From cc72da22279aff09df52000377a25ac6bc92798a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Danie=CC=88l=20de=20Kok?= <me@danieldk.eu>
Date: Wed, 17 Jan 2024 09:53:01 +0100
Subject: [PATCH] Temporily xfail local remote storage test

---
 spacy/tests/test_cli.py | 61 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 61 insertions(+)

diff --git a/spacy/tests/test_cli.py b/spacy/tests/test_cli.py
index a47f03e8ab4..c9e823ffe68 100644
--- a/spacy/tests/test_cli.py
+++ b/spacy/tests/test_cli.py
@@ -878,6 +878,67 @@ def test_applycli_user_data():
         assert result[0]._.ext == val
 
 
+# TODO: remove this xfail after merging master into v4. The issue
+#       is that for local files, pathy started returning os.stat_result,
+#       which doesn't have a last_modified property. So, recency-sorting
+#       fails and the test fails. However, once we merge master into
+#       v4, we'll use weasel, which in turn uses cloudpathlib, which
+#       should resolve this issue.
+@pytest.mark.xfail(reason="Recency sorting is broken on some platforms")
+def test_local_remote_storage():
+    with make_tempdir() as d:
+        filename = "a.txt"
+
+        content_hashes = ("aaaa", "cccc", "bbbb")
+        for i, content_hash in enumerate(content_hashes):
+            # make sure that each subsequent file has a later timestamp
+            if i > 0:
+                time.sleep(1)
+            content = f"{content_hash} content"
+            loc_file = d / "root" / filename
+            if not loc_file.parent.exists():
+                loc_file.parent.mkdir(parents=True)
+            with loc_file.open(mode="w") as file_:
+                file_.write(content)
+
+            # push first version to remote storage
+            remote = RemoteStorage(d / "root", str(d / "remote"))
+            remote.push(filename, "aaaa", content_hash)
+
+            # retrieve with full hashes
+            loc_file.unlink()
+            remote.pull(filename, command_hash="aaaa", content_hash=content_hash)
+            with loc_file.open(mode="r") as file_:
+                assert file_.read() == content
+
+            # retrieve with command hash
+            loc_file.unlink()
+            remote.pull(filename, command_hash="aaaa")
+            with loc_file.open(mode="r") as file_:
+                assert file_.read() == content
+
+            # retrieve with content hash
+            loc_file.unlink()
+            remote.pull(filename, content_hash=content_hash)
+            with loc_file.open(mode="r") as file_:
+                assert file_.read() == content
+
+            # retrieve with no hashes
+            loc_file.unlink()
+            remote.pull(filename)
+            with loc_file.open(mode="r") as file_:
+                assert file_.read() == content
+
+
+def test_local_remote_storage_pull_missing():
+    # pulling from a non-existent remote pulls nothing gracefully
+    with make_tempdir() as d:
+        filename = "a.txt"
+        remote = RemoteStorage(d / "root", str(d / "remote"))
+        assert remote.pull(filename, command_hash="aaaa") is None
+        assert remote.pull(filename) is None
+
+
 def test_cli_find_threshold(capsys):
     def make_examples(nlp: Language) -> List[Example]:
         docs: List[Example] = []