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 public PublicSuffixListParser() {
48 }
49
50 /**
51 * Parses the public suffix list format.
52 * <p>
53 * When creating the reader from the file, make sure to use the correct encoding
54 * (the original list is in UTF-8).
55 *
56 * @param reader the data reader. The caller is responsible for closing the reader.
57 * @throws java.io.IOException on error while reading from list
58 */
59 public PublicSuffixList parse(final Reader reader) throws IOException {
60 final List<String> rules = new ArrayList<>();
61 final List<String> exceptions = new ArrayList<>();
62 final BufferedReader r = new BufferedReader(reader);
63
64 String line;
65 while ((line = r.readLine()) != null) {
66 if (line.isEmpty()) {
67 continue;
68 }
69 if (line.startsWith("//")) {
70 continue; //entire lines can also be commented using //
71 }
72 if (line.startsWith(".")) {
73 line = line.substring(1); // A leading dot is optional
74 }
75 // An exclamation mark (!) at the start of a rule marks an exception to a previous wildcard rule
76 final boolean isException = line.startsWith("!");
77 if (isException) {
78 line = line.substring(1);
79 }
80
81 if (isException) {
82 exceptions.add(line);
83 } else {
84 rules.add(line);
85 }
86 }
87 return new PublicSuffixList(DomainType.UNKNOWN, rules, exceptions);
88 }
89
90 /**
91 * Parses the public suffix list format by domain type (currently supported ICANN and PRIVATE).
92 * <p>
93 * When creating the reader from the file, make sure to use the correct encoding
94 * (the original list is in UTF-8).
95 *
96 * @param reader the data reader. The caller is responsible for closing the reader.
97 * @throws java.io.IOException on error while reading from list
98 *
99 * @since 4.5
100 */
101 public List<PublicSuffixList> parseByType(final Reader reader) throws IOException {
102 final List<PublicSuffixList> result = new ArrayList<>(2);
103
104 final BufferedReader r = new BufferedReader(reader);
105
106 DomainType domainType = null;
107 List<String> rules = null;
108 List<String> exceptions = null;
109 String line;
110 while ((line = r.readLine()) != null) {
111 if (line.isEmpty()) {
112 continue;
113 }
114 if (line.startsWith("//")) {
115
116 if (domainType == null) {
117 if (line.contains("===BEGIN ICANN DOMAINS===")) {
118 domainType = DomainType.ICANN;
119 } else if (line.contains("===BEGIN PRIVATE DOMAINS===")) {
120 domainType = DomainType.PRIVATE;
121 }
122 } else {
123 if (line.contains("===END ICANN DOMAINS===") || line.contains("===END PRIVATE DOMAINS===")) {
124 if (rules != null) {
125 result.add(new PublicSuffixList(domainType, rules, exceptions));
126 }
127 domainType = null;
128 rules = null;
129 exceptions = null;
130 }
131 }
132
133 continue; //entire lines can also be commented using //
134 }
135 if (domainType == null) {
136 continue;
137 }
138
139 if (line.startsWith(".")) {
140 line = line.substring(1); // A leading dot is optional
141 }
142 // An exclamation mark (!) at the start of a rule marks an exception to a previous wildcard rule
143 final boolean isException = line.startsWith("!");
144 if (isException) {
145 line = line.substring(1);
146 }
147
148 if (isException) {
149 if (exceptions == null) {
150 exceptions = new ArrayList<>();
151 }
152 exceptions.add(line);
153 } else {
154 if (rules == null) {
155 rules = new ArrayList<>();
156 }
157 rules.add(line);
158 }
159 }
160 return result;
161 }
162
163 }