oxenai 0.42.4__cp312-cp312-macosx_10_13_x86_64.whl

oxen/workspace.py

@@ -0,0 +1,210 @@
+import os
+
+from typing import Optional, TYPE_CHECKING
+
+from .oxen import PyWorkspace, PyCommit
+
+# Use TYPE_CHECKING for type hints to avoid runtime circular imports
+if TYPE_CHECKING:
+    from .remote_repo import RemoteRepo
+
+
+class Workspace:
+    """
+    The Workspace class allows you to interact with an Oxen workspace
+    without downloading the data locally.
+
+    Workspaces can be created off a branch and is tied to the commit id of the branch
+    at the time of creation.
+
+    You can commit a Workspace back to the same branch if the branch has not
+    advanced, otherwise you will have to commit to a new branch and merge.
+
+    ## Examples
+
+    ### Adding Files to a Workspace
+
+    Create a workspace from a branch.
+
+    ```python
+    from oxen import RemoteRepo
+    from oxen import Workspace
+
+    # Connect to the remote repo
+    repo = RemoteRepo("ox/CatDogBBox")
+
+    # Create the workspace
+    workspace = Workspace(repo, "my-branch")
+
+    # Add a file to the workspace
+    workspace.add("my-image.png")
+
+    # Print the status of the workspace
+    status = workspace.status()
+    print(status.added_files())
+
+    # Commit the workspace
+    workspace.commit("Adding my image to the workspace.")
+    ```
+    """
+
+    def __init__(
+        self,
+        repo: "RemoteRepo",
+        branch: str,
+        workspace_id: Optional[str] = None,
+        workspace_name: Optional[str] = None,
+        path: Optional[str] = None,
+    ):
+        """
+        Create a new Workspace.
+
+        Args:
+            repo: `PyRemoteRepo`
+                The remote repo to create the workspace from.
+            branch: `str`
+                The branch name to create the workspace from. The workspace
+                will be tied to the commit id of the branch at the time of creation.
+            workspace_id: `Optional[str]`
+                The workspace id to create the workspace from.
+                If left empty, will create a unique workspace id.
+            workspace_name: `Optional[str]`
+                The name of the workspace. If left empty, the workspace will have no name.
+            path: `Optional[str]`
+                The path to the workspace. If left empty, the workspace will be created in the root of the remote repo.
+        """
+        self._repo = repo
+        if not self._repo.revision == branch:
+            self._repo.create_checkout_branch(branch)
+        try:
+            self._workspace = PyWorkspace(
+                repo._repo, branch, workspace_id, workspace_name, path
+            )
+        except ValueError as e:
+            print(e)
+            # Print this error in red
+            print(
+                f"\033[91mMake sure that you have write access to `{repo.namespace}/{repo.name}`\033[0m\n"
+            )
+            raise e
+
+    def __repr__(self):
+        return f"Workspace(id={self._workspace.id()}, branch={self._workspace.branch()}, commit_id={self._workspace.commit_id()})"
+
+    @property
+    def id(self):
+        """
+        Get the id of the workspace.
+        """
+        return self._workspace.id()
+
+    @property
+    def name(self):
+        """
+        Get the name of the workspace.
+        """
+        return self._workspace.name()
+
+    @property
+    def branch(self):
+        """
+        Get the branch that the workspace is tied to.
+        """
+        return self._workspace.branch()
+
+    @property
+    def commit_id(self):
+        """
+        Get the commit id of the workspace.
+        """
+        return self._workspace.commit_id()
+
+    @property
+    def repo(self) -> "RemoteRepo":
+        """
+        Get the remote repo that the workspace is tied to.
+        """
+        return self._repo
+
+    def status(self, path: str = ""):
+        """
+        Get the status of the workspace.
+
+        Args:
+            path: `str`
+                The path to check the status of.
+        """
+        return self._workspace.status(path)
+
+    def add(self, src: str, dst: str = ""):
+        """
+        Add a file to the workspace
+
+        Args:
+            src: `str`
+                The path to the local file to be staged
+            dst: `str`
+                The path in the remote repo where the file will be added
+        """
+        # Add a file to the workspace
+        if os.path.isdir(src):
+            paths = []
+            for dir_path, _, files in os.walk(src):
+                for file_name in files:
+                    path = os.path.join(dir_path, file_name)
+                    paths.append(path)
+            self._workspace.add_many(paths, dst)
+        else:
+            # Add a single file
+            self._workspace.add(src, dst)
+
+
+    def add_bytes(self, src: str, buf: bytes, dst: str = ""):
+        """
+        Adds from a memory buffer to the workspace
+
+        Args:
+            src: `str`
+                The relative path to be used as the entry's name in the workspace
+            buf: `bytes`
+                The memory buffer to be read from for this entry
+            dst: `str`
+                The path in the remote repo where the file will be added
+        """
+
+        self._workspace.add_bytes(src, buf, dst)
+
+    def rm(self, path: str):
+        """
+        Remove a file from the workspace
+
+        Args:
+            path: `str`
+                The path to the file on workspace to be removed
+        """
+        self._workspace.rm(path)
+
+    def commit(
+        self,
+        message: str,
+        branch_name: Optional[str] = None,
+    ) -> PyCommit:
+        """
+        Commit the workspace to a branch
+
+        Args:
+            message: `str`
+                The message to commit with
+            branch_name: `Optional[str]`
+                The name of the branch to commit to. If left empty, will commit to the branch
+                the workspace was created from.
+        """
+        if branch_name is None:
+            branch_name = self._workspace.branch()
+        return self._workspace.commit(message, branch_name)
+
+    def delete(self):
+        """
+        Delete the workspace
+        """
+        self._workspace.delete()

oxenai-0.42.4.dist-info/METADATA

@@ -0,0 +1,92 @@
+Metadata-Version: 2.4
+Name: oxenai
+Version: 0.42.4
+Classifier: Programming Language :: Rust
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Topic :: Software Development :: Version Control
+Requires-Dist: fsspec>=2025.3.0
+Requires-Dist: maturin>=1.9.3
+Requires-Dist: pandas>=2.3.1
+Requires-Dist: polars>=1.32.0
+Requires-Dist: pyarrow>=21.0.0
+Requires-Dist: pytest>=8.4.1
+Requires-Dist: pytest-datadir>=1.8.0
+Requires-Dist: requests>=2.32.4
+Requires-Dist: ruff>=0.12.7
+Requires-Dist: toml>=0.10.2
+Requires-Dist: tqdm>=4.67.1
+Summary: Data version control for machine learning
+Keywords: oxen,version control
+License-Expression: Apache-2.0
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
+Project-URL: Homepage, https://www.oxen.ai/
+Project-URL: Documentation, https://docs.oxen.ai/
+Project-URL: Repository, https://github.com/Oxen-AI/Oxen
+
+# 🐂 🐍 Oxen Python Interface 
+
+The Oxen python interface makes it easy to integrate Oxen datasets directly into machine learning dataloaders or other data pipelines.
+
+## Repositories
+
+There are two types of repositories one can interact with, a `Repo` and a `RemoteRepo`.
+
+
+## Local Repo
+
+To fully clone all the data to your local machine, you can use the `Repo` class.
+
+```python
+import oxen
+
+repo = oxen.Repo("path/to/repository")
+repo.clone("https://hub.oxen.ai/ox/CatDogBBox")
+```
+
+If there is a specific version of your data you want to access, you can specify the `branch` when cloning.
+
+```python
+repo.clone("https://hub.oxen.ai/ox/CatDogBBox", branch="my-pets")
+```
+
+Once you have a repository locally, you can perform the same operations you might via the command line, through the python api.
+
+For example, you can checkout a branch, add a file, commit, and push the data to the same remote you cloned it from.
+
+```python
+import oxen
+
+repo = oxen.Repo("path/to/repository")
+repo.clone("https://hub.oxen.ai/ox/CatDogBBox")
+repo.checkout()
+```
+
+## Remote Repo
+
+If you don't want to download the data locally, you can use the `RemoteRepo` class to interact with a remote repository on OxenHub.
+
+```python
+import oxen 
+
+repo = RemoteRepo("https://hub.oxen.ai/ox/CatDogBBox")
+```
+
+To stage and commit files to a specific version of the data, you can `checkout` an existing branch or create a new one.
+
+```python
+repo.create_branch("dev")
+repo.checkout("dev")
+```
+
+You can then stage files to the remote repository by specifying the file path and destination directory.
+
+```python
+repo.add("new-cat.png", "images") # Stage to images/new-cat.png on remote
+repo.commit("Adding another training image")
+```
+
+Note that no "push" command is required here, since the above code creates a commit directly on the remote branch.
+
+

oxenai-0.42.4.dist-info/RECORD

@@ -0,0 +1,32 @@
+oxen/__init__.py,sha256=fnWDRsrC_1osHMXikyIDVgP1_LP8RTW89EhC-f-df-s,1036
+oxen/auth.py,sha256=sEcWP2BVmWBd1mRmQNRts8CY0-1NlopcjLljy8wFTK0,1387
+oxen/clone.py,sha256=SIRSkG8qnuz2H0yV9RuFIk99i_V4EQoD1nJtnvXljJY,1963
+oxen/config.py,sha256=XolGXGFLjW-Zt6apnnGrKlUSvcbkwFSkxx9qIIFEiYI,430
+oxen/data_frame.py,sha256=E7yoqpj75NtD642Tsp3DxIw0Y3W47oCJoJNkRmfo648,15719
+oxen/datasets.py,sha256=DLsZg1GsGVTihu9gVyx2_QUazA7iHoQ2JDS7mexCviw,3401
+oxen/df_utils.py,sha256=ZmDY8mJm_0LCu9OEg8ve6uQ7Yy_ZZ_3TqW4Xh9kAvyI,1099
+oxen/diff/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+oxen/diff/change_type.py,sha256=MPExZECVhoU5pNvM8GmnoF0Mcvki-lvN0nUon3mktEk,218
+oxen/diff/diff.py,sha256=54uoGrHZqhRigrEuTjktj7rVdl1JcKFpekbTaDI00zc,5003
+oxen/diff/line_diff.py,sha256=gsfN1P4bEMhRUesshwfyQ-THE8jP8IIChZSULQBMmBo,1128
+oxen/diff/tabular_diff.py,sha256=NwglOL4KAdJKbSSkxCBGbeehhKqGd8Rh9AhMCyJPQTA,525
+oxen/diff/text_diff.py,sha256=94mVJtuJAoef9mpxSW4ZapiY_fo-Bru8foZktAfm_Y4,1389
+oxen/features.py,sha256=5zLscxbX_4OcpjqZz2mkj5obX-6AMyMNCXASJzo_qx4,1378
+oxen/fs.py,sha256=yfDX7jcIUUXAzfoj67znKoPNGUS8C0tWAOczEnSQAKI,1485
+oxen/init.py,sha256=OLNE_EaIpJuX5Z7oTot_k7gPQJpCqyVqRtNg1WqCQ3w,398
+oxen/oxen.cpython-312-darwin.so,sha256=Lqh2BkRqsoICgWiK4H6S4F7dExWDvrc6fa9EWpkj5uU,144970920
+oxen/oxen_fs.py,sha256=bk3BQy9KPOFIg87T-0pFmXpvR67K9TmU6BVdoD2ULhk,11095
+oxen/providers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+oxen/providers/dataset_path_provider.py,sha256=3hrzA2mGROIgY4et2HB5sSmZyyGdkHsy-uLwzTs9KIw,674
+oxen/providers/mock_provider.py,sha256=JmuR5lDVc3fTv-0qGVl0hBKKYo98vxkYCVhKqKW-bDo,2048
+oxen/providers/oxen_data_frame_provider.py,sha256=g6_eO5gTD6v1u4TxIcjGq4JGdR0LRxcjQ4ZX0PrQMtc,1593
+oxen/remote_repo.py,sha256=uIQk0tsmtqJpOMQjbLtL_-uX7CAlwerTh4gwCIY1Hrg,20417
+oxen/repo.py,sha256=hZv_2zlBD5yYetrYhh0RxqmpJmjjd97Sa4T7MSIfTY4,7031
+oxen/streaming_dataset.py,sha256=vHCZ6LuLMwKKHtySbPaekTj1xDJ5NeuXzMB_sjXtIeg,7978
+oxen/user.py,sha256=4KeGuoywCneA-ocTyqv-Da1Ho2W1xcdPlHB8h7Rt1HY,1165
+oxen/util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+oxen/workspace.py,sha256=lOaGZARIB2f6Yg7cvSeeAP-4vxypFZ-MR7OX434Phn8,6036
+oxenai-0.42.4.dist-info/METADATA,sha256=2XlR7tfdBidw9ddchEPk34_WSL25onJNrJgaKp9gNk8,2816
+oxenai-0.42.4.dist-info/WHEEL,sha256=RzpM5MCae0zSGyiAZroxbkepvywsAm9pLWSENAg7iow,107
+oxenai-0.42.4.dist-info/entry_points.txt,sha256=CvslGiUZsEt-5k6cJ19pRFHGicXb4XrR0CKhrzq1aEU,40
+oxenai-0.42.4.dist-info/RECORD,,

oxenai-0.42.4.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: maturin (1.10.2)
+Root-Is-Purelib: false
+Tag: cp312-cp312-macosx_10_13_x86_64

oxenai-0.42.4.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[fsspec.specs]
+oxen=oxen.oxen_fs:OxenFS