This is an automated email from the ASF dual-hosted git repository. tallison pushed a commit to branch branch_1x in repository https://gitbox.apache.org/repos/asf/tika.git
commit 943355e7c2a967029a5d7b5a213e54a8dc142d33 Author: tallison <[email protected]> AuthorDate: Wed Dec 8 12:21:17 2021 -0500 TIKA-3613 -- general dependency upgrades --- CHANGES.txt | 5 + tika-bundle/pom.xml | 8 + tika-langdetect/pom.xml | 1 - tika-parent/pom.xml | 1123 ++++++++++---------- tika-parsers/pom.xml | 1 - .../org/apache/tika/parser/epub/EpubParser.java | 2 +- .../microsoft/ooxml/OOXMLExtractorFactory.java | 22 +- .../apache/tika/parser/epub/EpubParserTest.java | 1 + .../tika/parser/microsoft/WordParserTest.java | 7 - 9 files changed, 600 insertions(+), 570 deletions(-) diff --git a/CHANGES.txt b/CHANGES.txt index 612d8ae..414fc1f 100644 --- a/CHANGES.txt +++ b/CHANGES.txt @@ -1,3 +1,8 @@ +Release 1.27.1 - ??? + + * General dependency upgrades (TIKA-3613). + + Release 1.27 - 06/30/2021 * Migrate MP4 parsing to Drew Noakes' metadata-extractor (TIKA-3459). diff --git a/tika-bundle/pom.xml b/tika-bundle/pom.xml index de9386d..604ae32 100644 --- a/tika-bundle/pom.xml +++ b/tika-bundle/pom.xml @@ -299,6 +299,7 @@ edu.usc.irds.agepredictor.spark.authorage;resolution:=optional, javax.activation;resolution:=optional, javax.annotation;resolution:=optional, + javax.annotation.meta;resolution:=optional, javax.mail;resolution:=optional, javax.mail.internet;resolution:=optional, javax.net.ssl;resolution:=optional, @@ -356,9 +357,15 @@ org.apache.sis.coverage.grid;resolution:=optional, org.apache.sis.distance;resolution:=optional, org.apache.sis.feature;resolution:=optional, + org.apache.sis.feature.builder;resolution:=optional, + org.apache.sis.filter;resolution:=optional, org.apache.sis.geometry;resolution:=optional, + org.apache.sis.image;resolution:=optional, org.apache.sis.internal.coverage;resolution:=optional, + org.apache.sis.internal.coverage.j2d;resolution:=optional, org.apache.sis.internal.feature;resolution:=optional, + org.apache.sis.internal.filter;resolution:=optional, + org.apache.sis.internal.geoapi.filter;resolution:=optional, org.apache.sis.internal.referencing;resolution:=optional, org.apache.sis.internal.referencing.j2d;resolution:=optional, org.apache.sis.internal.referencing.provider;resolution:=optional, @@ -368,6 +375,7 @@ org.apache.sis.referencing.crs;resolution:=optional, org.apache.sis.referencing.cs;resolution:=optional, org.apache.sis.referencing.datum;resolution:=optional, + org.apache.sis.referencing.factory;resolution:=optional, org.apache.sis.referencing.operation;resolution:=optional, org.apache.sis.referencing.operation.builder;resolution:=optional, org.apache.sis.referencing.operation.matrix;resolution:=optional, diff --git a/tika-langdetect/pom.xml b/tika-langdetect/pom.xml index 6b514a1..ea48ea5 100644 --- a/tika-langdetect/pom.xml +++ b/tika-langdetect/pom.xml @@ -48,7 +48,6 @@ <dependency> <groupId>org.glassfish.jaxb</groupId> <artifactId>jaxb-runtime</artifactId> - <version>${jaxb.version}</version> <exclusions> <exclusion> <groupId>jakarta.activation</groupId> diff --git a/tika-parent/pom.xml b/tika-parent/pom.xml index 742aae3..e44185a 100644 --- a/tika-parent/pom.xml +++ b/tika-parent/pom.xml @@ -19,328 +19,266 @@ under the License. --> -<project xmlns="http://maven.apache.org/POM/4.0.0"; xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"; xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd";> - <modelVersion>4.0.0</modelVersion> +<project xmlns="http://maven.apache.org/POM/4.0.0"; xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"; + xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd";> + <modelVersion>4.0.0</modelVersion> - <parent> - <groupId>org.apache</groupId> - <artifactId>apache</artifactId> - <version>17</version> - <relativePath /> - </parent> + <parent> + <groupId>org.apache</groupId> + <artifactId>apache</artifactId> + <version>17</version> + <relativePath/> + </parent> - <groupId>org.apache.tika</groupId> - <artifactId>tika-parent</artifactId> - <version>1.28-SNAPSHOT</version> - <packaging>pom</packaging> + <groupId>org.apache.tika</groupId> + <artifactId>tika-parent</artifactId> + <version>1.28-SNAPSHOT</version> + <packaging>pom</packaging> - <name>Apache Tika parent</name> - <description> - Apache Tika is a toolkit for detecting and extracting metadata and - structured text content from various documents using existing parser - libraries. - </description> - <inceptionYear>2007</inceptionYear> + <name>Apache Tika parent</name> + <description> + Apache Tika is a toolkit for detecting and extracting metadata and + structured text content from various documents using existing parser + libraries. + </description> + <inceptionYear>2007</inceptionYear> - <url>http://tika.apache.org/</url> + <url>http://tika.apache.org/</url> - <issueManagement> - <system>JIRA</system> - <url>https://issues.apache.org/jira/browse/TIKA</url> - </issueManagement> + <issueManagement> + <system>JIRA</system> + <url>https://issues.apache.org/jira/browse/TIKA</url> + </issueManagement> - <mailingLists> - <mailingList> - <name>Development mailing list</name> - <subscribe>[email protected]</subscribe> - <unsubscribe>[email protected]</unsubscribe> - <post>[email protected]</post> - <archive>https://lists.apache.org/[email protected]</archive> - <otherArchives> - <otherArchive>http://mail-archives.apache.org/mod_mbox/tika-dev/</otherArchive> - <otherArchive>http://mail-archives.apache.org/mod_mbox/lucene-tika-dev</otherArchive> - <otherArchive>http://www.mail-archive.com/[email protected]</otherArchive> - <otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive> - <otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive> - <otherArchive>http://www.nabble.com/Apache-Tika---Development-f20913.html</otherArchive> - <otherArchive>http://news.gmane.org/gmane.comp.apache.tika.devel</otherArchive> - <otherArchive>http://tika.markmail.org/</otherArchive> - </otherArchives> - </mailingList> - <mailingList> - <name>Commit mailing list</name> - <subscribe>[email protected]</subscribe> - <unsubscribe>[email protected]</unsubscribe> - <post>[email protected]</post> - <archive>https://lists.apache.org/[email protected]</archive> - <otherArchives> - <otherArchive>http://mail-archives.apache.org/mod_mbox/tika-commits/</otherArchive> - <otherArchive>http://mail-archives.apache.org/mod_mbox/lucene-tika-commits/</otherArchive> - <otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive> - <otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive> - </otherArchives> - </mailingList> - <mailingList> - <name>User mailing list</name> - <subscribe>[email protected]</subscribe> - <unsubscribe>[email protected]</unsubscribe> - <post>[email protected]</post> - <archive>https://lists.apache.org/[email protected]</archive> - <otherArchives> - <otherArchive>http://mail-archives.apache.org/mod_mbox/tika-user/</otherArchive> - <otherArchive>http://mail-archives.apache.org/mod_mbox/lucene-tika-user/</otherArchive> - <otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive> - </otherArchives> - </mailingList> - </mailingLists> + <mailingLists> + <mailingList> + <name>Development mailing list</name> + <subscribe>[email protected]</subscribe> + <unsubscribe>[email protected]</unsubscribe> + <post>[email protected]</post> + <archive>https://lists.apache.org/[email protected]</archive> + <otherArchives> + <otherArchive>http://mail-archives.apache.org/mod_mbox/tika-dev/</otherArchive> + <otherArchive>http://mail-archives.apache.org/mod_mbox/lucene-tika-dev</otherArchive> + <otherArchive>http://www.mail-archive.com/[email protected]</otherArchive> + <otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive> + <otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive> + <otherArchive>http://www.nabble.com/Apache-Tika---Development-f20913.html</otherArchive> + <otherArchive>http://news.gmane.org/gmane.comp.apache.tika.devel</otherArchive> + <otherArchive>http://tika.markmail.org/</otherArchive> + </otherArchives> + </mailingList> + <mailingList> + <name>Commit mailing list</name> + <subscribe>[email protected]</subscribe> + <unsubscribe>[email protected]</unsubscribe> + <post>[email protected]</post> + <archive>https://lists.apache.org/[email protected]</archive> + <otherArchives> + <otherArchive>http://mail-archives.apache.org/mod_mbox/tika-commits/</otherArchive> + <otherArchive>http://mail-archives.apache.org/mod_mbox/lucene-tika-commits/</otherArchive> + <otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive> + <otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive> + </otherArchives> + </mailingList> + <mailingList> + <name>User mailing list</name> + <subscribe>[email protected]</subscribe> + <unsubscribe>[email protected]</unsubscribe> + <post>[email protected]</post> + <archive>https://lists.apache.org/[email protected]</archive> + <otherArchives> + <otherArchive>http://mail-archives.apache.org/mod_mbox/tika-user/</otherArchive> + <otherArchive>http://mail-archives.apache.org/mod_mbox/lucene-tika-user/</otherArchive> + <otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive> + </otherArchives> + </mailingList> + </mailingLists> - <developers> - <developer> - <name>Rida Benjelloun</name> - <id>ridabenjelloun</id> - <email>[email protected]</email> - <roles> - <role>committer</role> - </roles> - </developer> - <developer> - <name>Keith Bennett</name> - <id>kbennett</id> - <roles> - <role>committer</role> - </roles> - </developer> - <developer> - <name>Mark Harwood</name> - <id>mharwood</id> - <roles> - <role>committer</role> - </roles> - </developer> - <developer> - <name>Ken Krugler</name> - <id>kkrugler</id> - <email>[email protected]</email> - <url>http://ken-blog.krugler.org</url> - <organization>Scale Unlimited</organization> - <organizationUrl>http://www.scaleunlimited.com</organizationUrl> - <roles> - <role>committer</role> - </roles> - </developer> - <developer> - <name>Chris A. Mattmann</name> - <id>mattmann</id> - <email>[email protected]</email> - <url>http://people.apache.org/~mattmann/</url> - <organization>NASA Jet Propulsion Laboratory</organization> - <organizationUrl>http://www.jpl.nasa.gov</organizationUrl> - <timezone>-8</timezone> - <properties /> - <roles> - <role>committer</role> - </roles> - </developer> - <developer> - <name>Michael McCandless</name> - <id>mikemccand</id> - <email>[email protected]</email> - <organization>IBM</organization> - <properties /> - <roles> - <role>committer</role> - </roles> - </developer> - <developer> - <name>Dave Meikle</name> - <id>dmeikle</id> - <roles> - <role>committer</role> - </roles> - </developer> - <developer> - <name>Sami Siren</name> - <id>siren</id> - <roles> - <role>committer</role> - </roles> - </developer> - <developer> - <name>Jukka Zitting</name> - <id>jukka</id> - <roles> - <role>committer</role> - </roles> - </developer> - <developer> - <name>Nick Burch</name> - <id>nick</id> - <organization>Alfresco</organization> - <organizationUrl>http://alfresco.com</organizationUrl> - <roles> - <role>committer</role> - </roles> - </developer> - <developer> - <name>Maxim Valyanskiy</name> - <id>maxcom</id> - <organization>Jet Infosystems</organization> - <roles> - <role>committer</role> - </roles> - <timezone>+3</timezone> - </developer> - <developer> - <name>Oleg Tikhonov</name> - <id>oleg</id> - <roles> - <role>committer</role> - </roles> - <timezone>+2</timezone> - </developer> - <developer> - <name>Ray Gauss II</name> - <id>rgauss</id> - <organization>Alfresco</organization> - <organizationUrl>http://alfresco.com</organizationUrl> - <timezone>-5</timezone> - <roles> - <role>committer</role> - </roles> - </developer> - <developer> - <name>Tyler Palsulich</name> - <id>tpalsulich</id> - <timezone>-8</timezone> - <roles> - <role>committer</role> - </roles> - </developer> - <developer> - <name>Tim Allison</name> - <id>tallison</id> - <timezone>-5</timezone> - <roles> - <role>committer</role> - </roles> - </developer> - <developer> - <name>Konstantin Gribov</name> - <id>grossws</id> - <timezone>+3</timezone> - <roles> - <role>committer</role> - </roles> - </developer> - </developers> - <contributors> - <contributor> - <name>Doug Cutting</name> - <roles> - <role>mentor</role> - </roles> - </contributor> - <contributor> - <name>Bertrand Delacretaz</name> - <roles> - <role>mentor</role> - </roles> - </contributor> - <contributor> - <name>Niall Pemberton</name> - <roles> - <role>emeritus</role> - </roles> - </contributor> - </contributors> - - <dependencyManagement> - <dependencies> - <dependency> - <groupId>biz.aQute</groupId> - <artifactId>bndlib</artifactId> - <version>1.50.0</version> - </dependency> - <dependency> - <groupId>org.apache.felix</groupId> - <artifactId>org.apache.felix.scr.annotations</artifactId> - <version>1.12.0</version> - </dependency> - <dependency> - <groupId>junit</groupId> - <artifactId>junit</artifactId> - <version>4.13.2</version> - <scope>test</scope> - </dependency> - <dependency> - <groupId>org.slf4j</groupId> - <artifactId>slf4j-api</artifactId> - <version>${slf4j.version}</version> - </dependency> - <dependency> - <groupId>org.slf4j</groupId> - <artifactId>slf4j-log4j12</artifactId> - <version>${slf4j.version}</version> - </dependency> - <dependency> - <groupId>org.slf4j</groupId> - <artifactId>slf4j-simple</artifactId> - <version>${slf4j.version}</version> - </dependency> - <dependency> - <groupId>org.slf4j</groupId> - <artifactId>jcl-over-slf4j</artifactId> - <version>${slf4j.version}</version> - </dependency> - <dependency> - <groupId>org.slf4j</groupId> - <artifactId>jul-to-slf4j</artifactId> - <version>${slf4j.version}</version> - </dependency> - - <dependency> - <groupId>jakarta.annotation</groupId> - <artifactId>jakarta.annotation-api</artifactId> - <version>1.3.5</version> - </dependency> - <dependency> - <groupId>javax.xml.soap</groupId> - <artifactId>javax.xml.soap-api</artifactId> - <version>1.4.0</version> - </dependency> - <dependency> - <groupId>org.jvnet.staxex</groupId> - <artifactId>stax-ex</artifactId> - <version>2.0.1</version> - </dependency> - </dependencies> - </dependencyManagement> - - <properties> - <maven.compiler.source>1.8</maven.compiler.source> - <maven.compiler.target>1.8</maven.compiler.target> - <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> - <project.reporting.outputEncoding>${project.build.sourceEncoding}</project.reporting.outputEncoding> - <!-- plugin versions --> - <forbiddenapis.version>3.1</forbiddenapis.version> - <groovy.maven.version>2.1.1</groovy.maven.version> - <maven.antrun.version>1.8</maven.antrun.version> - <maven.assembly.version>3.3.0</maven.assembly.version> - <maven.bundle.version>5.1.1</maven.bundle.version> - <maven.failsafe.version>2.22.2</maven.failsafe.version> - <maven.javadoc.version>3.1.1</maven.javadoc.version> - <maven.scr.version>1.26.4</maven.scr.version> - <maven.surefire.version>3.0.0-M4</maven.surefire.version> - <maven.shade.version>3.2.4</maven.shade.version> - <rat.version>0.13</rat.version> - <!-- NOTE: sync tukaani version with commons-compress in tika-parsers --> - <poi.version>4.1.2</poi.version> - <commons.compress.version>1.21</commons.compress.version> - <commons.io.version>2.11.0</commons.io.version> - <commons.lang3.version>3.12.0</commons.lang3.version> - <gson.version>2.8.9</gson.version> - <guava.version>31.0.1-jre</guava.version> - <osgi.core.version>6.0.0</osgi.core.version> + <developers> + <developer> + <name>Rida Benjelloun</name> + <id>ridabenjelloun</id> + <email>[email protected]</email> + <roles> + <role>committer</role> + </roles> + </developer> + <developer> + <name>Keith Bennett</name> + <id>kbennett</id> + <roles> + <role>committer</role> + </roles> + </developer> + <developer> + <name>Mark Harwood</name> + <id>mharwood</id> + <roles> + <role>committer</role> + </roles> + </developer> + <developer> + <name>Ken Krugler</name> + <id>kkrugler</id> + <email>[email protected]</email> + <url>http://ken-blog.krugler.org</url> + <organization>Scale Unlimited</organization> + <organizationUrl>http://www.scaleunlimited.com</organizationUrl> + <roles> + <role>committer</role> + </roles> + </developer> + <developer> + <name>Chris A. Mattmann</name> + <id>mattmann</id> + <email>[email protected]</email> + <url>http://people.apache.org/~mattmann/</url> + <organization>NASA Jet Propulsion Laboratory</organization> + <organizationUrl>http://www.jpl.nasa.gov</organizationUrl> + <timezone>-8</timezone> + <properties/> + <roles> + <role>committer</role> + </roles> + </developer> + <developer> + <name>Michael McCandless</name> + <id>mikemccand</id> + <email>[email protected]</email> + <organization>IBM</organization> + <properties/> + <roles> + <role>committer</role> + </roles> + </developer> + <developer> + <name>Dave Meikle</name> + <id>dmeikle</id> + <roles> + <role>committer</role> + </roles> + </developer> + <developer> + <name>Sami Siren</name> + <id>siren</id> + <roles> + <role>committer</role> + </roles> + </developer> + <developer> + <name>Jukka Zitting</name> + <id>jukka</id> + <roles> + <role>committer</role> + </roles> + </developer> + <developer> + <name>Nick Burch</name> + <id>nick</id> + <organization>Alfresco</organization> + <organizationUrl>http://alfresco.com</organizationUrl> + <roles> + <role>committer</role> + </roles> + </developer> + <developer> + <name>Maxim Valyanskiy</name> + <id>maxcom</id> + <organization>Jet Infosystems</organization> + <roles> + <role>committer</role> + </roles> + <timezone>+3</timezone> + </developer> + <developer> + <name>Oleg Tikhonov</name> + <id>oleg</id> + <roles> + <role>committer</role> + </roles> + <timezone>+2</timezone> + </developer> + <developer> + <name>Ray Gauss II</name> + <id>rgauss</id> + <organization>Alfresco</organization> + <organizationUrl>http://alfresco.com</organizationUrl> + <timezone>-5</timezone> + <roles> + <role>committer</role> + </roles> + </developer> + <developer> + <name>Tyler Palsulich</name> + <id>tpalsulich</id> + <timezone>-8</timezone> + <roles> + <role>committer</role> + </roles> + </developer> + <developer> + <name>Tim Allison</name> + <id>tallison</id> + <timezone>-5</timezone> + <roles> + <role>committer</role> + </roles> + </developer> + <developer> + <name>Konstantin Gribov</name> + <id>grossws</id> + <timezone>+3</timezone> + <roles> + <role>committer</role> + </roles> + </developer> + </developers> + <contributors> + <contributor> + <name>Doug Cutting</name> + <roles> + <role>mentor</role> + </roles> + </contributor> + <contributor> + <name>Bertrand Delacretaz</name> + <roles> + <role>mentor</role> + </roles> + </contributor> + <contributor> + <name>Niall Pemberton</name> + <roles> + <role>emeritus</role> + </roles> + </contributor> + </contributors> + <properties> + <maven.compiler.source>1.8</maven.compiler.source> + <maven.compiler.target>1.8</maven.compiler.target> + <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> + <project.reporting.outputEncoding>${project.build.sourceEncoding}</project.reporting.outputEncoding> + <!-- plugin versions --> + <forbiddenapis.version>3.1</forbiddenapis.version> + <groovy.maven.version>2.1.1</groovy.maven.version> + <maven.antrun.version>1.8</maven.antrun.version> + <maven.assembly.version>3.3.0</maven.assembly.version> + <maven.bundle.version>5.1.1</maven.bundle.version> + <maven.failsafe.version>2.22.2</maven.failsafe.version> + <maven.javadoc.version>3.1.1</maven.javadoc.version> + <maven.scr.version>1.26.4</maven.scr.version> + <maven.surefire.version>3.0.0-M4</maven.surefire.version> + <maven.shade.version>3.2.4</maven.shade.version> + <rat.version>0.13</rat.version> + <!-- NOTE: sync tukaani version with commons-compress in tika-parsers --> + <poi.version>4.1.2</poi.version> + <commons.compress.version>1.21</commons.compress.version> + <commons.io.version>2.11.0</commons.io.version> + <commons.lang3.version>3.12.0</commons.lang3.version> + <gson.version>2.8.9</gson.version> + <guava.version>31.0.1-jre</guava.version> + <osgi.core.version>6.0.0</osgi.core.version> <cxf.version>3.4.5</cxf.version> <slf4j.version>1.7.30</slf4j.version> @@ -350,261 +288,328 @@ javax.activation dependency in tika-server. Until then, DO NOT go above 2.x unless you know what you're doing. See TIKA-3407 --> - <jaxb.version>2.3.4</jaxb.version> + <jaxb.version>2.3.5</jaxb.version> <cli.version>1.5.0</cli.version> <lucene.version>8.9.0</lucene.version> <mockito.version>3.11.2</mockito.version> <opennlp.version>1.9.4</opennlp.version> </properties> + <dependencyManagement> + <dependencies> + <dependency> + <groupId>biz.aQute</groupId> + <artifactId>bndlib</artifactId> + <version>1.50.0</version> + </dependency> + <dependency> + <groupId>org.glassfish.jaxb</groupId> + <artifactId>jaxb-runtime</artifactId> + <version>${jaxb.version}</version> + </dependency> - <build> - <plugins> - <plugin> - <groupId>org.apache.maven.plugins</groupId> - <artifactId>maven-compiler-plugin</artifactId> - <version>3.8.1</version> - <configuration> - <source>${maven.compiler.source}</source> - <target>${maven.compiler.target}</target> - </configuration> - </plugin> - <!-- - mvn versions:display-plugin-updates - mvn versions:display-dependency-updates - --> - <plugin> - <groupId>org.codehaus.mojo</groupId> - <artifactId>versions-maven-plugin</artifactId> - <version>2.7</version> - <configuration> - <generateBackupPoms>false</generateBackupPoms> - </configuration> - </plugin> - <plugin> - <groupId>org.sonatype.ossindex.maven</groupId> - <artifactId>ossindex-maven-plugin</artifactId> - <version>3.1.0</version> + <dependency> + <groupId>org.apache.felix</groupId> + <artifactId>org.apache.felix.scr.annotations</artifactId> + <version>1.12.0</version> + </dependency> + <dependency> + <groupId>junit</groupId> + <artifactId>junit</artifactId> + <version>4.13.2</version> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.slf4j</groupId> + <artifactId>slf4j-api</artifactId> + <version>${slf4j.version}</version> + </dependency> + <dependency> + <groupId>org.slf4j</groupId> + <artifactId>slf4j-log4j12</artifactId> + <version>${slf4j.version}</version> + </dependency> + <dependency> + <groupId>org.slf4j</groupId> + <artifactId>slf4j-simple</artifactId> + <version>${slf4j.version}</version> + </dependency> + <dependency> + <groupId>org.slf4j</groupId> + <artifactId>jcl-over-slf4j</artifactId> + <version>${slf4j.version}</version> + </dependency> + <dependency> + <groupId>org.slf4j</groupId> + <artifactId>jul-to-slf4j</artifactId> + <version>${slf4j.version}</version> + </dependency> + + <dependency> + <groupId>jakarta.annotation</groupId> + <artifactId>jakarta.annotation-api</artifactId> + <version>1.3.5</version> + </dependency> + <dependency> + <groupId>javax.xml.soap</groupId> + <artifactId>javax.xml.soap-api</artifactId> + <version>1.4.0</version> + </dependency> + <dependency> + <groupId>org.jvnet.staxex</groupId> + <artifactId>stax-ex</artifactId> + <version>2.0.1</version> + </dependency> + </dependencies> + </dependencyManagement> + + <build> + <plugins> + <plugin> + <groupId>org.apache.maven.plugins</groupId> + <artifactId>maven-compiler-plugin</artifactId> + <version>3.8.1</version> + <configuration> + <source>${maven.compiler.source}</source> + <target>${maven.compiler.target}</target> + </configuration> + </plugin> + <!-- + mvn versions:display-plugin-updates + mvn versions:display-dependency-updates + --> + <plugin> + <groupId>org.codehaus.mojo</groupId> + <artifactId>versions-maven-plugin</artifactId> + <version>2.7</version> + <configuration> + <generateBackupPoms>false</generateBackupPoms> + </configuration> + </plugin> + <plugin> + <groupId>org.sonatype.ossindex.maven</groupId> + <artifactId>ossindex-maven-plugin</artifactId> + <version>3.1.0</version> + <configuration> + <fail>false</fail> + <excludeCoordinates> + <coordinate> + <groupId>junit</groupId> + <artifactId>junit</artifactId> + <version>4.13.1</version> + </coordinate> + </excludeCoordinates> + </configuration> + <executions> + <execution> + <id>audit-dependencies</id> + <phase>validate</phase> + <goals> + <goal>audit</goal> + </goals> + </execution> + </executions> + </plugin> + <!-- example of how to ignore coordinates <configuration> - <fail>false</fail> <excludeCoordinates> - <coordinate> - <groupId>junit</groupId> - <artifactId>junit</artifactId> - <version>4.13.1</version> - </coordinate> + <exclude> + <groupId>com.h2database</groupId> + <artifactId>h2</artifactId> + <version>1.4.197</version> + </exclude> </excludeCoordinates> </configuration> - <executions> - <execution> - <id>audit-dependencies</id> - <phase>validate</phase> - <goals> - <goal>audit</goal> - </goals> - </execution> - </executions> - </plugin> - <!-- example of how to ignore coordinates - <configuration> - <excludeCoordinates> - <exclude> - <groupId>com.h2database</groupId> - <artifactId>h2</artifactId> - <version>1.4.197</version> - </exclude> - </excludeCoordinates> - </configuration> - --> + --> - <plugin> - <groupId>de.thetaphi</groupId> - <artifactId>forbiddenapis</artifactId> - <version>${forbiddenapis.version}</version> - <configuration> - <targetVersion>${maven.compiler.target}</targetVersion> - <ignoreSignaturesOfMissingClasses>true</ignoreSignaturesOfMissingClasses> - <failOnUnsupportedJava>false</failOnUnsupportedJava> - <excludes>test-documents/*.class</excludes> - <bundledSignatures> - <bundledSignature>jdk-unsafe</bundledSignature> - <bundledSignature>jdk-deprecated</bundledSignature> - <bundledSignature>jdk-non-portable</bundledSignature> - <bundledSignature>jdk-internal</bundledSignature> - <!-- replace with ${commons.io.version} when available --> - <bundledSignature>commons-io-unsafe-2.7</bundledSignature> - </bundledSignatures> - </configuration> - <executions> - <execution> - <goals> - <goal>check</goal> - <goal>testCheck</goal> - </goals> - </execution> - </executions> - </plugin> - <plugin> - <groupId>org.apache.felix</groupId> - <artifactId>maven-bundle-plugin</artifactId> - <version>${maven.bundle.version}</version> - </plugin> - <plugin> - <groupId>org.apache.maven.plugins</groupId> - <artifactId>maven-surefire-plugin</artifactId> - <version>${maven.surefire.version} - </version> <!-- versions greater than this don't like System.exit calls in tika-batch --> - <configuration> - <argLine>-Xmx3072m -Duser.timezone=UTC -Djava.awt.headless=true</argLine> - </configuration> - </plugin> - <plugin> - <groupId>org.apache.maven.plugins</groupId> - <artifactId>maven-shade-plugin</artifactId> - <version>${maven.shade.version}</version> - </plugin> - <!-- assembly must happen after shade so that - tika-server's -bin.tgz/zip includes the uber jar - --> - <plugin> - <groupId>org.apache.maven.plugins</groupId> - <artifactId>maven-assembly-plugin</artifactId> - <version>${maven.assembly.version}</version> - <configuration> - <tarLongFileMode>posix</tarLongFileMode> - </configuration> - </plugin> - <plugin> - <groupId>org.apache.maven.plugins</groupId> - <artifactId>maven-release-plugin</artifactId> - <version>2.5.3</version> - <dependencies> - <dependency> - <groupId>org.apache.maven.scm</groupId> - <artifactId>maven-scm-provider-gitexe</artifactId> - <version>1.11.2</version> - </dependency> - <dependency> - <groupId>org.apache.maven.scm</groupId> - <artifactId>maven-scm-api</artifactId> - <version>1.11.2</version> - </dependency> - </dependencies> - </plugin> - <plugin> - <groupId>org.apache.maven.plugins</groupId> - <artifactId>maven-enforcer-plugin</artifactId> - <version>3.0.0-M3</version> - <executions> - <execution> - <id>enforce</id> - <configuration> - <rules> - <dependencyConvergence /> - <requireMavenVersion> - <version>3.5</version> - </requireMavenVersion> - </rules> - </configuration> - <goals> - <goal>enforce</goal> - </goals> - </execution> - </executions> - </plugin> - </plugins> - </build> + <plugin> + <groupId>de.thetaphi</groupId> + <artifactId>forbiddenapis</artifactId> + <version>${forbiddenapis.version}</version> + <configuration> + <targetVersion>${maven.compiler.target}</targetVersion> + <ignoreSignaturesOfMissingClasses>true</ignoreSignaturesOfMissingClasses> + <failOnUnsupportedJava>false</failOnUnsupportedJava> + <excludes>test-documents/*.class</excludes> + <bundledSignatures> + <bundledSignature>jdk-unsafe</bundledSignature> + <bundledSignature>jdk-deprecated</bundledSignature> + <bundledSignature>jdk-non-portable</bundledSignature> + <bundledSignature>jdk-internal</bundledSignature> + <!-- replace with ${commons.io.version} when available --> + <bundledSignature>commons-io-unsafe-2.7</bundledSignature> + </bundledSignatures> + </configuration> + <executions> + <execution> + <goals> + <goal>check</goal> + <goal>testCheck</goal> + </goals> + </execution> + </executions> + </plugin> + <plugin> + <groupId>org.apache.felix</groupId> + <artifactId>maven-bundle-plugin</artifactId> + <version>${maven.bundle.version}</version> + </plugin> + <plugin> + <groupId>org.apache.maven.plugins</groupId> + <artifactId>maven-surefire-plugin</artifactId> + <version>${maven.surefire.version} + </version> <!-- versions greater than this don't like System.exit calls in tika-batch --> + <configuration> + <argLine>-Xmx3072m -Duser.timezone=UTC -Djava.awt.headless=true</argLine> + </configuration> + </plugin> + <plugin> + <groupId>org.apache.maven.plugins</groupId> + <artifactId>maven-shade-plugin</artifactId> + <version>${maven.shade.version}</version> + </plugin> + <!-- assembly must happen after shade so that + tika-server's -bin.tgz/zip includes the uber jar + --> + <plugin> + <groupId>org.apache.maven.plugins</groupId> + <artifactId>maven-assembly-plugin</artifactId> + <version>${maven.assembly.version}</version> + <configuration> + <tarLongFileMode>posix</tarLongFileMode> + </configuration> + </plugin> + <plugin> + <groupId>org.apache.maven.plugins</groupId> + <artifactId>maven-release-plugin</artifactId> + <version>2.5.3</version> + <dependencies> + <dependency> + <groupId>org.apache.maven.scm</groupId> + <artifactId>maven-scm-provider-gitexe</artifactId> + <version>1.11.2</version> + </dependency> + <dependency> + <groupId>org.apache.maven.scm</groupId> + <artifactId>maven-scm-api</artifactId> + <version>1.11.2</version> + </dependency> + </dependencies> + </plugin> + <plugin> + <groupId>org.apache.maven.plugins</groupId> + <artifactId>maven-enforcer-plugin</artifactId> + <version>3.0.0-M3</version> + <executions> + <execution> + <id>enforce</id> + <configuration> + <rules> + <dependencyConvergence/> + <requireMavenVersion> + <version>3.5</version> + </requireMavenVersion> + </rules> + </configuration> + <goals> + <goal>enforce</goal> + </goals> + </execution> + </executions> + </plugin> + </plugins> + </build> - <profiles> - <profile> - <id>pedantic</id> - <build> - <plugins> - <plugin> - <groupId>org.apache.rat</groupId> - <artifactId>apache-rat-plugin</artifactId> - <version>${rat.version}</version> - <executions> - <execution> - <phase>verify</phase> - <goals> - <goal>check</goal> - </goals> - </execution> - </executions> - </plugin> - </plugins> - </build> - </profile> - <profile> - <id>sonar</id> - <build> - <plugins> - <plugin> - <groupId>org.apache.maven.plugins</groupId> - <artifactId>maven-surefire-plugin</artifactId> - <configuration> - <excludes> - <exclude>**/ForkParser*Test.java</exclude> - </excludes> - </configuration> - </plugin> - </plugins> - </build> - </profile> - <profile> - <id>doclint-java8-disable</id> - <activation> - <jdk>[1.8,)</jdk> - </activation> - <build> - <plugins> - <plugin> - <groupId>org.apache.maven.plugins</groupId> - <artifactId>maven-javadoc-plugin</artifactId> - <version>${maven.javadoc.version}</version> - <configuration> - <doclint>none</doclint> - <source>1.8</source> - </configuration> - </plugin> - </plugins> - </build> - </profile> - <profile> - <id>jdk9</id> - <activation> - <jdk>[1.9,)</jdk> - </activation> - <build> - <plugins> - <plugin> - <artifactId>maven-compiler-plugin</artifactId> - <configuration> - <release>8</release> - </configuration> - </plugin> - </plugins> - </build> - <!-- keep these at 2.x --> - <dependencies> - <dependency> - <groupId>jakarta.xml.bind</groupId> - <artifactId>jakarta.xml.bind-api</artifactId> - <version>2.3.3</version> - </dependency> - <dependency> - <groupId>jakarta.activation</groupId> - <artifactId>jakarta.activation-api</artifactId> - <version>1.2.2</version> - </dependency> - </dependencies> - </profile> - </profiles> + <profiles> + <profile> + <id>pedantic</id> + <build> + <plugins> + <plugin> + <groupId>org.apache.rat</groupId> + <artifactId>apache-rat-plugin</artifactId> + <version>${rat.version}</version> + <executions> + <execution> + <phase>verify</phase> + <goals> + <goal>check</goal> + </goals> + </execution> + </executions> + </plugin> + </plugins> + </build> + </profile> + <profile> + <id>sonar</id> + <build> + <plugins> + <plugin> + <groupId>org.apache.maven.plugins</groupId> + <artifactId>maven-surefire-plugin</artifactId> + <configuration> + <excludes> + <exclude>**/ForkParser*Test.java</exclude> + </excludes> + </configuration> + </plugin> + </plugins> + </build> + </profile> + <profile> + <id>doclint-java8-disable</id> + <activation> + <jdk>[1.8,)</jdk> + </activation> + <build> + <plugins> + <plugin> + <groupId>org.apache.maven.plugins</groupId> + <artifactId>maven-javadoc-plugin</artifactId> + <version>${maven.javadoc.version}</version> + <configuration> + <doclint>none</doclint> + <source>1.8</source> + </configuration> + </plugin> + </plugins> + </build> + </profile> + <profile> + <id>jdk9</id> + <activation> + <jdk>[1.9,)</jdk> + </activation> + <build> + <plugins> + <plugin> + <artifactId>maven-compiler-plugin</artifactId> + <configuration> + <release>8</release> + </configuration> + </plugin> + </plugins> + </build> + <!-- keep these at 2.x --> + <dependencies> + <dependency> + <groupId>jakarta.xml.bind</groupId> + <artifactId>jakarta.xml.bind-api</artifactId> + <version>2.3.3</version> + </dependency> + <dependency> + <groupId>jakarta.activation</groupId> + <artifactId>jakarta.activation-api</artifactId> + <version>1.2.2</version> + </dependency> + </dependencies> + </profile> + </profiles> - <scm> - <connection>scm:git:https://github.com/apache/</connection> - <developerConnection>scm:git:https://github.com/apache/</developerConnection> - <url>https://github.com/apache/tika</url> - <tag>1.22-rc3</tag> - </scm> + <scm> + <connection>scm:git:https://github.com/apache/</connection> + <developerConnection>scm:git:https://github.com/apache/</developerConnection> + <url>https://github.com/apache/tika</url> + <tag>1.22-rc3</tag> + </scm> </project> diff --git a/tika-parsers/pom.xml b/tika-parsers/pom.xml index bbfef15..1e4df3a 100644 --- a/tika-parsers/pom.xml +++ b/tika-parsers/pom.xml @@ -409,7 +409,6 @@ <dependency> <groupId>org.glassfish.jaxb</groupId> <artifactId>jaxb-runtime</artifactId> - <version>${jaxb.version}</version> </dependency> <!-- TIKA-2021: Tesseract OCR Parser dependencies, used for executing image processing script --> diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/epub/EpubParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/epub/EpubParser.java index a38d45e..0f2f7f7 100644 --- a/tika-parsers/src/main/java/org/apache/tika/parser/epub/EpubParser.java +++ b/tika-parsers/src/main/java/org/apache/tika/parser/epub/EpubParser.java @@ -189,7 +189,7 @@ public class EpubParser extends AbstractParser { ZipFile zipFile = null; try { zipFile = new ZipFile(tis.getPath().toFile()); - } catch (ZipException e) { + } catch (IOException e) { ParserUtils.recordParserFailure(this, e, metadata); trySalvage(tis.getPath(), bodyHandler, xhtml, metadata, context); return; diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java index 51b36c2..1a5eb62 100644 --- a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java +++ b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java @@ -112,7 +112,27 @@ public class OOXMLExtractorFactory { true, false)) { try { pkg = OPCPackage.open(rereadableInputStream); - } catch (EOFException|UnsupportedZipFeatureException e) { + } catch (UnsupportedZipFeatureException e) { + if (e.getFeature() != + UnsupportedZipFeatureException.Feature.DATA_DESCRIPTOR) { + throw e; + } + rereadableInputStream.rewind(); + tmpRepairedCopy = File.createTempFile("tika-ooxml-repair-", ""); + ZipSalvager.salvageCopy(rereadableInputStream, tmpRepairedCopy, false); + //if there isn't enough left to be opened as a package + //throw an exception -- we may want to fall back to streaming + //parsing + pkg = OPCPackage.open(tmpRepairedCopy, PackageAccess.READ); + } catch (IOException e) { + if (e instanceof EOFException) { + //keep going + } else if (e instanceof IOException && e.getMessage() != null && + e.getMessage().contains("Truncated")) { + //keep going + } else { + throw e; + } rereadableInputStream.rewind(); tmpRepairedCopy = File.createTempFile("tika-ooxml-repair-", ""); ZipSalvager.salvageCopy(rereadableInputStream, tmpRepairedCopy, false); diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/epub/EpubParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/epub/EpubParserTest.java index a16732c..9903c21 100644 --- a/tika-parsers/src/test/java/org/apache/tika/parser/epub/EpubParserTest.java +++ b/tika-parsers/src/test/java/org/apache/tika/parser/epub/EpubParserTest.java @@ -105,6 +105,7 @@ public class EpubParserTest extends TikaTest { String xml = metadataList.get(0).get(RecursiveParserWrapperHandler.TIKA_CONTENT); int ch1 = xml.indexOf("<h1>Chapter 1"); int ch2 = xml.indexOf("<h1>Chapter 2"); + assert(ch1 > -1); assert(ch1 < ch2); } diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java index 42c4268..73aa1b8 100644 --- a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java +++ b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java @@ -48,13 +48,6 @@ import org.xml.sax.ContentHandler; public class WordParserTest extends TikaTest { @Test - public void testOneOff() throws Exception { - System.out.println(AbstractRecursiveParserWrapperHandler.CONTAINER_EXCEPTION); - - debug(getRecursiveMetadata("testWORD_various.doc")); - } - - @Test public void testWordParser() throws Exception { try (InputStream input = WordParserTest.class.getResourceAsStream( "/test-documents/testWORD.doc")) {
