This page hosts a formal specification of Microsoft Compound File Binary (CFB), AKA OLE (Object Linking and Embedding) file format 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 = MicrosoftCfb.from_file("path/to/local/file.bin")
Or parse structure from a bytes:
from kaitaistruct import KaitaiStream, BytesIO
raw = b"\x00\x01\x02..."
data = MicrosoftCfb(KaitaiStream(BytesIO(raw)))
After that, one can get various attributes from the structure by invoking getter methods like:
data.header # => get header
# This is a generated file! Please edit source .ksy file and use kaitai-struct-compiler to rebuild
import kaitaistruct
from kaitaistruct import KaitaiStruct, KaitaiStream, BytesIO
from enum import Enum
if getattr(kaitaistruct, 'API_VERSION', (0, 9)) < (0, 9):
raise Exception("Incompatible Kaitai Struct Python API: 0.9 or later is required, but you have %s" % (kaitaistruct.__version__))
class MicrosoftCfb(KaitaiStruct):
def __init__(self, _io, _parent=None, _root=None):
self._io = _io
self._parent = _parent
self._root = _root if _root else self
self._read()
def _read(self):
self.header = MicrosoftCfb.CfbHeader(self._io, self, self._root)
class CfbHeader(KaitaiStruct):
def __init__(self, _io, _parent=None, _root=None):
self._io = _io
self._parent = _parent
self._root = _root if _root else self
self._read()
def _read(self):
self.signature = self._io.read_bytes(8)
if not self.signature == b"\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1":
raise kaitaistruct.ValidationNotEqualError(b"\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1", self.signature, self._io, u"/types/cfb_header/seq/0")
self.clsid = self._io.read_bytes(16)
if not self.clsid == b"\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00":
raise kaitaistruct.ValidationNotEqualError(b"\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", self.clsid, self._io, u"/types/cfb_header/seq/1")
self.version_minor = self._io.read_u2le()
self.version_major = self._io.read_u2le()
self.byte_order = self._io.read_bytes(2)
if not self.byte_order == b"\xFE\xFF":
raise kaitaistruct.ValidationNotEqualError(b"\xFE\xFF", self.byte_order, self._io, u"/types/cfb_header/seq/4")
self.sector_shift = self._io.read_u2le()
self.mini_sector_shift = self._io.read_u2le()
self.reserved1 = self._io.read_bytes(6)
self.size_dir = self._io.read_s4le()
self.size_fat = self._io.read_s4le()
self.ofs_dir = self._io.read_s4le()
self.transaction_seq = self._io.read_s4le()
self.mini_stream_cutoff_size = self._io.read_s4le()
self.ofs_mini_fat = self._io.read_s4le()
self.size_mini_fat = self._io.read_s4le()
self.ofs_difat = self._io.read_s4le()
self.size_difat = self._io.read_s4le()
self.difat = []
for i in range(109):
self.difat.append(self._io.read_s4le())
class FatEntries(KaitaiStruct):
def __init__(self, _io, _parent=None, _root=None):
self._io = _io
self._parent = _parent
self._root = _root if _root else self
self._read()
def _read(self):
self.entries = []
i = 0
while not self._io.is_eof():
self.entries.append(self._io.read_s4le())
i += 1
class DirEntry(KaitaiStruct):
class ObjType(Enum):
unknown = 0
storage = 1
stream = 2
root_storage = 5
class RbColor(Enum):
red = 0
black = 1
def __init__(self, _io, _parent=None, _root=None):
self._io = _io
self._parent = _parent
self._root = _root if _root else self
self._read()
def _read(self):
self.name = (self._io.read_bytes(64)).decode(u"UTF-16LE")
self.name_len = self._io.read_u2le()
self.object_type = KaitaiStream.resolve_enum(MicrosoftCfb.DirEntry.ObjType, self._io.read_u1())
self.color_flag = KaitaiStream.resolve_enum(MicrosoftCfb.DirEntry.RbColor, self._io.read_u1())
self.left_sibling_id = self._io.read_s4le()
self.right_sibling_id = self._io.read_s4le()
self.child_id = self._io.read_s4le()
self.clsid = self._io.read_bytes(16)
self.state = self._io.read_u4le()
self.time_create = self._io.read_u8le()
self.time_mod = self._io.read_u8le()
self.ofs = self._io.read_s4le()
self.size = self._io.read_u8le()
@property
def mini_stream(self):
if hasattr(self, '_m_mini_stream'):
return self._m_mini_stream
if self.object_type == MicrosoftCfb.DirEntry.ObjType.root_storage:
io = self._root._io
_pos = io.pos()
io.seek(((self.ofs + 1) * self._root.sector_size))
self._m_mini_stream = io.read_bytes(self.size)
io.seek(_pos)
return getattr(self, '_m_mini_stream', None)
@property
def child(self):
if hasattr(self, '_m_child'):
return self._m_child
if self.child_id != -1:
io = self._root._io
_pos = io.pos()
io.seek((((self._root.header.ofs_dir + 1) * self._root.sector_size) + (self.child_id * 128)))
self._m_child = MicrosoftCfb.DirEntry(io, self, self._root)
io.seek(_pos)
return getattr(self, '_m_child', None)
@property
def left_sibling(self):
if hasattr(self, '_m_left_sibling'):
return self._m_left_sibling
if self.left_sibling_id != -1:
io = self._root._io
_pos = io.pos()
io.seek((((self._root.header.ofs_dir + 1) * self._root.sector_size) + (self.left_sibling_id * 128)))
self._m_left_sibling = MicrosoftCfb.DirEntry(io, self, self._root)
io.seek(_pos)
return getattr(self, '_m_left_sibling', None)
@property
def right_sibling(self):
if hasattr(self, '_m_right_sibling'):
return self._m_right_sibling
if self.right_sibling_id != -1:
io = self._root._io
_pos = io.pos()
io.seek((((self._root.header.ofs_dir + 1) * self._root.sector_size) + (self.right_sibling_id * 128)))
self._m_right_sibling = MicrosoftCfb.DirEntry(io, self, self._root)
io.seek(_pos)
return getattr(self, '_m_right_sibling', None)
@property
def sector_size(self):
if hasattr(self, '_m_sector_size'):
return self._m_sector_size
self._m_sector_size = (1 << self.header.sector_shift)
return getattr(self, '_m_sector_size', None)
@property
def fat(self):
if hasattr(self, '_m_fat'):
return self._m_fat
_pos = self._io.pos()
self._io.seek(self.sector_size)
self._raw__m_fat = self._io.read_bytes((self.header.size_fat * self.sector_size))
_io__raw__m_fat = KaitaiStream(BytesIO(self._raw__m_fat))
self._m_fat = MicrosoftCfb.FatEntries(_io__raw__m_fat, self, self._root)
self._io.seek(_pos)
return getattr(self, '_m_fat', None)
@property
def dir(self):
if hasattr(self, '_m_dir'):
return self._m_dir
_pos = self._io.pos()
self._io.seek(((self.header.ofs_dir + 1) * self.sector_size))
self._m_dir = MicrosoftCfb.DirEntry(self._io, self, self._root)
self._io.seek(_pos)
return getattr(self, '_m_dir', None)