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 8f6dc930d2 branch_3x-various-improvements (#2698)
8f6dc930d2 is described below
commit 8f6dc930d2079e4c444086723c22100168f61930
Author: Tim Allison <[email protected]>
AuthorDate: Tue Mar 17 14:13:41 2026 -0400
branch_3x-various-improvements (#2698)
---
CHANGES.txt | 4 +++-
tika-bundles/tika-bundle-standard/pom.xml | 2 +-
tika-eval/tika-eval-app/pom.xml | 4 ++++
tika-parent/pom.xml | 11 +++++++++++
.../tika-parser-microsoft-module/pom.xml | 4 ++++
.../main/java/org/apache/tika/parser/pkg/PackageParser.java | 3 +++
6 files changed, 26 insertions(+), 2 deletions(-)
diff --git a/CHANGES.txt b/CHANGES.txt
index 5def269d65..9fd7eb98d9 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -1,5 +1,7 @@
Release 3.3.0 - ???
+ * Switch to poi-ooxml-full (TIKA-4563).
+
* Users need to add "allowAbsolutePaths=true" for the FileSystemFetcher to
fetch
an absolute path (TIKA-4649).
@@ -19,7 +21,7 @@ Release 3.3.0 - ???
* Improve extraction of Javascript from PDFs (TIKA-4465).
-Release 3.2.3 - ???
+Release 3.2.3 - 9/11/2025
* Allow backwards compatibility with versions of commons-compress before
1.28.0 (TIKA-4469).
diff --git a/tika-bundles/tika-bundle-standard/pom.xml
b/tika-bundles/tika-bundle-standard/pom.xml
index a771b4fe03..dc586b1e9f 100644
--- a/tika-bundles/tika-bundle-standard/pom.xml
+++ b/tika-bundles/tika-bundle-standard/pom.xml
@@ -167,7 +167,7 @@
poi|
poi-scratchpad|
poi-ooxml|
- poi-ooxml-lite|
+ poi-ooxml-full|
commons-math3|
curvesapi|
xmlbeans|
diff --git a/tika-eval/tika-eval-app/pom.xml b/tika-eval/tika-eval-app/pom.xml
index bfa683c383..0c10d52232 100644
--- a/tika-eval/tika-eval-app/pom.xml
+++ b/tika-eval/tika-eval-app/pom.xml
@@ -61,6 +61,10 @@
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
</dependency>
+ <dependency>
+ <groupId>org.apache.poi</groupId>
+ <artifactId>poi-ooxml-full</artifactId>
+ </dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-batch</artifactId>
diff --git a/tika-parent/pom.xml b/tika-parent/pom.xml
index 5a67995840..0d647afe13 100644
--- a/tika-parent/pom.xml
+++ b/tika-parent/pom.xml
@@ -904,6 +904,17 @@
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
<version>${poi.version}</version>
+ <exclusions>
+ <exclusion>
+ <groupId>org.apache.poi</groupId>
+ <artifactId>poi-ooxml-lite</artifactId>
+ </exclusion>
+ </exclusions>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.poi</groupId>
+ <artifactId>poi-ooxml-full</artifactId>
+ <version>${poi.version}</version>
</dependency>
<dependency>
<groupId>org.apache.xmlbeans</groupId>
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/pom.xml
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/pom.xml
index bfc4f24fa6..a1443b50ff 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/pom.xml
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/pom.xml
@@ -88,6 +88,10 @@
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
</dependency>
+ <dependency>
+ <groupId>org.apache.poi</groupId>
+ <artifactId>poi-ooxml-full</artifactId>
+ </dependency>
<!-- needed by jackcess -->
<dependency>
<groupId>commons-logging</groupId>
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 25b4fa1ccc..f596828fa8 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
@@ -444,6 +444,9 @@ public class PackageParser extends
AbstractEncodingDetectorParser {
extractor.parseEmbedded(entryStream, xhtml, entryMetadata,
true);
} catch (UnsupportedZipFeatureException e) {
EmbeddedDocumentUtil.recordEmbeddedStreamException(e,
parentMetadata);
+ if (name != null && name.length() > 0) {
+ xhtml.element("p", name);
+ }
}
}
}