New submission from Christian Heimes:
This is a *preliminary* patch for __file__ and co_filename which decodes
char* / PyString using the FS default encoding. I'm still working on it.
----------
components: Interpreter Core
files: py3k_file_fsenc.patch
messages: 56345
nosy: tiran
severity: normal
status: open
title: __file__ and co_filename as unicode
versions: Python 3.0
__________________________________
Tracker <[EMAIL PROTECTED]>
<http://bugs.python.org/issue1264>
__________________________________
Index: Python/pythonrun.c
===================================================================
--- Python/pythonrun.c (revision 58412)
+++ Python/pythonrun.c (working copy)
@@ -867,7 +867,8 @@
return -1;
d = PyModule_GetDict(m);
if (PyDict_GetItemString(d, "__file__") == NULL) {
- PyObject *f = PyString_FromString(filename);
+ PyObject *f;
+ f = _PyUnicode_DecodeFSDefault(filename, strlen(filename), NULL);
if (f == NULL)
return -1;
if (PyDict_SetItemString(d, "__file__", f) < 0) {
Index: Python/import.c
===================================================================
--- Python/import.c (revision 58412)
+++ Python/import.c (working copy)
@@ -652,9 +652,11 @@
/* Remember the filename as the __file__ attribute */
v = NULL;
if (pathname != NULL) {
- v = PyString_FromString(pathname);
- if (v == NULL)
+ v = _PyUnicode_DecodeFSDefault(pathname, strlen(pathname), NULL);
+ if (v == NULL) {
PyErr_Clear();
+ printf("__file__ error");
+ }
}
if (v == NULL) {
v = ((PyCodeObject *)co)->co_filename;
@@ -983,7 +985,7 @@
PySys_WriteStderr("import %s # directory %s\n",
name, pathname);
d = PyModule_GetDict(m);
- file = PyString_FromString(pathname);
+ file = _PyUnicode_DecodeFSDefault(pathname, strlen(pathname), NULL);
if (file == NULL)
goto error;
path = Py_BuildValue("[O]", file);
Index: Python/importdl.c
===================================================================
--- Python/importdl.c (revision 58412)
+++ Python/importdl.c (working copy)
@@ -62,7 +62,9 @@
return NULL;
}
/* Remember the filename as the __file__ attribute */
- if (PyModule_AddStringConstant(m, "__file__", pathname) < 0)
+ PyObject *path;
+ path = _PyUnicode_DecodeFSDefault(pathname, strlen(pathname), NULL);
+ if (PyModule_AddObject(m, "__file__", path) < 0)
PyErr_Clear(); /* Not important enough to report */
if (_PyImport_FixupExtension(name, pathname) == NULL)
Index: Include/unicodeobject.h
===================================================================
--- Include/unicodeobject.h (revision 58412)
+++ Include/unicodeobject.h (working copy)
@@ -154,6 +154,7 @@
# define PyUnicode_DecodeASCII PyUnicodeUCS2_DecodeASCII
# define PyUnicode_DecodeCharmap PyUnicodeUCS2_DecodeCharmap
# define PyUnicode_DecodeLatin1 PyUnicodeUCS2_DecodeLatin1
+# define _PyUnicode_DecodeFSDefault _PyUnicodeUCS2_DecodeFSDefault
# define PyUnicode_DecodeRawUnicodeEscape PyUnicodeUCS2_DecodeRawUnicodeEscape
# define PyUnicode_DecodeUTF32 PyUnicodeUCS2_DecodeUTF32
# define PyUnicode_DecodeUTF32Stateful PyUnicodeUCS2_DecodeUTF32Stateful
@@ -245,6 +246,7 @@
# define PyUnicode_DecodeASCII PyUnicodeUCS4_DecodeASCII
# define PyUnicode_DecodeCharmap PyUnicodeUCS4_DecodeCharmap
# define PyUnicode_DecodeLatin1 PyUnicodeUCS4_DecodeLatin1
+# define _PyUnicode_DecodeFSDefault _PyUnicodeUCS4_DecodeFSDefault
# define PyUnicode_DecodeRawUnicodeEscape PyUnicodeUCS4_DecodeRawUnicodeEscape
# define PyUnicode_DecodeUTF32 PyUnicodeUCS4_DecodeUTF32
# define PyUnicode_DecodeUTF32Stateful PyUnicodeUCS4_DecodeUTF32Stateful
@@ -641,6 +643,20 @@
PyAPI_FUNC(PyObject *) _PyUnicode_AsDefaultEncodedString(
PyObject *, const char *);
+/* Decode a string to a Python unicode object using either
+ Py_FileSystemDefaultEncoding or UTF-8 if the default encoding isn't given.
+
+ *** Exported for internal use by the interpreter only !!! ***
+
+*/
+
+PyAPI_FUNC(PyObject*) _PyUnicode_DecodeFSDefault(
+ const char *string, /* encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors /* error handling */
+ );
+
+
/* Return a char* holding the UTF-8 encoded value of the
Unicode object.
Index: Objects/codeobject.c
===================================================================
--- Objects/codeobject.c (revision 58412)
+++ Objects/codeobject.c (working copy)
@@ -59,7 +59,7 @@
freevars == NULL || !PyTuple_Check(freevars) ||
cellvars == NULL || !PyTuple_Check(cellvars) ||
name == NULL || (!PyString_Check(name) && !PyUnicode_Check(name)) ||
- filename == NULL || !PyString_Check(filename) ||
+ filename == NULL || (!PyString_Check(name) && !PyUnicode_Check(name)) ||
lnotab == NULL || !PyString_Check(lnotab) ||
!PyObject_CheckReadBuffer(code)) {
PyErr_BadInternalCall();
@@ -72,6 +72,20 @@
} else {
Py_INCREF(name);
}
+ if (PyString_Check(filename)) {
+ /* We don't have enough infrastructure here to use the codecs package.
+ What happens if the the fs default encoding is not UTF-8?
+
+ filename = PyString_AsDecodedObject(filename,
+ Py_FileSystemDefaultEncoding ? Py_FileSystemDefaultEncoding : "UTF-8",
+ NULL);
+ */
+ filename = PyUnicode_FromString(PyString_AS_STRING(filename));
+ if (filename == NULL)
+ return NULL;
+ } else {
+ Py_INCREF(filename);
+ }
intern_strings(names);
intern_strings(varnames);
intern_strings(freevars);
Index: Objects/unicodeobject.c
===================================================================
--- Objects/unicodeobject.c (revision 58412)
+++ Objects/unicodeobject.c (working copy)
@@ -1231,6 +1231,22 @@
return v;
}
+PyObject*
+_PyUnicode_DecodeFSDefault(const char *string,
+ Py_ssize_t length,
+ const char *errors)
+{
+ PyObject *v;
+
+ if (Py_FileSystemDefaultEncoding)
+ v = PyUnicode_Decode(string, length, Py_FileSystemDefaultEncoding,
+ errors);
+ else
+ v = PyUnicode_DecodeUTF8(string, length, errors);
+
+ return (PyObject*)v;
+}
+
char*
PyUnicode_AsStringAndSize(PyObject *unicode, Py_ssize_t *psize)
{
Index: Objects/moduleobject.c
===================================================================
--- Objects/moduleobject.c (revision 58412)
+++ Objects/moduleobject.c (working copy)
@@ -86,12 +86,12 @@
d = ((PyModuleObject *)m)->md_dict;
if (d == NULL ||
(fileobj = PyDict_GetItemString(d, "__file__")) == NULL ||
- !PyString_Check(fileobj))
+ !PyUnicode_Check(fileobj))
{
PyErr_SetString(PyExc_SystemError, "module filename missing");
return NULL;
}
- return PyString_AsString(fileobj);
+ return PyUnicode_AsString(fileobj);
}
void
_______________________________________________
Python-bugs-list mailing list
Unsubscribe:
http://mail.python.org/mailman/options/python-bugs-list/archive%40mail-archive.com
