diff --git a/README.md b/README.md
index 07b56ac390c6dd1a755b042b84b8bf7fbe9ea5d6..66ad82c9d09e6750c398f59851cb241e108592ca 100644
--- a/README.md
+++ b/README.md
@@ -1 +1,14 @@
-# BiTIA CLI
+# BioInformatics Tool for Infrastructure Automation (BiTIA) CLI utility
+
+This is the cli utility of the BiTIA project. The other component is
+`bitia-runner`. Most users only need the cli client `bitia` to submit jobs.
+Install it using pip.
+
+```
+pip install bitia
+```
+
+## BiTIA runner
+
+If you are self-hosting the BiTIA server, you need `bitia-runner` as well. See
+the documents of `bitia-runner` for more details.
diff --git a/bitia/__init__.py b/bitia/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..c876830eb0b0e93213106260588310611448d1a6
--- /dev/null
+++ b/bitia/__init__.py
@@ -0,0 +1,20 @@
+from importlib.metadata import version as _version
+import os
+import logging
+from rich.logging import RichHandler
+import logging.handlers
+
+log_level = os.environ.get("BITIA_LOGLEVEL", "NOTSET").upper()
+logging.basicConfig(
+ format="%(message)s",
+ level=log_level,
+ datefmt="[%X]",
+ handlers=[RichHandler(rich_tracebacks=True)],
+)
+
+__version__ = _version("bitia")
+
+
+def version() -> str:
+ """version"""
+ return __version__
diff --git a/bitia/__main__.py b/bitia/__main__.py
index 6ee261bb134bdf94bae54fd384264e07112d1254..2555dc0cb9c2307d137b8fd68ecad22065c53d34 100644
--- a/bitia/__main__.py
+++ b/bitia/__main__.py
@@ -14,7 +14,8 @@ from rich.logging import RichHandler
from pathlib import Path
import tempfile
-from checksumdir import dirhash
+
+from bitia.checksumdir import dirhash
FORMAT = "%(message)s"
logging.basicConfig(
diff --git a/bitia/checksumdir.py b/bitia/checksumdir.py
new file mode 100644
index 0000000000000000000000000000000000000000..5f0f9ab4d9503d2e6e077eda2a9f1bbe044b0c16
--- /dev/null
+++ b/bitia/checksumdir.py
@@ -0,0 +1,79 @@
+"""
+Function for deterministically creating a single hash for a directory of files,
+taking into account only file contents and not filenames.
+
+dirhash('/path/to/directory', 'md5')
+
+Orignally from
+https://raw.githubusercontent.com/SubconsciousCompute/checksumdir/master/checksumdir/__init__.p
+y
+
+"""
+
+import hashlib
+import typing as T
+import os
+import re
+from pathlib import Path
+
+HASH_FUNCS = {
+ "md5": hashlib.md5,
+ "sha1": hashlib.sha1,
+ "sha256": hashlib.sha256,
+ "sha512": hashlib.sha512,
+}
+
+
+def dirhash(
+ dirname: Path,
+ hashfunc: str = "md5",
+ excluded_files: T.List[Path] = [],
+ ignore_hidden: bool = False,
+ followlinks: bool = False,
+ excluded_extensions: T.List[str] = [],
+):
+ hash_func = HASH_FUNCS[hashfunc]
+ assert dirname.is_dir(), "{} is not a directory.".format(dirname)
+ hashvalues = []
+ for r_dir, dirs, files in os.walk(dirname, topdown=True, followlinks=followlinks):
+ if ignore_hidden and re.search(r"/\.", r_dir):
+ continue
+ root = Path(r_dir)
+ dirs.sort()
+ files.sort()
+ for fname in files:
+ if ignore_hidden and fname.startswith("."):
+ continue
+
+ if Path(fname).suffix in excluded_extensions:
+ continue
+
+ if fname in excluded_files:
+ continue
+
+ hashvalues.append(filehash(root / fname, hashfunc))
+
+ return _reduce_hash(hashvalues, hash_func)
+
+
+def filehash(filepath: Path, hashfunc: str = "md5"):
+ hasher = HASH_FUNCS[hashfunc]()
+ blocksize = 64 * 1024
+
+ if not filepath.is_file():
+ return hasher.hexdigest()
+
+ with filepath.open("rb") as fp:
+ while True:
+ data = fp.read(blocksize)
+ if not data:
+ break
+ hasher.update(data)
+ return hasher.hexdigest()
+
+
+def _reduce_hash(hashlist, hashfunc):
+ hasher = hashfunc()
+ for hashvalue in sorted(hashlist):
+ hasher.update(hashvalue.encode("utf-8"))
+ return hasher.hexdigest()
diff --git a/poetry.lock b/poetry.lock
index 43931f2f8c8362c03a97e8aa5a373eb2b29800b6..102eaf777ce33427f9ad98148a8bf88fa6674342 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -17,14 +17,6 @@ python-versions = ">=3.6.0"
[package.extras]
unicode_backport = ["unicodedata2"]
-[[package]]
-name = "checksumdir"
-version = "1.2.0"
-description = "Compute a single hash of the file contents of a directory."
-category = "main"
-optional = false
-python-versions = ">=3.6,<4.0"
-
[[package]]
name = "click"
version = "8.1.3"
@@ -149,7 +141,7 @@ socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
[metadata]
lock-version = "1.1"
python-versions = "^3.8"
-content-hash = "d60f75638b8835d054e6d589945791f581eb9275aae90e255a58aff3bfab3b27"
+content-hash = "876b8c11170f017ce20e5b481e80612ab81476f22aa411f669ad5edcc0fdd327"
[metadata.files]
certifi = [
@@ -160,10 +152,6 @@ charset-normalizer = [
{file = "charset-normalizer-2.1.1.tar.gz", hash = "sha256:5a3d016c7c547f69d6f81fb0db9449ce888b418b5b9952cc5e6e66843e9dd845"},
{file = "charset_normalizer-2.1.1-py3-none-any.whl", hash = "sha256:83e9a75d1911279afd89352c68b45348559d1fc0506b054b346651b5e7fee29f"},
]
-checksumdir = [
- {file = "checksumdir-1.2.0-py3-none-any.whl", hash = "sha256:77687e16da95970c94061c74ef2e13666c4b6e0e8c90a5eaf0c8f7591332cf01"},
- {file = "checksumdir-1.2.0.tar.gz", hash = "sha256:10bfd7518da5a14b0e9ac03e9ad105f0e70f58bba52b6e9aa2f21a3f73c7b5a8"},
-]
click = [
{file = "click-8.1.3-py3-none-any.whl", hash = "sha256:bb4d8133cb15a609f44e8213d9b391b0809795062913b383c62be0ee95b1db48"},
{file = "click-8.1.3.tar.gz", hash = "sha256:7682dc8afb30297001674575ea00d1814d808d6a36af415a82bd481d37ba7b8e"},
diff --git a/pyproject.toml b/pyproject.toml
index 6a9c48673355b1ab48b039d7b648bfcb164b9ce3..897d76bb3a56bbf77f47be6d35684707961eebb4 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,7 +1,7 @@
[tool.poetry]
name = "bitia"
version = "0.1.1"
-description = "BioInformatics Tool for Infrastructure Automation (BiTIA) command line utility."
+description = "BioInformatics Tool for Infrastructure Automation (BiTIA) CLI utility."
authors = ["Dilawar Singh <dilawar@subcom.tech>"]
readme = "README.md"
@@ -9,7 +9,6 @@ readme = "README.md"
python = "^3.8"
requests = "^2.28.1"
typer = "^0.6.1"
-checksumdir = "^1.2.0"
rich = "^12.5.1"
[tool.poetry.scripts]
diff --git a/tests/__init__.py b/tests/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/tests/test_sanity.py b/tests/test_sanity.py
new file mode 100644
index 0000000000000000000000000000000000000000..77a2e2b344a69e1a61ea49a1ca6e61a03e88cb1e
--- /dev/null
+++ b/tests/test_sanity.py
@@ -0,0 +1,5 @@
+import bitia
+
+
+def test_sanity():
+ assert bitia.version()