1/*
2 * The following code is adapted from code originally written by Bjoern
3 * Hoehrmann <bjoern@hoehrmann.de>. See
4 * http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.
5 *
6 * The original license:
7 *
8 * Copyright (c) 2008-2009 Bjoern Hoehrmann <bjoern@hoehrmann.de>
9 *
10 * Permission is hereby granted, free of charge, to any person obtaining a copy
11 * of this software and associated documentation files (the "Software"), to deal
12 * in the Software without restriction, including without limitation the rights
13 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
14 * copies of the Software, and to permit persons to whom the Software is
15 * furnished to do so, subject to the following conditions:
16 *
17 * The above copyright notice and this permission notice shall be included in
18 * all copies or substantial portions of the Software.
19 *
20 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
21 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
22 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
23 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
24 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
25 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
26 * SOFTWARE.
27 */
28
29/*
30 * IXUtf8Validator.h
31 * Author: Benjamin Sergeant
32 * Copyright (c) 2019 Machine Zone, Inc. All rights reserved.
33 *
34 * From websocketpp. Tiny modifications made for code style, function names etc...
35 */
36
37#pragma once
38
39#include <cstdint>
40#include <string>
41
42namespace ix
43{
44 /// State that represents a valid utf8 input sequence
45 static unsigned int const utf8_accept = 0;
46 /// State that represents an invalid utf8 input sequence
47 static unsigned int const utf8_reject = 1;
48
49 /// Lookup table for the UTF8 decode state machine
50 static uint8_t const utf8d[] = {
51 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
52 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 00..1f
53 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
54 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 20..3f
55 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
56 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 40..5f
57 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
58 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 60..7f
59 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
60 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, // 80..9f
61 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
62 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, // a0..bf
63 8, 8, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
64 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // c0..df
65 0xa, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x4, 0x3, 0x3, // e0..ef
66 0xb, 0x6, 0x6, 0x6, 0x5, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, // f0..ff
67 0x0, 0x1, 0x2, 0x3, 0x5, 0x8, 0x7, 0x1, 0x1, 0x1, 0x4, 0x6, 0x1, 0x1, 0x1, 0x1, // s0..s0
68 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
69 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, // s1..s2
70 1, 2, 1, 1, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 1, 1,
71 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, // s3..s4
72 1, 2, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1,
73 1, 1, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1, // s5..s6
74 1, 3, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1,
75 1, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // s7..s8
76 };
77
78 /// Decode the next byte of a UTF8 sequence
79 /**
80 * @param [out] state The decoder state to advance
81 * @param [out] codep The codepoint to fill in
82 * @param [in] byte The byte to input
83 * @return The ending state of the decode operation
84 */
85 inline uint32_t decodeNextByte(uint32_t* state, uint32_t* codep, uint8_t byte)
86 {
87 uint32_t type = utf8d[byte];
88
89 *codep = (*state != utf8_accept) ? (byte & 0x3fu) | (*codep << 6) : (0xff >> type) & (byte);
90
91 *state = utf8d[256 + *state * 16 + type];
92 return *state;
93 }
94
95 /// Provides streaming UTF8 validation functionality
96 class Utf8Validator
97 {
98 public:
99 /// Construct and initialize the validator
100 Utf8Validator()
101 : m_state(utf8_accept)
102 , m_codepoint(0)
103 {
104 }
105
106 /// Advance the state of the validator with the next input byte
107 /**
108 * @param byte The byte to advance the validation state with
109 * @return Whether or not the byte resulted in a validation error.
110 */
111 bool consume(uint8_t byte)
112 {
113 if (decodeNextByte(&m_state, &m_codepoint, byte) == utf8_reject)
114 {
115 return false;
116 }
117 return true;
118 }
119
120 /// Advance Validator state with input from an iterator pair
121 /**
122 * @param begin Input iterator to the start of the input range
123 * @param end Input iterator to the end of the input range
124 * @return Whether or not decoding the bytes resulted in a validation error.
125 */
126 template<typename iterator_type>
127 bool decode(iterator_type begin, iterator_type end)
128 {
129 for (iterator_type it = begin; it != end; ++it)
130 {
131 unsigned int result =
132 decodeNextByte(&m_state, &m_codepoint, static_cast<uint8_t>(*it));
133
134 if (result == utf8_reject)
135 {
136 return false;
137 }
138 }
139 return true;
140 }
141
142 /// Return whether the input sequence ended on a valid utf8 codepoint
143 /**
144 * @return Whether or not the input sequence ended on a valid codepoint.
145 */
146 bool complete()
147 {
148 return m_state == utf8_accept;
149 }
150
151 /// Reset the Validator to decode another message
152 void reset()
153 {
154 m_state = utf8_accept;
155 m_codepoint = 0;
156 }
157
158 private:
159 uint32_t m_state;
160 uint32_t m_codepoint;
161 };
162
163 /// Validate a UTF8 string
164 /**
165 * convenience function that creates a Validator, validates a complete string
166 * and returns the result.
167 */
168 inline bool validateUtf8(std::string const& s)
169 {
170 Utf8Validator v;
171 if (!v.decode(s.begin(), s.end()))
172 {
173 return false;
174 }
175 return v.complete();
176 }
177
178} // namespace ix
179