From: Victor Stinner <victor.stinner@gmail.com>
Date: Mon, 3 Dec 2012 11:48:53 +0000 (+0100)
Subject: (Merge 3.2) Issue #16416: On Mac OS X, operating system data are now always
X-Git-Tag: v3.3.1rc1~568
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=2660e427d1abcae9fc60115c45619ed2286fc560;p=python

(Merge 3.2) Issue #16416: On Mac OS X, operating system data are now always
encoded/decoded to/from UTF-8/surrogateescape, instead of the locale encoding
(which may be ASCII if no locale environment variable is set), to avoid
inconsistencies with os.fsencode() and os.fsdecode() functions which are
already using UTF-8/surrogateescape.
---

2660e427d1abcae9fc60115c45619ed2286fc560
diff --cc Misc/NEWS
index 6eff12c84e,fbcfe90c0b..c695be511c
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@@ -12,12 -10,13 +12,18 @@@ What's New in Python 3.3.1
  Core and Builtins
  -----------------
  
+ - Issue #16416: On Mac OS X, operating system data are now always
+   encoded/decoded to/from UTF-8/surrogateescape, instead of the locale encoding
+   (which may be ASCII if no locale environment variable is set), to avoid
+   inconsistencies with os.fsencode() and os.fsdecode() functions which are
+   already using UTF-8/surrogateescape.
+ 
 -- Issue #16588: Silence unused-but-set warnings in Python/thread_pthread.h
 +- Issue #16588: Silence unused-but-set warnings in Python/thread_pthread
 +
 +- Issue #16546: Fix: ast.YieldFrom argument is now mandatory.
 +
 +- Issue #16514: Fix regression causing a traceback when sys.path[0] is None
 +  (actually, any non-string or non-bytes type).
  
  - Issue #16306: Fix multiple error messages when unknown command line
    parameters where passed to the interpreter.  Patch by Hieu Nguyen.
diff --cc Modules/python.c
index c70bf37827,2be69f1f54..2c08b96856
--- a/Modules/python.c
+++ b/Modules/python.c
@@@ -45,13 -41,8 +41,9 @@@ main(int argc, char **argv
      oldloc = strdup(setlocale(LC_ALL, NULL));
      setlocale(LC_ALL, "");
      for (i = 0; i < argc; i++) {
- #ifdef __APPLE__
-         argv_copy[i] = _Py_DecodeUTF8_surrogateescape(argv[i], strlen(argv[i]));
- #else
          argv_copy[i] = _Py_char2wchar(argv[i], NULL);
- #endif
          if (!argv_copy[i]) {
 +            free(oldloc);
              fprintf(stderr, "Fatal Python error: "
                              "unable to decode the command line argument #%i\n",
                              i + 1);
diff --cc Python/fileutils.c
index 976c04b117,cba6696695..2e9ea359da
--- a/Python/fileutils.c
+++ b/Python/fileutils.c
@@@ -4,40 -3,10 +4,44 @@@
  #  include <windows.h>
  #endif
  
 +#ifdef HAVE_LANGINFO_H
 +#include <langinfo.h>
 +#endif
 +
+ #ifdef __APPLE__
+ extern wchar_t* _Py_DecodeUTF8_surrogateescape(const char *s, Py_ssize_t size);
+ #endif
+ 
 +PyObject *
 +_Py_device_encoding(int fd)
 +{
 +#if defined(MS_WINDOWS) || defined(MS_WIN64)
 +    UINT cp;
 +#endif
 +    if (!_PyVerify_fd(fd) || !isatty(fd)) {
 +        Py_RETURN_NONE;
 +    }
 +#if defined(MS_WINDOWS) || defined(MS_WIN64)
 +    if (fd == 0)
 +        cp = GetConsoleCP();
 +    else if (fd == 1 || fd == 2)
 +        cp = GetConsoleOutputCP();
 +    else
 +        cp = 0;
 +    /* GetConsoleCP() and GetConsoleOutputCP() return 0 if the application
 +       has no console */
 +    if (cp != 0)
 +        return PyUnicode_FromFormat("cp%u", (unsigned int)cp);
 +#elif defined(CODESET)
 +    {
 +        char *codeset = nl_langinfo(CODESET);
 +        if (codeset != NULL && codeset[0] != 0)
 +            return PyUnicode_FromString(codeset);
 +    }
 +#endif
 +    Py_RETURN_NONE;
 +}
 +
  #ifdef HAVE_STAT
  
  /* Decode a byte string from the locale encoding with the
@@@ -165,9 -141,9 +180,10 @@@ _Py_char2wchar(const char* arg, size_t 
          *size = out - res;
      return res;
  oom:
 -    fprintf(stderr, "out of memory\n");
 +    if (size != NULL)
 +        *size = (size_t)-1;
      return NULL;
+ #endif   /* __APPLE__ */
  }
  
  /* Encode a (wide) character string to the locale encoding with the