[ https://issues.apache.org/jira/browse/NUTCH-2651?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16657921#comment-16657921 ]
ASF GitHub Bot commented on NUTCH-2651: --------------------------------------- sebastian-nagel closed pull request #391: NUTCH-2651 Upgrade core and parse-tika to use Tika 1.19.1 URL: https://github.com/apache/nutch/pull/391 This is a PR merged from a forked repository. As GitHub hides the original diff on merge, it is displayed below for the sake of provenance: As this is a foreign pull request (from a fork), the diff is supplied below (as it won't show otherwise due to GitHub magic): diff --git a/default.properties b/default.properties index d6f606b0c..00af414e3 100644 --- a/default.properties +++ b/default.properties @@ -77,6 +77,14 @@ ivy.shared.default.root=${ivy.default.ivy.user.dir}/shared ivy.shared.default.ivy.pattern=[organisation]/[module]/[revision]/[type]s/[artifact].[ext] ivy.shared.default.artifact.pattern=[organisation]/[module]/[revision]/[type]s/[artifact].[ext] +# work-around to fix failing dependency download of +# javax.ws.rs-api.jar +# required by Tika (1.19 and higher) +# cf. (also affects ant/ivy) +# https://github.com/eclipse-ee4j/jaxrs-api/issues/572 +# https://github.com/gradle/gradle/issues/3065 +packaging.type=jar + # # Plugins API # diff --git a/ivy/ivy.xml b/ivy/ivy.xml index 112975ab9..0da272268 100644 --- a/ivy/ivy.xml +++ b/ivy/ivy.xml @@ -65,7 +65,7 @@ <dependency org="org.apache.hadoop" name="hadoop-mapreduce-client-jobclient" rev="2.7.4" conf="*->default"/> <!-- End of Hadoop Dependencies --> - <dependency org="org.apache.tika" name="tika-core" rev="1.18" /> + <dependency org="org.apache.tika" name="tika-core" rev="1.19.1" /> <dependency org="com.ibm.icu" name="icu4j" rev="61.1" /> <dependency org="xerces" name="xercesImpl" rev="2.11.0" /> diff --git a/src/plugin/parse-tika/ivy.xml b/src/plugin/parse-tika/ivy.xml index 81e7a8038..53c7775a7 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" rev="1.18" conf="*->default"> + <dependency org="org.apache.tika" name="tika-parsers" rev="1.19.1" conf="*->default"> <exclude org="org.apache.tika" name="tika-core" /> <exclude org="org.apache.httpcomponents" name="httpclient" /> <exclude org="org.apache.httpcomponents" name="httpcore" /> diff --git a/src/plugin/parse-tika/plugin.xml b/src/plugin/parse-tika/plugin.xml index 398c0e423..7dbe18093 100644 --- a/src/plugin/parse-tika/plugin.xml +++ b/src/plugin/parse-tika/plugin.xml @@ -26,76 +26,79 @@ <export name="*"/> </library> <!-- dependencies of Tika (tika-parsers) --> - <library name="aopalliance-1.0.jar"/> - <library name="apache-mime4j-core-0.8.1.jar"/> - <library name="apache-mime4j-dom-0.8.1.jar"/> - <library name="asm-5.0.4.jar"/> - <library name="bcmail-jdk15on-1.54.jar"/> - <library name="bcpkix-jdk15on-1.54.jar"/> - <library name="bcprov-jdk15on-1.54.jar"/> + <library name="activation-1.1.1.jar"/> + <library name="apache-mime4j-core-0.8.2.jar"/> + <library name="apache-mime4j-dom-0.8.2.jar"/> + <library name="asm-6.2.jar"/> + <library name="bcmail-jdk15on-1.60.jar"/> + <library name="bcpkix-jdk15on-1.60.jar"/> + <library name="bcprov-jdk15on-1.60.jar"/> <library name="boilerpipe-1.1.0.jar"/> <library name="bzip2-0.9.1.jar"/> <library name="c3p0-0.9.1.1.jar"/> <library name="cdm-4.5.5.jar"/> - <library name="commons-codec-1.10.jar"/> - <library name="commons-collections4-4.1.jar"/> - <library name="commons-compress-1.16.1.jar"/> - <library name="commons-csv-1.0.jar"/> + <library name="commons-codec-1.11.jar"/> + <library name="commons-collections4-4.2.jar"/> + <library name="commons-compress-1.18.jar"/> + <library name="commons-csv-1.5.jar"/> <library name="commons-exec-1.3.jar"/> <library name="commons-io-2.6.jar"/> - <library name="commons-logging-1.1.3.jar"/> <library name="commons-logging-1.2.jar"/> - <library name="commons-logging-api-1.1.jar"/> <library name="curvesapi-1.04.jar"/> - <library name="cxf-core-3.0.16.jar"/> - <library name="cxf-rt-frontend-jaxrs-3.0.16.jar"/> - <library name="cxf-rt-rs-client-3.0.16.jar"/> - <library name="cxf-rt-transports-http-3.0.16.jar"/> + <library name="cxf-core-3.2.6.jar"/> + <library name="cxf-rt-frontend-jaxrs-3.2.6.jar"/> + <library name="cxf-rt-rs-client-3.2.6.jar"/> + <library name="cxf-rt-transports-http-3.2.6.jar"/> <library name="dec-0.1.2.jar"/> <library name="ehcache-core-2.6.2.jar"/> - <library name="fontbox-2.0.9.jar"/> + <library name="FastInfoset-1.2.13.jar"/> + <library name="fontbox-2.0.12.jar"/> <library name="geoapi-3.0.1.jar"/> <library name="grib-4.5.5.jar"/> - <library name="gson-2.8.1.jar"/> + <library name="gson-2.8.5.jar"/> <library name="guava-17.0.jar"/> - <library name="httpmime-4.5.4.jar"/> + <library name="httpmime-4.5.6.jar"/> <library name="httpservices-4.5.5.jar"/> - <library name="isoparser-1.1.18.jar"/> - <library name="jackcess-2.1.10.jar"/> + <library name="isoparser-1.1.22.jar"/> + <library name="istack-commons-runtime-3.0.5.jar"/> + <library name="jackcess-2.1.12.jar"/> <library name="jackcess-encrypt-2.1.4.jar"/> - <library name="jackson-annotations-2.9.5.jar"/> - <library name="jackson-core-2.9.5.jar"/> - <library name="jackson-databind-2.9.5.jar"/> - <library name="jai-imageio-core-1.3.1.jar"/> + <library name="jackson-annotations-2.9.6.jar"/> + <library name="jackson-core-2.9.6.jar"/> + <library name="jackson-databind-2.9.6.jar"/> + <library name="jai-imageio-core-1.4.0.jar"/> <library name="java-libpst-0.8.1.jar"/> - <library name="javax.annotation-api-1.2.jar"/> - <library name="javax.ws.rs-api-2.0.1.jar"/> - <library name="jbig2-imageio-3.0.0.jar"/> + <library name="javax.annotation-api-1.3.jar"/> + <library name="javax.ws.rs-api-2.1.jar"/> + <library name="jaxb-api-2.3.0.jar"/> + <library name="jaxb-core-2.3.0.1.jar"/> + <library name="jaxb-runtime-2.3.0.1.jar"/> + <library name="jbig2-imageio-3.0.2.jar"/> <library name="jcip-annotations-1.0.jar"/> - <library name="jcl-over-slf4j-1.7.24.jar"/> + <library name="jcl-over-slf4j-1.7.25.jar"/> <library name="jcommander-1.35.jar"/> <library name="jdom2-2.0.6.jar"/> - <library name="jempbox-1.8.13.jar"/> - <library name="jhighlight-1.0.2.jar"/> - <library name="jmatio-1.2.jar"/> - <library name="jna-4.1.0.jar"/> + <library name="jempbox-1.8.16.jar"/> + <library name="jhighlight-1.0.3.jar"/> + <library name="jmatio-1.5.jar"/> + <library name="jna-4.3.0.jar"/> <library name="joda-time-2.2.jar"/> <library name="json-simple-1.1.1.jar"/> - <library name="jsoup-1.11.2.jar"/> - <library name="jul-to-slf4j-1.7.24.jar"/> + <library name="jsoup-1.11.3.jar"/> + <library name="jul-to-slf4j-1.7.25.jar"/> <library name="juniversalchardet-1.0.3.jar"/> - <library name="junrar-0.7.jar"/> - <library name="metadata-extractor-2.10.1.jar"/> + <library name="junrar-2.0.0.jar"/> + <library name="metadata-extractor-2.11.0.jar"/> <library name="netcdf4-4.5.5.jar"/> - <library name="objenesis-2.6.jar"/> <library name="openjson-1.0.10.jar"/> - <library name="opennlp-tools-1.8.4.jar"/> - <library name="pdfbox-2.0.9.jar"/> - <library name="pdfbox-tools-2.0.9.jar"/> - <library name="poi-3.17.jar"/> - <library name="poi-ooxml-3.17.jar"/> - <library name="poi-ooxml-schemas-3.17.jar"/> - <library name="poi-scratchpad-3.17.jar"/> + <library name="opennlp-tools-1.9.0.jar"/> + <library name="parso-2.0.9.jar"/> + <library name="pdfbox-2.0.12.jar"/> + <library name="pdfbox-tools-2.0.12.jar"/> + <library name="poi-4.0.0.jar"/> + <library name="poi-ooxml-4.0.0.jar"/> + <library name="poi-ooxml-schemas-4.0.0.jar"/> + <library name="poi-scratchpad-4.0.0.jar"/> <library name="quartz-2.2.0.jar"/> <library name="rome-1.5.1.jar"/> <library name="rome-utils-1.5.1.jar"/> @@ -106,23 +109,20 @@ <library name="sis-referencing-0.8.jar"/> <library name="sis-storage-0.8.jar"/> <library name="sis-utility-0.8.jar"/> - <library name="spring-aop-3.2.16.RELEASE.jar"/> - <library name="spring-beans-3.2.16.RELEASE.jar"/> - <library name="spring-context-3.2.16.RELEASE.jar"/> - <library name="spring-core-3.2.16.RELEASE.jar"/> - <library name="spring-expression-3.2.16.RELEASE.jar"/> - <library name="stax2-api-3.1.4.jar"/> + <library name="stax2-api-4.1.jar"/> + <library name="stax-ex-1.7.8.jar"/> <library name="tagsoup-1.2.1.jar"/> - <library name="tika-parsers-1.18.jar"/> + <library name="tika-parsers-1.19.1.jar"/> + <library name="txw2-2.3.0.1.jar"/> <library name="udunits-4.5.5.jar"/> <library name="uimafit-core-2.2.0.jar"/> <library name="uimaj-core-2.9.0.jar"/> <library name="unit-api-1.0.jar"/> <library name="vorbis-java-core-0.8.jar"/> <library name="vorbis-java-tika-0.8.jar"/> - <library name="woodstox-core-asl-4.4.1.jar"/> - <library name="xmlbeans-2.6.0.jar"/> - <library name="xmlschema-core-2.2.2.jar"/> + <library name="woodstox-core-5.1.0.jar"/> + <library name="xmlbeans-3.0.1.jar"/> + <library name="xmlschema-core-2.2.3.jar"/> <library name="xmpcore-5.1.3.jar"/> <library name="xz-1.8.jar"/> <!-- end of dependencies of Tika (tika-parsers) --> ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org > Upgrade to Tika 1.19.1 (from 1.18) > ---------------------------------- > > Key: NUTCH-2651 > URL: https://issues.apache.org/jira/browse/NUTCH-2651 > Project: Nutch > Issue Type: Improvement > Components: parser, protocol > Affects Versions: 1.15 > Reporter: Sebastian Nagel > Priority: Major > Fix For: 1.16 > > > [Tika 1.19.1|https://tika.apache.org/1.19.1/index.html] has been released > recently. Among all the other improvements and fixes (including those of > [1.19|https://tika.apache.org/1.19/index.html]) It contains one important > performance fix (TIKA-2645, cf. NUTCH-2578) affecting the MIME-/Content-Type > detector. -- This message was sent by Atlassian JIRA (v7.6.3#76005)