mirror of
https://github.com/postgres/postgres.git
synced 2025-11-13 16:22:44 +03:00
pgindent run on all C files. Java run to follow. initdb/regression
tests pass.
This commit is contained in:
Bruce Momjian
@@ -7,7 +7,7 @@
|
||||
*
|
||||
* 1999/1/15 Tatsuo Ishii
|
||||
*
|
||||
* $Id: big5.c,v 1.7 2001/02/10 02:31:27 tgl Exp $
|
||||
* $Id: big5.c,v 1.8 2001/10/25 05:49:51 momjian Exp $
|
||||
*/
|
||||
|
||||
/* can be used in either frontend or backend */
|
||||
@@ -19,7 +19,7 @@ typedef struct
|
||||
{
|
||||
unsigned short code,
|
||||
peer;
|
||||
} codes_t;
|
||||
} codes_t;
|
||||
|
||||
/* map Big5 Level 1 to CNS 11643-1992 Plane 1 */
|
||||
static codes_t big5Level1ToCnsPlane1[25] = { /* range */
|
||||
@@ -205,7 +205,7 @@ static unsigned short b2c3[][2] = {
|
||||
};
|
||||
|
||||
static unsigned short BinarySearchRange
|
||||
(codes_t * array, int high, unsigned short code)
|
||||
(codes_t *array, int high, unsigned short code)
|
||||
{
|
||||
int low,
|
||||
mid,
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
* WIN1250 client encoding support contributed by Pavel Behal
|
||||
* SJIS UDC (NEC selection IBM kanji) support contributed by Eiji Tokuya
|
||||
*
|
||||
* $Id: conv.c,v 1.32 2001/10/16 10:09:17 ishii Exp $
|
||||
* $Id: conv.c,v 1.33 2001/10/25 05:49:51 momjian Exp $
|
||||
*
|
||||
*
|
||||
*/
|
||||
@@ -64,7 +64,6 @@
|
||||
#include "Unicode/utf8_to_koi8r.map"
|
||||
#include "Unicode/utf8_to_win1251.map"
|
||||
|
||||
|
||||
#endif /* UNICODE_CONVERSION */
|
||||
|
||||
/*
|
||||
@@ -124,7 +123,6 @@ sjis2mic(unsigned char *sjis, unsigned char *p, int len)
|
||||
}
|
||||
else if (c1 > 0x7f)
|
||||
{
|
||||
|
||||
/*
|
||||
* JIS X0208, X0212, user defined extended characters
|
||||
*/
|
||||
@@ -168,7 +166,6 @@ sjis2mic(unsigned char *sjis, unsigned char *p, int len)
|
||||
}
|
||||
else if (k >= 0xf040 && k < 0xf540)
|
||||
{
|
||||
|
||||
/*
|
||||
* UDC1 mapping to X0208 85 ku - 94 ku JIS code 0x7521 -
|
||||
* 0x7e7e EUC 0xf5a1 - 0xfefe
|
||||
@@ -181,7 +178,6 @@ sjis2mic(unsigned char *sjis, unsigned char *p, int len)
|
||||
}
|
||||
else if (k >= 0xf540 && k < 0xfa40)
|
||||
{
|
||||
|
||||
/*
|
||||
* UDC2 mapping to X0212 85 ku - 94 ku JIS code 0x7521 -
|
||||
* 0x7e7e EUC 0x8ff5a1 - 0x8ffefe
|
||||
@@ -194,7 +190,6 @@ sjis2mic(unsigned char *sjis, unsigned char *p, int len)
|
||||
}
|
||||
else if (k >= 0xfa40)
|
||||
{
|
||||
|
||||
/*
|
||||
* mapping IBM kanji to X0208 and X0212
|
||||
*
|
||||
@@ -624,7 +619,7 @@ big52mic(unsigned char *big5, unsigned char *p, int len)
|
||||
{
|
||||
if (lc == LC_CNS11643_3 || lc == LC_CNS11643_4)
|
||||
{
|
||||
*p++ = 0x9d;/* LCPRV2 */
|
||||
*p++ = 0x9d; /* LCPRV2 */
|
||||
}
|
||||
*p++ = lc; /* Plane No. */
|
||||
*p++ = (cnsBuf >> 8) & 0x00ff;
|
||||
@@ -793,7 +788,6 @@ mic2latin5(unsigned char *mic, unsigned char *p, int len)
|
||||
{
|
||||
mic2latin(mic, p, len, LC_ISO8859_5);
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
/*
|
||||
@@ -1275,7 +1269,7 @@ compare2(const void *p1, const void *p2)
|
||||
*/
|
||||
static void
|
||||
utf_to_local(unsigned char *utf, unsigned char *iso,
|
||||
pg_utf_to_local * map, int size, int len)
|
||||
pg_utf_to_local *map, int size, int len)
|
||||
{
|
||||
unsigned int iutf;
|
||||
int l;
|
||||
@@ -1355,14 +1349,14 @@ utf_to_latin5(unsigned char *utf, unsigned char *iso, int len)
|
||||
{
|
||||
utf_to_local(utf, iso, ULmapISO8859_5, sizeof(ULmapISO8859_5) / sizeof(pg_utf_to_local), len);
|
||||
}
|
||||
#endif /* NOT_USED */
|
||||
#endif /* NOT_USED */
|
||||
|
||||
/*
|
||||
* Cyrillic charsets
|
||||
*/
|
||||
|
||||
/*
|
||||
* UTF-8 --->KOI8-R
|
||||
* UTF-8 --->KOI8-R
|
||||
*/
|
||||
static void
|
||||
utf_to_KOI8R(unsigned char *utf, unsigned char *iso, int len)
|
||||
@@ -1372,7 +1366,7 @@ utf_to_KOI8R(unsigned char *utf, unsigned char *iso, int len)
|
||||
}
|
||||
|
||||
/*
|
||||
* UTF-8 --->WIN1251
|
||||
* UTF-8 --->WIN1251
|
||||
*/
|
||||
static void
|
||||
utf_to_WIN1251(unsigned char *utf, unsigned char *iso, int len)
|
||||
@@ -1382,7 +1376,7 @@ utf_to_WIN1251(unsigned char *utf, unsigned char *iso, int len)
|
||||
}
|
||||
|
||||
/*
|
||||
* UTF-8 --->ALT
|
||||
* UTF-8 --->ALT
|
||||
*/
|
||||
static void
|
||||
utf_to_ALT(unsigned char *utf, unsigned char *iso, int len)
|
||||
@@ -1396,7 +1390,7 @@ utf_to_ALT(unsigned char *utf, unsigned char *iso, int len)
|
||||
*/
|
||||
static void
|
||||
local_to_utf(unsigned char *iso, unsigned char *utf,
|
||||
pg_local_to_utf * map, int size, int encoding, int len)
|
||||
pg_local_to_utf *map, int size, int encoding, int len)
|
||||
{
|
||||
unsigned int iiso;
|
||||
int l;
|
||||
@@ -1441,7 +1435,7 @@ local_to_utf(unsigned char *iso, unsigned char *utf,
|
||||
if (p == NULL)
|
||||
{
|
||||
elog(NOTICE, "local_to_utf: could not convert (0x%04x) %s to UTF-8. Ignored",
|
||||
iiso, (&pg_enc2name_tbl[ encoding ])->name);
|
||||
iiso, (&pg_enc2name_tbl[encoding])->name);
|
||||
continue;
|
||||
}
|
||||
if (p->utf & 0xff000000)
|
||||
@@ -1492,7 +1486,7 @@ latin5_to_utf(unsigned char *iso, unsigned char *utf, int len)
|
||||
{
|
||||
local_to_utf(iso, utf, LUmapISO8859_5, sizeof(LUmapISO8859_5) / sizeof(pg_local_to_utf), PG_LATIN5, len);
|
||||
}
|
||||
#endif /* NOT_USED */
|
||||
#endif /* NOT_USED */
|
||||
|
||||
#define UTF_ISO8859(_id_) \
|
||||
static void \
|
||||
@@ -1546,6 +1540,7 @@ ALT_to_utf(unsigned char *iso, unsigned char *utf, int len)
|
||||
{
|
||||
local_to_utf(iso, utf, LUmapALT, sizeof(LUmapALT) / sizeof(pg_local_to_utf), PG_ALT, len);
|
||||
}
|
||||
|
||||
/*
|
||||
* UTF-8 ---> EUC_JP
|
||||
*/
|
||||
@@ -1564,7 +1559,7 @@ static void
|
||||
euc_jp_to_utf(unsigned char *euc, unsigned char *utf, int len)
|
||||
{
|
||||
local_to_utf(euc, utf, LUmapEUC_JP,
|
||||
sizeof(LUmapEUC_JP) / sizeof(pg_local_to_utf), PG_EUC_JP, len);
|
||||
sizeof(LUmapEUC_JP) / sizeof(pg_local_to_utf), PG_EUC_JP, len);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -1585,7 +1580,7 @@ static void
|
||||
euc_cn_to_utf(unsigned char *euc, unsigned char *utf, int len)
|
||||
{
|
||||
local_to_utf(euc, utf, LUmapEUC_CN,
|
||||
sizeof(LUmapEUC_CN) / sizeof(pg_local_to_utf), PG_EUC_CN, len);
|
||||
sizeof(LUmapEUC_CN) / sizeof(pg_local_to_utf), PG_EUC_CN, len);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -1606,7 +1601,7 @@ static void
|
||||
euc_kr_to_utf(unsigned char *euc, unsigned char *utf, int len)
|
||||
{
|
||||
local_to_utf(euc, utf, LUmapEUC_KR,
|
||||
sizeof(LUmapEUC_KR) / sizeof(pg_local_to_utf), PG_EUC_KR, len);
|
||||
sizeof(LUmapEUC_KR) / sizeof(pg_local_to_utf), PG_EUC_KR, len);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -1627,7 +1622,7 @@ static void
|
||||
euc_tw_to_utf(unsigned char *euc, unsigned char *utf, int len)
|
||||
{
|
||||
local_to_utf(euc, utf, LUmapEUC_TW,
|
||||
sizeof(LUmapEUC_TW) / sizeof(pg_local_to_utf), PG_EUC_TW, len);
|
||||
sizeof(LUmapEUC_TW) / sizeof(pg_local_to_utf), PG_EUC_TW, len);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -1648,7 +1643,7 @@ static void
|
||||
sjis_to_utf(unsigned char *euc, unsigned char *utf, int len)
|
||||
{
|
||||
local_to_utf(euc, utf, LUmapSJIS,
|
||||
sizeof(LUmapSJIS) / sizeof(pg_local_to_utf), PG_SJIS, len);
|
||||
sizeof(LUmapSJIS) / sizeof(pg_local_to_utf), PG_SJIS, len);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -1669,7 +1664,7 @@ static void
|
||||
big5_to_utf(unsigned char *euc, unsigned char *utf, int len)
|
||||
{
|
||||
local_to_utf(euc, utf, LUmapBIG5,
|
||||
sizeof(LUmapBIG5) / sizeof(pg_local_to_utf), PG_BIG5, len);
|
||||
sizeof(LUmapBIG5) / sizeof(pg_local_to_utf), PG_BIG5, len);
|
||||
}
|
||||
|
||||
/* ----------
|
||||
@@ -1678,69 +1673,176 @@ big5_to_utf(unsigned char *euc, unsigned char *utf, int len)
|
||||
* WARINIG: must by same order as pg_enc in include/mb/pg_wchar.h!
|
||||
* ----------
|
||||
*/
|
||||
pg_enconv pg_enconv_tbl[] =
|
||||
pg_enconv pg_enconv_tbl[] =
|
||||
{
|
||||
{ PG_SQL_ASCII, ascii2mic, mic2ascii, ascii2utf, utf2ascii},
|
||||
{ PG_EUC_JP, euc_jp2mic, mic2euc_jp, euc_jp_to_utf, utf_to_euc_jp},
|
||||
{ PG_EUC_CN, euc_cn2mic, mic2euc_cn, euc_cn_to_utf, utf_to_euc_cn},
|
||||
{ PG_EUC_KR, euc_kr2mic, mic2euc_kr, euc_kr_to_utf, utf_to_euc_kr},
|
||||
{ PG_EUC_TW, euc_tw2mic, mic2euc_tw, euc_tw_to_utf, utf_to_euc_tw},
|
||||
{ PG_UTF8, 0, 0, 0, 0},
|
||||
{ PG_MULE_INTERNAL, 0, 0, 0, 0},
|
||||
{ PG_LATIN1, latin12mic, mic2latin1, iso8859_1_to_utf, utf_to_iso8859_1},
|
||||
{ PG_LATIN2, latin22mic, mic2latin2, iso8859_2_to_utf, utf_to_iso8859_2},
|
||||
{ PG_LATIN3, latin32mic, mic2latin3, iso8859_3_to_utf, utf_to_iso8859_3},
|
||||
{ PG_LATIN4, latin42mic, mic2latin4, iso8859_4_to_utf, utf_to_iso8859_4},
|
||||
{ PG_LATIN5, iso2mic, mic2iso, iso8859_9_to_utf, utf_to_iso8859_9},
|
||||
{ PG_LATIN6, 0, 0, iso8859_10_to_utf, utf_to_iso8859_10},
|
||||
{ PG_LATIN7, 0, 0, iso8859_13_to_utf, utf_to_iso8859_13},
|
||||
{ PG_LATIN8, 0, 0, iso8859_14_to_utf, utf_to_iso8859_14},
|
||||
{ PG_LATIN9, 0, 0, iso8859_15_to_utf, utf_to_iso8859_15},
|
||||
{ PG_LATIN10, 0, 0, iso8859_16_to_utf, utf_to_iso8859_16},
|
||||
{ PG_KOI8R, koi8r2mic, mic2koi8r, KOI8R_to_utf, utf_to_KOI8R},
|
||||
{ PG_WIN1251, win12512mic, mic2win1251, WIN1251_to_utf, utf_to_WIN1251},
|
||||
{ PG_ALT, alt2mic, mic2alt, ALT_to_utf, utf_to_ALT},
|
||||
{ PG_ISO_8859_5, 0, 0, iso8859_5_to_utf, utf_to_iso8859_5},
|
||||
{ PG_ISO_8859_6, 0, 0, iso8859_6_to_utf, utf_to_iso8859_6},
|
||||
{ PG_ISO_8859_7, 0, 0, iso8859_7_to_utf, utf_to_iso8859_7},
|
||||
{ PG_ISO_8859_8, 0, 0, iso8859_8_to_utf, utf_to_iso8859_8},
|
||||
{
|
||||
PG_SQL_ASCII, ascii2mic, mic2ascii, ascii2utf, utf2ascii
|
||||
} ,
|
||||
{
|
||||
PG_EUC_JP, euc_jp2mic, mic2euc_jp, euc_jp_to_utf, utf_to_euc_jp
|
||||
},
|
||||
{
|
||||
PG_EUC_CN, euc_cn2mic, mic2euc_cn, euc_cn_to_utf, utf_to_euc_cn
|
||||
},
|
||||
{
|
||||
PG_EUC_KR, euc_kr2mic, mic2euc_kr, euc_kr_to_utf, utf_to_euc_kr
|
||||
},
|
||||
{
|
||||
PG_EUC_TW, euc_tw2mic, mic2euc_tw, euc_tw_to_utf, utf_to_euc_tw
|
||||
},
|
||||
{
|
||||
PG_UTF8, 0, 0, 0, 0
|
||||
},
|
||||
{
|
||||
PG_MULE_INTERNAL, 0, 0, 0, 0
|
||||
},
|
||||
{
|
||||
PG_LATIN1, latin12mic, mic2latin1, iso8859_1_to_utf, utf_to_iso8859_1
|
||||
},
|
||||
{
|
||||
PG_LATIN2, latin22mic, mic2latin2, iso8859_2_to_utf, utf_to_iso8859_2
|
||||
},
|
||||
{
|
||||
PG_LATIN3, latin32mic, mic2latin3, iso8859_3_to_utf, utf_to_iso8859_3
|
||||
},
|
||||
{
|
||||
PG_LATIN4, latin42mic, mic2latin4, iso8859_4_to_utf, utf_to_iso8859_4
|
||||
},
|
||||
{
|
||||
PG_LATIN5, iso2mic, mic2iso, iso8859_9_to_utf, utf_to_iso8859_9
|
||||
},
|
||||
{
|
||||
PG_LATIN6, 0, 0, iso8859_10_to_utf, utf_to_iso8859_10
|
||||
},
|
||||
{
|
||||
PG_LATIN7, 0, 0, iso8859_13_to_utf, utf_to_iso8859_13
|
||||
},
|
||||
{
|
||||
PG_LATIN8, 0, 0, iso8859_14_to_utf, utf_to_iso8859_14
|
||||
},
|
||||
{
|
||||
PG_LATIN9, 0, 0, iso8859_15_to_utf, utf_to_iso8859_15
|
||||
},
|
||||
{
|
||||
PG_LATIN10, 0, 0, iso8859_16_to_utf, utf_to_iso8859_16
|
||||
},
|
||||
{
|
||||
PG_KOI8R, koi8r2mic, mic2koi8r, KOI8R_to_utf, utf_to_KOI8R
|
||||
},
|
||||
{
|
||||
PG_WIN1251, win12512mic, mic2win1251, WIN1251_to_utf, utf_to_WIN1251
|
||||
},
|
||||
{
|
||||
PG_ALT, alt2mic, mic2alt, ALT_to_utf, utf_to_ALT
|
||||
},
|
||||
{
|
||||
PG_ISO_8859_5, 0, 0, iso8859_5_to_utf, utf_to_iso8859_5
|
||||
},
|
||||
{
|
||||
PG_ISO_8859_6, 0, 0, iso8859_6_to_utf, utf_to_iso8859_6
|
||||
},
|
||||
{
|
||||
PG_ISO_8859_7, 0, 0, iso8859_7_to_utf, utf_to_iso8859_7
|
||||
},
|
||||
{
|
||||
PG_ISO_8859_8, 0, 0, iso8859_8_to_utf, utf_to_iso8859_8
|
||||
},
|
||||
|
||||
{ PG_SJIS, sjis2mic, mic2sjis, sjis_to_utf, utf_to_sjis},
|
||||
{ PG_BIG5, big52mic, mic2big5, big5_to_utf, utf_to_big5},
|
||||
{ PG_WIN1250, win12502mic, mic2win1250, 0, 0},
|
||||
{
|
||||
PG_SJIS, sjis2mic, mic2sjis, sjis_to_utf, utf_to_sjis
|
||||
},
|
||||
{
|
||||
PG_BIG5, big52mic, mic2big5, big5_to_utf, utf_to_big5
|
||||
},
|
||||
{
|
||||
PG_WIN1250, win12502mic, mic2win1250, 0, 0
|
||||
},
|
||||
};
|
||||
|
||||
#else
|
||||
|
||||
pg_enconv pg_enconv_tbl[] =
|
||||
pg_enconv pg_enconv_tbl[] =
|
||||
{
|
||||
{ PG_SQL_ASCII, ascii2mic, mic2ascii, 0, 0},
|
||||
{ PG_EUC_JP, euc_jp2mic, mic2euc_jp, 0, 0},
|
||||
{ PG_EUC_CN, euc_cn2mic, mic2euc_cn, 0, 0},
|
||||
{ PG_EUC_KR, euc_kr2mic, mic2euc_kr, 0, 0},
|
||||
{ PG_EUC_TW, euc_tw2mic, mic2euc_tw, 0, 0},
|
||||
{ PG_UTF8, 0, 0, 0, 0},
|
||||
{ PG_MULE_INTERNAL, 0, 0, 0, 0},
|
||||
{ PG_LATIN1, latin12mic, mic2latin1, 0, 0},
|
||||
{ PG_LATIN2, latin22mic, mic2latin2, 0, 0},
|
||||
{ PG_LATIN3, latin32mic, mic2latin3, 0, 0},
|
||||
{ PG_LATIN4, latin42mic, mic2latin4, 0, 0},
|
||||
{ PG_LATIN5, iso2mic, mic2iso, 0, 0},
|
||||
{ PG_LATIN6, 0, 0, 0, 0},
|
||||
{ PG_LATIN7, 0, 0, 0, 0},
|
||||
{ PG_LATIN8, 0, 0, 0, 0},
|
||||
{ PG_LATIN9, 0, 0, 0, 0},
|
||||
{ PG_LATIN10, 0, 0, 0, 0},
|
||||
{ PG_KOI8R, koi8r2mic, mic2koi8r, 0, 0},
|
||||
{ PG_WIN1251, win12512mic, mic2win1251, 0, 0},
|
||||
{ PG_ALT, alt2mic, mic2alt, 0, 0},
|
||||
{ PG_ISO_8859_5, 0, 0, 0, 0},
|
||||
{ PG_ISO_8859_6, 0, 0, 0, 0},
|
||||
{ PG_ISO_8859_7, 0, 0, 0, 0},
|
||||
{ PG_ISO_8859_8, 0, 0, 0, 0},
|
||||
{ PG_SJIS, sjis2mic, mic2sjis, 0, 0},
|
||||
{ PG_BIG5, big52mic, mic2big5, 0, 0},
|
||||
{ PG_WIN1250, win12502mic, mic2win1250, 0, 0},
|
||||
{
|
||||
PG_SQL_ASCII, ascii2mic, mic2ascii, 0, 0
|
||||
} ,
|
||||
{
|
||||
PG_EUC_JP, euc_jp2mic, mic2euc_jp, 0, 0
|
||||
},
|
||||
{
|
||||
PG_EUC_CN, euc_cn2mic, mic2euc_cn, 0, 0
|
||||
},
|
||||
{
|
||||
PG_EUC_KR, euc_kr2mic, mic2euc_kr, 0, 0
|
||||
},
|
||||
{
|
||||
PG_EUC_TW, euc_tw2mic, mic2euc_tw, 0, 0
|
||||
},
|
||||
{
|
||||
PG_UTF8, 0, 0, 0, 0
|
||||
},
|
||||
{
|
||||
PG_MULE_INTERNAL, 0, 0, 0, 0
|
||||
},
|
||||
{
|
||||
PG_LATIN1, latin12mic, mic2latin1, 0, 0
|
||||
},
|
||||
{
|
||||
PG_LATIN2, latin22mic, mic2latin2, 0, 0
|
||||
},
|
||||
{
|
||||
PG_LATIN3, latin32mic, mic2latin3, 0, 0
|
||||
},
|
||||
{
|
||||
PG_LATIN4, latin42mic, mic2latin4, 0, 0
|
||||
},
|
||||
{
|
||||
PG_LATIN5, iso2mic, mic2iso, 0, 0
|
||||
},
|
||||
{
|
||||
PG_LATIN6, 0, 0, 0, 0
|
||||
},
|
||||
{
|
||||
PG_LATIN7, 0, 0, 0, 0
|
||||
},
|
||||
{
|
||||
PG_LATIN8, 0, 0, 0, 0
|
||||
},
|
||||
{
|
||||
PG_LATIN9, 0, 0, 0, 0
|
||||
},
|
||||
{
|
||||
PG_LATIN10, 0, 0, 0, 0
|
||||
},
|
||||
{
|
||||
PG_KOI8R, koi8r2mic, mic2koi8r, 0, 0
|
||||
},
|
||||
{
|
||||
PG_WIN1251, win12512mic, mic2win1251, 0, 0
|
||||
},
|
||||
{
|
||||
PG_ALT, alt2mic, mic2alt, 0, 0
|
||||
},
|
||||
{
|
||||
PG_ISO_8859_5, 0, 0, 0, 0
|
||||
},
|
||||
{
|
||||
PG_ISO_8859_6, 0, 0, 0, 0
|
||||
},
|
||||
{
|
||||
PG_ISO_8859_7, 0, 0, 0, 0
|
||||
},
|
||||
{
|
||||
PG_ISO_8859_8, 0, 0, 0, 0
|
||||
},
|
||||
{
|
||||
PG_SJIS, sjis2mic, mic2sjis, 0, 0
|
||||
},
|
||||
{
|
||||
PG_BIG5, big52mic, mic2big5, 0, 0
|
||||
},
|
||||
{
|
||||
PG_WIN1250, win12502mic, mic2win1250, 0, 0
|
||||
},
|
||||
};
|
||||
|
||||
#endif /* UNICODE_CONVERSION */
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
* Encoding names and routines for work with it. All
|
||||
* in this file is shared bedween FE and BE.
|
||||
*
|
||||
* $Id: encnames.c,v 1.4 2001/10/16 10:09:17 ishii Exp $
|
||||
* $Id: encnames.c,v 1.5 2001/10/25 05:49:51 momjian Exp $
|
||||
*/
|
||||
#ifdef FRONTEND
|
||||
#include "postgres_fe.h"
|
||||
@@ -23,7 +23,7 @@
|
||||
#include <ctype.h>
|
||||
|
||||
/* ----------
|
||||
* All encoding names, sorted: *** A L P H A B E T I C ***
|
||||
* All encoding names, sorted: *** A L P H A B E T I C ***
|
||||
*
|
||||
* All names must be without irrelevan chars, search routines use
|
||||
* isalnum() chars only. It means ISO-8859-1, iso_8859-1 and Iso8859_1
|
||||
@@ -34,58 +34,153 @@
|
||||
* Karel Zak, Aug 2001
|
||||
* ----------
|
||||
*/
|
||||
pg_encname pg_encname_tbl[] =
|
||||
pg_encname pg_encname_tbl[] =
|
||||
{
|
||||
{ "alt", PG_ALT }, /* IBM866 */
|
||||
{ "big5", PG_BIG5 }, /* Big5; Chinese for Taiwan Multi-byte set */
|
||||
{ "euccn", PG_EUC_CN }, /* EUC-CN; Extended Unix Code for simplified Chinese */
|
||||
{ "eucjp", PG_EUC_JP }, /* EUC-JP; Extended UNIX Code fixed Width for Japanese, stdandard OSF */
|
||||
{ "euckr", PG_EUC_KR }, /* EUC-KR; RFC1557,Choi */
|
||||
{ "euctw", PG_EUC_TW }, /* EUC-TW; Extended Unix Code for traditional Chinese */
|
||||
{ "iso88591", PG_LATIN1 }, /* ISO-8859-1; RFC1345,KXS2 */
|
||||
{ "iso885910", PG_LATIN6 }, /* ISO-8859-10; RFC1345,KXS2 */
|
||||
{ "iso885913", PG_LATIN7 }, /* ISO-8859-13; RFC1345,KXS2 */
|
||||
{ "iso885914", PG_LATIN8 }, /* ISO-8859-14; RFC1345,KXS2 */
|
||||
{ "iso885915", PG_LATIN9 }, /* ISO-8859-15; RFC1345,KXS2 */
|
||||
{ "iso885916", PG_LATIN10 }, /* ISO-8859-16; RFC1345,KXS2 */
|
||||
{ "iso88592", PG_LATIN2 }, /* ISO-8859-2; RFC1345,KXS2 */
|
||||
{ "iso88593", PG_LATIN3 }, /* ISO-8859-3; RFC1345,KXS2 */
|
||||
{ "iso88594", PG_LATIN4 }, /* ISO-8859-4; RFC1345,KXS2 */
|
||||
{ "iso88595", PG_ISO_8859_5 }, /* ISO-8859-5; RFC1345,KXS2 */
|
||||
{ "iso88596", PG_ISO_8859_6 }, /* ISO-8859-6; RFC1345,KXS2 */
|
||||
{ "iso88597", PG_ISO_8859_7 }, /* ISO-8859-7; RFC1345,KXS2 */
|
||||
{ "iso88598", PG_ISO_8859_8 }, /* ISO-8859-8; RFC1345,KXS2 */
|
||||
{ "iso88599", PG_LATIN5 }, /* ISO-8859-9; RFC1345,KXS2 */
|
||||
{ "koi8", PG_KOI8R }, /* _dirty_ alias for KOI8-R (backward compatibility) */
|
||||
{ "koi8r", PG_KOI8R }, /* KOI8-R; RFC1489 */
|
||||
{ "latin1", PG_LATIN1 }, /* alias for ISO-8859-1 */
|
||||
{ "latin10", PG_LATIN10}, /* alias for ISO-8859-16 */
|
||||
{ "latin2", PG_LATIN2 }, /* alias for ISO-8859-2 */
|
||||
{ "latin3", PG_LATIN3 }, /* alias for ISO-8859-3 */
|
||||
{ "latin4", PG_LATIN4 }, /* alias for ISO-8859-4 */
|
||||
{ "latin5", PG_LATIN5 }, /* alias for ISO-8859-9 */
|
||||
{ "latin6", PG_LATIN6}, /* alias for ISO-8859-10 */
|
||||
{ "latin7", PG_LATIN7}, /* alias for ISO-8859-13 */
|
||||
{ "latin8", PG_LATIN8}, /* alias for ISO-8859-14 */
|
||||
{ "latin9", PG_LATIN9}, /* alias for ISO-8859-15 */
|
||||
{ "mskanji", PG_SJIS }, /* alias for Shift_JIS */
|
||||
{ "muleinternal",PG_MULE_INTERNAL },
|
||||
{ "shiftjis", PG_SJIS }, /* Shift_JIS; JIS X 0202-1991 */
|
||||
{ "sjis", PG_SJIS }, /* alias for Shift_JIS */
|
||||
{ "sqlascii", PG_SQL_ASCII },
|
||||
{ "unicode", PG_UTF8 }, /* alias for UTF-8 */
|
||||
{ "utf8", PG_UTF8 }, /* UTF-8; RFC2279 */
|
||||
{ "win", PG_WIN1251 }, /* _dirty_ alias for windows-1251 (backward compatibility) */
|
||||
{ "win1250", PG_WIN1250 }, /* alias for Windows-1250 */
|
||||
{ "win1251", PG_WIN1251 }, /* alias for Windows-1251 */
|
||||
{ "windows1250",PG_WIN1250 }, /* Windows-1251; Microsoft */
|
||||
{ "windows1251",PG_WIN1251 }, /* Windows-1251; Microsoft */
|
||||
{
|
||||
"alt", PG_ALT
|
||||
} , /* IBM866 */
|
||||
{
|
||||
"big5", PG_BIG5
|
||||
}, /* Big5; Chinese for Taiwan Multi-byte set */
|
||||
{
|
||||
"euccn", PG_EUC_CN
|
||||
}, /* EUC-CN; Extended Unix Code for
|
||||
* simplified Chinese */
|
||||
{
|
||||
"eucjp", PG_EUC_JP
|
||||
}, /* EUC-JP; Extended UNIX Code fixed Width
|
||||
* for Japanese, stdandard OSF */
|
||||
{
|
||||
"euckr", PG_EUC_KR
|
||||
}, /* EUC-KR; RFC1557,Choi */
|
||||
{
|
||||
"euctw", PG_EUC_TW
|
||||
}, /* EUC-TW; Extended Unix Code for
|
||||
* traditional Chinese */
|
||||
{
|
||||
"iso88591", PG_LATIN1
|
||||
}, /* ISO-8859-1; RFC1345,KXS2 */
|
||||
{
|
||||
"iso885910", PG_LATIN6
|
||||
}, /* ISO-8859-10; RFC1345,KXS2 */
|
||||
{
|
||||
"iso885913", PG_LATIN7
|
||||
}, /* ISO-8859-13; RFC1345,KXS2 */
|
||||
{
|
||||
"iso885914", PG_LATIN8
|
||||
}, /* ISO-8859-14; RFC1345,KXS2 */
|
||||
{
|
||||
"iso885915", PG_LATIN9
|
||||
}, /* ISO-8859-15; RFC1345,KXS2 */
|
||||
{
|
||||
"iso885916", PG_LATIN10
|
||||
}, /* ISO-8859-16; RFC1345,KXS2 */
|
||||
{
|
||||
"iso88592", PG_LATIN2
|
||||
}, /* ISO-8859-2; RFC1345,KXS2 */
|
||||
{
|
||||
"iso88593", PG_LATIN3
|
||||
}, /* ISO-8859-3; RFC1345,KXS2 */
|
||||
{
|
||||
"iso88594", PG_LATIN4
|
||||
}, /* ISO-8859-4; RFC1345,KXS2 */
|
||||
{
|
||||
"iso88595", PG_ISO_8859_5
|
||||
}, /* ISO-8859-5; RFC1345,KXS2 */
|
||||
{
|
||||
"iso88596", PG_ISO_8859_6
|
||||
}, /* ISO-8859-6; RFC1345,KXS2 */
|
||||
{
|
||||
"iso88597", PG_ISO_8859_7
|
||||
}, /* ISO-8859-7; RFC1345,KXS2 */
|
||||
{
|
||||
"iso88598", PG_ISO_8859_8
|
||||
}, /* ISO-8859-8; RFC1345,KXS2 */
|
||||
{
|
||||
"iso88599", PG_LATIN5
|
||||
}, /* ISO-8859-9; RFC1345,KXS2 */
|
||||
{
|
||||
"koi8", PG_KOI8R
|
||||
}, /* _dirty_ alias for KOI8-R (backward
|
||||
* compatibility) */
|
||||
{
|
||||
"koi8r", PG_KOI8R
|
||||
}, /* KOI8-R; RFC1489 */
|
||||
{
|
||||
"latin1", PG_LATIN1
|
||||
}, /* alias for ISO-8859-1 */
|
||||
{
|
||||
"latin10", PG_LATIN10
|
||||
}, /* alias for ISO-8859-16 */
|
||||
{
|
||||
"latin2", PG_LATIN2
|
||||
}, /* alias for ISO-8859-2 */
|
||||
{
|
||||
"latin3", PG_LATIN3
|
||||
}, /* alias for ISO-8859-3 */
|
||||
{
|
||||
"latin4", PG_LATIN4
|
||||
}, /* alias for ISO-8859-4 */
|
||||
{
|
||||
"latin5", PG_LATIN5
|
||||
}, /* alias for ISO-8859-9 */
|
||||
{
|
||||
"latin6", PG_LATIN6
|
||||
}, /* alias for ISO-8859-10 */
|
||||
{
|
||||
"latin7", PG_LATIN7
|
||||
}, /* alias for ISO-8859-13 */
|
||||
{
|
||||
"latin8", PG_LATIN8
|
||||
}, /* alias for ISO-8859-14 */
|
||||
{
|
||||
"latin9", PG_LATIN9
|
||||
}, /* alias for ISO-8859-15 */
|
||||
{
|
||||
"mskanji", PG_SJIS
|
||||
}, /* alias for Shift_JIS */
|
||||
{
|
||||
"muleinternal", PG_MULE_INTERNAL
|
||||
},
|
||||
{
|
||||
"shiftjis", PG_SJIS
|
||||
}, /* Shift_JIS; JIS X 0202-1991 */
|
||||
{
|
||||
"sjis", PG_SJIS
|
||||
}, /* alias for Shift_JIS */
|
||||
{
|
||||
"sqlascii", PG_SQL_ASCII
|
||||
},
|
||||
{
|
||||
"unicode", PG_UTF8
|
||||
}, /* alias for UTF-8 */
|
||||
{
|
||||
"utf8", PG_UTF8
|
||||
}, /* UTF-8; RFC2279 */
|
||||
{
|
||||
"win", PG_WIN1251
|
||||
}, /* _dirty_ alias for windows-1251
|
||||
* (backward compatibility) */
|
||||
{
|
||||
"win1250", PG_WIN1250
|
||||
}, /* alias for Windows-1250 */
|
||||
{
|
||||
"win1251", PG_WIN1251
|
||||
}, /* alias for Windows-1251 */
|
||||
{
|
||||
"windows1250", PG_WIN1250
|
||||
}, /* Windows-1251; Microsoft */
|
||||
{
|
||||
"windows1251", PG_WIN1251
|
||||
}, /* Windows-1251; Microsoft */
|
||||
|
||||
{ NULL, 0 } /* last */
|
||||
{
|
||||
NULL, 0
|
||||
} /* last */
|
||||
};
|
||||
|
||||
unsigned int pg_encname_tbl_sz = \
|
||||
sizeof(pg_encname_tbl) / sizeof(pg_encname_tbl[0]) -1;
|
||||
sizeof(pg_encname_tbl) / sizeof(pg_encname_tbl[0]) - 1;
|
||||
|
||||
/* ----------
|
||||
* These are "official" encoding names.
|
||||
@@ -94,33 +189,87 @@ unsigned int pg_encname_tbl_sz = \
|
||||
*/
|
||||
pg_enc2name pg_enc2name_tbl[] =
|
||||
{
|
||||
{ "SQL_ASCII", PG_SQL_ASCII },
|
||||
{ "EUC_JP", PG_EUC_JP },
|
||||
{ "EUC_CN", PG_EUC_CN },
|
||||
{ "EUC_KR", PG_EUC_KR },
|
||||
{ "EUC_TW", PG_EUC_TW },
|
||||
{ "UNICODE", PG_UTF8 },
|
||||
{ "MULE_INTERNAL",PG_MULE_INTERNAL },
|
||||
{ "LATIN1", PG_LATIN1 },
|
||||
{ "LATIN2", PG_LATIN2 },
|
||||
{ "LATIN3", PG_LATIN3 },
|
||||
{ "LATIN4", PG_LATIN4 },
|
||||
{ "LATIN5", PG_LATIN5 },
|
||||
{ "LATIN6", PG_LATIN6 },
|
||||
{ "LATIN7", PG_LATIN7 },
|
||||
{ "LATIN8", PG_LATIN8 },
|
||||
{ "LATIN9", PG_LATIN9 },
|
||||
{ "LATIN10", PG_LATIN10 },
|
||||
{ "KOI8", PG_KOI8R },
|
||||
{ "WIN", PG_WIN1251 },
|
||||
{ "ALT", PG_ALT },
|
||||
{ "ISO_8859_5", PG_ISO_8859_5 },
|
||||
{ "ISO_8859_6", PG_ISO_8859_6 },
|
||||
{ "ISO_8859_7", PG_ISO_8859_7 },
|
||||
{ "ISO_8859_8", PG_ISO_8859_8 },
|
||||
{ "SJIS", PG_SJIS },
|
||||
{ "BIG5", PG_BIG5 },
|
||||
{ "WIN1250", PG_WIN1250 }
|
||||
{
|
||||
"SQL_ASCII", PG_SQL_ASCII
|
||||
} ,
|
||||
{
|
||||
"EUC_JP", PG_EUC_JP
|
||||
},
|
||||
{
|
||||
"EUC_CN", PG_EUC_CN
|
||||
},
|
||||
{
|
||||
"EUC_KR", PG_EUC_KR
|
||||
},
|
||||
{
|
||||
"EUC_TW", PG_EUC_TW
|
||||
},
|
||||
{
|
||||
"UNICODE", PG_UTF8
|
||||
},
|
||||
{
|
||||
"MULE_INTERNAL", PG_MULE_INTERNAL
|
||||
},
|
||||
{
|
||||
"LATIN1", PG_LATIN1
|
||||
},
|
||||
{
|
||||
"LATIN2", PG_LATIN2
|
||||
},
|
||||
{
|
||||
"LATIN3", PG_LATIN3
|
||||
},
|
||||
{
|
||||
"LATIN4", PG_LATIN4
|
||||
},
|
||||
{
|
||||
"LATIN5", PG_LATIN5
|
||||
},
|
||||
{
|
||||
"LATIN6", PG_LATIN6
|
||||
},
|
||||
{
|
||||
"LATIN7", PG_LATIN7
|
||||
},
|
||||
{
|
||||
"LATIN8", PG_LATIN8
|
||||
},
|
||||
{
|
||||
"LATIN9", PG_LATIN9
|
||||
},
|
||||
{
|
||||
"LATIN10", PG_LATIN10
|
||||
},
|
||||
{
|
||||
"KOI8", PG_KOI8R
|
||||
},
|
||||
{
|
||||
"WIN", PG_WIN1251
|
||||
},
|
||||
{
|
||||
"ALT", PG_ALT
|
||||
},
|
||||
{
|
||||
"ISO_8859_5", PG_ISO_8859_5
|
||||
},
|
||||
{
|
||||
"ISO_8859_6", PG_ISO_8859_6
|
||||
},
|
||||
{
|
||||
"ISO_8859_7", PG_ISO_8859_7
|
||||
},
|
||||
{
|
||||
"ISO_8859_8", PG_ISO_8859_8
|
||||
},
|
||||
{
|
||||
"SJIS", PG_SJIS
|
||||
},
|
||||
{
|
||||
"BIG5", PG_BIG5
|
||||
},
|
||||
{
|
||||
"WIN1250", PG_WIN1250
|
||||
}
|
||||
};
|
||||
|
||||
/* ----------
|
||||
@@ -130,12 +279,12 @@ pg_enc2name pg_enc2name_tbl[] =
|
||||
int
|
||||
pg_valid_client_encoding(const char *name)
|
||||
{
|
||||
int enc;
|
||||
int enc;
|
||||
|
||||
if ((enc = pg_char_to_encoding(name)) < 0)
|
||||
return -1;
|
||||
|
||||
if (!PG_VALID_FE_ENCODING( enc))
|
||||
if (!PG_VALID_FE_ENCODING(enc))
|
||||
return -1;
|
||||
|
||||
return enc;
|
||||
@@ -144,12 +293,12 @@ pg_valid_client_encoding(const char *name)
|
||||
int
|
||||
pg_valid_server_encoding(const char *name)
|
||||
{
|
||||
int enc;
|
||||
int enc;
|
||||
|
||||
if ((enc = pg_char_to_encoding(name)) < 0)
|
||||
return -1;
|
||||
|
||||
if (!PG_VALID_BE_ENCODING( enc))
|
||||
if (!PG_VALID_BE_ENCODING(enc))
|
||||
return -1;
|
||||
|
||||
return enc;
|
||||
@@ -162,12 +311,13 @@ pg_valid_server_encoding(const char *name)
|
||||
static char *
|
||||
clean_encoding_name(char *key, char *newkey)
|
||||
{
|
||||
char *p, *np;
|
||||
char *p,
|
||||
*np;
|
||||
|
||||
for(p=key, np=newkey; *p!='\0'; p++)
|
||||
for (p = key, np = newkey; *p != '\0'; p++)
|
||||
{
|
||||
if (isalnum((unsigned char) *p))
|
||||
*np++=tolower((unsigned char) *p);
|
||||
*np++ = tolower((unsigned char) *p);
|
||||
}
|
||||
*np = '\0';
|
||||
return newkey;
|
||||
@@ -180,15 +330,15 @@ clean_encoding_name(char *key, char *newkey)
|
||||
pg_encname *
|
||||
pg_char_to_encname_struct(const char *name)
|
||||
{
|
||||
unsigned int nel = pg_encname_tbl_sz;
|
||||
pg_encname *base = pg_encname_tbl,
|
||||
*last = base + nel - 1,
|
||||
*position;
|
||||
int result;
|
||||
unsigned int nel = pg_encname_tbl_sz;
|
||||
pg_encname *base = pg_encname_tbl,
|
||||
*last = base + nel - 1,
|
||||
*position;
|
||||
int result;
|
||||
char buff[NAMEDATALEN],
|
||||
*key;
|
||||
*key;
|
||||
|
||||
if(name==NULL || *name=='\0')
|
||||
if (name == NULL || *name == '\0')
|
||||
return NULL;
|
||||
|
||||
if (strlen(name) > NAMEDATALEN)
|
||||
@@ -241,6 +391,7 @@ Datum
|
||||
PG_char_to_encoding(PG_FUNCTION_ARGS)
|
||||
{
|
||||
Name s = PG_GETARG_NAME(0);
|
||||
|
||||
PG_RETURN_INT32(pg_char_to_encoding(NameStr(*s)));
|
||||
}
|
||||
#endif
|
||||
@@ -250,8 +401,9 @@ pg_encoding_to_char(int encoding)
|
||||
{
|
||||
if (PG_VALID_ENCODING(encoding))
|
||||
{
|
||||
pg_enc2name *p = &pg_enc2name_tbl[ encoding ];
|
||||
Assert( encoding == p->encoding );
|
||||
pg_enc2name *p = &pg_enc2name_tbl[encoding];
|
||||
|
||||
Assert(encoding == p->encoding);
|
||||
return p->name;
|
||||
}
|
||||
return "";
|
||||
@@ -262,9 +414,8 @@ Datum
|
||||
PG_encoding_to_char(PG_FUNCTION_ARGS)
|
||||
{
|
||||
int32 encoding = PG_GETARG_INT32(0);
|
||||
const char *encoding_name = pg_encoding_to_char(encoding);
|
||||
const char *encoding_name = pg_encoding_to_char(encoding);
|
||||
|
||||
return DirectFunctionCall1(namein, CStringGetDatum(encoding_name));
|
||||
}
|
||||
#endif
|
||||
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
* client encoding and server internal encoding.
|
||||
* (currently mule internal code (mic) is used)
|
||||
* Tatsuo Ishii
|
||||
* $Id: mbutils.c,v 1.24 2001/10/12 02:08:34 ishii Exp $
|
||||
* $Id: mbutils.c,v 1.25 2001/10/25 05:49:51 momjian Exp $
|
||||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
@@ -12,7 +12,7 @@
|
||||
#include "utils/builtins.h"
|
||||
|
||||
/*
|
||||
* We handle for actual FE and BE encoding setting encoding-identificator
|
||||
* We handle for actual FE and BE encoding setting encoding-identificator
|
||||
* and encoding-name too. It prevent searching and conversion from encoding
|
||||
* to encoding name in getdatabaseencoding() and other routines.
|
||||
*
|
||||
@@ -21,13 +21,13 @@
|
||||
*
|
||||
* Karel Zak (Aug 2001)
|
||||
*/
|
||||
static pg_enc2name *ClientEncoding = &pg_enc2name_tbl[ PG_SQL_ASCII ];
|
||||
static pg_enc2name *DatabaseEncoding = &pg_enc2name_tbl[ PG_SQL_ASCII ];
|
||||
static pg_enc2name *ClientEncoding = &pg_enc2name_tbl[PG_SQL_ASCII];
|
||||
static pg_enc2name *DatabaseEncoding = &pg_enc2name_tbl[PG_SQL_ASCII];
|
||||
|
||||
static to_mic_converter client_to_mic; /* something to MIC */
|
||||
static from_mic_converter client_from_mic; /* MIC to something */
|
||||
static from_mic_converter client_from_mic; /* MIC to something */
|
||||
static to_mic_converter server_to_mic; /* something to MIC */
|
||||
static from_mic_converter server_from_mic; /* MIC to something */
|
||||
static from_mic_converter server_from_mic; /* MIC to something */
|
||||
|
||||
/*
|
||||
* find encoding table entry by encoding
|
||||
@@ -37,8 +37,8 @@ pg_get_enconv_by_encoding(int encoding)
|
||||
{
|
||||
if (PG_VALID_ENCODING(encoding))
|
||||
{
|
||||
Assert((&pg_enconv_tbl[ encoding ])->encoding == encoding);
|
||||
return &pg_enconv_tbl[ encoding ];
|
||||
Assert((&pg_enconv_tbl[encoding])->encoding == encoding);
|
||||
return &pg_enconv_tbl[encoding];
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
@@ -113,7 +113,7 @@ pg_find_encoding_converters(int src, int dest,
|
||||
int
|
||||
pg_set_client_encoding(int encoding)
|
||||
{
|
||||
int current_server_encoding = DatabaseEncoding->encoding;
|
||||
int current_server_encoding = DatabaseEncoding->encoding;
|
||||
|
||||
if (!PG_VALID_FE_ENCODING(encoding))
|
||||
return (-1);
|
||||
@@ -121,7 +121,7 @@ pg_set_client_encoding(int encoding)
|
||||
if (pg_find_encoding_converters(encoding, current_server_encoding, &client_to_mic, &server_from_mic) < 0)
|
||||
return (-1);
|
||||
|
||||
ClientEncoding = &pg_enc2name_tbl[ encoding ];
|
||||
ClientEncoding = &pg_enc2name_tbl[encoding];
|
||||
|
||||
Assert(ClientEncoding->encoding == encoding);
|
||||
|
||||
@@ -162,7 +162,7 @@ pg_get_client_encoding_name(void)
|
||||
* function). Another case is you have direct-conversion function from
|
||||
* src to dest. In this case either src_to_mic or dest_from_mic could
|
||||
* be set to 0 also.
|
||||
*
|
||||
*
|
||||
* Note that If src or dest is UNICODE, we have to do
|
||||
* direct-conversion, since we don't support conversion bwteen UNICODE
|
||||
* and MULE_INTERNAL, we cannot go through MULE_INTERNAL.
|
||||
@@ -175,7 +175,7 @@ pg_get_client_encoding_name(void)
|
||||
* to determine whether to pfree the result or not!
|
||||
*
|
||||
* Note: we assume that conversion cannot cause more than a 4-to-1 growth
|
||||
* in the length of the string --- is this enough? */
|
||||
* in the length of the string --- is this enough? */
|
||||
|
||||
unsigned char *
|
||||
pg_do_encoding_conversion(unsigned char *src, int len,
|
||||
@@ -212,32 +212,33 @@ pg_do_encoding_conversion(unsigned char *src, int len,
|
||||
Datum
|
||||
pg_convert(PG_FUNCTION_ARGS)
|
||||
{
|
||||
text *string = PG_GETARG_TEXT_P(0);
|
||||
Name s = PG_GETARG_NAME(1);
|
||||
int encoding = pg_char_to_encoding(NameStr(*s));
|
||||
int db_encoding = DatabaseEncoding->encoding;
|
||||
text *string = PG_GETARG_TEXT_P(0);
|
||||
Name s = PG_GETARG_NAME(1);
|
||||
int encoding = pg_char_to_encoding(NameStr(*s));
|
||||
int db_encoding = DatabaseEncoding->encoding;
|
||||
to_mic_converter src;
|
||||
from_mic_converter dest;
|
||||
unsigned char *result;
|
||||
text *retval;
|
||||
unsigned char *result;
|
||||
text *retval;
|
||||
|
||||
if (encoding < 0)
|
||||
elog(ERROR, "Invalid encoding name %s", NameStr(*s));
|
||||
elog(ERROR, "Invalid encoding name %s", NameStr(*s));
|
||||
|
||||
if (pg_find_encoding_converters(db_encoding, encoding, &src, &dest) < 0)
|
||||
{
|
||||
char *encoding_name = (char *)pg_encoding_to_char(db_encoding);
|
||||
elog(ERROR, "Conversion from %s to %s is not possible", NameStr(*s), encoding_name);
|
||||
char *encoding_name = (char *) pg_encoding_to_char(db_encoding);
|
||||
|
||||
elog(ERROR, "Conversion from %s to %s is not possible", NameStr(*s), encoding_name);
|
||||
}
|
||||
|
||||
result = pg_do_encoding_conversion(VARDATA(string), VARSIZE(string)-VARHDRSZ,
|
||||
src, dest);
|
||||
result = pg_do_encoding_conversion(VARDATA(string), VARSIZE(string) - VARHDRSZ,
|
||||
src, dest);
|
||||
if (result == NULL)
|
||||
elog(ERROR, "Encoding conversion failed");
|
||||
elog(ERROR, "Encoding conversion failed");
|
||||
|
||||
retval = DatumGetTextP(DirectFunctionCall1(textin, CStringGetDatum(result)));
|
||||
if (result != (unsigned char *)VARDATA(string))
|
||||
pfree(result);
|
||||
if (result != (unsigned char *) VARDATA(string))
|
||||
pfree(result);
|
||||
|
||||
/* free memory if allocated by the toaster */
|
||||
PG_FREE_IF_COPY(string, 0);
|
||||
@@ -253,35 +254,35 @@ pg_convert(PG_FUNCTION_ARGS)
|
||||
Datum
|
||||
pg_convert2(PG_FUNCTION_ARGS)
|
||||
{
|
||||
text *string = PG_GETARG_TEXT_P(0);
|
||||
char *src_encoding_name = NameStr(*PG_GETARG_NAME(1));
|
||||
int src_encoding = pg_char_to_encoding(src_encoding_name);
|
||||
char *dest_encoding_name = NameStr(*PG_GETARG_NAME(2));
|
||||
int dest_encoding = pg_char_to_encoding(dest_encoding_name);
|
||||
text *string = PG_GETARG_TEXT_P(0);
|
||||
char *src_encoding_name = NameStr(*PG_GETARG_NAME(1));
|
||||
int src_encoding = pg_char_to_encoding(src_encoding_name);
|
||||
char *dest_encoding_name = NameStr(*PG_GETARG_NAME(2));
|
||||
int dest_encoding = pg_char_to_encoding(dest_encoding_name);
|
||||
to_mic_converter src;
|
||||
from_mic_converter dest;
|
||||
unsigned char *result;
|
||||
text *retval;
|
||||
unsigned char *result;
|
||||
text *retval;
|
||||
|
||||
if (src_encoding < 0)
|
||||
elog(ERROR, "Invalid source encoding name %s", src_encoding_name);
|
||||
elog(ERROR, "Invalid source encoding name %s", src_encoding_name);
|
||||
if (dest_encoding < 0)
|
||||
elog(ERROR, "Invalid destination encoding name %s", dest_encoding_name);
|
||||
elog(ERROR, "Invalid destination encoding name %s", dest_encoding_name);
|
||||
|
||||
if (pg_find_encoding_converters(src_encoding, dest_encoding, &src, &dest) < 0)
|
||||
{
|
||||
elog(ERROR, "Conversion from %s to %s is not possible",
|
||||
src_encoding_name, dest_encoding_name);
|
||||
elog(ERROR, "Conversion from %s to %s is not possible",
|
||||
src_encoding_name, dest_encoding_name);
|
||||
}
|
||||
|
||||
result = pg_do_encoding_conversion(VARDATA(string), VARSIZE(string)-VARHDRSZ,
|
||||
src, dest);
|
||||
result = pg_do_encoding_conversion(VARDATA(string), VARSIZE(string) - VARHDRSZ,
|
||||
src, dest);
|
||||
if (result == NULL)
|
||||
elog(ERROR, "Encoding conversion failed");
|
||||
elog(ERROR, "Encoding conversion failed");
|
||||
|
||||
retval = DatumGetTextP(DirectFunctionCall1(textin, CStringGetDatum(result)));
|
||||
if (result != (unsigned char *)VARDATA(string))
|
||||
pfree(result);
|
||||
if (result != (unsigned char *) VARDATA(string))
|
||||
pfree(result);
|
||||
|
||||
/* free memory if allocated by the toaster */
|
||||
PG_FREE_IF_COPY(string, 0);
|
||||
@@ -309,7 +310,7 @@ pg_client_to_server(unsigned char *s, int len)
|
||||
Assert(ClientEncoding);
|
||||
|
||||
if (ClientEncoding->encoding == DatabaseEncoding->encoding)
|
||||
return s;
|
||||
return s;
|
||||
|
||||
return pg_do_encoding_conversion(s, len, client_to_mic, server_from_mic);
|
||||
}
|
||||
@@ -341,23 +342,23 @@ pg_server_to_client(unsigned char *s, int len)
|
||||
|
||||
/* convert a multi-byte string to a wchar */
|
||||
int
|
||||
pg_mb2wchar(const unsigned char *from, pg_wchar * to)
|
||||
pg_mb2wchar(const unsigned char *from, pg_wchar *to)
|
||||
{
|
||||
return (*pg_wchar_table[ DatabaseEncoding->encoding ].mb2wchar_with_len) (from, to, strlen(from));
|
||||
return (*pg_wchar_table[DatabaseEncoding->encoding].mb2wchar_with_len) (from, to, strlen(from));
|
||||
}
|
||||
|
||||
/* convert a multi-byte string to a wchar with a limited length */
|
||||
int
|
||||
pg_mb2wchar_with_len(const unsigned char *from, pg_wchar * to, int len)
|
||||
pg_mb2wchar_with_len(const unsigned char *from, pg_wchar *to, int len)
|
||||
{
|
||||
return (*pg_wchar_table[ DatabaseEncoding->encoding ].mb2wchar_with_len) (from, to, len);
|
||||
return (*pg_wchar_table[DatabaseEncoding->encoding].mb2wchar_with_len) (from, to, len);
|
||||
}
|
||||
|
||||
/* returns the byte length of a multi-byte word */
|
||||
int
|
||||
pg_mblen(const unsigned char *mbstr)
|
||||
{
|
||||
return ((*pg_wchar_table[ DatabaseEncoding->encoding ].mblen) (mbstr));
|
||||
return ((*pg_wchar_table[DatabaseEncoding->encoding].mblen) (mbstr));
|
||||
}
|
||||
|
||||
/* returns the length (counted as a wchar) of a multi-byte string */
|
||||
@@ -447,7 +448,7 @@ SetDatabaseEncoding(int encoding)
|
||||
if (!PG_VALID_BE_ENCODING(encoding))
|
||||
elog(ERROR, "SetDatabaseEncoding(): invalid database encoding");
|
||||
|
||||
DatabaseEncoding = &pg_enc2name_tbl[ encoding ];
|
||||
DatabaseEncoding = &pg_enc2name_tbl[encoding];
|
||||
Assert(DatabaseEncoding->encoding == encoding);
|
||||
}
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
/*
|
||||
* conversion functions between pg_wchar and multi-byte streams.
|
||||
* Tatsuo Ishii
|
||||
* $Id: wchar.c,v 1.24 2001/10/15 01:19:15 ishii Exp $
|
||||
* $Id: wchar.c,v 1.25 2001/10/25 05:49:51 momjian Exp $
|
||||
*
|
||||
* WIN1250 client encoding updated by Pavel Behal
|
||||
*
|
||||
@@ -29,7 +29,7 @@
|
||||
* SQL/ASCII
|
||||
*/
|
||||
static int pg_ascii2wchar_with_len
|
||||
(const unsigned char *from, pg_wchar * to, int len)
|
||||
(const unsigned char *from, pg_wchar *to, int len)
|
||||
{
|
||||
int cnt = 0;
|
||||
|
||||
@@ -54,7 +54,7 @@ pg_ascii_mblen(const unsigned char *s)
|
||||
*/
|
||||
|
||||
static int pg_euc2wchar_with_len
|
||||
(const unsigned char *from, pg_wchar * to, int len)
|
||||
(const unsigned char *from, pg_wchar *to, int len)
|
||||
{
|
||||
int cnt = 0;
|
||||
|
||||
@@ -111,7 +111,7 @@ pg_euc_mblen(const unsigned char *s)
|
||||
* EUC_JP
|
||||
*/
|
||||
static int pg_eucjp2wchar_with_len
|
||||
(const unsigned char *from, pg_wchar * to, int len)
|
||||
(const unsigned char *from, pg_wchar *to, int len)
|
||||
{
|
||||
return (pg_euc2wchar_with_len(from, to, len));
|
||||
}
|
||||
@@ -126,7 +126,7 @@ pg_eucjp_mblen(const unsigned char *s)
|
||||
* EUC_KR
|
||||
*/
|
||||
static int pg_euckr2wchar_with_len
|
||||
(const unsigned char *from, pg_wchar * to, int len)
|
||||
(const unsigned char *from, pg_wchar *to, int len)
|
||||
{
|
||||
return (pg_euc2wchar_with_len(from, to, len));
|
||||
}
|
||||
@@ -141,7 +141,7 @@ pg_euckr_mblen(const unsigned char *s)
|
||||
* EUC_CN
|
||||
*/
|
||||
static int pg_euccn2wchar_with_len
|
||||
(const unsigned char *from, pg_wchar * to, int len)
|
||||
(const unsigned char *from, pg_wchar *to, int len)
|
||||
{
|
||||
int cnt = 0;
|
||||
|
||||
@@ -195,7 +195,7 @@ pg_euccn_mblen(const unsigned char *s)
|
||||
* EUC_TW
|
||||
*/
|
||||
static int pg_euctw2wchar_with_len
|
||||
(const unsigned char *from, pg_wchar * to, int len)
|
||||
(const unsigned char *from, pg_wchar *to, int len)
|
||||
{
|
||||
int cnt = 0;
|
||||
|
||||
@@ -257,7 +257,7 @@ pg_euctw_mblen(const unsigned char *s)
|
||||
* "from" not necessarily null terminated.
|
||||
*/
|
||||
static int
|
||||
pg_utf2wchar_with_len(const unsigned char *from, pg_wchar * to, int len)
|
||||
pg_utf2wchar_with_len(const unsigned char *from, pg_wchar *to, int len)
|
||||
{
|
||||
unsigned char c1,
|
||||
c2,
|
||||
@@ -325,7 +325,7 @@ pg_utf_mblen(const unsigned char *s)
|
||||
* "from" not necessarily null terminated.
|
||||
*/
|
||||
static int
|
||||
pg_mule2wchar_with_len(const unsigned char *from, pg_wchar * to, int len)
|
||||
pg_mule2wchar_with_len(const unsigned char *from, pg_wchar *to, int len)
|
||||
{
|
||||
int cnt = 0;
|
||||
|
||||
@@ -395,7 +395,7 @@ pg_mule_mblen(const unsigned char *s)
|
||||
* ISO8859-1
|
||||
*/
|
||||
static int
|
||||
pg_latin12wchar_with_len(const unsigned char *from, pg_wchar * to, int len)
|
||||
pg_latin12wchar_with_len(const unsigned char *from, pg_wchar *to, int len)
|
||||
{
|
||||
int cnt = 0;
|
||||
|
||||
@@ -458,33 +458,33 @@ pg_big5_mblen(const unsigned char *s)
|
||||
}
|
||||
|
||||
pg_wchar_tbl pg_wchar_table[] = {
|
||||
{pg_ascii2wchar_with_len, pg_ascii_mblen, 1}, /* 0; PG_SQL_ASCII */
|
||||
{pg_eucjp2wchar_with_len, pg_eucjp_mblen, 3}, /* 1; PG_EUC_JP */
|
||||
{pg_euccn2wchar_with_len, pg_euccn_mblen, 3}, /* 2; PG_EUC_CN */
|
||||
{pg_euckr2wchar_with_len, pg_euckr_mblen, 3}, /* 3; PG_EUC_KR */
|
||||
{pg_euctw2wchar_with_len, pg_euctw_mblen, 3}, /* 4; PG_EUC_TW */
|
||||
{pg_ascii2wchar_with_len, pg_ascii_mblen, 1}, /* 0; PG_SQL_ASCII */
|
||||
{pg_eucjp2wchar_with_len, pg_eucjp_mblen, 3}, /* 1; PG_EUC_JP */
|
||||
{pg_euccn2wchar_with_len, pg_euccn_mblen, 3}, /* 2; PG_EUC_CN */
|
||||
{pg_euckr2wchar_with_len, pg_euckr_mblen, 3}, /* 3; PG_EUC_KR */
|
||||
{pg_euctw2wchar_with_len, pg_euctw_mblen, 3}, /* 4; PG_EUC_TW */
|
||||
{pg_utf2wchar_with_len, pg_utf_mblen, 3}, /* 5; PG_UNICODE */
|
||||
{pg_mule2wchar_with_len, pg_mule_mblen, 3}, /* 6; PG_MULE_INTERNAL */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 7; PG_LATIN1 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 8; PG_LATIN2 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 9; PG_LATIN3 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 10; PG_LATIN4 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 11; PG_LATIN5 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 12; PG_KOI8 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 13; PG_WIN1251 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 14; PG_ALT */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 15; ISO-8859-5 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 16; ISO-8859-6 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 17; ISO-8859-7 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 18; ISO-8859-8 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 19; ISO-8859-10 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 20; ISO-8859-13 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 21; ISO-8859-14 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 22; ISO-8859-15 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 23; ISO-8859-16 */
|
||||
{0, pg_sjis_mblen, 2}, /* 24; PG_SJIS */
|
||||
{0, pg_big5_mblen, 2}, /* 25; PG_BIG5 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1} /* 26; PG_WIN1250 */
|
||||
{pg_mule2wchar_with_len, pg_mule_mblen, 3}, /* 6; PG_MULE_INTERNAL */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 7; PG_LATIN1 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 8; PG_LATIN2 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 9; PG_LATIN3 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 10; PG_LATIN4 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 11; PG_LATIN5 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 12; PG_KOI8 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 13; PG_WIN1251 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 14; PG_ALT */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 15; ISO-8859-5 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 16; ISO-8859-6 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 17; ISO-8859-7 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 18; ISO-8859-8 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 19; ISO-8859-10 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 20; ISO-8859-13 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 21; ISO-8859-14 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 22; ISO-8859-15 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1}, /* 23; ISO-8859-16 */
|
||||
{0, pg_sjis_mblen, 2}, /* 24; PG_SJIS */
|
||||
{0, pg_big5_mblen, 2}, /* 25; PG_BIG5 */
|
||||
{pg_latin12wchar_with_len, pg_latin1_mblen, 1} /* 26; PG_WIN1250 */
|
||||
};
|
||||
|
||||
/* returns the byte length of a word for mule internal code */
|
||||
@@ -502,9 +502,9 @@ pg_encoding_mblen(int encoding, const unsigned char *mbstr)
|
||||
{
|
||||
Assert(PG_VALID_ENCODING(encoding));
|
||||
|
||||
return( (encoding >= 0 &&
|
||||
encoding < sizeof(pg_wchar_table)/sizeof(pg_wchar_tbl)) ?
|
||||
((*pg_wchar_table[encoding].mblen) (mbstr)) :
|
||||
return ((encoding >= 0 &&
|
||||
encoding < sizeof(pg_wchar_table) / sizeof(pg_wchar_tbl)) ?
|
||||
((*pg_wchar_table[encoding].mblen) (mbstr)) :
|
||||
((*pg_wchar_table[PG_SQL_ASCII].mblen) (mbstr)));
|
||||
}
|
||||
|
||||
@@ -531,59 +531,62 @@ pg_encoding_max_length(int encoding)
|
||||
char *
|
||||
pg_verifymbstr(const unsigned char *mbstr, int len)
|
||||
{
|
||||
int l;
|
||||
int i, j;
|
||||
static char buf[256];
|
||||
int slen = 0;
|
||||
int l;
|
||||
int i,
|
||||
j;
|
||||
static char buf[256];
|
||||
int slen = 0;
|
||||
|
||||
/* we do not check single byte encodings */
|
||||
if (pg_database_encoding_max_length() <= 1)
|
||||
return NULL;
|
||||
return NULL;
|
||||
|
||||
while (len > 0 && *mbstr)
|
||||
{
|
||||
/* special UTF-8 check */
|
||||
if (GetDatabaseEncoding() == PG_UTF8 &&
|
||||
(*mbstr & 0xf8) == 0xf0)
|
||||
(*mbstr & 0xf8) == 0xf0)
|
||||
{
|
||||
snprintf(buf, sizeof(buf), "Unicode >= 0x10000 is not supoorted");
|
||||
return(buf);
|
||||
snprintf(buf, sizeof(buf), "Unicode >= 0x10000 is not supoorted");
|
||||
return (buf);
|
||||
}
|
||||
|
||||
|
||||
l = pg_mblen(mbstr);
|
||||
|
||||
/* multi-byte letter? */
|
||||
if (l > 1)
|
||||
{
|
||||
for (i=1;i<l;i++)
|
||||
{
|
||||
if (i > len || *(mbstr+i) == '\0' ||
|
||||
/* we assume that every muti-byte letter
|
||||
* consists of bytes being the 8th bit set
|
||||
*/
|
||||
((*(mbstr+i) & 0x80) == 0))
|
||||
for (i = 1; i < l; i++)
|
||||
{
|
||||
int remains = sizeof(buf);
|
||||
char *p = buf;
|
||||
if (i > len || *(mbstr + i) == '\0' ||
|
||||
|
||||
slen = snprintf(p, remains, "Invalid %s character sequence found (0x",
|
||||
GetDatabaseEncodingName());
|
||||
p += slen;
|
||||
remains -= slen;
|
||||
/*
|
||||
* we assume that every muti-byte letter consists of bytes
|
||||
* being the 8th bit set
|
||||
*/
|
||||
((*(mbstr + i) & 0x80) == 0))
|
||||
{
|
||||
int remains = sizeof(buf);
|
||||
char *p = buf;
|
||||
|
||||
i = ((*(mbstr+i) & 0x80) == 0)?l:i;
|
||||
slen = snprintf(p, remains, "Invalid %s character sequence found (0x",
|
||||
GetDatabaseEncodingName());
|
||||
p += slen;
|
||||
remains -= slen;
|
||||
|
||||
for (j=0;j<i;j++)
|
||||
{
|
||||
slen = snprintf(p, remains, "%02x",
|
||||
*(mbstr+j));
|
||||
p += slen;
|
||||
remains -= slen;
|
||||
}
|
||||
snprintf(p, remains, ")");
|
||||
return(buf);
|
||||
i = ((*(mbstr + i) & 0x80) == 0) ? l : i;
|
||||
|
||||
for (j = 0; j < i; j++)
|
||||
{
|
||||
slen = snprintf(p, remains, "%02x",
|
||||
*(mbstr + j));
|
||||
p += slen;
|
||||
remains -= slen;
|
||||
}
|
||||
snprintf(p, remains, ")");
|
||||
return (buf);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
len -= l;
|
||||
mbstr += l;
|
||||
@@ -599,5 +602,4 @@ pg_database_encoding_max_length(void)
|
||||
{
|
||||
return pg_wchar_table[GetDatabaseEncoding()].maxmblen;
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
@@ -43,7 +43,7 @@ pg_char_and_wchar_strcmp(s1, s2)
|
||||
register const char *s1;
|
||||
register const pg_wchar *s2;
|
||||
{
|
||||
while ((pg_wchar) * s1 == *s2++)
|
||||
while ((pg_wchar) *s1 == *s2++)
|
||||
if (*s1++ == 0)
|
||||
return 0;
|
||||
return *(const unsigned char *) s1 - *(const pg_wchar *) (s2 - 1);
|
||||
|
||||
Reference in New Issue
Block a user