Return-Path: X-Original-To: apmail-tika-commits-archive@www.apache.org Delivered-To: apmail-tika-commits-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 219429EBF for ; Tue, 20 Dec 2011 06:00:31 +0000 (UTC) Received: (qmail 88651 invoked by uid 500); 20 Dec 2011 06:00:30 -0000 Delivered-To: apmail-tika-commits-archive@tika.apache.org Received: (qmail 88499 invoked by uid 500); 20 Dec 2011 06:00:23 -0000 Mailing-List: contact commits-help@tika.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@tika.apache.org Delivered-To: mailing list commits@tika.apache.org Received: (qmail 88484 invoked by uid 99); 20 Dec 2011 06:00:20 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Tue, 20 Dec 2011 06:00:20 +0000 X-ASF-Spam-Status: No, hits=-2000.0 required=5.0 tests=ALL_TRUSTED X-Spam-Check-By: apache.org Received: from [140.211.11.4] (HELO eris.apache.org) (140.211.11.4) by apache.org (qpsmtpd/0.29) with ESMTP; Tue, 20 Dec 2011 06:00:18 +0000 Received: from eris.apache.org (localhost [127.0.0.1]) by eris.apache.org (Postfix) with ESMTP id 58BAF238899C; Tue, 20 Dec 2011 05:59:58 +0000 (UTC) Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: svn commit: r1221109 - in /tika/trunk/tika-parsers: pom.xml src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java Date: Tue, 20 Dec 2011 05:59:58 -0000 To: commits@tika.apache.org From: nick@apache.org X-Mailer: svnmailer-1.0.8-patched Message-Id: <20111220055958.58BAF238899C@eris.apache.org> Author: nick Date: Tue Dec 20 05:59:57 2011 New Revision: 1221109 URL: http://svn.apache.org/viewvc?rev=1221109&view=rev Log: TIKA-700 Upgrade to POI 3.8 beta 5 Modified: tika/trunk/tika-parsers/pom.xml tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java Modified: tika/trunk/tika-parsers/pom.xml URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/pom.xml?rev=1221109&r1=1221108&r2=1221109&view=diff ============================================================================== --- tika/trunk/tika-parsers/pom.xml (original) +++ tika/trunk/tika-parsers/pom.xml Tue Dec 20 05:59:57 2011 @@ -35,7 +35,7 @@ http://tika.apache.org/ - 3.8-beta4 + 3.8-beta5 1.5 0.7 Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java?rev=1221109&r1=1221108&r2=1221109&view=diff ============================================================================== --- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java (original) +++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java Tue Dec 20 05:59:57 2011 @@ -78,7 +78,7 @@ public class XSLFPowerPointExtractorDeco continue; } - XSLFSlideMaster master = slide.getMasterSheet(); + XSLFSlideMaster master = slide.getSlideMaster(); CTNotesSlide notes = rawSlideShow.getNotes(slideId); CTCommentList comments = rawSlideShow.getSlideComments(slideId); Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java?rev=1221109&r1=1221108&r2=1221109&view=diff ============================================================================== --- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java (original) +++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java Tue Dec 20 05:59:57 2011 @@ -169,23 +169,23 @@ public class POIContainerExtractionTest // Filenames are a bit iffy... // Should really be 3*embedded pictures then 3*icons then embedded docs - assertEquals("image1", handler.filenames.get(0)); + assertEquals("image1.emf", handler.filenames.get(0)); assertEquals("image4.png", handler.filenames.get(1)); assertEquals("image5.jpg", handler.filenames.get(2)); assertEquals("image6.png", handler.filenames.get(3)); - assertEquals("image2", handler.filenames.get(4)); - assertEquals("image3", handler.filenames.get(5)); + assertEquals("image2.emf", handler.filenames.get(4)); + assertEquals("image3.emf", handler.filenames.get(5)); assertEquals(null, handler.filenames.get(6)); assertEquals("_1345471035.ppt", handler.filenames.get(7)); assertEquals("_1345470949.xls", handler.filenames.get(8)); // But we do know their types - assertEquals(MediaType.parse("image/unknown"), handler.mediaTypes.get(0)); // Icon of embedded office doc? + assertEquals(TYPE_EMF, handler.mediaTypes.get(0)); // Icon of embedded office doc? assertEquals(TYPE_PNG, handler.mediaTypes.get(1)); // Embedded image - logo assertEquals(TYPE_JPG, handler.mediaTypes.get(2)); // Embedded image - safe assertEquals(TYPE_PNG, handler.mediaTypes.get(3)); // Embedded image - try - assertEquals(MediaType.parse("image/unknown"), handler.mediaTypes.get(4)); // Icon of embedded office doc? - assertEquals(MediaType.parse("image/unknown"), handler.mediaTypes.get(5)); // Icon of embedded office doc? + assertEquals(TYPE_EMF, handler.mediaTypes.get(4)); // Icon of embedded office doc? + assertEquals(TYPE_EMF, handler.mediaTypes.get(5)); // Icon of embedded office doc? assertEquals(TYPE_DOCX, handler.mediaTypes.get(6)); // Embedded office doc assertEquals(TYPE_PPT, handler.mediaTypes.get(7)); // Embedded office doc assertEquals(TYPE_XLS, handler.mediaTypes.get(8)); // Embedded office doc @@ -197,12 +197,12 @@ public class POIContainerExtractionTest assertEquals(13, handler.mediaTypes.size()); // We don't know their filenames, except for doc images + docx - assertEquals("image1", handler.filenames.get(0)); + assertEquals("image1.emf", handler.filenames.get(0)); assertEquals("image4.png", handler.filenames.get(1)); assertEquals("image5.jpg", handler.filenames.get(2)); assertEquals("image6.png", handler.filenames.get(3)); - assertEquals("image2", handler.filenames.get(4)); - assertEquals("image3", handler.filenames.get(5)); + assertEquals("image2.emf", handler.filenames.get(4)); + assertEquals("image3.emf", handler.filenames.get(5)); assertEquals(null, handler.filenames.get(6)); assertEquals("image2.png", handler.filenames.get(7)); assertEquals("image3.jpeg", handler.filenames.get(8)); @@ -211,12 +211,12 @@ public class POIContainerExtractionTest assertNull(handler.filenames.get(i)); } // But we do know their types - assertEquals(MediaType.parse("image/unknown"), handler.mediaTypes.get(0)); // Icon of embedded office doc? + assertEquals(TYPE_EMF, handler.mediaTypes.get(0)); // Icon of embedded office doc assertEquals(TYPE_PNG, handler.mediaTypes.get(1)); // Embedded image - logo assertEquals(TYPE_JPG, handler.mediaTypes.get(2)); // Embedded image - safe assertEquals(TYPE_PNG, handler.mediaTypes.get(3)); // Embedded image - try - assertEquals(MediaType.parse("image/unknown"), handler.mediaTypes.get(4)); // Icon of embedded office doc? - assertEquals(MediaType.parse("image/unknown"), handler.mediaTypes.get(5)); // Icon of embedded office doc? + assertEquals(TYPE_EMF, handler.mediaTypes.get(4)); // Icon of embedded office doc + assertEquals(TYPE_EMF, handler.mediaTypes.get(5)); // Icon of embedded office doc assertEquals(TYPE_DOCX, handler.mediaTypes.get(6)); // Embedded office doc assertEquals(TYPE_PNG, handler.mediaTypes.get(7)); // PNG inside .docx assertEquals(TYPE_JPG, handler.mediaTypes.get(8)); // JPG inside .docx