[3.7] bpo-34485: stdout uses surrogateescape on POSIX locale (GH-8986) (GH-8987)

* bpo-34485: stdout uses surrogateescape on POSIX locale (GH-8986)

Standard streams like sys.stdout now use the "surrogateescape" error
handler, instead of "strict", on the POSIX locale (when the C locale is not
coerced and the UTF-8 Mode is disabled).

Add tests on sys.stdout.errors with LC_ALL=POSIX.

Fix the error handler of standard streams like sys.stdout:
PYTHONIOENCODING=":" is now ignored instead of setting the error handler to
"strict".

(cherry picked from commit 315877dc36)
This commit is contained in:
Victor Stinner 2018-08-29 11:01:33 +02:00 committed by GitHub
parent 98c49c6ab2
commit 0b9ea4b211
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 62 additions and 28 deletions

View file

@ -423,13 +423,13 @@ get_default_standard_stream_error_handler(void)
{
const char *ctype_loc = setlocale(LC_CTYPE, NULL);
if (ctype_loc != NULL) {
/* "surrogateescape" is the default in the legacy C locale */
if (strcmp(ctype_loc, "C") == 0) {
/* surrogateescape is the default in the legacy C and POSIX locales */
if (strcmp(ctype_loc, "C") == 0 || strcmp(ctype_loc, "POSIX") == 0) {
return "surrogateescape";
}
#ifdef PY_COERCE_C_LOCALE
/* "surrogateescape" is the default in locale coercion target locales */
/* surrogateescape is the default in locale coercion target locales */
const _LocaleCoercionTarget *target = NULL;
for (target = _TARGET_LOCALES; target->locale_name; target++) {
if (strcmp(ctype_loc, target->locale_name) == 0) {
@ -440,7 +440,7 @@ get_default_standard_stream_error_handler(void)
}
/* Otherwise return NULL to request the typical default error handler */
return NULL;
return "strict";
}
#ifdef PY_COERCE_C_LOCALE
@ -1851,20 +1851,42 @@ init_sys_streams(PyInterpreterState *interp)
if (err) {
*err = '\0';
err++;
if (*err && !errors) {
errors = err;
if (!err[0]) {
err = NULL;
}
}
if (*pythonioencoding && !encoding) {
encoding = pythonioencoding;
/* Does PYTHONIOENCODING contain an encoding? */
if (pythonioencoding[0]) {
if (!encoding) {
encoding = pythonioencoding;
}
/* If the encoding is set but not the error handler,
use "strict" error handler by default.
PYTHONIOENCODING=latin1 behaves as
PYTHONIOENCODING=latin1:strict. */
if (!err) {
err = "strict";
}
}
if (!errors && err != NULL) {
errors = err;
}
}
else if (interp->core_config.utf8_mode) {
encoding = "utf-8";
errors = "surrogateescape";
if (interp->core_config.utf8_mode) {
if (!encoding) {
encoding = "utf-8";
}
if (!errors) {
errors = "surrogateescape";
}
}
if (!errors && !pythonioencoding) {
if (!errors) {
/* Choose the default error handler based on the current locale */
errors = get_default_standard_stream_error_handler();
}