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
|
/* NOTE:
Do not include this file in your project. The fparser.cc file #includes
this file internally and thus you don't need to do anything (other than keep
this file in the same directory as fparser.cc).
Part of this file is generated code (by using the make_function_name_parser
utility, found in the development version of this library). It's not intended
to be modified by hand.
*/
unsigned nameLength = 0;
const unsigned maximumNameLength = 0x80000000U-8;
/*
Due to the manner the identifier lengths are returned from
the readOpcode() function, the maximum supported length for
identifiers is 0x7FFFFFFF bytes. We minus 8 here to add some
buffer, because of the multibyteness of UTF-8.
Function names are limited to 0xFFFF bytes instead, but because
function names that long just are not defined, the point is moot.
*/
const unsigned char* const uptr = (const unsigned char*) input;
typedef signed char schar;
while(likely(nameLength < maximumNameLength))
{
unsigned char byte = uptr[nameLength+0];
/* Handle the common case of A-Za-z first */
if(byte >= 0x40)
{
if(byte < 0x80) // 0x40..0x7F - most common case
{
// Valid characters in 40..7F: A-Za-z_
// Valid bitmask for 40..5F: 01111111111111111111111111100001
// Valid bitmask for 60..7F: 01111111111111111111111111100000
if(sizeof(unsigned long) == 8)
{
const unsigned n = sizeof(unsigned long)*8-32;
// ^ avoids compiler warning when not 64-bit
unsigned long masklow6bits = 1UL << (byte & 0x3F);
if(masklow6bits & ~((1UL << 0) | (0x0FUL << (0x1B ))
| (1UL << n) | (0x1FUL << (0x1B+n))))
{ ++nameLength; continue; }
}
else
{
unsigned masklow5bits = 1 << (byte & 0x1F);
if((masklow5bits & ~(1 | (0x1F << 0x1B))) || byte == '_')
{ ++nameLength; continue; }
}
break;
}
if(byte < 0xF0)
{
if(byte < 0xE0)
{
if(byte < 0xC2) break; // 0x80..0xC1
if(byte == 0xC2 && uptr[nameLength+1]==0xA0) break; // skip nbsp
// C2-DF - next common case when >= 0x40
// Valid sequence: C2-DF 80-BF
if(schar(uptr[nameLength+1]) > schar(0xBF)) break;
nameLength += 2;
continue;
}
if(byte == 0xE0) // E0
{
// Valid sequence: E0 A0-BF 80-BF
if((unsigned char)(uptr[nameLength+1] - 0xA0) > (0xBF-0xA0)) break;
}
else
{
if(byte == 0xED) break; // ED is invalid
// Valid sequence: E1-EC 80-BF 80-BF
// And: EE-EF 80-BF 80-BF
if(byte == 0xE2)
{
// break on various space characters
if(uptr[nameLength+1] == 0x80
&& (schar(uptr[nameLength+2]) <= schar(0x8B)
|| (uptr[nameLength+2] == 0xAF))) break;
if(uptr[nameLength+1] == 0x81
&& uptr[nameLength+2] == 0x9F) break;
} else
if(byte == 0xE3 && uptr[nameLength+1] == 0x80
&& uptr[nameLength+2] == 0x80) break; // this too
if(schar(uptr[nameLength+1]) > schar(0xBF)) break;
}
if(schar(uptr[nameLength+2]) > schar(0xBF)) break;
nameLength += 3;
continue;
}
if(byte == 0xF0) // F0
{
// Valid sequence: F0 90-BF 80-BF 80-BF
if((unsigned char)(uptr[nameLength+1] - 0x90) > (0xBF-0x90)) break;
}
else
{
if(byte > 0xF4) break; // F5-FF are invalid
if(byte == 0xF4) // F4
{
// Valid sequence: F4 80-8F
if(schar(uptr[nameLength+1]) > schar(0x8F)) break;
}
else
{
// F1-F3
// Valid sequence: F1-F3 80-BF 80-BF 80-BF
if(schar(uptr[nameLength+1]) > schar(0xBF)) break;
}
}
if(schar(uptr[nameLength+2]) > schar(0xBF)) break;
if(schar(uptr[nameLength+3]) > schar(0xBF)) break;
nameLength += 4;
continue;
}
if(nameLength > 0)
{
if(sizeof(unsigned long) == 8)
{
// Valid bitmask for 00..1F: 00000000000000000000000000000000
// Valid bitmask for 20..3F: 00000000000000001111111111000000
const unsigned n = sizeof(unsigned long)*8-32;
// ^ avoids compiler warning when not 64-bit
unsigned long masklow6bits = 1UL << byte;
if(masklow6bits & (((1UL << 10)-1UL) << (16+n)))
{ ++nameLength; continue; }
}
else
{
if(byte >= '0' && byte <= '9')
{ ++nameLength; continue; }
}
}
break;
}
/* This function generated with make_function_name_parser.cc */
#define lO l3 lH
#define lN switch(
#define lM l4 lH
#define lL if('i' l5
#define lK 'n' l5
#define lJ 0x80000003U;
#define lI l1 3]={
#define lH case
#define lG 0x80000005U;
#define lF )==0)l0(
#define lE l8 3;}lH
#define lD std::memcmp(uptr+
#define lC l2 3 lF
#define lB lA 1]){lH
#define lA :lN uptr[
#define l9 'a' lB
#define l8 default:l0
#define l7 lG l0 5;}lH
#define l6 <<16)|
#define l5 ==uptr[
#define l4 lJ l0 3;
#define l3 0x80000004U;l0 4;
#define l2 lD 1,tmp,
#define l1 static const char tmp[
#define l0 return
lN
nameLength){lH
2:lL
0]&&'f' l5
1])l0(cIf
l6
0x80000002U;l0
2;lH
3
lA
0]){lH
l9'b':if('s' l5
2])l0(cAbs
l6
lM'r':if('g' l5
2])l0(cArg
l6
l4
lE'c' lB'o' lA
2]){lH's':l0(cCos
l6
lJ
lH't':l0(cCot
l6
lJ
lE's':if('c' l5
2])l0(cCsc
l6
l4
lE'e':if('x' l5
1]&&'p' l5
2])l0(cExp
l6
lM'i':if(lK
1]&&'t' l5
2])l0(cInt
l6
lM'l':if('o' l5
1]&&'g' l5
2])l0(cLog
l6
lM'm' lB'a':if('x' l5
2])l0(cMax
l6
lM'i':if(lK
2])l0(cMin
l6
l4
lE'p':if('o' l5
1]&&'w' l5
2])l0(cPow
l6
lM's' lB'e':if('c' l5
2])l0(cSec
l6
lM'i':if(lK
2])l0(cSin
l6
l4
lE't':if('a' l5
1]&&lK
2])l0(cTan
l6
l4
lE
4
lA
0]){lH
l9'c':if('o' l5
2]&&'s' l5
3])l0(cAcos
l6
lO's':lL
2]&&lK
3])l0(cAsin
l6
lO't':if('a' l5
2]&&lK
3])l0(cAtan
l6
l3
l8
4;}
lH'c' lB'b':if('r' l5
2]&&'t' l5
3])l0(cCbrt
l6
lO'e':lL
2]&&'l' l5
3])l0(cCeil
l6
lO'o' lA
2]){lH'n':if('j' l5
3])l0(cConj
l6
lO's':if('h' l5
3])l0(cCosh
l6
l3
l8
4;}
l8
4;}
lH'e':{lI'x','p','2'}
;if(lC
cExp2
l6
l3}
lH'i':{lI'm','a','g'}
;if(lC
cImag
l6
l3}
lH'l':{lI'o','g','2'}
;if(lC
cLog2
l6
l3}
lH'r':{lI'e','a','l'}
;if(lC
cReal
l6
l3}
lH's' lB'i':if(lK
2]&&'h' l5
3])l0(cSinh
l6
lO'q':if('r' l5
2]&&'t' l5
3])l0(cSqrt
l6
l3
l8
4;}
lH't':{lI'a','n','h'}
;if(lC
cTanh
l6
l3}
l8
4;}
lH
5
lA
0]){lH
l9'c':{lI'o','s','h'}
;if(lD
2,tmp,3
lF
cAcosh
l6
l7's':{lI'i','n','h'}
;if(lD
2,tmp,3
lF
cAsinh
l6
l7't':if('a' l5
2]){if(lK
3]){lN
uptr[4]){lH'2':l0(cAtan2
l6
lG
lH'h':l0(cAtanh
l6
lG
l8
5;}
}
l0
5;}
l0
5;l8
5;}
lH'f':{l1
4]={'l','o','o','r'}
;if(l2
4
lF
cFloor
l6
l7'h':{l1
4]={'y','p','o','t'}
;if(l2
4
lF
cHypot
l6
l7'l':{l1
4]={'o','g','1','0'}
;if(l2
4
lF
cLog10
l6
l7'p':{l1
4]={'o','l','a','r'}
;if(l2
4
lF
cPolar
l6
l7't':{l1
4]={'r','u','n','c'}
;if(l2
4
lF
cTrunc
l6
lG
l0
5;}
l8
5;}
default:break;}
l0
nameLength;
|
