From 2d51c4ad57d5cbb083b5bce94ff692490c10ee2d Mon Sep 17 00:00:00 2001 From: Rich Felker Date: Thu, 1 Oct 2015 22:59:56 +0000 Subject: make nl_langinfo(CODESET) always return "ASCII" in byte-based C locale commit 844212d94f582c4e3c5055e0a1524931e89ebe76, which did not make it into any releases, changed nl_langinfo(CODESET) to always return "UTF-8", even in the byte-based C locale. this was problematic because application software was found to use the string match for "UTF-8" to activate its own UTF-8 processing. this both undermines the byte-based functionality of the C locale, and if mixed with with calls to the standard multibyte functions, which happened in practice, could result in severe mis-handling of input. the motive for the previous change was that, to avoid widespread compatibility problems, the string returned by nl_langinfo(CODESET) needs to be accepted by iconv and by third-party character conversion code. thus, the only remaining choice is "ASCII". this choice accurately represents the intent that high bytes do not have individual meaning in the C locale, but it does mean that iconv, when passed nl_langinfo(CODESET) in the C locale, will produce errors in cases where mbrtowc would have succeeded. for reference, glibc behaves similarly in this regard, so I don't think it will be a problem. --- src/locale/langinfo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/locale/langinfo.c b/src/locale/langinfo.c index a1ada246..d3c90d96 100644 --- a/src/locale/langinfo.c +++ b/src/locale/langinfo.c @@ -33,7 +33,7 @@ char *__nl_langinfo_l(nl_item item, locale_t loc) int idx = item & 65535; const char *str; - if (item == CODESET) return "UTF-8"; + if (item == CODESET) return MB_CUR_MAX==1 ? "ASCII" : "UTF-8"; switch (cat) { case LC_NUMERIC: -- cgit v1.2.1