This is an automated email from the ASF dual-hosted git repository.
tilman pushed a commit to branch branch_3x
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/branch_3x by this push:
new 22ae36f8c0 TIKA-4704: add 4 TODOs on unsolved cases
22ae36f8c0 is described below
commit 22ae36f8c0b7b87154163b0e127475ef3c9d484f
Author: Tilman Hausherr <[email protected]>
AuthorDate: Mon Mar 30 16:37:33 2026 +0200
TIKA-4704: add 4 TODOs on unsolved cases
---
.../java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java | 4 ++++
1 file changed, 4 insertions(+)
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
index 8d8be04e57..60696cc877 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
@@ -817,6 +817,7 @@ public class OOXMLParserTest extends MultiThreadedTikaTest {
context.set(Locale.class, Locale.US);
new OOXMLParser().parse(input, handler, metadata, context);
}
+ //TODO temp file leak
assertEquals("application/vnd.openxmlformats-officedocument.wordprocessingml.document",
metadata.get(Metadata.CONTENT_TYPE));
@@ -851,6 +852,7 @@ public class OOXMLParserTest extends MultiThreadedTikaTest {
context.set(Locale.class, Locale.US);
new OOXMLParser().parse(input, handler, metadata, context);
}
+ //TODO temp file leak
assertEquals("application/vnd.openxmlformats-officedocument.presentationml.presentation",
metadata.get(Metadata.CONTENT_TYPE));
@@ -883,6 +885,7 @@ public class OOXMLParserTest extends MultiThreadedTikaTest {
"/test-documents/testWORD_embedded_pdf.docx")) {
new OOXMLParser().parse(input, handler, metadata, new
ParseContext());
}
+ //TODO tmp file leak
String xml = sw.toString();
int i = xml.indexOf("Here is the pdf file:");
int j = xml.indexOf("<div class=\"embedded\" id=\"rId5\"/>");
@@ -936,6 +939,7 @@ public class OOXMLParserTest extends MultiThreadedTikaTest {
try (InputStream stream =
getResourceAsStream("/test-documents/testWORD_no_format.docx")) {
new OOXMLParser().parse(stream, handler, metadata, new
ParseContext());
}
+ //TODO temp file leak
String content = handler.toString();
assertContains("This is a piece of text that causes an exception",
content);