|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Tags | Line # 24 | 30 | 1 | 0% |
0.0
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||||
| No Tests | |||
| 1 | package org.apache.lucene.demo.html; | |
| 2 | ||
| 3 | /** | |
| 4 | * Copyright 2004 The Apache Software Foundation | |
| 5 | * | |
| 6 | * Licensed under the Apache License, Version 2.0 (the "License"); | |
| 7 | * you may not use this file except in compliance with the License. | |
| 8 | * 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, software | |
| 13 | * distributed under the License is distributed on an "AS IS" BASIS, | |
| 14 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| 15 | * See the License for the specific language governing permissions and | |
| 16 | * limitations under the License. | |
| 17 | */ | |
| 18 | ||
| 19 | import java.util.Collections; | |
| 20 | import java.util.HashSet; | |
| 21 | import java.util.Set; | |
| 22 | ||
| 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.synchronizedSet(new HashSet()); | |
| 30 | ||
| 31 | 0 |
static{ |
| 32 | 0 | WS_ELEMS.add("<hr"); |
| 33 | 0 | WS_ELEMS.add("<hr/"); // note that "<hr />" does not need to be listed explicitly |
| 34 | 0 | WS_ELEMS.add("<br"); |
| 35 | 0 | WS_ELEMS.add("<br/"); |
| 36 | 0 | WS_ELEMS.add("<p"); |
| 37 | 0 | WS_ELEMS.add("</p"); |
| 38 | 0 | WS_ELEMS.add("<div"); |
| 39 | 0 | WS_ELEMS.add("</div"); |
| 40 | 0 | WS_ELEMS.add("<td"); |
| 41 | 0 | WS_ELEMS.add("</td"); |
| 42 | 0 | WS_ELEMS.add("<li"); |
| 43 | 0 | WS_ELEMS.add("</li"); |
| 44 | 0 | WS_ELEMS.add("<q"); |
| 45 | 0 | WS_ELEMS.add("</q"); |
| 46 | 0 | WS_ELEMS.add("<blockquote"); |
| 47 | 0 | WS_ELEMS.add("</blockquote"); |
| 48 | 0 | WS_ELEMS.add("<dt"); |
| 49 | 0 | WS_ELEMS.add("</dt"); |
| 50 | 0 | WS_ELEMS.add("<h1"); |
| 51 | 0 | WS_ELEMS.add("</h1"); |
| 52 | 0 | WS_ELEMS.add("<h2"); |
| 53 | 0 | WS_ELEMS.add("</h2"); |
| 54 | 0 | WS_ELEMS.add("<h3"); |
| 55 | 0 | WS_ELEMS.add("</h3"); |
| 56 | 0 | WS_ELEMS.add("<h4"); |
| 57 | 0 | WS_ELEMS.add("</h4"); |
| 58 | 0 | WS_ELEMS.add("<h5"); |
| 59 | 0 | WS_ELEMS.add("</h5"); |
| 60 | 0 | WS_ELEMS.add("<h6"); |
| 61 | 0 | WS_ELEMS.add("</h6"); |
| 62 | } | |
| 63 | } | |
|
||||||||||