datachain 0.24.2__py3-none-any.whl → 0.24.4__py3-none-any.whl

datachain/catalog/catalog.py

@@ -1098,9 +1098,18 @@ class Catalog:
     ) -> DatasetRecord:
         from datachain.lib.listing import is_listing_dataset
 
+        project = project or self.metastore.default_project
+
         if is_listing_dataset(name):
             project = self.metastore.listing_project
-        return self.metastore.get_dataset(name, project.id if project else None)
+
+        try:
+            return self.metastore.get_dataset(name, project.id if project else None)
+        except DatasetNotFoundError:
+            raise DatasetNotFoundError(
+                f"Dataset {name} not found in namespace {project.namespace.name}"
+                f" and project {project.name}"
+            ) from None
 
     def get_dataset_with_remote_fallback(
         self,
@@ -1111,6 +1120,14 @@ class Catalog:
         pull_dataset: bool = False,
         update: bool = False,
     ) -> DatasetRecord:
+        # Intentionally ignore update flag is version is provided. Here only exact
+        # version can be provided and update then doesn't make sense.
+        # It corresponds to a query like this for example:
+        #
+        #    dc.read_dataset("some.remote.dataset", version="1.0.0", update=True)
+        if version:
+            update = False
+
         if self.metastore.is_local_dataset(namespace_name) or not update:
             try:
                 project = self.metastore.get_project(project_name, namespace_name)
@@ -1124,7 +1141,7 @@ class Catalog:
             raise DatasetNotFoundError(
                 f"Dataset {name}"
                 + (f" version {version} " if version else " ")
-                + "not found"
+                + f"not found in namespace {namespace_name} and project {project_name}"
             )
 
         if pull_dataset:

datachain/data_storage/metastore.py

@@ -1194,14 +1194,16 @@ class AbstractDBMetastore(AbstractMetastore):
         Gets a single dataset in project by dataset name.
         """
         project_id = project_id or self.default_project.id
+
         d = self._datasets
         query = self._base_dataset_query()
         query = query.where(d.c.name == name, d.c.project_id == project_id)  # type: ignore [attr-defined]
         ds = self._parse_dataset(self.db.execute(query, conn=conn))
         if not ds:
             raise DatasetNotFoundError(
-                f"Dataset {name} not found in project {project_id}"
+                f"Dataset {name} not found in project with id {project_id}"
             )
+
         return ds
 
     def remove_dataset_version(

datachain/data_storage/sqlite.py

@@ -774,7 +774,15 @@ class SQLiteWarehouse(AbstractWarehouse):
         query: Select,
         progress_cb: Optional[Callable[[int], None]] = None,
     ) -> None:
-        if len(query._group_by_clause) > 0:
+        col_id = (
+            query.selected_columns.sys__id
+            if "sys__id" in query.selected_columns
+            else None
+        )
+
+        # If there is no sys__id column, we cannot copy the table in batches,
+        # and we need to copy all rows at once. Same if there is a group by clause.
+        if col_id is None or len(query._group_by_clause) > 0:
             select_q = query.with_only_columns(
                 *[c for c in query.selected_columns if c.name != "sys__id"]
             )
@@ -782,12 +790,7 @@ class SQLiteWarehouse(AbstractWarehouse):
             self.db.execute(q)
             return
 
-        if "sys__id" in query.selected_columns:
-            col_id = query.selected_columns.sys__id
-        else:
-            col_id = sqlalchemy.column("sys__id")
         select_ids = query.with_only_columns(col_id)
-
         ids = self.db.execute(select_ids).fetchall()
 
         select_q = (

datachain/dataset.py

@@ -32,7 +32,7 @@ QUERY_DATASET_PREFIX = "ds_query_"
 LISTING_PREFIX = "lst__"
 
 DEFAULT_DATASET_VERSION = "1.0.0"
-DATASET_NAME_RESERVED_CHARS = ["."]
+DATASET_NAME_RESERVED_CHARS = [".", "@"]
 DATASET_NAME_REPLACEMENT_CHAR = "_"
 
 

datachain/lib/dc/datachain.py

@@ -21,6 +21,7 @@ from typing import (
 import orjson
 import sqlalchemy
 from pydantic import BaseModel
+from sqlalchemy.sql.elements import ColumnElement
 from tqdm import tqdm
 
 from datachain import semver
@@ -806,11 +807,35 @@ class DataChain:
             chain.save("new_dataset")
             ```
         """
+        # Convert string partition_by parameters to Column objects
+        processed_partition_by = partition_by
+        if partition_by is not None:
+            if isinstance(partition_by, (str, Function, ColumnElement)):
+                list_partition_by = [partition_by]
+            else:
+                list_partition_by = list(partition_by)
+
+            processed_partition_columns: list[ColumnElement] = []
+            for col in list_partition_by:
+                if isinstance(col, str):
+                    col_db_name = ColumnMeta.to_db_name(col)
+                    col_type = self.signals_schema.get_column_type(col_db_name)
+                    column = Column(col_db_name, python_to_sql(col_type))
+                    processed_partition_columns.append(column)
+                elif isinstance(col, Function):
+                    column = col.get_column(self.signals_schema)
+                    processed_partition_columns.append(column)
+                else:
+                    # Assume it's already a ColumnElement
+                    processed_partition_columns.append(col)
+
+            processed_partition_by = processed_partition_columns
+
         udf_obj = self._udf_to_obj(Aggregator, func, params, output, signal_map)
         return self._evolve(
             query=self._query.generate(
                 udf_obj.to_udf_wrapper(),
-                partition_by=partition_by,
+                partition_by=processed_partition_by,
                 **self._settings.to_dict(),
             ),
             signal_schema=udf_obj.output,

datachain/lib/dc/datasets.py

@@ -189,6 +189,7 @@ def read_dataset(
         namespace_name=namespace_name,
         version=version,  #  type: ignore[arg-type]
         session=session,
+        update=update,
     )
 
     signals_schema = SignalSchema({"sys": Sys})

datachain/listing.py

@@ -65,10 +65,17 @@ class Listing:
 
     @cached_property
     def dataset(self) -> "DatasetRecord":
+        from datachain.error import DatasetNotFoundError
+
         assert self.dataset_name
-        return self.metastore.get_dataset(
-            self.dataset_name, self.metastore.listing_project.id
-        )
+        project = self.metastore.listing_project
+        try:
+            return self.metastore.get_dataset(self.dataset_name, project.id)
+        except DatasetNotFoundError:
+            raise DatasetNotFoundError(
+                f"Dataset {self.dataset_name} not found in namespace"
+                f" {project.namespace.name} and project {project.name}"
+            ) from None
 
     @cached_property
     def dataset_rows(self):

datachain/namespace.py

@@ -6,7 +6,7 @@ from typing import Any, Optional, TypeVar
 from datachain.error import InvalidNamespaceNameError
 
 N = TypeVar("N", bound="Namespace")
-NAMESPACE_NAME_RESERVED_CHARS = ["."]
+NAMESPACE_NAME_RESERVED_CHARS = [".", "@"]
 
 
 @dataclass(frozen=True)

datachain/project.py

@@ -7,7 +7,7 @@ from datachain.error import InvalidProjectNameError
 from datachain.namespace import Namespace
 
 P = TypeVar("P", bound="Project")
-PROJECT_NAME_RESERVED_CHARS = ["."]
+PROJECT_NAME_RESERVED_CHARS = [".", "@"]
 
 
 @dataclass(frozen=True)

datachain/query/dataset.py

@@ -82,7 +82,10 @@ if TYPE_CHECKING:
 INSERT_BATCH_SIZE = 10000
 
 PartitionByType = Union[
-    Function, ColumnElement, Sequence[Union[Function, ColumnElement]]
+    str,
+    Function,
+    ColumnElement,
+    Sequence[Union[str, Function, ColumnElement]],
 ]
 JoinPredicateType = Union[str, ColumnClause, ColumnElement]
 DatasetDependencyType = tuple["DatasetRecord", str]
@@ -1142,6 +1145,7 @@ class DatasetQuery:
                     project_name=project_name,
                     version=version,
                     pull_dataset=True,
+                    update=update,
                 )
             )
 

{datachain-0.24.2.dist-info → datachain-0.24.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.24.2
+Version: 0.24.4
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0

{datachain-0.24.2.dist-info → datachain-0.24.4.dist-info}/RECORD

@@ -3,17 +3,17 @@ datachain/__main__.py,sha256=hG3Y4ARGEqe1AWwNMd259rBlqtphx1Wk39YbueQ0yV8,91
 datachain/asyn.py,sha256=RH_jFwJcTXxhEFomaI9yL6S3Onau6NZ6FSKfKFGtrJE,9689
 datachain/cache.py,sha256=ESVRaCJXEThMIfGEFVHx6wJPOZA7FYk9V6WxjyuqUBY,3626
 datachain/config.py,sha256=g8qbNV0vW2VEKpX-dGZ9pAn0DAz6G2ZFcr7SAV3PoSM,4272
-datachain/dataset.py,sha256=wDrukmkDnYP0X8bAGY-7O1NDE3DWCFqrH8VVDpXM9Ok,25263
+datachain/dataset.py,sha256=ATGa-CBTFoZeTN2V40-zHEzfMBcdYK0WuoJ6H2yEAvo,25268
 datachain/delta.py,sha256=fTEhCedseUsHuH_Ek52NXFhFPyFD_6MioEH5sCilNgo,9897
 datachain/error.py,sha256=OWwWMkzZYJrkcoEDGhJHMf7SfKvxcsOLRF94mjPf29I,1609
 datachain/job.py,sha256=x5PB6d5sqx00hePNNkirESlOVAvnmkEM5ygUgQmAhsk,1262
-datachain/listing.py,sha256=T4bCgdCRuFW7bsPUG2PSl5om2nfJL6fzB84m7mCO8cA,7136
-datachain/namespace.py,sha256=r7YwpXFc7LdMS2jhyLMTrAHffALFG2bAIiYUSuZa5Rc,1786
+datachain/listing.py,sha256=GuUlj3oYJQOIbLYr3IqNCSeuiU5pfOtRAQQl9uBEFQU,7458
+datachain/namespace.py,sha256=MozcXYxedIbamzY56YKy9r9fgSpOm2VryhWfIf6stYk,1791
 datachain/node.py,sha256=KWDT0ClYXB7FYI-QOvzAa-UDkLJErUI2eWm5FBteYuU,5577
 datachain/nodes_fetcher.py,sha256=_wgaKyqEjkqdwJ_Hj6D8vUYz7hnU7g6xhm0H6ZnYxmE,1095
 datachain/nodes_thread_pool.py,sha256=mdo0s-VybuSZkRUARcUO4Tjh8KFfZr9foHqmupx2SmM,3989
 datachain/progress.py,sha256=lRzxoYP4Qv2XBwD78sOkmYRzHFpZ2ExVNJF8wAeICtY,770
-datachain/project.py,sha256=kX5urIAnkHcZJ8m_IIzrUtHEytMBeiceVTrqgCXc_4E,2275
+datachain/project.py,sha256=90D4GpJSA3t0fayYZbzrL3sk4U7EJhQo8psnWvdI7_o,2280
 datachain/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/script_meta.py,sha256=V-LaFOZG84pD0Zc0NvejYdzwDgzITv6yHvAHggDCnuY,4978
 datachain/semver.py,sha256=UB8GHPBtAP3UJGeiuJoInD7SK-DnB93_Xd1qy_CQ9cU,2074
@@ -21,7 +21,7 @@ datachain/studio.py,sha256=bLok-eJNFRHQScEyAyA_Fas52dmijd5r-73KudWxV4k,13337
 datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
 datachain/utils.py,sha256=DNqOi-Ydb7InyWvD9m7_yailxz6-YGpZzh00biQaHNo,15305
 datachain/catalog/__init__.py,sha256=cMZzSz3VoUi-6qXSVaHYN-agxQuAcz2XSqnEPZ55crE,353
-datachain/catalog/catalog.py,sha256=z4GbRMHeW0YA20Sjh7QuPy1Rj4RkX547WN9Pp5wAD6o,65277
+datachain/catalog/catalog.py,sha256=3QwiljkEHWm5xNmvqT3ey_JvKS8viiJgGWwhbqWIH0M,65996
 datachain/catalog/datasource.py,sha256=IkGMh0Ttg6Q-9DWfU_H05WUnZepbGa28HYleECi6K7I,1353
 datachain/catalog/loader.py,sha256=UXjYD6BNRoupPvkiz3-b04jepXhtLHCA4gzKFnXxOtQ,5987
 datachain/cli/__init__.py,sha256=WvBqnwjG8Wp9xGCn-4eqfoZ3n7Sj1HJemCi4MayJh_c,8221
@@ -49,10 +49,10 @@ datachain/client/s3.py,sha256=6DNVGLg-woPS1DVlYVX2rIlunNblsuxyOnI1rSzhW3k,7515
 datachain/data_storage/__init__.py,sha256=9Wit-oe5P46V7CJQTD0BJ5MhOa2Y9h3ddJ4VWTe-Lec,273
 datachain/data_storage/db_engine.py,sha256=n8ojCbvVMPY2e3SG8fUaaD0b9GkVfpl_Naa_6EiHfWg,3788
 datachain/data_storage/job.py,sha256=9r0OGwh22bHNIvLHqg8_-eJSP1YYB-BN5HOla5TdCxw,402
-datachain/data_storage/metastore.py,sha256=9mWYOKK3AoHeKPGFm-WBfPrmnYHhwYeXx5MOueKTe7I,52657
+datachain/data_storage/metastore.py,sha256=af7TsMHbANXmWKIu-LzQmsZpNxM6-hhzZfInWx7MQXI,52667
 datachain/data_storage/schema.py,sha256=o3JbURKXRg3IJyIVA4QjHHkn6byRuz7avbydU2FlvNY,9897
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
-datachain/data_storage/sqlite.py,sha256=tT_soVi6l_pFSKaDktA1t4qW_vmPvXnvYSf4TZTKZYk,30067
+datachain/data_storage/sqlite.py,sha256=TTQjdDXUaZSr3MEaxZjDhsVIkIJqxFNA-sD25TO3m_4,30228
 datachain/data_storage/warehouse.py,sha256=2Bp2fXfcm-acwYjDWqVzGjoIQSAR4L56GPNtPcaT2gU,32418
 datachain/diff/__init__.py,sha256=-OFZzgOplqO84iWgGY7kfe60NXaWR9JRIh9T-uJboAM,9668
 datachain/fs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -103,8 +103,8 @@ datachain/lib/convert/values_to_tuples.py,sha256=j5yZMrVUH6W7b-7yUvdCTGI7JCUAYUO
 datachain/lib/dc/__init__.py,sha256=HD0NYrdy44u6kkpvgGjJcvGz-UGTHui2azghcT8ZUg0,838
 datachain/lib/dc/csv.py,sha256=q6a9BpapGwP6nwy6c5cklxQumep2fUp9l2LAjtTJr6s,4411
 datachain/lib/dc/database.py,sha256=g5M6NjYR1T0vKte-abV-3Ejnm-HqxTIMir5cRi_SziE,6051
-datachain/lib/dc/datachain.py,sha256=dOPtNOYx6ocFr61YHTDrKGoMTDWDY0AZt8MLh79EJkc,85876
-datachain/lib/dc/datasets.py,sha256=U4xqAfs6FdW8HIJjeayQaIg1dunaIsVXYGqfq_sDSv0,13274
+datachain/lib/dc/datachain.py,sha256=_FJnpgNN_b2xz39MsgeS0NTto0hzpcFPbJlaUBLcqTs,87094
+datachain/lib/dc/datasets.py,sha256=MzM7MTn90Q-dZYuMNUzJXRW1YHOpHeFHspadRjQoI70,13297
 datachain/lib/dc/hf.py,sha256=PJl2wiLjdRsMz0SYbLT-6H8b-D5i2WjeH7li8HHOk_0,2145
 datachain/lib/dc/json.py,sha256=dNijfJ-H92vU3soyR7X1IiDrWhm6yZIGG3bSnZkPdAE,2733
 datachain/lib/dc/listings.py,sha256=V379Cb-7ZyquM0w7sWArQZkzInZy4GB7QQ1ZfowKzQY,4544
@@ -125,7 +125,7 @@ datachain/model/ultralytics/pose.py,sha256=pBlmt63Qe68FKmexHimUGlNbNOoOlMHXG4fzX
 datachain/model/ultralytics/segment.py,sha256=63bDCj43E6iZ0hFI5J6uQfksdCmjEp6sEm1XzVaE8pw,2986
 datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
 datachain/query/batch.py,sha256=-goxLpE0EUvaDHu66rstj53UnfHpYfBUGux8GSpJ93k,4306
-datachain/query/dataset.py,sha256=mKee4PkQHYPT96utPjM1DocURU4TghAR7AHtYkzdqwY,61292
+datachain/query/dataset.py,sha256=t9EWZkJGPRPcBvKOsFO7ZiaTeUXc8YuTZydRbcv83_E,61350
 datachain/query/dispatch.py,sha256=A0nPxn6mEN5d9dDo6S8m16Ji_9IvJLXrgF2kqXdi4fs,15546
 datachain/query/metrics.py,sha256=DOK5HdNVaRugYPjl8qnBONvTkwjMloLqAr7Mi3TjCO0,858
 datachain/query/params.py,sha256=O_j89mjYRLOwWNhYZl-z7mi-rkdP7WyFmaDufsdTryE,863
@@ -157,9 +157,9 @@ datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR
 datachain/toolkit/__init__.py,sha256=eQ58Q5Yf_Fgv1ZG0IO5dpB4jmP90rk8YxUWmPc1M2Bo,68
 datachain/toolkit/split.py,sha256=ktGWzY4kyzjWyR86dhvzw-Zhl0lVk_LOX3NciTac6qo,2914
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.24.2.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.24.2.dist-info/METADATA,sha256=66Dz51BXpod8ZZG-pcmodALbszVZjNJXykMIrYRwXdA,13281
-datachain-0.24.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-datachain-0.24.2.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.24.2.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.24.2.dist-info/RECORD,,
+datachain-0.24.4.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.24.4.dist-info/METADATA,sha256=N2RlOFlgnsdSuBeN_JKm_NZEZY6qvBv8YgSiXeGeRZQ,13281
+datachain-0.24.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+datachain-0.24.4.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.24.4.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.24.4.dist-info/RECORD,,