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.

1 files changed, 22 insertions, 9 deletions

diff --git a/Python/pylifecycle.c b/Python/pylifecycle.c
index 8c77859..33af06e 100644
--- a/Python/pylifecycle.c
+++ b/Python/pylifecycle.c
@@ -345,13 +345,13 @@ get_stdio_errors(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) {
@@ -1791,16 +1791,29 @@ init_sys_streams(PyInterpreterState *interp)
             if (err) {
                 *err = '\0';
                 err++;
-                if (*err && !errors) {
-                    errors = err;
+                if (!err[0]) {
+                    err = NULL;
                 }
             }
-            if (!encoding && *pythonioencoding) {
-                encoding = pythonioencoding;
-                if (!errors) {
-                    errors = "strict";
+
+            /* 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;
+            }
         }
 
         if (interp->core_config.utf8_mode) {