[DataCatalog2.0]: KedroDataCatalog

RELEASE.md

@@ -1,6 +1,11 @@
 # Upcoming Release
 
 ## Major features and improvements
+* Implemented `KedroDataCatalog` repeating `DataCatalog` functionality with a few API enhancements:
+  * Removed `_FrozenDatasets` and access datasets as properties;
+  * Added get dataset by name feature;
+  * `add_feed_dict()` was simplified and renamed to `add_data()`;
+  * Datasets' initialisation was moved out from `from_config()` method to the constructor.
 * Moved development requirements from `requirements.txt` to the dedicated section in `pyproject.toml` for project template.
 * Implemented `Protocol` abstraction for the current `DataCatalog` and adding new catalog implementations.
 * Refactored `kedro run` and `kedro catalog` commands.

docs/source/conf.py

@@ -134,6 +134,7 @@
         "kedro.io.core.DatasetError",
         "kedro.io.core.Version",
         "kedro.io.data_catalog.DataCatalog",
+        "kedro.io.kedro_data_catalog.KedroDataCatalog",
         "kedro.io.memory_dataset.MemoryDataset",
         "kedro.io.partitioned_dataset.PartitionedDataset",
         "kedro.pipeline.pipeline.Pipeline",
@@ -172,6 +173,7 @@
         "Patterns",
         "CatalogConfigResolver",
         "CatalogProtocol",
+        "KedroDataCatalog",
     ),
     "py:data": (
         "typing.Any",

kedro/framework/cli/catalog.py

@@ -95,9 +95,7 @@ def list_datasets(metadata: ProjectMetadata, pipeline: str, env: str) -> None:
 
         for ds_name in default_ds:
             if data_catalog.config_resolver.match_pattern(ds_name):
-                ds_config = data_catalog.config_resolver.resolve_dataset_pattern(
-                    ds_name
-                )
+                ds_config = data_catalog.config_resolver.resolve_pattern(ds_name)
                 factory_ds_by_type[ds_config.get("type", "DefaultDataset")].append(
                     ds_name
                 )
@@ -250,7 +248,7 @@ def resolve_patterns(metadata: ProjectMetadata, env: str) -> None:
         if ds_name in explicit_datasets or is_parameter(ds_name):
             continue
 
-        ds_config = data_catalog.config_resolver.resolve_dataset_pattern(ds_name)
+        ds_config = data_catalog.config_resolver.resolve_pattern(ds_name)
 
         # Exclude MemoryDatasets not set in the catalog explicitly
         if ds_config:

kedro/io/__init__.py

@@ -16,6 +16,7 @@
     Version,
 )
 from .data_catalog import DataCatalog
+from .kedro_data_catalog import KedroDataCatalog
 from .lambda_dataset import LambdaDataset
 from .memory_dataset import MemoryDataset
 from .shared_memory_dataset import SharedMemoryDataset
@@ -30,6 +31,7 @@
     "DatasetAlreadyExistsError",
     "DatasetError",
     "DatasetNotFoundError",
+    "KedroDataCatalog",
     "LambdaDataset",
     "MemoryDataset",
     "SharedMemoryDataset",

kedro/io/catalog_config_resolver.py

@@ -229,7 +229,7 @@ def _resolve_config_credentials(
 
         return resolved_configs
 
-    def resolve_dataset_pattern(self, ds_name: str) -> dict[str, Any]:
+    def resolve_pattern(self, ds_name: str) -> dict[str, Any]:
         """Resolve dataset patterns and return resolved configurations based on the existing patterns."""
         matched_pattern = self.match_pattern(ds_name)
 

kedro/io/data_catalog.py

@@ -75,7 +75,7 @@ def __setattr__(self, key: str, value: Any) -> None:
         if key == "_original_names":
             super().__setattr__(key, value)
             return
-        msg = "Operation not allowed! "
+        msg = "Operation not allowed. "
         if key in self.__dict__:
             msg += "Please change datasets through configuration."
         else:
@@ -324,7 +324,7 @@ def _get_dataset(
         version: Version | None = None,
         suggest: bool = True,
     ) -> AbstractDataset:
-        ds_config = self._config_resolver.resolve_dataset_pattern(dataset_name)
+        ds_config = self._config_resolver.resolve_pattern(dataset_name)
 
         if dataset_name not in self._datasets and ds_config:
             ds = AbstractDataset.from_config(