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
/*--------------------------------------------------------------------
* Symbols referenced in this file:
* - pg_enc2name_tbl
*--------------------------------------------------------------------
*/
/*-------------------------------------------------------------------------
*
* encnames.c
* Encoding names and routines for working with them.
*
* Portions Copyright (c) 2001-2024, PostgreSQL Global Development Group
*
* IDENTIFICATION
* src/common/encnames.c
*
*-------------------------------------------------------------------------
*/
#include "c.h"
#include <ctype.h>
#include <unistd.h>
#include "mb/pg_wchar.h"
/* ----------
* All encoding names, sorted: *** A L P H A B E T I C ***
*
* All names must be without irrelevant chars, search routines use
* isalnum() chars only. It means ISO-8859-1, iso_8859-1 and Iso8859_1
* are always converted to 'iso88591'. All must be lower case.
*
* The table doesn't contain 'cs' aliases (like csISOLatin1). It's needed?
*
* Karel Zak, Aug 2001
* ----------
*/
typedef struct pg_encname
{
const char *name;
pg_enc encoding;
} pg_encname;
/* ----------
* These are "official" encoding names.
* ----------
*/
#ifndef WIN32
#define DEF_ENC2NAME(name, codepage) { #name, PG_##name }
#else
#define DEF_ENC2NAME(name, codepage) { #name, PG_##name, codepage }
#endif
const pg_enc2name pg_enc2name_tbl[] =
{
[PG_SQL_ASCII] = DEF_ENC2NAME(SQL_ASCII, 0),
[PG_EUC_JP] = DEF_ENC2NAME(EUC_JP, 20932),
[PG_EUC_CN] = DEF_ENC2NAME(EUC_CN, 20936),
[PG_EUC_KR] = DEF_ENC2NAME(EUC_KR, 51949),
[PG_EUC_TW] = DEF_ENC2NAME(EUC_TW, 0),
[PG_EUC_JIS_2004] = DEF_ENC2NAME(EUC_JIS_2004, 20932),
[PG_UTF8] = DEF_ENC2NAME(UTF8, 65001),
[PG_MULE_INTERNAL] = DEF_ENC2NAME(MULE_INTERNAL, 0),
[PG_LATIN1] = DEF_ENC2NAME(LATIN1, 28591),
[PG_LATIN2] = DEF_ENC2NAME(LATIN2, 28592),
[PG_LATIN3] = DEF_ENC2NAME(LATIN3, 28593),
[PG_LATIN4] = DEF_ENC2NAME(LATIN4, 28594),
[PG_LATIN5] = DEF_ENC2NAME(LATIN5, 28599),
[PG_LATIN6] = DEF_ENC2NAME(LATIN6, 0),
[PG_LATIN7] = DEF_ENC2NAME(LATIN7, 0),
[PG_LATIN8] = DEF_ENC2NAME(LATIN8, 0),
[PG_LATIN9] = DEF_ENC2NAME(LATIN9, 28605),
[PG_LATIN10] = DEF_ENC2NAME(LATIN10, 0),
[PG_WIN1256] = DEF_ENC2NAME(WIN1256, 1256),
[PG_WIN1258] = DEF_ENC2NAME(WIN1258, 1258),
[PG_WIN866] = DEF_ENC2NAME(WIN866, 866),
[PG_WIN874] = DEF_ENC2NAME(WIN874, 874),
[PG_KOI8R] = DEF_ENC2NAME(KOI8R, 20866),
[PG_WIN1251] = DEF_ENC2NAME(WIN1251, 1251),
[PG_WIN1252] = DEF_ENC2NAME(WIN1252, 1252),
[PG_ISO_8859_5] = DEF_ENC2NAME(ISO_8859_5, 28595),
[PG_ISO_8859_6] = DEF_ENC2NAME(ISO_8859_6, 28596),
[PG_ISO_8859_7] = DEF_ENC2NAME(ISO_8859_7, 28597),
[PG_ISO_8859_8] = DEF_ENC2NAME(ISO_8859_8, 28598),
[PG_WIN1250] = DEF_ENC2NAME(WIN1250, 1250),
[PG_WIN1253] = DEF_ENC2NAME(WIN1253, 1253),
[PG_WIN1254] = DEF_ENC2NAME(WIN1254, 1254),
[PG_WIN1255] = DEF_ENC2NAME(WIN1255, 1255),
[PG_WIN1257] = DEF_ENC2NAME(WIN1257, 1257),
[PG_KOI8U] = DEF_ENC2NAME(KOI8U, 21866),
[PG_SJIS] = DEF_ENC2NAME(SJIS, 932),
[PG_BIG5] = DEF_ENC2NAME(BIG5, 950),
[PG_GBK] = DEF_ENC2NAME(GBK, 936),
[PG_UHC] = DEF_ENC2NAME(UHC, 949),
[PG_GB18030] = DEF_ENC2NAME(GB18030, 54936),
[PG_JOHAB] = DEF_ENC2NAME(JOHAB, 0),
[PG_SHIFT_JIS_2004] = DEF_ENC2NAME(SHIFT_JIS_2004, 932),
};
/* ----------
* These are encoding names for gettext.
*
* This covers all encodings except MULE_INTERNAL, which is alien to gettext.
* ----------
*/
/*
* Table of encoding names for ICU (currently covers backend encodings only)
*
* Reference: <https://ssl.icu-project.org/icu-bin/convexp>
*
* NULL entries are not supported by ICU, or their mapping is unclear.
*/
StaticAssertDecl(lengthof(pg_enc2icu_tbl) == PG_ENCODING_BE_LAST + 1,
"pg_enc2icu_tbl incomplete");
/*
* Is this encoding supported by ICU?
*/
/*
* Returns ICU's name for encoding, or NULL if not supported
*/
/* ----------
* Encoding checks, for error returns -1 else encoding id
* ----------
*/
/*
* Remove irrelevant chars from encoding name, store at *newkey
*
* (Caller's responsibility to provide a large enough buffer)
*/
/*
* Search encoding by encoding name
*
* Returns encoding ID, or -1 if not recognized
*/