Add types to objects

how_to/Change_06.md

@@ -0,0 +1,17 @@
+- data: Add types to objects
+
+As we will soon see, there will be different logical types of objects that are
+used in different contexts (even though, from the Object Database's point of
+view, they are just all bytes). In order to lower the chance of using an object
+in the wrong context we're going to add a type tag for each object.
+
+The type is just a string that's going to be prepended to the start of the file,
+followed by a null byte. When reading the file later we'll extract the type and
+verify that it's indeed the expected type.
+
+The default type is going to be `blob`, since by default an object is a
+collection of bytes with no further semantic meaning.
+
+We can also pass `expected=None` to `get_object()` if we don't want to verify
+the type. This is useful for the `cat-file` CLI command which is a debug command
+used for printing all objects.

ugit/cli.py

@@ -43,4 +43,4 @@ def hash_object(args):
 
 def cat_file(args):
     sys.stdout.flush()
-    sys.stdout.buffer.write(data.get_object(args.object))
+    sys.stdout.buffer.write(data.get_object(args.object), expected=None)

ugit/data.py

@@ -10,13 +10,21 @@ def init():
     Path.mkdir(f"{GIT_DIR}/objects")
 
 
-def hash_object(data):
-    oid = hashlib.sha1(data).hexdigest()
+def hash_object(data, type_="blob"):
+    obj = type_.encode() + b"\x00" + data
+    oid = hashlib.sha1(obj).hexdigest()
     with open(f"{GIT_DIR}/objects/{oid}", "wb") as out:
-        out.write(data)
+        out.write(obj)
     return oid
 
 
-def get_object(oid):
+def get_object(oid, expected="blob"):
     with open(f"{GIT_DIR}/objects/{oid}", "rb") as f:
-        return f.read()
+        obj = f.read()
+
+    type_, _, content = obj.partition(b"\x00")
+    type_ = type_.decode()
+
+    if expected is not None:
+        assert type_ == expected, f"Expected {expected}, got {type_}"
+    return content