Added initial hasher code

.gitignore

@@ -0,0 +1,160 @@
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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 maintained 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/

hasher/__main__.py

@@ -0,0 +1,56 @@
+from __future__ import annotations
+from argparse import ArgumentParser, FileType, Namespace
+from functools import partial
+from hashlib import algorithms_available, new
+from io import BufferedReader
+from typing import IO, Generic, Protocol, Type, TypeVar
+
+
+CHUNK_SIZE = 2 ** 20
+DEFAULT_HASH_ALGORITHM = "md5"
+
+T = TypeVar("T")
+T_contra = TypeVar("T_contra", contravariant=True)
+
+class Updatable(Protocol, Generic[T_contra]):
+    def update(self, __data: T_contra, /): ...
+
+def check_arg_type(args: Namespace, key: str, expected: Type[T] | str) -> T:
+    try:
+        value = args.__getattribute__(key)
+    except AttributeError:
+        raise Exception(f"Expected argument {key} in args namespace!")
+    if isinstance(expected, str):
+        value_class = value.__class__
+        class_name = value_class.__name__
+        if class_name != expected:
+            raise Exception(f"Expected argument {key} to be of known type {expected}, but got {class_name}!")
+    elif not isinstance(value, expected): 
+        raise Exception(f"Expected argument {key} to be of type {expected}, but got {type(value).__name__}!")
+    return value
+
+def parse_args():
+    parser = ArgumentParser("python -m hasher")
+    if not DEFAULT_HASH_ALGORITHM in algorithms_available:
+        raise Exception(f"Default hash algorithm {DEFAULT_HASH_ALGORITHM} is not available!")
+    parser.add_argument("-a", type=str, choices=algorithms_available, default=DEFAULT_HASH_ALGORITHM, help="hash algorithm to use")
+    parser.add_argument("file", type=FileType("rb"))
+    return parser.parse_args()
+
+def update(hasher: Updatable[bytes], file: IO[bytes], chunk_size: int = CHUNK_SIZE):
+    while True:
+        data = file.read(chunk_size)
+        if not data: break
+        hasher.update(data)
+
+def main():
+    args = parse_args()
+    check_arg = partial(check_arg_type, args)
+    algo = check_arg("a", str)
+    file = check_arg("file", BufferedReader)
+    hasher = new(algo)
+    update(hasher, file)
+    print(hasher.hexdigest())
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1 @@
+argparse