01: package org.apache.lucene.demo.html;
02:
03: /**
04: * Licensed to the Apache Software Foundation (ASF) under one or more
05: * contributor license agreements. See the NOTICE file distributed with
06: * this work for additional information regarding copyright ownership.
07: * The ASF licenses this file to You under the Apache License, Version 2.0
08: * (the "License"); you may not use this file except in compliance with
09: * the License. You may obtain a copy of the License at
10: *
11: * http://www.apache.org/licenses/LICENSE-2.0
12: *
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.
18: */
19:
20: import java.util.Collections;
21: import java.util.HashSet;
22: import java.util.Set;
23:
24: public final class Tags {
25:
26: /**
27: * contains all tags for which whitespaces have to be inserted for proper tokenization
28: */
29: public static final Set WS_ELEMS = Collections
30: .synchronizedSet(new HashSet());
31:
32: static {
33: WS_ELEMS.add("<hr");
34: WS_ELEMS.add("<hr/"); // note that "<hr />" does not need to be listed explicitly
35: WS_ELEMS.add("<br");
36: WS_ELEMS.add("<br/");
37: WS_ELEMS.add("<p");
38: WS_ELEMS.add("</p");
39: WS_ELEMS.add("<div");
40: WS_ELEMS.add("</div");
41: WS_ELEMS.add("<td");
42: WS_ELEMS.add("</td");
43: WS_ELEMS.add("<li");
44: WS_ELEMS.add("</li");
45: WS_ELEMS.add("<q");
46: WS_ELEMS.add("</q");
47: WS_ELEMS.add("<blockquote");
48: WS_ELEMS.add("</blockquote");
49: WS_ELEMS.add("<dt");
50: WS_ELEMS.add("</dt");
51: WS_ELEMS.add("<h1");
52: WS_ELEMS.add("</h1");
53: WS_ELEMS.add("<h2");
54: WS_ELEMS.add("</h2");
55: WS_ELEMS.add("<h3");
56: WS_ELEMS.add("</h3");
57: WS_ELEMS.add("<h4");
58: WS_ELEMS.add("</h4");
59: WS_ELEMS.add("<h5");
60: WS_ELEMS.add("</h5");
61: WS_ELEMS.add("<h6");
62: WS_ELEMS.add("</h6");
63: }
64: }
|