/
ascii_number.h
323 lines (300 loc) · 10.8 KB
/
ascii_number.h
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
#ifndef FASTFLOAT_ASCII_NUMBER_H
#define FASTFLOAT_ASCII_NUMBER_H
#include <cstdio>
#include <cctype>
#include <cstdint>
#include <cstring>
#include <iterator>
#include "float_common.h"
namespace fast_float {
// Next function can be micro-optimized, but compilers are entirely
// able to optimize it well.
fastfloat_really_inline bool is_integer(char c) noexcept { return c >= '0' && c <= '9'; }
fastfloat_really_inline uint64_t byteswap(uint64_t val) {
return (val & 0xFF00000000000000) >> 56
| (val & 0x00FF000000000000) >> 40
| (val & 0x0000FF0000000000) >> 24
| (val & 0x000000FF00000000) >> 8
| (val & 0x00000000FF000000) << 8
| (val & 0x0000000000FF0000) << 24
| (val & 0x000000000000FF00) << 40
| (val & 0x00000000000000FF) << 56;
}
fastfloat_really_inline uint64_t read_u64(const char *chars) {
uint64_t val;
::memcpy(&val, chars, sizeof(uint64_t));
#if FASTFLOAT_IS_BIG_ENDIAN == 1
// Need to read as-if the number was in little-endian order.
val = byteswap(val);
#endif
return val;
}
fastfloat_really_inline void write_u64(uint8_t *chars, uint64_t val) {
#if FASTFLOAT_IS_BIG_ENDIAN == 1
// Need to read as-if the number was in little-endian order.
val = byteswap(val);
#endif
::memcpy(chars, &val, sizeof(uint64_t));
}
// credit @aqrit
fastfloat_really_inline uint32_t parse_eight_digits_unrolled(uint64_t val) {
const uint64_t mask = 0x000000FF000000FF;
const uint64_t mul1 = 0x000F424000000064; // 100 + (1000000ULL << 32)
const uint64_t mul2 = 0x0000271000000001; // 1 + (10000ULL << 32)
val -= 0x3030303030303030;
val = (val * 10) + (val >> 8); // val = (val * 2561) >> 8;
val = (((val & mask) * mul1) + (((val >> 16) & mask) * mul2)) >> 32;
return uint32_t(val);
}
fastfloat_really_inline uint32_t parse_eight_digits_unrolled(const char *chars) noexcept {
return parse_eight_digits_unrolled(read_u64(chars));
}
// credit @aqrit
fastfloat_really_inline bool is_made_of_eight_digits_fast(uint64_t val) noexcept {
return !((((val + 0x4646464646464646) | (val - 0x3030303030303030)) &
0x8080808080808080));
}
fastfloat_really_inline bool is_made_of_eight_digits_fast(const char *chars) noexcept {
return is_made_of_eight_digits_fast(read_u64(chars));
}
struct parsed_number_string {
int64_t exponent;
uint64_t mantissa;
const char *lastmatch;
bool negative;
bool valid;
bool too_many_digits;
};
// Assuming that you use no more than 19 digits, this will
// parse an ASCII string.
fastfloat_really_inline
parsed_number_string parse_number_string(const char *p, const char *pend, parse_options options) noexcept {
const chars_format fmt = options.format;
const char decimal_point = options.decimal_point;
parsed_number_string answer;
answer.valid = false;
answer.too_many_digits = false;
answer.negative = (*p == '-');
if (*p == '-') { // C++17 20.19.3.(7.1) explicitly forbids '+' sign here
++p;
if (p == pend) {
return answer;
}
if (!is_integer(*p) && (*p != decimal_point)) { // a sign must be followed by an integer or the dot
return answer;
}
}
const char *const start_digits = p;
uint64_t i = 0; // an unsigned int avoids signed overflows (which are bad)
while ((p != pend) && is_integer(*p)) {
// a multiplication by 10 is cheaper than an arbitrary integer
// multiplication
i = 10 * i +
uint64_t(*p - '0'); // might overflow, we will handle the overflow later
++p;
}
const char *const end_of_integer_part = p;
int64_t digit_count = int64_t(end_of_integer_part - start_digits);
int64_t exponent = 0;
if ((p != pend) && (*p == decimal_point)) {
++p;
// Fast approach only tested under little endian systems
if ((std::distance(p, pend) >= 8) && is_made_of_eight_digits_fast(p)) {
i = i * 100000000 + parse_eight_digits_unrolled(p); // in rare cases, this will overflow, but that's ok
p += 8;
if ((std::distance(p, pend) >= 8) && is_made_of_eight_digits_fast(p)) {
i = i * 100000000 + parse_eight_digits_unrolled(p); // in rare cases, this will overflow, but that's ok
p += 8;
}
}
while ((p != pend) && is_integer(*p)) {
uint8_t digit = uint8_t(*p - '0');
++p;
i = i * 10 + digit; // in rare cases, this will overflow, but that's ok
}
exponent = end_of_integer_part + 1 - p;
digit_count -= exponent;
}
// we must have encountered at least one integer!
if (digit_count == 0) {
return answer;
}
int64_t exp_number = 0; // explicit exponential part
if ((fmt & chars_format::scientific) && (p != pend) && (('e' == *p) || ('E' == *p))) {
const char * location_of_e = p;
++p;
bool neg_exp = false;
if ((p != pend) && ('-' == *p)) {
neg_exp = true;
++p;
} else if ((p != pend) && ('+' == *p)) { // '+' on exponent is allowed by C++17 20.19.3.(7.1)
++p;
}
if ((p == pend) || !is_integer(*p)) {
if(!(fmt & chars_format::fixed)) {
// We are in error.
return answer;
}
// Otherwise, we will be ignoring the 'e'.
p = location_of_e;
} else {
while ((p != pend) && is_integer(*p)) {
uint8_t digit = uint8_t(*p - '0');
if (exp_number < 0x10000) {
exp_number = 10 * exp_number + digit;
}
++p;
}
if(neg_exp) { exp_number = - exp_number; }
exponent += exp_number;
}
} else {
// If it scientific and not fixed, we have to bail out.
if((fmt & chars_format::scientific) && !(fmt & chars_format::fixed)) { return answer; }
}
answer.lastmatch = p;
answer.valid = true;
// If we frequently had to deal with long strings of digits,
// we could extend our code by using a 128-bit integer instead
// of a 64-bit integer. However, this is uncommon.
//
// We can deal with up to 19 digits.
if (digit_count > 19) { // this is uncommon
// It is possible that the integer had an overflow.
// We have to handle the case where we have 0.0000somenumber.
// We need to be mindful of the case where we only have zeroes...
// E.g., 0.000000000...000.
const char *start = start_digits;
while ((start != pend) && (*start == '0' || *start == decimal_point)) {
if(*start == '0') { digit_count --; }
start++;
}
if (digit_count > 19) {
answer.too_many_digits = true;
// Let us start again, this time, avoiding overflows.
i = 0;
p = start_digits;
const uint64_t minimal_nineteen_digit_integer{1000000000000000000};
while((i < minimal_nineteen_digit_integer) && (p != pend) && is_integer(*p)) {
i = i * 10 + uint64_t(*p - '0');
++p;
}
if (i >= minimal_nineteen_digit_integer) { // We have a big integers
exponent = end_of_integer_part - p + exp_number;
} else { // We have a value with a fractional component.
p++; // skip the dot
const char *first_after_period = p;
while((i < minimal_nineteen_digit_integer) && (p != pend) && is_integer(*p)) {
i = i * 10 + uint64_t(*p - '0');
++p;
}
exponent = first_after_period - p + exp_number;
}
// We have now corrected both exponent and i, to a truncated value
}
}
answer.exponent = exponent;
answer.mantissa = i;
return answer;
}
// This should always succeed since it follows a call to parse_number_string
// This function could be optimized. In particular, we could stop after 19 digits
// and try to bail out. Furthermore, we should be able to recover the computed
// exponent from the pass in parse_number_string.
fastfloat_really_inline decimal parse_decimal(const char *p, const char *pend, parse_options options) noexcept {
const char decimal_point = options.decimal_point;
decimal answer;
answer.num_digits = 0;
answer.decimal_point = 0;
answer.truncated = false;
answer.negative = (*p == '-');
if (*p == '-') { // C++17 20.19.3.(7.1) explicitly forbids '+' sign here
++p;
}
// skip leading zeroes
while ((p != pend) && (*p == '0')) {
++p;
}
while ((p != pend) && is_integer(*p)) {
if (answer.num_digits < max_digits) {
answer.digits[answer.num_digits] = uint8_t(*p - '0');
}
answer.num_digits++;
++p;
}
if ((p != pend) && (*p == decimal_point)) {
++p;
const char *first_after_period = p;
// if we have not yet encountered a zero, we have to skip it as well
if(answer.num_digits == 0) {
// skip zeros
while ((p != pend) && (*p == '0')) {
++p;
}
}
// We expect that this loop will often take the bulk of the running time
// because when a value has lots of digits, these digits often
while ((std::distance(p, pend) >= 8) && (answer.num_digits + 8 < max_digits)) {
uint64_t val = read_u64(p);
if(! is_made_of_eight_digits_fast(val)) { break; }
// We have eight digits, process them in one go!
val -= 0x3030303030303030;
write_u64(answer.digits + answer.num_digits, val);
answer.num_digits += 8;
p += 8;
}
while ((p != pend) && is_integer(*p)) {
if (answer.num_digits < max_digits) {
answer.digits[answer.num_digits] = uint8_t(*p - '0');
}
answer.num_digits++;
++p;
}
answer.decimal_point = int32_t(first_after_period - p);
}
// We want num_digits to be the number of significant digits, excluding
// leading *and* trailing zeros! Otherwise the truncated flag later is
// going to be misleading.
if(answer.num_digits > 0) {
// We potentially need the answer.num_digits > 0 guard because we
// prune leading zeros. So with answer.num_digits > 0, we know that
// we have at least one non-zero digit.
const char *preverse = p - 1;
int32_t trailing_zeros = 0;
while ((*preverse == '0') || (*preverse == decimal_point)) {
if(*preverse == '0') { trailing_zeros++; };
--preverse;
}
answer.decimal_point += int32_t(answer.num_digits);
answer.num_digits -= uint32_t(trailing_zeros);
}
if(answer.num_digits > max_digits) {
answer.truncated = true;
answer.num_digits = max_digits;
}
if ((p != pend) && (('e' == *p) || ('E' == *p))) {
++p;
bool neg_exp = false;
if ((p != pend) && ('-' == *p)) {
neg_exp = true;
++p;
} else if ((p != pend) && ('+' == *p)) { // '+' on exponent is allowed by C++17 20.19.3.(7.1)
++p;
}
int32_t exp_number = 0; // exponential part
while ((p != pend) && is_integer(*p)) {
uint8_t digit = uint8_t(*p - '0');
if (exp_number < 0x10000) {
exp_number = 10 * exp_number + digit;
}
++p;
}
answer.decimal_point += (neg_exp ? -exp_number : exp_number);
}
// In very rare cases, we may have fewer than 19 digits, we want to be able to reliably
// assume that all digits up to max_digit_without_overflow have been initialized.
for(uint32_t i = answer.num_digits; i < max_digit_without_overflow; i++) { answer.digits[i] = 0; }
return answer;
}
} // namespace fast_float
#endif