diff options
Diffstat (limited to 'src/port')
-rw-r--r-- | src/port/pgstrcasecmp.c | 125 | ||||
-rw-r--r-- | src/port/strcasecmp.c | 74 |
2 files changed, 125 insertions, 74 deletions
diff --git a/src/port/pgstrcasecmp.c b/src/port/pgstrcasecmp.c new file mode 100644 index 00000000000..6ac07804af4 --- /dev/null +++ b/src/port/pgstrcasecmp.c @@ -0,0 +1,125 @@ +/*------------------------------------------------------------------------- + * + * pgstrcasecmp.c + * Portable SQL-like case-independent comparisons and conversions. + * + * SQL99 specifies Unicode-aware case normalization, which we don't yet + * have the infrastructure for. Instead we use tolower() to provide a + * locale-aware translation. However, there are some locales where this + * is not right either (eg, Turkish may do strange things with 'i' and + * 'I'). Our current compromise is to use tolower() for characters with + * the high bit set, and use an ASCII-only downcasing for 7-bit + * characters. + * + * NB: this code should match downcase_truncate_identifier() in scansup.c. + * + * + * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group + * + * $PostgreSQL: pgsql/src/port/pgstrcasecmp.c,v 1.1 2004/05/07 00:24:59 tgl Exp $ + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include <ctype.h> + + +/* + * Case-independent comparison of two null-terminated strings. + */ +int +pg_strcasecmp(const char *s1, const char *s2) +{ + for (;;) + { + unsigned char ch1 = (unsigned char) *s1++; + unsigned char ch2 = (unsigned char) *s2++; + + if (ch1 != ch2) + { + if (ch1 >= 'A' && ch1 <= 'Z') + ch1 += 'a' - 'A'; + else if (ch1 >= 0x80 && isupper(ch1)) + ch1 = tolower(ch1); + + if (ch2 >= 'A' && ch2 <= 'Z') + ch2 += 'a' - 'A'; + else if (ch2 >= 0x80 && isupper(ch2)) + ch2 = tolower(ch2); + + if (ch1 != ch2) + return (int) ch1 - (int) ch2; + } + if (ch1 == 0) + break; + } + return 0; +} + +/* + * Case-independent comparison of two not-necessarily-null-terminated strings. + * At most n bytes will be examined from each string. + */ +int +pg_strncasecmp(const char *s1, const char *s2, size_t n) +{ + while (n-- > 0) + { + unsigned char ch1 = (unsigned char) *s1++; + unsigned char ch2 = (unsigned char) *s2++; + + if (ch1 != ch2) + { + if (ch1 >= 'A' && ch1 <= 'Z') + ch1 += 'a' - 'A'; + else if (ch1 >= 0x80 && isupper(ch1)) + ch1 = tolower(ch1); + + if (ch2 >= 'A' && ch2 <= 'Z') + ch2 += 'a' - 'A'; + else if (ch2 >= 0x80 && isupper(ch2)) + ch2 = tolower(ch2); + + if (ch1 != ch2) + return (int) ch1 - (int) ch2; + } + if (ch1 == 0) + break; + } + return 0; +} + +/* + * Fold a character to upper case. + * + * Unlike some versions of toupper(), this is safe to apply to characters + * that aren't upper case letters. Note however that the whole thing is + * a bit bogus for multibyte character sets. + */ +unsigned char +pg_toupper(unsigned char ch) +{ + if (ch >= 'a' && ch <= 'z') + ch += 'A' - 'a'; + else if (ch >= 0x80 && islower(ch)) + ch = toupper(ch); + return ch; +} + +/* + * Fold a character to lower case. + * + * Unlike some versions of tolower(), this is safe to apply to characters + * that aren't lower case letters. Note however that the whole thing is + * a bit bogus for multibyte character sets. + */ +unsigned char +pg_tolower(unsigned char ch) +{ + if (ch >= 'A' && ch <= 'Z') + ch += 'a' - 'A'; + else if (ch >= 0x80 && isupper(ch)) + ch = tolower(ch); + return ch; +} diff --git a/src/port/strcasecmp.c b/src/port/strcasecmp.c deleted file mode 100644 index a89a84019dd..00000000000 --- a/src/port/strcasecmp.c +++ /dev/null @@ -1,74 +0,0 @@ -/* $PostgreSQL: pgsql/src/port/strcasecmp.c,v 1.4 2003/11/29 22:41:31 pgsql Exp $ */ - -/* - * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group - * Portions Copyright (c) 1987 Regents of the University of California. - * All rights reserved. - * - * Redistribution and use in source and binary forms are permitted - * provided that this notice is preserved and that due credit is given - * to the University of California at Berkeley. The name of the University - * may not be used to endorse or promote products derived from this - * software without specific written prior permission. This software - * is provided ``as is'' without express or implied warranty. - */ - -#include <sys/types.h> -#include <string.h> - -/* - * This array is designed for mapping upper and lower case letter - * together for a case independent comparison. The mappings are - * based upon ascii character sequences. - */ -static unsigned char charmap[] = { - '\000', '\001', '\002', '\003', '\004', '\005', '\006', '\007', - '\010', '\011', '\012', '\013', '\014', '\015', '\016', '\017', - '\020', '\021', '\022', '\023', '\024', '\025', '\026', '\027', - '\030', '\031', '\032', '\033', '\034', '\035', '\036', '\037', - '\040', '\041', '\042', '\043', '\044', '\045', '\046', '\047', - '\050', '\051', '\052', '\053', '\054', '\055', '\056', '\057', - '\060', '\061', '\062', '\063', '\064', '\065', '\066', '\067', - '\070', '\071', '\072', '\073', '\074', '\075', '\076', '\077', - '\100', '\141', '\142', '\143', '\144', '\145', '\146', '\147', - '\150', '\151', '\152', '\153', '\154', '\155', '\156', '\157', - '\160', '\161', '\162', '\163', '\164', '\165', '\166', '\167', - '\170', '\171', '\172', '\133', '\134', '\135', '\136', '\137', - '\140', '\141', '\142', '\143', '\144', '\145', '\146', '\147', - '\150', '\151', '\152', '\153', '\154', '\155', '\156', '\157', - '\160', '\161', '\162', '\163', '\164', '\165', '\166', '\167', - '\170', '\171', '\172', '\173', '\174', '\175', '\176', '\177', - '\200', '\201', '\202', '\203', '\204', '\205', '\206', '\207', - '\210', '\211', '\212', '\213', '\214', '\215', '\216', '\217', - '\220', '\221', '\222', '\223', '\224', '\225', '\226', '\227', - '\230', '\231', '\232', '\233', '\234', '\235', '\236', '\237', - '\240', '\241', '\242', '\243', '\244', '\245', '\246', '\247', - '\250', '\251', '\252', '\253', '\254', '\255', '\256', '\257', - '\260', '\261', '\262', '\263', '\264', '\265', '\266', '\267', - '\270', '\271', '\272', '\273', '\274', '\275', '\276', '\277', - '\300', '\341', '\342', '\343', '\344', '\345', '\346', '\347', - '\350', '\351', '\352', '\353', '\354', '\355', '\356', '\357', - '\360', '\361', '\362', '\363', '\364', '\365', '\366', '\367', - '\370', '\371', '\372', '\333', '\334', '\335', '\336', '\337', - '\340', '\341', '\342', '\343', '\344', '\345', '\346', '\347', - '\350', '\351', '\352', '\353', '\354', '\355', '\356', '\357', - '\360', '\361', '\362', '\363', '\364', '\365', '\366', '\367', - '\370', '\371', '\372', '\373', '\374', '\375', '\376', '\377', -}; - -int -strcasecmp(char *s1, char *s2) -{ - unsigned char u1, - u2; - - for (;;) - { - u1 = (unsigned char) *s1++; - u2 = (unsigned char) *s2++; - if (charmap[u1] != charmap[u2]) - return charmap[u1] - charmap[u2]; - if (u1 == '\0') - return 0; - } -} |