gettext: add is_utf8_locale()

This function returns true if git is running under an UTF-8
locale. pcre in the next patch will need this.

is_encoding_utf8() is used instead of strcmp() to catch both "utf-8"
and "utf8" suffixes.

When built with no gettext support, we peek in several env variables
to detect UTF-8. pcre library might support utf-8 even if libc is
built without locale support.. The peeking code is a copy from
compat/regex/regcomp.c

Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 23 insertions, 2 deletions

diff --git a/gettext.c b/gettext.c
index a268a2c52c..db727ea020 100644
--- a/gettext.c
+++ b/gettext.c
@@ -18,6 +18,8 @@
 #	endif
 #endif
 
+static const char *charset;
+
 /*
  * Guess the user's preferred languages from the value in LANGUAGE environment
  * variable and LC_MESSAGES locale category if NO_GETTEXT is not defined.
@@ -65,7 +67,6 @@ static int test_vsnprintf(const char *fmt, ...)
 	return ret;
 }
 
-static const char *charset;
 static void init_gettext_charset(const char *domain)
 {
 	/*
@@ -172,8 +173,27 @@ int gettext_width(const char *s)
 {
 	static int is_utf8 = -1;
 	if (is_utf8 == -1)
-		is_utf8 = !strcmp(charset, "UTF-8");
+		is_utf8 = is_utf8_locale();
 
 	return is_utf8 ? utf8_strwidth(s) : strlen(s);
 }
 #endif
+
+int is_utf8_locale(void)
+{
+#ifdef NO_GETTEXT
+	if (!charset) {
+		const char *env = getenv("LC_ALL");
+		if (!env || !*env)
+			env = getenv("LC_CTYPE");
+		if (!env || !*env)
+			env = getenv("LANG");
+		if (!env)
+			env = "";
+		if (strchr(env, '.'))
+			env = strchr(env, '.') + 1;
+		charset = xstrdup(env);
+	}
+#endif
+	return is_encoding_utf8(charset);
+}
diff --git a/gettext.h b/gettext.h
index 33696a40b8..7eee64a34f 100644
--- a/gettext.h
+++ b/gettext.h
@@ -90,5 +90,6 @@ const char *Q_(const char *msgid, const char *plu, unsigned long n)
 #endif
 
 const char *get_preferred_languages(void);
+extern int is_utf8_locale(void);
 
 #endif