        } catch (TikaException e) {
-          throw new SolrException(ErrorCode.SERVER_ERROR, e);
-        }
+        config = TikaConfig.getDefaultConfig();
       }
       NamedList configDateFormats = (NamedList) initArgs.get(DATE_FORMATS);
       if (configDateFormats != null && configDateFormats.size() > 0) {
@@ -92,11 +88,7 @@
         }
       }
     } else {
-      try {
-        config = TikaConfig.getDefaultConfig();
-      } catch (TikaException e) {
-        throw new SolrException(ErrorCode.SERVER_ERROR, e);
-      }
+      config = TikaConfig.getDefaultConfig();
     }
     factory = createFactory();
   }