diff options
| author | bar@bar.myoffice.izhnet.ru <> | 2007-10-30 12:21:44 +0400 |
|---|---|---|
| committer | bar@bar.myoffice.izhnet.ru <> | 2007-10-30 12:21:44 +0400 |
| commit | 628b46288195f5b13608a810f4b83036b5800cfb (patch) | |
| tree | 8d498b79e065eb55a66f3846f2a97454b8615e18 /strings | |
| parent | 53b1c3a29941634fb77cb20a62cc0f1acfc8d05d (diff) | |
| parent | 87fd52cd8ca88aefc928101f60e27474c873d788 (diff) | |
| download | mariadb-git-628b46288195f5b13608a810f4b83036b5800cfb.tar.gz | |
Merge abarkov@bk-internal.mysql.com:/home/bk/mysql-5.0
into mysql.com:/home/bar/mysql-work/mysql-5.0-rpl-merge
Diffstat (limited to 'strings')
| -rw-r--r-- | strings/ctype-euc_kr.c | 27 |
1 files changed, 23 insertions, 4 deletions
diff --git a/strings/ctype-euc_kr.c b/strings/ctype-euc_kr.c index 0a67d4c0a54..511a81f0cd4 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; |