Merge pull request #259 from WorksApplications/feature/258-deprecate-…

…dictfactory

Deprecate dictionary factory

src/main/java/com/worksap/nlp/sudachi/Dictionary.java

@@ -37,6 +37,19 @@
  */
 public interface Dictionary extends AutoCloseable {
 
+    /**
+     * Creates {@code Dictionary} from configuration.
+     *
+     * @param config
+     *            configuration of the dictionary to create
+     * @return {@link Dictionary}
+     * @throws IOException
+     *             if reading a file is failed
+     */
+    public static Dictionary load(Config config) throws IOException {
+        return new JapaneseDictionary(config);
+    }
+
     /**
      * Creates a tokenizer instance.
      *

src/main/java/com/worksap/nlp/sudachi/DictionaryFactory.java

@@ -21,7 +21,10 @@
 
 /**
  * Build a {@link Dictionary} instance from a dictionary file.
+ * 
+ * @deprecated use {@link Dictionary#load} instead
  */
+@Deprecated
 public class DictionaryFactory {
 
     /**
@@ -47,7 +50,10 @@ public Dictionary create() throws IOException {
      * @return {@link Dictionary}
      * @throws IOException
      *             if reading a file is failed
+     * 
+     * @deprecated use {@link Dictionary#load(Config)} instead
      */
+    @Deprecated
     public Dictionary create(Config config) throws IOException {
         return new JapaneseDictionary(config);
     }

src/test/java/com/worksap/nlp/sudachi/JapaneseDictionaryTest.kt

@@ -77,7 +77,7 @@ class JapaneseDictionaryTest {
   @Test
   fun instantiateConfigWithoutCharDef() {
     val config = setupMinimumConfig()
-    val jdict = DictionaryFactory().create(config)
+    val jdict = Dictionary.load(config)
 
     assertNotNull(jdict)
     assertNotNull(jdict.tokenizer())
@@ -87,7 +87,7 @@ class JapaneseDictionaryTest {
   @Test
   fun throwExceptionOnDictionaryUsageAfterClose() {
     val config = setupMinimumConfig()
-    val jdict = DictionaryFactory().create(config)
+    val jdict = Dictionary.load(config)
     jdict.close()
 
     assertFailsWith(IllegalStateException::class) { jdict.tokenizer() }
@@ -96,7 +96,7 @@ class JapaneseDictionaryTest {
   @Test
   fun throwExceptionOnTokenizerUsageAfterClose() {
     val config = setupMinimumConfig()
-    val jdict = DictionaryFactory().create(config)
+    val jdict = Dictionary.load(config)
     val tok = jdict.tokenizer()
     jdict.close()
 
@@ -189,7 +189,7 @@ abc,1,1,4675,AbC,名詞,普通名詞,一般,*,*,*,エービーシー,,,,,""")
             .clearUserDictionaries()
             .systemDictionary(sdict)
             .addUserDictionary(udict)
-    val mdict = DictionaryFactory().create(cfg)
+    val mdict = Dictionary.load(cfg)
 
     val found = mdict.lookup("ABC")
     assertEquals(4, found.size)

src/test/java/com/worksap/nlp/sudachi/JapaneseTokenizerMaskTest.kt

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2022 Works Applications Co., Ltd.
+ * Copyright (c) 2022-2024 Works Applications Co., Ltd.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -40,7 +40,7 @@ class JapaneseTokenizerMaskTest {
     cfg0.addOovProviderPlugin(CaptureOtherWords::class.java)
     cfg0.addOovProviderPlugin(SimpleOovProviderPlugin::class.java)
     val cfg = cfg0.withFallback(TestDictionary.user0Cfg())
-    val dic = DictionaryFactory().create(cfg) as JapaneseDictionary
+    val dic = Dictionary.load(cfg) as JapaneseDictionary
     val tokenizer = dic.tokenizer()
 
     assertEquals(2, dic.oovProviderPlugins.size)
@@ -61,7 +61,7 @@ class JapaneseTokenizerMaskTest {
   fun correctMasksWithSecondProvider() {
     val cfg = TestDictionary.user0Cfg()
     cfg.addOovProviderPlugin(CaptureOtherWords::class.java)
-    val dic = DictionaryFactory().create(cfg) as JapaneseDictionary
+    val dic = Dictionary.load(cfg) as JapaneseDictionary
     val tokenizer = dic.tokenizer()
 
     assertIs<SimpleOovProviderPlugin>(dic.oovProviderPlugins[0])

src/test/java/com/worksap/nlp/sudachi/JapaneseTokenizerTest.java

@@ -353,7 +353,7 @@ public void zeroLengthMorpheme() {
     @Test
     public void disableEmptyMorpheme() throws IOException {
         Config config = TestDictionary.INSTANCE.user1Cfg();
-        dict = new DictionaryFactory().create(Config.empty().withFallback(config).allowEmptyMorpheme(false));
+        dict = Dictionary.load(Config.empty().withFallback(config).allowEmptyMorpheme(false));
         tokenizer = (JapaneseTokenizer) dict.tokenizer();
 
         List<Morpheme> s = tokenizer.tokenize("…");

src/test/java/com/worksap/nlp/sudachi/JoinNumericPluginTest.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2022 Works Applications Co., Ltd.
+ * Copyright (c) 2017-2024 Works Applications Co., Ltd.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -32,7 +32,7 @@ public class JoinNumericPluginTest {
     public void setUp() throws IOException {
         Config config = TestDictionary.INSTANCE.user0Cfg()
                 .characterDefinition(getClass().getClassLoader().getResource("joinnumeric/char.def"));
-        Dictionary dict = new DictionaryFactory().create(config);
+        Dictionary dict = Dictionary.load(config);
         tokenizer = (JapaneseTokenizer) dict.tokenizer();
 
         plugin = new JoinNumericPlugin();

src/test/java/com/worksap/nlp/sudachi/OovProviderPluginTest.kt

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2022 Works Applications Co., Ltd.
+ * Copyright (c) 2022-2024 Works Applications Co., Ltd.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -49,7 +49,7 @@ class OovProviderPluginTest {
     val cfg = TestDictionary.user0Cfg()
     cfg.addOovProviderPlugin(FakeOovProvider::class.java)
         .addList("pos", "名詞", "普通名詞", "一般", "*", "*", "*")
-    val inst = DictionaryFactory().create(cfg) as JapaneseDictionary
+    val inst = Dictionary.load(cfg) as JapaneseDictionary
     val plugin = assertIs<FakeOovProvider>(inst.oovProviderPlugins.last())
     assertEquals(4, plugin.posId)
   }
@@ -60,7 +60,7 @@ class OovProviderPluginTest {
     cfg.addOovProviderPlugin(FakeOovProvider::class.java)
         .addList("pos", "名詞", "普通名詞", "一般", "*", "*", "new")
         .add(USER_POS, USER_POS_ALLOW)
-    val inst = DictionaryFactory().create(cfg) as JapaneseDictionary
+    val inst = Dictionary.load(cfg) as JapaneseDictionary
     val plugin = assertIs<FakeOovProvider>(inst.oovProviderPlugins.last())
     assertEquals(8, plugin.posId)
   }
@@ -71,15 +71,15 @@ class OovProviderPluginTest {
     cfg.addOovProviderPlugin(FakeOovProvider::class.java)
         .addList("pos", "名詞", "普通名詞", "一般", "*", "*", "*")
         .add(USER_POS, "test")
-    assertFails { DictionaryFactory().create(cfg) }
+    assertFails { Dictionary.load(cfg) }
   }
 
   @Test
   fun failInvalidPos() {
     val cfg = TestDictionary.user0Cfg()
     cfg.addOovProviderPlugin(FakeOovProvider::class.java)
         .addList("pos", "名詞", "普通名詞", "一般", "*", "*", "test")
-    assertFails { DictionaryFactory().create(cfg) }
+    assertFails { Dictionary.load(cfg) }
   }
 
   @Test
@@ -91,7 +91,7 @@ class OovProviderPluginTest {
     cfg.addOovProviderPlugin(FakeOovProvider::class.java)
         .addList("pos", "名詞", "普通名詞", "一般", "*", "*", "new")
         .add(USER_POS, USER_POS_ALLOW)
-    val inst = DictionaryFactory().create(cfg) as JapaneseDictionary
+    val inst = Dictionary.load(cfg) as JapaneseDictionary
     val oovPlugins = inst.oovProviderPlugins
     val p1 = assertIs<FakeOovProvider>(oovPlugins[oovPlugins.size - 2])
     assertEquals(8, p1.posId)
@@ -105,7 +105,7 @@ class OovProviderPluginTest {
     cfg.addOovProviderPlugin(FakeOovProvider::class.java)
         .addList("pos", "名詞", "普通名詞", "一般", "*", "*", "new")
         .add(USER_POS, USER_POS_ALLOW)
-    val dict = DictionaryFactory().create(cfg) as JapaneseDictionary
+    val dict = Dictionary.load(cfg) as JapaneseDictionary
     val plugin = assertIs<FakeOovProvider>(dict.oovProviderPlugins.last())
     assertEquals(8, plugin.posId)
     val tokinzer = dict.tokenizer()

src/test/java/com/worksap/nlp/sudachi/PosMatcherTest.kt

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2022 Works Applications Co., Ltd.
+ * Copyright (c) 2022-2024 Works Applications Co., Ltd.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -21,7 +21,7 @@ import kotlin.test.*
 
 class PosMatcherTest {
 
-  private val dic = DictionaryFactory().create(TestDictionary.user2Cfg()) as JapaneseDictionary
+  private val dic = Dictionary.load(TestDictionary.user2Cfg()) as JapaneseDictionary
   private val tok = dic.tokenizer()
 
   @Test

src/test/java/com/worksap/nlp/sudachi/RegexOovProviderTest.kt

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2022 Works Applications Co., Ltd.
+ * Copyright (c) 2022-2024 Works Applications Co., Ltd.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -34,7 +34,7 @@ class RegexOovProviderTest {
             .addList("pos", "名詞", "普通名詞", "一般", "*", "*", "*")
     @Suppress("UNCHECKED_CAST") block(cfg, pluginCfg as Config.PluginConf<RegexOovProvider>)
     // prepend our OOV configuration to the main configuration
-    return DictionaryFactory().create(cfg.withFallback(TestDictionary.user0Cfg())).tokenizer()
+    return Dictionary.load(cfg.withFallback(TestDictionary.user0Cfg())).tokenizer()
   }
 
   @Test

src/test/java/com/worksap/nlp/sudachi/TestDictionary.kt

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2022 Works Applications Co., Ltd.
+ * Copyright (c) 2017-2024 Works Applications Co., Ltd.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -67,11 +67,11 @@ object TestDictionary {
 
   /** System only */
   fun user0(): JapaneseDictionary {
-    return DictionaryFactory().create(user0Cfg()) as JapaneseDictionary
+    return Dictionary.load(user0Cfg()) as JapaneseDictionary
   }
 
   /** System + One User dictionary */
   fun user1(): JapaneseDictionary {
-    return DictionaryFactory().create(user1Cfg()) as JapaneseDictionary
+    return Dictionary.load(user1Cfg()) as JapaneseDictionary
   }
 }

src/test/java/com/worksap/nlp/sudachi/TextNormalizerTest.kt

@@ -23,8 +23,8 @@ import kotlin.test.*
 class TextNormalizerTest {
 
   private val dic =
-      DictionaryFactory()
-          .create(TestDictionary.user2Cfg().characterDefinition(CharacterCategory.loadDefault()))
+      Dictionary.load(
+          TestDictionary.user2Cfg().characterDefinition(CharacterCategory.loadDefault()))
           as JapaneseDictionary
 
   @Test

src/test/java/com/worksap/nlp/sudachi/UserDictionaryTest.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2022 Works Applications Co., Ltd.
+ * Copyright (c) 2017-2024 Works Applications Co., Ltd.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -37,7 +37,7 @@ public void fullUserDict() throws IOException {
         }
         config.addUserDictionary(instance.getUserDict2());
 
-        try (Dictionary dict = new DictionaryFactory().create(config)) {
+        try (Dictionary dict = Dictionary.load(config)) {
             Tokenizer tokenizer = dict.tokenizer();
             List<Morpheme> morphs = tokenizer.tokenize("ぴさる");
             assertThat(morphs.size(), is(1));
@@ -54,14 +54,14 @@ public void openTooManyUserDict() throws IOException {
         for (int i = 0; i < 15; i++) {
             config.addUserDictionary(instance.getUserDict1());
         }
-        new DictionaryFactory().create(config);
+        Dictionary.load(config);
     }
 
     @Test
     public void splitForUserDict() throws IOException {
         TestDictionary td = TestDictionary.INSTANCE;
         Config config = td.user0Cfg().addUserDictionary(td.getUserDict2()).addUserDictionary(td.getUserDict1());
-        try (Dictionary dict = new DictionaryFactory().create(config)) {
+        try (Dictionary dict = Dictionary.load(config)) {
             Tokenizer tokenizer = dict.tokenizer();
             List<Morpheme> morphs = tokenizer.tokenize("東京府");
             assertThat(morphs.size(), is(1));
@@ -76,7 +76,7 @@ public void splitForUserDict() throws IOException {
     @Test
     public void userDefinedPos() throws IOException {
         Config config = TestDictionary.INSTANCE.user2Cfg();
-        try (Dictionary dict = new DictionaryFactory().create(config)) {
+        try (Dictionary dict = Dictionary.load(config)) {
             Tokenizer tokenizer = dict.tokenizer();
             List<Morpheme> morphs = tokenizer.tokenize("すだちかぼす");
             assertThat(morphs.size(), is(2));
@@ -88,7 +88,7 @@ public void userDefinedPos() throws IOException {
 
         TestDictionary td = TestDictionary.INSTANCE;
         config = td.user0Cfg().addUserDictionary(td.getUserDict2()).addUserDictionary(td.getUserDict1());
-        try (Dictionary dict = new DictionaryFactory().create(config)) {
+        try (Dictionary dict = Dictionary.load(config)) {
             Tokenizer tokenizer = dict.tokenizer();
             List<Morpheme> morphs = tokenizer.tokenize("すだちかぼす");
             assertThat(morphs.size(), is(2));

src/test/java/com/worksap/nlp/sudachi/dictionary/build/UserDicTest.kt

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2022 Works Applications Co., Ltd.
+ * Copyright (c) 2017-2024 Works Applications Co., Ltd.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -71,7 +71,7 @@ class TestDic {
   fun load(): Dictionary {
     val config = Config.fromClasspath(config).systemDictionary(systemDic)
     userDics.forEach { config.addUserDictionary(it) }
-    return DictionaryFactory().create(config)
+    return Dictionary.load(config)
   }
 }