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
|
/* Copyright 2012 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.
*/
#include "mongo/platform/basic.h"
#include "mongo/base/parse_number.h"
#include <algorithm>
#include <cerrno>
#include <cstdlib>
#include <limits>
#include <string>
#include "mongo/platform/cstdint.h"
namespace mongo {
/**
* Returns the value of the digit "c", with the same conversion behavior as strtol.
*
* Assumes "c" is an ASCII character or UTF-8 octet.
*/
static uint8_t _digitValue(char c) {
if (c >= '0' && c <= '9')
return uint8_t(c - '0');
if (c >= 'a' && c <= 'z')
return uint8_t(c - 'a' + 10);
if (c >= 'A' && c <= 'Z')
return uint8_t(c - 'A' + 10);
return 36; // Illegal digit value for all supported bases.
}
/**
* Assuming "stringValue" represents a parseable number, extracts the sign and returns a
* substring with any sign characters stripped away. "*isNegative" is set to true if the
* number is negative, and false otherwise.
*/
static inline StringData _extractSign(StringData stringValue, bool* isNegative) {
if (stringValue.empty()) {
*isNegative = false;
return stringValue;
}
bool foundSignMarker;
switch (stringValue[0]) {
case '-':
foundSignMarker = true;
*isNegative = true;
break;
case '+':
foundSignMarker = true;
*isNegative = false;
break;
default:
foundSignMarker = false;
*isNegative = false;
break;
}
if (foundSignMarker)
return stringValue.substr(1);
return stringValue;
}
/**
* Assuming "stringValue" represents a parseable number, determines what base to use given
* "inputBase". Stores the correct base into "*outputBase". Follows strtol rules. If
* "inputBase" is not 0, *outputBase is set to "inputBase". Otherwise, if "stringValue" starts
* with "0x" or "0X", sets outputBase to 16, or if it starts with 0, sets outputBase to 8.
*
* Returns stringValue, unless it sets *outputBase to 16, in which case it will strip off the
* "0x" or "0X" prefix, if present.
*/
static inline StringData _extractBase(
StringData stringValue, int inputBase, int* outputBase) {
const StringData hexPrefixLower("0x", StringData::LiteralTag());
const StringData hexPrefixUpper("0X", StringData::LiteralTag());
if (inputBase == 0) {
if (stringValue.size() > 2 && (stringValue.startsWith(hexPrefixLower) ||
stringValue.startsWith(hexPrefixUpper))) {
*outputBase = 16;
return stringValue.substr(2);
}
if (stringValue.size() > 1 && stringValue[0] == '0') {
*outputBase = 8;
return stringValue;
}
*outputBase = 10;
return stringValue;
}
else {
*outputBase = inputBase;
if (inputBase == 16 && (stringValue.startsWith(hexPrefixLower) ||
stringValue.startsWith(hexPrefixUpper))) {
return stringValue.substr(2);
}
return stringValue;
}
}
template <typename NumberType>
Status parseNumberFromStringWithBase(
StringData stringValue, int base, NumberType* result) {
typedef ::std::numeric_limits<NumberType> limits;
if (base == 1 || base < 0 || base > 36)
return Status(ErrorCodes::BadValue, "Invalid base", 0);
bool isNegative = false;
StringData str = _extractBase(_extractSign(stringValue, &isNegative), base, &base);
if (str.empty())
return Status(ErrorCodes::FailedToParse, "No digits");
NumberType n(0);
if (isNegative) {
if (limits::is_signed) {
for (size_t i = 0; i < str.size(); ++i) {
NumberType digitValue = NumberType(_digitValue(str[i]));
if (int(digitValue) >= base) {
return Status(ErrorCodes::FailedToParse,
"Bad digit \"" + str.substr(i, 1).toString() +
"\" while parsing " + stringValue.toString());
}
// MSVC: warning C4146: unary minus operator applied to unsigned type, result still unsigned
// This code is statically known to be dead when NumberType is unsigned, so the warning is not real
#pragma warning(push)
#pragma warning(disable:4146)
if ((NumberType(limits::min() / base) > n) ||
((limits::min() - NumberType(n * base)) > -digitValue)) {
#pragma warning(pop)
return Status(ErrorCodes::FailedToParse, "Underflow");
}
n *= NumberType(base);
n -= NumberType(digitValue);
}
}
else {
return Status(ErrorCodes::FailedToParse, "Negative value");
}
}
else {
for (size_t i = 0; i < str.size(); ++i) {
NumberType digitValue = NumberType(_digitValue(str[i]));
if (int(digitValue) >= base) {
return Status(ErrorCodes::FailedToParse,
"Bad digit \"" + str.substr(i, 1).toString() +
"\" while parsing " + stringValue.toString());
}
if ((NumberType(limits::max() / base) < n) ||
(NumberType(limits::max() - n * base) < digitValue)) {
return Status(ErrorCodes::FailedToParse, "Overflow");
}
n *= NumberType(base);
n += NumberType(digitValue);
}
}
*result = n;
return Status::OK();
}
// Definition of the various supported implementations of parseNumberFromStringWithBase.
#define DEFINE_PARSE_NUMBER_FROM_STRING_WITH_BASE(NUMBER_TYPE) \
template MONGO_COMPILER_API_EXPORT Status parseNumberFromStringWithBase<NUMBER_TYPE>(StringData, int, NUMBER_TYPE*);
DEFINE_PARSE_NUMBER_FROM_STRING_WITH_BASE(long)
DEFINE_PARSE_NUMBER_FROM_STRING_WITH_BASE(long long)
DEFINE_PARSE_NUMBER_FROM_STRING_WITH_BASE(unsigned long)
DEFINE_PARSE_NUMBER_FROM_STRING_WITH_BASE(unsigned long long)
DEFINE_PARSE_NUMBER_FROM_STRING_WITH_BASE(short)
DEFINE_PARSE_NUMBER_FROM_STRING_WITH_BASE(unsigned short)
DEFINE_PARSE_NUMBER_FROM_STRING_WITH_BASE(int)
DEFINE_PARSE_NUMBER_FROM_STRING_WITH_BASE(unsigned int)
DEFINE_PARSE_NUMBER_FROM_STRING_WITH_BASE(int8_t);
DEFINE_PARSE_NUMBER_FROM_STRING_WITH_BASE(uint8_t);
#undef DEFINE_PARSE_NUMBER_FROM_STRING_WITH_BASE
#ifdef _WIN32
namespace {
/**
* Converts ascii c-locale uppercase characters to lower case, leaves other char values
* unchanged.
*/
char toLowerAscii(char c) {
if (isascii(c) && isupper(c))
return _tolower(c);
return c;
}
} // namespace
#endif // defined(_WIN32)
template <>
Status parseNumberFromStringWithBase<double>(StringData stringValue,
int base,
double* result) {
if (base != 0) {
return Status(ErrorCodes::BadValue,
"Must pass 0 as base to parseNumberFromStringWithBase<double>.");
}
if (stringValue.empty())
return Status(ErrorCodes::FailedToParse, "Empty string");
if (isspace(stringValue[0]))
return Status(ErrorCodes::FailedToParse, "Leading whitespace");
std::string str = stringValue.toString();
const char* cStr = str.c_str();
char* endp;
errno = 0;
double d = strtod(cStr, &endp);
int actualErrno = errno;
if (endp != stringValue.size() + cStr) {
#ifdef _WIN32
// The Windows libc implementation of strtod cannot parse +/-infinity or nan,
// so handle that here.
std::transform(str.begin(), str.end(), str.begin(), toLowerAscii);
if (str == StringData("nan", StringData::LiteralTag())) {
*result = std::numeric_limits<double>::quiet_NaN();
return Status::OK();
}
else if (str == StringData("+infinity", StringData::LiteralTag()) ||
str == StringData("infinity", StringData::LiteralTag())) {
*result = std::numeric_limits<double>::infinity();
return Status::OK();
}
else if (str == StringData("-infinity", StringData::LiteralTag())) {
*result = -std::numeric_limits<double>::infinity();
return Status::OK();
}
#endif // defined(_WIN32)
return Status(ErrorCodes::FailedToParse, "Did not consume whole number.");
}
if (actualErrno == ERANGE)
return Status(ErrorCodes::FailedToParse, "Out of range");
*result = d;
return Status::OK();
}
} // namespace mongo
|