Store YBlob as bytes, not base64-encoded string (#209)

* Store YBlob as bytes, not base64-encoded string

* Add test

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Automatic application of license header

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

.gitignore

@@ -147,3 +147,5 @@ jupyter_ydoc/_version.py
 !.yarn/versions
 docs/source/api
 docs/source/changelog.md
+# pixi environments
+.pixi

jupyter_ydoc/yblob.py

@@ -1,9 +1,8 @@
 # Copyright (c) Jupyter Development Team.
 # Distributed under the terms of the Modified BSD License.
 
-import base64
 from functools import partial
-from typing import Any, Callable, Optional, Union
+from typing import Any, Callable, Optional
 
 from pycrdt import Doc, Map
 
@@ -13,10 +12,7 @@
 class YBlob(YBaseDoc):
     """
     Extends :class:`YBaseDoc`, and represents a blob document.
-    It is currently encoded as base64 because of:
-    https://github.com/y-crdt/ypy/issues/108#issuecomment-1377055465
-    The Y document can be set from bytes or from str, in which case it is assumed to be encoded as
-    base64.
+    The Y document is set from bytes.
 
     Schema:
 
@@ -46,7 +42,7 @@ def version(self) -> str:
         :return: Document's version.
         :rtype: str
         """
-        return "1.0.0"
+        return "2.0.0"
 
     def get(self) -> bytes:
         """
@@ -55,18 +51,16 @@ def get(self) -> bytes:
         :return: Document's content.
         :rtype: bytes
         """
-        return base64.b64decode(self._ysource.get("base64", "").encode())
+        return self._ysource.get("bytes", b"")
 
-    def set(self, value: Union[bytes, str]) -> None:
+    def set(self, value: bytes) -> None:
         """
         Sets the content of the document.
 
         :param value: The content of the document.
-        :type value: Union[bytes, str]
+        :type value: bytes
         """
-        if isinstance(value, bytes):
-            value = base64.b64encode(value).decode()
-        self._ysource["base64"] = value
+        self._ysource["bytes"] = value
 
     def observe(self, callback: Callable[[str, Any], None]) -> None:
         """

pyproject.toml

@@ -13,7 +13,7 @@ requires-python = ">=3.7"
 keywords = ["jupyter", "ypy"]
 dependencies = [
     "importlib_metadata >=3.6; python_version<'3.10'",
-    "pycrdt >=0.8.1,<0.9.0",
+    "pycrdt >=0.8.3,<0.9.0",
 ]
 
 [[project.authors]]

tests/test_ydocs.py

@@ -0,0 +1,24 @@
+# Copyright (c) Jupyter Development Team.
+# Distributed under the terms of the Modified BSD License.
+
+from jupyter_ydoc import YBlob
+
+
+def test_yblob():
+    yblob = YBlob()
+    assert yblob.get() == b""
+    yblob.set(b"012")
+    assert yblob.get() == b"012"
+    changes = []
+
+    def callback(topic, event):
+        print(topic, event)
+        changes.append((topic, event))
+
+    yblob.observe(callback)
+    yblob.set(b"345")
+    assert len(changes) == 1
+    topic, event = changes[0]
+    assert topic == "source"
+    assert event.keys["bytes"]["oldValue"] == b"012"
+    assert event.keys["bytes"]["newValue"] == b"345"