forked from nodejs/node
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathstring_bytes.cc
More file actions
927 lines (760 loc) · 25.8 KB
/
string_bytes.cc
File metadata and controls
927 lines (760 loc) · 25.8 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
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
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
#include "string_bytes.h"
#include "node.h"
#include "node_buffer.h"
#include "v8.h"
#include <limits.h>
#include <string.h> // memcpy
#include <vector>
// When creating strings >= this length v8's gc spins up and consumes
// most of the execution time. For these cases it's more performant to
// use external string resources.
#define EXTERN_APEX 0xFBEE9
namespace node {
using v8::EscapableHandleScope;
using v8::HandleScope;
using v8::Isolate;
using v8::Local;
using v8::Object;
using v8::String;
using v8::Value;
using v8::MaybeLocal;
template <typename ResourceType, typename TypeName>
class ExternString: public ResourceType {
public:
~ExternString() override {
free(const_cast<TypeName*>(data_));
isolate()->AdjustAmountOfExternalAllocatedMemory(-byte_length());
}
const TypeName* data() const override {
return data_;
}
size_t length() const override {
return length_;
}
int64_t byte_length() const {
return length() * sizeof(*data());
}
static Local<String> NewFromCopy(Isolate* isolate,
const TypeName* data,
size_t length) {
EscapableHandleScope scope(isolate);
if (length == 0)
return scope.Escape(String::Empty(isolate));
TypeName* new_data =
static_cast<TypeName*>(malloc(length * sizeof(*new_data)));
if (new_data == nullptr) {
return Local<String>();
}
memcpy(new_data, data, length * sizeof(*new_data));
return scope.Escape(ExternString<ResourceType, TypeName>::New(isolate,
new_data,
length));
}
// uses "data" for external resource, and will be free'd on gc
static Local<String> New(Isolate* isolate,
const TypeName* data,
size_t length) {
EscapableHandleScope scope(isolate);
if (length == 0)
return scope.Escape(String::Empty(isolate));
ExternString* h_str = new ExternString<ResourceType, TypeName>(isolate,
data,
length);
MaybeLocal<String> str = NewExternal(isolate, h_str);
isolate->AdjustAmountOfExternalAllocatedMemory(h_str->byte_length());
if (str.IsEmpty()) {
delete h_str;
return Local<String>();
}
return scope.Escape(str.ToLocalChecked());
}
inline Isolate* isolate() const { return isolate_; }
private:
ExternString(Isolate* isolate, const TypeName* data, size_t length)
: isolate_(isolate), data_(data), length_(length) { }
static MaybeLocal<String> NewExternal(Isolate* isolate,
ExternString* h_str);
Isolate* isolate_;
const TypeName* data_;
size_t length_;
};
typedef ExternString<String::ExternalOneByteStringResource,
char> ExternOneByteString;
typedef ExternString<String::ExternalStringResource,
uint16_t> ExternTwoByteString;
template <>
MaybeLocal<String> ExternOneByteString::NewExternal(
Isolate* isolate, ExternOneByteString* h_str) {
return String::NewExternalOneByte(isolate, h_str);
}
template <>
MaybeLocal<String> ExternTwoByteString::NewExternal(
Isolate* isolate, ExternTwoByteString* h_str) {
return String::NewExternalTwoByte(isolate, h_str);
}
//// Base 64 ////
#define base64_encoded_size(size) ((size + 2 - ((size + 2) % 3)) / 3 * 4)
// Doesn't check for padding at the end. Can be 1-2 bytes over.
static inline size_t base64_decoded_size_fast(size_t size) {
size_t remainder = size % 4;
size = (size / 4) * 3;
if (remainder) {
if (size == 0 && remainder == 1) {
// special case: 1-byte input cannot be decoded
size = 0;
} else {
// non-padded input, add 1 or 2 extra bytes
size += 1 + (remainder == 3);
}
}
return size;
}
template <typename TypeName>
size_t base64_decoded_size(const TypeName* src, size_t size) {
if (size == 0)
return 0;
if (src[size - 1] == '=')
size--;
if (size > 0 && src[size - 1] == '=')
size--;
return base64_decoded_size_fast(size);
}
// supports regular and URL-safe base64
static const int8_t unbase64_table[] =
{ -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -2, -1, -1, -2, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-2, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 62, -1, 62, -1, 63,
52, 53, 54, 55, 56, 57, 58, 59, 60, 61, -1, -1, -1, -1, -1, -1,
-1, 0, 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, -1, -1, -1, -1, 63,
-1, 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, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
};
#define unbase64(x) \
static_cast<uint8_t>(unbase64_table[static_cast<uint8_t>(x)])
template <typename TypeName>
size_t base64_decode_slow(char* dst, size_t dstlen,
const TypeName* src, size_t srclen) {
uint8_t hi;
uint8_t lo;
size_t i = 0;
size_t k = 0;
for (;;) {
#define V(expr) \
while (i < srclen) { \
const uint8_t c = src[i]; \
lo = unbase64(c); \
i += 1; \
if (lo < 64) \
break; /* Legal character. */ \
if (c == '=') \
return k; \
} \
expr; \
if (i >= srclen) \
return k; \
if (k >= dstlen) \
return k; \
hi = lo;
V(/* Nothing. */);
V(dst[k++] = ((hi & 0x3F) << 2) | ((lo & 0x30) >> 4));
V(dst[k++] = ((hi & 0x0F) << 4) | ((lo & 0x3C) >> 2));
V(dst[k++] = ((hi & 0x03) << 6) | ((lo & 0x3F) >> 0));
#undef V
}
UNREACHABLE();
}
template <typename TypeName>
size_t base64_decode_fast(char* const dst, const size_t dstlen,
const TypeName* const src, const size_t srclen,
const size_t decoded_size) {
const size_t available = dstlen < decoded_size ? dstlen : decoded_size;
const size_t max_i = srclen / 4 * 4;
const size_t max_k = available / 3 * 3;
size_t i = 0;
size_t k = 0;
while (i < max_i && k < max_k) {
const uint32_t v =
unbase64(src[i + 0]) << 24 |
unbase64(src[i + 1]) << 16 |
unbase64(src[i + 2]) << 8 |
unbase64(src[i + 3]);
// If MSB is set, input contains whitespace or is not valid base64.
if (v & 0x80808080) {
break;
}
dst[k + 0] = ((v >> 22) & 0xFC) | ((v >> 20) & 0x03);
dst[k + 1] = ((v >> 12) & 0xF0) | ((v >> 10) & 0x0F);
dst[k + 2] = ((v >> 2) & 0xC0) | ((v >> 0) & 0x3F);
i += 4;
k += 3;
}
if (i < srclen && k < dstlen) {
return k + base64_decode_slow(dst + k, dstlen - k, src + i, srclen - i);
}
return k;
}
template <typename TypeName>
size_t base64_decode(char* const dst, const size_t dstlen,
const TypeName* const src, const size_t srclen) {
const size_t decoded_size = base64_decoded_size(src, srclen);
return base64_decode_fast(dst, dstlen, src, srclen, decoded_size);
}
template <typename TypeName>
unsigned hex2bin(TypeName c) {
if (c >= '0' && c <= '9')
return c - '0';
if (c >= 'A' && c <= 'F')
return 10 + (c - 'A');
if (c >= 'a' && c <= 'f')
return 10 + (c - 'a');
return static_cast<unsigned>(-1);
}
template <typename TypeName>
size_t hex_decode(char* buf,
size_t len,
const TypeName* src,
const size_t srcLen) {
size_t i;
for (i = 0; i < len && i * 2 + 1 < srcLen; ++i) {
unsigned a = hex2bin(src[i * 2 + 0]);
unsigned b = hex2bin(src[i * 2 + 1]);
if (!~a || !~b)
return i;
buf[i] = a * 16 + b;
}
return i;
}
bool StringBytes::GetExternalParts(Isolate* isolate,
Local<Value> val,
const char** data,
size_t* len) {
if (Buffer::HasInstance(val)) {
*data = Buffer::Data(val);
*len = Buffer::Length(val);
return true;
}
if (!val->IsString())
return false;
Local<String> str = val.As<String>();
if (str->IsExternalOneByte()) {
const String::ExternalOneByteStringResource* ext;
ext = str->GetExternalOneByteStringResource();
*data = ext->data();
*len = ext->length();
return true;
} else if (str->IsExternal()) {
const String::ExternalStringResource* ext;
ext = str->GetExternalStringResource();
*data = reinterpret_cast<const char*>(ext->data());
*len = ext->length() * sizeof(*ext->data());
return true;
}
return false;
}
size_t StringBytes::WriteUCS2(char* buf,
size_t buflen,
size_t nbytes,
const char* data,
Local<String> str,
int flags,
size_t* chars_written) {
uint16_t* const dst = reinterpret_cast<uint16_t*>(buf);
size_t max_chars = (buflen / sizeof(*dst));
size_t nchars;
size_t alignment = reinterpret_cast<uintptr_t>(dst) % sizeof(*dst);
if (alignment == 0) {
nchars = str->Write(dst, 0, max_chars, flags);
*chars_written = nchars;
return nchars * sizeof(*dst);
}
uint16_t* aligned_dst =
reinterpret_cast<uint16_t*>(buf + sizeof(*dst) - alignment);
ASSERT_EQ(reinterpret_cast<uintptr_t>(aligned_dst) % sizeof(*dst), 0);
// Write all but the last char
nchars = str->Write(aligned_dst, 0, max_chars - 1, flags);
// Shift everything to unaligned-left
memmove(dst, aligned_dst, nchars * sizeof(*dst));
// One more char to be written
uint16_t last;
if (nchars == max_chars - 1 && str->Write(&last, nchars, 1, flags) != 0) {
memcpy(buf + nchars * sizeof(*dst), &last, sizeof(last));
nchars++;
}
*chars_written = nchars;
return nchars * sizeof(*dst);
}
size_t StringBytes::Write(Isolate* isolate,
char* buf,
size_t buflen,
Local<Value> val,
enum encoding encoding,
int* chars_written) {
HandleScope scope(isolate);
const char* data = nullptr;
size_t nbytes = 0;
const bool is_extern = GetExternalParts(isolate, val, &data, &nbytes);
const size_t external_nbytes = nbytes;
CHECK(val->IsString() == true);
Local<String> str = val.As<String>();
if (nbytes > buflen)
nbytes = buflen;
int flags = String::HINT_MANY_WRITES_EXPECTED |
String::NO_NULL_TERMINATION |
String::REPLACE_INVALID_UTF8;
switch (encoding) {
case ASCII:
case BINARY:
if (is_extern && str->IsOneByte()) {
memcpy(buf, data, nbytes);
} else {
uint8_t* const dst = reinterpret_cast<uint8_t*>(buf);
nbytes = str->WriteOneByte(dst, 0, buflen, flags);
}
if (chars_written != nullptr)
*chars_written = nbytes;
break;
case BUFFER:
case UTF8:
nbytes = str->WriteUtf8(buf, buflen, chars_written, flags);
break;
case UCS2: {
size_t nchars;
if (is_extern && !str->IsOneByte()) {
memcpy(buf, data, nbytes);
nchars = nbytes / sizeof(uint16_t);
} else {
nbytes = WriteUCS2(buf, buflen, nbytes, data, str, flags, &nchars);
}
if (chars_written != nullptr)
*chars_written = nchars;
if (!IsBigEndian())
break;
// Node's "ucs2" encoding wants LE character data stored in
// the Buffer, so we need to reorder on BE platforms. See
// http://nodejs.org/api/buffer.html regarding Node's "ucs2"
// encoding specification
const bool is_aligned =
reinterpret_cast<uintptr_t>(buf) % sizeof(uint16_t);
if (is_aligned) {
uint16_t* const dst = reinterpret_cast<uint16_t*>(buf);
SwapBytes(dst, dst, nchars);
}
ASSERT_EQ(sizeof(uint16_t), 2);
for (size_t i = 0; i < nchars; i++) {
char tmp = buf[i * 2];
buf[i * 2] = buf[i * 2 + 1];
buf[i * 2 + 1] = tmp;
}
break;
}
case BASE64:
if (is_extern) {
nbytes = base64_decode(buf, buflen, data, external_nbytes);
} else {
String::Value value(str);
nbytes = base64_decode(buf, buflen, *value, value.length());
}
if (chars_written != nullptr) {
*chars_written = nbytes;
}
break;
case HEX:
if (is_extern) {
nbytes = hex_decode(buf, buflen, data, external_nbytes);
} else {
String::Value value(str);
nbytes = hex_decode(buf, buflen, *value, value.length());
}
if (chars_written != nullptr) {
*chars_written = nbytes;
}
break;
default:
CHECK(0 && "unknown encoding");
break;
}
return nbytes;
}
bool StringBytes::IsValidString(Isolate* isolate,
Local<String> string,
enum encoding enc) {
if (enc == HEX && string->Length() % 2 != 0)
return false;
// TODO(bnoordhuis) Add BASE64 check?
return true;
}
// Quick and dirty size calculation
// Will always be at least big enough, but may have some extra
// UTF8 can be as much as 3x the size, Base64 can have 1-2 extra bytes
size_t StringBytes::StorageSize(Isolate* isolate,
Local<Value> val,
enum encoding encoding) {
HandleScope scope(isolate);
size_t data_size = 0;
bool is_buffer = Buffer::HasInstance(val);
if (is_buffer && (encoding == BUFFER || encoding == BINARY)) {
return Buffer::Length(val);
}
Local<String> str = val->ToString(isolate);
switch (encoding) {
case BINARY:
case ASCII:
data_size = str->Length();
break;
case BUFFER:
case UTF8:
// A single UCS2 codepoint never takes up more than 3 utf8 bytes.
// It is an exercise for the caller to decide when a string is
// long enough to justify calling Size() instead of StorageSize()
data_size = 3 * str->Length();
break;
case UCS2:
data_size = str->Length() * sizeof(uint16_t);
break;
case BASE64:
data_size = base64_decoded_size_fast(str->Length());
break;
case HEX:
CHECK(str->Length() % 2 == 0 && "invalid hex string length");
data_size = str->Length() / 2;
break;
default:
CHECK(0 && "unknown encoding");
break;
}
return data_size;
}
size_t StringBytes::Size(Isolate* isolate,
Local<Value> val,
enum encoding encoding) {
HandleScope scope(isolate);
size_t data_size = 0;
bool is_buffer = Buffer::HasInstance(val);
if (is_buffer && (encoding == BUFFER || encoding == BINARY))
return Buffer::Length(val);
const char* data;
if (GetExternalParts(isolate, val, &data, &data_size))
return data_size;
Local<String> str = val->ToString(isolate);
switch (encoding) {
case BINARY:
case ASCII:
data_size = str->Length();
break;
case BUFFER:
case UTF8:
data_size = str->Utf8Length();
break;
case UCS2:
data_size = str->Length() * sizeof(uint16_t);
break;
case BASE64: {
String::Value value(str);
data_size = base64_decoded_size(*value, value.length());
break;
}
case HEX:
data_size = str->Length() / 2;
break;
default:
CHECK(0 && "unknown encoding");
break;
}
return data_size;
}
static bool contains_non_ascii_slow(const char* buf, size_t len) {
for (size_t i = 0; i < len; ++i) {
if (buf[i] & 0x80)
return true;
}
return false;
}
static bool contains_non_ascii(const char* src, size_t len) {
if (len < 16) {
return contains_non_ascii_slow(src, len);
}
const unsigned bytes_per_word = sizeof(uintptr_t);
const unsigned align_mask = bytes_per_word - 1;
const unsigned unaligned = reinterpret_cast<uintptr_t>(src) & align_mask;
if (unaligned > 0) {
const unsigned n = bytes_per_word - unaligned;
if (contains_non_ascii_slow(src, n))
return true;
src += n;
len -= n;
}
#if defined(_WIN64) || defined(_LP64)
const uintptr_t mask = 0x8080808080808080ll;
#else
const uintptr_t mask = 0x80808080l;
#endif
const uintptr_t* srcw = reinterpret_cast<const uintptr_t*>(src);
for (size_t i = 0, n = len / bytes_per_word; i < n; ++i) {
if (srcw[i] & mask)
return true;
}
const unsigned remainder = len & align_mask;
if (remainder > 0) {
const size_t offset = len - remainder;
if (contains_non_ascii_slow(src + offset, remainder))
return true;
}
return false;
}
static void force_ascii_slow(const char* src, char* dst, size_t len) {
for (size_t i = 0; i < len; ++i) {
dst[i] = src[i] & 0x7f;
}
}
static void force_ascii(const char* src, char* dst, size_t len) {
if (len < 16) {
force_ascii_slow(src, dst, len);
return;
}
const unsigned bytes_per_word = sizeof(uintptr_t);
const unsigned align_mask = bytes_per_word - 1;
const unsigned src_unalign = reinterpret_cast<uintptr_t>(src) & align_mask;
const unsigned dst_unalign = reinterpret_cast<uintptr_t>(dst) & align_mask;
if (src_unalign > 0) {
if (src_unalign == dst_unalign) {
const unsigned unalign = bytes_per_word - src_unalign;
force_ascii_slow(src, dst, unalign);
src += unalign;
dst += unalign;
len -= src_unalign;
} else {
force_ascii_slow(src, dst, len);
return;
}
}
#if defined(_WIN64) || defined(_LP64)
const uintptr_t mask = ~0x8080808080808080ll;
#else
const uintptr_t mask = ~0x80808080l;
#endif
const uintptr_t* srcw = reinterpret_cast<const uintptr_t*>(src);
uintptr_t* dstw = reinterpret_cast<uintptr_t*>(dst);
for (size_t i = 0, n = len / bytes_per_word; i < n; ++i) {
dstw[i] = srcw[i] & mask;
}
const unsigned remainder = len & align_mask;
if (remainder > 0) {
const size_t offset = len - remainder;
force_ascii_slow(src + offset, dst + offset, remainder);
}
}
static size_t base64_encode(const char* src,
size_t slen,
char* dst,
size_t dlen) {
// We know how much we'll write, just make sure that there's space.
CHECK(dlen >= base64_encoded_size(slen) &&
"not enough space provided for base64 encode");
dlen = base64_encoded_size(slen);
unsigned a;
unsigned b;
unsigned c;
unsigned i;
unsigned k;
unsigned n;
static const char table[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
"abcdefghijklmnopqrstuvwxyz"
"0123456789+/";
i = 0;
k = 0;
n = slen / 3 * 3;
while (i < n) {
a = src[i + 0] & 0xff;
b = src[i + 1] & 0xff;
c = src[i + 2] & 0xff;
dst[k + 0] = table[a >> 2];
dst[k + 1] = table[((a & 3) << 4) | (b >> 4)];
dst[k + 2] = table[((b & 0x0f) << 2) | (c >> 6)];
dst[k + 3] = table[c & 0x3f];
i += 3;
k += 4;
}
if (n != slen) {
switch (slen - n) {
case 1:
a = src[i + 0] & 0xff;
dst[k + 0] = table[a >> 2];
dst[k + 1] = table[(a & 3) << 4];
dst[k + 2] = '=';
dst[k + 3] = '=';
break;
case 2:
a = src[i + 0] & 0xff;
b = src[i + 1] & 0xff;
dst[k + 0] = table[a >> 2];
dst[k + 1] = table[((a & 3) << 4) | (b >> 4)];
dst[k + 2] = table[(b & 0x0f) << 2];
dst[k + 3] = '=';
break;
}
}
return dlen;
}
static size_t hex_encode(const char* src, size_t slen, char* dst, size_t dlen) {
// We know how much we'll write, just make sure that there's space.
CHECK(dlen >= slen * 2 &&
"not enough space provided for hex encode");
dlen = slen * 2;
for (uint32_t i = 0, k = 0; k < dlen; i += 1, k += 2) {
static const char hex[] = "0123456789abcdef";
uint8_t val = static_cast<uint8_t>(src[i]);
dst[k + 0] = hex[val >> 4];
dst[k + 1] = hex[val & 15];
}
return dlen;
}
Local<Value> StringBytes::Encode(Isolate* isolate,
const char* buf,
size_t buflen,
enum encoding encoding) {
EscapableHandleScope scope(isolate);
CHECK_NE(encoding, UCS2);
CHECK_LE(buflen, Buffer::kMaxLength);
if (!buflen && encoding != BUFFER)
return scope.Escape(String::Empty(isolate));
Local<String> val;
switch (encoding) {
case BUFFER:
{
Local<Object> vbuf =
Buffer::Copy(isolate, buf, buflen).ToLocalChecked();
return scope.Escape(vbuf);
}
case ASCII:
if (contains_non_ascii(buf, buflen)) {
char* out = static_cast<char*>(malloc(buflen));
if (out == nullptr) {
return Local<String>();
}
force_ascii(buf, out, buflen);
if (buflen < EXTERN_APEX) {
val = OneByteString(isolate, out, buflen);
free(out);
} else {
val = ExternOneByteString::New(isolate, out, buflen);
}
} else {
if (buflen < EXTERN_APEX)
val = OneByteString(isolate, buf, buflen);
else
val = ExternOneByteString::NewFromCopy(isolate, buf, buflen);
}
break;
case UTF8:
val = String::NewFromUtf8(isolate,
buf,
String::kNormalString,
buflen);
break;
case BINARY:
if (buflen < EXTERN_APEX)
val = OneByteString(isolate, buf, buflen);
else
val = ExternOneByteString::NewFromCopy(isolate, buf, buflen);
break;
case BASE64: {
size_t dlen = base64_encoded_size(buflen);
char* dst = static_cast<char*>(malloc(dlen));
if (dst == nullptr) {
return Local<String>();
}
size_t written = base64_encode(buf, buflen, dst, dlen);
CHECK_EQ(written, dlen);
if (dlen < EXTERN_APEX) {
val = OneByteString(isolate, dst, dlen);
free(dst);
} else {
val = ExternOneByteString::New(isolate, dst, dlen);
}
break;
}
case HEX: {
size_t dlen = buflen * 2;
char* dst = static_cast<char*>(malloc(dlen));
if (dst == nullptr) {
return Local<String>();
}
size_t written = hex_encode(buf, buflen, dst, dlen);
CHECK_EQ(written, dlen);
if (dlen < EXTERN_APEX) {
val = OneByteString(isolate, dst, dlen);
free(dst);
} else {
val = ExternOneByteString::New(isolate, dst, dlen);
}
break;
}
default:
CHECK(0 && "unknown encoding");
break;
}
return scope.Escape(val);
}
Local<Value> StringBytes::Encode(Isolate* isolate,
const uint16_t* buf,
size_t buflen) {
Local<String> val;
std::vector<uint16_t> dst;
if (IsBigEndian()) {
// Node's "ucs2" encoding expects LE character data inside a
// Buffer, so we need to reorder on BE platforms. See
// http://nodejs.org/api/buffer.html regarding Node's "ucs2"
// encoding specification
dst.resize(buflen);
SwapBytes(&dst[0], buf, buflen);
buf = &dst[0];
}
if (buflen < EXTERN_APEX) {
val = String::NewFromTwoByte(isolate,
buf,
String::kNormalString,
buflen);
} else {
val = ExternTwoByteString::NewFromCopy(isolate, buf, buflen);
}
return val;
}
Local<Value> StringBytes::Encode(Isolate* isolate,
const char* buf,
enum encoding encoding) {
const size_t len = strlen(buf);
Local<Value> ret;
if (encoding == UCS2) {
// In Node, UCS2 means utf16le. The data must be in little-endian
// order and must be aligned on 2-bytes. This returns an empty
// value if it's not aligned and ensures the appropriate byte order
// on big endian architectures.
const bool be = IsBigEndian();
if (len % 2 != 0)
return ret;
std::vector<uint16_t> vec(len / 2);
for (size_t i = 0, k = 0; i < len; i += 2, k += 1) {
const uint8_t hi = static_cast<uint8_t>(buf[i + 0]);
const uint8_t lo = static_cast<uint8_t>(buf[i + 1]);
vec[k] = be ?
static_cast<uint16_t>(hi) << 8 | lo
: static_cast<uint16_t>(lo) << 8 | hi;
}
ret = vec.empty() ?
static_cast< Local<Value> >(String::Empty(isolate))
: StringBytes::Encode(isolate, &vec[0], vec.size());
} else {
ret = StringBytes::Encode(isolate, buf, len, encoding);
}
return ret;
}
} // namespace node