Python - Windows 原始磁盘无法读取最终扇区
Python - Windows Raw Disk unable to read final sectors
当通过 Python open() 访问 Windows 上的原始磁盘时，无论出于何种原因，它都不允许我读取最后的 10240 字节（也就是 2048 处的最后 5 个扇区 bytes/sector).
通过其他方式转储光盘映像并比较映像时，我可以看到数据也不能被认为是空的。事实上，第一个丢失的扇区有一个 UDF 锚标记，其中包含相关的元数据。以下扇区完全空白。
这是我转储光盘内容的方式：
out = open("test.iso", "wb")
with open(r"\.\D:", "rb") as f:
while True:
data = f.read(512)
if len(data) == 0:
break
out.write(data)
如果我使用同一个 open() 对象并告诉它搜索到光盘的最末端，它就会执行。所以它至少在寻求方面可以清楚地到达部门。如果我然后返回 10240 字节然后尝试 f.read(...)，它 returns b''（空结果）而不是错误。我告诉它阅读什么尺寸也没关系。各种尺码我都试过了，no-arg/default、1、12、255、512、2048、999999等
另一个关于不同（但相关）问题的 Whosebug answer 也报告了关于增强型音频光盘的类似发现，但此后似乎没有讨论。
我已经在来自不同类型的工作室和创作者的多张 DVD 光盘上对此进行了测试，所有这些都处于良好状态并且仍在发生。
Example reproducing code:
- 我不知道它是否会发生在你的系统上config/disc/reader)。
- PyPI 依赖项：wmic
- WMIC 也报告磁盘大小为 10240，也许这是一个 Windows 问题？
import os
from wmi import WMI
DISC_LETTER = "D:"
c = WMI()
disc_info = next(iter(c.Win32_CDROMDrive(Drive=DISC_LETTER)), None)
if not disc_info:
raise("Disc %s not found...", DISC_LETTER)
disc_size = int(disc_info.size)
disc_size += 10240 # WMIC also reports the size without 10240, but it is real!
f = open(r"\.\%s" % DISC_LETTER, "rb")
f.seek(disc_size)
if f.tell() == disc_size:
print("Seeked to the end of the disc...")
f.seek(-10240, os.SEEK_CUR)
if f.tell() == disc_size - (2048 * 5):
print("Seeked 5 sectors before the end of the disc...")
data = f.read(2048 * 5):
print("Data read (len: %d): %b" % (len(data), data))
任何关于为什么这可能会很好的想法都会很棒，因为我已经尽我所能。
这似乎是因为 open(r'\.\N:') 打开具有受限边界的设备。
我的解决方案是使用 IOCTL 而不是 open() 打开光盘。特别是 CreateFile, DeviceIoControl, and FSCTL_ALLOW_EXTENDED_DASD_IO.
handle = win32file.CreateFile(
r"\.\D:",
win32con.MAXIMUM_ALLOWED,
win32con.FILE_SHARE_READ | win32con.FILE_SHARE_WRITE,
None,
win32con.OPEN_EXISTING,
win32con.FILE_ATTRIBUTE_NORMAL,
None
)
if handle == win32file.INVALID_HANDLE_VALUE:
raise RuntimeError("Failed to obtain device handle...")
win32file.DeviceIoControl(handle, winioctlcon.FSCTL_ALLOW_EXTENDED_DASD_IO, None, None)
从这里我可以使用 ReadFile and SetFilePointer 分别替代 read 和 seek。
我什至开发了一个新的 class，可以加载所有内容并允许您动态读取和查找，而不必担心扇区对齐。
class Win32Device:
"""
Class to read and seek a Windows Raw Device IO object without bother.
It deals with getting the full size, allowing full access to all sectors,
and alignment with the discs sector size.
Author: PHOENiX <pragma.exe@gmail.com>
License: Free, enjoy! This should be a thing open() does by default.
"""
def __init__(self, target):
# type: (str) -> None
self.target = target
self.sector_size = None
self.disc_size = None
self.position = 0
self.handle = self.get_handle()
self.geometry = self.get_geometry()
def __enter__(self):
return self
def __exit__(self, *_, **__):
self.dispose()
def __len__(self) -> int:
return self.geometry[-2]
def dispose(self):
if self.handle != win32file.INVALID_HANDLE_VALUE:
win32file.CloseHandle(self.handle)
def get_target(self):
# type: () -> str
"""Get UNC target name. Can be `E:` or `PhysicalDriveN`."""
target = self.target
if not target.startswith("\\.\"):
target += rf"\.\{target}"
return target
def get_handle(self):
# type: () -> int
"""Get a direct handle to the raw UNC target, and unlock its IO capabilities."""
handle = win32file.CreateFile(
# https://docs.microsoft.com/en-us/windows/win32/api/fileapi/nf-fileapi-createfilea
self.get_target(), # target
win32con.MAXIMUM_ALLOWED, # desired access
win32con.FILE_SHARE_READ | win32con.FILE_SHARE_WRITE, # share mode, write needed
None, # security attributes
win32con.OPEN_EXISTING, # creation disposition
win32con.FILE_ATTRIBUTE_NORMAL, # flags and attributes
None # template file
)
if handle == win32file.INVALID_HANDLE_VALUE:
raise RuntimeError("Failed to obtain device handle...")
# elevate accessible sectors, without this the last 5 sectors (in my case) will not be readable
win32file.DeviceIoControl(handle, winioctlcon.FSCTL_ALLOW_EXTENDED_DASD_IO, None, None)
return handle
def get_geometry(self):
# type: () -> tuple[int, ...]
"""
Retrieves information about the physical disk's geometry.
https://docs.microsoft.com/en-us/windows/win32/api/winioctl/ns-winioctl-disk_geometry_ex
Returns a tuple of:
Cylinders-Lo
Cylinders-Hi
Media Type
Tracks Per Cylinder
Sectors Per Track
Bytes Per Sector
Disk Size
Extra Data
"""
return struct.unpack("8L", win32file.DeviceIoControl(
self.handle, # handle
winioctlcon.IOCTL_DISK_GET_DRIVE_GEOMETRY_EX, # ioctl api
b"", # in buffer
32 # out buffer
))
def tell(self):
# type: () -> int
"""Get current (spoofed) position."""
return self.position
def _tell(self):
# type: () -> int
"""Get current real position."""
if not self.handle:
self.handle = self.get_handle()
return win32file.SetFilePointer(self.handle, 0, win32file.FILE_CURRENT)
def seek(self, offset, whence=os.SEEK_SET):
# type: (int, int) -> int
"""Seek at any point in the stream, in an aligned way."""
if whence == os.SEEK_CUR:
whence = self.tell()
elif whence == os.SEEK_END:
whence = len(self)
to = whence + offset
closest = self.align(to) # get as close as we can while being aligned
if not self.handle:
self.handle = self.get_handle()
pos = win32file.SetFilePointer(self.handle, closest, win32file.FILE_BEGIN)
if pos != closest:
raise IOError(f"Seek was not precise...")
self.position = to # not actually at this location, read will deal with it
return to
def read(self, size=-1):
# type: (int) -> Optional[bytes]
"""Read any amount of bytes in the stream, in an aligned way."""
if not self.handle:
self.handle = self.get_handle()
sector_size = self.geometry[-3]
offset = abs(self._tell() - self.tell())
has_data = b''
while self._tell() < self.tell() + size:
res, data = win32file.ReadFile(self.handle, sector_size, None)
if res != 0:
raise IOError(f"An error occurred: {res} {data}")
if len(data) < sector_size:
raise IOError(f"Read {sector_size - len(data)} less bytes than requested...")
has_data += data
# seek to the position wanted + size read, which will then be re-aligned
self.seek(self.tell() + size)
return has_data[offset:offset + size]
def align(self, size, to=None):
# type: (int, Optional[int]) -> int
"""
Align size to the closest but floor mod `to` value.
Examples:
align(513, to=512)
>>>512
align(1023, to=512)
>>>512
align(1026, to=512)
>>>1024
align(12, to=10)
>>>10
"""
if not to:
to = self.geometry[-3] # logical bytes per sector value
return math.floor(size / to) * to
当通过 Python open() 访问 Windows 上的原始磁盘时，无论出于何种原因，它都不允许我读取最后的 10240 字节（也就是 2048 处的最后 5 个扇区 bytes/sector).
通过其他方式转储光盘映像并比较映像时，我可以看到数据也不能被认为是空的。事实上，第一个丢失的扇区有一个 UDF 锚标记，其中包含相关的元数据。以下扇区完全空白。
这是我转储光盘内容的方式：
out = open("test.iso", "wb")
with open(r"\.\D:", "rb") as f:
while True:
data = f.read(512)
if len(data) == 0:
break
out.write(data)
如果我使用同一个 open() 对象并告诉它搜索到光盘的最末端，它就会执行。所以它至少在寻求方面可以清楚地到达部门。如果我然后返回 10240 字节然后尝试 f.read(...)，它 returns b''（空结果）而不是错误。我告诉它阅读什么尺寸也没关系。各种尺码我都试过了，no-arg/default、1、12、255、512、2048、999999等
另一个关于不同（但相关）问题的 Whosebug answer 也报告了关于增强型音频光盘的类似发现，但此后似乎没有讨论。
我已经在来自不同类型的工作室和创作者的多张 DVD 光盘上对此进行了测试，所有这些都处于良好状态并且仍在发生。
Example reproducing code:
- 我不知道它是否会发生在你的系统上config/disc/reader)。
- PyPI 依赖项：wmic
- WMIC 也报告磁盘大小为 10240，也许这是一个 Windows 问题？
import os
from wmi import WMI
DISC_LETTER = "D:"
c = WMI()
disc_info = next(iter(c.Win32_CDROMDrive(Drive=DISC_LETTER)), None)
if not disc_info:
raise("Disc %s not found...", DISC_LETTER)
disc_size = int(disc_info.size)
disc_size += 10240 # WMIC also reports the size without 10240, but it is real!
f = open(r"\.\%s" % DISC_LETTER, "rb")
f.seek(disc_size)
if f.tell() == disc_size:
print("Seeked to the end of the disc...")
f.seek(-10240, os.SEEK_CUR)
if f.tell() == disc_size - (2048 * 5):
print("Seeked 5 sectors before the end of the disc...")
data = f.read(2048 * 5):
print("Data read (len: %d): %b" % (len(data), data))
任何关于为什么这可能会很好的想法都会很棒，因为我已经尽我所能。
这似乎是因为 open(r'\.\N:') 打开具有受限边界的设备。
我的解决方案是使用 IOCTL 而不是 open() 打开光盘。特别是 CreateFile, DeviceIoControl, and FSCTL_ALLOW_EXTENDED_DASD_IO.
handle = win32file.CreateFile(
r"\.\D:",
win32con.MAXIMUM_ALLOWED,
win32con.FILE_SHARE_READ | win32con.FILE_SHARE_WRITE,
None,
win32con.OPEN_EXISTING,
win32con.FILE_ATTRIBUTE_NORMAL,
None
)
if handle == win32file.INVALID_HANDLE_VALUE:
raise RuntimeError("Failed to obtain device handle...")
win32file.DeviceIoControl(handle, winioctlcon.FSCTL_ALLOW_EXTENDED_DASD_IO, None, None)
从这里我可以使用 ReadFile and SetFilePointer 分别替代 read 和 seek。
我什至开发了一个新的 class，可以加载所有内容并允许您动态读取和查找，而不必担心扇区对齐。
class Win32Device:
"""
Class to read and seek a Windows Raw Device IO object without bother.
It deals with getting the full size, allowing full access to all sectors,
and alignment with the discs sector size.
Author: PHOENiX <pragma.exe@gmail.com>
License: Free, enjoy! This should be a thing open() does by default.
"""
def __init__(self, target):
# type: (str) -> None
self.target = target
self.sector_size = None
self.disc_size = None
self.position = 0
self.handle = self.get_handle()
self.geometry = self.get_geometry()
def __enter__(self):
return self
def __exit__(self, *_, **__):
self.dispose()
def __len__(self) -> int:
return self.geometry[-2]
def dispose(self):
if self.handle != win32file.INVALID_HANDLE_VALUE:
win32file.CloseHandle(self.handle)
def get_target(self):
# type: () -> str
"""Get UNC target name. Can be `E:` or `PhysicalDriveN`."""
target = self.target
if not target.startswith("\\.\"):
target += rf"\.\{target}"
return target
def get_handle(self):
# type: () -> int
"""Get a direct handle to the raw UNC target, and unlock its IO capabilities."""
handle = win32file.CreateFile(
# https://docs.microsoft.com/en-us/windows/win32/api/fileapi/nf-fileapi-createfilea
self.get_target(), # target
win32con.MAXIMUM_ALLOWED, # desired access
win32con.FILE_SHARE_READ | win32con.FILE_SHARE_WRITE, # share mode, write needed
None, # security attributes
win32con.OPEN_EXISTING, # creation disposition
win32con.FILE_ATTRIBUTE_NORMAL, # flags and attributes
None # template file
)
if handle == win32file.INVALID_HANDLE_VALUE:
raise RuntimeError("Failed to obtain device handle...")
# elevate accessible sectors, without this the last 5 sectors (in my case) will not be readable
win32file.DeviceIoControl(handle, winioctlcon.FSCTL_ALLOW_EXTENDED_DASD_IO, None, None)
return handle
def get_geometry(self):
# type: () -> tuple[int, ...]
"""
Retrieves information about the physical disk's geometry.
https://docs.microsoft.com/en-us/windows/win32/api/winioctl/ns-winioctl-disk_geometry_ex
Returns a tuple of:
Cylinders-Lo
Cylinders-Hi
Media Type
Tracks Per Cylinder
Sectors Per Track
Bytes Per Sector
Disk Size
Extra Data
"""
return struct.unpack("8L", win32file.DeviceIoControl(
self.handle, # handle
winioctlcon.IOCTL_DISK_GET_DRIVE_GEOMETRY_EX, # ioctl api
b"", # in buffer
32 # out buffer
))
def tell(self):
# type: () -> int
"""Get current (spoofed) position."""
return self.position
def _tell(self):
# type: () -> int
"""Get current real position."""
if not self.handle:
self.handle = self.get_handle()
return win32file.SetFilePointer(self.handle, 0, win32file.FILE_CURRENT)
def seek(self, offset, whence=os.SEEK_SET):
# type: (int, int) -> int
"""Seek at any point in the stream, in an aligned way."""
if whence == os.SEEK_CUR:
whence = self.tell()
elif whence == os.SEEK_END:
whence = len(self)
to = whence + offset
closest = self.align(to) # get as close as we can while being aligned
if not self.handle:
self.handle = self.get_handle()
pos = win32file.SetFilePointer(self.handle, closest, win32file.FILE_BEGIN)
if pos != closest:
raise IOError(f"Seek was not precise...")
self.position = to # not actually at this location, read will deal with it
return to
def read(self, size=-1):
# type: (int) -> Optional[bytes]
"""Read any amount of bytes in the stream, in an aligned way."""
if not self.handle:
self.handle = self.get_handle()
sector_size = self.geometry[-3]
offset = abs(self._tell() - self.tell())
has_data = b''
while self._tell() < self.tell() + size:
res, data = win32file.ReadFile(self.handle, sector_size, None)
if res != 0:
raise IOError(f"An error occurred: {res} {data}")
if len(data) < sector_size:
raise IOError(f"Read {sector_size - len(data)} less bytes than requested...")
has_data += data
# seek to the position wanted + size read, which will then be re-aligned
self.seek(self.tell() + size)
return has_data[offset:offset + size]
def align(self, size, to=None):
# type: (int, Optional[int]) -> int
"""
Align size to the closest but floor mod `to` value.
Examples:
align(513, to=512)
>>>512
align(1023, to=512)
>>>512
align(1026, to=512)
>>>1024
align(12, to=10)
>>>10
"""
if not to:
to = self.geometry[-3] # logical bytes per sector value
return math.floor(size / to) * to