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 2024/03/25 17:00:07 UTC
(tika) branch TIKA-4220-branch2x updated: TIKA-4220 -- temporary workaround for tar detection regression in commons-compress
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch TIKA-4220-branch2x
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/TIKA-4220-branch2x by this push:
new 01d97ea5a TIKA-4220 -- temporary workaround for tar detection regression in commons-compress
01d97ea5a is described below
commit 01d97ea5ab575295981661281ad43c1f1c8a8df7
Author: tallison <ta...@apache.org>
AuthorDate: Mon Mar 25 12:59:58 2024 -0400
TIKA-4220 -- temporary workaround for tar detection regression in commons-compress
---
.../main/java/org/apache/tika/parser/pkg/PackageParser.java | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/PackageParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/PackageParser.java
index f45fa23bd..2fc4af38e 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/PackageParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/PackageParser.java
@@ -253,6 +253,16 @@ public class PackageParser extends AbstractEncodingDetectorParser {
}
TemporaryResources tmp = new TemporaryResources();
+ try {
+ _parse(stream, handler, metadata, context, tmp);
+ } finally {
+ tmp.close();
+ }
+ }
+
+ private void _parse(InputStream stream, ContentHandler handler, Metadata metadata,
+ ParseContext context, TemporaryResources tmp)
+ throws TikaException, IOException, SAXException {
ArchiveInputStream ais = null;
String encoding = null;
try {
@@ -304,11 +314,9 @@ public class PackageParser extends AbstractEncodingDetectorParser {
// Pending a fix for COMPRESS-269 / TIKA-1525, this bit is a little nasty
ais = new SevenZWrapper(sevenz);
} else {
- tmp.close();
throw new TikaException("Unknown non-streaming format " + sne.getFormat(), sne);
}
} catch (ArchiveException e) {
- tmp.close();
throw new TikaException("Unable to unpack document stream", e);
}
@@ -340,7 +348,6 @@ public class PackageParser extends AbstractEncodingDetectorParser {
}
} finally {
ais.close();
- tmp.close();
xhtml.endDocument();
}
}