erepo: get rid of get_checksum (#5145)

Author: efiop

dvc/dependency/repo.py

@@ -1,5 +1,7 @@
 from voluptuous import Required
 
+from dvc.path_info import PathInfo
+
 from .local import LocalDependency
 
 
@@ -48,7 +50,8 @@ def _get_hash(self, locked=True):
         # we want stream but not fetch, so DVC out directories are
         # walked, but dir contents is not fetched
         with self._make_repo(locked=locked, fetch=False, stream=True) as repo:
-            return repo.get_checksum(self.def_path)
+            path_info = PathInfo(repo.root_dir) / self.def_path
+            return repo.repo_tree.get_hash(path_info, follow_subrepos=False)
 
     def workspace_status(self):
         current = self._get_hash(locked=True)

dvc/external_repo.py

@@ -218,15 +218,6 @@ def _get_tree_for(self, repo, **kwargs):
             kw["fetch"] = True
         return RepoTree(repo, **kw)
 
-    def get_checksum(self, path):
-        path_info = PathInfo(self.root_dir) / path
-        with reraise(FileNotFoundError, PathMissingError(path, self.url)):
-            metadata = self.repo_tree.metadata(path_info)
-
-        # skip subrepos to check for
-        tree = self._get_tree_for(metadata.repo)
-        return tree.get_hash(path_info)
-
     @staticmethod
     def _fix_local_remote(orig_repo, src_repo, remote_name):
         # If a remote URL is relative to the source repo,

dvc/tree/repo.py

@@ -309,7 +309,13 @@ def is_dvc_repo(d):
                 yield from self._walk(repo_walk, None, dvcfiles=dvcfiles)
 
     def walk(
-        self, top, topdown=True, onerror=None, dvcfiles=False, **kwargs
+        self,
+        top,
+        topdown=True,
+        onerror=None,
+        dvcfiles=False,
+        follow_subrepos=None,
+        **kwargs
     ):  # pylint: disable=arguments-differ
         """Walk and merge both DVC and repo trees.
 
@@ -336,13 +342,17 @@ def walk(
                 onerror(NotADirectoryError(top))
             return
 
+        ignore_subrepos = not self._traverse_subrepos
+        if follow_subrepos is not None:
+            ignore_subrepos = not follow_subrepos
+
         tree, dvc_tree = self._get_tree_pair(top)
         repo_exists = tree.exists(top)
         repo_walk = tree.walk(
             top,
             topdown=topdown,
             onerror=onerror,
-            ignore_subrepos=not self._traverse_subrepos,
+            ignore_subrepos=ignore_subrepos,
         )
 
         if not dvc_tree or (repo_exists and dvc_tree.isdvc(top)):
@@ -363,10 +373,14 @@ def walk_files(self, top, **kwargs):  # pylint: disable=arguments-differ
             for fname in files:
                 yield PathInfo(root) / fname
 
-    def get_dir_hash(self, path_info, **kwargs):
+    def get_dir_hash(
+        self, path_info, follow_subrepos=None, **kwargs
+    ):  # pylint: disable=arguments-differ
         tree, dvc_tree = self._get_tree_pair(path_info)
         if tree.exists(path_info):
-            return super().get_dir_hash(path_info, **kwargs)
+            return super().get_dir_hash(
+                path_info, follow_subrepos=follow_subrepos, **kwargs
+            )
         if not dvc_tree:
             raise FileNotFoundError
         return dvc_tree.get_dir_hash(path_info, **kwargs)

tests/func/test_external_repo.py

@@ -194,7 +194,9 @@ def test_subrepos_are_ignored(tmp_dir, erepo_dir):
 
         expected_hash = HashInfo("md5", "e1d9e8eae5374860ae025ec84cfd85c7.dir")
         assert (
-            repo.get_checksum(os.path.join(repo.root_dir, "dir"))
+            repo.repo_tree.get_hash(
+                os.path.join(repo.root_dir, "dir"), follow_subrepos=False
+            )
             == expected_hash
         )