ANY23-610 -- Upgrade Tika to 2.8.0

cli/src/test/java/org/apache/any23/cli/MimeDetectorTest.java

@@ -17,6 +17,7 @@
 
 package org.apache.any23.cli;
 
+import org.junit.Ignore;
 import org.junit.Test;
 
 /**
@@ -31,6 +32,7 @@ public MimeDetectorTest() {
  }
 
  @Test
+ @Ignore("url now broken; redirects to https://twitter.com")
  public void testDetectURL() throws Exception {
  assumeOnlineAllowed();
  runToolCheckExit0("http://twitter.com#micmos");

cli/src/test/java/org/apache/any23/cli/RoverTest.java

@@ -23,6 +23,7 @@
 import org.apache.any23.util.URLUtils;
 import org.junit.Assert;
 import org.junit.Assume;
+import org.junit.Ignore;
 import org.junit.Test;
 import org.eclipse.rdf4j.model.Statement;
 import org.eclipse.rdf4j.rio.RDFFormat;
@@ -112,6 +113,7 @@ public void testDelegatingWriterFactory() throws Exception {
  /* BEGIN: online tests. */
 
  @Test
+ @Ignore("urls no longer work as expected")
  public void testRunMultiURLs() throws Exception {
  // Assuming first accessibility to remote resources.
  assumeOnlineAllowed();

core/src/main/java/org/apache/any23/extractor/yaml/YAMLExtractor.java

@@ -32,6 +32,7 @@
 import org.eclipse.rdf4j.model.vocabulary.RDFS;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
+import org.yaml.snakeyaml.LoaderOptions;
 import org.yaml.snakeyaml.Yaml;
 import org.yaml.snakeyaml.constructor.SafeConstructor;
 
@@ -42,7 +43,7 @@ public class YAMLExtractor implements Extractor.ContentExtractor {
 
  private final Logger log = LoggerFactory.getLogger(getClass());
 
- private static final Yaml yml = new Yaml(new SafeConstructor());
+ private static final Yaml yml = new Yaml(new SafeConstructor(new LoaderOptions()));
 
  private static final YAML vocab = YAML.getInstance();
 

core/src/test/java/org/apache/any23/Any23Test.java

@@ -51,6 +51,7 @@
 import org.apache.any23.writer.TripleHandlerException;
 import org.apache.commons.io.IOUtils;
 import org.junit.AssumptionViolatedException;
+import org.junit.Ignore;
 import org.junit.Test;
 import org.eclipse.rdf4j.model.Statement;
 import org.eclipse.rdf4j.repository.Repository;
@@ -286,6 +287,7 @@ protected int getSoTimeout() {
  * if there is an error defining input URI's
  */
  @Test
+ @Ignore("url returns 404")
  public void testGZippedContent() throws IOException, URISyntaxException, ExtractionException {
  assumeOnlineAllowed();
  final Any23 runner = new Any23();

pom.xml

@@ -280,10 +280,10 @@
  <semargl.version>0.7</semargl.version>
  <log4j2.version>2.17.2</log4j2.version>
  <slf4j.version>1.7.36</slf4j.version>
- <tika.version>2.4.0</tika.version>
+ <tika.version>2.8.0</tika.version>
  <openie_2.11.version>4.2.6</openie_2.11.version>
  <openregex.version>1.1.1</openregex.version>
- <jackson.version>2.13.1</jackson.version>
+ <jackson.version>2.14.2</jackson.version>
  <commons-io.version>2.11.0</commons-io.version>
  <velocity.version>1.7</velocity.version>
 
@@ -351,6 +351,16 @@
  <artifactId>commons-lang3</artifactId>
  <version>3.12.0</version>
  </dependency>
+ <dependency>
+ <groupId>org.apache.commons</groupId>
+ <artifactId>commons-text</artifactId>
+ <version>1.10.0</version>
+ </dependency>
+ <dependency>
+ <groupId>org.yaml</groupId>
+ <artifactId>snakeyaml</artifactId>
+ <version>2.0</version>
+ </dependency>
  <dependency>
  <groupId>org.apache.httpcomponents</groupId>
  <artifactId>httpclient</artifactId>
@@ -389,14 +399,43 @@
  <dependency>
  <groupId>org.jsoup</groupId>
  <artifactId>jsoup</artifactId>
- <version>1.15.1</version>
+ <version>1.16.1</version>
  </dependency>
  <dependency>
  <groupId>net.sf.biweekly</groupId>
  <artifactId>biweekly</artifactId>
  <version>0.6.6</version>
  </dependency>
-
+ <dependency>
+ <groupId>org.bouncycastle</groupId>
+ <artifactId>bcprov-jdk18on</artifactId>
+ <version>1.73</version>
+ </dependency>
+ <dependency>
+ <groupId>org.osgi</groupId>
+ <artifactId>osgi.annotation</artifactId>
+ <version>8.1.0</version>
+ </dependency>
+ <dependency>
+ <groupId>org.osgi</groupId>
+ <artifactId>org.osgi.util.function</artifactId>
+ <version>1.2.0</version>
+ </dependency>
+ <dependency>
+ <groupId>com.fasterxml.jackson.core</groupId>
+ <artifactId>jackson-annotations</artifactId>
+ <version>${jackson.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>com.fasterxml.jackson.core</groupId>
+ <artifactId>jackson-core</artifactId>
+ <version>${jackson.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>com.fasterxml.jackson.core</groupId>
+ <artifactId>jackson-databind</artifactId>
+ <version>${jackson.version}</version>
+ </dependency>
  <!-- BEGIN: Tika -->
  <dependency>
  <groupId>org.apache.tika</groupId>
@@ -656,12 +695,6 @@
  </dependency>
  <!-- END: logger -->
 
- <dependency>
- <groupId>org.yaml</groupId>
- <artifactId>snakeyaml</artifactId>
- <version>1.30</version>
- </dependency>
-
  <!-- BEGIN: Test Dependencies -->
  <dependency>
  <groupId>junit</groupId>
@@ -837,6 +870,21 @@
  <!-- Remove once we upgrade to org.apache.tika:tika-parsers-standard-package:jar:2.3.0 -->
  <exclude>af5f9c26-c09d-401f-a7fc-0785eeabeab3</exclude>
  </excludeVulnerabilityIds>
+ <excludeCoordinates>
+ <!-- https://ossindex.sonatype.org/component/pkg:maven/com.google.guava/[email protected]?utm_source=ossindex-client&utm_medium=integration&utm_content=1.8.1 -->
+ <exclude>
+ <groupId>com.google.guava</groupId>
+ <artifactId>guava</artifactId>
+ <version>30.1.1-jre</version>
+ </exclude>
+ <exclude>
+ <!-- https://ossindex.sonatype.org/component/pkg:maven/xerces/[email protected]?utm_source=ossindex-client&utm_medium=integration&utm_content=1.8.1 -->
+ <groupId>xerces</groupId>
+ <artifactId>xercesImpl</artifactId>
+ <version>2.12.2</version>
+ </exclude>
+ </excludeCoordinates>
+
  </configuration>
  <executions>
  <execution>