From 61a3364d246e72b903da8b76c2e27a225a51351e Mon Sep 17 00:00:00 2001
From: Rich Felker <dalias@aerifal.cx>
Date: Wed, 27 May 2015 03:22:52 -0400
Subject: overhaul locale internals to treat categories roughly uniformly

previously, LC_MESSAGES was treated specially as the only category
which could be set to a locale name without a definition file, in
order to facilitate gettext message translations when no libc locale
was available. LC_NUMERIC was completely un-settable, and LC_CTYPE
stored a flag intended to be used for a possible future byte-based C
locale, instead of storing a __locale_map pointer like the other
categories use.

this patch changes all categories to be represented by pointers to
__locale_map structures, and allows locale names without definition
files to be treated as valid locales with trivial definition when used
in any category. outwardly visible functional changes should be minor,
limited mainly to the strings read back from setlocale and the way
gettext handles translations in categories other than LC_MESSAGES.

various internal refactoring has also been performed, and improvements
in const correctness have been made.
---
 src/locale/setlocale.c | 72 +++++++++++++++++++-------------------------------
 1 file changed, 27 insertions(+), 45 deletions(-)

(limited to 'src/locale/setlocale.c')

diff --git a/src/locale/setlocale.c b/src/locale/setlocale.c
index 32a8fcab..8dae5a4e 100644
--- a/src/locale/setlocale.c
+++ b/src/locale/setlocale.c
@@ -5,38 +5,23 @@
 #include "libc.h"
 #include "atomic.h"
 
-static char buf[2+4*(LOCALE_NAME_MAX+1)];
+static char buf[LC_ALL*(LOCALE_NAME_MAX+1)];
 
 static char *setlocale_one_unlocked(int cat, const char *name)
 {
-	struct __locale_map *lm;
+	const struct __locale_map *lm;
 
-	if (name) __setlocalecat(&libc.global_locale, cat, name);
+	if (name) libc.global_locale.cat[cat] = lm = __get_locale(cat, name);
+	else lm = libc.global_locale.cat[cat];
 
-	switch (cat) {
-	case LC_CTYPE:
-		return libc.global_locale.ctype_utf8 ? "C.UTF-8" : "C";
-	case LC_NUMERIC:
-		return "C";
-	case LC_MESSAGES:
-		return libc.global_locale.messages_name[0]
-			? libc.global_locale.messages_name : "C";
-	default:
-		lm = libc.global_locale.cat[cat-2];
-		return lm ? lm->name : "C";
-	}
+	return lm ? (char *)lm->name : "C";
 }
 
+char *__strchrnul(const char *, int);
+
 char *setlocale(int cat, const char *name)
 {
 	static volatile int lock[2];
-	struct __locale_map *lm;
-	int i, j;
-
-	if (!libc.global_locale.messages_name) {
-		libc.global_locale.messages_name =
-			buf + 2 + 3*(LOCALE_NAME_MAX+1);
-	}
 
 	if ((unsigned)cat > LC_ALL) return 0;
 
@@ -48,34 +33,31 @@ char *setlocale(int cat, const char *name)
 	 * performs both the serialization and deserialization, depends
 	 * on the format, so it can easily be changed if needed. */
 	if (cat == LC_ALL) {
+		int i;
 		if (name) {
-			char part[LOCALE_NAME_MAX+1];
-			if (name[0] && name[1]==';'
-			    && strlen(name) > 2 + 3*(LOCALE_NAME_MAX+1)) {
-				part[0] = name[0];
-				part[1] = 0;
-				setlocale(LC_CTYPE, part);
-				part[LOCALE_NAME_MAX] = 0;
-				for (i=LC_TIME; i<LC_MESSAGES; i++) {
-					memcpy(part, name + 2 + (i-2)*(LOCALE_NAME_MAX+1), LOCALE_NAME_MAX);
-					for (j=LOCALE_NAME_MAX-1; j && part[j]==';'; j--)
-						part[j] = 0;
-					setlocale_one_unlocked(i, part);
+			char part[LOCALE_NAME_MAX+1] = "C.UTF-8";
+			const char *p = name;
+			for (i=0; i<LC_ALL; i++) {
+				const char *z = __strchrnul(p, ';');
+				if (z-p <= LOCALE_NAME_MAX) {
+					memcpy(part, p, z-p);
+					part[z-p] = 0;
+					if (*z) p = z+1;
 				}
-				setlocale_one_unlocked(LC_MESSAGES, name
-					+ 2 + 3*(LOCALE_NAME_MAX+1));
-			} else {
-				for (i=0; i<LC_ALL; i++)
-					setlocale_one_unlocked(i, name);
+				setlocale_one_unlocked(i, part);
 			}
 		}
-		memset(buf, ';', 2 + 3*(LOCALE_NAME_MAX+1));
-		buf[0] = libc.global_locale.ctype_utf8 ? 'U' : 'C';
-		for (i=LC_TIME; i<LC_MESSAGES; i++) {
-			lm = libc.global_locale.cat[i-2];
-			if (lm) memcpy(buf + 2 + (i-2)*(LOCALE_NAME_MAX+1),
-				lm->name, strlen(lm->name));
+		char *s = buf;
+		for (i=0; i<LC_ALL; i++) {
+			const struct __locale_map *lm =
+				libc.global_locale.cat[i];
+			const char *part = lm ? lm->name : "C";
+			size_t l = strlen(part);
+			memcpy(s, part, l);
+			s[l] = ';';
+			s += l+1;
 		}
+		*--s = 0;
 		UNLOCK(lock);
 		return buf;
 	}
-- 
cgit v1.2.1