diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-04 12:17:33 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-04 12:17:33 +0000 |
commit | 5e45211a64149b3c659b90ff2de6fa982a5a93ed (patch) | |
tree | 739caf8c461053357daa9f162bef34516c7bf452 /src/port/pgstrcasecmp.c | |
parent | Initial commit. (diff) | |
download | postgresql-15-5e45211a64149b3c659b90ff2de6fa982a5a93ed.tar.xz postgresql-15-5e45211a64149b3c659b90ff2de6fa982a5a93ed.zip |
Adding upstream version 15.5.upstream/15.5
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'src/port/pgstrcasecmp.c')
-rw-r--r-- | src/port/pgstrcasecmp.c | 151 |
1 files changed, 151 insertions, 0 deletions
diff --git a/src/port/pgstrcasecmp.c b/src/port/pgstrcasecmp.c new file mode 100644 index 0000000..fc7ee91 --- /dev/null +++ b/src/port/pgstrcasecmp.c @@ -0,0 +1,151 @@ +/*------------------------------------------------------------------------- + * + * 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. + * + * We also provide strict ASCII-only case conversion functions, which can + * be used to implement C/POSIX case folding semantics no matter what the + * C library thinks the locale is. + * + * + * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group + * + * src/port/pgstrcasecmp.c + * + *------------------------------------------------------------------------- + */ +#include "c.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 (IS_HIGHBIT_SET(ch1) && isupper(ch1)) + ch1 = tolower(ch1); + + if (ch2 >= 'A' && ch2 <= 'Z') + ch2 += 'a' - 'A'; + else if (IS_HIGHBIT_SET(ch2) && 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 (IS_HIGHBIT_SET(ch1) && isupper(ch1)) + ch1 = tolower(ch1); + + if (ch2 >= 'A' && ch2 <= 'Z') + ch2 += 'a' - 'A'; + else if (IS_HIGHBIT_SET(ch2) && 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 lower 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 (IS_HIGHBIT_SET(ch) && 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 upper 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 (IS_HIGHBIT_SET(ch) && isupper(ch)) + ch = tolower(ch); + return ch; +} + +/* + * Fold a character to upper case, following C/POSIX locale rules. + */ +unsigned char +pg_ascii_toupper(unsigned char ch) +{ + if (ch >= 'a' && ch <= 'z') + ch += 'A' - 'a'; + return ch; +} + +/* + * Fold a character to lower case, following C/POSIX locale rules. + */ +unsigned char +pg_ascii_tolower(unsigned char ch) +{ + if (ch >= 'A' && ch <= 'Z') + ch += 'a' - 'A'; + return ch; +} |