This is an automated email from the ASF dual-hosted git repository. snagel 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 568993b90 NUTCH-2948 Upgrade dependencies to Any23 2.7 and Tika 2.3.0 568993b90 is described below commit 568993b908702b9631a705c8122ba99af1b72f04 Author: Sebastian Nagel <sna...@apache.org> AuthorDate: Thu May 5 18:59:16 2022 +0200 NUTCH-2948 Upgrade dependencies to Any23 2.7 and Tika 2.3.0 --- ivy/ivy.xml | 2 +- src/plugin/any23/ivy.xml | 2 +- src/plugin/any23/plugin.xml | 98 ++++++++++++++++--------------- src/plugin/language-identifier/ivy.xml | 2 +- src/plugin/language-identifier/plugin.xml | 4 +- src/plugin/parse-tika/ivy.xml | 2 +- src/plugin/parse-tika/plugin.xml | 69 +++++++++++----------- 7 files changed, 92 insertions(+), 87 deletions(-) diff --git a/ivy/ivy.xml b/ivy/ivy.xml index 34e298f48..a03bce45f 100644 --- a/ivy/ivy.xml +++ b/ivy/ivy.xml @@ -63,7 +63,7 @@ <dependency org="org.apache.hadoop" name="hadoop-mapreduce-client-jobclient" rev="3.1.3" conf="*->default" /> <!-- End of Hadoop Dependencies --> - <dependency org="org.apache.tika" name="tika-core" rev="2.2.1" /> + <dependency org="org.apache.tika" name="tika-core" rev="2.3.0" /> <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="2.12.1" /> diff --git a/src/plugin/any23/ivy.xml b/src/plugin/any23/ivy.xml index 7220a2562..3b755ee3f 100644 --- a/src/plugin/any23/ivy.xml +++ b/src/plugin/any23/ivy.xml @@ -36,7 +36,7 @@ </publications> <dependencies> - <dependency org="org.apache.any23" name="apache-any23-core" rev="2.6" conf="*->default"> + <dependency org="org.apache.any23" name="apache-any23-core" rev="2.7" conf="*->default"> <exclude org="org.apache.commons" name="commons-lang" /> <exclude org="org.apache.commons" name="commons-compress" /> <exclude org="org.slf4j" name="slf4j-log4j12" /> diff --git a/src/plugin/any23/plugin.xml b/src/plugin/any23/plugin.xml index 40a42c7b7..dae8c47aa 100644 --- a/src/plugin/any23/plugin.xml +++ b/src/plugin/any23/plugin.xml @@ -26,12 +26,11 @@ <export name="*"/> </library> <!-- Begin Any23 dependencies --> - <library name="SparseBitSet-1.2.jar"/> - <library name="apache-any23-api-2.6.jar"/> - <library name="apache-any23-core-2.6.jar"/> - <library name="apache-any23-csvutils-2.6.jar"/> - <library name="apache-any23-encoding-2.6.jar"/> - <library name="apache-any23-mime-2.6.jar"/> + <library name="apache-any23-api-2.7.jar"/> + <library name="apache-any23-core-2.7.jar"/> + <library name="apache-any23-csvutils-2.7.jar"/> + <library name="apache-any23-encoding-2.7.jar"/> + <library name="apache-any23-mime-2.7.jar"/> <library name="apache-mime4j-core-0.8.4.jar"/> <library name="apache-mime4j-dom-0.8.4.jar"/> <library name="asm-9.2.jar"/> @@ -84,8 +83,8 @@ <library name="jaxb-api-2.3.1.jar"/> <library name="jaxb-runtime-2.3.5.jar"/> <library name="jbig2-imageio-3.0.3.jar"/> - <library name="jcl-over-slf4j-1.7.32.jar"/> - <library name="jcommander-1.81.jar"/> + <library name="jcl-over-slf4j-1.7.35.jar"/> + <library name="jcommander-1.82.jar"/> <library name="jdom2-2.0.6.1.jar"/> <library name="jempbox-1.8.16.jar"/> <library name="jhighlight-1.0.3.jar"/> @@ -94,27 +93,28 @@ <library name="jsoup-1.14.3.jar"/> <library name="jsr305-3.0.2.jar"/> <library name="juniversalchardet-1.0.3.jar"/> - <library name="junrar-7.4.0.jar"/> + <library name="junrar-7.4.1.jar"/> <library name="listenablefuture-9999.0-empty-to-avoid-conflict-with-guava.jar"/> + <library name="log4j-api-2.17.1.jar"/> <library name="log4j-core-2.17.1.jar"/> <library name="log4j-slf4j-impl-2.17.1.jar"/> <library name="mapdb-1.0.8.jar"/> <library name="metadata-extractor-2.16.0.jar"/> - <library name="owlapi-api-5.1.19.jar"/> - <library name="owlapi-apibinding-5.1.19.jar"/> - <library name="owlapi-impl-5.1.19.jar"/> - <library name="owlapi-oboformat-5.1.19.jar"/> - <library name="owlapi-parsers-5.1.19.jar"/> - <library name="owlapi-rio-5.1.19.jar"/> - <library name="owlapi-tools-5.1.19.jar"/> + <library name="owlapi-api-5.1.20.jar"/> + <library name="owlapi-apibinding-5.1.20.jar"/> + <library name="owlapi-impl-5.1.20.jar"/> + <library name="owlapi-oboformat-5.1.20.jar"/> + <library name="owlapi-parsers-5.1.20.jar"/> + <library name="owlapi-rio-5.1.20.jar"/> + <library name="owlapi-tools-5.1.20.jar"/> <library name="parso-2.0.14.jar"/> <library name="pdfbox-2.0.25.jar"/> <library name="pdfbox-debugger-2.0.25.jar"/> <library name="pdfbox-tools-2.0.25.jar"/> - <library name="poi-4.1.2.jar"/> - <library name="poi-ooxml-4.1.2.jar"/> - <library name="poi-ooxml-schemas-4.1.2.jar"/> - <library name="poi-scratchpad-4.1.2.jar"/> + <library name="poi-5.2.0.jar"/> + <library name="poi-ooxml-5.2.0.jar"/> + <library name="poi-ooxml-lite-5.2.0.jar"/> + <library name="poi-scratchpad-5.2.0.jar"/> <library name="rdf4j-http-client-3.7.4.jar"/> <library name="rdf4j-http-protocol-3.7.4.jar"/> <library name="rdf4j-model-3.7.4.jar"/> @@ -134,7 +134,7 @@ <library name="rdf4j-rio-api-3.7.4.jar"/> <library name="rdf4j-rio-binary-3.7.4.jar"/> <library name="rdf4j-rio-datatypes-3.7.4.jar"/> - <library name="rdf4j-rio-hdt-3.4.3.jar"/> + <library name="rdf4j-rio-hdt-3.7.4.jar"/> <library name="rdf4j-rio-jsonld-3.7.4.jar"/> <library name="rdf4j-rio-languages-3.7.4.jar"/> <library name="rdf4j-rio-n3-3.7.4.jar"/> @@ -149,43 +149,45 @@ <library name="rdf4j-sail-base-3.7.4.jar"/> <library name="rdf4j-sail-memory-3.7.4.jar"/> <library name="rdf4j-util-3.7.4.jar"/> - <library name="rome-1.16.0.jar"/> - <library name="rome-utils-1.16.0.jar"/> + <library name="rome-1.18.0.jar"/> + <library name="rome-utils-1.18.0.jar"/> <library name="semargl-core-0.7.jar"/> <library name="semargl-rdf-0.7.jar"/> <library name="semargl-rdf4j-0.7.jar"/> <library name="semargl-rdfa-0.7.jar"/> <library name="snakeyaml-1.30.jar"/> + <library name="SparseBitSet-1.2.jar"/> <library name="tagsoup-1.2.1.jar"/> - <library name="tika-core-2.2.1.jar"/> - <library name="tika-parser-apple-module-2.2.1.jar"/> - <library name="tika-parser-audiovideo-module-2.2.1.jar"/> - <library name="tika-parser-cad-module-2.2.1.jar"/> - <library name="tika-parser-code-module-2.2.1.jar"/> - <library name="tika-parser-crypto-module-2.2.1.jar"/> - <library name="tika-parser-digest-commons-2.2.1.jar"/> - <library name="tika-parser-font-module-2.2.1.jar"/> - <library name="tika-parser-html-commons-2.2.1.jar"/> - <library name="tika-parser-html-module-2.2.1.jar"/> - <library name="tika-parser-image-module-2.2.1.jar"/> - <library name="tika-parser-mail-commons-2.2.1.jar"/> - <library name="tika-parser-mail-module-2.2.1.jar"/> - <library name="tika-parser-microsoft-module-2.2.1.jar"/> - <library name="tika-parser-miscoffice-module-2.2.1.jar"/> - <library name="tika-parser-news-module-2.2.1.jar"/> - <library name="tika-parser-ocr-module-2.2.1.jar"/> - <library name="tika-parser-pdf-module-2.2.1.jar"/> - <library name="tika-parser-pkg-module-2.2.1.jar"/> - <library name="tika-parser-text-module-2.2.1.jar"/> - <library name="tika-parser-xml-module-2.2.1.jar"/> - <library name="tika-parser-xmp-commons-2.2.1.jar"/> - <library name="tika-parser-zip-commons-2.2.1.jar"/> - <library name="tika-parsers-standard-package-2.2.1.jar"/> + <library name="tika-core-2.3.0.jar"/> + <library name="tika-parser-apple-module-2.3.0.jar"/> + <library name="tika-parser-audiovideo-module-2.3.0.jar"/> + <library name="tika-parser-cad-module-2.3.0.jar"/> + <library name="tika-parser-code-module-2.3.0.jar"/> + <library name="tika-parser-crypto-module-2.3.0.jar"/> + <library name="tika-parser-digest-commons-2.3.0.jar"/> + <library name="tika-parser-font-module-2.3.0.jar"/> + <library name="tika-parser-html-commons-2.3.0.jar"/> + <library name="tika-parser-html-module-2.3.0.jar"/> + <library name="tika-parser-image-module-2.3.0.jar"/> + <library name="tika-parser-mail-commons-2.3.0.jar"/> + <library name="tika-parser-mail-module-2.3.0.jar"/> + <library name="tika-parser-microsoft-module-2.3.0.jar"/> + <library name="tika-parser-miscoffice-module-2.3.0.jar"/> + <library name="tika-parser-news-module-2.3.0.jar"/> + <library name="tika-parser-ocr-module-2.3.0.jar"/> + <library name="tika-parser-pdf-module-2.3.0.jar"/> + <library name="tika-parser-pkg-module-2.3.0.jar"/> + <library name="tika-parsers-standard-package-2.3.0.jar"/> + <library name="tika-parser-text-module-2.3.0.jar"/> + <library name="tika-parser-xml-module-2.3.0.jar"/> + <library name="tika-parser-xmp-commons-2.3.0.jar"/> + <library name="tika-parser-zip-commons-2.3.0.jar"/> <library name="txw2-2.3.5.jar"/> <library name="vinnie-2.0.2.jar"/> <library name="vorbis-java-core-0.8.jar"/> <library name="vorbis-java-tika-0.8.jar"/> - <library name="xmlbeans-3.1.0.jar"/> + <library name="xmlbeans-5.0.3.jar"/> + <library name="xmpbox-2.0.25.jar"/> <library name="xmpcore-6.1.11.jar"/> <library name="xz-1.9.jar"/> <!-- End Any23 dependencies --> diff --git a/src/plugin/language-identifier/ivy.xml b/src/plugin/language-identifier/ivy.xml index feba0bb01..395047c6f 100644 --- a/src/plugin/language-identifier/ivy.xml +++ b/src/plugin/language-identifier/ivy.xml @@ -36,7 +36,7 @@ </publications> <dependencies> - <dependency org="org.apache.tika" name="tika-langdetect-optimaize" rev="2.2.1" conf="*->default"> + <dependency org="org.apache.tika" name="tika-langdetect-optimaize" rev="2.3.0" 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 360b81afe..357c4a67c 100644 --- a/src/plugin/language-identifier/plugin.xml +++ b/src/plugin/language-identifier/plugin.xml @@ -35,8 +35,8 @@ <library name="jsr305-3.0.2.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-2.2.1.jar"/> - </runtime> + <library name="tika-langdetect-optimaize-2.3.0.jar"/> + </runtime> <requires> <import plugin="nutch-extensionpoints"/> diff --git a/src/plugin/parse-tika/ivy.xml b/src/plugin/parse-tika/ivy.xml index f0033b824..f0ec7a8d8 100644 --- a/src/plugin/parse-tika/ivy.xml +++ b/src/plugin/parse-tika/ivy.xml @@ -36,7 +36,7 @@ </publications> <dependencies> - <dependency org="org.apache.tika" name="tika-parsers-standard-package" rev="2.2.1" conf="*->default"> + <dependency org="org.apache.tika" name="tika-parsers-standard-package" rev="2.3.0" conf="*->default"> <!-- exclusions of dependencies provided in Nutch core (ivy/ivy.xml) --> <exclude org="org.apache.tika" name="tika-core" /> <exclude org="org.apache.commons" name="commons-lang3" /> diff --git a/src/plugin/parse-tika/plugin.xml b/src/plugin/parse-tika/plugin.xml index 1d4e2c7b8..d88405bc1 100644 --- a/src/plugin/parse-tika/plugin.xml +++ b/src/plugin/parse-tika/plugin.xml @@ -26,7 +26,6 @@ <export name="*"/> </library> <!-- dependencies of Tika (tika-parsers) --> - <library name="SparseBitSet-1.2.jar"/> <library name="apache-mime4j-core-0.8.4.jar"/> <library name="apache-mime4j-dom-0.8.4.jar"/> <library name="asm-9.2.jar"/> @@ -53,54 +52,58 @@ <library name="java-libpst-0.9.3.jar"/> <library name="jaxb-runtime-2.3.5.jar"/> <library name="jbig2-imageio-3.0.3.jar"/> - <library name="jcl-over-slf4j-1.7.32.jar"/> + <library name="jcl-over-slf4j-1.7.35.jar"/> <library name="jdom2-2.0.6.1.jar"/> <library name="jempbox-1.8.16.jar"/> <library name="jhighlight-1.0.3.jar"/> <library name="jmatio-1.5.jar"/> <library name="juniversalchardet-1.0.3.jar"/> - <library name="junrar-7.4.0.jar"/> + <library name="junrar-7.4.1.jar"/> + <library name="log4j-api-2.17.1.jar"/> <library name="metadata-extractor-2.16.0.jar"/> <library name="parso-2.0.14.jar"/> <library name="pdfbox-2.0.25.jar"/> <library name="pdfbox-debugger-2.0.25.jar"/> <library name="pdfbox-tools-2.0.25.jar"/> - <library name="poi-4.1.2.jar"/> - <library name="poi-ooxml-4.1.2.jar"/> - <library name="poi-ooxml-schemas-4.1.2.jar"/> - <library name="poi-scratchpad-4.1.2.jar"/> - <library name="rome-1.16.0.jar"/> - <library name="rome-utils-1.16.0.jar"/> + <library name="poi-5.2.0.jar"/> + <library name="poi-ooxml-5.2.0.jar"/> + <library name="poi-ooxml-lite-5.2.0.jar"/> + <library name="poi-scratchpad-5.2.0.jar"/> + <library name="rome-1.18.0.jar"/> + <library name="rome-utils-1.18.0.jar"/> + <library name="SparseBitSet-1.2.jar"/> <library name="tagsoup-1.2.1.jar"/> - <library name="tika-parser-apple-module-2.2.1.jar"/> - <library name="tika-parser-audiovideo-module-2.2.1.jar"/> - <library name="tika-parser-cad-module-2.2.1.jar"/> - <library name="tika-parser-code-module-2.2.1.jar"/> - <library name="tika-parser-crypto-module-2.2.1.jar"/> - <library name="tika-parser-digest-commons-2.2.1.jar"/> - <library name="tika-parser-font-module-2.2.1.jar"/> - <library name="tika-parser-html-commons-2.2.1.jar"/> - <library name="tika-parser-html-module-2.2.1.jar"/> - <library name="tika-parser-image-module-2.2.1.jar"/> - <library name="tika-parser-mail-commons-2.2.1.jar"/> - <library name="tika-parser-mail-module-2.2.1.jar"/> - <library name="tika-parser-microsoft-module-2.2.1.jar"/> - <library name="tika-parser-miscoffice-module-2.2.1.jar"/> - <library name="tika-parser-news-module-2.2.1.jar"/> - <library name="tika-parser-ocr-module-2.2.1.jar"/> - <library name="tika-parser-pdf-module-2.2.1.jar"/> - <library name="tika-parser-pkg-module-2.2.1.jar"/> - <library name="tika-parser-text-module-2.2.1.jar"/> - <library name="tika-parser-xml-module-2.2.1.jar"/> - <library name="tika-parser-xmp-commons-2.2.1.jar"/> - <library name="tika-parser-zip-commons-2.2.1.jar"/> - <library name="tika-parsers-standard-package-2.2.1.jar"/> + <library name="tika-parser-apple-module-2.3.0.jar"/> + <library name="tika-parser-audiovideo-module-2.3.0.jar"/> + <library name="tika-parser-cad-module-2.3.0.jar"/> + <library name="tika-parser-code-module-2.3.0.jar"/> + <library name="tika-parser-crypto-module-2.3.0.jar"/> + <library name="tika-parser-digest-commons-2.3.0.jar"/> + <library name="tika-parser-font-module-2.3.0.jar"/> + <library name="tika-parser-html-commons-2.3.0.jar"/> + <library name="tika-parser-html-module-2.3.0.jar"/> + <library name="tika-parser-image-module-2.3.0.jar"/> + <library name="tika-parser-mail-commons-2.3.0.jar"/> + <library name="tika-parser-mail-module-2.3.0.jar"/> + <library name="tika-parser-microsoft-module-2.3.0.jar"/> + <library name="tika-parser-miscoffice-module-2.3.0.jar"/> + <library name="tika-parser-news-module-2.3.0.jar"/> + <library name="tika-parser-ocr-module-2.3.0.jar"/> + <library name="tika-parser-pdf-module-2.3.0.jar"/> + <library name="tika-parser-pkg-module-2.3.0.jar"/> + <library name="tika-parsers-standard-package-2.3.0.jar"/> + <library name="tika-parser-text-module-2.3.0.jar"/> + <library name="tika-parser-xml-module-2.3.0.jar"/> + <library name="tika-parser-xmp-commons-2.3.0.jar"/> + <library name="tika-parser-zip-commons-2.3.0.jar"/> <library name="txw2-2.3.5.jar"/> <library name="vorbis-java-core-0.8.jar"/> <library name="vorbis-java-tika-0.8.jar"/> - <library name="xmlbeans-3.1.0.jar"/> + <library name="xmlbeans-5.0.3.jar"/> + <library name="xmpbox-2.0.25.jar"/> <library name="xmpcore-6.1.11.jar"/> <library name="xz-1.9.jar"/> + <!-- end of dependencies of Tika (tika-parsers) --> </runtime>