This is an automated email from the ASF dual-hosted git repository.
tallison 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 ed79ce41a TIKA-4490 (#2349) -- fixes for problems found via ossfuzz
integration
ed79ce41a is described below
commit ed79ce41aa96e652fdc951e39385301b345a8783
Author: Tim Allison <[email protected]>
AuthorDate: Thu Oct 2 16:33:29 2025 -0400
TIKA-4490 (#2349) -- fixes for problems found via ossfuzz integration
(cherry picked from commit 8a0bbe87c10faee8715589ecfce9f086bb091b41)
---
.../tika/parser/mail/MailContentHandler.java | 7 ++
.../detect/microsoft/ooxml/OPCPackageDetector.java | 4 ++
.../tika/parser/microsoft/ExcelExtractor.java | 3 +
.../org/apache/tika/ossfuzz/OssFuzzReplicator.java | 32 +++++++++
.../java/org/apache/tika/ossfuzz/ParserFuzzer.java | 77 ++++++++++++++++++++++
5 files changed, 123 insertions(+)
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mail/MailContentHandler.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mail/MailContentHandler.java
index 7c5d266ca..916c3c5e9 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mail/MailContentHandler.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mail/MailContentHandler.java
@@ -129,6 +129,10 @@ class MailContentHandler implements ContentHandler {
if (!extractAllAlternatives && alternativePartBuffer.size() > 0) {
UnsynchronizedByteArrayOutputStream bos =
UnsynchronizedByteArrayOutputStream.builder().get();
IOUtils.copy(is, bos);
+ byte[] bytes = bos.toByteArray();
+ if (bytes.length == 0) {
+ return;
+ }
alternativePartBuffer.peek().children.add(new BodyContents(submd,
bos.toByteArray()));
} else if (!extractAllAlternatives && parts.size() < 2) {
//if you're at the first level of embedding
@@ -138,6 +142,9 @@ class MailContentHandler implements ContentHandler {
UnsynchronizedByteArrayOutputStream bos =
UnsynchronizedByteArrayOutputStream.builder().get();
IOUtils.copy(is, bos);
final byte[] bytes = bos.toByteArray();
+ if (bytes.length == 0) {
+ return;
+ }
if (detectInlineTextOrHtml(submd, bytes)) {
handleInlineBodyPart(new BodyContents(submd, bytes));
} else {
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/detect/microsoft/ooxml/OPCPackageDetector.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/detect/microsoft/ooxml/OPCPackageDetector.java
index 341e9755b..28db84e09 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/detect/microsoft/ooxml/OPCPackageDetector.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/detect/microsoft/ooxml/OPCPackageDetector.java
@@ -198,6 +198,10 @@ public class OPCPackageDetector implements
ZipContainerDetector {
// Get the type of the core document part
PackagePart corePart = pkg.getPart(core.getRelationship(0));
+ if (corePart == null) {
+ return null;
+ }
+
String coreType = corePart.getContentType();
if (coreType.contains(".xps")) {
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java
index 41a1a840e..1604b5aab 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java
@@ -508,6 +508,9 @@ public class ExcelExtractor extends AbstractPOIFSExtractor {
break;
case LabelSSTRecord.sid: // Ref. a string in the shared string
table
+ if (sstRecord == null) {
+ throw new TikaException("sstRecord should have been
initialized before a ref to the shared string table");
+ }
LabelSSTRecord sst = (LabelSSTRecord) record;
UnicodeString unicode =
sstRecord.getString(sst.getSSTIndex());
String cellString = null;
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/ossfuzz/OssFuzzReplicator.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/ossfuzz/OssFuzzReplicator.java
new file mode 100644
index 000000000..83e168e1a
--- /dev/null
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/ossfuzz/OssFuzzReplicator.java
@@ -0,0 +1,32 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.ossfuzz;
+
+import org.junit.jupiter.api.Disabled;
+import org.junit.jupiter.api.Test;
+
+import org.apache.tika.parser.mail.RFC822Parser;
+
+public class OssFuzzReplicator {
+
+ @Test
+ @Disabled("turn this on for debugging ossfuzz findings")
+ public void testOne() throws Throwable {
+ byte[] bytes = new byte[0];//specify bytes here...probably from a path
+ ParserFuzzer.parseOne(new RFC822Parser(), bytes);
+ }
+}
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/ossfuzz/ParserFuzzer.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/ossfuzz/ParserFuzzer.java
new file mode 100644
index 000000000..d13a4748f
--- /dev/null
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/ossfuzz/ParserFuzzer.java
@@ -0,0 +1,77 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.ossfuzz;
+
+import java.io.InputStream;
+
+import org.xml.sax.ContentHandler;
+
+import org.apache.tika.io.TikaInputStream;
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.parser.Parser;
+import org.apache.tika.parser.RecursiveParserWrapper;
+import org.apache.tika.sax.BasicContentHandlerFactory;
+import org.apache.tika.sax.RecursiveParserWrapperHandler;
+
+import org.apache.tika.sax.ToTextContentHandler;
+
+
+class ParserFuzzer {
+
+ public static void parseOne(Parser parser, byte[] bytes, ParseContext
parseContext) throws Throwable {
+ parseBytes(parser, bytes, parseContext);
+ parseFile(parser, bytes, parseContext);
+ }
+
+
+ public static void parseOne(Parser parser, byte[] bytes) throws Throwable {
+ parseBytes(parser, bytes, new ParseContext());
+ parseFile(parser, bytes, new ParseContext());
+ }
+
+ public static void parseRMetaFile(Parser parser, byte[] bytes) throws
Throwable {
+ RecursiveParserWrapper wrapper = new RecursiveParserWrapper(parser);
+ RecursiveParserWrapperHandler rpwh = new RecursiveParserWrapperHandler(
+ new
BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.XML, -1));
+ try (TikaInputStream tis = TikaInputStream.get(bytes)) {
+ tis.getPath();
+ wrapper.parse(tis, rpwh, new Metadata(), new ParseContext());
+ }
+ }
+
+ public static void parseBytes(Parser parser, byte[] bytes, ParseContext
parseContext) throws Throwable {
+ ContentHandler handler = new ToTextContentHandler();
+ //make sure that other parsers cannot be invoked
+ parseContext.set(Parser.class, parser);
+ //try first with bytes
+ try (InputStream is = TikaInputStream.get(bytes)) {
+ parser.parse(is, handler, new Metadata(), parseContext);
+ }
+ }
+
+ public static void parseFile(Parser parser, byte[] bytes, ParseContext
parseContext) throws Throwable {
+ ContentHandler handler = new ToTextContentHandler();
+ //make sure that other parsers cannot be invoked
+ parseContext.set(Parser.class, parser);
+ try (TikaInputStream tis = TikaInputStream.get(bytes)) {
+ //force writing to tmp file
+ tis.getPath();
+ parser.parse(tis, handler, new Metadata(), parseContext);
+ }
+ }
+}
