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
|
// string_data.h
/* Copyright 2010 10gen Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License, version 3,
* as published by the Free Software Foundation.
*
* 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
* GNU Affero General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*
* 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 GNU Affero General 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.
*/
#pragma once
#include <algorithm> // for min
#include <cstring>
#include <iosfwd>
#include <limits>
#include <stdexcept>
#include <string>
#include "mongo/stdx/type_traits.h"
#define MONGO_INCLUDE_INVARIANT_H_WHITELISTED
#include "mongo/util/invariant.h"
#undef MONGO_INCLUDE_INVARIANT_H_WHITELISTED
namespace mongo {
/**
* A StringData object wraps a 'const std::string&' or a 'const char*' without copying its
* contents. The most common usage is as a function argument that takes any of the two
* forms of strings above. Fundamentally, this class tries go around the fact that string
* literals in C++ are char[N]'s.
*
* Notes:
*
* + The object StringData wraps around must be alive while the StringData is.
*
* + Because std::string data can be used to pass a substring around, one should never assume a
* rawData() terminates with a null.
*/
class StringData {
struct TrustedInitTag {};
constexpr StringData(const char* c, size_t len, TrustedInitTag) : _data(c), _size(len) {}
public:
// Declared in string_data_comparator_interface.h.
class ComparatorInterface;
// Iterator type
using const_iterator = const char*;
/** Constructs an empty StringData. */
constexpr StringData() = default;
/**
* Constructs a StringData, for the case where the length of the
* string is not known. 'c' must either be NULL, or a pointer to a
* null-terminated string.
*/
StringData(const char* str) : StringData(str, str ? std::strlen(str) : 0) {}
/**
* Constructs a StringData, for the case of a std::string. We can
* use the trusted init path with no follow on checks because
* string::data is assured to never return nullptr.
*/
StringData(const std::string& s) : StringData(s.data(), s.length(), TrustedInitTag()) {}
/**
* Constructs a StringData with an explicit length. 'c' must
* either be NULL (in which case len must be zero), or be a
* pointer into a character array. The StringData will refer to
* the first 'len' characters starting at 'c'. The range of
* characters c to c+len must be valid.
*/
StringData(const char* c, size_t len) : StringData(c, len, TrustedInitTag()) {
invariant(_data || (_size == 0));
}
/**
* Constructs a StringData from a user defined literal. This allows
* for constexpr creation of StringData's that are known at compile time.
*/
constexpr friend StringData operator"" _sd(const char* c, std::size_t len);
/**
* Constructs a StringData with begin and end iterators. begin points to the beginning of the
* string. end points to the position past the end of the string. In a null-terminated string,
* end points to the null-terminator.
*
* We template the second parameter to ensure if StringData is called with 0 in the second
* parameter, the (ptr,len) constructor is chosen instead.
*/
template <
typename InputIt,
typename = stdx::enable_if_t<std::is_same<StringData::const_iterator, InputIt>::value>>
StringData(InputIt begin, InputIt end) {
invariant(begin && end);
_data = begin;
_size = std::distance(begin, end);
}
/**
* Returns -1, 0, or 1 if 'this' is less, equal, or greater than 'other' in
* lexicographical order.
*/
int compare(StringData other) const;
/**
* note: this uses tolower, and therefore does not handle
* come languages correctly.
* should be use sparingly
*/
bool equalCaseInsensitive(StringData other) const;
void copyTo(char* dest, bool includeEndingNull) const;
StringData substr(size_t pos, size_t n = std::numeric_limits<size_t>::max()) const;
//
// finders
//
size_t find(char c, size_t fromPos = 0) const;
size_t find(StringData needle, size_t fromPos = 0) const;
size_t rfind(char c, size_t fromPos = std::string::npos) const;
/**
* Returns true if 'prefix' is a substring of this instance, anchored at position 0.
*/
bool startsWith(StringData prefix) const;
/**
* Returns true if 'suffix' is a substring of this instance, anchored at the end.
*/
bool endsWith(StringData suffix) const;
//
// accessors
//
/**
* Get the pointer to the first byte of StringData. This is not guaranteed to be
* null-terminated, so if using this without checking size(), you are likely doing
* something wrong.
*/
constexpr const char* rawData() const {
return _data;
}
constexpr size_t size() const {
return _size;
}
constexpr bool empty() const {
return size() == 0;
}
std::string toString() const {
return std::string(_data, size());
}
constexpr char operator[](unsigned pos) const {
return _data[pos];
}
//
// iterators
//
constexpr const_iterator begin() const {
return rawData();
}
constexpr const_iterator end() const {
return rawData() + size();
}
private:
const char* _data = nullptr; // is not guaranted to be null terminated (see "notes" above)
size_t _size = 0; // 'size' does not include the null terminator
};
inline bool operator==(StringData lhs, StringData rhs) {
return (lhs.size() == rhs.size()) && (lhs.compare(rhs) == 0);
}
inline bool operator!=(StringData lhs, StringData rhs) {
return !(lhs == rhs);
}
inline bool operator<(StringData lhs, StringData rhs) {
return lhs.compare(rhs) < 0;
}
inline bool operator<=(StringData lhs, StringData rhs) {
return lhs.compare(rhs) <= 0;
}
inline bool operator>(StringData lhs, StringData rhs) {
return lhs.compare(rhs) > 0;
}
inline bool operator>=(StringData lhs, StringData rhs) {
return lhs.compare(rhs) >= 0;
}
std::ostream& operator<<(std::ostream& stream, StringData value);
constexpr StringData operator"" _sd(const char* c, std::size_t len) {
return StringData(c, len, StringData::TrustedInitTag{});
}
inline int StringData::compare(StringData other) const {
// It is illegal to pass nullptr to memcmp. It is an invariant of
// StringData that if _data is nullptr, _size is zero. If asked to
// compare zero bytes, memcmp returns zero (how could they
// differ?). So, if either StringData object has a nullptr _data
// object, then memcmp would return zero. Achieve this by assuming
// zero, and only calling memcmp if both pointers are valid.
int res = 0;
if (_data && other._data)
res = memcmp(_data, other._data, std::min(_size, other._size));
if (res != 0)
return res > 0 ? 1 : -1;
if (_size == other._size)
return 0;
return _size > other._size ? 1 : -1;
}
inline bool StringData::equalCaseInsensitive(StringData other) const {
if (other.size() != size())
return false;
for (size_t x = 0; x < size(); x++) {
char a = _data[x];
char b = other._data[x];
if (a == b)
continue;
if (tolower(a) == tolower(b))
continue;
return false;
}
return true;
}
inline void StringData::copyTo(char* dest, bool includeEndingNull) const {
if (_data)
memcpy(dest, _data, size());
if (includeEndingNull)
dest[size()] = 0;
}
inline size_t StringData::find(char c, size_t fromPos) const {
if (fromPos >= size())
return std::string::npos;
const void* x = memchr(_data + fromPos, c, _size - fromPos);
if (x == 0)
return std::string::npos;
return static_cast<size_t>(static_cast<const char*>(x) - _data);
}
inline size_t StringData::find(StringData needle, size_t fromPos) const {
size_t mx = size();
size_t needleSize = needle.size();
if (needleSize == 0)
return 0;
else if (needleSize > mx)
return std::string::npos;
if (fromPos > size())
return std::string::npos;
mx -= needleSize;
for (size_t i = fromPos; i <= mx; i++) {
if (memcmp(_data + i, needle._data, needleSize) == 0)
return i;
}
return std::string::npos;
}
inline size_t StringData::rfind(char c, size_t fromPos) const {
const size_t sz = size();
if (fromPos > sz)
fromPos = sz;
for (const char* cur = _data + fromPos; cur > _data; --cur) {
if (*(cur - 1) == c)
return (cur - _data) - 1;
}
return std::string::npos;
}
inline StringData StringData::substr(size_t pos, size_t n) const {
if (pos > size())
throw std::out_of_range("out of range");
// truncate to end of string
if (n > size() - pos)
n = size() - pos;
return StringData(_data + pos, n);
}
inline bool StringData::startsWith(StringData prefix) const {
// TODO: Investigate an optimized implementation.
return substr(0, prefix.size()) == prefix;
}
inline bool StringData::endsWith(StringData suffix) const {
// TODO: Investigate an optimized implementation.
const size_t thisSize = size();
const size_t suffixSize = suffix.size();
if (suffixSize > thisSize)
return false;
return substr(thisSize - suffixSize) == suffix;
}
inline std::string operator+(std::string lhs, StringData rhs) {
if (!rhs.empty())
lhs.append(rhs.rawData(), rhs.size());
return lhs;
}
inline std::string operator+(StringData lhs, std::string rhs) {
if (!lhs.empty())
rhs.insert(0, lhs.rawData(), lhs.size());
return rhs;
}
} // namespace mongo
|