GeckoCorruptTagCleaner


1   /*
2    * Copyright 2004 Outerthought bvba and Schaubroeck nv
3    *
4    * Licensed under the Apache License, Version 2.0 (the "License");
5    * you may not use this file except in compliance with the License.
6    * You may obtain a copy of the License at
7    *
8    *     http://www.apache.org/licenses/LICENSE-2.0
9    *
10   * Unless required by applicable law or agreed to in writing, software
11   * distributed under the License is distributed on an "AS IS" BASIS,
12   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13   * See the License for the specific language governing permissions and
14   * limitations under the License.
15   */
16  package org.outerj.daisy.htmlcleaner;
17  
18  class GeckoCorruptTagCleaner {
19      /**
20       * Removes invalid tags produced by gecko editor.
21       *
22       * <p>The Gecko Midas editor (or Mozilla Composer for that matter) sometimes
23       * leaves things like '&lt;&gt;' or '&lt; /&gt;' (for those reading the
24       * source: it leaves the unescaped tags), thus tags without names. This
25       * is easily reproduceable by hitting enter twice followed by backspace twice
26       * when in the middle of a paragraph or header.
27       */
28      public static String   clean(String   input) {
29          char[] inputChars = input.toCharArray();
30          StringBuffer   result = new StringBuffer  (input.length());
31  
32          int i = 0;
33          while(i < inputChars.length) {
34              char c = inputChars[i];
35              if (c == '<' && i + 3 < inputChars.length) {
36                  if (inputChars[i + 1] == '>') {
37                      i = i + 2;
38                      continue;
39                  } else if (c == '<' && inputChars[i + 1] == ' ' && inputChars[i + 2] == '/' && inputChars[i + 3] == '>') {
40                      i = i + 4;
41                      continue;
42                  } else if (c == '<' && inputChars[i + 1] == '<') {
43                      i = i + 1;
44                      continue;
45                  }
46              }
47              result.append(c);
48              i = i + 1;
49          }
50  
51          return result.toString();
52      }
53  }
54
A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame
Popular Tags