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 2020/09/08 19:01:26 UTC
[tika] branch branch_1x updated: TIKA-3119 -- general upgrades for
1.25
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
The following commit(s) were added to refs/heads/branch_1x by this push:
new 6ef132c TIKA-3119 -- general upgrades for 1.25
6ef132c is described below
commit 6ef132c1352252d881a4c5cf6dcfed1e8a981869
Author: tallison <ta...@apache.org>
AuthorDate: Tue Sep 8 15:01:05 2020 -0400
TIKA-3119 -- general upgrades for 1.25
---
tika-example/pom.xml | 6 +++---
tika-parent/pom.xml | 12 ++++++------
tika-parsers/pom.xml | 18 +++++++++---------
.../apache/tika/parser/microsoft/JackcessParser.java | 2 ++
.../java/org/apache/tika/parser/pkg/RarParser.java | 3 +--
.../tika/parser/microsoft/xml/XML2003ParserTest.java | 6 +++---
6 files changed, 24 insertions(+), 23 deletions(-)
diff --git a/tika-example/pom.xml b/tika-example/pom.xml
index 3beb890..e79eb55 100644
--- a/tika-example/pom.xml
+++ b/tika-example/pom.xml
@@ -100,7 +100,7 @@
<dependency>
<groupId>org.apache.jackrabbit</groupId>
<artifactId>jackrabbit-jcr-server</artifactId>
- <version>2.21.1</version>
+ <version>2.21.3</version>
<exclusions>
<exclusion>
<groupId>org.apache.tika</groupId>
@@ -127,7 +127,7 @@
<dependency>
<groupId>org.apache.jackrabbit</groupId>
<artifactId>jackrabbit-core</artifactId>
- <version>2.21.1</version>
+ <version>2.21.3</version>
<exclusions>
<exclusion>
<groupId>org.apache.tika</groupId>
@@ -156,7 +156,7 @@
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-context</artifactId>
- <version>5.2.7.RELEASE</version>
+ <version>5.2.8.RELEASE</version>
<exclusions>
<exclusion>
<groupId>commons-logging</groupId>
diff --git a/tika-parent/pom.xml b/tika-parent/pom.xml
index b72940e..b58f608 100644
--- a/tika-parent/pom.xml
+++ b/tika-parent/pom.xml
@@ -337,21 +337,21 @@
<poi.version>4.1.2</poi.version>
<commons.compress.version>1.20</commons.compress.version>
<commons.io.version>2.7</commons.io.version>
- <commons.lang3.version>3.10</commons.lang3.version>
+ <commons.lang3.version>3.11</commons.lang3.version>
<gson.version>2.8.6</gson.version>
<guava.version>29.0-jre</guava.version>
<osgi.core.version>6.0.0</osgi.core.version>
- <cxf.version>3.3.6</cxf.version>
+ <cxf.version>3.4.0</cxf.version>
<slf4j.version>1.7.28</slf4j.version>
- <jackson.version>2.11.0</jackson.version>
+ <jackson.version>2.11.2</jackson.version>
<!-- when this is next upgraded, see if we can get rid of
javax.activation dependency in tika-server -->
<jaxb.version>2.3.3</jaxb.version>
<cli.version>1.4</cli.version>
- <lucene.version>8.5.1</lucene.version>
- <mockito.version>3.3.3</mockito.version>
- <opennlp.version>1.9.2</opennlp.version>
+ <lucene.version>8.6.2</lucene.version>
+ <mockito.version>3.5.10</mockito.version>
+ <opennlp.version>1.9.3</opennlp.version>
</properties>
<build>
diff --git a/tika-parsers/pom.xml b/tika-parsers/pom.xml
index 979c63b..09b97ce 100644
--- a/tika-parsers/pom.xml
+++ b/tika-parsers/pom.xml
@@ -40,7 +40,7 @@
in XML2003ParserTest#testBasicWord see:
https://issues.apache.org/jira/browse/CODEC-263?focusedCommentId=17043716&page=com.atlassian.jira.plugin.system.issuetabpanels%3Acomment-tabpanel#comment-17043716
-->
- <codec.version>1.13</codec.version>
+ <codec.version>1.15</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-->
@@ -51,9 +51,9 @@
<jempbox.version>1.8.16</jempbox.version>
<netcdf-java.version>4.5.5</netcdf-java.version>
<sis.version>1.0</sis.version>
- <parso.version>2.0.11</parso.version>
+ <parso.version>2.0.12</parso.version>
<!-- used by POI, PDFBox and Jackcess ...try to sync -->
- <bouncycastle.version>1.65</bouncycastle.version>
+ <bouncycastle.version>1.66</bouncycastle.version>
<commonsexec.version>1.3</commonsexec.version>
<httpcomponents.version>4.5.12</httpcomponents.version>
</properties>
@@ -168,7 +168,7 @@
<dependency>
<groupId>com.github.luben</groupId>
<artifactId>zstd-jni</artifactId>
- <version>1.4.5-4</version>
+ <version>1.4.5-6</version>
<scope>provided</scope>
</dependency>
@@ -264,7 +264,7 @@
<dependency>
<groupId>com.healthmarketscience.jackcess</groupId>
<artifactId>jackcess</artifactId>
- <version>3.0.1</version>
+ <version>3.5.0</version>
<exclusions>
<exclusion>
<groupId>org.apache.commons</groupId>
@@ -329,7 +329,7 @@
<dependency>
<groupId>com.rometools</groupId>
<artifactId>rome</artifactId>
- <version>1.13.1</version>
+ <version>1.15.0</version>
<exclusions>
<exclusion>
<groupId>org.jdom</groupId>
@@ -366,7 +366,7 @@
<dependency>
<groupId>com.github.junrar</groupId>
<artifactId>junrar</artifactId>
- <version>4.0.0</version>
+ <version>7.3.0</version>
<exclusions>
<exclusion>
<groupId>commons-logging</groupId>
@@ -420,7 +420,7 @@
<dependency>
<groupId>org.xerial</groupId>
<artifactId>sqlite-jdbc</artifactId>
- <version>3.31.1</version>
+ <version>3.32.3.2</version>
<scope>provided</scope>
</dependency>
@@ -572,7 +572,7 @@
<dependency>
<groupId>net.java.dev.jna</groupId>
<artifactId>jna</artifactId>
- <version>5.5.0</version>
+ <version>5.6.0</version>
</dependency>
<!-- grib's current jsoup is vulnerable to xss
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/JackcessParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/JackcessParser.java
index 784a244..5daf678 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/JackcessParser.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/JackcessParser.java
@@ -27,6 +27,7 @@ import java.util.Set;
import com.healthmarketscience.jackcess.CryptCodecProvider;
import com.healthmarketscience.jackcess.Database;
import com.healthmarketscience.jackcess.DatabaseBuilder;
+import com.healthmarketscience.jackcess.DateTimeType;
import com.healthmarketscience.jackcess.util.LinkResolver;
import org.apache.tika.exception.EncryptedDocumentException;
import org.apache.tika.exception.TikaException;
@@ -97,6 +98,7 @@ public class JackcessParser extends AbstractParser {
.setCodecProvider(new CryptCodecProvider(password))
.setReadOnly(true).open();
}
+ db.setDateTimeType(DateTimeType.DATE);
db.setLinkResolver(IGNORE_LINK_RESOLVER);//just in case
JackcessExtractor ex = new JackcessExtractor(metadata, context, locale);
ex.parse(db, xhtml);
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 4cdcedd..bb12839 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
@@ -23,7 +23,6 @@ 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;
@@ -72,7 +71,7 @@ public class RarParser extends AbstractParser {
Archive rar = null;
try (TemporaryResources tmp = new TemporaryResources()) {
TikaInputStream tis = TikaInputStream.get(stream, tmp);
- rar = new Archive(new FileVolumeManager(tis.getFile()));
+ rar = new Archive(tis.getFile());
if (rar.isEncrypted()) {
throw new EncryptedDocumentException();
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/xml/XML2003ParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/xml/XML2003ParserTest.java
index 4da5965..7c85cfb 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/xml/XML2003ParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/xml/XML2003ParserTest.java
@@ -46,7 +46,7 @@ public class XML2003ParserTest extends MultiThreadedTikaTest {
@Test
public void testBasicWord() throws Exception {
List<Metadata> list = getRecursiveMetadata("testWORD2003.xml");
- assertEquals(6, list.size());
+ assertEquals(8, list.size());
Metadata m = list.get(0);//container doc
String xml = m.get(RecursiveParserWrapper.TIKA_CONTENT);
xml = xml.replaceAll("\\s+", " ");
@@ -79,9 +79,9 @@ public class XML2003ParserTest extends MultiThreadedTikaTest {
//make sure embedded docs were properly processed
assertContains("moscow-birds",
- Arrays.asList(list.get(5).getValues(TikaCoreProperties.KEYWORDS)));
+ Arrays.asList(list.get(7).getValues(TikaCoreProperties.KEYWORDS)));
- assertEquals("testJPEG_EXIF.jpg", list.get(5).get(TikaCoreProperties.ORIGINAL_RESOURCE_NAME));
+ assertEquals("testJPEG_EXIF.jpg", list.get(7).get(TikaCoreProperties.ORIGINAL_RESOURCE_NAME));
//check that text is extracted with breaks between elements
String txt = getText(getResourceAsStream("/test-documents/testWORD2003.xml"),AUTO_DETECT_PARSER);