Repository navigation
Expand file tree
/
Copy pathutf8.v
More file actions
342 lines (336 loc) · 9.01 KB
/
Copy pathutf8.v
File metadata and controls
342 lines (336 loc) · 9.01 KB
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
// Copyright (c) 2019 Alexander Medvednikov. All rights reserved.
// Use of this source code is governed by an MIT license
// that can be found in the LICENSE file.
module builtin
fn (s string) is_utf8() int {
faulty_bytes := 0
len := s.len
i := 0
// # size_t i = 0;
# byte * str = s.str;
#
# while (i < len) {
# if (str[i] <= 0x7F) /* 00..7F */ {
# i += 1;
# }
#else if (str[i] >= 0xC2 && str[i] <= 0xDF) /* C2..DF 80..BF */ {
# if (i + 1 < len) /* Expect a 2nd byte */ {
# if (str[i + 1] < 0x80 || str[i + 1] > 0xBF) {
# printf( "After a first byte between C2 and DF, expecting a 2nd byte between 80 and BF");
# faulty_bytes = 2;
# goto end;
# }
# }
#else {
# printf( "After a first byte between C2 and DF, expecting a 2nd byte.");
# faulty_bytes = 1;
# goto end;
# }
# i += 2;
# }
#else if (str[i] == 0xE0) /* E0 A0..BF 80..BF */ {
# if (i + 2 < len) /* Expect a 2nd and 3rd byte */ {
# if (str[i + 1] < 0xA0 || str[i + 1] > 0xBF) {
# printf( "After a first byte of E0, expecting a 2nd byte between A0 and BF.");
# faulty_bytes = 2;
# goto end;
# }
# if (str[i + 2] < 0x80 || str[i + 2] > 0xBF) {
# printf( "After a first byte of E0, expecting a 3nd byte between 80 and BF.");
# faulty_bytes = 3;
# goto end;
# }
# }
#else {
# printf( "After a first byte of E0, expecting two following bytes.");
# faulty_bytes = 1;
# goto end;
# }
# i += 3;
# }
#else if (str[i] >= 0xE1 && str[i] <= 0xEC) /* E1..EC 80..BF 80..BF */ {
# if (i + 2 < len) /* Expect a 2nd and 3rd byte */ {
# if (str[i + 1] < 0x80 || str[i + 1] > 0xBF) {
# printf( "After a first byte between E1 and EC, expecting the 2nd byte between 80 and BF.");
# faulty_bytes = 2;
# goto end;
# }
# if (str[i + 2] < 0x80 || str[i + 2] > 0xBF) {
# printf( "After a first byte between E1 and EC, expecting the 3rd byte between 80 and BF.");
# faulty_bytes = 3;
# goto end;
# }
# }
#else {
# printf( "After a first byte between E1 and EC, expecting two following bytes.");
# faulty_bytes = 1;
# goto end;
# }
# i += 3;
# }
#else if (str[i] == 0xED) /* ED 80..9F 80..BF */ {
# if (i + 2 < len) /* Expect a 2nd and 3rd byte */ {
# if (str[i + 1] < 0x80 || str[i + 1] > 0x9F) {
# printf( "After a first byte of ED, expecting 2nd byte between 80 and 9F.");
# faulty_bytes = 2;
# goto end;
# }
# if (str[i + 2] < 0x80 || str[i + 2] > 0xBF) {
# printf( "After a first byte of ED, expecting 3rd byte between 80 and BF.");
# faulty_bytes = 3;
# goto end;
# }
# }
#else {
# printf( "After a first byte of ED, expecting two following bytes.");
# faulty_bytes = 1;
# goto end;
# }
# i += 3;
# }
#else if (str[i] >= 0xEE && str[i] <= 0xEF) /* EE..EF 80..BF 80..BF */ {
# if (i + 2 < len) /* Expect a 2nd and 3rd byte */ {
# if (str[i + 1] < 0x80 || str[i + 1] > 0xBF) {
# printf( "After a first byte between EE and EF, expecting 2nd byte between 80 and BF.");
# faulty_bytes = 2;
# goto end;
# }
# if (str[i + 2] < 0x80 || str[i + 2] > 0xBF) {
# printf( "After a first byte between EE and EF, expecting 3rd byte between 80 and BF.");
# faulty_bytes = 3;
# goto end;
# }
# }
#else {
# printf( "After a first byte between EE and EF, two following bytes.");
# faulty_bytes = 1;
# goto end;
# }
# i += 3;
# }
#else if (str[i] == 0xF0) /* F0 90..BF 80..BF 80..BF */ {
# if (i + 3 < len) /* Expect a 2nd, 3rd 3th byte */ {
# if (str[i + 1] < 0x90 || str[i + 1] > 0xBF) {
# printf( "After a first byte of F0, expecting 2nd byte between 90 and BF.");
# faulty_bytes = 2;
# goto end;
# }
# if (str[i + 2] < 0x80 || str[i + 2] > 0xBF) {
# printf( "After a first byte of F0, expecting 3rd byte between 80 and BF.");
# faulty_bytes = 3;
# goto end;
# }
# if (str[i + 3] < 0x80 || str[i + 3] > 0xBF) {
# printf( "After a first byte of F0, expecting 4th byte between 80 and BF.");
# faulty_bytes = 4;
# goto end;
# }
# }
#else {
# printf( "After a first byte of F0, expecting three following bytes.");
# faulty_bytes = 1;
# goto end;
# }
# i += 4;
# }
#else if (str[i] >= 0xF1 && str[i] <= 0xF3) /* F1..F3 80..BF 80..BF 80..BF */ {
# if (i + 3 < len) /* Expect a 2nd, 3rd 3th byte */ {
# if (str[i + 1] < 0x80 || str[i + 1] > 0xBF) {
# printf( "After a first byte of F1, F2, or F3, expecting a 2nd byte between 80 and BF.");
# faulty_bytes = 2;
# goto end;
# }
# if (str[i + 2] < 0x80 || str[i + 2] > 0xBF) {
# printf( "After a first byte of F1, F2, or F3, expecting a 3rd byte between 80 and BF.");
# faulty_bytes = 3;
# goto end;
# }
# if (str[i + 3] < 0x80 || str[i + 3] > 0xBF) {
# printf( "After a first byte of F1, F2, or F3, expecting a 4th byte between 80 and BF.");
# faulty_bytes = 4;
# goto end;
# }
# }
#else {
# printf( "After a first byte of F1, F2, or F3, expecting three following bytes.");
# faulty_bytes = 1;
# goto end;
# }
# i += 4;
# }
#else if (str[i] == 0xF4) /* F4 80..8F 80..BF 80..BF */ {
# if (i + 3 < len) /* Expect a 2nd, 3rd 3th byte */ {
# if (str[i + 1] < 0x80 || str[i + 1] > 0x8F) {
# printf( "After a first byte of F4, expecting 2nd byte between 80 and 8F.");
# faulty_bytes = 2;
# goto end;
# }
# if (str[i + 2] < 0x80 || str[i + 2] > 0xBF) {
# printf( "After a first byte of F4, expecting 3rd byte between 80 and BF.");
# faulty_bytes = 3;
# goto end;
# }
# if (str[i + 3] < 0x80 || str[i + 3] > 0xBF) {
# printf( "After a first byte of F4, expecting 4th byte between 80 and BF.");
# faulty_bytes = 4;
# goto end;
# }
# }
#else {
# printf( "After a first byte of F4, expecting three following bytes.");
# faulty_bytes = 1;
# goto end;
# }
# i += 4;
# }
#else {
# printf( "i=%d Expecting bytes in the following ranges: 00..7F C2..F4.",
# i);
# faulty_bytes = 1;
# goto end;
# }
# }
#
# end: ;
// println('faulty bytes=$faulty_bytes i=$i')
// # printf("c='%c'\n", str[i]);
ok := faulty_bytes == 0
if ok {
return -1
}
if !ok {
println('utf is bad dalen=$len KEK $s sdf')
// s = s.left(i)
}
return i
// return ok
}
/*
fn (s string) runes() []string {
res2 := []string{}
// res := new_empty_array_with_cap_string(s.len)
res := []string{}
if !s.is_utf8() {
mys := s
println('string.me runes bad utf $mys HAHA')
return res
}
for i := 0; i < s.len; i++ {
char_len := 0
# char_len =UTF8_CHAR_LEN(s.str[i]);
switch char_len {
case 1:
// println('ONE')
res <<(char2string(s[i]))
case 2:
// println('TWO')
rune2 := s.substr(i, i + 2)
res <<(rune2)
i++
case 3:
// println('TWO')
rune3 := s.substr(i, i + 3)
res <<(rune3)
i++
i++
case 4:
// println('TWO')
rune4 := s.substr(i, i + 4)
res <<(rune4)
i++
i++
i++
}
}
return res
}
*/
// Convert utf32 to utf8
// utf32 == Codepoint
fn utf32_to_str(code u32) string {
// println('code = $code')
buffer := malloc(5)
# if (code <= 0x7F) {
// println('!!!!!!!1')
# buffer[0] = code;
# return tos(buffer, 1);
# }
# if (code <= 0x7FF) {
// println('!!!!!!!2')
# buffer[0] = 0xC0 | (code >> 6); /* 110xxxxx */
# buffer[1] = 0x80 | (code & 0x3F); /* 10xxxxxx */
# return tos(buffer, 2);
# }
# if (code <= 0xFFFF) {
// println('!!!!!!!3')
# buffer[0] = 0xE0 | (code >> 12); /* 1110xxxx */
# buffer[1] = 0x80 | ((code >> 6) & 0x3F); /* 10xxxxxx */
# buffer[2] = 0x80 | (code & 0x3F); /* 10xxxxxx */
# return tos(buffer, 3);
# }
# if (code <= 0x10FFFF) {
# buffer[0] = 0xF0 | (code >> 18); /* 11110xxx */
# buffer[1] = 0x80 | ((code >> 12) & 0x3F); /* 10xxxxxx */
# buffer[2] = 0x80 | ((code >> 6) & 0x3F); /* 10xxxxxx */
# buffer[3] = 0x80 | (code & 0x3F); /* 10xxxxxx */
# return tos(buffer, 4);
# }
return ''
}
// TODO copypasta
fn utf32_to_str_no_malloc(code u32, buf voidptr) string {
// println('code = $code')
# char* buffer = buf;
# if (code <= 0x7F) {
// println('!!!!!!!1')
# buffer[0] = code;
# return tos(buffer, 1);
# }
# if (code <= 0x7FF) {
// println('!!!!!!!2')
# buffer[0] = 0xC0 | (code >> 6); /* 110xxxxx */
# buffer[1] = 0x80 | (code & 0x3F); /* 10xxxxxx */
# return tos(buffer, 2);
# }
# if (code <= 0xFFFF) {
// println('!!!!!!!3')
# buffer[0] = 0xE0 | (code >> 12); /* 1110xxxx */
# buffer[1] = 0x80 | ((code >> 6) & 0x3F); /* 10xxxxxx */
# buffer[2] = 0x80 | (code & 0x3F); /* 10xxxxxx */
# return tos(buffer, 3);
# }
# if (code <= 0x10FFFF) {
# buffer[0] = 0xF0 | (code >> 18); /* 11110xxx */
# buffer[1] = 0x80 | ((code >> 12) & 0x3F); /* 10xxxxxx */
# buffer[2] = 0x80 | ((code >> 6) & 0x3F); /* 10xxxxxx */
# buffer[3] = 0x80 | (code & 0x3F); /* 10xxxxxx */
# return tos(buffer, 4);
# }
return ''
}
// Convert utf8 to utf32
fn (_rune string) utf32_code() int {
// println('utf 32 of $rune len=$rune.len')
if _rune.len == 0 {
return 0
}
// save ASC symbol as is
if _rune.len == 1 {
return int(_rune[0])
}
b := byte(int(_rune[0]))
// TODO should be
// res := int( rune[0] << rune.len)
# b <<= _rune.len;
res := int(b)
mut shift := 6 - _rune.len
for i := 1; i < _rune.len; i++ {
// println('c=$res')
c := int(_rune[i])
# res <<= shift;
# res |= c & 0x3f;
shift = 6
}
// println('!!!!!!!! utf32 $rune res = $res')
return res
}