1 /*
2 * Licensed to the Apache Software Foundation (ASF) under one *
3 * or more contributor license agreements. See the NOTICE file *
4 * distributed with this work for additional information *
5 * regarding copyright ownership. The ASF licenses this file *
6 * to you under the Apache License, Version 2.0 (the *
7 * "License"); you may not use this file except in compliance *
8 * with the License. You may obtain a copy of the License at *
9 * *
10 * http://www.apache.org/licenses/LICENSE-2.0 *
11 * *
12 * Unless required by applicable law or agreed to in writing, *
13 * software distributed under the License is distributed on an *
14 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY *
15 * KIND, either express or implied. See the License for the *
16 * specific language governing permissions and limitations *
17 * under the License. *
18 */
19 package org.apache.rat.analysis.matchers;
20
21 import java.util.Locale;
22
23 import org.apache.rat.analysis.IHeaders;
24
25 /**
26 * Accumulates all letters and numbers contained inside the header and compares
27 * it to the full text of a given license (after reducing it to letters and
28 * numbers as well).
29 * <p>
30 * The text comparison is case-insensitive but assumes only characters in the
31 * US-ASCII charset are being matched.
32 * </p>
33 */
34 public class FullTextMatcher extends SimpleTextMatcher {
35 /**
36 * The text that we are searching for. This text has been pruned and converted to lower case.
37 */
38 private final String prunedText;
39
40 /**
41 * Constructs the full text matcher with a unique random id and the specified
42 * text to match.
43 *
44 * @param simpleText the text to match
45 */
46 public FullTextMatcher(final String simpleText) {
47 this(null, simpleText);
48 }
49
50 /**
51 * Constructs the full text matcher for the specified text.
52 *
53 * @param id the id for the matcher
54 * @param simpleText the text to match
55 */
56 public FullTextMatcher(final String id, final String simpleText) {
57 super(id, simpleText);
58 this.prunedText = prune(simpleText).toLowerCase(Locale.ENGLISH);
59 }
60
61 /**
62 * Removes everything except letter or digit from text.
63 *
64 * @param text The text to remove extra chars from.
65 * @return the pruned text.
66 */
67 public static String prune(final String text) {
68 final int length = text.length();
69 final StringBuilder buffer = new StringBuilder(length);
70 for (int i = 0; i < length; i++) {
71 char at = text.charAt(i);
72 if (Character.isLetterOrDigit(at)) {
73 buffer.append(at);
74 }
75 }
76 return buffer.toString();
77 }
78
79 @Override
80 public boolean matches(final IHeaders headers) {
81 if (headers.pruned().length() >= prunedText.length()) { // we have enough data to match
82 return headers.pruned().contains(prunedText);
83 }
84 return false;
85 }
86 }