You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2018/07/26 20:28:39 UTC
[tika] 03/03: TIKA-2692 -- general upgrades in prep for 1.19
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 1438d8a22a634912d7a5ccbfd6f9c3d4543de583
Author: TALLISON <ta...@apache.org>
AuthorDate: Thu Jul 26 15:17:38 2018 -0400
TIKA-2692 -- general upgrades in prep for 1.19
# Conflicts:
# tika-dl/pom.xml
# tika-parsers/pom.xml
---
tika-bundle/pom.xml | 1 +
tika-parent/pom.xml | 8 ++--
tika-parsers/pom.xml | 56 +++++++++++++++++-----
.../java/org/apache/tika/parser/pkg/RarParser.java | 3 +-
4 files changed, 51 insertions(+), 17 deletions(-)
diff --git a/tika-bundle/pom.xml b/tika-bundle/pom.xml
index b08cb9e..584d8e8 100644
--- a/tika-bundle/pom.xml
+++ b/tika-bundle/pom.xml
@@ -144,6 +144,7 @@
<configuration>
<instructions>
<_runsystempackages>com.sun.xml.bind.marshaller, com.sun.xml.internal.bind.marshaller</_runsystempackages>
+ <_noee>true</_noee>
<Bundle-Activator>
org.apache.tika.parser.internal.Activator
</Bundle-Activator>
diff --git a/tika-parent/pom.xml b/tika-parent/pom.xml
index 9110f42..baa7ec1 100644
--- a/tika-parent/pom.xml
+++ b/tika-parent/pom.xml
@@ -308,10 +308,10 @@
<!-- NOTE: sync tukaani version with commons-compress in tika-parsers -->
<commons.compress.version>1.17</commons.compress.version>
<commons.io.version>2.6</commons.io.version>
- <gson.version>2.8.1</gson.version>
+ <gson.version>2.8.5</gson.version>
<cxf.version>3.2.5</cxf.version>
- <slf4j.version>1.7.24</slf4j.version>
- <jackson.version>2.9.5</jackson.version>
+ <slf4j.version>1.7.25</slf4j.version>
+ <jackson.version>2.9.6</jackson.version>
<jaxb.version>2.3.0</jaxb.version>
<mockito.version>2.20.0</mockito.version>
</properties>
@@ -355,7 +355,7 @@
<plugin>
<groupId>org.apache.felix</groupId>
<artifactId>maven-bundle-plugin</artifactId>
- <version>3.3.0</version>
+ <version>3.5.1</version>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
diff --git a/tika-parsers/pom.xml b/tika-parsers/pom.xml
index 38b15db..6b51f30 100644
--- a/tika-parsers/pom.xml
+++ b/tika-parsers/pom.xml
@@ -37,17 +37,18 @@
<properties>
<poi.version>3.17</poi.version>
<!-- NOTE: sync codec version with POI -->
- <codec.version>1.10</codec.version>
+ <codec.version>1.11</codec.version>
<!-- NOTE: sync tukaani version with commons-compress in tika-parent-->
<tukaani.version>1.8</tukaani.version>
<!-- NOTE: sync brotli version with commons-compress in tika-parent-->
<brotli.version>0.1.2</brotli.version>
- <mime4j.version>0.8.1</mime4j.version>
+ <mime4j.version>0.8.2</mime4j.version>
<vorbis.version>0.8</vorbis.version>
<pdfbox.version>2.0.11</pdfbox.version>
<jempbox.version>1.8.15</jempbox.version>
<netcdf-java.version>4.5.5</netcdf-java.version>
<sis.version>0.8</sis.version>
+ <parso.version>2.0.9</parso.version>
<!-- used by POI, PDFBox and Jackcess ...try to sync -->
<bouncycastle.version>1.60</bouncycastle.version>
<commonsexec.version>1.3</commonsexec.version>
@@ -115,7 +116,7 @@
<dependency>
<groupId>com.healthmarketscience.jackcess</groupId>
<artifactId>jackcess</artifactId>
- <version>2.1.10</version>
+ <version>2.1.12</version>
<exclusions>
<exclusion>
<groupId>commons-logging</groupId>
@@ -239,6 +240,12 @@
<groupId>org.apache.poi</groupId>
<artifactId>poi</artifactId>
<version>${poi.version}</version>
+ <exclusions>
+ <exclusion>
+ <groupId>commons-codec</groupId>
+ <artifactId>commons-codec</artifactId>
+ </exclusion>
+ </exclusions>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
@@ -268,17 +275,17 @@
<dependency>
<groupId>org.ow2.asm</groupId>
<artifactId>asm</artifactId>
- <version>5.0.4</version>
+ <version>6.2</version>
</dependency>
<dependency>
<groupId>com.googlecode.mp4parser</groupId>
<artifactId>isoparser</artifactId>
- <version>1.1.18</version>
+ <version>1.1.22</version>
</dependency>
<dependency>
<groupId>com.drewnoakes</groupId>
<artifactId>metadata-extractor</artifactId>
- <version>2.10.1</version>
+ <version>2.11.0</version>
</dependency>
<dependency>
<groupId>de.l3s.boilerpipe</groupId>
@@ -309,7 +316,13 @@
<dependency>
<groupId>org.codelibs</groupId>
<artifactId>jhighlight</artifactId>
- <version>1.0.2</version>
+ <version>1.0.3</version>
+ <exclusions>
+ <exclusion>
+ <groupId>commons-io</groupId>
+ <artifactId>commons-io</artifactId>
+ </exclusion>
+ </exclusions>
</dependency>
<!-- can't upgrade to java-libpst 0.9.3 because it requires Java 8
and is buggy with OST TIKA-2415 -->
@@ -321,7 +334,7 @@
<dependency>
<groupId>com.github.junrar</groupId>
<artifactId>junrar</artifactId>
- <version>1.0.1</version>
+ <version>2.0.0</version>
<exclusions>
<exclusion>
<groupId>commons-logging</groupId>
@@ -363,7 +376,7 @@
<dependency>
<groupId>org.apache.opennlp</groupId>
<artifactId>opennlp-tools</artifactId>
- <version>1.8.4</version>
+ <version>1.9.0</version>
</dependency>
<dependency>
@@ -446,6 +459,12 @@
<groupId>org.jdom</groupId>
<artifactId>jdom2</artifactId>
</exclusion>
+ <!--TIKA 2672 exclude jna to resolve the dependency convergence with tika-dl's
+ deeplearning4j-nn:1.0.0-SNAPSHOT-->
+ <exclusion>
+ <groupId>net.java.dev.jna</groupId>
+ <artifactId>jna</artifactId>
+ </exclusion>
</exclusions>
</dependency>
<dependency>
@@ -467,13 +486,22 @@
</exclusion>
</exclusions>
</dependency>
+ <!--TIKA 2672 include a later version of jna as a direct dependency to resolve dependency convergence with tika-dl's
+ deeplearning4j-nn:1.0.0-SNAPSHOT -->
+ <dependency>
+ <groupId>net.java.dev.jna</groupId>
+ <artifactId>jna</artifactId>
+ <version>4.3.0</version>
+ </dependency>
+
<!-- grib's current jsoup is vulnerable to xss
exclude and import a more modern version TIKA-2561-->
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
- <version>1.11.2</version>
- </dependency> <dependency>
+ <version>1.11.3</version>
+ </dependency>
+ <dependency>
<groupId>edu.ucar</groupId>
<artifactId>cdm</artifactId>
<version>${netcdf-java.version}</version>
@@ -529,6 +557,10 @@
<groupId>commons-logging</groupId>
<artifactId>commons-logging</artifactId>
</exclusion>
+ <exclusion>
+ <groupId>commons-codec</groupId>
+ <artifactId>commons-codec</artifactId>
+ </exclusion>
</exclusions>
</dependency>
<dependency>
@@ -541,7 +573,7 @@
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-csv</artifactId>
- <version>1.0</version>
+ <version>1.5</version>
</dependency>
<dependency>
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/pkg/RarParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/pkg/RarParser.java
index cf80e47..633b2cc 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/pkg/RarParser.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/pkg/RarParser.java
@@ -23,6 +23,7 @@ import java.util.Set;
import com.github.junrar.Archive;
import com.github.junrar.exception.RarException;
+import com.github.junrar.impl.FileVolumeManager;
import com.github.junrar.rarfile.FileHeader;
import org.apache.tika.exception.EncryptedDocumentException;
import org.apache.tika.exception.TikaException;
@@ -65,7 +66,7 @@ public class RarParser extends AbstractParser {
Archive rar = null;
try (TemporaryResources tmp = new TemporaryResources()) {
TikaInputStream tis = TikaInputStream.get(stream, tmp);
- rar = new Archive(tis.getFile());
+ rar = new Archive(new FileVolumeManager(tis.getFile()));
if (rar.isEncrypted()) {
throw new EncryptedDocumentException();