Christian Heimes added the comment:
> I think find_module() should return a file descriptor (fd), not a
> FILE*, but most of the rest of the code should call fdopen() on that
> fd. Only call_find_module() should use the fd to turn it into a Python
> file object. Then the amount of change should be pretty minimal.
I'd have to touch most functions in import.c and related files to change
find_module() to use a file descriptor. It's a PITA and I don't think
it's worse the effort for now.
The new patch adds PyFile_FromFd and removes the other PyFile_FromFile*
functions. It also changes some methods to use a file descriptor and
some documentation. Two minor changes aren't related to the bug but they
nagged me.
Added file: http://bugs.python.org/file8585/py3k_filefromfd.patch
__________________________________
Tracker <[EMAIL PROTECTED]>
<http://bugs.python.org/issue1267>
__________________________________
Index: Python/pythonrun.c
===================================================================
--- Python/pythonrun.c (revision 58574)
+++ Python/pythonrun.c (working copy)
@@ -719,7 +719,7 @@
}
/* Set sys.stdin */
- if (!(std = PyFile_FromFileEx(stdin, "<stdin>", "r", fclose, -1,
+ if (!(std = PyFile_FromFd(STDIN_FILENO, "<stdin>", "r", -1,
NULL, "\n"))) {
goto error;
}
@@ -728,7 +728,7 @@
Py_DECREF(std);
/* Set sys.stdout */
- if (!(std = PyFile_FromFileEx(stdout, "<stdout>", "w", fclose, -1,
+ if (!(std = PyFile_FromFd(STDOUT_FILENO, "<stdout>", "w", -1,
NULL, "\n"))) {
goto error;
}
@@ -737,7 +737,7 @@
Py_DECREF(std);
/* Set sys.stderr */
- if (!(std = PyFile_FromFileEx(stderr, "<stderr>", "w", fclose, -1,
+ if (!(std = PyFile_FromFd(STDERR_FILENO, "<stderr>", "w", -1,
NULL, "\n"))) {
goto error;
}
Index: Python/import.c
===================================================================
--- Python/import.c (revision 58574)
+++ Python/import.c (working copy)
@@ -92,7 +92,7 @@
extern struct _inittab _PyImport_Inittab[];
/* Method from Parser/tokenizer.c */
-extern char * PyTokenizer_FindEncoding(FILE *fp);
+extern char * PyTokenizer_FindEncoding(int);
struct _inittab *PyImport_Inittab = _PyImport_Inittab;
@@ -2561,6 +2561,7 @@
struct filedescr *fdp;
char pathname[MAXPATHLEN+1];
FILE *fp = NULL;
+ int fd = -1;
char *found_encoding = NULL;
char *encoding = NULL;
@@ -2571,17 +2572,24 @@
if (fdp == NULL)
return NULL;
if (fp != NULL) {
+ fd = fileno(fp);
+ if (fd != -1)
+ fd = dup(fd);
+ fclose(fp);
+ fp = NULL;
+ }
+ if (fd != -1) {
if (strchr(fdp->mode, 'b') == NULL) {
/* PyTokenizer_FindEncoding() returns PyMem_MALLOC'ed
memory. */
- found_encoding = PyTokenizer_FindEncoding(fp);
+ found_encoding = PyTokenizer_FindEncoding(fd);
encoding = (found_encoding != NULL) ? found_encoding :
(char*)PyUnicode_GetDefaultEncoding();
}
- fob = PyFile_FromFileEx(fp, pathname, fdp->mode, fclose, -1,
+ fob = PyFile_FromFd(fd, pathname, fdp->mode, -1,
(char*)encoding, NULL);
if (fob == NULL) {
- fclose(fp);
+ close(fd);
PyMem_FREE(found_encoding);
return NULL;
}
Index: Include/fileobject.h
===================================================================
--- Include/fileobject.h (revision 58574)
+++ Include/fileobject.h (working copy)
@@ -8,10 +8,7 @@
#define PY_STDIOTEXTMODE "b"
-PyAPI_FUNC(PyObject *) PyFile_FromFile(FILE *, char *, char *, int (*)(FILE*));
-PyAPI_FUNC(PyObject *) PyFile_FromFileEx(FILE *, char *, char *,
- int (*)(FILE *), int, char *,
- char *);
+PyAPI_FUNC(PyObject *) PyFile_FromFd(int, char *, char *, int, char *, char *);
PyAPI_FUNC(PyObject *) PyFile_GetLine(PyObject *, int);
PyAPI_FUNC(int) PyFile_WriteObject(PyObject *, PyObject *, int);
PyAPI_FUNC(int) PyFile_WriteString(const char *, PyObject *);
Index: Objects/fileobject.c
===================================================================
--- Objects/fileobject.c (revision 58574)
+++ Objects/fileobject.c (working copy)
@@ -26,21 +26,15 @@
/* External C interface */
PyObject *
-PyFile_FromFile(FILE *fp, char *name, char *mode, int (*close)(FILE *))
+PyFile_FromFd(int fd, char *name, char *mode, int buffering, char *encoding,
+ char *newline)
{
- return PyFile_FromFileEx(fp, name, mode, close, -1, NULL, NULL);
-}
-
-PyObject *
-PyFile_FromFileEx(FILE *fp, char *name, char *mode, int (*close)(FILE *),
- int buffering, char *encoding, char *newline)
-{
PyObject *io, *stream, *nameobj=NULL;
io = PyImport_ImportModule("io");
if (io == NULL)
return NULL;
- stream = PyObject_CallMethod(io, "open", "isiss", fileno(fp), mode,
+ stream = PyObject_CallMethod(io, "open", "isiss", fd, mode,
buffering, encoding, newline);
Py_DECREF(io);
if (stream == NULL)
Index: Objects/bytesobject.c
===================================================================
--- Objects/bytesobject.c (revision 58574)
+++ Objects/bytesobject.c (working copy)
@@ -1214,7 +1214,7 @@
Py_ssize_t len = PyBytes_GET_SIZE(self);
const char* str;
Py_buffer vsubstr;
- int rv;
+ int rv = -1;
str = PyBytes_AS_STRING(self);
Index: Misc/NEWS
===================================================================
--- Misc/NEWS (revision 58574)
+++ Misc/NEWS (working copy)
@@ -8,6 +8,18 @@
*Unreleased*
+Core and Builtins
+-----------------
+
+- Replaced `PyFile_FromFile()` with `PyFile_FromFd(fd, name. mode, buffer,
+ encoding, newline)`
+
+- Fixed `imp.find_module()` to obey the -*- coding: -*- header.
+
+- Changed `__file__` and `co_filename` to unicode. The path names are decoded
+ with `Py_FileSystemDefaultEncoding` and a new API method
+ `PyUnicode_DecodeFSDefault(char*)` was added.
+
Extension Modules
-----------------
Index: Parser/tokenizer.c
===================================================================
--- Parser/tokenizer.c (revision 58574)
+++ Parser/tokenizer.c (working copy)
@@ -1612,13 +1612,19 @@
when no longer needed.
*/
char *
-PyTokenizer_FindEncoding(FILE *fp) {
+PyTokenizer_FindEncoding(int fd) {
struct tok_state *tok;
+ FILE *fp;
char *p_start=NULL, *p_end=NULL, *encoding=NULL;
+ fp = fdopen(dup(fd), "r");
+ if (fp == NULL)
+ return NULL;
+
if ((tok = PyTokenizer_FromFile(fp, NULL, NULL, NULL)) == NULL) {
/* lseek() usage is on purpose; see note later in code. */
- lseek(fileno(fp), 0, 0);
+ fclose(fp);
+ lseek(fd, 0, 0);
return NULL;
}
while(((tok->lineno < 2) && (tok->done == E_OK))) {
@@ -1628,7 +1634,8 @@
/* lseek() must be used instead of fseek()/rewind() as those fail on
OS X 10.4 to properly seek back to the beginning when reading from
the file descriptor instead of the file pointer. */
- lseek(fileno(fp), 0, 0);
+ fclose(fp);
+ lseek(fd, 0, 0);
if (tok->encoding) {
encoding = (char *)PyMem_MALLOC(strlen(tok->encoding));
Index: Parser/tokenizer.h
===================================================================
--- Parser/tokenizer.h (revision 58574)
+++ Parser/tokenizer.h (working copy)
@@ -67,7 +67,7 @@
extern int PyTokenizer_Get(struct tok_state *, char **, char **);
extern char * PyTokenizer_RestoreEncoding(struct tok_state* tok,
int len, int *offset);
-extern char * PyTokenizer_FindEncoding(FILE *fp);
+extern char * PyTokenizer_FindEncoding(int);
#ifdef __cplusplus
}
Index: Doc/c-api/concrete.rst
===================================================================
--- Doc/c-api/concrete.rst (revision 58575)
+++ Doc/c-api/concrete.rst (working copy)
@@ -2410,33 +2410,25 @@
:ctype:`PyFileObject`.
-.. cfunction:: PyObject* PyFile_FromString(char *filename, char *mode)
+.. cfunction:: PyFile_FromFd(int fd, char *name, char *mode, int buffering, char *encoding, char *newline)
- .. index:: single: fopen()
+ Create a new :ctype:`PyFileObject` from the file descriptor of an already
+ opened file *fd*. The arguments *name*, *encoding* and *newline* can be
+ *NULL* as well as buffering can be *-1* to use the defaults. Return *NULL* on
+ failure.
- On success, return a new file object that is opened on the file given by
- *filename*, with a file mode given by *mode*, where *mode* has the same
- semantics as the standard C routine :cfunc:`fopen`. On failure, return *NULL*.
+ .. warning::
+ Take care when you are mixing streams and descriptors! For more
+ information, see `GNU C Library
+ <http://www.gnu.org/software/libc/manual/html_node/Stream_002fDescriptor-Precautions.html#Stream_002fDescriptor-Precautions>`_.
-.. cfunction:: PyObject* PyFile_FromFile(FILE *fp, char *name, char *mode, int (*close)(FILE*))
- Create a new :ctype:`PyFileObject` from the already-open standard C file
- pointer, *fp*. The function *close* will be called when the file should be
- closed. Return *NULL* on failure.
+.. cfunction:: int PyObject_AsFileDescriptor(PyObject *p)
-.. cfunction:: PyFile_FromFileEx(FILE *fp, char *name, char *mode, int (*close)(FILE *), int buffering, char *encoding, char *newline)
+ Return the file descriptor associated with *p* as an :ctype:`int`.
- Create a new :ctype:`PyFileObject` from the already-open standard C file
- pointer, *fp*. The functions works similar to *PyFile_FromFile* but takes
- optional arguments for *buffering*, *encoding* and *newline*. Use -1 resp.
- *NULL* for default values.
-.. cfunction:: FILE* PyFile_AsFile(PyObject *p)
-
- Return the file object associated with *p* as a :ctype:`FILE\*`.
-
-
.. cfunction:: PyObject* PyFile_GetLine(PyObject *p, int n)
.. index:: single: EOFError (built-in exception)
Index: Doc/reference/introduction.rst
===================================================================
--- Doc/reference/introduction.rst (revision 58575)
+++ Doc/reference/introduction.rst (working copy)
@@ -60,7 +60,7 @@
This implementation actually uses the CPython implementation, but is a managed
.NET application and makes .NET libraries available. This was created by Brian
Lloyd. For more information, see the `Python for .NET home page
- <http://www.zope.org/Members/Brian/PythonNet>`_.
+ <http://pythonnet.sourceforge.net>`_.
IronPython
An alternate Python for .NET. Unlike Python.NET, this is a complete Python
Index: Lib/test/test_imp.py
===================================================================
--- Lib/test/test_imp.py (revision 58574)
+++ Lib/test/test_imp.py (working copy)
@@ -44,6 +44,18 @@
fd = imp.find_module("heapq")[0]
self.assertEqual(fd.encoding, "iso-8859-1")
+ def test_issue1267(self):
+ fd, filename, info = imp.find_module("pydoc")
+ self.assertEqual(fd.encoding, "iso-8859-1")
+ self.assertEqual(fd.tell(), 0)
+ self.assertEqual(fd.readline(), '#!/usr/bin/env python\n')
+
+ fd, filename, info = imp.find_module("tokenize")
+ self.assertEqual(fd.encoding, "utf-8")
+ self.assertEqual(fd.tell(), 0)
+ self.assertEqual(fd.readline(), '"""Tokenization help for Python programs.\n')
+
+
def test_main():
test_support.run_unittest(
LockTests,
Index: Modules/posixmodule.c
===================================================================
--- Modules/posixmodule.c (revision 58574)
+++ Modules/posixmodule.c (working copy)
@@ -5386,11 +5386,18 @@
posix_tmpfile(PyObject *self, PyObject *noargs)
{
FILE *fp;
+ int fd;
fp = tmpfile();
if (fp == NULL)
return posix_error();
- return PyFile_FromFile(fp, "<tmpfile>", "w+b", fclose);
+ fd = fileno(fp);
+ if (fd != -1)
+ fd = dup(fd);
+ fclose(fp);
+ if (fd == -1)
+ return posix_error();
+ return PyFile_FromFd(fd, "<tmpfile>", "w+b", -1, NULL, NULL);
}
#endif
_______________________________________________
Python-bugs-list mailing list
Unsubscribe:
http://mail.python.org/mailman/options/python-bugs-list/archive%40mail-archive.com