1 /*
2 * ====================================================================
3 * Licensed to the Apache Software Foundation (ASF) under one
4 * or more contributor license agreements. See the NOTICE file
5 * distributed with this work for additional information
6 * regarding copyright ownership. The ASF licenses this file
7 * to you under the Apache License, Version 2.0 (the
8 * "License"); you may not use this file except in compliance
9 * with 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,
14 * software distributed under the License is distributed on an
15 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
16 * KIND, either express or implied. See the License for the
17 * specific language governing permissions and limitations
18 * under the License.
19 * ====================================================================
20 *
21 * This software consists of voluntary contributions made by many
22 * individuals on behalf of the Apache Software Foundation. For more
23 * information on the Apache Software Foundation, please see
24 * <http://www.apache.org/>.
25 *
26 */
27 package org.apache.hc.client5.http.psl;
28
29 import java.io.BufferedReader;
30 import java.io.IOException;
31 import java.io.Reader;
32 import java.util.ArrayList;
33 import java.util.List;
34
35 import org.apache.hc.core5.annotation.Contract;
36 import org.apache.hc.core5.annotation.ThreadingBehavior;
37
38 /**
39 * Parses the list from <a href="http://publicsuffix.org/">publicsuffix.org</a>
40 * and configures a PublicSuffixFilter.
41 *
42 * @since 4.4
43 */
44 @Contract(threading = ThreadingBehavior.STATELESS)
45 public final class PublicSuffixListParser {
46
47 /**
48 * Singleton instance.
49 *
50 * @since 5.2
51 */
52 public static final PublicSuffixListParser INSTANCE = new PublicSuffixListParser();
53
54 public PublicSuffixListParser() {
55 }
56
57 /**
58 * Parses the public suffix list format.
59 * <p>
60 * When creating the reader from the file, make sure to use the correct encoding
61 * (the original list is in UTF-8).
62 *
63 * @param reader the data reader. The caller is responsible for closing the reader.
64 * @throws java.io.IOException on error while reading from list
65 */
66 public PublicSuffixList parse(final Reader reader) throws IOException {
67 final List<String> rules = new ArrayList<>();
68 final List<String> exceptions = new ArrayList<>();
69 final BufferedReader r = new BufferedReader(reader);
70
71 String line;
72 while ((line = r.readLine()) != null) {
73 if (line.isEmpty()) {
74 continue;
75 }
76 if (line.startsWith("//")) {
77 continue; //entire lines can also be commented using //
78 }
79 if (line.startsWith(".")) {
80 line = line.substring(1); // A leading dot is optional
81 }
82 // An exclamation mark (!) at the start of a rule marks an exception to a previous wildcard rule
83 final boolean isException = line.startsWith("!");
84 if (isException) {
85 line = line.substring(1);
86 }
87
88 if (isException) {
89 exceptions.add(line);
90 } else {
91 rules.add(line);
92 }
93 }
94 return new PublicSuffixList(DomainType.UNKNOWN, rules, exceptions);
95 }
96
97 /**
98 * Parses the public suffix list format by domain type (currently supported ICANN and PRIVATE).
99 * <p>
100 * When creating the reader from the file, make sure to use the correct encoding
101 * (the original list is in UTF-8).
102 *
103 * @param reader the data reader. The caller is responsible for closing the reader.
104 * @throws java.io.IOException on error while reading from list
105 *
106 * @since 4.5
107 */
108 public List<PublicSuffixList> parseByType(final Reader reader) throws IOException {
109 final List<PublicSuffixList> result = new ArrayList<>(2);
110
111 final BufferedReader r = new BufferedReader(reader);
112
113 DomainType domainType = null;
114 List<String> rules = null;
115 List<String> exceptions = null;
116 String line;
117 while ((line = r.readLine()) != null) {
118 if (line.isEmpty()) {
119 continue;
120 }
121 if (line.startsWith("//")) {
122
123 if (domainType == null) {
124 if (line.contains("===BEGIN ICANN DOMAINS===")) {
125 domainType = DomainType.ICANN;
126 } else if (line.contains("===BEGIN PRIVATE DOMAINS===")) {
127 domainType = DomainType.PRIVATE;
128 }
129 } else {
130 if (line.contains("===END ICANN DOMAINS===") || line.contains("===END PRIVATE DOMAINS===")) {
131 if (rules != null) {
132 result.add(new PublicSuffixList(domainType, rules, exceptions));
133 }
134 domainType = null;
135 rules = null;
136 exceptions = null;
137 }
138 }
139
140 continue; //entire lines can also be commented using //
141 }
142 if (domainType == null) {
143 continue;
144 }
145
146 if (line.startsWith(".")) {
147 line = line.substring(1); // A leading dot is optional
148 }
149 // An exclamation mark (!) at the start of a rule marks an exception to a previous wildcard rule
150 final boolean isException = line.startsWith("!");
151 if (isException) {
152 line = line.substring(1);
153 }
154
155 if (isException) {
156 if (exceptions == null) {
157 exceptions = new ArrayList<>();
158 }
159 exceptions.add(line);
160 } else {
161 if (rules == null) {
162 rules = new ArrayList<>();
163 }
164 rules.add(line);
165 }
166 }
167 return result;
168 }
169
170 }