Feature: Transition all checksums to use SHA256 (#12432)

src/documents/utils.py

@@ -1,3 +1,4 @@
+import hashlib
 import logging
 import shutil
 from os import utime
@@ -128,3 +129,28 @@ def get_boolean(boolstr: str) -> bool:
     Return a boolean value from a string representation.
     """
     return bool(boolstr.lower() in ("yes", "y", "1", "t", "true"))
+
+
+def compute_checksum(path: Path, chunk_size: int = 65536) -> str:
+    """
+    Compute the SHA-256 checksum of a file.
+
+    Reads the file in chunks to avoid loading the entire file into memory.
+
+    Args:
+        path (Path): Path to the file to hash.
+        chunk_size (int, optional): Number of bytes to read per chunk.
+            Defaults to 65536.
+
+    Returns:
+        str: Hexadecimal SHA-256 digest of the file contents.
+
+    Raises:
+        FileNotFoundError: If the file does not exist.
+        OSError: If the file cannot be read.
+    """
+    h = hashlib.sha256()
+    with path.open("rb") as f:
+        while chunk := f.read(chunk_size):
+            h.update(chunk)
+    return h.hexdigest()