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
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
|
/**
* Copyright (C) 2019-present MongoDB, Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the Server Side Public License, version 1,
* as published by MongoDB, Inc.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* Server Side Public License for more details.
*
* You should have received a copy of the Server Side Public License
* along with this program. If not, see
* <http://www.mongodb.com/licensing/server-side-public-license>.
*
* As a special exception, the copyright holders give permission to link the
* code of portions of this program with the OpenSSL library under certain
* conditions as described in each individual source file and distribute
* linked combinations including the program with the OpenSSL library. You
* must comply with the Server Side Public License in all respects for
* all of the code used other than as permitted herein. If you modify file(s)
* with this exception, you may extend this exception to your version of the
* file(s), but you are not obligated to do so. If you do not wish to do so,
* delete this exception statement from your version. If you delete this
* exception statement from all source files in the program, then also delete
* it in the license file.
*/
#include "mongo/logv2/string_escape.h"
#include "mongo/logv2/constants.h"
#include <algorithm>
#include <array>
#include <iterator>
namespace mongo::logv2 {
namespace {
constexpr char kHexChar[] = "0123456789abcdef";
// 'singleHandler' Function to write a valid single byte UTF-8 sequence with desired escaping.
// 'singleEscaper' Function to write a byte of invalid UTF-8 encoding
// 'twoEscaper' Function to write a valid two byte UTF-8 sequence with desired escaping, for C1
// control codes.
// All these functions take a function object as their first parameter to perform the
// writing of any escaped data. This function expects the number of handled bytes as its first
// parameter and the corresponding escaped string as the second. They are templates to they can be
// inlined.
template <typename SingleByteHandler, typename SingleByteEscaper, typename TwoByteEscaper>
std::string escape(StringData str,
SingleByteHandler singleHandler,
SingleByteEscaper singleEscaper,
TwoByteEscaper twoEscaper) {
std::string escaped;
// If input string is over the SSO size and we're going to need to allocate memory, add some
// extra to fit a couple of eventual escape sequences.
if (str.size() > escaped.capacity())
escaped.reserve(str.size() + constants::kReservedSpaceForEscaping);
// The range [begin, it) contains input that does not need to be escaped and that has not been
// written to output yet.
// The range [it end) contains remaining input to scan 'begin' is pointing to the beginning of
// the input that has not yet been written to 'escaped'.
// 'it' is pointing to the beginning of the unicode code point we're currently processing in the
// while-loop below. 'end' is the end of the input sequence.
auto begin = str.begin();
auto it = str.begin();
auto end = str.end();
// Writes an escaped sequence to output after flushing pending input that does not need to be
// escaped. 'it' is assumed to be at the beginning of the input sequence represented by the
// escaped data.
// 'numHandled' the number of bytes of unescaped data being written escaped in 'escapeSequence'
auto flushAndWrite = [&](size_t numHandled, StringData escapeSequence) {
// Flush range of unmodified input
escaped.append(begin, it);
begin = it + numHandled;
// Write escaped data
escaped.append(escapeSequence.rawData(), escapeSequence.size());
};
auto isValidCodePoint = [&](auto pos, int len) {
return std::distance(pos, end) >= len &&
std::all_of(pos + 1, pos + len, [](uint8_t c) { return (c >> 6) == 0b10; });
};
// Helper function to write a valid one byte UTF-8 sequence from the input stream
auto writeValid1Byte = [&]() { singleHandler(flushAndWrite, *it); };
// Helper function to write a valid two byte UTF-8 sequence from the input stream
auto writeValid2Byte = [&]() {
uint8_t first = *it;
uint8_t second = *(it + 1);
if (MONGO_unlikely(first == 0xc2 && second >= 0x80 && second < 0xa0)) {
twoEscaper(flushAndWrite, first, second);
}
};
// Helper function to write an invalid UTF-8 sequence from the input stream
// Will try and write up to num bytes but bail if we reach the end of the input.
// Updates the position of 'it'.
auto writeInvalid = [&](uint8_t c) { singleEscaper(flushAndWrite, c); };
while (it != end) {
uint8_t c = *it;
bool bit7 = (c >> 7) & 1;
if (MONGO_likely(!bit7)) {
writeValid1Byte();
++it;
continue;
}
bool bit6 = (c >> 6) & 1;
if (MONGO_unlikely(!bit6)) {
writeInvalid(c);
++it;
continue;
}
bool bit5 = (c >> 5) & 1;
if (!bit5) {
// 2 byte sequence
if (MONGO_likely(isValidCodePoint(it, 2))) {
writeValid2Byte();
it += 2;
} else {
writeInvalid(c);
++it;
}
continue;
}
bool bit4 = (c >> 4) & 1;
if (!bit4) {
// 3 byte sequence
if (MONGO_likely(isValidCodePoint(it, 3))) {
it += 3;
} else {
writeInvalid(c);
++it;
}
continue;
}
bool bit3 = (c >> 3) & 1;
if (bit3) {
writeInvalid(c);
++it;
continue;
}
// 4 byte sequence
if (MONGO_likely(isValidCodePoint(it, 4))) {
it += 4;
} else {
writeInvalid(c);
++it;
}
}
// Write last block
escaped.append(begin, it);
return escaped;
}
} // namespace
std::string escapeForText(StringData str) {
return escape(str,
[](const auto& writer, uint8_t unescaped) {
switch (unescaped) {
case '\0':
writer(1, "\\0"_sd);
break;
case 0x01:
writer(1, "\\x01"_sd);
break;
case 0x02:
writer(1, "\\x02"_sd);
break;
case 0x03:
writer(1, "\\x03"_sd);
break;
case 0x04:
writer(1, "\\x04"_sd);
break;
case 0x05:
writer(1, "\\x05"_sd);
break;
case 0x06:
writer(1, "\\x06"_sd);
break;
case 0x07:
writer(1, "\\a"_sd);
break;
case 0x08:
writer(1, "\\b"_sd);
break;
case 0x09:
writer(1, "\\t"_sd);
break;
case 0x0a:
writer(1, "\\n"_sd);
break;
case 0x0b:
writer(1, "\\v"_sd);
break;
case 0x0c:
writer(1, "\\f"_sd);
break;
case 0x0d:
writer(1, "\\r"_sd);
break;
case 0x0e:
writer(1, "\\x0e"_sd);
break;
case 0x0f:
writer(1, "\\x0f"_sd);
break;
case 0x10:
writer(1, "\\x10"_sd);
break;
case 0x11:
writer(1, "\\x11"_sd);
break;
case 0x12:
writer(1, "\\x12"_sd);
break;
case 0x13:
writer(1, "\\x13"_sd);
break;
case 0x14:
writer(1, "\\x14"_sd);
break;
case 0x15:
writer(1, "\\x15"_sd);
break;
case 0x16:
writer(1, "\\x16"_sd);
break;
case 0x17:
writer(1, "\\x17"_sd);
break;
case 0x18:
writer(1, "\\x18"_sd);
break;
case 0x19:
writer(1, "\\x19"_sd);
break;
case 0x1a:
writer(1, "\\x1a"_sd);
break;
case 0x1b:
writer(1, "\\e"_sd);
break;
case 0x1c:
writer(1, "\\x1c"_sd);
break;
case 0x1d:
writer(1, "\\x1d"_sd);
break;
case 0x1e:
writer(1, "\\x1e"_sd);
break;
case 0x1f:
writer(1, "\\x1f"_sd);
break;
case '\\':
writer(1, "\\\\"_sd);
break;
case 0x7f:
writer(1, "\\x7f"_sd);
break;
default:
break;
}
},
[](const auto& writer, uint8_t unescaped) {
std::array<char, 4> buffer = {
'\\', 'x', kHexChar[unescaped >> 4], kHexChar[unescaped & 0xf]};
writer(1, StringData(buffer.data(), buffer.size()));
},
[](const auto& writer, uint8_t first, uint8_t second) {
std::array<char, 8> buffer = {'\\',
'x',
kHexChar[first >> 4],
kHexChar[first & 0xf],
'\\',
'x',
kHexChar[second >> 4],
kHexChar[second & 0xf]};
writer(2, StringData(buffer.data(), buffer.size()));
}
);
}
std::string escapeForJSON(StringData str) {
return escape(str,
[](const auto& writer, uint8_t unescaped) {
switch (unescaped) {
case '\0':
writer(1, "\\u0000"_sd);
break;
case 0x01:
writer(1, "\\u0001"_sd);
break;
case 0x02:
writer(1, "\\u0002"_sd);
break;
case 0x03:
writer(1, "\\u0003"_sd);
break;
case 0x04:
writer(1, "\\u0004"_sd);
break;
case 0x05:
writer(1, "\\u0005"_sd);
break;
case 0x06:
writer(1, "\\u0006"_sd);
break;
case 0x07:
writer(1, "\\u0007"_sd);
break;
case 0x08:
writer(1, "\\b"_sd);
break;
case 0x09:
writer(1, "\\t"_sd);
break;
case 0x0a:
writer(1, "\\n"_sd);
break;
case 0x0b:
writer(1, "\\u000b"_sd);
break;
case 0x0c:
writer(1, "\\f"_sd);
break;
case 0x0d:
writer(1, "\\r"_sd);
break;
case 0x0e:
writer(1, "\\u000e"_sd);
break;
case 0x0f:
writer(1, "\\u000f"_sd);
break;
case 0x10:
writer(1, "\\u0010"_sd);
break;
case 0x11:
writer(1, "\\u0011"_sd);
break;
case 0x12:
writer(1, "\\u0012"_sd);
break;
case 0x13:
writer(1, "\\u0013"_sd);
break;
case 0x14:
writer(1, "\\u0014"_sd);
break;
case 0x15:
writer(1, "\\u0015"_sd);
break;
case 0x16:
writer(1, "\\u0016"_sd);
break;
case 0x17:
writer(1, "\\u0017"_sd);
break;
case 0x18:
writer(1, "\\u0018"_sd);
break;
case 0x19:
writer(1, "\\u0019"_sd);
break;
case 0x1a:
writer(1, "\\u001a"_sd);
break;
case 0x1b:
writer(1, "\\u001b"_sd);
break;
case 0x1c:
writer(1, "\\u000c"_sd);
break;
case 0x1d:
writer(1, "\\u001d"_sd);
break;
case 0x1e:
writer(1, "\\u001e"_sd);
break;
case 0x1f:
writer(1, "\\u001f"_sd);
break;
case '\\':
writer(1, "\\\\"_sd);
break;
case '\"':
writer(1, "\\\""_sd);
break;
case 0x7f:
writer(1, "\\u007f"_sd);
break;
default:
break;
}
},
[](const auto& writer, uint8_t unescaped) {
std::array<char, 6> buffer = {
'\\', 'u', '0', '0', kHexChar[unescaped >> 4], kHexChar[unescaped & 0xf]};
writer(1, StringData(buffer.data(), buffer.size()));
},
[](const auto& writer, uint8_t first, uint8_t second) {
std::array<char, 6> buffer = {'\\',
'u',
kHexChar[first >> 4],
kHexChar[first & 0xf],
kHexChar[second >> 4],
kHexChar[second & 0xf]};
writer(2, StringData(buffer.data(), buffer.size()));
});
}
} // namespace mongo::logv2
|
