You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ti...@apache.org on 2026/03/31 08:08:07 UTC
(tika) branch TIKA-4704-5 created (now 3a0bffc624)
This is an automated email from the ASF dual-hosted git repository.
tilman pushed a change to branch TIKA-4704-5
in repository https://gitbox.apache.org/repos/asf/tika.git
at 3a0bffc624 [TIKA-4704] use TemporaryResources to avoid leak
This branch includes the following new commits:
new 3a0bffc624 [TIKA-4704] use TemporaryResources to avoid leak
The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
(tika) 01/01: [TIKA-4704] use TemporaryResources to avoid leak
Posted by ti...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tilman pushed a commit to branch TIKA-4704-5
in repository https://gitbox.apache.org/repos/asf/tika.git
commit 3a0bffc62485870afcd7466213324d4e8119ec23
Author: Tilman Hausherr <ti...@snafu.de>
AuthorDate: Tue Mar 31 10:07:58 2026 +0200
[TIKA-4704] use TemporaryResources to avoid leak
---
.../apache/tika/parser/odf/OpenDocumentParser.java | 74 ++++++++++++----------
1 file changed, 40 insertions(+), 34 deletions(-)
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java
index 78ecd8916f..f8932383c3 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java
@@ -38,6 +38,7 @@ import org.apache.tika.config.Field;
import org.apache.tika.exception.EncryptedDocumentException;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentUtil;
+import org.apache.tika.io.TemporaryResources;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
@@ -131,47 +132,52 @@ public class OpenDocumentParser implements Parser {
// Use a File if we can, and an already open zip is even better
ZipFile zipFile = null;
TikaInputStream tmpTis = null;
- if (stream instanceof TikaInputStream) {
- TikaInputStream tis = (TikaInputStream) stream;
- Object container = ((TikaInputStream) stream).getOpenContainer();
- if (container instanceof ZipFile) {
- zipFile = (ZipFile) container;
+ TemporaryResources tmp = new TemporaryResources();
+ try {
+ if (stream instanceof TikaInputStream) {
+ TikaInputStream tis = (TikaInputStream) stream;
+ Object container = ((TikaInputStream) stream).getOpenContainer();
+ if (container instanceof ZipFile) {
+ zipFile = (ZipFile) container;
+ } else {
+ zipFile = new ZipFile(tis.getFile());
+ tis.setOpenContainer(zipFile);
+ }
} else {
- zipFile = new ZipFile(tis.getFile());
- tis.setOpenContainer(zipFile);
+ tmpTis = TikaInputStream.get(stream, tmp, metadata);
+ tmpTis.setOpenContainer(new ZipFile(tmpTis.getFile()));
+ zipFile = (ZipFile) tmpTis.getOpenContainer();
}
- } else {
- tmpTis = TikaInputStream.get(stream);
- tmpTis.setOpenContainer(new ZipFile(tmpTis.getFile()));
- zipFile = (ZipFile) tmpTis.getOpenContainer();
- }
- // Prepare to handle the content
- XHTMLContentHandler xhtml = new XHTMLContentHandler(baseHandler, metadata);
- xhtml.startDocument();
- // As we don't know which of the metadata or the content
- // we'll hit first, catch the endDocument call initially
- EndDocumentShieldingContentHandler handler = new EndDocumentShieldingContentHandler(xhtml);
+ // Prepare to handle the content
+ XHTMLContentHandler xhtml = new XHTMLContentHandler(baseHandler, metadata);
+ xhtml.startDocument();
+ // As we don't know which of the metadata or the content
+ // we'll hit first, catch the endDocument call initially
+ EndDocumentShieldingContentHandler handler = new EndDocumentShieldingContentHandler(xhtml);
- try {
try {
- handleZipFile(zipFile, metadata, context, handler, embeddedDocumentUtil);
- } finally {
- //Do we want to close silently == catch an exception here?
- if (tmpTis != null) {
- //tmpTis handles closing of the open zip container
- tmpTis.close();
+ try {
+ handleZipFile(zipFile, metadata, context, handler, embeddedDocumentUtil);
+ } finally {
+ //Do we want to close silently == catch an exception here?
+ if (tmpTis != null) {
+ //tmpTis handles closing of the open zip container
+ tmpTis.close();
+ }
}
+ } catch (SAXException e) {
+ if (e.getCause() instanceof EncryptedDocumentException) {
+ throw (EncryptedDocumentException)e.getCause();
+ }
+ throw e;
}
- } catch (SAXException e) {
- if (e.getCause() instanceof EncryptedDocumentException) {
- throw (EncryptedDocumentException)e.getCause();
- }
- throw e;
- }
- // Only now call the end document
- if (handler.isEndDocumentWasCalled()) {
- handler.reallyEndDocument();
+ // Only now call the end document
+ if (handler.isEndDocumentWasCalled()) {
+ handler.reallyEndDocument();
+ }
+ } finally {
+ tmp.dispose();
}
}