Upgrade org.apache.lucene to 9.12.1

pom.xml

@@ -109,7 +109,7 @@
         <version.kryo>2.20</version.kryo>
         <version.kryonet>2.20</version.kryonet>
         <version.log4j2>2.17.2</version.log4j2>
-        <version.lucene>7.5.0</version.lucene>
+        <version.lucene>9.12.1</version.lucene>
         <version.maven-install-plugin>2.5.2</version.maven-install-plugin>
         <version.metrics-cdi>1.6.0</version.metrics-cdi>
         <version.minlog>1.2</version.minlog>
@@ -828,7 +828,7 @@
             </dependency>
             <dependency>
                 <groupId>org.apache.lucene</groupId>
-                <artifactId>lucene-analyzers-common</artifactId>
+                <artifactId>lucene-analysis-common</artifactId>
                 <version>${version.lucene}</version>
             </dependency>
             <dependency>

warehouse/ingest-core/pom.xml

@@ -116,7 +116,7 @@
         </dependency>
         <dependency>
             <groupId>org.apache.lucene</groupId>
-            <artifactId>lucene-analyzers-common</artifactId>
+            <artifactId>lucene-analysis-common</artifactId>
         </dependency>
         <dependency>
             <groupId>org.apache.lucene</groupId>

warehouse/ingest-core/src/main/java/datawave/ingest/data/tokenize/StandardAnalyzer.java

@@ -1,15 +1,12 @@
 package datawave.ingest.data.tokenize;
 
-import java.io.Reader;
-
 import org.apache.lucene.analysis.CharArraySet;
 import org.apache.lucene.analysis.StopwordAnalyzerBase;
 import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.classic.ClassicFilter;
 import org.apache.lucene.analysis.core.LowerCaseFilter;
-import org.apache.lucene.analysis.core.StopAnalyzer;
 import org.apache.lucene.analysis.core.StopFilter;
 import org.apache.lucene.analysis.en.EnglishAnalyzer;
-import org.apache.lucene.analysis.standard.ClassicFilter;
 
 /**
  * Filters {@link StandardTokenizer} with {@link LowerCaseFilter} {@link ClassicFilter} and {@link StopFilter}, using a list of English stop words (unless

warehouse/ingest-core/src/main/java/datawave/ingest/data/tokenize/TokenizationHelper.java

@@ -6,6 +6,7 @@
 import org.apache.log4j.Logger;
 import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.analysis.CharArraySet;
+import org.apache.lucene.analysis.en.EnglishAnalyzer;
 
 import datawave.ingest.data.config.DataTypeHelper;
 import datawave.util.ObjectFactory;
@@ -373,7 +374,7 @@ public static final CharArraySet getStopWords(DataTypeHelper helper, Configurati
             }
         } else {
             log.warn("Utilizing default stopword set. Tokenization and indexing may generate unwanted data");
-            stopWords = org.apache.lucene.analysis.core.StopAnalyzer.ENGLISH_STOP_WORDS_SET;
+            stopWords = EnglishAnalyzer.ENGLISH_STOP_WORDS_SET;
         }
         return stopWords;
     }

warehouse/ingest-core/src/main/java/datawave/ingest/util/NGramTokenizationStrategy.java

@@ -6,9 +6,9 @@
 
 import org.apache.log4j.Logger;
 import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.classic.ClassicFilter;
 import org.apache.lucene.analysis.core.LowerCaseFilter;
 import org.apache.lucene.analysis.ngram.NGramTokenizer;
-import org.apache.lucene.analysis.standard.ClassicFilter;
 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
 
 import com.google.common.hash.BloomFilter;

warehouse/ingest-csv/pom.xml

@@ -59,7 +59,7 @@
         </dependency>
         <dependency>
             <groupId>org.apache.lucene</groupId>
-            <artifactId>lucene-analyzers-common</artifactId>
+            <artifactId>lucene-analysis-common</artifactId>
         </dependency>
         <dependency>
             <groupId>org.apache.lucene</groupId>

warehouse/ingest-json/pom.xml

@@ -49,7 +49,7 @@
         </dependency>
         <dependency>
             <groupId>org.apache.lucene</groupId>
-            <artifactId>lucene-analyzers-common</artifactId>
+            <artifactId>lucene-analysis-common</artifactId>
         </dependency>
         <dependency>
             <groupId>org.apache.lucene</groupId>

warehouse/ingest-scripts/src/main/resources/bin/ingest/findJars.sh

@@ -79,7 +79,7 @@ LOG4J2_SLF4J_JAR=$(findJar log4j-slf4j-impl)
 JSON_SIMPLE=$(findJar json-simple)
 LUCENE_JAR=$(findJar lucene-core)
 LUCENE_JAR=$LUCENE_JAR:$(findJar lucene-queryparser)
-LUCENE_JAR=$LUCENE_JAR:$(findJar lucene-analyzers-common)
+LUCENE_JAR=$LUCENE_JAR:$(findJar lucene-analysis-common)
 THRIFT_JAR=$(findJar libthrift)
 AC_CORE_JAR=$(findAccumuloJar accumulo-core)
 AC_SERVER_JAR=$(findAccumuloJar accumulo-server-base)

warehouse/ingest-wikipedia/pom.xml

@@ -40,7 +40,7 @@
         </dependency>
         <dependency>
             <groupId>org.apache.lucene</groupId>
-            <artifactId>lucene-analyzers-common</artifactId>
+            <artifactId>lucene-analysis-common</artifactId>
         </dependency>
         <dependency>
             <groupId>org.apache.lucene</groupId>

warehouse/query-core/pom.xml

@@ -161,7 +161,7 @@
         </dependency>
         <dependency>
             <groupId>org.apache.lucene</groupId>
-            <artifactId>lucene-analyzers-common</artifactId>
+            <artifactId>lucene-analysis-common</artifactId>
         </dependency>
         <dependency>
             <groupId>org.apache.lucene</groupId>

warehouse/query-core/src/main/java/datawave/core/iterators/DatawaveFieldIndexListIteratorJexl.java

@@ -10,6 +10,8 @@
 import java.util.Map;
 import java.util.SortedSet;
 
+import javax.management.ObjectName;
+
 import org.apache.accumulo.core.data.Key;
 import org.apache.accumulo.core.data.Range;
 import org.apache.accumulo.core.data.Value;
@@ -21,11 +23,14 @@
 import org.apache.hadoop.io.compress.CompressionCodec;
 import org.apache.lucene.store.DataInput;
 import org.apache.lucene.store.InputStreamDataInput;
+import org.apache.lucene.util.BytesRefBuilder;
 import org.apache.lucene.util.IntsRef;
 import org.apache.lucene.util.IntsRefBuilder;
 import org.apache.lucene.util.fst.FST;
+import org.apache.lucene.util.fst.FSTCompiler;
 import org.apache.lucene.util.fst.NoOutputs;
 import org.apache.lucene.util.fst.Outputs;
+import org.apache.lucene.util.fst.PositiveIntOutputs;
 import org.apache.lucene.util.fst.Util;
 
 import datawave.core.iterators.filesystem.FileSystemCache;
@@ -185,28 +190,16 @@ protected boolean matches(Key k) throws IOException {
 
     public static FST<?> getFST(SortedSet<String> values) throws IOException {
         final IntsRefBuilder irBuilder = new IntsRefBuilder();
-        // The builder options with defaults
-        FST.INPUT_TYPE inputType = FST.INPUT_TYPE.BYTE1;
-        int minSuffixCount1 = 0;
-        int minSuffixCount2 = 0;
-        boolean doShareSuffix = true;
-        boolean doShareNonSingletonNodes = true;
-        int shareMaxTailLength = Integer.MAX_VALUE;
-
-        boolean allowArrayArcs = true;
-        int bytesPageBits = 15;
         final Outputs<Object> outputs = NoOutputs.getSingleton();
 
-        // create the FST from the values
-        org.apache.lucene.util.fst.Builder<Object> fstBuilder = new org.apache.lucene.util.fst.Builder<>(inputType, minSuffixCount1, minSuffixCount2,
-                        doShareSuffix, doShareNonSingletonNodes, shareMaxTailLength, outputs, allowArrayArcs, bytesPageBits);
-
+        // Add the values to the compiler and create the FST.
+        FSTCompiler<Object> fstCompiler = new FSTCompiler.Builder<>(FST.INPUT_TYPE.BYTE1, outputs).build();
         for (String value : values) {
             Util.toUTF16(value, irBuilder);
             final IntsRef scratchInt = irBuilder.get();
-            fstBuilder.add(scratchInt, outputs.getNoOutput());
+            fstCompiler.add(scratchInt, outputs.getNoOutput());
         }
-        return fstBuilder.finish();
+        return FST.fromFSTReader(fstCompiler.compile(), fstCompiler.getFSTReader());
     }
 
     /** Utility class to load one instance of any FST per classloader */
@@ -260,8 +253,10 @@ public static FST<Object> loadFSTFromFile(Path filename, String compressionCodec
                 fis = codec.createInputStream(fis);
             }
             NoOutputs outputs = NoOutputs.getSingleton();
+
             DataInput di = new InputStreamDataInput(fis);
-            return new FST<>(di, outputs);
+            FST.FSTMetadata<Object> metadata = FST.readMetadata(di, outputs);
+            return new FST<>(metadata, di);
         }
 
         public static synchronized void clear(String file) {

warehouse/query-core/src/main/java/datawave/query/jexl/visitors/PushdownLargeFieldedListsVisitor.java

@@ -334,7 +334,7 @@ protected void assignNodeByField(JexlNode origNode, JexlNode subNode, Multimap<S
 
     protected URI createFst(SortedSet<String> values) throws IOException, ClassNotFoundException, InstantiationException, IllegalAccessException,
                     NoSuchMethodException, InvocationTargetException {
-        FST fst = DatawaveFieldIndexListIteratorJexl.getFST(values);
+        FST<?> fst = DatawaveFieldIndexListIteratorJexl.getFST(values);
 
         // now serialize to our file system
         CompressionCodec codec = null;
@@ -357,7 +357,7 @@ protected URI createFst(SortedSet<String> values) throws IOException, ClassNotFo
         }
 
         OutputStreamDataOutput outStream = new OutputStreamDataOutput(fstFileOut);
-        fst.save(outStream);
+        fst.save(outStream, outStream);
         outStream.close();
 
         return fstFile.toUri();

warehouse/query-core/src/main/java/datawave/query/language/parser/lucene/AccumuloSyntaxParser.java

@@ -40,6 +40,7 @@
 import org.apache.lucene.queryparser.flexible.messages.MessageImpl;
 import org.apache.lucene.queryparser.flexible.standard.nodes.RegexpQueryNode;
 import org.apache.lucene.queryparser.flexible.standard.nodes.TermRangeQueryNode;
+import org.apache.lucene.search.FuzzyQuery;
 
 @SuppressWarnings("all")
 public class AccumuloSyntaxParser implements SyntaxParser, AcumuloSyntaxParserConstants {
@@ -387,7 +388,7 @@ final public QueryNode Term(CharSequence field) throws ParseException {
         boolean endInc = false;
         QueryNode q = null;
         FieldQueryNode qLower, qUpper;
-        float defaultMinSimilarity = org.apache.lucene.search.FuzzyQuery.defaultMinSimilarity;
+        float defaultMinSimilarity = FuzzyQuery.defaultMaxEdits;
         switch ((jj_ntk == -1) ? jj_ntk() : jj_ntk) {
             case FUNCTION:
             case TERM: