From 4bc3a16677be061e60abd8d9e732c434784566db Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Mon, 30 Mar 2020 11:14:58 -0400 Subject: [PATCH] Be more careful about extracting encoding from locale strings on Windows. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit GetLocaleInfoEx() can fail on strings that setlocale() was perfectly happy with. A common way for that to happen is if the locale string is actually a Unix-style string, say "et_EE.UTF-8". In that case, what's after the dot is an encoding name, not a Windows codepage number; blindly treating it as a codepage number led to failure, with a fairly silly error message. Hence, check to see if what's after the dot is all digits, and if not, treat it as a literal encoding name rather than a codepage number. This will do the right thing with many Unix-style locale strings, and produce a more sensible error message otherwise. Somewhat independently of that, treat a zero (CP_ACP) result from GetLocaleInfoEx() as meaning that we must use UTF-8 encoding. Back-patch to all supported branches. Juan José Santamaría Flecha Discussion: https://postgr.es/m/24905.1585445371@sss.pgh.pa.us --- src/port/chklocale.c | 29 ++++++++++++++++++++++++----- 1 file changed, 24 insertions(+), 5 deletions(-) diff --git a/src/port/chklocale.c b/src/port/chklocale.c index dde913099f..edcc6939ed 100644 --- a/src/port/chklocale.c +++ b/src/port/chklocale.c @@ -239,25 +239,44 @@ win32_langinfo(const char *ctype) { r = malloc(16); /* excess */ if (r != NULL) - sprintf(r, "CP%u", cp); + { + /* + * If the return value is CP_ACP that means no ANSI code page is + * available, so only Unicode can be used for the locale. + */ + if (cp == CP_ACP) + strcpy(r, "utf8"); + else + sprintf(r, "CP%u", cp); + } } else #endif { /* - * Locale format on Win32 is _. . For - * example, English_United States.1252. + * Locale format on Win32 is _.. For + * example, English_United States.1252. If we see digits after the + * last dot, assume it's a codepage number. Otherwise, we might be + * dealing with a Unix-style locale string; Windows' setlocale() will + * take those even though GetLocaleInfoEx() won't, so we end up here. + * In that case, just return what's after the last dot and hope we can + * find it in our table. */ codepage = strrchr(ctype, '.'); if (codepage != NULL) { - int ln; + size_t ln; codepage++; ln = strlen(codepage); r = malloc(ln + 3); if (r != NULL) - sprintf(r, "CP%s", codepage); + { + if (strspn(codepage, "0123456789") == ln) + sprintf(r, "CP%s", codepage); + else + strcpy(r, codepage); + } } }