From 5cb258950ce9b69b1f65646431c464c0c17b1510 Mon Sep 17 00:00:00 2001 From: Victor Stinner Date: Tue, 28 Aug 2018 12:35:44 +0200 Subject: bpo-34527: POSIX locale enables the UTF-8 Mode (GH-8972) * The UTF-8 Mode is now also enabled by the "POSIX" locale, not only by the "C" locale. * On FreeBSD, Py_DecodeLocale() and Py_EncodeLocale() now also forces the ASCII encoding if the LC_CTYPE locale is "POSIX", not only if the LC_CTYPE locale is "C". * test_utf8_mode.test_cmd_line() checks also that the command line arguments are decoded from UTF-8 when the the UTF-8 Mode is enabled with POSIX locale or C locale. --- Python/coreconfig.c | 16 ++++++++++++---- Python/fileutils.c | 2 +- 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'Python') diff --git a/Python/coreconfig.c b/Python/coreconfig.c index 1b9e26e50a..acf46451f1 100644 --- a/Python/coreconfig.c +++ b/Python/coreconfig.c @@ -1,5 +1,6 @@ #include "Python.h" #include "internal/pystate.h" +#include #define DECODE_LOCALE_ERR(NAME, LEN) \ @@ -828,14 +829,21 @@ static void config_init_locale(_PyCoreConfig *config) { if (_Py_LegacyLocaleDetected()) { - /* POSIX locale: enable C locale coercion and UTF-8 Mode */ - if (config->utf8_mode < 0) { - config->utf8_mode = 1; - } + /* The C locale enables the C locale coercion (PEP 538) */ if (config->coerce_c_locale < 0) { config->coerce_c_locale = 1; } } +#ifndef MS_WINDOWS + const char *ctype_loc = setlocale(LC_CTYPE, NULL); + if (ctype_loc != NULL + && (strcmp(ctype_loc, "C") == 0 || strcmp(ctype_loc, "POSIX") == 0)) { + /* The C locale and the POSIX locale enable the UTF-8 Mode (PEP 540) */ + if (config->utf8_mode < 0) { + config->utf8_mode = 1; + } + } +#endif } diff --git a/Python/fileutils.c b/Python/fileutils.c index 35869c81ac..b413f4e1e6 100644 --- a/Python/fileutils.c +++ b/Python/fileutils.c @@ -128,7 +128,7 @@ check_force_ascii(void) loc = setlocale(LC_CTYPE, NULL); if (loc == NULL) goto error; - if (strcmp(loc, "C") != 0) { + if (strcmp(loc, "C") != 0 && strcmp(loc, "POSIX") != 0) { /* the LC_CTYPE locale is different than C */ return 0; } -- cgit v1.2.1