You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2017/11/27 18:02:52 UTC
[tika] branch master updated: TIKA-2510 -- Extract media files from
ooxml
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/master by this push:
new d4fd659 TIKA-2510 -- Extract media files from ooxml
d4fd659 is described below
commit d4fd659ac5c3070104a85df4a535afe570b08a0e
Author: tballison <ta...@mitre.org>
AuthorDate: Mon Nov 27 13:02:34 2017 -0500
TIKA-2510 -- Extract media files from ooxml
---
CHANGES.txt | 2 ++
.../parser/microsoft/ooxml/AbstractOOXMLExtractor.java | 7 ++++++-
.../tika/parser/microsoft/ooxml/OOXMLParserTest.java | 10 ++++++++++
.../tika/parser/microsoft/ooxml/SXSLFExtractorTest.java | 11 +++++++++++
.../resources/test-documents/testPPT_embeddedMP3.pptx | Bin 0 -> 84434 bytes
5 files changed, 29 insertions(+), 1 deletion(-)
diff --git a/CHANGES.txt b/CHANGES.txt
index a1af97e..8c74689 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -1,5 +1,7 @@
Release 1.17 - ???
+ * Extract media files from ooxml (TIKA-2510).
+
* Standardize the way the Image and Video captioning
dockers and extraction work (TIKA-2400, GitHub-208)
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
index 4e1bfd6..327422e 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
@@ -78,6 +78,8 @@ public abstract class AbstractOOXMLExtractor implements OOXMLExtractor {
static final String RELATION_AUDIO = "http://schemas.openxmlformats.org/officeDocument/2006/relationships/audio";
+ static final String RELATION_MEDIA = "http://schemas.microsoft.com/office/2007/relationships/media";
+ static final String RELATION_VIDEO = "http://schemas.openxmlformats.org/officeDocument/2006/relationships/video";
static final String RELATION_DIAGRAM_DATA = "http://schemas.openxmlformats.org/officeDocument/2006/relationships/diagramData";
private static final String TYPE_OLE_OBJECT =
@@ -247,7 +249,10 @@ public abstract class AbstractOOXMLExtractor implements OOXMLExtractor {
if (POIXMLDocument.OLE_OBJECT_REL_TYPE.equals(type)
&& TYPE_OLE_OBJECT.equals(target.getContentType())) {
handleEmbeddedOLE(target, handler, sourceDesc + rel.getId(), parentMetadata);
- } else if (RELATION_AUDIO.equals(type)
+ } else if (
+ RELATION_MEDIA.equals(type)
+ || RELATION_VIDEO.equals(type)
+ || RELATION_AUDIO.equals(type)
|| PackageRelationshipTypes.IMAGE_PART.equals(type)
|| POIXMLDocument.PACK_OBJECT_REL_TYPE.equals(type)
|| POIXMLDocument.OLE_OBJECT_REL_TYPE.equals(type)) {
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
index 7dc455f..e45ee2a 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
@@ -1773,6 +1773,16 @@ public class OOXMLParserTest extends TikaTest {
assertNotContained("\u3068", xml);
}
+ @Test
+ public void testEmbeddedMedia() throws Exception {
+ List<Metadata> metadataList = getRecursiveMetadata("testPPT_embeddedMP3.pptx");
+ assertEquals(4, metadataList.size());
+ assertEquals("application/vnd.openxmlformats-officedocument.presentationml.presentation",
+ metadataList.get(0).get(Metadata.CONTENT_TYPE));
+ assertEquals("audio/mpeg", metadataList.get(1).get(Metadata.CONTENT_TYPE));
+ assertEquals("image/png", metadataList.get(2).get(Metadata.CONTENT_TYPE));
+ assertEquals("image/jpeg", metadataList.get(3).get(Metadata.CONTENT_TYPE));
+ }
}
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXSLFExtractorTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXSLFExtractorTest.java
index cad4913..8385263 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXSLFExtractorTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXSLFExtractorTest.java
@@ -580,4 +580,15 @@ public class SXSLFExtractorTest extends TikaTest {
assertNotContained("chartSpace", xml);
}
+ @Test
+ public void testEmbeddedMedia() throws Exception {
+ List<Metadata> metadataList = getRecursiveMetadata("testPPT_embeddedMP3.pptx", parseContext);
+ assertEquals(4, metadataList.size());
+ assertEquals("application/vnd.openxmlformats-officedocument.presentationml.presentation",
+ metadataList.get(0).get(Metadata.CONTENT_TYPE));
+ assertEquals("audio/mpeg", metadataList.get(1).get(Metadata.CONTENT_TYPE));
+ assertEquals("image/png", metadataList.get(2).get(Metadata.CONTENT_TYPE));
+ assertEquals("image/jpeg", metadataList.get(3).get(Metadata.CONTENT_TYPE));
+
+ }
}
diff --git a/tika-parsers/src/test/resources/test-documents/testPPT_embeddedMP3.pptx b/tika-parsers/src/test/resources/test-documents/testPPT_embeddedMP3.pptx
new file mode 100644
index 0000000..4a16900
Binary files /dev/null and b/tika-parsers/src/test/resources/test-documents/testPPT_embeddedMP3.pptx differ
--
To stop receiving notification emails like this one, please contact
['"commits@tika.apache.org" <co...@tika.apache.org>'].