TIKA-2354 -- .doc is missing many pictures
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.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 @@
*/
private boolean isRendered(final CharacterRun cr) {
if (cr == null) {
- return false;
+ return true;
}
return !cr.isMarkedDeleted() ||
(cr.isMarkedDeleted() && extractDeletedContent);
