Compatibility: Solr v9.1.0 & Lucene v9.3.0

conf/gradle/dependencies.gradle

@@ -24,7 +24,7 @@ dependencies {
     // Relying on the Solr directly would ensure that the correct Lucene version
     // is pulled down, instead of trying to guess which Lucene version to use.
     api "org.apache.solr:solr-core:${solrVersion}"
-    api "org.apache.lucene:lucene-analysis-kuromoji:${solrVersion}"
+    api "org.apache.lucene:lucene-analysis-kuromoji:${luceneVersion}"
 
     // See conf/tests.gradle for test related dependencies
 }

conf/gradle/tests.gradle

@@ -62,7 +62,7 @@ testing {
             dependencies {
                 implementation project()
                 implementation "commons-io:commons-io:2.8.0"
-                implementation "org.apache.lucene:lucene-queryparser:${solrVersion}"
+                implementation "org.apache.lucene:lucene-queryparser:${luceneVersion}"
                 implementation "org.apache.solr:solr-test-framework:${solrVersion}"
                 implementation "junit:junit:4.13.2"
             }
@@ -72,6 +72,7 @@ testing {
                     testTask.configure {
                         systemProperty "test.solr.allowed.securerandom", "NativePRNG"
                         systemProperty "solr.log.dir", "/var/solr/logs"
+                        systemProperty "solr.install.dir", "."
                         shouldRunAfter(test)
                     }
                 }

gradle.properties

@@ -3,9 +3,10 @@ solrLuceneAnalyzerSudachiProjectGroup=io.github.azagniotov
 solrLuceneAnalyzerSudachiProjectVersion=1.0.0-SNAPSHOT
 
 sudachiVersion=0.7.3
-solrVersion=9.0.0
-log4j2Version=2.17.1
+solrVersion=9.1.0
+luceneVersion=9.3.0
 slf4jVersion=1.7.36
+log4j2Version=2.17.1
 
 systemProp.file.encoding=UTF-8
 

src/functionalTest/java/io/github/azagniotov/lucene/analysis/ja/sudachi/LuceneQueryIndexTest.java

@@ -20,7 +20,6 @@
 import java.io.File;
 import java.nio.file.Files;
 import org.apache.lucene.analysis.Analyzer;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.document.Document;
 import org.apache.lucene.document.Field;
@@ -38,6 +37,7 @@
 import org.apache.lucene.search.TotalHitCountCollector;
 import org.apache.lucene.store.Directory;
 import org.apache.lucene.store.MMapDirectory;
+import org.apache.lucene.tests.analysis.BaseTokenStreamTestCase;
 import org.junit.Test;
 
 public class LuceneQueryIndexTest extends BaseTokenStreamTestCase {

src/integrationTest/java/io/github/azagniotov/lucene/analysis/ja/sudachi/analyzer/ImportedLuceneJapaneseAnalyzerTest.java

@@ -21,7 +21,7 @@
 import java.io.IOException;
 import java.util.Random;
 import org.apache.lucene.analysis.Analyzer;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.tests.analysis.BaseTokenStreamTestCase;
 import org.junit.Ignore;
 import org.junit.Test;
 

src/integrationTest/java/io/github/azagniotov/lucene/analysis/ja/sudachi/analyzer/SudachiAnalyzerTest.java

@@ -29,13 +29,13 @@
 import java.util.List;
 import java.util.Map;
 import org.apache.lucene.analysis.Analyzer;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
 import org.apache.lucene.analysis.CharArraySet;
 import org.apache.lucene.analysis.LowerCaseFilter;
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.Tokenizer;
 import org.apache.lucene.analysis.core.StopFilter;
 import org.apache.lucene.analysis.ja.JapaneseKatakanaStemFilter;
+import org.apache.lucene.tests.analysis.BaseTokenStreamTestCase;
 import org.apache.lucene.util.AttributeFactory;
 import org.junit.Test;
 

src/integrationTest/java/io/github/azagniotov/lucene/analysis/ja/sudachi/filters/SudachiBaseFormFilterTest.java

@@ -19,8 +19,8 @@
 import io.github.azagniotov.lucene.analysis.ja.sudachi.test.TestUtils;
 import java.io.IOException;
 import java.util.Collections;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
 import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.tests.analysis.BaseTokenStreamTestCase;
 import org.junit.Test;
 
 public class SudachiBaseFormFilterTest extends BaseTokenStreamTestCase {

src/integrationTest/java/io/github/azagniotov/lucene/analysis/ja/sudachi/filters/SudachiNormalizedFormFilterTest.java

@@ -19,8 +19,8 @@
 import io.github.azagniotov.lucene.analysis.ja.sudachi.test.TestUtils;
 import java.io.IOException;
 import java.util.Collections;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
 import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.tests.analysis.BaseTokenStreamTestCase;
 import org.junit.Test;
 
 public class SudachiNormalizedFormFilterTest extends BaseTokenStreamTestCase {

src/integrationTest/java/io/github/azagniotov/lucene/analysis/ja/sudachi/filters/SudachiPartOfSpeechStopFilterTest.java

@@ -23,8 +23,8 @@
 import io.github.azagniotov.lucene.analysis.ja.sudachi.util.StringResourceLoader;
 import java.io.IOException;
 import java.util.HashMap;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
 import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.tests.analysis.BaseTokenStreamTestCase;
 import org.apache.lucene.util.ClasspathResourceLoader;
 import org.junit.Test;
 

src/integrationTest/java/io/github/azagniotov/lucene/analysis/ja/sudachi/tokenizer/ImportedLuceneJapaneseTokenizerTest.java

@@ -21,8 +21,8 @@
 
 import com.worksap.nlp.sudachi.Config;
 import io.github.azagniotov.lucene.analysis.ja.sudachi.test.TestUtils;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
 import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.tests.analysis.BaseTokenStreamTestCase;
 import org.junit.Before;
 
 public class ImportedLuceneJapaneseTokenizerTest extends BaseTokenStreamTestCase {

src/integrationTest/java/io/github/azagniotov/lucene/analysis/ja/sudachi/tokenizer/SudachiTokenizerTest.java

@@ -26,11 +26,11 @@
 import java.nio.charset.Charset;
 import java.util.Collections;
 import java.util.List;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.Tokenizer;
 import org.apache.lucene.analysis.charfilter.MappingCharFilter;
 import org.apache.lucene.analysis.charfilter.NormalizeCharMap;
+import org.apache.lucene.tests.analysis.BaseTokenStreamTestCase;
 import org.junit.After;
 import org.junit.Before;
 import org.junit.Test;

src/smokeTest/solr_9.x.x/solr_9_1_0/Dockerfile

@@ -0,0 +1,64 @@
+# A few useful Docker commands to build an image and run the Solr container.
+#
+# Build (run with '--no-cache' to ensure that Git repo new tags will be pulled down, as Docker caches RUN layers):
+# docker build -t solr-sudachi . --progress=plain --no-cache
+#
+# Run:
+# docker run -p 8983:8983 --rm solr-sudachi:latest solr-precreate example
+#
+# cURL requests:
+# 1. curl -sS 'http://localhost:8983/solr/example/analysis/field?analysis.fieldtype=text_ja' --get --data-urlencode 'analysis.fieldvalue=ちいかわ'  | jq '.analysis.field_types.text_ja.index[1][].text'
+# 2. curl -sS 'http://localhost:8983/solr/example/analysis/field?analysis.fieldtype=text_ja' --get --data-urlencode 'analysis.fieldvalue=すもももももももものうち'  | jq '.analysis.field_types.text_ja.index[1][].text'
+# 3. curl -sS 'http://localhost:8983/solr/example/analysis/field?analysis.fieldtype=text_ja' --get --data-urlencode 'analysis.fieldvalue=聖川真斗'  | jq '.analysis.field_types.text_ja.index[1][].text'
+#
+# See: https://github.com/apache/lucene/pull/12517
+#
+
+########################################################################################
+# Stage 1 : Solr Lucene Analyzer Sudachi JAR
+ ########################################################################################
+FROM gradle:8.1.1-jdk11@sha256:681c18e70745546bf66949861d18019b979810ac151a5e0933d4ff83c76b4f5f AS BUILD_JAR_STAGE
+
+ARG PLUGIN_GIT_TAG=9.1.0
+
+ENV GRADLE_USER_HOME=/home/gradle
+WORKDIR $GRADLE_USER_HOME
+
+RUN git clone -b v$PLUGIN_GIT_TAG https://github.com/azagniotov/solr-lucene-analyzer-sudachi.git --depth 1 && \
+    git config --global user.name "Alexander Zagniotov" && \
+    git config --global user.email "[email protected]"
+
+# Download the dictionary and assemble the JAR to be placed under Solr /opt/solr/server/solr-webapp/webapp/WEB-INF/lib/
+RUN cd solr-lucene-analyzer-sudachi && \
+    gradle configureDictionariesLocally && \
+    gradle -PsolrVersion=$PLUGIN_GIT_TAG assemble && \
+    ls -al ./build/libs/
+
+
+########################################################################################
+# Stage 2 : Run Solr
+########################################################################################
+FROM solr:9.1.0@sha256:2377b0acf16c68b1c223cf685350584debc49dbc5950e0ddff82317be566cb79
+
+MAINTAINER Alexander Zagniotov <[email protected]>
+
+ENV SOLR_JAVA_MEM="-Xms2g -Xmx2g"
+ENV SOLR_SERVER_HOME=/opt/solr/server
+ENV SUDACHI_DICT_HOME=/tmp/sudachi
+ENV SOLR_WEB_INF_LIB_HOME=$SOLR_SERVER_HOME/solr-webapp/webapp/WEB-INF/lib
+
+USER root
+
+# Removing existing Lucene Kuromoji JAR to avoid polluting the classpath with
+# Japanese analysis-related classes. Also, Lucene team has renamed the packages
+# from analyzers => analysis at some point, thus using a wildcard.
+# RUN rm $SOLR_WEB_INF_LIB_HOME/lucene-*-kuromoji-*.jar
+
+COPY --from=BUILD_JAR_STAGE $SUDACHI_DICT_HOME/system-dict/system_core.dic $SUDACHI_DICT_HOME/system-dict/system_core.dic
+COPY --from=BUILD_JAR_STAGE $SUDACHI_DICT_HOME/user_lexicon.dic $SUDACHI_DICT_HOME/user_lexicon.dic
+COPY --from=BUILD_JAR_STAGE /home/gradle/solr-lucene-analyzer-sudachi/build/libs/solr-lucene-analyzer-sudachi*.jar $SOLR_WEB_INF_LIB_HOME/
+COPY schema.xml $SOLR_SERVER_HOME/solr/configsets/_default/conf/managed-schema.xml
+
+RUN chown -R solr:solr /tmp/sudachi
+
+USER solr