From 96b1c903f5310202a665e86e624a38ede50429c3 Mon Sep 17 00:00:00 2001 From: Just van Rossum Date: Mon, 3 Mar 2003 17:32:15 +0000 Subject: [PATCH] Patch #683592 revisited, after discussions with MvL: - Implement the behavior as specified in PEP 277, meaning os.listdir() will only return unicode strings if it is _called_ with a unicode argument. - And then return only unicode, don't attempt to convert to ASCII. - Don't switch on Py_FileSystemDefaultEncoding, but simply use the default encoding if Py_FileSystemDefaultEncoding is NULL. This means os.listdir() can now raise UnicodeDecodeError if the default encoding can't represent the directory entry. (This seems better than silcencing the error and fall back to a byte string.) - Attempted to decribe the above in Doc/lib/libos.tex. - Reworded the Misc/NEWS items to reflect the current situation. This checkin also fixes bug #696261, which was due to os.listdir() not using Py_FileSystemDefaultEncoding, like all file system calls are supposed to. --- Doc/lib/libos.tex | 4 ++-- Misc/NEWS | 12 +++++------- Modules/posixmodule.c | 18 ++++++++---------- 3 files changed, 15 insertions(+), 19 deletions(-) diff --git a/Doc/lib/libos.tex b/Doc/lib/libos.tex index b2c10f7365d..844704b0591 100644 --- a/Doc/lib/libos.tex +++ b/Doc/lib/libos.tex @@ -711,8 +711,8 @@ entries \code{'.'} and \code{'..'} even if they are present in the directory. Availability: Macintosh, \UNIX, Windows. -\versionadded[On Windows NT/2k/XP, if \var{path} is a Unicode object, -the result will be a list of Unicode objects.]{2.3} +\versionadded[On Windows NT/2k/XP and Unix, if \var{path} is a Unicode +object, the result will be a list of Unicode objects.]{2.3} \end{funcdesc} \begin{funcdesc}{lstat}{path} diff --git a/Misc/NEWS b/Misc/NEWS index bb13310d20a..5bf335a5a9f 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -41,11 +41,9 @@ Library about the rationale is in the NEWS entry for that. See also SF bug report . -- os.listdir() now returns Unicode strings on platforms that set - Py_FileSystemDefaultEncoding, for file names that are not representable - in ASCII. (This currently only affects MacOS X; on Windows versions - with wide file name support os.listdir() already returned Unicode - strings.) +- On Unix platforms, if os.listdir() is called with a Unicode argument, + it now returns Unicode strings. (This behavior was added earlier + to the Windows NT/2k/XP version of os.listdir().) - Distutils: both 'py_modules' and 'packages' keywords can now be specified in core.setup(). Previously you could supply one or the other, but @@ -88,8 +86,8 @@ TBD Mac --- -- os.listdir() now may return Unicode strings on MacOS X. See the general - news item under "Library". +- os.listdir() now returns Unicode strings on MacOS X when called with + a Unicode argument. See the general news item under "Library". - A new method MacOS.WMAvailable() returns true if it is safe to access the window manager, false otherwise. diff --git a/Modules/posixmodule.c b/Modules/posixmodule.c index 482bba95cbd..d9033f6c5ae 100644 --- a/Modules/posixmodule.c +++ b/Modules/posixmodule.c @@ -1775,7 +1775,13 @@ posix_listdir(PyObject *self, PyObject *args) PyObject *d, *v; DIR *dirp; struct dirent *ep; - if (!PyArg_ParseTuple(args, "s:listdir", &name)) + int arg_is_unicode = 1; + + if (!PyArg_ParseTuple(args, "U:listdir", &v)) { + arg_is_unicode = 0; + PyErr_Clear(); + } + if (!PyArg_ParseTuple(args, "et:listdir", Py_FileSystemDefaultEncoding, &name)) return NULL; if ((dirp = opendir(name)) == NULL) { return posix_error_with_filename(name); @@ -1796,7 +1802,7 @@ posix_listdir(PyObject *self, PyObject *args) break; } #ifdef Py_USING_UNICODE - if (Py_FileSystemDefaultEncoding != NULL) { + if (arg_is_unicode) { PyObject *w; w = PyUnicode_FromEncodedObject(v, @@ -1809,14 +1815,6 @@ posix_listdir(PyObject *self, PyObject *args) d = NULL; break; } - /* attempt to convert to ASCII */ - w = PyUnicode_AsASCIIString(v); - if (w != NULL) { - Py_DECREF(v); - v = w; - } - else - PyErr_Clear(); } #endif if (PyList_Append(d, v) != 0) {