summaryrefslogtreecommitdiffstats
path: root/src/port/pgstrcasecmp.c
blob: fc7ee91e8fb4101fe00c182e61c569a6967da315 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
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;
}