This page hosts a formal specification of VMWare Virtual Disk using Kaitai Struct. This specification can be automatically translated into a variety of programming languages to get a parsing library.
All parsing code for Python generated by Kaitai Struct depends on the Python runtime library. You have to install it before you can parse data.
The Python runtime library can be installed from PyPI:
python3 -m pip install kaitaistructParse a local file and get structure in memory:
data = VmwareVmdk.from_file("path/to/local/file.vmdk")
Or parse structure from a bytes:
from kaitaistruct import KaitaiStream, BytesIO
raw = b"\x00\x01\x02..."
data = VmwareVmdk(KaitaiStream(BytesIO(raw)))
After that, one can get various attributes from the structure by invoking getter methods like:
data.size_max # => Maximum number of sectors in a given image file (capacity)
# This is a generated file! Please edit source .ksy file and use kaitai-struct-compiler to rebuild
# type: ignore
import kaitaistruct
from kaitaistruct import KaitaiStruct, KaitaiStream, BytesIO
from enum import IntEnum
if getattr(kaitaistruct, 'API_VERSION', (0, 9)) < (0, 11):
raise Exception("Incompatible Kaitai Struct Python API: 0.11 or later is required, but you have %s" % (kaitaistruct.__version__))
class VmwareVmdk(KaitaiStruct):
"""
.. seealso::
Source - https://github.com/libyal/libvmdk/blob/main/documentation/VMWare%20Virtual%20Disk%20Format%20(VMDK).asciidoc#41-file-header
"""
class CompressionMethods(IntEnum):
none = 0
deflate = 1
def __init__(self, _io, _parent=None, _root=None):
super(VmwareVmdk, self).__init__(_io)
self._parent = _parent
self._root = _root or self
self._read()
def _read(self):
self.magic = self._io.read_bytes(4)
if not self.magic == b"\x4B\x44\x4D\x56":
raise kaitaistruct.ValidationNotEqualError(b"\x4B\x44\x4D\x56", self.magic, self._io, u"/seq/0")
self.version = self._io.read_s4le()
self.flags = VmwareVmdk.HeaderFlags(self._io, self, self._root)
self.size_max = self._io.read_s8le()
self.size_grain = self._io.read_s8le()
self.start_descriptor = self._io.read_s8le()
self.size_descriptor = self._io.read_s8le()
self.num_grain_table_entries = self._io.read_s4le()
self.start_secondary_grain = self._io.read_s8le()
self.start_primary_grain = self._io.read_s8le()
self.size_metadata = self._io.read_s8le()
self.is_dirty = self._io.read_u1()
self.stuff = self._io.read_bytes(4)
self.compression_method = KaitaiStream.resolve_enum(VmwareVmdk.CompressionMethods, self._io.read_u2le())
def _fetch_instances(self):
pass
self.flags._fetch_instances()
_ = self.descriptor
if hasattr(self, '_m_descriptor'):
pass
_ = self.grain_primary
if hasattr(self, '_m_grain_primary'):
pass
_ = self.grain_secondary
if hasattr(self, '_m_grain_secondary'):
pass
class HeaderFlags(KaitaiStruct):
"""
.. seealso::
Source - https://github.com/libyal/libvmdk/blob/main/documentation/VMWare%20Virtual%20Disk%20Format%20(VMDK).asciidoc#411-flags
"""
def __init__(self, _io, _parent=None, _root=None):
super(VmwareVmdk.HeaderFlags, self).__init__(_io)
self._parent = _parent
self._root = _root
self._read()
def _read(self):
self.reserved1 = self._io.read_bits_int_be(5)
self.zeroed_grain_table_entry = self._io.read_bits_int_be(1) != 0
self.use_secondary_grain_dir = self._io.read_bits_int_be(1) != 0
self.valid_new_line_detection_test = self._io.read_bits_int_be(1) != 0
self.reserved2 = self._io.read_u1()
self.reserved3 = self._io.read_bits_int_be(6)
self.has_metadata = self._io.read_bits_int_be(1) != 0
self.has_compressed_grain = self._io.read_bits_int_be(1) != 0
self.reserved4 = self._io.read_u1()
def _fetch_instances(self):
pass
@property
def descriptor(self):
if hasattr(self, '_m_descriptor'):
return self._m_descriptor
_pos = self._io.pos()
self._io.seek(self.start_descriptor * self._root.len_sector)
self._m_descriptor = self._io.read_bytes(self.size_descriptor * self._root.len_sector)
self._io.seek(_pos)
return getattr(self, '_m_descriptor', None)
@property
def grain_primary(self):
if hasattr(self, '_m_grain_primary'):
return self._m_grain_primary
_pos = self._io.pos()
self._io.seek(self.start_primary_grain * self._root.len_sector)
self._m_grain_primary = self._io.read_bytes(self.size_grain * self._root.len_sector)
self._io.seek(_pos)
return getattr(self, '_m_grain_primary', None)
@property
def grain_secondary(self):
if hasattr(self, '_m_grain_secondary'):
return self._m_grain_secondary
_pos = self._io.pos()
self._io.seek(self.start_secondary_grain * self._root.len_sector)
self._m_grain_secondary = self._io.read_bytes(self.size_grain * self._root.len_sector)
self._io.seek(_pos)
return getattr(self, '_m_grain_secondary', None)
@property
def len_sector(self):
if hasattr(self, '_m_len_sector'):
return self._m_len_sector
self._m_len_sector = 512
return getattr(self, '_m_len_sector', None)