This is an automated email from the ASF dual-hosted git repository.

sebastian-nagel pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/nutch.git


The following commit(s) were added to refs/heads/master by this push:
     new 3544a71c7 NUTCH-3183 Upgrade Tika to 3.3.1
3544a71c7 is described below

commit 3544a71c78a3ca9034862f6391d83d9ac23a068e
Author: Sebastian Nagel <[email protected]>
AuthorDate: Fri Jun 12 22:36:47 2026 +0200

    NUTCH-3183 Upgrade Tika to 3.3.1
---
 ivy/ivy.xml                               |   2 +-
 src/plugin/language-identifier/ivy.xml    |   2 +-
 src/plugin/language-identifier/plugin.xml |  18 ++--
 src/plugin/parse-tika/ivy.xml             |   4 +-
 src/plugin/parse-tika/plugin.xml          | 132 +++++++++++++++---------------
 5 files changed, 79 insertions(+), 79 deletions(-)

diff --git a/ivy/ivy.xml b/ivy/ivy.xml
index 944a329a0..5e2da4b76 100644
--- a/ivy/ivy.xml
+++ b/ivy/ivy.xml
@@ -74,7 +74,7 @@
     </dependency>
     <!-- End of Hadoop Dependencies -->
 
-    <dependency org="org.apache.tika" name="tika-core" rev="3.2.3" 
conf="*->default"/>
+    <dependency org="org.apache.tika" name="tika-core" rev="3.3.1" 
conf="*->default"/>
 
     <dependency org="xml-apis" name="xml-apis" rev="1.4.01" /><!-- force this 
version as it is required by Tika -->
     <dependency org="xerces" name="xercesImpl" rev="2.12.2" />
diff --git a/src/plugin/language-identifier/ivy.xml 
b/src/plugin/language-identifier/ivy.xml
index 448619ac1..b588b1979 100644
--- a/src/plugin/language-identifier/ivy.xml
+++ b/src/plugin/language-identifier/ivy.xml
@@ -37,7 +37,7 @@
   </publications>
 
   <dependencies>
-    <dependency org="org.apache.tika" name="tika-langdetect-optimaize" 
rev="3.2.3" conf="*->default">
+    <dependency org="org.apache.tika" name="tika-langdetect-optimaize" 
rev="3.3.1" conf="*->default">
       <!-- exclusions of dependencies provided in Nutch core (ivy/ivy.xml) -->
       <exclude org="org.apache.tika" name="tika-core" />
       <exclude org="com.google.guava" name="guava" />
diff --git a/src/plugin/language-identifier/plugin.xml 
b/src/plugin/language-identifier/plugin.xml
index 7fc3d555c..724810040 100644
--- a/src/plugin/language-identifier/plugin.xml
+++ b/src/plugin/language-identifier/plugin.xml
@@ -26,15 +26,15 @@
          <export name="*"/>
       </library>
       <!-- dependencies of Tika's Optimaize language detector 
(tika-langdetect-optimaize) -->
-        <library name="annotations-26.0.2.jar"/>
-        <library name="error_prone_annotations-2.41.0.jar"/>
-        <library name="failureaccess-1.0.3.jar"/>
-        <library name="j2objc-annotations-3.0.0.jar"/>
-        <library name="jsonic-1.2.11.jar"/>
-        <library name="jspecify-1.0.0.jar"/>
-        <library name="language-detector-0.6.jar"/>
-        <library 
name="listenablefuture-9999.0-empty-to-avoid-conflict-with-guava.jar"/>
-        <library name="tika-langdetect-optimaize-3.2.3.jar"/>
+      <library name="annotations-26.1.0.jar"/>
+      <library name="error_prone_annotations-2.49.0.jar"/>
+      <library name="failureaccess-1.0.3.jar"/>
+      <library name="j2objc-annotations-3.1.jar"/>
+      <library name="jsonic-1.2.11.jar"/>
+      <library name="jspecify-1.0.0.jar"/>
+      <library name="language-detector-0.6.jar"/>
+      <library 
name="listenablefuture-9999.0-empty-to-avoid-conflict-with-guava.jar"/>
+      <library name="tika-langdetect-optimaize-3.3.1.jar"/>
     </runtime>
 
    <requires>
diff --git a/src/plugin/parse-tika/ivy.xml b/src/plugin/parse-tika/ivy.xml
index 23af88eec..a81c37294 100644
--- a/src/plugin/parse-tika/ivy.xml
+++ b/src/plugin/parse-tika/ivy.xml
@@ -37,13 +37,13 @@
   </publications>
 
   <dependencies>
-    <dependency org="org.apache.tika" name="tika-parsers-standard-package" 
rev="3.2.3" conf="*->default">
+    <dependency org="org.apache.tika" name="tika-parsers-standard-package" 
rev="3.3.1" conf="*->default">
       <!-- exclusions of dependencies provided in Nutch core (ivy/ivy.xml) -->
       <exclude org="org.apache.tika" name="tika-core"/>
       <exclude org="org.slf4j" name="slf4j-api"/>
     </dependency>
     <!-- Boilerpipe for text extraction (tika.extractor=boilerpipe) - 
TIKA-4138 -->
-    <dependency org="org.apache.tika" name="tika-handler-boilerpipe" 
rev="3.2.3" conf="*->default">
+    <dependency org="org.apache.tika" name="tika-handler-boilerpipe" 
rev="3.3.1" conf="*->default">
       <exclude org="org.slf4j" name="slf4j-api"/>
     </dependency>
   </dependencies>
diff --git a/src/plugin/parse-tika/plugin.xml b/src/plugin/parse-tika/plugin.xml
index 1b9252cc6..eafa71709 100644
--- a/src/plugin/parse-tika/plugin.xml
+++ b/src/plugin/parse-tika/plugin.xml
@@ -27,94 +27,94 @@
       </library>
       <!-- dependencies of Tika (tika-parsers-standard-package) -->
       <library name="SparseBitSet-1.3.jar"/>
-      <library name="angus-activation-2.0.2.jar"/>
-      <library name="apache-mime4j-core-0.8.13.jar"/>
-      <library name="apache-mime4j-dom-0.8.13.jar"/>
-      <library name="asm-9.8.jar"/>
-      <library name="bcjmail-jdk18on-1.81.jar"/>
-      <library name="bcpkix-jdk18on-1.81.jar"/>
-      <library name="bcprov-jdk18on-1.81.jar"/>
-      <library name="bcutil-jdk18on-1.81.jar"/>
+      <library name="angus-activation-2.0.3.jar"/>
+      <library name="apache-mime4j-core-0.8.14.jar"/>
+      <library name="apache-mime4j-dom-0.8.14.jar"/>
+      <library name="asm-9.10.jar"/>
+      <library name="bcjmail-jdk18on-1.84.jar"/>
+      <library name="bcpkix-jdk18on-1.84.jar"/>
+      <library name="bcprov-jdk18on-1.84.jar"/>
+      <library name="bcutil-jdk18on-1.84.jar"/>
       <library name="boilerpipe-1.1.0.jar"/>
-      <library name="commons-codec-1.19.0.jar"/>
+      <library name="commons-codec-1.22.0.jar"/>
       <library name="commons-collections4-4.5.0.jar"/>
       <library name="commons-compress-1.28.0.jar"/>
       <library name="commons-csv-1.14.1.jar"/>
-      <library name="commons-exec-1.5.0.jar"/>
-      <library name="commons-io-2.20.0.jar"/>
-      <library name="commons-lang3-3.18.0.jar"/>
-      <library name="commons-logging-1.3.5.jar"/>
+      <library name="commons-exec-1.6.0.jar"/>
+      <library name="commons-io-2.22.0.jar"/>
+      <library name="commons-lang3-3.20.0.jar"/>
+      <library name="commons-logging-1.3.6.jar"/>
       <library name="commons-math3-3.6.1.jar"/>
       <library name="curvesapi-1.08.jar"/>
-      <library name="dd-plist-1.28.jar"/>
+      <library name="dd-plist-1.29.jar"/>
       <library name="dec-0.1.2.jar"/>
-      <library name="fontbox-3.0.5.jar"/>
+      <library name="fontbox-3.0.7.jar"/>
       <library name="istack-commons-runtime-4.1.2.jar"/>
-      <library name="jackcess-4.0.8.jar"/>
+      <library name="jackcess-4.0.10.jar"/>
       <library name="jackcess-encrypt-4.0.3.jar"/>
-      <library name="jackson-annotations-2.20.jar"/>
-      <library name="jackson-core-2.20.0.jar"/>
-      <library name="jackson-databind-2.20.0.jar"/>
+      <library name="jackson-annotations-2.21.jar"/>
+      <library name="jackson-core-2.21.3.jar"/>
+      <library name="jackson-databind-2.21.3.jar"/>
       <library name="jai-imageio-core-1.4.0.jar"/>
-      <library name="jakarta.activation-api-2.1.3.jar"/>
-      <library name="jakarta.xml.bind-api-4.0.2.jar"/>
+      <library name="jakarta.activation-api-2.1.4.jar"/>
+      <library name="jakarta.xml.bind-api-4.0.5.jar"/>
       <library name="java-libpst-0.9.3.jar"/>
-      <library name="jaxb-core-4.0.5.jar"/>
-      <library name="jaxb-runtime-4.0.5.jar"/>
-      <library name="jbig2-imageio-3.0.4.jar"/>
-      <library name="jcl-over-slf4j-2.0.17.jar"/>
+      <library name="jaxb-core-4.0.8.jar"/>
+      <library name="jaxb-runtime-4.0.8.jar"/>
+      <library name="jbig2-imageio-3.0.5.jar"/>
+      <library name="jcl-over-slf4j-2.0.18.jar"/>
       <library name="jdom2-2.0.6.1.jar"/>
       <library name="jempbox-1.8.17.jar"/>
-      <library name="jhighlight-1.1.0.jar"/>
+      <library name="jhighlight-1.1.1.jar"/>
       <library name="jmatio-1.5.jar"/>
-      <library name="jsoup-1.21.2.jar"/>
+      <library name="jsoup-1.22.2.jar"/>
       <library name="juniversalchardet-2.5.0.jar"/>
-      <library name="junrar-7.5.5.jar"/>
-      <library name="jwarc-0.32.0.jar"/>
-      <library name="log4j-api-2.25.1.jar"/>
-      <library name="metadata-extractor-2.19.0.jar"/>
+      <library name="junrar-7.6.0.jar"/>
+      <library name="jwarc-0.36.0.jar"/>
+      <library name="log4j-api-2.26.0.jar"/>
+      <library name="metadata-extractor-2.20.0.jar"/>
       <library name="parso-2.0.14.jar"/>
-      <library name="pdfbox-3.0.5.jar"/>
-      <library name="pdfbox-io-3.0.5.jar"/>
-      <library name="pdfbox-tools-3.0.5.jar"/>
-      <library name="picocli-4.7.6.jar"/>
-      <library name="poi-5.4.1.jar"/>
-      <library name="poi-ooxml-5.4.1.jar"/>
-      <library name="poi-ooxml-lite-5.4.1.jar"/>
-      <library name="poi-scratchpad-5.4.1.jar"/>
+      <library name="pdfbox-3.0.7.jar"/>
+      <library name="pdfbox-io-3.0.7.jar"/>
+      <library name="pdfbox-tools-3.0.7.jar"/>
+      <library name="picocli-4.7.7.jar"/>
+      <library name="poi-5.5.1.jar"/>
+      <library name="poi-ooxml-5.5.1.jar"/>
+      <library name="poi-ooxml-full-5.5.1.jar"/>
+      <library name="poi-scratchpad-5.5.1.jar"/>
       <library name="rome-2.1.0.jar"/>
       <library name="rome-utils-2.1.0.jar"/>
-      <library name="tika-parser-apple-module-3.2.3.jar"/>
-      <library name="tika-parser-audiovideo-module-3.2.3.jar"/>
-      <library name="tika-parser-cad-module-3.2.3.jar"/>
-      <library name="tika-parser-code-module-3.2.3.jar"/>
-      <library name="tika-parser-crypto-module-3.2.3.jar"/>
-      <library name="tika-parser-digest-commons-3.2.3.jar"/>
-      <library name="tika-parser-font-module-3.2.3.jar"/>
-      <library name="tika-parser-html-module-3.2.3.jar"/>
-      <library name="tika-parser-image-module-3.2.3.jar"/>
-      <library name="tika-parser-mail-commons-3.2.3.jar"/>
-      <library name="tika-parser-mail-module-3.2.3.jar"/>
-      <library name="tika-parser-microsoft-module-3.2.3.jar"/>
-      <library name="tika-parser-miscoffice-module-3.2.3.jar"/>
-      <library name="tika-parser-news-module-3.2.3.jar"/>
-      <library name="tika-parser-ocr-module-3.2.3.jar"/>
-      <library name="tika-parser-pdf-module-3.2.3.jar"/>
-      <library name="tika-parser-pkg-module-3.2.3.jar"/>
-      <library name="tika-parser-text-module-3.2.3.jar"/>
-      <library name="tika-parser-webarchive-module-3.2.3.jar"/>
-      <library name="tika-parser-xml-module-3.2.3.jar"/>
-      <library name="tika-parser-xmp-commons-3.2.3.jar"/>
-      <library name="tika-parser-zip-commons-3.2.3.jar"/>
-      <library name="tika-parsers-standard-package-3.2.3.jar"/>
-      <library name="tika-handler-boilerpipe-3.2.3.jar"/>
-      <library name="txw2-4.0.5.jar"/>
+      <library name="tika-handler-boilerpipe-3.3.1.jar"/>
+      <library name="tika-parser-apple-module-3.3.1.jar"/>
+      <library name="tika-parser-audiovideo-module-3.3.1.jar"/>
+      <library name="tika-parser-cad-module-3.3.1.jar"/>
+      <library name="tika-parser-code-module-3.3.1.jar"/>
+      <library name="tika-parser-crypto-module-3.3.1.jar"/>
+      <library name="tika-parser-digest-commons-3.3.1.jar"/>
+      <library name="tika-parser-font-module-3.3.1.jar"/>
+      <library name="tika-parser-html-module-3.3.1.jar"/>
+      <library name="tika-parser-image-module-3.3.1.jar"/>
+      <library name="tika-parser-mail-commons-3.3.1.jar"/>
+      <library name="tika-parser-mail-module-3.3.1.jar"/>
+      <library name="tika-parser-microsoft-module-3.3.1.jar"/>
+      <library name="tika-parser-miscoffice-module-3.3.1.jar"/>
+      <library name="tika-parser-news-module-3.3.1.jar"/>
+      <library name="tika-parser-ocr-module-3.3.1.jar"/>
+      <library name="tika-parser-pdf-module-3.3.1.jar"/>
+      <library name="tika-parser-pkg-module-3.3.1.jar"/>
+      <library name="tika-parser-text-module-3.3.1.jar"/>
+      <library name="tika-parser-webarchive-module-3.3.1.jar"/>
+      <library name="tika-parser-xml-module-3.3.1.jar"/>
+      <library name="tika-parser-xmp-commons-3.3.1.jar"/>
+      <library name="tika-parser-zip-commons-3.3.1.jar"/>
+      <library name="tika-parsers-standard-package-3.3.1.jar"/>
+      <library name="txw2-4.0.8.jar"/>
       <library name="vorbis-java-core-0.8.jar"/>
       <library name="vorbis-java-tika-0.8.jar"/>
       <library name="xmlbeans-5.3.0.jar"/>
-      <library name="xmpbox-3.0.5.jar"/>
+      <library name="xmpbox-3.0.7.jar"/>
       <library name="xmpcore-6.1.11.jar"/>
-      <library name="xz-1.10.jar"/>
+      <library name="xz-1.12.jar"/>
       <!-- end of dependencies of Tika (tika-parsers-standard-package) -->
    </runtime>
 

Reply via email to