dungba88 commented on code in PR #12915: URL: https://github.com/apache/lucene/pull/12915#discussion_r1423575442
########## lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/JapaneseHiraganaUppercaseFilter.java: ########## @@ -0,0 +1,81 @@ +/* + * 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> s2l; + + static { + // supported characters are: + // ぁ ぃ ぅ ぇ ぉ っ ゃ ゅ ょ ゎ ゕ ゖ + s2l = + 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()) { + String term = termAttr.toString(); + char[] src = term.toCharArray(); + char[] result = new char[src.length]; + for (int i = 0; i < src.length; i++) { + Character c = s2l.get(src[i]); + if (c != null) { + result[i] = c; Review Comment: I see, that makes sense. Thank you -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
