rzo1 commented on code in PR #1138: URL: https://github.com/apache/opennlp/pull/1138#discussion_r3569114120
########## opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/normalizer/FullCaseFoldCharSequenceNormalizer.java: ########## @@ -0,0 +1,171 @@ +/* + * 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 opennlp.tools.util.normalizer; + +import java.io.BufferedReader; +import java.io.IOException; +import java.io.InputStream; +import java.io.InputStreamReader; +import java.io.UncheckedIOException; +import java.nio.charset.StandardCharsets; +import java.util.HashMap; +import java.util.Map; + +/** + * A {@link CharSequenceNormalizer} that applies Unicode full case folding for case-insensitive + * matching, as defined by the Default Case Algorithms in + * <a href="https://www.unicode.org/versions/latest/core-spec/chapter-3/";>Section 3.13 of the + * Unicode Standard</a>, using the bundled {@code CaseFolding.txt} data of the Unicode Character + * Database. + * + * <p>Unlike {@link CaseFoldCharSequenceNormalizer}, which lower cases with + * {@link java.util.Locale#ROOT}, this applies the full case foldings (the {@code C} common and + * {@code F} full status mappings), including the expanding folds that plain lower casing does not + * perform: the sharp s (U+00DF) to {@code ss}, the Latin ligatures (for example U+FB00 to + * {@code ff}), and the Greek and Armenian multi-character folds. It is therefore an expanding, + * offset-changing transform, so it is offset-aware: {@link #normalizeAligned(CharSequence)} reports + * the {@link Alignment} from the folded text back to the input. A single cursor pass with no regular + * expression.</p> + * + * <p>The {@code S} simple and {@code T} Turkic status mappings are excluded, so the Turkish and + * Azerbaijani dotless-i rule is not applied here. Input is expected in NFC: the fold matches + * precomposed code points, so decomposed sequences pass through unchanged.</p> + */ +public final class FullCaseFoldCharSequenceNormalizer implements OffsetAwareNormalizer { + + private static final long serialVersionUID = 4520210518330612934L; + + private static final String RESOURCE = "CaseFolding.txt"; + + /** + * Maps a source code point to its full case folding (one or more code points), for the C and F + * status rows of {@code CaseFolding.txt}. Loaded once when this class initializes, which + * happens on first use. + */ + private static final Map<Integer, String> FOLDINGS = Map.copyOf(initFoldings()); + + private static final FullCaseFoldCharSequenceNormalizer INSTANCE = + new FullCaseFoldCharSequenceNormalizer(); + + /** Creates the singleton; use {@link #getInstance()}. */ + private FullCaseFoldCharSequenceNormalizer() { + } + + /** {@return the shared, stateless instance} */ + public static FullCaseFoldCharSequenceNormalizer getInstance() { + return INSTANCE; + } + + /** + * {@inheritDoc} + * + * @throws IllegalArgumentException if {@code text} is {@code null}. Review Comment: shouldn't that go into the interface? ;-) -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
