This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch 2.x
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/2.x by this push:
new 0a55b4a TIKA-2354 -- .doc is missing many pictures
0a55b4a is described below
commit 0a55b4a4e29f94e3eec29889117ac2445a9d3577
Author: tballison <[email protected]>
AuthorDate: Wed May 3 22:32:22 2017 -0400
TIKA-2354 -- .doc is missing many pictures
---
.../main/java/org/apache/tika/parser/microsoft/WordExtractor.java | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git
a/tika-parser-modules/tika-parser-office-module/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java
b/tika-parser-modules/tika-parser-office-module/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java
index ad4c16c..42ea44b 100644
---
a/tika-parser-modules/tika-parser-office-module/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java
+++
b/tika-parser-modules/tika-parser-office-module/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java
@@ -16,8 +16,6 @@
*/
package org.apache.tika.parser.microsoft;
-import static java.nio.charset.StandardCharsets.UTF_8;
-
import java.io.FileNotFoundException;
import java.io.IOException;
import java.util.ArrayList;
@@ -60,6 +58,8 @@ import org.apache.tika.sax.XHTMLContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.AttributesImpl;
+import static java.nio.charset.StandardCharsets.UTF_8;
+
public class WordExtractor extends AbstractPOIFSExtractor {
private static final char UNICODECHAR_NONBREAKING_HYPHEN = '\u2011';
@@ -665,7 +665,7 @@ public class WordExtractor extends AbstractPOIFSExtractor {
*/
private boolean isRendered(final CharacterRun cr) {
if (cr == null) {
- return false;
+ return true;
}
return !cr.isMarkedDeleted() ||
(cr.isMarkedDeleted() && extractDeletedContent);
--
To stop receiving notification emails like this one, please contact
['"[email protected]" <[email protected]>'].
