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 2025/07/02 10:32:08 UTC
(tika) branch main updated (1164e7808 -> c3f020f49)
This is an automated email from the ASF dual-hosted git repository.
tilman pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
from 1164e7808 TIKA-4327: make json texts beautiful
new a343e1f11 TIKA-4327: replace deprecated, fix annotations
new c3f020f49 TIKA-4327: update aws, azure, nimbus
The 2 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.
Summary of changes:
.../src/main/java/org/apache/tika/embedder/ExternalEmbedder.java | 8 +++++---
.../java/org/apache/tika/extractor/ParserContainerExtractor.java | 6 +++++-
.../java/org/apache/tika/example/PickBestTextEncodingParser.java | 1 +
tika-parent/pom.xml | 8 ++++----
4 files changed, 15 insertions(+), 8 deletions(-)
(tika) 01/02: TIKA-4327: replace deprecated, fix annotations
Posted by ti...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tilman pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
commit a343e1f111e895444a22efebcb2456abecad9843
Author: Tilman Hausherr <ti...@apache.org>
AuthorDate: Wed Jul 2 12:29:54 2025 +0200
TIKA-4327: replace deprecated, fix annotations
---
.../src/main/java/org/apache/tika/embedder/ExternalEmbedder.java | 8 +++++---
.../java/org/apache/tika/extractor/ParserContainerExtractor.java | 6 +++++-
.../java/org/apache/tika/example/PickBestTextEncodingParser.java | 1 +
3 files changed, 11 insertions(+), 4 deletions(-)
diff --git a/tika-core/src/main/java/org/apache/tika/embedder/ExternalEmbedder.java b/tika-core/src/main/java/org/apache/tika/embedder/ExternalEmbedder.java
index b2411d7a8..c58d57345 100644
--- a/tika-core/src/main/java/org/apache/tika/embedder/ExternalEmbedder.java
+++ b/tika-core/src/main/java/org/apache/tika/embedder/ExternalEmbedder.java
@@ -146,6 +146,7 @@ public class ExternalEmbedder implements Embedder {
}
}
+ @Override
public Set<MediaType> getSupportedEmbedTypes(ParseContext context) {
return getSupportedEmbedTypes();
}
@@ -330,6 +331,7 @@ public class ExternalEmbedder implements Embedder {
* Metadata is only extracted if {@link #setMetadataCommandArguments(Map)}
* has been called to set arguments.
*/
+ @Override
public void embed(final Metadata metadata, final InputStream inputStream,
final OutputStream outputStream, final ParseContext context)
throws IOException, TikaException {
@@ -399,9 +401,9 @@ public class ExternalEmbedder implements Embedder {
// Execute
Process process;
if (cmd.toArray().length == 1) {
- process = Runtime.getRuntime().exec(cmd.toArray(new String[]{})[0]);
+ process = Runtime.getRuntime().exec(cmd.toArray(String[]::new)[0]);
} else {
- process = Runtime.getRuntime().exec(cmd.toArray(new String[]{}));
+ process = Runtime.getRuntime().exec(cmd.toArray(String[]::new));
}
UnsynchronizedByteArrayOutputStream stdErrOutputStream = UnsynchronizedByteArrayOutputStream.builder().get();
@@ -425,7 +427,7 @@ public class ExternalEmbedder implements Embedder {
} catch (InterruptedException ignore) {
}
// The command is finished, read the output file into the given output stream
- InputStream tempOutputFileInputStream = TikaInputStream.get(tempOutputFile);
+ InputStream tempOutputFileInputStream = TikaInputStream.get(tempOutputFile.toPath());
IOUtils.copy(tempOutputFileInputStream, outputStream);
}
} finally {
diff --git a/tika-core/src/main/java/org/apache/tika/extractor/ParserContainerExtractor.java b/tika-core/src/main/java/org/apache/tika/extractor/ParserContainerExtractor.java
index b2e9cd169..caa4636ee 100644
--- a/tika-core/src/main/java/org/apache/tika/extractor/ParserContainerExtractor.java
+++ b/tika-core/src/main/java/org/apache/tika/extractor/ParserContainerExtractor.java
@@ -69,11 +69,13 @@ public class ParserContainerExtractor implements ContainerExtractor {
this.detector = detector;
}
+ @Override
public boolean isSupported(TikaInputStream input) throws IOException {
MediaType type = detector.detect(input, new Metadata());
return parser.getSupportedTypes(new ParseContext()).contains(type);
}
+ @Override
public void extract(
TikaInputStream stream, ContainerExtractor recurseExtractor,
EmbeddedResourceHandler handler)
@@ -101,10 +103,12 @@ public class ParserContainerExtractor implements ContainerExtractor {
this.handler = handler;
}
+ @Override
public Set<MediaType> getSupportedTypes(ParseContext context) {
return parser.getSupportedTypes(context);
}
+ @Override
public void parse(
InputStream stream, ContentHandler ignored,
Metadata metadata, ParseContext context)
@@ -125,7 +129,7 @@ public class ParserContainerExtractor implements ContainerExtractor {
File file = tis.getFile();
// Let the handler process the embedded resource
- try (InputStream input = TikaInputStream.get(file)) {
+ try (InputStream input = TikaInputStream.get(file.toPath())) {
handler.handle(filename, type, input);
}
diff --git a/tika-example/src/main/java/org/apache/tika/example/PickBestTextEncodingParser.java b/tika-example/src/main/java/org/apache/tika/example/PickBestTextEncodingParser.java
index 8f925d3d4..b5ddffdb3 100644
--- a/tika-example/src/main/java/org/apache/tika/example/PickBestTextEncodingParser.java
+++ b/tika-example/src/main/java/org/apache/tika/example/PickBestTextEncodingParser.java
@@ -55,6 +55,7 @@ import org.apache.tika.sax.ContentHandlerFactory;
*
* @deprecated Currently not suitable for real use, more a demo / prototype!
*/
+@Deprecated
public class PickBestTextEncodingParser extends AbstractMultipleParser {
/**
* Serial version UID.
(tika) 02/02: TIKA-4327: update aws, azure, nimbus
Posted by ti...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tilman pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
commit c3f020f491aecdbfd096f8cc8db1bdd10e4e12ed
Author: Tilman Hausherr <ti...@apache.org>
AuthorDate: Wed Jul 2 12:31:41 2025 +0200
TIKA-4327: update aws, azure, nimbus
---
tika-parent/pom.xml | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/tika-parent/pom.xml b/tika-parent/pom.xml
index bf838d6e4..e0ba1333d 100644
--- a/tika-parent/pom.xml
+++ b/tika-parent/pom.xml
@@ -312,14 +312,14 @@
<!-- change threetenbp exclusion version -->
<google.cloud.version>2.53.2</google.cloud.version>
<aws.version>1.12.787</aws.version>
- <aws2.version>2.31.73</aws2.version>
+ <aws2.version>2.31.75</aws2.version>
<!-- WARNING: when you upgrade asm make sure that you update the
OpCode in the initializer in org.apache.tika.parser.asm.XHTMLClassVisitor
See TIKA-2992.
-->
<asm.version>9.8</asm.version>
- <azure.core.version>1.55.4</azure.core.version>
- <azure.core.http.netty.version>1.15.12</azure.core.http.netty.version>
+ <azure.core.version>1.55.5</azure.core.version>
+ <azure.core.http.netty.version>1.15.13</azure.core.http.netty.version>
<azure.storage.blob.version>12.31.0-beta.1</azure.storage.blob.version>
<azure.storage.common>12.30.0-beta.1</azure.storage.common>
<azure-identity.version>1.16.2</azure-identity.version>
@@ -455,7 +455,7 @@
<xmpcore.version>6.1.11</xmpcore.version>
<zookeeper.version>3.9.3</zookeeper.version>
<zstd.version>1.5.7-3</zstd.version>
- <nimbus-jose-jwt.version>10.3</nimbus-jose-jwt.version>
+ <nimbus-jose-jwt.version>10.3.1</nimbus-jose-jwt.version>
<javacpp.version>1.5.11</javacpp.version>
<!-- needs to exist even if empty due to problems with jacoco-maven-plugin -->