gh-99726: Improves correctness of stat results for Windows, and uses …

…faster API when available
zooba · Mar 16, 2023 · Feb 22, 2023 · Feb 22, 2023 · Feb 22, 2023 · Feb 28, 2023
commit 5187810c2a24e6b12c612e5cd8bdd2018fab7d0a
diff --git a/Doc/library/os.rst b/Doc/library/os.rst
@@ -2790,6 +2790,10 @@ features:
       Added support for the :class:`~os.PathLike` interface.  Added support
       for :class:`bytes` paths on Windows.
 
+   .. versionchanged:: 3.12
+      The ``st_ctime`` attributes of a stat result are now set to zero, rather
+      than being incorrectly set to the creation time of the file.
+
 
 .. function:: stat(path, *, dir_fd=None, follow_symlinks=True)
 
@@ -2905,10 +2909,7 @@ features:
 
    .. attribute:: st_ctime
 
-      Platform dependent:
-
-      * the time of most recent metadata change on Unix,
-      * the time of creation on Windows, expressed in seconds.
+      Time of most recent metadata change expressed in seconds.
 
    .. attribute:: st_atime_ns
 
@@ -2921,11 +2922,8 @@ features:
 
    .. attribute:: st_ctime_ns
 
-      Platform dependent:
-
-      * the time of most recent metadata change on Unix,
-      * the time of creation on Windows, expressed in nanoseconds as an
-        integer.
+      Time of most recent metadata change expressed in nanoseconds as an
+      integer.
 
    .. note::
 
@@ -2975,7 +2973,7 @@ features:
 
    .. attribute:: st_birthtime
 
-      Time of file creation.
+      Time of file creation. This is also available on Windows.
 
    On Solaris and derivatives, the following attributes may also be
    available:
@@ -2999,7 +2997,8 @@ features:
 
       File type.
 
-   On Windows systems, the following attributes are also available:
+   On Windows systems, as well as ``st_birthtime`` above, the following
+   attributes are also available:
 
    .. attribute:: st_file_attributes
 
@@ -3049,6 +3048,24 @@ features:
       files as :const:`S_IFCHR`, :const:`S_IFIFO` or :const:`S_IFBLK`
       as appropriate.
 
+   .. versionchanged:: 3.12
+      On Windows, :attr:`st_ctime` now also contains the last metadata
+      change time, for consistency with other platforms.
+      Use :attr:`st_birthtime` for the creation time when available.
+
+   .. versionchanged:: 3.12
+      On Windows, :attr:`st_ino` may now be up to 128 bits, depending
+      on the file system. Previously it would not be above 64 bits, and
+      larger file identifiers would be arbitrarily packed.
+
+   .. versionchanged:: 3.12
+      On Windows, :attr:`st_rdev` no longer returns a value. Previously
+      it would contain the same as :attr:`st_dev`, which was incorrect.
+
+   .. versionadded:: 3.12
+      Added the :attr:`st_birthtime` on Windows
+
+
 .. function:: statvfs(path)
 
    Perform a :c:func:`statvfs` system call on the given path.  The return value is

@@ -292,6 +292,15 @@ os
   method to check if the entry is a junction.
   (Contributed by Charles Machalow in :gh:`99547`.)
 
+* :func:`os.stat` and :func:`os.lstat` are now more accurate on Windows.
+  The ``st_birthtime`` field will now be filled with the creation time
+  of the file, and ``st_ctime`` now returns the last metadata change,
+  for consistency with other platforms. ``st_ino`` may now be up to 128
+  bits, depending on your file system, and ``st_rdev`` is always set to
+  zero rather than to incorrect values. 
+  Both functions may be significantly faster on newer releases of
+  Windows. (Contributed by Steve Dower in :gh:`99726`.)
+
 os.path
 -------
 

diff --git a/Include/internal/pycore_fileutils.h b/Include/internal/pycore_fileutils.h
@@ -66,7 +66,7 @@ PyAPI_FUNC(PyObject *) _Py_device_encoding(int);
 
 #ifdef MS_WINDOWS
 struct _Py_stat_struct {
-    unsigned long st_dev;
+    uint64_t st_dev;
     uint64_t st_ino;
     unsigned short st_mode;
     int st_nlink;
@@ -80,8 +80,11 @@ struct _Py_stat_struct {
     int st_mtime_nsec;
     time_t st_ctime;
     int st_ctime_nsec;
+    time_t st_birthtime;
+    int st_birthtime_nsec;
     unsigned long st_file_attributes;
     unsigned long st_reparse_tag;
+    uint64_t st_ino_high;
 };
 #else
 #  define _Py_stat_struct stat

diff --git a/Include/internal/pycore_fileutils_windows.h b/Include/internal/pycore_fileutils_windows.h
@@ -0,0 +1,80 @@
+#ifndef Py_INTERNAL_FILEUTILS_WINDOWS_H
+#define Py_INTERNAL_FILEUTILS_WINDOWS_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_BUILD_CORE
+#  error "Py_BUILD_CORE must be defined to include this header"
+#endif
+
+#ifdef MS_WINDOWS
+
+#if !defined(NTDDI_WIN10_NI) || !(NTDDI_VERSION >= NTDDI_WIN10_NI)
+typedef struct _FILE_STAT_BASIC_INFORMATION {
+    LARGE_INTEGER FileId;
+    LARGE_INTEGER CreationTime;
+    LARGE_INTEGER LastAccessTime;
+    LARGE_INTEGER LastWriteTime;
+    LARGE_INTEGER ChangeTime;
+    LARGE_INTEGER AllocationSize;
+    LARGE_INTEGER EndOfFile;
+    ULONG FileAttributes;
+    ULONG ReparseTag;
+    ULONG NumberOfLinks;
+    ULONG DeviceType;
+    ULONG DeviceCharacteristics;
+    ULONG Reserved;
+    ULONGLONG FileIdHigh;
+    ULONGLONG VolumeSerialNumber;
+} FILE_STAT_BASIC_INFORMATION;
+
+typedef enum _FILE_INFO_BY_NAME_CLASS {
+    FileStatByNameInfo,
+    FileStatLxByNameInfo,
+    FileCaseSensitiveByNameInfo,
+    FileStatBasicByNameInfo,
+    MaximumFileInfoByNameClass
+} FILE_INFO_BY_NAME_CLASS;
+#endif
+
+typedef BOOL (WINAPI *PGetFileInformationByName)(
+    PCWSTR FileName,
+    FILE_INFO_BY_NAME_CLASS FileInformationClass,
+    PVOID FileInfoBuffer,
+    ULONG FileInfoBufferSize
+);
+
+static inline BOOL _Py_GetFileInformationByName(
+    PCWSTR FileName,
+    FILE_INFO_BY_NAME_CLASS FileInformationClass,
+    PVOID FileInfoBuffer,
+    ULONG FileInfoBufferSize
+) {
+    static PGetFileInformationByName GetFileInformationByName = NULL;
+    static int GetFileInformationByName_init = -1;
+
+    if (GetFileInformationByName_init < 0) {
+        HMODULE hMod = LoadLibraryW(L"api-ms-win-core-file-l2-1-4");
+        GetFileInformationByName_init = 0;
+        if (hMod) {
+            GetFileInformationByName = (PGetFileInformationByName)GetProcAddress(
+                hMod, "GetFileInformationByName");
+            if (GetFileInformationByName) {
+                GetFileInformationByName_init = 1;
+            } else {
+                FreeLibrary(hMod);
+            }
+        }
+    }
+
+    if (GetFileInformationByName_init <= 0) {
+        SetLastError(ERROR_NOT_SUPPORTED);
+        return FALSE;
+    }
+    return GetFileInformationByName(FileName, FileInformationClass, FileInfoBuffer, FileInfoBufferSize);
+}
+
+#endif
+
+#endif
diff --git a/Lib/test/test_os.py b/Lib/test/test_os.py
@@ -4164,7 +4164,8 @@ def assert_stat_equal(self, stat1, stat2, skip_fields):
             for attr in dir(stat1):
                 if not attr.startswith("st_"):
                     continue
-                if attr in ("st_dev", "st_ino", "st_nlink"):
+                if attr in ("st_dev", "st_ino", "st_nlink", "st_ctime",
+                            "st_ctime_ns"):
                     continue
                 self.assertEqual(getattr(stat1, attr),
                                  getattr(stat2, attr),

diff --git a/Misc/NEWS.d/next/Windows/2023-02-22-17-26-10.gh-issue-99726.76t957.rst b/Misc/NEWS.d/next/Windows/2023-02-22-17-26-10.gh-issue-99726.76t957.rst
@@ -0,0 +1,2 @@
+Improves correctness of stat results for Windows, and uses faster API when
+available
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		Improves correctness of stat results for Windows, and uses faster API when
		available