added dataset name dependencies test and fixes

src/datachain/dataset.py

@@ -79,11 +79,13 @@ class DatasetDependency:
     @property
     def dataset_name(self) -> str:
         """Returns clean dependency dataset name"""
-        from datachain.lib.listing import listing_dataset_name
+        from datachain.lib.listing import parse_listing_uri
 
         if self.type == DatasetDependencyType.DATASET:
             return self.name
-        return listing_dataset_name(self.name.strip("/"), "")
+
+        list_dataset_name, _, _ = parse_listing_uri(self.name.strip("/"), None, {})
+        return list_dataset_name
 
     @classmethod
     def parse(

src/datachain/lib/listing.py

@@ -96,12 +96,14 @@ def is_listing_dataset(name: str) -> bool:
     """Returns True if it's special listing dataset"""
     return name.startswith(LISTING_PREFIX)
 
+
 def listing_uri_from_name(dataset_name: str) -> str:
     """Returns clean storage URI from listing dataset name"""
     if not is_listing_dataset(dataset_name):
         raise ValueError(f"Dataset {dataset_name} is not a listing")
     return dataset_name.removeprefix(LISTING_PREFIX)
 
+
 def is_listing_expired(created_at: datetime) -> bool:
     """Checks if listing has expired based on it's creation date"""
     return datetime.now(timezone.utc) > created_at + timedelta(seconds=LISTING_TTL)

tests/func/test_listing.py

@@ -10,7 +10,7 @@ def test_listing_generator(cloud_test_catalog, cloud_type):
     uri = f"{ctc.src_uri}/cats"
 
     dc = DataChain.from_records(DataChain.DEFAULT_FILE_RECORD).gen(
-        file=list_bucket(uri, **ctc.catalog.client_config)
+        file=list_bucket(uri, client_config=ctc.catalog.client_config)
     )
     assert dc.count() == 2
 

tests/unit/lib/test_datachain.py

@@ -258,11 +258,6 @@ def test_datasets_in_memory():
     assert datasets[0].num_objects == 6
 
 
-@pytest.mark.parametrize(
-    "cloud_type,version_aware",
-    [("file", False)],
-    indirect=True,
-)
 def test_listings(test_session, tmp_dir):
     df = pd.DataFrame(DF_DATA)
     df.to_parquet(tmp_dir / "df.parquet")
@@ -294,11 +289,6 @@ def test_listings(test_session, tmp_dir):
     assert listing.status == 4
 
 
-@pytest.mark.parametrize(
-    "cloud_type,version_aware",
-    [("file", False)],
-    indirect=True,
-)
 def test_listings_reindex(test_session, tmp_dir):
     df = pd.DataFrame(DF_DATA)
     df.to_parquet(tmp_dir / "df.parquet")

tests/unit/test_dataset.py

@@ -1,8 +1,12 @@
+from datetime import datetime, timezone
+
+import pytest
 from sqlalchemy import Column, DateTime
 from sqlalchemy.dialects.sqlite import dialect as sqlite_dialect
 from sqlalchemy.schema import CreateTable
 
 from datachain.data_storage.schema import DataTable
+from datachain.dataset import DatasetDependency, DatasetDependencyType
 from datachain.sql.types import (
     JSON,
     Array,
@@ -84,3 +88,27 @@ def test_schema_serialization(dataset_record):
             "item_type": {"type": "Array", "item_type": {"type": "Float64"}},
         }
     }
+
+
+@pytest.mark.parametrize(
+    "dep_name,dep_type,expected",
+    [
+        ("dogs_dataset", DatasetDependencyType.DATASET, "dogs_dataset"),
+        (
+            "s3://dogs_dataset/dogs",
+            DatasetDependencyType.STORAGE,
+            "lst__s3://dogs_dataset/dogs/",
+        ),
+    ],
+)
+def test_dataset_dependency_dataset_name(dep_name, dep_type, expected):
+    dep = DatasetDependency(
+        id=1,
+        name=dep_name,
+        version="1",
+        type=dep_type,
+        created_at=datetime.now(timezone.utc),
+        dependencies=[],
+    )
+
+    assert dep.dataset_name == expected