From 1ff1ff869ca7730b272c33765f1c7e1cff90c8a1 Mon Sep 17 00:00:00 2001 From: unknown Date: Mon, 1 Oct 2007 15:35:42 +0500 Subject: Bug#30315 Character sets: insertion of euckr code value 0xa141 fails Problem: some valid euc-kr characters were rejected because condition checking multi-byte tail didn't allow multi-byte characters having the second byte in the ranges [0x41..0x5A] and [0x61..0x7A]. Fix: allow these byte ranges for mb tails mysql-test/r/ctype_euckr.result: Adding tests mysql-test/t/ctype_euckr.test: Adding tests strings/ctype-euc_kr.c: Fixing wrong tail character pattern --- strings/ctype-euc_kr.c | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) (limited to 'strings') diff --git a/strings/ctype-euc_kr.c b/strings/ctype-euc_kr.c index abaa8f1a516..1aaf65c98b3 100644 --- a/strings/ctype-euc_kr.c +++ b/strings/ctype-euc_kr.c @@ -179,20 +179,39 @@ static uchar NEAR sort_order_euc_kr[]= /* Support for Korean(EUC_KR) characters, by powerm90@tinc.co.kr and mrpark@tinc.co.kr */ -#define iseuc_kr(c) ((0xa1<=(uchar)(c) && (uchar)(c)<=0xfe)) +/* + Unicode mapping is done according to: + ftp://ftp.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/KSC/KSC5601.TXT + + Valid multi-byte characters: + + [A1..FE][41..5A,61..7A,81..FE] + + Note, 0x5C is not a valid MB tail, + so escape_with_backslash_is_dangerous is not set. +*/ + +#define iseuc_kr_head(c) ((0xa1<=(uchar)(c) && (uchar)(c)<=0xfe)) + +#define iseuc_kr_tail1(c) ((uchar) (c) >= 0x41 && (uchar) (c) <= 0x5A) +#define iseuc_kr_tail2(c) ((uchar) (c) >= 0x61 && (uchar) (c) <= 0x7A) +#define iseuc_kr_tail3(c) ((uchar) (c) >= 0x81 && (uchar) (c) <= 0xFE) +#define iseuc_kr_tail(c) (iseuc_kr_tail1(c) || \ + iseuc_kr_tail2(c) || \ + iseuc_kr_tail3(c)) static int ismbchar_euc_kr(CHARSET_INFO *cs __attribute__((unused)), const char* p, const char *e) { return ((*(uchar*)(p)<0x80)? 0:\ - iseuc_kr(*(p)) && (e)-(p)>1 && iseuc_kr(*((p)+1))? 2:\ + iseuc_kr_head(*(p)) && (e)-(p)>1 && iseuc_kr_tail(*((p)+1))? 2:\ 0); } static int mbcharlen_euc_kr(CHARSET_INFO *cs __attribute__((unused)),uint c) { - return (iseuc_kr(c) ? 2 : 1); + return (iseuc_kr_head(c) ? 2 : 1); } @@ -8653,7 +8672,7 @@ my_well_formed_len_euckr(CHARSET_INFO *cs __attribute__((unused)), /* Single byte ascii character */ b++; } - else if (b < emb && iseuc_kr(*b) && iseuc_kr(b[1])) + else if (b < emb && iseuc_kr_head(*b) && iseuc_kr_tail(b[1])) { /* Double byte character */ b+= 2; -- cgit v1.2.1