use cache dir as a default remote when importing from local repo

dvc/external_repo.py

@@ -4,11 +4,11 @@
 import tempfile
 from contextlib import contextmanager
 from distutils.dir_util import copy_tree
-
 from funcy import retry
 
-from dvc.config import NoRemoteError
 from dvc.exceptions import NoRemoteInExternalRepoError
+from dvc.remote import RemoteConfig
+from dvc.config import NoRemoteError
 from dvc.exceptions import NoOutputInExternalRepoError
 from dvc.exceptions import OutputNotFoundError
 from dvc.utils.fs import remove
@@ -69,6 +69,20 @@ def _external_repo(url=None, rev=None, cache_dir=None):
 
     repo = Repo(new_path)
     try:
+        # check if the URL is local and no default remote is present
+        # add default remote pointing to the original repo's cache location
+        if os.path.isdir(url):
+            rconfig = RemoteConfig(repo.config)
+            if not rconfig.remote_config_exists():
+                original_repo = Repo(url)
+                rconfig.add(
+                    "upstream",
+                    original_repo.cache.local.cache_dir,
+                    default=True,
+                    level=Config.LEVEL_LOCAL,
+                )
+                original_repo.close()
+
         if cache_dir is not None:
             cache_config = CacheConfig(repo.config)
             cache_config.set_dir(cache_dir, level=Config.LEVEL_LOCAL)

dvc/remote/config.py

@@ -156,3 +156,18 @@ def get_default(self, level=None):
         return self.config.get(
             Config.SECTION_CORE, Config.SECTION_CORE_REMOTE, level=level
         )
+
+    def remote_config_exists(self):
+        """
+        Checks if default remote config is present.
+        Args:
+            rconfig: a remote config
+
+        Returns:
+            True if the remote config exists, else False
+        """
+        try:
+            default = self.get_default()
+        except ConfigError:
+            default = None
+        return bool(default)

tests/conftest.py

@@ -7,7 +7,6 @@
 from git import Repo
 from git.exc import GitCommandNotFound
 
-from dvc.remote.config import RemoteConfig
 from dvc.remote.ssh.connection import SSHConnection
 from dvc.repo import Repo as DvcRepo
 from dvc.utils.compat import cast_bytes_py2
@@ -148,11 +147,6 @@ def erepo(repo_dir):
         repo.dvc.scm.add([stage_foo.path, stage_bar.path, stage_data_dir.path])
         repo.dvc.scm.commit("init repo")
 
-        rconfig = RemoteConfig(repo.dvc.config)
-        rconfig.add("upstream", repo.dvc.cache.local.cache_dir, default=True)
-        repo.dvc.scm.add([repo.dvc.config.config_file])
-        repo.dvc.scm.commit("add remote")
-
         repo.create("version", "master")
         repo.dvc.add("version")
         repo.dvc.scm.add([".gitignore", "version.dvc"])

tests/func/test_external_repo.py

@@ -1,7 +1,9 @@
+import filecmp
 import os
 
 from mock import patch
 
+from dvc.repo import Repo
 from dvc.external_repo import external_repo
 from dvc.scm.git import Git
 from dvc.utils.fs import path_isin
@@ -26,3 +28,13 @@ def test_external_repo(erepo):
             assert path_isin(repo.cache.local.cache_dir, repo.root_dir)
 
         assert mock.call_count == 1
+
+
+def test_external_repo_import_without_remote(erepo, dvc_repo):
+    src = erepo.FOO
+    dst = os.path.join(dvc_repo.root_dir, "foo")
+
+    Repo.get(erepo.root_dir, src, dst)
+    assert os.path.exists(dst)
+    assert os.path.isfile(dst)
+    assert filecmp.cmp(erepo.FOO, dst, shallow=False)

tests/func/test_get.py

@@ -101,7 +101,6 @@ def test_get_from_non_dvc_master(erepo, tmp_path, monkeypatch, caplog):
     with caplog.at_level(logging.INFO, logger="dvc"):
         Repo.get(erepo._root_dir, erepo.FOO, out=imported_file, rev="branch")
 
-    assert caplog.text == ""
     assert filecmp.cmp(
         os.path.join(erepo._root_dir, erepo.FOO), imported_file, shallow=False
     )