lib/rawstr: borrow raw string functions from curl

We'll need these functions to do locale agnostic and case insensitive
string comparisons.

Signed-off-by: Dave Reisner <dreisner@archlinux.org>

3 files changed, 138 insertions, 0 deletions

diff --git a/lib/libalpm/Makefile.am b/lib/libalpm/Makefile.am
index b2b6d0d2..c863fa9b 100644
--- a/lib/libalpm/Makefile.am
+++ b/lib/libalpm/Makefile.am
@@ -41,6 +41,7 @@ libalpm_la_SOURCES = \
 	log.h log.c \
 	package.h package.c \
 	pkghash.h pkghash.c \
+	rawstr.c \
 	remove.h remove.c \
 	signing.c signing.h \
 	sync.h sync.c \
diff --git a/lib/libalpm/rawstr.c b/lib/libalpm/rawstr.c
new file mode 100644
index 00000000..69224cbc
--- /dev/null
+++ b/lib/libalpm/rawstr.c
@@ -0,0 +1,135 @@
+/***************************************************************************
+ *                                  _   _ ____  _
+ *  Project                     ___| | | |  _ \| |
+ *                             / __| | | | |_) | |
+ *                            | (__| |_| |  _ <| |___
+ *                             \___|\___/|_| \_\_____|
+ *
+ * Copyright (C) 1998 - 2011, Daniel Stenberg, <daniel@haxx.se>, et al.
+ *
+ * This software is licensed as described in the file COPYING, which
+ * you should have received as part of this distribution. The terms
+ * are also available at http://curl.haxx.se/docs/copyright.html.
+ *
+ * You may opt to use, copy, modify, merge, publish, distribute and/or sell
+ * copies of the Software, and permit persons to whom the Software is
+ * furnished to do so, under the terms of the COPYING file.
+ *
+ * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
+ * KIND, either express or implied.
+ *
+ ***************************************************************************/
+
+/* These functions are borrowed from libcurl's lib/rawstr.c with minor
+ * modifications to style and naming. Curl_raw_equal and Curl_raw_nequal are
+ * further modified to be true cmp style functions, returning negative, zero,
+ * or positive. */
+
+#include <stdlib.h>
+
+/* Portable, consistent toupper (remember EBCDIC). Do not use toupper() because
+	 its behavior is altered by the current locale. */
+static char raw_toupper(char in)
+{
+	switch(in) {
+	case 'a':
+		return 'A';
+	case 'b':
+		return 'B';
+	case 'c':
+		return 'C';
+	case 'd':
+		return 'D';
+	case 'e':
+		return 'E';
+	case 'f':
+		return 'F';
+	case 'g':
+		return 'G';
+	case 'h':
+		return 'H';
+	case 'i':
+		return 'I';
+	case 'j':
+		return 'J';
+	case 'k':
+		return 'K';
+	case 'l':
+		return 'L';
+	case 'm':
+		return 'M';
+	case 'n':
+		return 'N';
+	case 'o':
+		return 'O';
+	case 'p':
+		return 'P';
+	case 'q':
+		return 'Q';
+	case 'r':
+		return 'R';
+	case 's':
+		return 'S';
+	case 't':
+		return 'T';
+	case 'u':
+		return 'U';
+	case 'v':
+		return 'V';
+	case 'w':
+		return 'W';
+	case 'x':
+		return 'X';
+	case 'y':
+		return 'Y';
+	case 'z':
+		return 'Z';
+	}
+	return in;
+}
+
+/*
+ * _alpm_raw_cmp() is for doing "raw" case insensitive strings. This is meant
+ * to be locale independent and only compare strings we know are safe for
+ * this.  See http://daniel.haxx.se/blog/2008/10/15/strcasecmp-in-turkish/ for
+ * some further explanation to why this function is necessary.
+ *
+ * The function is capable of comparing a-z case insensitively even for
+ * non-ascii.
+ */
+
+int _alpm_raw_cmp(const char *first, const char *second)
+{
+	while(*first && *second) {
+		if(raw_toupper(*first) != raw_toupper(*second)) {
+			/* get out of the loop as soon as they don't match */
+			break;
+		}
+		first++;
+		second++;
+	}
+	/* we do the comparison here (possibly again), just to make sure that if the
+		 loop above is skipped because one of the strings reached zero, we must not
+		 return this as a successful match */
+	return (raw_toupper(*first) - raw_toupper(*second));
+}
+
+int _alpm_raw_ncmp(const char *first, const char *second, size_t max)
+{
+	while(*first && *second && max) {
+		if(raw_toupper(*first) != raw_toupper(*second)) {
+			break;
+		}
+		max--;
+		first++;
+		second++;
+	}
+	if(0 == max) {
+		/* they are equal this far */
+		return 0;
+	}
+
+	return (raw_toupper(*first) - raw_toupper(*second));
+}
+
+/* vim: set ts=2 sw=2 noet: */
diff --git a/lib/libalpm/util.h b/lib/libalpm/util.h
index fd97824a..450dac9b 100644
--- a/lib/libalpm/util.h
+++ b/lib/libalpm/util.h
@@ -113,6 +113,8 @@ int _alpm_splitname(const char *target, char **name, char **version,
 		unsigned long *name_hash);
 unsigned long _alpm_hash_sdbm(const char *str);
 long _alpm_parsedate(const char *line);
+int _alpm_raw_cmp(const char *first, const char *second);
+int _alpm_raw_ncmp(const char *first, const char *second, size_t max);
 
 #ifndef HAVE_STRSEP
 char *strsep(char **, const char *);