Do case-insensitive comparisons assuming ASCII strings.

Do the case-insensitive comparisons in a locale-independent fashion that
only maps ASCII letters, in the standard English-language fashion; that
way, we don't get bitten by, for example, Turkish having separate "i
with dot" and "i without dot" letters, with lower-case "i with dot" being
mapped to upper-case "I with dot" rather than being mapped to "I".

1 files changed, 110 insertions, 0 deletions

diff --git a/ascii_strcasecmp.c b/ascii_strcasecmp.c
new file mode 100644
index 00000000..05e587d7
--- /dev/null
+++ b/ascii_strcasecmp.c
@@ -0,0 +1,110 @@
+/*
+ * 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 "ascii_strcasecmp.h"
+
+/*
+ * This array is designed for mapping upper and lower case letters
+ * together for a case independent comparison.  The mappings are
+ * based upon ASCII character sequences; all values other than
+ * ASCII letters are mapped to themselves, so this is locale-
+ * independent and intended to be locale-independent, to avoid
+ * issues with, for example, "i" and "I" not being lower-case
+ * and upper-case versions of the same letter in Turkish, where
+ * there are separate "i with dot" and "i without dot" letters.
+ */
+static const 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
+ascii_strcasecmp(s1, s2)
+	const char *s1, *s2;
+{
+	register const unsigned char *cm = charmap,
+			*us1 = (const unsigned char *)s1,
+			*us2 = (const unsigned char *)s2;
+
+	while (cm[*us1] == cm[*us2++])
+		if (*us1++ == '\0')
+			return(0);
+	return(cm[*us1] - cm[*--us2]);
+}
+
+int
+ascii_strncasecmp(s1, s2, n)
+	const char *s1, *s2;
+	register size_t n;
+{
+	register const unsigned char *cm = charmap,
+			*us1 = (const unsigned char *)s1,
+			*us2 = (const unsigned char *)s2;
+
+	for (;;) {
+		if (n == 0) {
+			/*
+			 * We've run out of characters that we should
+			 * compare, and they've all been equal; return
+			 * 0, to indicate that the prefixes are the
+			 * same.
+			 */
+			return(0);
+		}
+		if (cm[*us1] != cm[*us2++]) {
+			/*
+			 * We've found a mismatch.
+			 */
+			break;
+		}
+		if (*us1++ == '\0') {
+			/*
+			 * We've run out of characters *to* compare,
+			 * and they've all been equal; return 0, to
+			 * indicate that the strings are the same.
+			 */
+			return(0);
+		}
+		n--;
+	}
+	return(cm[*us1] - cm[*--us2]);
+}