Make prefix not being recognised as dirs anymore

HISTORY.md

@@ -1,5 +1,9 @@
 # cloudpathlib Changelog
 
+## v0.9.1 (UNRELEASED)
+
+ - Fixed S3Path.exists() returns True on partial matches. ([Issue #208](https://github.com/drivendataorg/cloudpathlib/issues/208), [PR #244](https://github.com/drivendataorg/cloudpathlib/pull/244))
+
 ## v0.9.0 (2022-06-03)
  - Added `absolute` to `CloudPath` (does nothing as `CloudPath` is always absolute) ([PR #230](https://github.com/drivendataorg/cloudpathlib/pull/230))
  - Added `resolve` to `CloudPath` (does nothing as `CloudPath` is resolved in advance) ([Issue #151](https://github.com/drivendataorg/cloudpathlib/issues/151), [PR #230](https://github.com/drivendataorg/cloudpathlib/pull/230))

cloudpathlib/s3/s3client.py

@@ -156,13 +156,13 @@ def _s3_file_query(self, cloud_path: S3Path):
 
         # else, confirm it is a dir by filtering to the first item under the prefix
         except ClientError:
+            key = cloud_path.key.rstrip("/") + "/"
+
             return next(
                 (
                     obj
                     for obj in (
-                        self.s3.Bucket(cloud_path.bucket)
-                        .objects.filter(Prefix=cloud_path.key)
-                        .limit(1)
+                        self.s3.Bucket(cloud_path.bucket).objects.filter(Prefix=key).limit(1)
                     )
                 ),
                 None,

tests/test_s3_specific.py

@@ -164,6 +164,24 @@ def test_fake_directories(s3_like_rig):
         assert not test_case.is_file()
 
 
+def test_directories(s3_like_rig):
+    """Fixing bug that marks as directories prefixes of existing paths
+
+    Ref: https://github.com/drivendataorg/cloudpathlib/issues/208
+    """
+    super_path = s3_like_rig.create_cloud_path("dir_0/file0_0.txt")
+    assert super_path.exists()
+    assert not super_path.is_dir()
+
+    super_path = s3_like_rig.create_cloud_path("dir_0")
+    assert super_path.exists()
+    assert super_path.is_dir()
+
+    super_path = s3_like_rig.create_cloud_path("dir_0/file0")
+    assert not super_path.exists()
+    assert not super_path.is_dir()
+
+
 def test_no_sign_request(s3_rig, tmp_path):
     """Tests that we can pass no_sign_request to the S3Client and we will
     be able to access public resources but not private ones.