You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by mi...@apache.org on 2012/10/12 19:23:26 UTC

svn commit: r1397653 - in /tika/trunk: ./ tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/ tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/ tika-parsers/src/test/resources/test-documents/

Author: mikemccand
Date: Fri Oct 12 17:23:25 2012
New Revision: 1397653

URL: http://svn.apache.org/viewvc?rev=1397653&view=rev
Log:
TIKA-1006: don't NPE if style is null

Added:
    tika/trunk/tika-parsers/src/test/resources/test-documents/testWORD_null_style.docx   (with props)
Modified:
    tika/trunk/CHANGES.txt
    tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
    tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java

Modified: tika/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/tika/trunk/CHANGES.txt?rev=1397653&r1=1397652&r2=1397653&view=diff
==============================================================================
--- tika/trunk/CHANGES.txt (original)
+++ tika/trunk/CHANGES.txt Fri Oct 12 17:23:25 2012
@@ -23,7 +23,8 @@ Release 1.3 - Current Development
     occurred.  The id (rId) is included in the Metadata of each
     embedded document as the new Metadata.EMBEDDED_RELATIONSHIP_ID
     key, and TikaCLI prepends the rId (if present) onto the filename
-    it extracts (TIKA-989).
+    it extracts (TIKA-989).  Fixed NullPointerException when style is
+    null (TIKA-1006).
 
   * RTF: Page, word, character count and creation date metadata are
     now extracted for RTF documents (TIKA-999).

Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java?rev=1397653&r1=1397652&r2=1397653&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java Fri Oct 12 17:23:25 2012
@@ -123,12 +123,14 @@ public class XWPFWordExtractorDecorator 
           XWPFStyle style = styles.getStyle(
                 paragraph.getStyleID()
           );
-          
-          TagAndStyle tas = WordExtractor.buildParagraphTagAndStyle(
-                style.getName(), paragraph.getPartType() == BodyType.TABLECELL
-          );
-          tag = tas.getTag();
-          styleClass = tas.getStyleClass();
+
+          if (style != null) {
+             TagAndStyle tas = WordExtractor.buildParagraphTagAndStyle(
+                   style.getName(), paragraph.getPartType() == BodyType.TABLECELL
+             );
+             tag = tas.getTag();
+             styleClass = tas.getStyleClass();
+          }
        }
        
        if(styleClass == null) {

Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java?rev=1397653&r1=1397652&r2=1397653&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java Fri Oct 12 17:23:25 2012
@@ -897,4 +897,10 @@ public class OOXMLParserTest extends Tik
         assertTrue(i < j);
         assertTrue(j < k);
     }
+  
+    // TIKA-1006
+    public void testWordNullStyle() throws Exception {
+      String xml = getXML("testWORD_null_style.docx").xml;        
+      assertContains("Test av styrt dokument", xml);
+    }
 }

Added: tika/trunk/tika-parsers/src/test/resources/test-documents/testWORD_null_style.docx
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/resources/test-documents/testWORD_null_style.docx?rev=1397653&view=auto
==============================================================================
Binary file - no diff available.

Propchange: tika/trunk/tika-parsers/src/test/resources/test-documents/testWORD_null_style.docx
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream