1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
/*
* Authored by Alex Hultman, 2018-2022.
* Intellectual property of third-party.
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
* http://www.apache.org/licenses/LICENSE-2.0
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#ifndef UWS_CHUNKEDENCODING_H
#define UWS_CHUNKEDENCODING_H
/* Independent chunked encoding parser, used by HttpParser. */
#include <string>
#include <cstring>
#include <algorithm>
#include <string_view>
#include "MoveOnlyFunction.h"
#include <optional>
namespace uWS {
constexpr uint32_t STATE_HAS_SIZE = 0x80000000;
constexpr uint32_t STATE_IS_CHUNKED = 0x40000000;
constexpr uint32_t STATE_SIZE_MASK = 0x3FFFFFFF;
constexpr uint32_t STATE_IS_ERROR = 0xFFFFFFFF;
constexpr uint32_t STATE_SIZE_OVERFLOW = 0x0F000000;
inline unsigned int chunkSize(unsigned int state) {
return state & STATE_SIZE_MASK;
}
/* Reads hex number until CR or out of data to consume. Updates state. Returns bytes consumed. */
inline void consumeHexNumber(std::string_view &data, unsigned int &state) {
/* Consume everything higher than 32 */
while (data.length() && data.data()[0] > 32) {
unsigned char digit = (unsigned char)data.data()[0];
if (digit >= 'a') {
digit = (unsigned char) (digit - ('a' - ':'));
} else if (digit >= 'A') {
digit = (unsigned char) (digit - ('A' - ':'));
}
unsigned int number = ((unsigned int) digit - (unsigned int) '0');
if (number > 16 || (chunkSize(state) & STATE_SIZE_OVERFLOW)) {
state = STATE_IS_ERROR;
return;
}
// extract state bits
unsigned int bits = /*state &*/ STATE_IS_CHUNKED;
state = (state & STATE_SIZE_MASK) * 16u + number;
state |= bits;
data.remove_prefix(1);
}
/* Consume everything not /n */
while (data.length() && data.data()[0] != '\n') {
data.remove_prefix(1);
}
/* Now we stand on \n so consume it and enable size */
if (data.length()) {
state += 2; // include the two last /r/n
state |= STATE_HAS_SIZE | STATE_IS_CHUNKED;
data.remove_prefix(1);
}
}
inline void decChunkSize(unsigned int &state, unsigned int by) {
//unsigned int bits = state & STATE_IS_CHUNKED;
state = (state & ~STATE_SIZE_MASK) | (chunkSize(state) - by);
//state |= bits;
}
inline bool hasChunkSize(unsigned int state) {
return state & STATE_HAS_SIZE;
}
/* Are we in the middle of parsing chunked encoding? */
inline bool isParsingChunkedEncoding(unsigned int state) {
return state & ~STATE_SIZE_MASK;
}
inline bool isParsingInvalidChunkedEncoding(unsigned int state) {
return state == STATE_IS_ERROR;
}
/* Returns next chunk (empty or not), or if all data was consumed, nullopt is returned. */
static std::optional<std::string_view> getNextChunk(std::string_view &data, unsigned int &state, bool trailer = false) {
while (data.length()) {
// if in "drop trailer mode", just drop up to what we have as size
if (((state & STATE_IS_CHUNKED) == 0) && hasChunkSize(state) && chunkSize(state)) {
//printf("Parsing trailer now\n");
while(data.length() && chunkSize(state)) {
data.remove_prefix(1);
decChunkSize(state, 1);
if (chunkSize(state) == 0) {
/* This is an actual place where we need 0 as state */
state = 0;
/* The parser MUST stop consuming here */
return std::nullopt;
}
}
continue;
}
if (!hasChunkSize(state)) {
consumeHexNumber(data, state);
if (isParsingInvalidChunkedEncoding(state)) {
return std::nullopt;
}
if (hasChunkSize(state) && chunkSize(state) == 2) {
//printf("Setting state to trailer-parsing and emitting empty chunk\n");
// set trailer state and increase size to 4
if (trailer) {
state = 4 /*| STATE_IS_CHUNKED*/ | STATE_HAS_SIZE;
} else {
state = 2 /*| STATE_IS_CHUNKED*/ | STATE_HAS_SIZE;
}
return std::string_view(nullptr, 0);
}
continue;
}
// do we have data to emit all?
if (data.length() >= chunkSize(state)) {
// emit all but 2 bytes then reset state to 0 and goto beginning
// not fin
std::string_view emitSoon;
bool shouldEmit = false;
if (chunkSize(state) > 2) {
emitSoon = std::string_view(data.data(), chunkSize(state) - 2);
shouldEmit = true;
}
data.remove_prefix(chunkSize(state));
state = STATE_IS_CHUNKED;
if (shouldEmit) {
return emitSoon;
}
continue;
} else {
/* We will consume all our input data */
std::string_view emitSoon;
if (chunkSize(state) > 2) {
unsigned int maximalAppEmit = chunkSize(state) - 2;
if (data.length() > maximalAppEmit) {
emitSoon = data.substr(0, maximalAppEmit);
} else {
//cb(data);
emitSoon = data;
}
}
decChunkSize(state, (unsigned int) data.length());
state |= STATE_IS_CHUNKED;
// new: decrease data by its size (bug)
data.remove_prefix(data.length()); // ny bug fix för getNextChunk
if (emitSoon.length()) {
return emitSoon;
} else {
return std::nullopt;
}
}
}
return std::nullopt;
}
/* This is really just a wrapper for convenience */
struct ChunkIterator {
std::string_view *data;
std::optional<std::string_view> chunk;
unsigned int *state;
bool trailer;
ChunkIterator(std::string_view *data, unsigned int *state, bool trailer = false) : data(data), state(state), trailer(trailer) {
chunk = uWS::getNextChunk(*data, *state, trailer);
}
ChunkIterator() {
}
ChunkIterator begin() {
return *this;
}
ChunkIterator end() {
return ChunkIterator();
}
std::string_view operator*() {
if (!chunk.has_value()) {
std::abort();
}
return chunk.value();
}
bool operator!=(const ChunkIterator &other) const {
return other.chunk.has_value() != chunk.has_value();
}
ChunkIterator &operator++() {
chunk = uWS::getNextChunk(*data, *state, trailer);
return *this;
}
};
}
#endif // UWS_CHUNKEDENCODING_H