Skip to content

Commit

Permalink
NUTCH-3019 -- update Tika (#797)
Browse files Browse the repository at this point in the history
Update to Tika 2.9.1
  • Loading branch information
tballison committed Nov 6, 2023
1 parent bbf0867 commit f88b9a1
Show file tree
Hide file tree
Showing 5 changed files with 12 additions and 10 deletions.
14 changes: 8 additions & 6 deletions ivy/ivy.xml
Original file line number Diff line number Diff line change
Expand Up @@ -36,19 +36,21 @@
</publications>

<dependencies>
<dependency org="org.apache.logging.log4j" name="log4j-api" rev="2.20.0" conf="*->master" />
<dependency org="org.apache.logging.log4j" name="log4j-core" rev="2.20.0" conf="*->master" />
<dependency org="org.apache.logging.log4j" name="log4j-slf4j2-impl" rev="2.20.0" conf="*->master" />
<dependency org="org.slf4j" name="slf4j-api" rev="2.0.7" conf="*->master" />
<dependency org="org.apache.logging.log4j" name="log4j-api" rev="2.21.1" conf="*->master" />
<dependency org="org.apache.logging.log4j" name="log4j-core" rev="2.21.1" conf="*->master" />
<dependency org="org.apache.logging.log4j" name="log4j-slf4j2-impl" rev="2.21.1" conf="*->master" />
<dependency org="org.slf4j" name="slf4j-api" rev="2.0.9" conf="*->master" />

<dependency org="org.apache.commons" name="commons-lang3" rev="3.13.0" conf="*->default" />
<dependency org="org.apache.commons" name="commons-collections4" rev="4.4" conf="*->master" />
<dependency org="org.apache.httpcomponents" name="httpclient" rev="4.5.13" conf="*->master" />
<dependency org="commons-codec" name="commons-codec" rev="1.16.0" conf="*->default" />
<!-- hadoop 3.4.0 should have 2.11.0; Tika is broken in distributed mode until then;
We're currently relying on the hadoop-safe-tika shim that shades commons-io to upgrade
Tika
see https://github.com/apache/nutch/pull/776 -->
<dependency org="commons-io" name="commons-io" rev="2.11.0" conf="*->default" />
<dependency org="org.apache.commons" name="commons-compress" rev="1.23.0" conf="*->default" />
<dependency org="org.apache.commons" name="commons-compress" rev="1.24.0" conf="*->default" />
<dependency org="org.apache.commons" name="commons-jexl3" rev="3.2.1" conf="*->default" />
<dependency org="com.tdunning" name="t-digest" rev="3.3" />

Expand All @@ -70,7 +72,7 @@
<exclude org="org.slf4j" name="*" />
</dependency><!-- End of Hadoop Dependencies -->

<dependency org="org.tallison.tika" name="tika-core-shaded" rev="2.9.0.0" conf="*->default" transitive="false"/>
<dependency org="org.tallison.tika" name="tika-core-shaded" rev="2.9.1.0" conf="*->default" transitive="false"/>

<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" />
Expand Down
2 changes: 1 addition & 1 deletion src/plugin/language-identifier/ivy.xml
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@
</publications>

<dependencies>
<dependency org="org.tallison.tika" name="tika-langdetect-optimaize-shaded" rev="2.9.0.0" conf="*->default" transitive="false"/>
<dependency org="org.tallison.tika" name="tika-langdetect-optimaize-shaded" rev="2.9.1.0" conf="*->default" transitive="false"/>
</dependencies>

</ivy-module>
2 changes: 1 addition & 1 deletion src/plugin/language-identifier/plugin.xml
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@
<export name="*"/>
</library>
<!-- dependencies of Tika's Optimaize language detector (tika-langdetect-optimaize) -->
<library name="tika-langdetect-optimaize-shaded-2.9.0.0.jar"/>
<library name="tika-langdetect-optimaize-shaded-2.9.1.0.jar"/>
</runtime>

<requires>
Expand Down
2 changes: 1 addition & 1 deletion src/plugin/parse-tika/ivy.xml
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@
</publications>

<dependencies>
<dependency org="org.tallison.tika" name="tika-parsers-standard-package-shaded" rev="2.9.0.0" conf="*->default" transitive="false"/>
<dependency org="org.tallison.tika" name="tika-parsers-standard-package-shaded" rev="2.9.1.0" conf="*->default" transitive="false"/>
</dependencies>

</ivy-module>
2 changes: 1 addition & 1 deletion src/plugin/parse-tika/plugin.xml
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@
<library name="parse-tika.jar">
<export name="*"/>
</library>
<library name="tika-parsers-standard-package-shaded-2.9.0.0.jar"/>
<library name="tika-parsers-standard-package-shaded-2.9.1.0.jar"/>
</runtime>

<requires>
Expand Down

0 comments on commit f88b9a1

Please sign in to comment.