wrap: be more robust with locale

On (some?) MacOS systems there is no C.UTF-8 locale available. Instead
there is a non-standard "UTF-8" (encoding only) replacement. Running
wrap on MacOS results in an error:

  error: failed to set locale: Bad file descriptor

Instead of expecting that C.UTF-8 will always be available, try to use
the user set locale (either from the $LC_ALL or $LANG environment
variables). If these variables are unset or if they are set to an
invalid/non-existent locale, fallback on C.UTF-8. If C.UTF-8 is not
available, make one last desperate attempt for this UTF-8 non-standard
locale (MacOS only).

aerc will always send UTF-8 encoded text to the filter commands, If the
locale that we managed to load does not use the UTF-8 character
encoding, exit with an explicit error instead of risking undefined
behaviour.

Reported-by: Ben Cohen <ben@bencohen.net>
Signed-off-by: Robin Jarry <robin@jarry.cc>

1 files changed, 36 insertions, 7 deletions

diff --git a/filters/wrap.c b/filters/wrap.c
index ba084c35..cfe86581 100644
--- a/filters/wrap.c
+++ b/filters/wrap.c
@@ -418,6 +418,40 @@ static void sanitize_line(const wchar_t *in, wchar_t *out)
 	*out = L'\0';
 }
 
+static int set_stdio_encoding(void)
+{
+	const char *locale = setlocale(LC_ALL, "");
+
+	if (!locale) {
+		/* Neither LC_ALL nor LANG env vars are defined or are set to
+		 * a non existant/installed locale. Try with a generic UTF-8
+		 * locale which is expected to be available on all POSIX
+		 * systems. */
+		locale = setlocale(LC_ALL, "C.UTF-8");
+		if (!locale) {
+			/* The system is not following POSIX standards. Last
+			 * resort: check if 'UTF-8' (encoding only) exists. */
+			locale = setlocale(LC_CTYPE, "UTF-8");
+		}
+	}
+	if (!locale) {
+		perror("error: failed to set locale");
+		return 1;
+	}
+
+	/* aerc will always send UTF-8 text, ensure that we read that properly */
+	if (!strstr(locale, "UTF-8") && !strstr(locale, "utf-8")) {
+		fprintf(stderr, "error: locale '%s' is not UTF-8\n", locale);
+		return 1;
+	}
+
+	/* ensure files are configured to read/write wide characters */
+	fwide(in_file, true);
+	fwide(stdout, true);
+
+	return 0;
+}
+
 int main(int argc, char **argv)
 {
 	/* line needs to be 8 times larger than buf since every read character
@@ -440,14 +474,9 @@ int main(int argc, char **argv)
 		is_patch = true;
 	regfree(&re);
 
-	/* aerc will always send UTF-8 text, force locale here */
-	if (!setlocale(LC_CTYPE, "C.UTF-8")) {
-		err = 1;
-		perror("error: failed to set locale");
+	err = set_stdio_encoding();
+	if (err)
 		goto end;
-	}
-	fwide(in_file, true);
-	fwide(stdout, true);
 
 	while (fgetws(buf, BUFFER_SIZE, in_file)) {
 		if (is_patch) {