View Javadoc
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    *      https://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  
18  package org.apache.commons.codec.net;
19  
20  import static org.junit.jupiter.api.Assertions.assertEquals;
21  
22  import java.nio.charset.StandardCharsets;
23  import java.util.BitSet;
24  
25  import org.junit.jupiter.params.ParameterizedTest;
26  import org.junit.jupiter.params.provider.ValueSource;
27  
28  /**
29   * Tests the reproduction in <a href="https://issues.apache.org/jira/browse/CODEC-345">CODEC-345</a>.
30   */
31  class Codec345Test {
32  
33      @ParameterizedTest
34      @ValueSource(strings = { "/pages/1/Test+Page", "/display/TST/Caf%C3%A9" })
35      void testEncodeUrlWithCallerSuppliedSafeCharacters(final String input) throws Exception {
36          // RFC 2396 abs_path, as used by HtmlUnit's UrlUtils and HttpClient 3.x's URI.
37          final BitSet allowed = new BitSet(256);
38          for (int c = 'a'; c <= 'z'; c++) {
39              allowed.set(c);
40          }
41          for (int c = 'A'; c <= 'Z'; c++) {
42              allowed.set(c);
43          }
44          for (int c = '0'; c <= '9'; c++) {
45              allowed.set(c);
46          }
47          for (final char c : "-_.!~*'()".toCharArray()) {
48              allowed.set(c); // mark
49          }
50          allowed.set('%'); // escaped
51          for (final char c : ":@&=+$,;/".toCharArray()) {
52              allowed.set(c); // pchar
53          }
54          final byte[] encoded = URLCodec.encodeUrl(allowed, input.getBytes(StandardCharsets.UTF_8));
55          assertEquals(input, new String(encoded, StandardCharsets.US_ASCII));
56          assertEquals(input, new String(URLCodec.decodeUrl(allowed, encoded), StandardCharsets.UTF_8));
57      }
58  }