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 2022/03/10 19:58:30 UTC
[tika] branch main updated: TIKA-3698 -- duplicate metadata keys for subject+description in Outlook msg files.
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/main by this push:
new a0b8e09 TIKA-3698 -- duplicate metadata keys for subject+description in Outlook msg files.
a0b8e09 is described below
commit a0b8e09b37241704ed5c422dedfd6bf6403f8581
Author: tallison <ta...@apache.org>
AuthorDate: Thu Mar 10 14:57:14 2022 -0500
TIKA-3698 -- duplicate metadata keys for subject+description in Outlook msg files.
---
.../main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java | 2 +-
.../test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java | 4 ++++
2 files changed, 5 insertions(+), 1 deletion(-)
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java
index 99462d8..ef7f16f 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java
@@ -181,7 +181,7 @@ public class OutlookExtractor extends AbstractPOIFSExtractor {
handleFromTo(headers, metadata);
metadata.set(TikaCoreProperties.TITLE, subject);
- // TODO: Move to description in Tika 2.0
+ metadata.set(TikaCoreProperties.SUBJECT, msg.getConversationTopic());
metadata.set(TikaCoreProperties.DESCRIPTION, msg.getConversationTopic());
try {
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java
index 1863c74..5b8a719 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java
@@ -146,6 +146,10 @@ public class OutlookParserTest extends TikaTest {
assertEquals("application/vnd.ms-outlook", metadata.get(Metadata.CONTENT_TYPE));
assertEquals("Welcome to Microsoft Office Outlook 2003",
metadata.get(TikaCoreProperties.TITLE));
+ assertEquals("Welcome to Microsoft Office Outlook 2003",
+ metadata.get(TikaCoreProperties.SUBJECT));
+ assertEquals("Welcome to Microsoft Office Outlook 2003",
+ metadata.get(TikaCoreProperties.DESCRIPTION));
String content = handler.toString();
assertContains("Outlook 2003", content);