datachain 0.3.19__py3-none-any.whl → 0.3.20__py3-none-any.whl

datachain/catalog/catalog.py

@@ -79,6 +79,7 @@ if TYPE_CHECKING:
     )
     from datachain.dataset import DatasetVersion
     from datachain.job import Job
+    from datachain.lib.file import File
 
 logger = logging.getLogger("datachain")
 
@@ -1399,65 +1400,34 @@ class Catalog:
         dataset = self.get_dataset(name)
         return self.update_dataset(dataset, **update_data)
 
-    def get_file_signals(
-        self, dataset_name: str, dataset_version: int, row: RowDict
-    ) -> Optional[RowDict]:
+    def get_file_from_row(
+        self, dataset_name: str, dataset_version: int, row: RowDict, signal_name: str
+    ) -> "File":
         """
-        Function that returns file signals from dataset row.
-        Note that signal names are without prefix, so if there was 'laion__file__source'
-        in original row, result will have just 'source'
-        Example output:
-            {
-                "source": "s3://ldb-public",
-                "path": "animals/dogs/dog.jpg",
-                ...
-            }
+        Function that returns specific file signal from dataset row by name.
         """
         from datachain.lib.file import File
         from datachain.lib.signal_schema import DEFAULT_DELIMITER, SignalSchema
 
         version = self.get_dataset(dataset_name).get_version(dataset_version)
-
-        file_signals_values = RowDict()
-
         schema = SignalSchema.deserialize(version.feature_schema)
-        for file_signals in schema.get_signals(File):
-            prefix = file_signals.replace(".", DEFAULT_DELIMITER) + DEFAULT_DELIMITER
-            file_signals_values[file_signals] = {
-                c_name.removeprefix(prefix): c_value
-                for c_name, c_value in row.items()
-                if c_name.startswith(prefix)
-                and DEFAULT_DELIMITER not in c_name.removeprefix(prefix)
-            }
 
-        if not file_signals_values:
-            return None
-
-        # there can be multiple file signals in a schema, but taking the first
-        # one for now. In future we might add ability to choose from which one
-        # to open object
-        return next(iter(file_signals_values.values()))
-
-    def open_object(
-        self,
-        dataset_name: str,
-        dataset_version: int,
-        row: RowDict,
-        use_cache: bool = True,
-        **config: Any,
-    ):
-        from datachain.lib.file import File
+        if signal_name not in schema.get_signals(File):
+            raise RuntimeError(
+                f"File signal with path {signal_name} not found in ",
+                f"dataset {dataset_name}@v{dataset_version} signals schema",
+            )
 
-        file_signals = self.get_file_signals(dataset_name, dataset_version, row)
-        if not file_signals:
-            raise RuntimeError("Cannot open object without file signals")
+        prefix = signal_name.replace(".", DEFAULT_DELIMITER) + DEFAULT_DELIMITER
+        file_signals = {
+            c_name.removeprefix(prefix): c_value
+            for c_name, c_value in row.items()
+            if c_name.startswith(prefix)
+            and DEFAULT_DELIMITER not in c_name.removeprefix(prefix)
+            and c_name.removeprefix(prefix) in File.model_fields
+        }
 
-        config = config or self.client_config
-        client = self.get_client(file_signals["source"], **config)
-        return client.open_object(
-            File._from_row(file_signals),
-            use_cache=use_cache,
-        )
+        return File(**file_signals)
 
     def ls(
         self,

{datachain-0.3.19.dist-info → datachain-0.3.20.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.3.19
+Version: 0.3.20
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0

{datachain-0.3.19.dist-info → datachain-0.3.20.dist-info}/RECORD

@@ -18,7 +18,7 @@ datachain/storage.py,sha256=RiSJLYdHUjnrEWkLBKPcETHpAxld_B2WxLg711t0aZI,3733
 datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
 datachain/utils.py,sha256=KeFSRHsiYthnTu4a6bH-rw04mX1m8krTX0f2NqfQGFI,12114
 datachain/catalog/__init__.py,sha256=g2iAAFx_gEIrqshXlhSEbrc8qDaEH11cjU40n3CHDz4,409
-datachain/catalog/catalog.py,sha256=poTu_B5va35MTCV60ntsn4jvAFXepqa2peCjYCXWeU0,64982
+datachain/catalog/catalog.py,sha256=MC8qxu5r0eWtVSWBxPmnYsc-0sUnkzGUZZxgwFQDhH0,64002
 datachain/catalog/datasource.py,sha256=D-VWIVDCM10A8sQavLhRXdYSCG7F4o4ifswEF80_NAQ,1412
 datachain/catalog/loader.py,sha256=-6VelNfXUdgUnwInVyA8g86Boxv2xqhTh9xNS-Zlwig,8242
 datachain/client/__init__.py,sha256=T4wiYL9KIM0ZZ_UqIyzV8_ufzYlewmizlV4iymHNluE,86
@@ -97,9 +97,9 @@ datachain/sql/sqlite/base.py,sha256=WLPHBhZbXbiqPoRV1VgDrXJqku4UuvJpBhYeQ0k5rI8,
 datachain/sql/sqlite/types.py,sha256=yzvp0sXSEoEYXs6zaYC_2YubarQoZH-MiUNXcpuEP4s,1573
 datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR0,469
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.3.19.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.3.19.dist-info/METADATA,sha256=yMBpXwOmeoWOmpS0m_hp8GFiMs3Zu_ixMzkG6GF_Z2U,17157
-datachain-0.3.19.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-datachain-0.3.19.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.3.19.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.3.19.dist-info/RECORD,,
+datachain-0.3.20.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.3.20.dist-info/METADATA,sha256=zFk_QWL3Ag3kxLdQPqYAFEXnTD2WkxrvJmLLGOxXpsE,17157
+datachain-0.3.20.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+datachain-0.3.20.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.3.20.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.3.20.dist-info/RECORD,,