bpo-29240: PEP 540: Add a new UTF-8 Mode (#855)

* Add -X utf8 command line option, PYTHONUTF8 environment variable
  and a new sys.flags.utf8_mode flag.
* If the LC_CTYPE locale is "C" at startup: enable automatically the
  UTF-8 mode.
* Add _winapi.GetACP(). encodings._alias_mbcs() now calls
  _winapi.GetACP() to get the ANSI code page
* locale.getpreferredencoding() now returns 'UTF-8' in the UTF-8
  mode. As a side effect, open() now uses the UTF-8 encoding by
  default in this mode.
* Py_DecodeLocale() and Py_EncodeLocale() now use the UTF-8 encoding
  in the UTF-8 Mode.
* Update subprocess._args_from_interpreter_flags() to handle -X utf8
* Skip some tests relying on the current locale if the UTF-8 mode is
  enabled.
* Add test_utf8mode.py.
* _Py_DecodeUTF8_surrogateescape() gets a new optional parameter to
  return also the length (number of wide characters).
* pymain_get_global_config() and pymain_set_global_config() now
  always copy flag values, rather than only copying if the new value
  is greater than the old value.

1 files changed, 14 insertions, 9 deletions

diff --git a/Programs/python.c b/Programs/python.c
index 22d55bbc4c..aef7122517 100644
--- a/Programs/python.c
+++ b/Programs/python.c
@@ -17,6 +17,15 @@ wmain(int argc, wchar_t **argv)
 #else
 
 
+static void _Py_NO_RETURN
+fatal_error(const char *msg)
+{
+    fprintf(stderr, "Fatal Python error: %s\n", msg);
+    fflush(stderr);
+    exit(1);
+}
+
+
 int
 main(int argc, char **argv)
 {
@@ -28,9 +37,7 @@ main(int argc, char **argv)
 
     _PyInitError err = _PyRuntime_Initialize();
     if (_Py_INIT_FAILED(err)) {
-        fprintf(stderr, "Fatal Python error: %s\n", err.msg);
-        fflush(stderr);
-        exit(1);
+        fatal_error(err.msg);
     }
 
     /* Force default allocator, to be able to release memory above
@@ -40,7 +47,7 @@ main(int argc, char **argv)
     argv_copy = (wchar_t **)PyMem_RawMalloc(sizeof(wchar_t*) * (argc+1));
     argv_copy2 = (wchar_t **)PyMem_RawMalloc(sizeof(wchar_t*) * (argc+1));
     if (!argv_copy || !argv_copy2) {
-        fprintf(stderr, "out of memory\n");
+        fatal_error("out of memory");
         return 1;
     }
 
@@ -55,7 +62,7 @@ main(int argc, char **argv)
 
     oldloc = _PyMem_RawStrdup(setlocale(LC_ALL, NULL));
     if (!oldloc) {
-        fprintf(stderr, "out of memory\n");
+        fatal_error("out of memory");
         return 1;
     }
 
@@ -73,6 +80,7 @@ main(int argc, char **argv)
      * details.
      */
     if (_Py_LegacyLocaleDetected()) {
+        Py_UTF8Mode = 1;
         _Py_CoerceLegacyLocale();
     }
 
@@ -81,10 +89,7 @@ main(int argc, char **argv)
         argv_copy[i] = Py_DecodeLocale(argv[i], NULL);
         if (!argv_copy[i]) {
             PyMem_RawFree(oldloc);
-            fprintf(stderr, "Fatal Python error: "
-                            "unable to decode the command line argument #%i\n",
-                            i + 1);
-            return 1;
+            fatal_error("unable to decode the command line arguments");
         }
         argv_copy2[i] = argv_copy[i];
     }