merge .util package to .dict

mocobeta · Mar 19, 2022 · 67ed016 · 67ed016
1 parent 4387d3f
commit 67ed016
Show file tree

Hide file tree

Showing 43 changed files with 55 additions and 122 deletions.
diff --git a/gradle/generation/kuromoji.gradle b/gradle/generation/kuromoji.gradle
@@ -19,7 +19,7 @@
 
 def recompileDictionary(project, dictionaryName, Closure closure) {
   project.javaexec {
-    main = "org.apache.lucene.analysis.ja.util.DictionaryBuilder"
+    main = "org.apache.lucene.analysis.ja.dict.DictionaryBuilder"
     classpath = project.sourceSets.main.runtimeClasspath
 
     jvmArgs '-Xmx1G'

diff --git a/gradle/generation/nori.gradle b/gradle/generation/nori.gradle
@@ -19,7 +19,7 @@
 
 def recompileDictionary(project, dictionaryName, Closure closure) {
   project.javaexec {
-    main = "org.apache.lucene.analysis.ko.util.DictionaryBuilder"
+    main = "org.apache.lucene.analysis.ko.dict.DictionaryBuilder"
     classpath = project.sourceSets.main.runtimeClasspath
 
     jvmArgs '-Xmx1G'

diff --git a/lucene/analysis/kuromoji/src/java/module-info.java b/lucene/analysis/kuromoji/src/java/module-info.java
@@ -24,7 +24,6 @@
   exports org.apache.lucene.analysis.ja.completion;
   exports org.apache.lucene.analysis.ja.dict;
   exports org.apache.lucene.analysis.ja.tokenattributes;
-  exports org.apache.lucene.analysis.ja.util;
 
   opens org.apache.lucene.analysis.ja to
       org.apache.lucene.core;

diff --git a/...e/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/JapaneseReadingFormFilter.java b/...e/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/JapaneseReadingFormFilter.java
@@ -19,8 +19,8 @@
 import java.io.IOException;
 import org.apache.lucene.analysis.TokenFilter;
 import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.ja.dict.ToStringUtil;
 import org.apache.lucene.analysis.ja.tokenattributes.ReadingAttribute;
-import org.apache.lucene.analysis.ja.util.ToStringUtil;
 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
 
 /**

diff --git a/lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/JapaneseTokenizer.java b/lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/JapaneseTokenizer.java
@@ -28,6 +28,7 @@
 import org.apache.lucene.analysis.Tokenizer;
 import org.apache.lucene.analysis.ja.dict.CharacterDefinition;
 import org.apache.lucene.analysis.ja.dict.ConnectionCosts;
+import org.apache.lucene.analysis.ja.dict.DictionaryBuilder;
 import org.apache.lucene.analysis.ja.dict.JaMorphData;
 import org.apache.lucene.analysis.ja.dict.TokenInfoDictionary;
 import org.apache.lucene.analysis.ja.dict.TokenInfoFST;
@@ -264,8 +265,7 @@ public JapaneseTokenizer(
   /**
    * Create a new JapaneseTokenizer, supplying a custom system dictionary and unknown dictionary.
    * This constructor provides an entry point for users that want to construct custom language
-   * models that can be used as input to {@link
-   * org.apache.lucene.analysis.ja.util.DictionaryBuilder}.
+   * models that can be used as input to {@link DictionaryBuilder}.
    *
    * @param factory the AttributeFactory to use
    * @param systemDictionary a custom known token dictionary

diff --git a/...ache/lucene/analysis/ja/util/CSVUtil.java → ...ache/lucene/analysis/ja/dict/CSVUtil.java b/...ache/lucene/analysis/ja/util/CSVUtil.java → ...ache/lucene/analysis/ja/dict/CSVUtil.java
@@ -14,14 +14,14 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.apache.lucene.analysis.ja.util;
+package org.apache.lucene.analysis.ja.dict;
 
 import java.util.ArrayList;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
 /** Utility class for parsing CSV text */
-public final class CSVUtil {
+final class CSVUtil {
   private static final char QUOTE = '"';
 
   private static final char COMMA = ',';

diff --git a/...lysis/ja/util/ConnectionCostsBuilder.java → ...lysis/ja/dict/ConnectionCostsBuilder.java b/...lysis/ja/util/ConnectionCostsBuilder.java → ...lysis/ja/dict/ConnectionCostsBuilder.java
@@ -14,18 +14,17 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.apache.lucene.analysis.ja.util;
+package org.apache.lucene.analysis.ja.dict;
 
 import java.io.IOException;
 import java.io.LineNumberReader;
 import java.io.Reader;
 import java.nio.charset.StandardCharsets;
 import java.nio.file.Files;
 import java.nio.file.Path;
-import org.apache.lucene.analysis.ja.dict.ConnectionCosts;
 import org.apache.lucene.analysis.morph.ConnectionCostsWriter;
 
-class ConnectionCostsBuilder {
+final class ConnectionCostsBuilder {
 
   private ConnectionCostsBuilder() {}
 

diff --git a/...e/analysis/ja/util/DictionaryBuilder.java → ...e/analysis/ja/dict/DictionaryBuilder.java b/...e/analysis/ja/util/DictionaryBuilder.java → ...e/analysis/ja/dict/DictionaryBuilder.java
@@ -14,19 +14,18 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.apache.lucene.analysis.ja.util;
+package org.apache.lucene.analysis.ja.dict;
 
 import java.io.IOException;
 import java.nio.file.Path;
 import java.nio.file.Paths;
 import java.util.Locale;
-import org.apache.lucene.analysis.ja.dict.DictionaryConstants;
 
 /**
  * Tool to build dictionaries. Usage:
  *
  * <pre>
- *    java -cp [lucene classpath] org.apache.lucene.analysis.ja.util.DictionaryBuilder \
+ *    java -cp [lucene classpath] org.apache.lucene.analysis.ja.dict.DictionaryBuilder \
  *          ${inputDir} ${outputDir} ${encoding} ${normalizeEntry}
  * </pre>
  *
@@ -44,7 +43,7 @@
  *
  * @lucene.experimental
  */
-public class DictionaryBuilder {
+public final class DictionaryBuilder {
 
   /** Format of the dictionary. */
   public enum DictionaryFormat {

diff --git a/...ne/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/dict/DictionaryConstants.java b/...ne/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/dict/DictionaryConstants.java
@@ -17,7 +17,7 @@
 package org.apache.lucene.analysis.ja.dict;
 
 /** Dictionary constants */
-public final class DictionaryConstants {
+final class DictionaryConstants {
   /** Codec header of the dictionary file. */
   public static final String DICT_HEADER = "kuromoji_dict";
   /** Codec header of the dictionary mapping file. */

diff --git a/...lucene/analysis/ja/util/ToStringUtil.java → ...lucene/analysis/ja/dict/ToStringUtil.java b/...lucene/analysis/ja/util/ToStringUtil.java → ...lucene/analysis/ja/dict/ToStringUtil.java
@@ -14,13 +14,13 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.apache.lucene.analysis.ja.util;
+package org.apache.lucene.analysis.ja.dict;
 
 import java.io.IOException;
 import java.util.HashMap;
 
 /** Utility class for english translations of morphological data, used only for debugging. */
-public class ToStringUtil {
+public final class ToStringUtil {
   // a translation map for parts of speech, only used for reflectWith
   private static final HashMap<String, String> posTranslations = new HashMap<>();
 

diff --git a/...s/ja/util/TokenInfoDictionaryBuilder.java → ...s/ja/dict/TokenInfoDictionaryBuilder.java b/...s/ja/util/TokenInfoDictionaryBuilder.java → ...s/ja/dict/TokenInfoDictionaryBuilder.java
@@ -14,7 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.apache.lucene.analysis.ja.util;
+package org.apache.lucene.analysis.ja.dict;
 
 import java.io.BufferedReader;
 import java.io.IOException;
@@ -28,14 +28,14 @@
 import java.util.List;
 import java.util.stream.Collectors;
 import java.util.stream.Stream;
-import org.apache.lucene.analysis.ja.util.DictionaryBuilder.DictionaryFormat;
+import org.apache.lucene.analysis.ja.dict.DictionaryBuilder.DictionaryFormat;
 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.PositiveIntOutputs;
 
 /** */
-class TokenInfoDictionaryBuilder {
+final class TokenInfoDictionaryBuilder {
 
   private final String encoding;
   private final Normalizer.Form normalForm;

diff --git a/.../util/TokenInfoDictionaryEntryWriter.java → .../dict/TokenInfoDictionaryEntryWriter.java b/.../util/TokenInfoDictionaryEntryWriter.java → .../dict/TokenInfoDictionaryEntryWriter.java
@@ -14,18 +14,17 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.apache.lucene.analysis.ja.util;
+package org.apache.lucene.analysis.ja.dict;
 
 import java.io.IOException;
 import java.io.OutputStream;
 import java.nio.ByteBuffer;
-import org.apache.lucene.analysis.ja.dict.TokenInfoMorphData;
 import org.apache.lucene.analysis.morph.DictionaryEntryWriter;
 import org.apache.lucene.store.DataOutput;
 import org.apache.lucene.util.ArrayUtil;
 
 /** Writes system dictionary entries */
-class TokenInfoDictionaryEntryWriter extends DictionaryEntryWriter {
+final class TokenInfoDictionaryEntryWriter extends DictionaryEntryWriter {
   private static final int ID_LIMIT = 8192;
 
   TokenInfoDictionaryEntryWriter(int size) {

diff --git a/...is/ja/util/TokenInfoDictionaryWriter.java → ...is/ja/dict/TokenInfoDictionaryWriter.java b/...is/ja/util/TokenInfoDictionaryWriter.java → ...is/ja/dict/TokenInfoDictionaryWriter.java
@@ -14,17 +14,15 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.apache.lucene.analysis.ja.util;
+package org.apache.lucene.analysis.ja.dict;
 
 import java.io.IOException;
 import java.nio.file.Files;
 import java.nio.file.Path;
 import java.util.Objects;
-import org.apache.lucene.analysis.ja.dict.DictionaryConstants;
-import org.apache.lucene.analysis.ja.dict.TokenInfoDictionary;
 import org.apache.lucene.util.fst.FST;
 
-class TokenInfoDictionaryWriter
+final class TokenInfoDictionaryWriter
     extends org.apache.lucene.analysis.morph.BinaryDictionaryWriter<TokenInfoDictionary> {
   private FST<Long> fst;
 

diff --git a/lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/dict/TokenInfoMorphData.java b/lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/dict/TokenInfoMorphData.java
@@ -26,7 +26,7 @@
 import org.apache.lucene.util.IOSupplier;
 
 /** Morphological information for system dictionary. */
-public class TokenInfoMorphData implements JaMorphData {
+class TokenInfoMorphData implements JaMorphData {
 
   private final ByteBuffer buffer;
   private final String[] posDict;

diff --git a/...sis/ja/util/UnknownDictionaryBuilder.java → ...sis/ja/dict/UnknownDictionaryBuilder.java b/...sis/ja/util/UnknownDictionaryBuilder.java → ...sis/ja/dict/UnknownDictionaryBuilder.java
@@ -14,7 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.apache.lucene.analysis.ja.util;
+package org.apache.lucene.analysis.ja.dict;
 
 import java.io.IOException;
 import java.io.LineNumberReader;
@@ -25,9 +25,8 @@
 import java.util.ArrayList;
 import java.util.Comparator;
 import java.util.List;
-import org.apache.lucene.analysis.ja.dict.CharacterDefinition;
 
-class UnknownDictionaryBuilder {
+final class UnknownDictionaryBuilder {
   private static final String NGRAM_DICTIONARY_ENTRY = "NGRAM,5,5,-32768,記号,一般,*,*,*,*,*,*,*";
 
   private final String encoding;

diff --git a/...ysis/ja/util/UnknownDictionaryWriter.java → ...ysis/ja/dict/UnknownDictionaryWriter.java b/...ysis/ja/util/UnknownDictionaryWriter.java → ...ysis/ja/dict/UnknownDictionaryWriter.java
@@ -14,17 +14,14 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.apache.lucene.analysis.ja.util;
+package org.apache.lucene.analysis.ja.dict;
 
 import java.io.IOException;
 import java.nio.file.Path;
-import org.apache.lucene.analysis.ja.dict.CharacterDefinition;
-import org.apache.lucene.analysis.ja.dict.DictionaryConstants;
-import org.apache.lucene.analysis.ja.dict.UnknownDictionary;
 import org.apache.lucene.analysis.morph.BinaryDictionaryWriter;
 import org.apache.lucene.analysis.morph.CharacterDefinitionWriter;
 
-class UnknownDictionaryWriter extends BinaryDictionaryWriter<UnknownDictionary> {
+final class UnknownDictionaryWriter extends BinaryDictionaryWriter<UnknownDictionary> {
   private final CharacterDefinitionWriter<CharacterDefinition> characterDefinition =
       new CharacterDefinitionWriter<>(
           CharacterDefinition.class,

diff --git a/lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/dict/UserDictionary.java b/lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/dict/UserDictionary.java
@@ -25,7 +25,6 @@
 import java.util.List;
 import java.util.Map;
 import java.util.TreeMap;
-import org.apache.lucene.analysis.ja.util.CSVUtil;
 import org.apache.lucene.analysis.morph.Dictionary;
 import org.apache.lucene.util.IntsRefBuilder;
 import org.apache.lucene.util.fst.FST;

diff --git a/lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/dict/UserMorphData.java b/lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/dict/UserMorphData.java
@@ -19,8 +19,6 @@
 import static org.apache.lucene.analysis.ja.dict.UserDictionary.CUSTOM_DICTIONARY_WORD_ID_OFFSET;
 import static org.apache.lucene.analysis.ja.dict.UserDictionary.INTERNAL_SEPARATOR;
 
-import org.apache.lucene.analysis.ja.util.CSVUtil;
-
 /** Morphological information for user dictionary. */
 final class UserMorphData implements JaMorphData {
   public static final int WORD_COST = -100000;

diff --git a/...omoji/src/java/org/apache/lucene/analysis/ja/tokenattributes/InflectionAttributeImpl.java b/...omoji/src/java/org/apache/lucene/analysis/ja/tokenattributes/InflectionAttributeImpl.java
@@ -17,7 +17,7 @@
 package org.apache.lucene.analysis.ja.tokenattributes;
 
 import org.apache.lucene.analysis.ja.Token;
-import org.apache.lucene.analysis.ja.util.ToStringUtil;
+import org.apache.lucene.analysis.ja.dict.ToStringUtil;
 import org.apache.lucene.util.AttributeImpl;
 import org.apache.lucene.util.AttributeReflector;
 

diff --git a/...oji/src/java/org/apache/lucene/analysis/ja/tokenattributes/PartOfSpeechAttributeImpl.java b/...oji/src/java/org/apache/lucene/analysis/ja/tokenattributes/PartOfSpeechAttributeImpl.java
@@ -17,7 +17,7 @@
 package org.apache.lucene.analysis.ja.tokenattributes;
 
 import org.apache.lucene.analysis.ja.Token;
-import org.apache.lucene.analysis.ja.util.ToStringUtil;
+import org.apache.lucene.analysis.ja.dict.ToStringUtil;
 import org.apache.lucene.util.AttributeImpl;
 import org.apache.lucene.util.AttributeReflector;
 

diff --git a/...kuromoji/src/java/org/apache/lucene/analysis/ja/tokenattributes/ReadingAttributeImpl.java b/...kuromoji/src/java/org/apache/lucene/analysis/ja/tokenattributes/ReadingAttributeImpl.java
@@ -17,7 +17,7 @@
 package org.apache.lucene.analysis.ja.tokenattributes;
 
 import org.apache.lucene.analysis.ja.Token;
-import org.apache.lucene.analysis.ja.util.ToStringUtil;
+import org.apache.lucene.analysis.ja.dict.ToStringUtil;
 import org.apache.lucene.util.AttributeImpl;
 import org.apache.lucene.util.AttributeReflector;
 

diff --git a/lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/util/package-info.java b/lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/util/package-info.java
diff --git a/...pache/lucene/analysis/ja/TestCSVUtil.java → .../lucene/analysis/ja/dict/TestCSVUtil.java b/...pache/lucene/analysis/ja/TestCSVUtil.java → .../lucene/analysis/ja/dict/TestCSVUtil.java
@@ -14,10 +14,9 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.apache.lucene.analysis.ja;
+package org.apache.lucene.analysis.ja.dict;
 
 import java.io.IOException;
-import org.apache.lucene.analysis.ja.util.CSVUtil;
 import org.apache.lucene.tests.util.LuceneTestCase;
 
 /*

diff --git a/...analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/dict/TestExternalDictionary.java b/...analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/dict/TestExternalDictionary.java
@@ -25,7 +25,6 @@
 import java.nio.charset.StandardCharsets;
 import java.nio.file.Files;
 import java.nio.file.Path;
-import org.apache.lucene.analysis.ja.util.DictionaryBuilder;
 import org.apache.lucene.tests.util.LuceneTestCase;
 import org.junit.Before;
 

diff --git a/...ne/analysis/ja/util/TestToStringUtil.java → ...ne/analysis/ja/dict/TestToStringUtil.java b/...ne/analysis/ja/util/TestToStringUtil.java → ...ne/analysis/ja/dict/TestToStringUtil.java
@@ -14,7 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.apache.lucene.analysis.ja.util;
+package org.apache.lucene.analysis.ja.dict;
 
 import java.util.HashMap;
 import java.util.Map;

diff --git a/...nalysis/kuromoji/src/test/org/apache/lucene/analysis/ja/dict/TestTokenInfoDictionary.java b/...nalysis/kuromoji/src/test/org/apache/lucene/analysis/ja/dict/TestTokenInfoDictionary.java
@@ -27,9 +27,7 @@
 import java.nio.charset.StandardCharsets;
 import java.nio.file.Files;
 import java.nio.file.Path;
-import org.apache.lucene.analysis.ja.util.DictionaryBuilder;
-import org.apache.lucene.analysis.ja.util.DictionaryBuilder.DictionaryFormat;
-import org.apache.lucene.analysis.ja.util.ToStringUtil;
+import org.apache.lucene.analysis.ja.dict.DictionaryBuilder.DictionaryFormat;
 import org.apache.lucene.tests.util.LuceneTestCase;
 import org.apache.lucene.util.IntsRef;
 import org.apache.lucene.util.IntsRefBuilder;

diff --git a/...alysis/ja/util/TestUnknownDictionary.java → ...alysis/ja/dict/TestUnknownDictionary.java b/...alysis/ja/util/TestUnknownDictionary.java → ...alysis/ja/dict/TestUnknownDictionary.java
@@ -14,7 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.apache.lucene.analysis.ja.util;
+package org.apache.lucene.analysis.ja.dict;
 
 import org.apache.lucene.tests.util.LuceneTestCase;
 import org.junit.Test;

diff --git a/lucene/analysis/nori/src/java/module-info.java b/lucene/analysis/nori/src/java/module-info.java
@@ -23,7 +23,6 @@
   exports org.apache.lucene.analysis.ko;
   exports org.apache.lucene.analysis.ko.dict;
   exports org.apache.lucene.analysis.ko.tokenattributes;
-  exports org.apache.lucene.analysis.ko.util;
 
   provides org.apache.lucene.analysis.TokenizerFactory with
       org.apache.lucene.analysis.ko.KoreanTokenizerFactory;

diff --git a/lucene/analysis/nori/src/java/org/apache/lucene/analysis/ko/KoreanTokenizer.java b/lucene/analysis/nori/src/java/org/apache/lucene/analysis/ko/KoreanTokenizer.java
@@ -197,7 +197,7 @@ public KoreanTokenizer(
   /**
    * Create a new KoreanTokenizer supplying a custom system dictionary and unknown dictionary. This
    * constructor provides an entry point for users that want to construct custom language models
-   * that can be used as input to {@link org.apache.lucene.analysis.ko.util.DictionaryBuilder}.
+   * that can be used as input to {@link org.apache.lucene.analysis.ko.dict.DictionaryBuilder}.
    *
    * @param factory the AttributeFactory to use
    * @param systemDictionary a custom known token dictionary