1 /*
2 * Licensed to the Apache Software Foundation (ASF) under one or more
3 * contributor license agreements. See the NOTICE file distributed with
4 * this work for additional information regarding copyright ownership.
5 * The ASF licenses this file to You under the Apache License, Version 2.0
6 * (the "License"); you may not use this file except in compliance with
7 * the License. You may obtain a copy of the License at
8 *
9 * http://www.apache.org/licenses/LICENSE-2.0
10 *
11 * Unless required by applicable law or agreed to in writing, software
12 * distributed under the License is distributed on an "AS IS" BASIS,
13 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 * See the License for the specific language governing permissions and
15 * limitations under the License.
16 */
17 package org.apache.commons.text.similarity;
18
19 import java.util.ArrayList;
20 import java.util.List;
21 import java.util.regex.Matcher;
22 import java.util.regex.Pattern;
23
24 import org.apache.commons.lang3.ArrayUtils;
25 import org.apache.commons.lang3.StringUtils;
26 import org.apache.commons.lang3.Validate;
27
28 /**
29 * A simple word {@link Tokenizer} that utilizes a regex to find words. It applies a regex {@code (\w)+} over the input text to extract words from a given
30 * character sequence.
31 * <p>
32 * Instances of this class are immutable and are safe for use by multiple concurrent threads.
33 * </p>
34 *
35 * @since 1.0
36 */
37 final class RegexTokenizer implements CharSequenceTokenizer<CharSequence> {
38
39 /** The whitespace pattern. */
40 private static final Pattern PATTERN = Pattern.compile("(\\w)+");
41
42 /**
43 * Singleton instance.
44 */
45 static final RegexTokenizer INSTANCE = new RegexTokenizer();
46
47 /**
48 * {@inheritDoc}
49 *
50 * @throws IllegalArgumentException if the input text is blank
51 */
52 @Override
53 public CharSequence[] apply(final CharSequence text) {
54 Validate.isTrue(StringUtils.isNotBlank(text), "Invalid text");
55 final Matcher matcher = PATTERN.matcher(text);
56 final List<String> tokens = new ArrayList<>();
57 while (matcher.find()) {
58 tokens.add(matcher.group(0));
59 }
60 return tokens.toArray(ArrayUtils.EMPTY_STRING_ARRAY);
61 }
62
63 }