fs: rename DvcFileSystem to DataFileSystem

Current naming for `DvcFileSystem` and `RepoFileSystem` is confusing, because
dvc is not only about data and it is much more natural to expect something
named `dvcfs` to include complete view for your whole repo (including git
files), which is what `repofs` is doing right now.

`DvcFileSystem` can provide a view not only for the repo data, but also for
external data (e.g. local external outputs). So it makes more sense to call
it a `DataFileSystem`, since it really represents the data management side
of dvc.

dvc/fs/data.py

@@ -14,7 +14,7 @@ if typing.TYPE_CHECKING:
 logger = logging.getLogger(__name__)
 
 
-class _DvcFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
+class _DataFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
     """DVC repo fs.
 
     Args:
@@ -178,7 +178,7 @@ class _DvcFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
         raise NotImplementedError
 
 
-class DvcFileSystem(FileSystem):
+class DataFileSystem(FileSystem):
     scheme = "local"
 
     PARAM_CHECKSUM = "md5"
@@ -189,7 +189,7 @@ class DvcFileSystem(FileSystem):
     @wrap_prop(threading.Lock())
     @cached_property
     def fs(self):
-        return _DvcFileSystem(**self.fs_args)
+        return _DataFileSystem(**self.fs_args)
 
     def isdvc(self, path, **kwargs):
         return self.fs.isdvc(path, **kwargs)

dvc/fs/repo.py

@@ -10,7 +10,7 @@ from funcy import cached_property, wrap_prop, wrap_with
 
 from ._callback import DEFAULT_CALLBACK
 from .base import FileSystem
-from .dvc import DvcFileSystem
+from .data import DataFileSystem
 from .path import Path
 
 if TYPE_CHECKING:
@@ -70,7 +70,7 @@ class _RepoFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
         repo: DVC or git repo.
         subrepos: traverse to subrepos (by default, it ignores subrepos)
         repo_factory: A function to initialize subrepo with, default is Repo.
-        kwargs: Additional keyword arguments passed to the `DvcFileSystem()`.
+        kwargs: Additional keyword arguments passed to the `DataFileSystem()`.
     """
 
     root_marker = "/"
@@ -124,11 +124,11 @@ class _RepoFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
         key = self._get_key(self.repo.root_dir)
         self._subrepos_trie[key] = repo
 
-        self._dvcfss = {}
-        """Keep a dvcfs instance of each repo."""
+        self._datafss = {}
+        """Keep a datafs instance of each repo."""
 
         if hasattr(repo, "dvc_dir"):
-            self._dvcfss[key] = DvcFileSystem(repo=repo)
+            self._datafss[key] = DataFileSystem(repo=repo)
 
     def _get_key(self, path):
         parts = self.repo.fs.path.relparts(path, self.repo.root_dir)
@@ -245,7 +245,7 @@ class _RepoFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
                     scm=self.repo.scm,
                     repo_factory=self.repo_factory,
                 )
-                self._dvcfss[key] = DvcFileSystem(repo=repo)
+                self._datafss[key] = DataFileSystem(repo=repo)
             self._subrepos_trie[key] = repo
 
     def _is_dvc_repo(self, dir_path):
@@ -263,7 +263,7 @@ class _RepoFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
     ) -> Tuple[
         Optional[FileSystem],
         Optional[str],
-        Optional[DvcFileSystem],
+        Optional[DataFileSystem],
         Optional[str],
     ]:
         """
@@ -286,7 +286,7 @@ class _RepoFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
             dvc_parts = dvc_parts[1:]
 
         key = self._get_key(repo.root_dir)
-        dvc_fs = self._dvcfss.get(key)
+        dvc_fs = self._datafss.get(key)
         if dvc_fs:
             dvc_path = dvc_fs.path.join(*dvc_parts) if dvc_parts else ""
         else:

dvc/repo/__init__.py

@@ -484,10 +484,10 @@ class Repo:
         return self.DVC_DIR in path_parts
 
     @cached_property
-    def dvcfs(self):
-        from dvc.fs.dvc import DvcFileSystem
+    def datafs(self):
+        from dvc.fs.data import DataFileSystem
 
-        return DvcFileSystem(repo=self)
+        return DataFileSystem(repo=self)
 
     @cached_property
     def repo_fs(self):
@@ -504,11 +504,11 @@ class Repo:
     @contextmanager
     def open_by_relpath(self, path, remote=None, mode="r", encoding=None):
         """Opens a specified resource as a file descriptor"""
-        from dvc.fs.dvc import DvcFileSystem
+        from dvc.fs.data import DataFileSystem
         from dvc.fs.repo import RepoFileSystem
 
         if os.path.isabs(path):
-            fs = DvcFileSystem(repo=self, workspace="local")
+            fs = DataFileSystem(repo=self, workspace="local")
             fs_path = path
         else:
             fs = RepoFileSystem(repo=self, subrepos=True)

dvc/repo/get.py

@@ -52,9 +52,9 @@ def get(url, path, out=None, rev=None, jobs=None):
         ) as repo:
 
             if os.path.isabs(path):
-                from dvc.fs.dvc import DvcFileSystem
+                from dvc.fs.data import DataFileSystem
 
-                fs = DvcFileSystem(repo=repo, workspace="local")
+                fs = DataFileSystem(repo=repo, workspace="local")
                 fs_path = path
             else:
                 fs = repo.repo_fs

tests/unit/fs/test_data.py

@@ -5,7 +5,7 @@ import pytest
 
 from dvc.config import NoRemoteError
 from dvc.data.stage import stage
-from dvc.fs.dvc import DvcFileSystem
+from dvc.fs.data import DataFileSystem
 from dvc.objects.hash_info import HashInfo
 from dvc.utils.fs import remove
 
@@ -21,7 +21,7 @@ from dvc.utils.fs import remove
     ],
 )
 def test_get_key(tmp_dir, dvc, path, key):
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
     assert fs.fs._get_key(path) == key
 
 
@@ -30,7 +30,7 @@ def test_exists(tmp_dir, dvc):
     dvc.add("foo")
     (tmp_dir / "foo").unlink()
 
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
     assert fs.exists("foo")
 
 
@@ -39,7 +39,7 @@ def test_open(tmp_dir, dvc):
     dvc.add("foo")
     (tmp_dir / "foo").unlink()
 
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
     with fs.open("foo", "r") as fobj:
         assert fobj.read() == "foo"
 
@@ -48,9 +48,9 @@ def test_open_dirty_hash(tmp_dir, dvc):
     tmp_dir.dvc_gen("file", "file")
     (tmp_dir / "file").write_text("something")
 
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
     with fs.open("file", "r") as fobj:
-        # NOTE: Unlike RepoFileSystem, DvcFileSystem should not
+        # NOTE: Unlike RepoFileSystem, DataFileSystem should not
         # be affected by a dirty workspace.
         assert fobj.read() == "file"
 
@@ -60,7 +60,7 @@ def test_open_no_remote(tmp_dir, dvc):
     (tmp_dir / "file").unlink()
     remove(dvc.odb.local.cache_dir)
 
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
     with pytest.raises(FileNotFoundError) as exc_info:
         with fs.open("file", "r"):
             pass
@@ -71,8 +71,8 @@ def test_open_dirty_no_hash(tmp_dir, dvc):
     tmp_dir.gen("file", "file")
     (tmp_dir / "file.dvc").write_text("outs:\n- path: file\n")
 
-    fs = DvcFileSystem(repo=dvc)
-    # NOTE: Unlike RepoFileSystem, DvcFileSystem should not
+    fs = DataFileSystem(repo=dvc)
+    # NOTE: Unlike RepoFileSystem, DataFileSystem should not
     # be affected by a dirty workspace.
     with pytest.raises(FileNotFoundError):
         with fs.open("file", "r"):
@@ -94,7 +94,7 @@ def test_open_in_history(tmp_dir, scm, dvc):
         if rev == "workspace":
             continue
 
-        fs = DvcFileSystem(repo=dvc)
+        fs = DataFileSystem(repo=dvc)
         with fs.open("foo", "r") as fobj:
             assert fobj.read() == "foo"
 
@@ -102,7 +102,7 @@ def test_open_in_history(tmp_dir, scm, dvc):
 def test_isdir_isfile(tmp_dir, dvc):
     tmp_dir.gen({"datafile": "data", "datadir": {"foo": "foo", "bar": "bar"}})
 
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
     assert not fs.isdir("datadir")
     assert not fs.isfile("datadir")
     assert not fs.isdir("datafile")
@@ -123,7 +123,7 @@ def test_isdir_mixed(tmp_dir, dvc):
 
     dvc.add(str(tmp_dir / "dir" / "foo"))
 
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
     assert fs.isdir("dir")
     assert not fs.isfile("dir")
 
@@ -141,7 +141,7 @@ def test_walk(tmp_dir, dvc):
     )
 
     dvc.add("dir", recursive=True)
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
 
     expected = [
         "dir/subdir1",
@@ -175,7 +175,7 @@ def test_walk_dir(tmp_dir, dvc):
     )
 
     dvc.add("dir")
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
 
     expected = [
         "dir/subdir1",
@@ -197,7 +197,7 @@ def test_walk_dir(tmp_dir, dvc):
 
 
 def test_walk_missing(tmp_dir, dvc):
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
 
     for _ in fs.walk("dir"):
         pass
@@ -205,7 +205,7 @@ def test_walk_missing(tmp_dir, dvc):
 
 def test_walk_not_a_dir(tmp_dir, dvc):
     tmp_dir.dvc_gen("foo", "foo")
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
 
     for _ in fs.walk("foo"):
         pass
@@ -214,14 +214,14 @@ def test_walk_not_a_dir(tmp_dir, dvc):
 def test_isdvc(tmp_dir, dvc):
     tmp_dir.gen({"foo": "foo", "bar": "bar"})
     dvc.add("foo")
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
     assert fs.isdvc("foo")
     assert not fs.isdvc("bar")
 
 
 def test_get_hash_file(tmp_dir, dvc):
     tmp_dir.dvc_gen({"foo": "foo"})
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
     assert fs.info("foo")["md5"] == "acbd18db4cc2f85cedef654fccc4a4d8"
 
 
@@ -231,7 +231,7 @@ def test_get_hash_dir(tmp_dir, dvc, mocker):
     tmp_dir.dvc_gen(
         {"dir": {"foo": "foo", "bar": "bar", "subdir": {"data": "data"}}}
     )
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
     get_file_hash_spy = mocker.spy(dvc_module.data.stage, "get_file_hash")
     assert fs.info("dir")["md5"] == "8761c4e9acad696bee718615e23e22db.dir"
     assert not get_file_hash_spy.called
@@ -241,7 +241,7 @@ def test_get_hash_granular(tmp_dir, dvc):
     tmp_dir.dvc_gen(
         {"dir": {"foo": "foo", "bar": "bar", "subdir": {"data": "data"}}}
     )
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
     subdir = "dir/subdir"
     assert fs.info(subdir).get("md5") is None
     _, _, obj = stage(dvc.odb.local, subdir, fs, "md5", dry_run=True)
@@ -258,7 +258,7 @@ def test_get_hash_dirty_file(tmp_dir, dvc):
     tmp_dir.dvc_gen("file", "file")
     (tmp_dir / "file").write_text("something")
 
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
     expected = "8c7dd922ad47494fc02c388e12c00eac"
     assert fs.info("file").get("md5") == expected
     _, _, obj = stage(dvc.odb.local, "file", fs, "md5", dry_run=True)
@@ -269,7 +269,7 @@ def test_get_hash_dirty_dir(tmp_dir, dvc):
     tmp_dir.dvc_gen({"dir": {"foo": "foo", "bar": "bar"}})
     (tmp_dir / "dir" / "baz").write_text("baz")
 
-    fs = DvcFileSystem(repo=dvc)
+    fs = DataFileSystem(repo=dvc)
     expected = "5ea40360f5b4ec688df672a4db9c17d1.dir"
     assert fs.info("dir").get("md5") == expected
     _, _, obj = stage(dvc.odb.local, "dir", fs, "md5", dry_run=True)