1 package org.apache.lucene.analysis.icu.segmentation;
4 * Licensed to the Apache Software Foundation (ASF) under one or more
5 * contributor license agreements. See the NOTICE file distributed with
6 * this work for additional information regarding copyright ownership.
7 * The ASF licenses this file to You under the Apache License, Version 2.0
8 * (the "License"); you may not use this file except in compliance with
9 * the License. You may obtain a copy of the License at
11 * http://www.apache.org/licenses/LICENSE-2.0
13 * Unless required by applicable law or agreed to in writing, software
14 * distributed under the License is distributed on an "AS IS" BASIS,
15 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 * See the License for the specific language governing permissions and
17 * limitations under the License.
20 import com.ibm.icu.text.BreakIterator;
23 * Class that allows for tailored Unicode Text Segmentation on
24 * a per-writing system basis.
25 * @lucene.experimental
27 public abstract class ICUTokenizerConfig {
28 /** Return a breakiterator capable of processing a given script. */
29 public abstract BreakIterator getBreakIterator(int script);
30 /** Return a token type value for a given script and BreakIterator
32 public abstract String getType(int script, int ruleStatus);