From febd60bf5db947ff3ebc0ffa8097f2b7a7629611 Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Mon, 15 Oct 2007 22:46:27 +0000 Subject: [PATCH] Fix pg_wchar_table[] to match revised ordering of the encoding ID enum. Add some comments so hopefully the next poor sod doesn't fall into the same trap. (Wrong comments are worse than none at all...) --- src/backend/utils/mb/encnames.c | 4 +- src/backend/utils/mb/wchar.c | 93 +++++++++++++++------------------ src/include/mb/pg_wchar.h | 7 +-- 3 files changed, 49 insertions(+), 55 deletions(-) diff --git a/src/backend/utils/mb/encnames.c b/src/backend/utils/mb/encnames.c index f7ef85511c..9e8f210240 100644 --- a/src/backend/utils/mb/encnames.c +++ b/src/backend/utils/mb/encnames.c @@ -2,7 +2,7 @@ * Encoding names and routines for work with it. All * in this file is shared bedween FE and BE. * - * $PostgreSQL: pgsql/src/backend/utils/mb/encnames.c,v 1.35 2007/10/13 20:18:41 tgl Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/encnames.c,v 1.36 2007/10/15 22:46:27 tgl Exp $ */ #ifdef FRONTEND #include "postgres_fe.h" @@ -294,7 +294,7 @@ sizeof(pg_encname_tbl) / sizeof(pg_encname_tbl[0]) - 1; /* ---------- * These are "official" encoding names. - * XXX must be sorted by the same order as pg_enc type (see mb/pg_wchar.h) + * XXX must be sorted by the same order as enum pg_enc (in mb/pg_wchar.h) * ---------- */ pg_enc2name pg_enc2name_tbl[] = diff --git a/src/backend/utils/mb/wchar.c b/src/backend/utils/mb/wchar.c index 2c98f4b476..dd5cf210f9 100644 --- a/src/backend/utils/mb/wchar.c +++ b/src/backend/utils/mb/wchar.c @@ -1,7 +1,7 @@ /* * conversion functions between pg_wchar and multibyte streams. * Tatsuo Ishii - * $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.64 2007/09/18 17:41:17 adunstan Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.65 2007/10/15 22:46:27 tgl Exp $ * */ /* can be used in either frontend or backend */ @@ -38,8 +38,7 @@ * SQL/ASCII */ static int - pg_ascii2wchar_with_len - (const unsigned char *from, pg_wchar *to, int len) +pg_ascii2wchar_with_len(const unsigned char *from, pg_wchar *to, int len) { int cnt = 0; @@ -73,8 +72,8 @@ pg_ascii_dsplen(const unsigned char *s) /* * EUC */ -static int pg_euc2wchar_with_len - (const unsigned char *from, pg_wchar *to, int len) +static int +pg_euc2wchar_with_len(const unsigned char *from, pg_wchar *to, int len) { int cnt = 0; @@ -148,8 +147,8 @@ pg_euc_dsplen(const unsigned char *s) /* * EUC_JP */ -static int pg_eucjp2wchar_with_len - (const unsigned char *from, pg_wchar *to, int len) +static int +pg_eucjp2wchar_with_len(const unsigned char *from, pg_wchar *to, int len) { return pg_euc2wchar_with_len(from, to, len); } @@ -179,8 +178,8 @@ pg_eucjp_dsplen(const unsigned char *s) /* * EUC_KR */ -static int pg_euckr2wchar_with_len - (const unsigned char *from, pg_wchar *to, int len) +static int +pg_euckr2wchar_with_len(const unsigned char *from, pg_wchar *to, int len) { return pg_euc2wchar_with_len(from, to, len); } @@ -201,8 +200,8 @@ pg_euckr_dsplen(const unsigned char *s) * EUC_CN * */ -static int pg_euccn2wchar_with_len - (const unsigned char *from, pg_wchar *to, int len) +static int +pg_euccn2wchar_with_len(const unsigned char *from, pg_wchar *to, int len) { int cnt = 0; @@ -268,8 +267,8 @@ pg_euccn_dsplen(const unsigned char *s) * EUC_TW * */ -static int pg_euctw2wchar_with_len - (const unsigned char *from, pg_wchar *to, int len) +static int +pg_euctw2wchar_with_len(const unsigned char *from, pg_wchar *to, int len) { int cnt = 0; @@ -343,12 +342,6 @@ pg_euctw_dsplen(const unsigned char *s) /* * JOHAB */ -static int -pg_johab2wchar_with_len(const unsigned char *from, pg_wchar *to, int len) -{ - return pg_euc2wchar_with_len(from, to, len); -} - static int pg_johab_mblen(const unsigned char *s) { @@ -1307,6 +1300,7 @@ pg_utf8_islegal(const unsigned char *source, int length) /* *------------------------------------------------------------------- * encoding info table + * XXX must be sorted by the same order as enum pg_enc (in mb/pg_wchar.h) *------------------------------------------------------------------- */ pg_wchar_tbl pg_wchar_table[] = { @@ -1315,41 +1309,41 @@ pg_wchar_tbl pg_wchar_table[] = { {pg_euccn2wchar_with_len, pg_euccn_mblen, pg_euccn_dsplen, pg_euccn_verifier, 2}, /* 2; PG_EUC_CN */ {pg_euckr2wchar_with_len, pg_euckr_mblen, pg_euckr_dsplen, pg_euckr_verifier, 3}, /* 3; PG_EUC_KR */ {pg_euctw2wchar_with_len, pg_euctw_mblen, pg_euctw_dsplen, pg_euctw_verifier, 4}, /* 4; PG_EUC_TW */ - {pg_utf2wchar_with_len, pg_utf_mblen, pg_utf_dsplen, pg_utf8_verifier, 4}, /* 5; PG_UTF8 */ - {pg_mule2wchar_with_len, pg_mule_mblen, pg_mule_dsplen, pg_mule_verifier, 4}, /* 6; PG_MULE_INTERNAL */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 7; PG_LATIN1 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 8; PG_LATIN2 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 9; PG_LATIN3 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 10; PG_LATIN4 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 11; PG_LATIN5 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 12; PG_LATIN6 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 13; PG_LATIN7 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 14; PG_LATIN8 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 15; PG_LATIN9 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 16; PG_LATIN10 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 17; PG_WIN1256 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 18; PG_WIN1258 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 19; PG_WIN874 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 21; PG_KOI8 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 22; PG_WIN1251 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 23; PG_WIN1252 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 24; PG_WIN866 */ + {pg_eucjp2wchar_with_len, pg_eucjp_mblen, pg_eucjp_dsplen, pg_eucjp_verifier, 3}, /* 5; PG_EUC_JIS_2004 */ + {pg_utf2wchar_with_len, pg_utf_mblen, pg_utf_dsplen, pg_utf8_verifier, 4}, /* 6; PG_UTF8 */ + {pg_mule2wchar_with_len, pg_mule_mblen, pg_mule_dsplen, pg_mule_verifier, 4}, /* 7; PG_MULE_INTERNAL */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 8; PG_LATIN1 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 9; PG_LATIN2 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 10; PG_LATIN3 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 11; PG_LATIN4 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 12; PG_LATIN5 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 13; PG_LATIN6 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 14; PG_LATIN7 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 15; PG_LATIN8 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 16; PG_LATIN9 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 17; PG_LATIN10 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 18; PG_WIN1256 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 19; PG_WIN1258 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 20; PG_WIN866 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 21; PG_WIN874 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 22; PG_KOI8R */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 23; PG_WIN1251 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 24; PG_WIN1252 */ {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 25; ISO-8859-5 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 25; ISO-8859-6 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 26; ISO-8859-7 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 27; ISO-8859-8 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 28; PG_WIN1250 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 29; PG_WIN1253 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 30; PG_WIN1254 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 31; PG_WIN1255 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 32; PG_WIN1257 */ - {pg_eucjp2wchar_with_len, pg_eucjp_mblen, pg_eucjp_dsplen, pg_eucjp_verifier, 3}, /* 33; PG_EUC_JIS_2004 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 26; ISO-8859-6 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 27; ISO-8859-7 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 28; ISO-8859-8 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 29; PG_WIN1250 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 30; PG_WIN1253 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 31; PG_WIN1254 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 32; PG_WIN1255 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 33; PG_WIN1257 */ {0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifier, 2}, /* 34; PG_SJIS */ {0, pg_big5_mblen, pg_big5_dsplen, pg_big5_verifier, 2}, /* 35; PG_BIG5 */ {0, pg_gbk_mblen, pg_gbk_dsplen, pg_gbk_verifier, 2}, /* 36; PG_GBK */ {0, pg_uhc_mblen, pg_uhc_dsplen, pg_uhc_verifier, 2}, /* 37; PG_UHC */ - {pg_johab2wchar_with_len, pg_johab_mblen, pg_johab_dsplen, pg_johab_verifier, 3}, /* 38; PG_JOHAB */ - {0, pg_gb18030_mblen, pg_gb18030_dsplen, pg_gb18030_verifier, 4}, /* 39; PG_GB18030 */ + {0, pg_gb18030_mblen, pg_gb18030_dsplen, pg_gb18030_verifier, 4}, /* 38; PG_GB18030 */ + {0, pg_johab_mblen, pg_johab_dsplen, pg_johab_verifier, 3}, /* 39; PG_JOHAB */ {0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifier, 2} /* 40; PG_SHIFT_JIS_2004 */ }; @@ -1440,7 +1434,6 @@ pg_verifymbstr(const char *mbstr, int len, bool noError) /* * Verify mbstr to make sure that it is validly encoded in the specified * encoding. - * */ bool pg_verify_mbstr(int encoding, const char *mbstr, int len, bool noError) diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 7660a7d585..34c1ec1d18 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -6,7 +6,7 @@ * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California * - * $PostgreSQL: pgsql/src/include/mb/pg_wchar.h,v 1.74 2007/10/13 20:18:41 tgl Exp $ + * $PostgreSQL: pgsql/src/include/mb/pg_wchar.h,v 1.75 2007/10/15 22:46:27 tgl Exp $ * * NOTES * This is used both by the backend and by libpq, but should not be @@ -152,8 +152,9 @@ typedef unsigned int pg_wchar; /* * PostgreSQL encoding identifiers * - * WARNING: the order of this table must be same as order - * in the pg_enc2name[] (mb/encnames.c) array! + * WARNING: the order of this enum must be same as order of entries + * in the pg_enc2name_tbl[] array (in mb/encnames.c), and + * in the pg_wchar_table[] array (in mb/wchar.c)! * * If you add some encoding don't forget to check * PG_ENCODING_BE_LAST macro.