Add function for computing the hash of a directory

1 files changed, 20 insertions, 0 deletions

diff --git a/gn3/file_utils.py b/gn3/file_utils.py
new file mode 100644
index 0000000..8e342c9
--- /dev/null
+++ b/gn3/file_utils.py
@@ -0,0 +1,20 @@
+"""Procedures that operate on files/ directories"""
+import hashlib
+import os
+
+from functools import partial
+
+
+def get_dir_hash(directory: str) -> str:
+    """Return the hash of a DIRECTORY"""
+    md5hash = hashlib.md5()
+    if not os.path.exists(directory):
+        raise FileNotFoundError
+    for root, _, files in os.walk(directory):
+        for names in files:
+            file_path = os.path.join(root, names)
+            with open(file_path, "rb") as file_:
+                for buf in iter(partial(file_.read, 4096), b''):
+                    md5hash.update(bytearray(hashlib.md5(buf).hexdigest(),
+                                             "utf-8"))
+    return md5hash.hexdigest()