Initial commit

.gitignore

@@ -0,0 +1,154 @@
+# ---> Python
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintainted in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+

README.md

@@ -0,0 +1,3 @@
+# mslnk-py
+
+Windows shell link (.lnk) parser in Python.

mslnk.py

@@ -0,0 +1,121 @@
+#!/usr/bin/env python3
+
+from locale import getdefaultlocale
+from struct import unpack
+from collections import namedtuple
+from typing import Any, Tuple
+
+# https://learn.microsoft.com/en-us/openspecs/windows_protocols/ms-shllink/16cb4ca1-9339-4d0c-a68d-bf1d6cc0f943
+
+TShellLink = namedtuple('ShellLink', ('ShellLinkHeader', 'LinkTargetIDList', 'LinkInfo', 'StringData', 'ExtraData'))
+def parse_shell_link(data: bytes, offset: int=0) -> TShellLink:
+	shell_link_header = parse_shell_link_header(data, offset)
+	offset += shell_link_header.HeaderSize
+	if shell_link_header.LinkFlags & 0x01:
+		link_target_id_list = parse_link_target_id_list(data, offset)
+		offset += link_target_id_list.IDListSize + 0x02
+	else:
+		link_target_id_list = None
+	if shell_link_header.LinkFlags & 0x02:
+		link_info = parse_link_info(data, offset)
+		offset += link_info.LinkInfoSize
+	else:
+		link_info = None
+	string_data = parse_string_data(data, offset, shell_link_header.LinkFlags)
+	offset += string_data.StringDataSize
+	return TShellLink(shell_link_header, link_target_id_list, link_info, string_data, parse_extra_data(data, offset))
+
+TShellLinkHeader = namedtuple('ShellLinkHeader', ('HeaderSize', 'LinkCLSID', 'LinkFlags', 'FileAttributes', 'CreationTime', 'AccessTime', 'WriteTime', 'FileSize', 'IconIndex', 'ShowCommand', 'HotKey'))
+def parse_shell_link_header(data: bytes, offset: int=0) -> TShellLinkHeader:
+	sz = unpack('<I', data[offset: offset + 0x04])[0]
+	return TShellLinkHeader(*unpack('<L16sLLQQQLlLH2x4x4x', data[offset: offset + sz]))
+
+TLinkTargetIDList = namedtuple('LinkTargetIDList', ('IDListSize', 'IDList'))
+def parse_link_target_id_list(data: bytes, offset: int=0) -> TLinkTargetIDList:
+	sz = unpack('<H', data[offset: offset + 0x02])[0]
+	return TLinkTargetIDList(*unpack('<H' + str(sz) + 's', data[offset: offset + 0x02 + sz]))
+
+TLinkInfo = namedtuple('LinkInfo', ('LinkInfoSize', 'LinkInfoHeaderSize', 'LinkInfoFlags', 'VolumeIDOffset', 'LocalBasePathOffset', 'CommonNetworkRelativeLinkOffset', 'CommonPathSuffixOffset', 'LocalBasePathOffsetUnicode', 'CommonPathSuffixOffsetUnicode', 'VolumeID', 'LocalBasePath', 'CommonNetworkRelativeLink', 'CommonPathSuffix', 'LocalBasePathUnicode', 'CommonPathSuffixUnicode'))
+TLinkInfo.__new__.__defaults__ = (None,)*len(TLinkInfo._fields)
+def parse_link_info(data: bytes, offset: int=0) -> TLinkInfo:
+	sz = unpack('<I', data[offset + 0x04: offset + 0x08])[0]
+	res = TLinkInfo(*unpack('<' + 'L'*(sz//4), data[offset: offset + sz]))
+	values = {}
+	values['VolumeID'] = parse_blob(data, offset + res.VolumeIDOffset) if res.VolumeIDOffset > 0 else None
+	values['LocalBasePath'] = parse_str(data, offset + res.LocalBasePathOffset) if res.LocalBasePathOffset > 0 else None
+	values['CommonNetworkRelativeLink'] = parse_common_network_relative_link(data, offset + res.CommonNetworkRelativeLinkOffset) if res.CommonNetworkRelativeLinkOffset > 0 else None
+	values['CommonPathSuffix'] = parse_str(data, offset + res.CommonPathSuffixOffset) if res.CommonPathSuffixOffset > 0 else None
+	values['LocalBasePathUnicode'] = parse_ustr(data, offset + res.LocalBasePathOffsetUnicode) if res.LocalBasePathOffsetUnicode is not None and res.LocalBasePathOffsetUnicode > 0 else None
+	values['CommonPathSuffixUnicode'] = parse_ustr(data, offset + res.CommonPathSuffixOffsetUnicode) if res.CommonPathSuffixOffsetUnicode is not None and res.CommonPathSuffixOffsetUnicode > 0 else None
+	return res._replace(**values) if len(values) > 0 else res
+
+TCommonNetworkRelativeLink = namedtuple('CommonNetworkRelativeLink', ('CommonNetworkRelativeLinkSize', 'CommonNetworkRelativeLinkFlags', 'NetNameOffset', 'DeviceNameOffset', 'NetworkProviderType', 'NetNameOffsetUnicode', 'DeviceNameOffsetUnicode', 'NetName', 'DeviceName', 'NetNameUnicode', 'DeviceNameUnicode'))
+TCommonNetworkRelativeLink.__new__.__defaults__ = (None,)*len(TCommonNetworkRelativeLink._fields)
+def parse_common_network_relative_link(data: bytes, offset: int=0) -> TCommonNetworkRelativeLink:
+	sz = unpack('<I', data[offset + 0x08: offset + 0x0C])[0]
+	res = TCommonNetworkRelativeLink(*unpack('<' + 'L'*(sz//4), data[offset: offset + sz]))
+	values = {}
+	values['NetName'] = parse_str(data, offset + res.NetNameOffset) if res.NetNameOffset > 0 else None
+	values['DeviceName'] = parse_str(data, offset + res.DeviceNameOffset) if res.DeviceNameOffset > 0 else None
+	values['NetNameUnicode'] = parse_ustr(data, offset + res.NetNameOffsetUnicode) if res.NetNameOffsetUnicode is not None and res.NetNameOffsetUnicode > 0 else None
+	values['DeviceNameUnicode'] = parse_ustr(data, offset + res.DeviceNameOffsetUnicode) if res.DeviceNameOffsetUnicode is not None and res.DeviceNameOffsetUnicode > 0 else None
+	return res._replace(**values) if len(values) > 0 else res
+
+TStringData = namedtuple('StringData', ('StringDataSize', 'NAME_STRING', 'RELATIVE_PATH', 'WORKING_DIR', 'COMMAND_LINE_ARGUMENTS', 'ICON_LOCATION'))
+TStringData.__new__.__defaults__ = (None,)*len(TStringData._fields)
+def parse_string_data(data: bytes, offset: int=0, LinkFlags: int=0) -> TStringData:
+	values = {}
+	cursor = offset
+	IsUnicode = LinkFlags & 0b10000000
+	if LinkFlags & 0b100:
+		num, values['NAME_STRING'] = parse_pstr(data, cursor, IsUnicode)
+		cursor += num + 0x02
+	if LinkFlags & 0b1000:
+		num, values['RELATIVE_PATH'] = parse_pstr(data, cursor, IsUnicode)
+		cursor += num + 0x02
+	if LinkFlags & 0b10000:
+		num, values['WORKING_DIR'] = parse_pstr(data, cursor, IsUnicode)
+		cursor += num + 0x02
+	if LinkFlags & 0b100000:
+		num, values['COMMAND_LINE_ARGUMENTS'] = parse_pstr(data, cursor, IsUnicode)
+		cursor += num + 0x02
+	if LinkFlags & 0b1000000:
+		num, values['ICON_LOCATION'] = parse_pstr(data, cursor, IsUnicode)
+		cursor += num + 0x02
+	return TStringData(StringDataSize=cursor - offset, **values)
+
+def parse_extra_data(data: bytes, offset: int=0) -> Tuple[bytes, ...]:
+	res = []
+	while (sz := unpack('<I', data[offset: offset + 0x04])[0]) >= 0x04:
+		res.append(data[offset: offset + sz])
+		offset += sz
+	return tuple(res)
+
+def parse_str(data: bytes, offset: int=0) -> bytes:
+	return data[offset:].split(b'\x00', 1)[0] if offset > 0 else data.split(b'\x00', 1)[0]
+
+def parse_ustr(data: bytes, offset: int=0) -> bytes:
+	return data[offset:].split(b'\x00\x00', 1)[0] if offset > 0 else data.split(b'\x00\x00', 1)[0]
+
+def parse_pstr(data: bytes, offset: int=0, isunicode: bool=True) -> str:
+	sz = unpack('<H', data[offset: offset + 0x02])[0]
+	if isunicode:
+		val = data[offset + 0x02: offset + 0x02 + 4*sz].decode('utf-16', errors='ignore')[:sz]
+		return len(val.encode('utf-16-le')), val
+	else:
+		enc = getdefaultlocale()[1]
+		val = data[offset + 0x02: offset + 0x02 + 4*sz].decode(enc, errors='ignore')[:sz]
+		return len(val.encode(enc)), val
+
+def parse_blob(data: bytes, offset: int=0) -> bytes:
+	sz = unpack('<I', data[offset: offset + 0x04])[0]
+	return data[offset: offset + sz]
+
+def parse(x: Any) -> TShellLink:
+	if isinstance(x, bytes):
+		return parse_shell_link(x)
+	elif hasattr(x, 'read') and callable(x.read):
+		return parse_shell_link(x.read())
+	elif isinstance(x, str):
+		with open(x, 'rb') as stream:
+			return parse_shell_link(stream.read())