summaryrefslogtreecommitdiffstats
path: root/src/port/chklocale.c
blob: 9e3c6db7856385442a427ce73767d73f1534453d (plain)
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
/*-------------------------------------------------------------------------
 *
 * chklocale.c
 *		Functions for handling locale-related info
 *
 *
 * Copyright (c) 1996-2020, PostgreSQL Global Development Group
 *
 *
 * IDENTIFICATION
 *	  src/port/chklocale.c
 *
 *-------------------------------------------------------------------------
 */

#ifndef FRONTEND
#include "postgres.h"
#else
#include "postgres_fe.h"
#endif

#ifdef HAVE_LANGINFO_H
#include <langinfo.h>
#endif

#include "mb/pg_wchar.h"


/*
 * This table needs to recognize all the CODESET spellings for supported
 * backend encodings, as well as frontend-only encodings where possible
 * (the latter case is currently only needed for initdb to recognize
 * error situations).  On Windows, we rely on entries for codepage
 * numbers (CPnnn).
 *
 * Note that we search the table with pg_strcasecmp(), so variant
 * capitalizations don't need their own entries.
 */
struct encoding_match
{
	enum pg_enc pg_enc_code;
	const char *system_enc_name;
};

static const struct encoding_match encoding_match_list[] = {
	{PG_EUC_JP, "EUC-JP"},
	{PG_EUC_JP, "eucJP"},
	{PG_EUC_JP, "IBM-eucJP"},
	{PG_EUC_JP, "sdeckanji"},
	{PG_EUC_JP, "CP20932"},

	{PG_EUC_CN, "EUC-CN"},
	{PG_EUC_CN, "eucCN"},
	{PG_EUC_CN, "IBM-eucCN"},
	{PG_EUC_CN, "GB2312"},
	{PG_EUC_CN, "dechanzi"},
	{PG_EUC_CN, "CP20936"},

	{PG_EUC_KR, "EUC-KR"},
	{PG_EUC_KR, "eucKR"},
	{PG_EUC_KR, "IBM-eucKR"},
	{PG_EUC_KR, "deckorean"},
	{PG_EUC_KR, "5601"},
	{PG_EUC_KR, "CP51949"},

	{PG_EUC_TW, "EUC-TW"},
	{PG_EUC_TW, "eucTW"},
	{PG_EUC_TW, "IBM-eucTW"},
	{PG_EUC_TW, "cns11643"},
	/* No codepage for EUC-TW ? */

	{PG_UTF8, "UTF-8"},
	{PG_UTF8, "utf8"},
	{PG_UTF8, "CP65001"},

	{PG_LATIN1, "ISO-8859-1"},
	{PG_LATIN1, "ISO8859-1"},
	{PG_LATIN1, "iso88591"},
	{PG_LATIN1, "CP28591"},

	{PG_LATIN2, "ISO-8859-2"},
	{PG_LATIN2, "ISO8859-2"},
	{PG_LATIN2, "iso88592"},
	{PG_LATIN2, "CP28592"},

	{PG_LATIN3, "ISO-8859-3"},
	{PG_LATIN3, "ISO8859-3"},
	{PG_LATIN3, "iso88593"},
	{PG_LATIN3, "CP28593"},

	{PG_LATIN4, "ISO-8859-4"},
	{PG_LATIN4, "ISO8859-4"},
	{PG_LATIN4, "iso88594"},
	{PG_LATIN4, "CP28594"},

	{PG_LATIN5, "ISO-8859-9"},
	{PG_LATIN5, "ISO8859-9"},
	{PG_LATIN5, "iso88599"},
	{PG_LATIN5, "CP28599"},

	{PG_LATIN6, "ISO-8859-10"},
	{PG_LATIN6, "ISO8859-10"},
	{PG_LATIN6, "iso885910"},

	{PG_LATIN7, "ISO-8859-13"},
	{PG_LATIN7, "ISO8859-13"},
	{PG_LATIN7, "iso885913"},

	{PG_LATIN8, "ISO-8859-14"},
	{PG_LATIN8, "ISO8859-14"},
	{PG_LATIN8, "iso885914"},

	{PG_LATIN9, "ISO-8859-15"},
	{PG_LATIN9, "ISO8859-15"},
	{PG_LATIN9, "iso885915"},
	{PG_LATIN9, "CP28605"},

	{PG_LATIN10, "ISO-8859-16"},
	{PG_LATIN10, "ISO8859-16"},
	{PG_LATIN10, "iso885916"},

	{PG_KOI8R, "KOI8-R"},
	{PG_KOI8R, "CP20866"},

	{PG_KOI8U, "KOI8-U"},
	{PG_KOI8U, "CP21866"},

	{PG_WIN866, "CP866"},
	{PG_WIN874, "CP874"},
	{PG_WIN1250, "CP1250"},
	{PG_WIN1251, "CP1251"},
	{PG_WIN1251, "ansi-1251"},
	{PG_WIN1252, "CP1252"},
	{PG_WIN1253, "CP1253"},
	{PG_WIN1254, "CP1254"},
	{PG_WIN1255, "CP1255"},
	{PG_WIN1256, "CP1256"},
	{PG_WIN1257, "CP1257"},
	{PG_WIN1258, "CP1258"},

	{PG_ISO_8859_5, "ISO-8859-5"},
	{PG_ISO_8859_5, "ISO8859-5"},
	{PG_ISO_8859_5, "iso88595"},
	{PG_ISO_8859_5, "CP28595"},

	{PG_ISO_8859_6, "ISO-8859-6"},
	{PG_ISO_8859_6, "ISO8859-6"},
	{PG_ISO_8859_6, "iso88596"},
	{PG_ISO_8859_6, "CP28596"},

	{PG_ISO_8859_7, "ISO-8859-7"},
	{PG_ISO_8859_7, "ISO8859-7"},
	{PG_ISO_8859_7, "iso88597"},
	{PG_ISO_8859_7, "CP28597"},

	{PG_ISO_8859_8, "ISO-8859-8"},
	{PG_ISO_8859_8, "ISO8859-8"},
	{PG_ISO_8859_8, "iso88598"},
	{PG_ISO_8859_8, "CP28598"},

	{PG_SJIS, "SJIS"},
	{PG_SJIS, "PCK"},
	{PG_SJIS, "CP932"},
	{PG_SJIS, "SHIFT_JIS"},

	{PG_BIG5, "BIG5"},
	{PG_BIG5, "BIG5HKSCS"},
	{PG_BIG5, "Big5-HKSCS"},
	{PG_BIG5, "CP950"},

	{PG_GBK, "GBK"},
	{PG_GBK, "CP936"},

	{PG_UHC, "UHC"},
	{PG_UHC, "CP949"},

	{PG_JOHAB, "JOHAB"},
	{PG_JOHAB, "CP1361"},

	{PG_GB18030, "GB18030"},
	{PG_GB18030, "CP54936"},

	{PG_SHIFT_JIS_2004, "SJIS_2004"},

	{PG_SQL_ASCII, "US-ASCII"},

	{PG_SQL_ASCII, NULL}		/* end marker */
};

#ifdef WIN32
/*
 * On Windows, use CP<code page number> instead of the nl_langinfo() result
 *
 * Visual Studio 2012 expanded the set of valid LC_CTYPE values, so have its
 * locale machinery determine the code page.  See comments at IsoLocaleName().
 * For other compilers, follow the locale's predictable format.
 *
 * Visual Studio 2015 should still be able to do the same, but the declaration
 * of lc_codepage is missing in _locale_t, causing this code compilation to
 * fail, hence this falls back instead on GetLocaleInfoEx. VS 2015 may be an
 * exception and post-VS2015 versions should be able to handle properly the
 * codepage number using _create_locale(). So, instead of the same logic as
 * VS 2012 and VS 2013, this routine uses GetLocaleInfoEx to parse short
 * locale names like "de-DE", "fr-FR", etc. If those cannot be parsed correctly
 * process falls back to the pre-VS-2010 manual parsing done with
 * using <Language>_<Country>.<CodePage> as a base.
 *
 * Returns a malloc()'d string for the caller to free.
 */
static char *
win32_langinfo(const char *ctype)
{
	char	   *r = NULL;

#if defined(_MSC_VER) && (_MSC_VER < 1900)
	_locale_t	loct = NULL;

	loct = _create_locale(LC_CTYPE, ctype);
	if (loct != NULL)
	{
		r = malloc(16);			/* excess */
		if (r != NULL)
			sprintf(r, "CP%u", loct->locinfo->lc_codepage);
		_free_locale(loct);
	}
#else
	char	   *codepage;

#if defined(_MSC_VER) && (_MSC_VER >= 1900)
	uint32		cp;
	WCHAR		wctype[LOCALE_NAME_MAX_LENGTH];

	memset(wctype, 0, sizeof(wctype));
	MultiByteToWideChar(CP_ACP, 0, ctype, -1, wctype, LOCALE_NAME_MAX_LENGTH);

	if (GetLocaleInfoEx(wctype,
						LOCALE_IDEFAULTANSICODEPAGE | LOCALE_RETURN_NUMBER,
						(LPWSTR) &cp, sizeof(cp) / sizeof(WCHAR)) > 0)
	{
		r = malloc(16);			/* excess */
		if (r != NULL)
		{
			/*
			 * If the return value is CP_ACP that means no ANSI code page is
			 * available, so only Unicode can be used for the locale.
			 */
			if (cp == CP_ACP)
				strcpy(r, "utf8");
			else
				sprintf(r, "CP%u", cp);
		}
	}
	else
#endif
	{
		/*
		 * Locale format on Win32 is <Language>_<Country>.<CodePage>.  For
		 * example, English_United States.1252.  If we see digits after the
		 * last dot, assume it's a codepage number.  Otherwise, we might be
		 * dealing with a Unix-style locale string; Windows' setlocale() will
		 * take those even though GetLocaleInfoEx() won't, so we end up here.
		 * In that case, just return what's after the last dot and hope we can
		 * find it in our table.
		 */
		codepage = strrchr(ctype, '.');
		if (codepage != NULL)
		{
			size_t		ln;

			codepage++;
			ln = strlen(codepage);
			r = malloc(ln + 3);
			if (r != NULL)
			{
				if (strspn(codepage, "0123456789") == ln)
					sprintf(r, "CP%s", codepage);
				else
					strcpy(r, codepage);
			}
		}

	}
#endif

	return r;
}

#ifndef FRONTEND
/*
 * Given a Windows code page identifier, find the corresponding PostgreSQL
 * encoding.  Issue a warning and return -1 if none found.
 */
int
pg_codepage_to_encoding(UINT cp)
{
	char		sys[16];
	int			i;

	sprintf(sys, "CP%u", cp);

	/* Check the table */
	for (i = 0; encoding_match_list[i].system_enc_name; i++)
		if (pg_strcasecmp(sys, encoding_match_list[i].system_enc_name) == 0)
			return encoding_match_list[i].pg_enc_code;

	ereport(WARNING,
			(errmsg("could not determine encoding for codeset \"%s\"", sys)));

	return -1;
}
#endif
#endif							/* WIN32 */

#if (defined(HAVE_LANGINFO_H) && defined(CODESET)) || defined(WIN32)

/*
 * Given a setting for LC_CTYPE, return the Postgres ID of the associated
 * encoding, if we can determine it.  Return -1 if we can't determine it.
 *
 * Pass in NULL to get the encoding for the current locale setting.
 * Pass "" to get the encoding selected by the server's environment.
 *
 * If the result is PG_SQL_ASCII, callers should treat it as being compatible
 * with any desired encoding.
 *
 * If running in the backend and write_message is false, this function must
 * cope with the possibility that elog() and palloc() are not yet usable.
 */
int
pg_get_encoding_from_locale(const char *ctype, bool write_message)
{
	char	   *sys;
	int			i;

	/* Get the CODESET property, and also LC_CTYPE if not passed in */
	if (ctype)
	{
		char	   *save;
		char	   *name;

		/* If locale is C or POSIX, we can allow all encodings */
		if (pg_strcasecmp(ctype, "C") == 0 ||
			pg_strcasecmp(ctype, "POSIX") == 0)
			return PG_SQL_ASCII;

		save = setlocale(LC_CTYPE, NULL);
		if (!save)
			return -1;			/* setlocale() broken? */
		/* must copy result, or it might change after setlocale */
		save = strdup(save);
		if (!save)
			return -1;			/* out of memory; unlikely */

		name = setlocale(LC_CTYPE, ctype);
		if (!name)
		{
			free(save);
			return -1;			/* bogus ctype passed in? */
		}

#ifndef WIN32
		sys = nl_langinfo(CODESET);
		if (sys)
			sys = strdup(sys);
#else
		sys = win32_langinfo(name);
#endif

		setlocale(LC_CTYPE, save);
		free(save);
	}
	else
	{
		/* much easier... */
		ctype = setlocale(LC_CTYPE, NULL);
		if (!ctype)
			return -1;			/* setlocale() broken? */

		/* If locale is C or POSIX, we can allow all encodings */
		if (pg_strcasecmp(ctype, "C") == 0 ||
			pg_strcasecmp(ctype, "POSIX") == 0)
			return PG_SQL_ASCII;

#ifndef WIN32
		sys = nl_langinfo(CODESET);
		if (sys)
			sys = strdup(sys);
#else
		sys = win32_langinfo(ctype);
#endif
	}

	if (!sys)
		return -1;				/* out of memory; unlikely */

	/* Check the table */
	for (i = 0; encoding_match_list[i].system_enc_name; i++)
	{
		if (pg_strcasecmp(sys, encoding_match_list[i].system_enc_name) == 0)
		{
			free(sys);
			return encoding_match_list[i].pg_enc_code;
		}
	}

	/* Special-case kluges for particular platforms go here */

#ifdef __darwin__

	/*
	 * Current macOS has many locales that report an empty string for CODESET,
	 * but they all seem to actually use UTF-8.
	 */
	if (strlen(sys) == 0)
	{
		free(sys);
		return PG_UTF8;
	}
#endif

	/*
	 * We print a warning if we got a CODESET string but couldn't recognize
	 * it.  This means we need another entry in the table.
	 */
	if (write_message)
	{
#ifdef FRONTEND
		fprintf(stderr, _("could not determine encoding for locale \"%s\": codeset is \"%s\""),
				ctype, sys);
		/* keep newline separate so there's only one translatable string */
		fputc('\n', stderr);
#else
		ereport(WARNING,
				(errmsg("could not determine encoding for locale \"%s\": codeset is \"%s\"",
						ctype, sys)));
#endif
	}

	free(sys);
	return -1;
}
#else							/* (HAVE_LANGINFO_H && CODESET) || WIN32 */

/*
 * stub if no multi-language platform support
 *
 * Note: we could return -1 here, but that would have the effect of
 * forcing users to specify an encoding to initdb on such platforms.
 * It seems better to silently default to SQL_ASCII.
 */
int
pg_get_encoding_from_locale(const char *ctype, bool write_message)
{
	return PG_SQL_ASCII;
}

#endif							/* (HAVE_LANGINFO_H && CODESET) || WIN32 */