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 2017/03/10 20:34:39 UTC

[tika] branch master updated: TIKA-2295 -- extract images from ODT

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  65182ee   TIKA-2295 -- extract images from ODT
65182ee is described below

commit 65182ee39b4fcbea0ec4d96a651194b9751b6c9b
Author: tballison <ta...@mitre.org>
AuthorDate: Fri Mar 10 15:34:31 2017 -0500

    TIKA-2295 -- extract images from ODT
---
 CHANGES.txt                                        |   2 ++
 .../apache/tika/parser/odf/OpenDocumentParser.java |  28 +++++++++++++++++++++
 .../org/apache/tika/parser/odf/ODFParserTest.java  |   8 ++++++
 .../resources/test-documents/testODTEmbedded.odt   | Bin 0 -> 9936 bytes
 4 files changed, 38 insertions(+)

diff --git a/CHANGES.txt b/CHANGES.txt
index ec55287..383ef65 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -1,5 +1,7 @@
 Release 1.15 - ??
 
+  * Extract images and thumbnails from ODT via Sam Bayer (TIKA-2295).
+
   * Enabled configuration of the EncodingDetector used by
     parsers that extend AbstractEncodingDetectorParser (TIKA-2273).
 
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java
index 00145d2..e7eb76a 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java
@@ -31,12 +31,17 @@ import java.util.zip.ZipInputStream;
 
 import org.apache.commons.io.IOUtils;
 import org.apache.tika.exception.TikaException;
+import org.apache.tika.extractor.EmbeddedDocumentExtractor;
+import org.apache.tika.extractor.EmbeddedDocumentUtil;
 import org.apache.tika.io.TikaInputStream;
 import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
+import org.apache.tika.metadata.TikaMetadataKeys;
 import org.apache.tika.mime.MediaType;
 import org.apache.tika.parser.AbstractParser;
 import org.apache.tika.parser.ParseContext;
 import org.apache.tika.parser.Parser;
+import org.apache.tika.sax.EmbeddedContentHandler;
 import org.apache.tika.sax.EndDocumentShieldingContentHandler;
 import org.apache.tika.sax.XHTMLContentHandler;
 import org.xml.sax.ContentHandler;
@@ -220,6 +225,29 @@ public class OpenDocumentParser extends AbstractParser {
                 // Foreign content parser was set:
                 content.parse(zip, handler, metadata, context);
             }
+        } else {
+            String embeddedName = entry.getName();
+            //scrape everything under Thumbnails/ and Pictures/
+            if (embeddedName.contains("Thumbnails/") ||
+                    embeddedName.contains("Pictures/")) {
+                EmbeddedDocumentExtractor embeddedDocumentExtractor =
+                        EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
+                Metadata embeddedMetadata = new Metadata();
+                embeddedMetadata.set(TikaCoreProperties.ORIGINAL_RESOURCE_NAME, entry.getName());
+                /* if (embeddedName.startsWith("Thumbnails/")) {
+                    embeddedMetadata.set(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
+                            TikaCoreProperties.EmbeddedResourceType.THUMBNAIL);
+                }*/
+                if (embeddedName.contains("Pictures/")) {
+                    embeddedMetadata.set(TikaMetadataKeys.EMBEDDED_RESOURCE_TYPE,
+                            TikaCoreProperties.EmbeddedResourceType.INLINE.toString());
+                }
+                if (embeddedDocumentExtractor.shouldParseEmbedded(embeddedMetadata)) {
+                    embeddedDocumentExtractor.parseEmbedded(zip,
+                            new EmbeddedContentHandler(handler), embeddedMetadata, false);
+                }
+            }
+
         }
     }
 }
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/odf/ODFParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/odf/ODFParserTest.java
index f9fe636..40b1168 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/odf/ODFParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/odf/ODFParserTest.java
@@ -20,6 +20,7 @@ import static org.junit.Assert.assertEquals;
 import static org.junit.Assert.assertTrue;
 
 import java.io.InputStream;
+import java.util.List;
 
 import org.apache.tika.TikaTest;
 import org.apache.tika.io.TikaInputStream;
@@ -398,4 +399,11 @@ public class ODFParserTest extends TikaTest {
         System.out.println(xml);
         assertContains("<p><b>WOUTERS Rolf</b><span class=\"annotation\"> Beschermde persoon is overleden </annotation>", xml);
     }
+
+    @Test
+    public void testEmbedded() throws Exception {
+        List<Metadata> metadataList = getRecursiveMetadata("testODTEmbedded.odt");
+        assertEquals(3, metadataList.size());
+    }
+    
 }
diff --git a/tika-parsers/src/test/resources/test-documents/testODTEmbedded.odt b/tika-parsers/src/test/resources/test-documents/testODTEmbedded.odt
new file mode 100644
index 0000000..b74ad72
Binary files /dev/null and b/tika-parsers/src/test/resources/test-documents/testODTEmbedded.odt differ

-- 
To stop receiving notification emails like this one, please contact
['"commits@tika.apache.org" <co...@tika.apache.org>'].