-
Notifications
You must be signed in to change notification settings - Fork 958
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add new token filters for Japanese sutegana (捨て仮名) (#12915)
### Description Sutegana (捨て仮名) is small letter of hiragana and katakana in Japanese. In the old Japanese text, sutegana (捨て仮名) is not used unlikely to modern one. For example: - "ストップウォッチ" is written as "ストツプウオツチ" - "ちょっとまって" is written as "ちよつとまつて" So it's meaningful to normalize sutegana to normal (uppercase) characters if we search against the corpus which includes old Japanese text such as patents, legal documents, contract policies, etc. This pull request introduces 2 token filters: - JapaneseHiraganaUppercaseFilter for hiragana - JapaneseKatakanaUppercaseFilter for katakana so that user can use either one separately. Each. filter make all the sutegana (small characters) into normal kana (uppercase character) to normalize the token. ### Why it is needed This transformation must be done as token filter. There have already been [MappingCharFilter](https://lucene.apache.org/core/8_0_0/analyzers-common/org/apache/lucene/analysis/charfilter/MappingCharFilter.html), but if we apply this character filter to normalize sutegana, it will impact to tokenization and it is not expected.
- Loading branch information
Showing
11 changed files
with
579 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
75 changes: 75 additions & 0 deletions
75
...ysis/kuromoji/src/java/org/apache/lucene/analysis/ja/JapaneseHiraganaUppercaseFilter.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,75 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one or more | ||
| * contributor license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright ownership. | ||
| * The ASF licenses this file to You under the Apache License, Version 2.0 | ||
| * (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
| package org.apache.lucene.analysis.ja; | ||
|
|
||
| import java.io.IOException; | ||
| import java.util.Map; | ||
| import org.apache.lucene.analysis.TokenFilter; | ||
| import org.apache.lucene.analysis.TokenStream; | ||
| import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; | ||
|
|
||
| /** | ||
| * A {@link TokenFilter} that normalizes small letters (捨て仮名) in hiragana into normal letters. For | ||
| * instance, "ちょっとまって" will be translated to "ちよつとまつて". | ||
| * | ||
| * <p>This filter is useful if you want to search against old style Japanese text such as patents, | ||
| * legal, contract policies, etc. | ||
| */ | ||
| public final class JapaneseHiraganaUppercaseFilter extends TokenFilter { | ||
| private static final Map<Character, Character> LETTER_MAPPINGS; | ||
|
|
||
| static { | ||
| // supported characters are: | ||
| // ぁ ぃ ぅ ぇ ぉ っ ゃ ゅ ょ ゎ ゕ ゖ | ||
| LETTER_MAPPINGS = | ||
| Map.ofEntries( | ||
| Map.entry('ぁ', 'あ'), | ||
| Map.entry('ぃ', 'い'), | ||
| Map.entry('ぅ', 'う'), | ||
| Map.entry('ぇ', 'え'), | ||
| Map.entry('ぉ', 'お'), | ||
| Map.entry('っ', 'つ'), | ||
| Map.entry('ゃ', 'や'), | ||
| Map.entry('ゅ', 'ゆ'), | ||
| Map.entry('ょ', 'よ'), | ||
| Map.entry('ゎ', 'わ'), | ||
| Map.entry('ゕ', 'か'), | ||
| Map.entry('ゖ', 'け')); | ||
| } | ||
|
|
||
| private final CharTermAttribute termAttr = addAttribute(CharTermAttribute.class); | ||
|
|
||
| public JapaneseHiraganaUppercaseFilter(TokenStream input) { | ||
| super(input); | ||
| } | ||
|
|
||
| @Override | ||
| public boolean incrementToken() throws IOException { | ||
| if (input.incrementToken()) { | ||
| char[] termBuffer = termAttr.buffer(); | ||
| for (int i = 0; i < termBuffer.length; i++) { | ||
| Character c = LETTER_MAPPINGS.get(termBuffer[i]); | ||
| if (c != null) { | ||
| termBuffer[i] = c; | ||
| } | ||
| } | ||
| return true; | ||
| } else { | ||
| return false; | ||
| } | ||
| } | ||
| } |
49 changes: 49 additions & 0 deletions
49
...romoji/src/java/org/apache/lucene/analysis/ja/JapaneseHiraganaUppercaseFilterFactory.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,49 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one or more | ||
| * contributor license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright ownership. | ||
| * The ASF licenses this file to You under the Apache License, Version 2.0 | ||
| * (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
| package org.apache.lucene.analysis.ja; | ||
|
|
||
| import java.util.Map; | ||
| import org.apache.lucene.analysis.TokenFilterFactory; | ||
| import org.apache.lucene.analysis.TokenStream; | ||
|
|
||
| /** | ||
| * Factory for {@link JapaneseHiraganaUppercaseFilter}. | ||
| * | ||
| * @lucene.spi {@value #NAME} | ||
| */ | ||
| public class JapaneseHiraganaUppercaseFilterFactory extends TokenFilterFactory { | ||
|
|
||
| /** SPI name */ | ||
| public static final String NAME = "japaneseHiraganaUppercase"; | ||
|
|
||
| public JapaneseHiraganaUppercaseFilterFactory(Map<String, String> args) { | ||
| super(args); | ||
| if (!args.isEmpty()) { | ||
| throw new IllegalArgumentException("Unknown parameters: " + args); | ||
| } | ||
| } | ||
|
|
||
| /** Default ctor for compatibility with SPI */ | ||
| public JapaneseHiraganaUppercaseFilterFactory() { | ||
| throw defaultCtorException(); | ||
| } | ||
|
|
||
| @Override | ||
| public TokenStream create(TokenStream input) { | ||
| return new JapaneseHiraganaUppercaseFilter(input); | ||
| } | ||
| } |
96 changes: 96 additions & 0 deletions
96
...ysis/kuromoji/src/java/org/apache/lucene/analysis/ja/JapaneseKatakanaUppercaseFilter.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,96 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one or more | ||
| * contributor license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright ownership. | ||
| * The ASF licenses this file to You under the Apache License, Version 2.0 | ||
| * (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
| package org.apache.lucene.analysis.ja; | ||
|
|
||
| import java.io.IOException; | ||
| import java.util.Map; | ||
| import org.apache.lucene.analysis.TokenFilter; | ||
| import org.apache.lucene.analysis.TokenStream; | ||
| import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; | ||
|
|
||
| /** | ||
| * A {@link TokenFilter} that normalizes small letters (捨て仮名) in katakana into normal letters. For | ||
| * instance, "ストップウォッチ" will be translated to "ストツプウオツチ". | ||
| * | ||
| * <p>This filter is useful if you want to search against old style Japanese text such as patents, | ||
| * legal, contract policies, etc. | ||
| */ | ||
| public final class JapaneseKatakanaUppercaseFilter extends TokenFilter { | ||
| private static final Map<Character, Character> LETTER_MAPPINGS; | ||
|
|
||
| static { | ||
| // supported characters are: | ||
| // ァ ィ ゥ ェ ォ ヵ ㇰ ヶ ㇱ ㇲ ッ ㇳ ㇴ ㇵ ㇶ ㇷ ㇷ゚ ㇸ ㇹ ㇺ ャ ュ ョ ㇻ ㇼ ㇽ ㇾ ㇿ ヮ | ||
| LETTER_MAPPINGS = | ||
| Map.ofEntries( | ||
| Map.entry('ァ', 'ア'), | ||
| Map.entry('ィ', 'イ'), | ||
| Map.entry('ゥ', 'ウ'), | ||
| Map.entry('ェ', 'エ'), | ||
| Map.entry('ォ', 'オ'), | ||
| Map.entry('ヵ', 'カ'), | ||
| Map.entry('ㇰ', 'ク'), | ||
| Map.entry('ヶ', 'ケ'), | ||
| Map.entry('ㇱ', 'シ'), | ||
| Map.entry('ㇲ', 'ス'), | ||
| Map.entry('ッ', 'ツ'), | ||
| Map.entry('ㇳ', 'ト'), | ||
| Map.entry('ㇴ', 'ヌ'), | ||
| Map.entry('ㇵ', 'ハ'), | ||
| Map.entry('ㇶ', 'ヒ'), | ||
| Map.entry('ㇷ', 'フ'), | ||
| Map.entry('ㇸ', 'ヘ'), | ||
| Map.entry('ㇹ', 'ホ'), | ||
| Map.entry('ㇺ', 'ム'), | ||
| Map.entry('ャ', 'ヤ'), | ||
| Map.entry('ュ', 'ユ'), | ||
| Map.entry('ョ', 'ヨ'), | ||
| Map.entry('ㇻ', 'ラ'), | ||
| Map.entry('ㇼ', 'リ'), | ||
| Map.entry('ㇽ', 'ル'), | ||
| Map.entry('ㇾ', 'レ'), | ||
| Map.entry('ㇿ', 'ロ'), | ||
| Map.entry('ヮ', 'ワ')); | ||
| } | ||
|
|
||
| private final CharTermAttribute termAttr = addAttribute(CharTermAttribute.class); | ||
|
|
||
| public JapaneseKatakanaUppercaseFilter(TokenStream input) { | ||
| super(input); | ||
| } | ||
|
|
||
| @Override | ||
| public boolean incrementToken() throws IOException { | ||
| if (input.incrementToken()) { | ||
| String term = termAttr.toString(); | ||
| if (term.contains("ㇷ゚")) { | ||
| term = term.replace("ㇷ゚", "プ"); | ||
| termAttr.setEmpty().append(term); | ||
| } | ||
| char[] termBuffer = termAttr.buffer(); | ||
| for (int i = 0; i < termBuffer.length; i++) { | ||
| Character c = LETTER_MAPPINGS.get(termBuffer[i]); | ||
| if (c != null) { | ||
| termBuffer[i] = c; | ||
| } | ||
| } | ||
| return true; | ||
| } else { | ||
| return false; | ||
| } | ||
| } | ||
| } |
49 changes: 49 additions & 0 deletions
49
...romoji/src/java/org/apache/lucene/analysis/ja/JapaneseKatakanaUppercaseFilterFactory.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,49 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one or more | ||
| * contributor license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright ownership. | ||
| * The ASF licenses this file to You under the Apache License, Version 2.0 | ||
| * (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
| package org.apache.lucene.analysis.ja; | ||
|
|
||
| import java.util.Map; | ||
| import org.apache.lucene.analysis.TokenFilterFactory; | ||
| import org.apache.lucene.analysis.TokenStream; | ||
|
|
||
| /** | ||
| * Factory for {@link JapaneseKatakanaUppercaseFilter}. | ||
| * | ||
| * @lucene.spi {@value #NAME} | ||
| */ | ||
| public class JapaneseKatakanaUppercaseFilterFactory extends TokenFilterFactory { | ||
|
|
||
| /** SPI name */ | ||
| public static final String NAME = "japaneseKatakanaUppercase"; | ||
|
|
||
| public JapaneseKatakanaUppercaseFilterFactory(Map<String, String> args) { | ||
| super(args); | ||
| if (!args.isEmpty()) { | ||
| throw new IllegalArgumentException("Unknown parameters: " + args); | ||
| } | ||
| } | ||
|
|
||
| /** Default ctor for compatibility with SPI */ | ||
| public JapaneseKatakanaUppercaseFilterFactory() { | ||
| throw defaultCtorException(); | ||
| } | ||
|
|
||
| @Override | ||
| public TokenStream create(TokenStream input) { | ||
| return new JapaneseKatakanaUppercaseFilter(input); | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
85 changes: 85 additions & 0 deletions
85
.../kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseHiraganaUppercaseFilter.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,85 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one or more | ||
| * contributor license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright ownership. | ||
| * The ASF licenses this file to You under the Apache License, Version 2.0 | ||
| * (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
| package org.apache.lucene.analysis.ja; | ||
|
|
||
| import java.io.IOException; | ||
| import org.apache.lucene.analysis.Analyzer; | ||
| import org.apache.lucene.analysis.Tokenizer; | ||
| import org.apache.lucene.tests.analysis.BaseTokenStreamTestCase; | ||
| import org.apache.lucene.tests.analysis.MockTokenizer; | ||
|
|
||
| /** Tests for {@link JapaneseHiraganaUppercaseFilter} */ | ||
| public class TestJapaneseHiraganaUppercaseFilter extends BaseTokenStreamTestCase { | ||
| private Analyzer keywordAnalyzer, japaneseAnalyzer; | ||
|
|
||
| @Override | ||
| public void setUp() throws Exception { | ||
| super.setUp(); | ||
| keywordAnalyzer = | ||
| new Analyzer() { | ||
| @Override | ||
| protected TokenStreamComponents createComponents(String fieldName) { | ||
| Tokenizer tokenizer = new MockTokenizer(MockTokenizer.WHITESPACE, false); | ||
| return new TokenStreamComponents( | ||
| tokenizer, new JapaneseHiraganaUppercaseFilter(tokenizer)); | ||
| } | ||
| }; | ||
| japaneseAnalyzer = | ||
| new Analyzer() { | ||
| @Override | ||
| protected TokenStreamComponents createComponents(String fieldName) { | ||
| Tokenizer tokenizer = | ||
| new JapaneseTokenizer( | ||
| newAttributeFactory(), null, false, JapaneseTokenizer.Mode.SEARCH); | ||
| return new TokenStreamComponents( | ||
| tokenizer, new JapaneseHiraganaUppercaseFilter(tokenizer)); | ||
| } | ||
| }; | ||
| } | ||
|
|
||
| @Override | ||
| public void tearDown() throws Exception { | ||
| keywordAnalyzer.close(); | ||
| japaneseAnalyzer.close(); | ||
| super.tearDown(); | ||
| } | ||
|
|
||
| public void testKanaUppercase() throws IOException { | ||
| assertAnalyzesTo(keywordAnalyzer, "ぁぃぅぇぉっゃゅょゎゕゖ", new String[] {"あいうえおつやゆよわかけ"}); | ||
| assertAnalyzesTo(keywordAnalyzer, "ちょっとまって", new String[] {"ちよつとまつて"}); | ||
| } | ||
|
|
||
| public void testKanaUppercaseWithSurrogatePair() throws IOException { | ||
| // 𠀋 : \uD840\uDC0B | ||
| assertAnalyzesTo( | ||
| keywordAnalyzer, | ||
| "\uD840\uDC0Bちょっとまって ちょっと\uD840\uDC0Bまって ちょっとまって\uD840\uDC0B", | ||
| new String[] {"\uD840\uDC0Bちよつとまつて", "ちよつと\uD840\uDC0Bまつて", "ちよつとまつて\uD840\uDC0B"}); | ||
| } | ||
|
|
||
| public void testKanaUppercaseWithJapaneseTokenizer() throws IOException { | ||
| assertAnalyzesTo(japaneseAnalyzer, "ちょっとまって", new String[] {"ちよつと", "まつ", "て"}); | ||
| } | ||
|
|
||
| public void testRandomData() throws IOException { | ||
| checkRandomData(random(), keywordAnalyzer, 200 * RANDOM_MULTIPLIER); | ||
| } | ||
|
|
||
| public void testEmptyTerm() throws IOException { | ||
| assertAnalyzesTo(keywordAnalyzer, "", new String[] {}); | ||
| } | ||
| } |
Oops, something went wrong.