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
|
/*-------------------------------------------------------------------------
*
* Utility functions for conversion procs.
*
* Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* src/backend/utils/mb/conv.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "mb/pg_wchar.h"
/*
* local2local: a generic single byte charset encoding
* conversion between two ASCII-superset encodings.
*
* l points to the source string of length len
* p is the output area (must be large enough!)
* src_encoding is the PG identifier for the source encoding
* dest_encoding is the PG identifier for the target encoding
* tab holds conversion entries for the source charset
* starting from 128 (0x80). each entry in the table holds the corresponding
* code point for the target charset, or 0 if there is no equivalent code.
*/
void
local2local(const unsigned char *l,
unsigned char *p,
int len,
int src_encoding,
int dest_encoding,
const unsigned char *tab)
{
unsigned char c1,
c2;
while (len > 0)
{
c1 = *l;
if (c1 == 0)
report_invalid_encoding(src_encoding, (const char *) l, len);
if (!IS_HIGHBIT_SET(c1))
*p++ = c1;
else
{
c2 = tab[c1 - HIGHBIT];
if (c2)
*p++ = c2;
else
report_untranslatable_char(src_encoding, dest_encoding,
(const char *) l, len);
}
l++;
len--;
}
*p = '\0';
}
/*
* LATINn ---> MIC when the charset's local codes map directly to MIC
*
* l points to the source string of length len
* p is the output area (must be large enough!)
* lc is the mule character set id for the local encoding
* encoding is the PG identifier for the local encoding
*/
void
latin2mic(const unsigned char *l, unsigned char *p, int len,
int lc, int encoding)
{
int c1;
while (len > 0)
{
c1 = *l;
if (c1 == 0)
report_invalid_encoding(encoding, (const char *) l, len);
if (IS_HIGHBIT_SET(c1))
*p++ = lc;
*p++ = c1;
l++;
len--;
}
*p = '\0';
}
/*
* MIC ---> LATINn when the charset's local codes map directly to MIC
*
* mic points to the source string of length len
* p is the output area (must be large enough!)
* lc is the mule character set id for the local encoding
* encoding is the PG identifier for the local encoding
*/
void
mic2latin(const unsigned char *mic, unsigned char *p, int len,
int lc, int encoding)
{
int c1;
while (len > 0)
{
c1 = *mic;
if (c1 == 0)
report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len);
if (!IS_HIGHBIT_SET(c1))
{
/* easy for ASCII */
*p++ = c1;
mic++;
len--;
}
else
{
int l = pg_mule_mblen(mic);
if (len < l)
report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic,
len);
if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]))
report_untranslatable_char(PG_MULE_INTERNAL, encoding,
(const char *) mic, len);
*p++ = mic[1];
mic += 2;
len -= 2;
}
}
*p = '\0';
}
/*
* latin2mic_with_table: a generic single byte charset encoding
* conversion from a local charset to the mule internal code.
*
* l points to the source string of length len
* p is the output area (must be large enough!)
* lc is the mule character set id for the local encoding
* encoding is the PG identifier for the local encoding
* tab holds conversion entries for the local charset
* starting from 128 (0x80). each entry in the table holds the corresponding
* code point for the mule encoding, or 0 if there is no equivalent code.
*/
void
latin2mic_with_table(const unsigned char *l,
unsigned char *p,
int len,
int lc,
int encoding,
const unsigned char *tab)
{
unsigned char c1,
c2;
while (len > 0)
{
c1 = *l;
if (c1 == 0)
report_invalid_encoding(encoding, (const char *) l, len);
if (!IS_HIGHBIT_SET(c1))
*p++ = c1;
else
{
c2 = tab[c1 - HIGHBIT];
if (c2)
{
*p++ = lc;
*p++ = c2;
}
else
report_untranslatable_char(encoding, PG_MULE_INTERNAL,
(const char *) l, len);
}
l++;
len--;
}
*p = '\0';
}
/*
* mic2latin_with_table: a generic single byte charset encoding
* conversion from the mule internal code to a local charset.
*
* mic points to the source string of length len
* p is the output area (must be large enough!)
* lc is the mule character set id for the local encoding
* encoding is the PG identifier for the local encoding
* tab holds conversion entries for the mule internal code's second byte,
* starting from 128 (0x80). each entry in the table holds the corresponding
* code point for the local charset, or 0 if there is no equivalent code.
*/
void
mic2latin_with_table(const unsigned char *mic,
unsigned char *p,
int len,
int lc,
int encoding,
const unsigned char *tab)
{
unsigned char c1,
c2;
while (len > 0)
{
c1 = *mic;
if (c1 == 0)
report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len);
if (!IS_HIGHBIT_SET(c1))
{
/* easy for ASCII */
*p++ = c1;
mic++;
len--;
}
else
{
int l = pg_mule_mblen(mic);
if (len < l)
report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic,
len);
if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) ||
(c2 = tab[mic[1] - HIGHBIT]) == 0)
{
report_untranslatable_char(PG_MULE_INTERNAL, encoding,
(const char *) mic, len);
break; /* keep compiler quiet */
}
*p++ = c2;
mic += 2;
len -= 2;
}
}
*p = '\0';
}
/*
* comparison routine for bsearch()
* this routine is intended for combined UTF8 -> local code
*/
static int
compare3(const void *p1, const void *p2)
{
uint32 s1,
s2,
d1,
d2;
s1 = *(const uint32 *) p1;
s2 = *((const uint32 *) p1 + 1);
d1 = ((const pg_utf_to_local_combined *) p2)->utf1;
d2 = ((const pg_utf_to_local_combined *) p2)->utf2;
return (s1 > d1 || (s1 == d1 && s2 > d2)) ? 1 : ((s1 == d1 && s2 == d2) ? 0 : -1);
}
/*
* comparison routine for bsearch()
* this routine is intended for local code -> combined UTF8
*/
static int
compare4(const void *p1, const void *p2)
{
uint32 v1,
v2;
v1 = *(const uint32 *) p1;
v2 = ((const pg_local_to_utf_combined *) p2)->code;
return (v1 > v2) ? 1 : ((v1 == v2) ? 0 : -1);
}
/*
* store 32bit character representation into multibyte stream
*/
static inline unsigned char *
store_coded_char(unsigned char *dest, uint32 code)
{
if (code & 0xff000000)
*dest++ = code >> 24;
if (code & 0x00ff0000)
*dest++ = code >> 16;
if (code & 0x0000ff00)
*dest++ = code >> 8;
if (code & 0x000000ff)
*dest++ = code;
return dest;
}
/*
* Convert a character using a conversion radix tree.
*
* 'l' is the length of the input character in bytes, and b1-b4 are
* the input character's bytes.
*/
static inline uint32
pg_mb_radix_conv(const pg_mb_radix_tree *rt,
int l,
unsigned char b1,
unsigned char b2,
unsigned char b3,
unsigned char b4)
{
if (l == 4)
{
/* 4-byte code */
/* check code validity */
if (b1 < rt->b4_1_lower || b1 > rt->b4_1_upper ||
b2 < rt->b4_2_lower || b2 > rt->b4_2_upper ||
b3 < rt->b4_3_lower || b3 > rt->b4_3_upper ||
b4 < rt->b4_4_lower || b4 > rt->b4_4_upper)
return 0;
/* perform lookup */
if (rt->chars32)
{
uint32 idx = rt->b4root;
idx = rt->chars32[b1 + idx - rt->b4_1_lower];
idx = rt->chars32[b2 + idx - rt->b4_2_lower];
idx = rt->chars32[b3 + idx - rt->b4_3_lower];
return rt->chars32[b4 + idx - rt->b4_4_lower];
}
else
{
uint16 idx = rt->b4root;
idx = rt->chars16[b1 + idx - rt->b4_1_lower];
idx = rt->chars16[b2 + idx - rt->b4_2_lower];
idx = rt->chars16[b3 + idx - rt->b4_3_lower];
return rt->chars16[b4 + idx - rt->b4_4_lower];
}
}
else if (l == 3)
{
/* 3-byte code */
/* check code validity */
if (b2 < rt->b3_1_lower || b2 > rt->b3_1_upper ||
b3 < rt->b3_2_lower || b3 > rt->b3_2_upper ||
b4 < rt->b3_3_lower || b4 > rt->b3_3_upper)
return 0;
/* perform lookup */
if (rt->chars32)
{
uint32 idx = rt->b3root;
idx = rt->chars32[b2 + idx - rt->b3_1_lower];
idx = rt->chars32[b3 + idx - rt->b3_2_lower];
return rt->chars32[b4 + idx - rt->b3_3_lower];
}
else
{
uint16 idx = rt->b3root;
idx = rt->chars16[b2 + idx - rt->b3_1_lower];
idx = rt->chars16[b3 + idx - rt->b3_2_lower];
return rt->chars16[b4 + idx - rt->b3_3_lower];
}
}
else if (l == 2)
{
/* 2-byte code */
/* check code validity - first byte */
if (b3 < rt->b2_1_lower || b3 > rt->b2_1_upper ||
b4 < rt->b2_2_lower || b4 > rt->b2_2_upper)
return 0;
/* perform lookup */
if (rt->chars32)
{
uint32 idx = rt->b2root;
idx = rt->chars32[b3 + idx - rt->b2_1_lower];
return rt->chars32[b4 + idx - rt->b2_2_lower];
}
else
{
uint16 idx = rt->b2root;
idx = rt->chars16[b3 + idx - rt->b2_1_lower];
return rt->chars16[b4 + idx - rt->b2_2_lower];
}
}
else if (l == 1)
{
/* 1-byte code */
/* check code validity - first byte */
if (b4 < rt->b1_lower || b4 > rt->b1_upper)
return 0;
/* perform lookup */
if (rt->chars32)
return rt->chars32[b4 + rt->b1root - rt->b1_lower];
else
return rt->chars16[b4 + rt->b1root - rt->b1_lower];
}
return 0; /* shouldn't happen */
}
/*
* UTF8 ---> local code
*
* utf: input string in UTF8 encoding (need not be null-terminated)
* len: length of input string (in bytes)
* iso: pointer to the output area (must be large enough!)
(output string will be null-terminated)
* map: conversion map for single characters
* cmap: conversion map for combined characters
* (optional, pass NULL if none)
* cmapsize: number of entries in the conversion map for combined characters
* (optional, pass 0 if none)
* conv_func: algorithmic encoding conversion function
* (optional, pass NULL if none)
* encoding: PG identifier for the local encoding
*
* For each character, the cmap (if provided) is consulted first; if no match,
* the map is consulted next; if still no match, the conv_func (if provided)
* is applied. An error is raised if no match is found.
*
* See pg_wchar.h for more details about the data structures used here.
*/
void
UtfToLocal(const unsigned char *utf, int len,
unsigned char *iso,
const pg_mb_radix_tree *map,
const pg_utf_to_local_combined *cmap, int cmapsize,
utf_local_conversion_func conv_func,
int encoding)
{
uint32 iutf;
int l;
const pg_utf_to_local_combined *cp;
if (!PG_VALID_ENCODING(encoding))
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("invalid encoding number: %d", encoding)));
for (; len > 0; len -= l)
{
unsigned char b1 = 0;
unsigned char b2 = 0;
unsigned char b3 = 0;
unsigned char b4 = 0;
/* "break" cases all represent errors */
if (*utf == '\0')
break;
l = pg_utf_mblen(utf);
if (len < l)
break;
if (!pg_utf8_islegal(utf, l))
break;
if (l == 1)
{
/* ASCII case is easy, assume it's one-to-one conversion */
*iso++ = *utf++;
continue;
}
/* collect coded char of length l */
if (l == 2)
{
b3 = *utf++;
b4 = *utf++;
}
else if (l == 3)
{
b2 = *utf++;
b3 = *utf++;
b4 = *utf++;
}
else if (l == 4)
{
b1 = *utf++;
b2 = *utf++;
b3 = *utf++;
b4 = *utf++;
}
else
{
elog(ERROR, "unsupported character length %d", l);
iutf = 0; /* keep compiler quiet */
}
iutf = (b1 << 24 | b2 << 16 | b3 << 8 | b4);
/* First, try with combined map if possible */
if (cmap && len > l)
{
const unsigned char *utf_save = utf;
int len_save = len;
int l_save = l;
/* collect next character, same as above */
len -= l;
l = pg_utf_mblen(utf);
if (len < l)
break;
if (!pg_utf8_islegal(utf, l))
break;
/* We assume ASCII character cannot be in combined map */
if (l > 1)
{
uint32 iutf2;
uint32 cutf[2];
if (l == 2)
{
iutf2 = *utf++ << 8;
iutf2 |= *utf++;
}
else if (l == 3)
{
iutf2 = *utf++ << 16;
iutf2 |= *utf++ << 8;
iutf2 |= *utf++;
}
else if (l == 4)
{
iutf2 = *utf++ << 24;
iutf2 |= *utf++ << 16;
iutf2 |= *utf++ << 8;
iutf2 |= *utf++;
}
else
{
elog(ERROR, "unsupported character length %d", l);
iutf2 = 0; /* keep compiler quiet */
}
cutf[0] = iutf;
cutf[1] = iutf2;
cp = bsearch(cutf, cmap, cmapsize,
sizeof(pg_utf_to_local_combined), compare3);
if (cp)
{
iso = store_coded_char(iso, cp->code);
continue;
}
}
/* fail, so back up to reprocess second character next time */
utf = utf_save;
len = len_save;
l = l_save;
}
/* Now check ordinary map */
if (map)
{
uint32 converted = pg_mb_radix_conv(map, l, b1, b2, b3, b4);
if (converted)
{
iso = store_coded_char(iso, converted);
continue;
}
}
/* if there's a conversion function, try that */
if (conv_func)
{
uint32 converted = (*conv_func) (iutf);
if (converted)
{
iso = store_coded_char(iso, converted);
continue;
}
}
/* failed to translate this character */
report_untranslatable_char(PG_UTF8, encoding,
(const char *) (utf - l), len);
}
/* if we broke out of loop early, must be invalid input */
if (len > 0)
report_invalid_encoding(PG_UTF8, (const char *) utf, len);
*iso = '\0';
}
/*
* local code ---> UTF8
*
* iso: input string in local encoding (need not be null-terminated)
* len: length of input string (in bytes)
* utf: pointer to the output area (must be large enough!)
(output string will be null-terminated)
* map: conversion map for single characters
* cmap: conversion map for combined characters
* (optional, pass NULL if none)
* cmapsize: number of entries in the conversion map for combined characters
* (optional, pass 0 if none)
* conv_func: algorithmic encoding conversion function
* (optional, pass NULL if none)
* encoding: PG identifier for the local encoding
*
* For each character, the map is consulted first; if no match, the cmap
* (if provided) is consulted next; if still no match, the conv_func
* (if provided) is applied. An error is raised if no match is found.
*
* See pg_wchar.h for more details about the data structures used here.
*/
void
LocalToUtf(const unsigned char *iso, int len,
unsigned char *utf,
const pg_mb_radix_tree *map,
const pg_local_to_utf_combined *cmap, int cmapsize,
utf_local_conversion_func conv_func,
int encoding)
{
uint32 iiso;
int l;
const pg_local_to_utf_combined *cp;
if (!PG_VALID_ENCODING(encoding))
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("invalid encoding number: %d", encoding)));
for (; len > 0; len -= l)
{
unsigned char b1 = 0;
unsigned char b2 = 0;
unsigned char b3 = 0;
unsigned char b4 = 0;
/* "break" cases all represent errors */
if (*iso == '\0')
break;
if (!IS_HIGHBIT_SET(*iso))
{
/* ASCII case is easy, assume it's one-to-one conversion */
*utf++ = *iso++;
l = 1;
continue;
}
l = pg_encoding_verifymbchar(encoding, (const char *) iso, len);
if (l < 0)
break;
/* collect coded char of length l */
if (l == 1)
b4 = *iso++;
else if (l == 2)
{
b3 = *iso++;
b4 = *iso++;
}
else if (l == 3)
{
b2 = *iso++;
b3 = *iso++;
b4 = *iso++;
}
else if (l == 4)
{
b1 = *iso++;
b2 = *iso++;
b3 = *iso++;
b4 = *iso++;
}
else
{
elog(ERROR, "unsupported character length %d", l);
iiso = 0; /* keep compiler quiet */
}
iiso = (b1 << 24 | b2 << 16 | b3 << 8 | b4);
if (map)
{
uint32 converted = pg_mb_radix_conv(map, l, b1, b2, b3, b4);
if (converted)
{
utf = store_coded_char(utf, converted);
continue;
}
/* If there's a combined character map, try that */
if (cmap)
{
cp = bsearch(&iiso, cmap, cmapsize,
sizeof(pg_local_to_utf_combined), compare4);
if (cp)
{
utf = store_coded_char(utf, cp->utf1);
utf = store_coded_char(utf, cp->utf2);
continue;
}
}
}
/* if there's a conversion function, try that */
if (conv_func)
{
uint32 converted = (*conv_func) (iiso);
if (converted)
{
utf = store_coded_char(utf, converted);
continue;
}
}
/* failed to translate this character */
report_untranslatable_char(encoding, PG_UTF8,
(const char *) (iso - l), len);
}
/* if we broke out of loop early, must be invalid input */
if (len > 0)
report_invalid_encoding(encoding, (const char *) iso, len);
*utf = '\0';
}
|