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 2011/09/21 20:04:39 UTC

svn commit: r1173775 - in /tika/trunk/tika-parsers/src/test: java/org/apache/tika/parser/microsoft/ java/org/apache/tika/parser/microsoft/ooxml/ resources/test-documents/

Author: mikemccand
Date: Wed Sep 21 18:04:38 2011
New Revision: 1173775

URL: http://svn.apache.org/viewvc?rev=1173775&view=rev
Log:
TIKA-712: master slide's text is now extracted

Added:
    tika/trunk/tika-parsers/src/test/resources/test-documents/testPPT_masterFooter.ppt   (with props)
    tika/trunk/tika-parsers/src/test/resources/test-documents/testPPT_masterFooter.pptx   (with props)
Modified:
    tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
    tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java

Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java?rev=1173775&r1=1173774&r2=1173775&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java Wed Sep 21 18:04:38 2011
@@ -114,4 +114,20 @@ public class PowerPointParserTest extend
         assertContains("And then some Gothic text:", content);
         assertContains("\uD800\uDF32\uD800\uDF3f\uD800\uDF44\uD800\uDF39\uD800\uDF43\uD800\uDF3A", content);
     }
+
+    public void testMasterSlide() throws Exception {
+        ContentHandler handler = new BodyContentHandler();
+        Metadata metadata = new Metadata();
+
+        InputStream stream = PowerPointParserTest.class.getResourceAsStream(
+                "/test-documents/testPPT_masterFooter.ppt");
+        try {
+            new OfficeParser().parse(stream, handler, metadata, new ParseContext());
+        } finally {
+            stream.close();
+        }
+
+        String content = handler.toString();
+        assertContains("Master footer is here", content);
+    }
 }

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=1173775&r1=1173774&r2=1173775&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 Wed Sep 21 18:04:38 2011
@@ -616,4 +616,21 @@ public class OOXMLParserTest extends Tik
         assertContains("And then some Gothic text:", content);
         assertContains("\uD800\uDF32\uD800\uDF3f\uD800\uDF44\uD800\uDF39\uD800\uDF43\uD800\uDF3A", content);
     }
+
+
+    public void testMasterSlide() throws Exception {
+        ContentHandler handler = new BodyContentHandler();
+        Metadata metadata = new Metadata();
+
+        InputStream stream = OOXMLParserTest.class.getResourceAsStream(
+                "/test-documents/testPPT_masterFooter.pptx");
+        try {
+            new AutoDetectParser().parse(stream, handler, metadata, new ParseContext());
+        } finally {
+            stream.close();
+        }
+
+        String content = handler.toString();
+        assertContains("Master footer is here", content);
+    }
 }

Added: tika/trunk/tika-parsers/src/test/resources/test-documents/testPPT_masterFooter.ppt
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/resources/test-documents/testPPT_masterFooter.ppt?rev=1173775&view=auto
==============================================================================
Binary file - no diff available.

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

Added: tika/trunk/tika-parsers/src/test/resources/test-documents/testPPT_masterFooter.pptx
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/resources/test-documents/testPPT_masterFooter.pptx?rev=1173775&view=auto
==============================================================================
Binary file - no diff available.

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