STINNER Victor added the comment:

macosx-2.patch patches _Py_wchar2char() and _Py_char2wchar() functions to
use UTF-8/surrogateescape for any function using the locale encoding, not
only file related functions of fileutils.h. The patch does also simplify
the code, no more specific #ifdef __APPLE__ in python.c:

-#ifdef __APPLE__
-        argv_copy[i] = _Py_DecodeUTF8_surrogateescape(argv[i],
strlen(argv[i]));
-#else
         argv_copy[i] = _Py_char2wchar(argv[i], NULL);
-#endif

2012/11/7 Andrew Svetlov <rep...@bugs.python.org>

>
> Changes by Andrew Svetlov <andrew.svet...@gmail.com>:
>
>
> ----------
> nosy: +asvetlov
>
> _______________________________________
> Python tracker <rep...@bugs.python.org>
> <http://bugs.python.org/issue16416>
> _______________________________________
>

----------
Added file: http://bugs.python.org/file27969/macosx-2.patch

_______________________________________
Python tracker <rep...@bugs.python.org>
<http://bugs.python.org/issue16416>
_______________________________________
diff -r 6a6ad09faad2 Modules/python.c
--- a/Modules/python.c  Mon Nov 12 01:23:51 2012 +0100
+++ b/Modules/python.c  Mon Nov 12 14:29:44 2012 +0100
@@ -15,10 +15,6 @@ wmain(int argc, wchar_t **argv)
 }
 #else
 
-#ifdef __APPLE__
-extern wchar_t* _Py_DecodeUTF8_surrogateescape(const char *s, Py_ssize_t size);
-#endif
-
 int
 main(int argc, char **argv)
 {
@@ -45,11 +41,7 @@ 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: "
diff -r 6a6ad09faad2 Python/fileutils.c
--- a/Python/fileutils.c        Mon Nov 12 01:23:51 2012 +0100
+++ b/Python/fileutils.c        Mon Nov 12 14:29:44 2012 +0100
@@ -7,6 +7,10 @@
 #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)
 {
@@ -59,6 +63,15 @@ PyObject *
 wchar_t*
 _Py_char2wchar(const char* arg, size_t *size)
 {
+#ifdef __APPLE__
+    wchar_t *wstr;
+    wstr = _Py_DecodeUTF8_surrogateescape(arg, strlen(arg));
+    if (wstr == NULL)
+        return NULL;
+    if (size != NULL)
+        *size = wcslen(wstr);
+    return wstr;
+#else
     wchar_t *res;
 #ifdef HAVE_BROKEN_MBSTOWCS
     /* Some platforms have a broken implementation of
@@ -144,7 +157,7 @@ wchar_t*
         argsize -= converted;
         out++;
     }
-#else
+#else   /* HAVE_MBRTOWC */
     /* Cannot use C locale for escaping; manually escape as if charset
        is ASCII (i.e. escape all bytes > 128. This will still roundtrip
        correctly in the locale's charset, which must be an ASCII superset. */
@@ -159,7 +172,7 @@ wchar_t*
         else
             *out++ = 0xdc00 + *in++;
     *out = 0;
-#endif
+#endif   /* HAVE_MBRTOWC */
     if (size != NULL)
         *size = out - res;
     return res;
@@ -167,6 +180,7 @@ oom:
     if (size != NULL)
         *size = (size_t)-1;
     return NULL;
+#endif   /* __APPLE__ */
 }
 
 /* Encode a (wide) character string to the locale encoding with the
@@ -183,6 +197,34 @@ oom:
 char*
 _Py_wchar2char(const wchar_t *text, size_t *error_pos)
 {
+#ifdef __APPLE__
+    Py_ssize_t len;
+    PyObject *unicode, *bytes = NULL;
+    char *cpath;
+
+    unicode = PyUnicode_FromWideChar(text, wcslen(text));
+    if (unicode == NULL) {
+        Py_DECREF(unicode);
+        return NULL;
+    }
+
+    bytes = _PyUnicode_AsUTF8String(unicode, "surrogateescape");
+    Py_DECREF(unicode);
+    if (bytes == NULL) {
+        PyErr_Clear();
+        return NULL;
+    }
+
+    len = PyBytes_GET_SIZE(bytes);
+    cpath = PyMem_Malloc(len+1);
+    if (cpath == NULL) {
+        Py_DECREF(bytes);
+        return NULL;
+    }
+    memcpy(cpath, PyBytes_AsString(bytes), len + 1);
+    Py_DECREF(bytes);
+    return cpath;
+#else   /* __APPLE__ */
     const size_t len = wcslen(text);
     char *result = NULL, *bytes = NULL;
     size_t i, size, converted;
@@ -242,6 +284,7 @@ char*
         bytes = result;
     }
     return result;
+#endif   /* __APPLE__ */
 }
 
 /* In principle, this should use HAVE__WSTAT, and _wstat
_______________________________________________
Python-bugs-list mailing list
Unsubscribe: 
http://mail.python.org/mailman/options/python-bugs-list/archive%40mail-archive.com

Reply via email to