Revisit tika dependencies

Author: breskeby

settings.gradle

@@ -144,14 +144,14 @@ dependencyResolutionManagement {
     withModule("org.apache.arrow:arrow-vector", ExcludeTransitivesRule)
     withModule("org.apache.commons:commons-compress", ExcludeTransitivesRule)
     withModule("org.apache.commons:commons-text", ExcludeTransitivesRule)
-    
+
     // org.apache.directory.api:api-asn1-ber brings in org.slf4j:slf4j-api:1.7.25. We use 2.0.6
     withModule("org.apache.directory.api:api-asn1-ber", ExcludeTransitiveOtherGroupsRule)
 
     // org.apache.directory.api:api-ldap-client-api brings in org.apache.mina:mina-core:2.0.16. We use 2.2.4
     withModule("org.apache.directory.api:api-ldap-client-api", ExcludeTransitiveOtherGroupsRule)
     withModule("org.apache.directory.api:api-ldap-codec-core", ExcludeTransitivesRule)
-    
+
     // "org.apache.directory.api:api-ldap-codec-standalone brings in org.apache.mina:mina-core:2.0.16. We use 2.2.4
     withModule("org.apache.directory.api:api-ldap-codec-standalone", ExcludeTransitiveOtherGroupsRule)
 
@@ -172,7 +172,7 @@ dependencyResolutionManagement {
 
     // org.apache.directory.api:api-ldap-model brings in org.apache.mina:mina-core:2.0.17. We use 2.2.4
     withModule("org.apache.directory.api:api-ldap-net-mina", ExcludeTransitiveOtherGroupsRule)
-    
+
     // org.apache.directory.api:api-asn1-ber brings in org.slf4j:slf4j-api:1.7.25. We use 2.0.6
     // TODO: For org.apache.directory.api dependencies we use partially 1.0.1 and partially 1.0.0. We should align these.
     withModule("org.apache.directory.api:api-util", ExcludeTransitivesRule)
@@ -227,19 +227,20 @@ dependencyResolutionManagement {
     // lucene-analysis-morfologik brings in org.carrot2:morfologik-polish:2.1.9. we use none.
     // lucene-analysis-morfologik brings in ua.net.nlp:morfologik-ukrainian-search:4.9.1 we use 3.7.5.
     withModule("org.apache.lucene:lucene-analysis-morfologik", ExcludeTransitiveOtherGroupsRule)
-    
+
     // lucene-analysis-phonetic brings in commons-codec:1.17. We use 1.15
     withModule("org.apache.lucene:lucene-analysis-phonetic", ExcludeTransitiveOtherGroupsRule)
 
     // lucene-spatial-extras brings in different version of spatial4j
     // lucene-spatial-extras brings in different version of s2-geometry-library-java
     withModule("org.apache.lucene:lucene-spatial-extras", ExcludeTransitiveOtherGroupsRule)
-    
+
     // lucene-expressions brings in org.antlr:antlr4-runtime:4.13.2
     // lucene-expressions brings in org.ow2.asm:asm:9.6
     // lucene-expressions brings in org.ow2.asm:asm-commons:9.6
     withModule("org.apache.lucene:lucene-expressions", ExcludeTransitiveOtherGroupsRule)
     withModule("org.apache.lucene:lucene-test-framework", ExcludeTransitiveOtherGroupsRule)
+
     withModule("org.apache.mina:mina-core", ExcludeTransitivesRule)
     withModule("org.apache.pdfbox:fontbox", ExcludeTransitivesRule)
     withModule("org.apache.pdfbox:pdfbox", ExcludeTransitivesRule)
@@ -248,14 +249,35 @@ dependencyResolutionManagement {
     withModule("org.apache.poi:poi-ooxml", ExcludeTransitivesRule)
     withModule("org.apache.poi:poi-scratchpad", ExcludeTransitivesRule)
     withModule("org.apache.santuario:xmlsec", ExcludeTransitivesRule)
-    withModule("org.apache.tika:tika-core", ExcludeTransitivesRule)
-    withModule("org.apache.tika:tika-langdetect-tika", ExcludeTransitivesRule)
-    withModule("org.apache.tika:tika-parser-apple-module", ExcludeTransitivesRule)
+
+    // org.apache.tika:tika-core brings in org.slf4j:slf4j-api:2.0.17. We use 2.0.6
+    // org.apache.tika:tika-core brings in commons-io:commons-io:2.20.0. We use 2.5
+    withModule("org.apache.tika:tika-core", ExcludeTransitiveOtherGroupsRule)
+
+    // org.apache.tika:tika-langdetect-tika brings in com.optimaize.languagedetector:language-detector:0.6.
+    withModule("org.apache.tika:tika-langdetect-tika", ExcludeTransitiveOtherGroupsRule)
+    // org.apache.tika:tika-parser-apple-module brings in com.googlecode.plist:dd-plist:1.28.
+    withModule("org.apache.tika:tika-parser-apple-module", ExcludeTransitiveOtherGroupsRule)
+    // org.apache.tika:tika-parser-microsoft-module brings in com.healthmarketscience.jackcess:jackcess-encrypt:4.0.3.
+    // org.apache.tika:tika-parser-microsoft-module brings in com.healthmarketscience.jackcess:jackcess:4.0.8.
+    // org.apache.tika:tika-parser-microsoft-module brings in com.pff:java-libpst:0.9.3.
+    // org.apache.tika:tika-parser-microsoft-module brings in commons-logging:commons-logging:1.3.5. We use 1.2.
+    // org.apache.tika:tika-parser-microsoft-module brings in org.bouncycastle:bcjmail-jdk18on:1.81.
+    // org.apache.tika:tika-parser-microsoft-module brings in org.bouncycastle:bcprov-jdk18on:1.81. We use 1.78.1/1.79.
+    // org.apache.tika:tika-parser-microsoft-module brings in tika-parser-mail-commons.
     withModule("org.apache.tika:tika-parser-microsoft-module", ExcludeTransitivesRule)
-    withModule("org.apache.tika:tika-parser-miscoffice-module", ExcludeTransitivesRule)
-    withModule("org.apache.tika:tika-parser-pdf-module", ExcludeTransitivesRule)
-    withModule("org.apache.tika:tika-parser-text-module", ExcludeTransitivesRule)
-    withModule("org.apache.tika:tika-parser-xmp-commons", ExcludeTransitivesRule)
+    // org.apache.tika:tika-parser-miscoffice-module brings in org.glassfish.jaxb:jaxb-runtime:4.0.5.
+    withModule("org.apache.tika:tika-parser-miscoffice-module", ExcludeTransitiveOtherGroupsRule)
+    // org.apache.tika:tika-parser-pdf-module brings in org.apache.pdfbox:pdfbox-tools:3.0.5.
+    // org.apache.tika:tika-parser-pdf-module brings in org.bouncycastle:bcjmail-jdk18on:1.81. Closest we use is bcprov-jdk18on:1.78.1/1.79.
+    // org.apache.tika:tika-parser-pdf-module brings in org.bouncycastle:bcprov-jdk18on:1.81. We use 1.78.1/1.79.
+    // org.apache.tika:tika-parser-pdf-module brings in org.glassfish.jaxb:jaxb-runtime:4.0.5.
+    withModule("org.apache.tika:tika-parser-pdf-module", ExcludeTransitiveOtherGroupsRule)
+    // org.apache.tika:tika-parser-text-module brings in com.github.albfernandez:juniversalchardet:2.5.0..
+    // org.apache.tika:tika-parser-text-module brings in org.apache.commons:commons-csv:1.14.1. We use 1.0.
+    withModule("org.apache.tika:tika-parser-text-module", ExcludeTransitiveOtherGroupsRule)
+    // org.apache.tika:tika-parser-xmp-commons brings in org.apache.pdfbox:xmpbox:3.0.5.
+    withModule("org.apache.tika:tika-parser-xmp-commons", ExcludeTransitiveOtherGroupsRule)
     withModule("org.apache.xmlbeans:xmlbeans", ExcludeTransitivesRule)
     withModule("org.bouncycastle:bcpg-fips", ExcludeTransitivesRule)
     withModule("org.bouncycastle:bcpkix-jdk18on", ExcludeTransitivesRule)