datachain 0.22.0__py3-none-any.whl → 0.23.0__py3-none-any.whl

datachain/catalog/catalog.py

@@ -1059,6 +1059,39 @@ class Catalog:
 
         return self.get_dataset(name, project)
 
+    def get_full_dataset_name(
+        self,
+        name: str,
+        project_name: Optional[str] = None,
+        namespace_name: Optional[str] = None,
+    ) -> tuple[str, str, str]:
+        """
+        Returns dataset name together with separated namespace and project name.
+        It takes into account all the ways namespace and project can be added.
+        """
+        parsed_namespace_name, parsed_project_name, name = parse_dataset_name(name)
+
+        namespace_env = os.environ.get("DATACHAIN_NAMESPACE")
+        project_env = os.environ.get("DATACHAIN_PROJECT")
+        if project_env and len(project_env.split(".")) == 2:
+            # we allow setting both namespace and project in DATACHAIN_PROJECT
+            namespace_env, project_env = project_env.split(".")
+
+        namespace_name = (
+            parsed_namespace_name
+            or namespace_name
+            or namespace_env
+            or self.metastore.default_namespace_name
+        )
+        project_name = (
+            parsed_project_name
+            or project_name
+            or project_env
+            or self.metastore.default_project_name
+        )
+
+        return namespace_name, project_name, name
+
     def get_dataset(
         self, name: str, project: Optional[Project] = None
     ) -> DatasetRecord:

datachain/cli/commands/datasets.py

@@ -8,7 +8,6 @@ if TYPE_CHECKING:
 
 from datachain.cli.utils import determine_flavors
 from datachain.config import Config
-from datachain.dataset import parse_dataset_name
 from datachain.error import DataChainError, DatasetNotFoundError
 from datachain.studio import list_datasets as list_datasets_studio
 
@@ -106,9 +105,8 @@ def list_datasets_local(catalog: "Catalog", name: Optional[str] = None):
 
 
 def list_datasets_local_versions(catalog: "Catalog", name: str):
-    namespace_name, project_name, name = parse_dataset_name(name)
-    namespace_name = namespace_name or catalog.metastore.default_namespace_name
-    project_name = project_name or catalog.metastore.default_project_name
+    namespace_name, project_name, name = catalog.get_full_dataset_name(name)
+
     project = catalog.metastore.get_project(project_name, namespace_name)
     ds = catalog.get_dataset(name, project)
     for v in ds.versions:
@@ -137,9 +135,7 @@ def rm_dataset(
     studio: Optional[bool] = False,
     team: Optional[str] = None,
 ):
-    namespace_name, project_name, name = parse_dataset_name(name)
-    namespace_name = namespace_name or catalog.metastore.default_namespace_name
-    project_name = project_name or catalog.metastore.default_project_name
+    namespace_name, project_name, name = catalog.get_full_dataset_name(name)
 
     if not catalog.metastore.is_local_dataset(namespace_name) and studio:
         from datachain.studio import remove_studio_dataset
@@ -166,9 +162,7 @@ def edit_dataset(
     attrs: Optional[list[str]] = None,
     team: Optional[str] = None,
 ):
-    namespace_name, project_name, name = parse_dataset_name(name)
-    namespace_name = namespace_name or catalog.metastore.default_namespace_name
-    project_name = project_name or catalog.metastore.default_project_name
+    namespace_name, project_name, name = catalog.get_full_dataset_name(name)
 
     if catalog.metastore.is_local_dataset(namespace_name):
         try:

datachain/data_storage/metastore.py

@@ -132,6 +132,7 @@ class AbstractMetastore(ABC, Serializable):
         description: Optional[str] = None,
         uuid: Optional[str] = None,
         ignore_if_exists: bool = True,
+        validate: bool = True,
         **kwargs,
     ) -> Namespace:
         """Creates new namespace"""
@@ -192,6 +193,7 @@ class AbstractMetastore(ABC, Serializable):
         description: Optional[str] = None,
         uuid: Optional[str] = None,
         ignore_if_exists: bool = True,
+        validate: bool = True,
         **kwargs,
     ) -> Project:
         """Creates new project in specific namespace"""
@@ -725,8 +727,11 @@ class AbstractDBMetastore(AbstractMetastore):
         description: Optional[str] = None,
         uuid: Optional[str] = None,
         ignore_if_exists: bool = True,
+        validate: bool = True,
         **kwargs,
     ) -> Namespace:
+        if validate:
+            Namespace.validate_name(name)
         query = self._namespaces_insert().values(
             name=name,
             uuid=uuid or str(uuid4()),
@@ -775,12 +780,15 @@ class AbstractDBMetastore(AbstractMetastore):
         description: Optional[str] = None,
         uuid: Optional[str] = None,
         ignore_if_exists: bool = True,
+        validate: bool = True,
         **kwargs,
     ) -> Project:
+        if validate:
+            Project.validate_name(name)
         try:
             namespace = self.get_namespace(namespace_name)
         except NamespaceNotFoundError:
-            namespace = self.create_namespace(namespace_name)
+            namespace = self.create_namespace(namespace_name, validate=validate)
 
         query = self._projects_insert().values(
             namespace_id=namespace.id,
@@ -817,11 +825,14 @@ class AbstractDBMetastore(AbstractMetastore):
         """Gets a single project inside some namespace by name"""
         n = self._namespaces
         p = self._projects
+        validate = True
+
         if self._is_listing_project(name, namespace_name) or self._is_default_project(
             name, namespace_name
         ):
             # we are always creating default and listing projects if they don't exist
             create = True
+            validate = False
 
         query = self._projects_select(
             *(getattr(n.c, f) for f in self._namespaces_fields),
@@ -834,7 +845,7 @@ class AbstractDBMetastore(AbstractMetastore):
         rows = list(self.db.execute(query, conn=conn))
         if not rows:
             if create:
-                return self.create_project(namespace_name, name)
+                return self.create_project(namespace_name, name, validate=validate)
             raise ProjectNotFoundError(
                 f"Project {name} in namespace {namespace_name} not found."
             )

datachain/data_storage/sqlite.py

@@ -468,8 +468,12 @@ class SQLiteMetastore(AbstractDBMetastore):
         be created implicitly though, to keep the same fully qualified name with
         Studio dataset.
         """
-        system_namespace = self.create_namespace(Namespace.system(), "System namespace")
-        self.create_project(system_namespace.name, Project.listing(), "Listing project")
+        system_namespace = self.create_namespace(
+            Namespace.system(), "System namespace", validate=False
+        )
+        self.create_project(
+            system_namespace.name, Project.listing(), "Listing project", validate=False
+        )
 
     def _check_schema_version(self) -> None:
         """

datachain/dataset.py

@@ -81,8 +81,10 @@ def create_dataset_uri(
 def parse_dataset_name(name: str) -> tuple[Optional[str], Optional[str], str]:
     """Parses dataset name and returns namespace, project and name"""
     if not name:
-        raise ValueError("Name must be defined to parse it")
+        raise InvalidDatasetNameError("Name must be defined to parse it")
     split = name.split(".")
+    if len(split) > 3:
+        raise InvalidDatasetNameError(f"Invalid dataset name {name}")
     name = split[-1]
     project_name = split[-2] if len(split) > 1 else None
     namespace_name = split[-3] if len(split) > 2 else None

datachain/lib/dc/datachain.py

@@ -24,7 +24,7 @@ from pydantic import BaseModel
 from tqdm import tqdm
 
 from datachain import semver
-from datachain.dataset import DatasetRecord, parse_dataset_name
+from datachain.dataset import DatasetRecord
 from datachain.delta import delta_disabled
 from datachain.error import ProjectCreateNotAllowedError, ProjectNotFoundError
 from datachain.func import literal
@@ -557,6 +557,7 @@ class DataChain:
             update_version: which part of the dataset version to automatically increase.
                 Available values: `major`, `minor` or `patch`. Default is `patch`.
         """
+        catalog = self.session.catalog
         if version is not None:
             semver.validate(version)
 
@@ -570,17 +571,10 @@ class DataChain:
                 " patch"
             )
 
-        namespace_name, project_name, name = parse_dataset_name(name)
-
-        namespace_name = (
-            namespace_name
-            or self._settings.namespace
-            or self.session.catalog.metastore.default_namespace_name
-        )
-        project_name = (
-            project_name
-            or self._settings.project
-            or self.session.catalog.metastore.default_project_name
+        namespace_name, project_name, name = catalog.get_full_dataset_name(
+            name,
+            namespace_name=self._settings.namespace,
+            project_name=self._settings.project,
         )
 
         try:

datachain/lib/dc/datasets.py

@@ -1,7 +1,6 @@
 from collections.abc import Sequence
 from typing import TYPE_CHECKING, Optional, Union, get_origin, get_type_hints
 
-from datachain.dataset import parse_dataset_name
 from datachain.error import (
     DatasetNotFoundError,
     DatasetVersionNotFoundError,
@@ -125,11 +124,11 @@ def read_dataset(
     session = Session.get(session)
     catalog = session.catalog
 
-    namespace_name, project_name, name = parse_dataset_name(name)
-    namespace_name = (
-        namespace_name or namespace or catalog.metastore.default_namespace_name
+    namespace_name, project_name, name = catalog.get_full_dataset_name(
+        name,
+        project_name=project,
+        namespace_name=namespace,
     )
-    project_name = project_name or project or catalog.metastore.default_project_name
 
     if version is not None:
         try:
@@ -320,11 +319,11 @@ def delete_dataset(
     session = Session.get(session, in_memory=in_memory)
     catalog = session.catalog
 
-    namespace_name, project_name, name = parse_dataset_name(name)
-    namespace_name = (
-        namespace_name or namespace or catalog.metastore.default_namespace_name
+    namespace_name, project_name, name = catalog.get_full_dataset_name(
+        name,
+        project_name=project,
+        namespace_name=namespace,
     )
-    project_name = project_name or project or catalog.metastore.default_project_name
 
     if not catalog.metastore.is_local_dataset(namespace_name) and studio:
         return remove_studio_dataset(

datachain/lib/dc/records.py

@@ -97,4 +97,4 @@ def read_records(
     for chunk in batched(records, INSERT_BATCH_SIZE):
         warehouse.insert_rows(table, chunk)
     warehouse.insert_rows_done(table)
-    return read_dataset(name=dsr.name, session=session, settings=settings)
+    return read_dataset(name=dsr.full_name, session=session, settings=settings)

datachain/lib/signal_schema.py

@@ -25,6 +25,7 @@ from pydantic import BaseModel, Field, create_model
 from sqlalchemy import ColumnElement
 from typing_extensions import Literal as LiteralEx
 
+from datachain.func import literal
 from datachain.func.func import Func
 from datachain.lib.convert.python_to_sql import python_to_sql
 from datachain.lib.convert.sql_to_python import sql_to_python
@@ -659,6 +660,7 @@ class SignalSchema:
 
     def mutate(self, args_map: dict) -> "SignalSchema":
         new_values = self.values.copy()
+        primitives = (bool, str, int, float)
 
         for name, value in args_map.items():
             if isinstance(value, Column) and value.name in self.values:
@@ -679,6 +681,12 @@ class SignalSchema:
                 # adding new signal with function
                 new_values[name] = value.get_result_type(self)
                 continue
+            if isinstance(value, primitives):
+                # For primitives, store the type, not the value
+                val = literal(value)
+                val.type = python_to_sql(type(value))()
+                new_values[name] = sql_to_python(val)
+                continue
             if isinstance(value, ColumnElement):
                 # adding new signal
                 new_values[name] = sql_to_python(value)

{datachain-0.22.0.dist-info → datachain-0.23.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.22.0
+Version: 0.23.0
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0

{datachain-0.22.0.dist-info → datachain-0.23.0.dist-info}/RECORD

@@ -3,7 +3,7 @@ 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=--7UI8lZ2lVhk2mNCsHACGigQe96-jBUcbnDMebj-cE,24089
+datachain/dataset.py,sha256=Dn8zx_4zuiW28dF-cNtAXFLS7Her0015YYdLlFGwMas,24195
 datachain/delta.py,sha256=4RqLLc9dJLF8x9GG9IDgi86DwuPerZQ4HAUnNBeACw8,8446
 datachain/error.py,sha256=OWwWMkzZYJrkcoEDGhJHMf7SfKvxcsOLRF94mjPf29I,1609
 datachain/job.py,sha256=x5PB6d5sqx00hePNNkirESlOVAvnmkEM5ygUgQmAhsk,1262
@@ -21,13 +21,13 @@ 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=43Yp1xQnwrozl2_VhVWQDFHxYPunXP95v7n1PoGc6mw,63546
+datachain/catalog/catalog.py,sha256=j8aH0zAHJRCJ_-uOYapK0spp9Go_Ehwxz_1FI3p-Q5I,64733
 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
 datachain/cli/utils.py,sha256=wrLnAh7Wx8O_ojZE8AE4Lxn5WoxHbOj7as8NWlLAA74,3036
 datachain/cli/commands/__init__.py,sha256=zp3bYIioO60x_X04A4-IpZqSYVnpwOa1AdERQaRlIhI,493
-datachain/cli/commands/datasets.py,sha256=Bva9gTi1HMvvCQPFUPxLYrHQduDlJDWV8EN6IcJcC3Y,6949
+datachain/cli/commands/datasets.py,sha256=LfOe22O9OCEDI8K2cy05Gp4_Q-GFHOHRv4bXQ-USM4s,6472
 datachain/cli/commands/du.py,sha256=9edEzDEs98K2VYk8Wf-ZMpUzALcgm9uD6YtoqbvtUGU,391
 datachain/cli/commands/index.py,sha256=eglNaIe1yyIadUHHumjtNbgIjht6kme7SS7xE3YHR88,198
 datachain/cli/commands/ls.py,sha256=CBmk838Q-EQp04lE2Qdnpsc1GXAkC4-I-b-a_828n1E,5272
@@ -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=YhkHEHvE--jKoOpCS5LkcLDMekfCX76VwubbXPoAiic,52317
+datachain/data_storage/metastore.py,sha256=9mWYOKK3AoHeKPGFm-WBfPrmnYHhwYeXx5MOueKTe7I,52657
 datachain/data_storage/schema.py,sha256=o3JbURKXRg3IJyIVA4QjHHkn6byRuz7avbydU2FlvNY,9897
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
-datachain/data_storage/sqlite.py,sha256=bGb4_kEFvnGf3ZWekiv8z3VMZBzQyO0bSaNB5RrpUUs,29991
+datachain/data_storage/sqlite.py,sha256=tT_soVi6l_pFSKaDktA1t4qW_vmPvXnvYSf4TZTKZYk,30067
 datachain/data_storage/warehouse.py,sha256=_7btARw-kd-Nx19S0qW6JqdF3VYyypQXFzsXq68SWKI,32327
 datachain/diff/__init__.py,sha256=-OFZzgOplqO84iWgGY7kfe60NXaWR9JRIh9T-uJboAM,9668
 datachain/fs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -85,7 +85,7 @@ datachain/lib/namespaces.py,sha256=it52UbbwB8dzhesO2pMs_nThXiPQ1Ph9sD9I3GQkg5s,2
 datachain/lib/projects.py,sha256=C-HTzTLUbIB735_iBSV6MjWnntV6gaKCEIkMSR1YEQw,2596
 datachain/lib/pytorch.py,sha256=oBBd6cxYrcwaFz7IQajKqhGqDdNnwUZWs0wJPRizrjk,7712
 datachain/lib/settings.py,sha256=9wi0FoHxRxNiyn99pR28IYsMkoo47jQxeXuObQr2Ar0,2929
-datachain/lib/signal_schema.py,sha256=Zhg8qThFDf9eoNWFH6KGeYB-sIGys7A_ybq2CUBG7Dg,36127
+datachain/lib/signal_schema.py,sha256=dVEqqrQQ_BS3yzU_49-Gari7IjVyMl1UT8h1WIsZabs,36489
 datachain/lib/tar.py,sha256=MLcVjzIgBqRuJacCNpZ6kwSZNq1i2tLyROc8PVprHsA,999
 datachain/lib/text.py,sha256=UNHm8fhidk7wdrWqacEWaA6I9ykfYqarQ2URby7jc7M,1261
 datachain/lib/udf.py,sha256=3uITkhO8IZnX49aePheObzd5ORYi2DIDYZVMQlBAJ-s,16687
@@ -103,14 +103,14 @@ 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=B6z8e33ZAUKbJ-cqQko-VJEtmia2bfUnuqH7BQQVt_A,85998
-datachain/lib/dc/datasets.py,sha256=xiVNe7PosuIsyACFhly9qNxGmRQy1J2TQw3AD6uj9UM,12747
+datachain/lib/dc/datachain.py,sha256=dFI7JX5-41HLgA-TUR99dtR1lvk2vokaMC3mbIW1XT4,85814
+datachain/lib/dc/datasets.py,sha256=H7s_4B68MMpRvLrK874QS8xSq1FeT1f6j7qPhnP2i64,12490
 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=eVBUP25W81dv46DLqkv8K0X7N3nxhoZm77gFrByeT_E,4660
 datachain/lib/dc/pandas.py,sha256=ObueUXDUFKJGu380GmazdG02ARpKAHPhSaymfmOH13E,1489
 datachain/lib/dc/parquet.py,sha256=zYcSgrWwyEDW9UxGUSVdIVsCu15IGEf0xL8KfWQqK94,1782
-datachain/lib/dc/records.py,sha256=AMtfWc7K6mtbW2OiaeIm3SjHTxDGnSgCEQW5u984Qh0,3111
+datachain/lib/dc/records.py,sha256=FpPbApWopUri1gIaSMsfXN4fevja4mjmfb6Q5eiaGxI,3116
 datachain/lib/dc/storage.py,sha256=8xiV3c6k-sG14RGwNJCp0AbV6L0mNDsTVZ-Est-ccnw,7672
 datachain/lib/dc/utils.py,sha256=VawOAlJSvAtZbsMg33s5tJe21TRx1Km3QggI1nN6tnw,3984
 datachain/lib/dc/values.py,sha256=7l1n352xWrEdql2NhBcZ3hj8xyPglWiY4qHjFPjn6iw,1428
@@ -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-0.22.0.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.22.0.dist-info/METADATA,sha256=xfdXuYjS-y5_IokpYEC7ZlmB6Wx1ouF7bh6K-TAacJI,13281
-datachain-0.22.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-datachain-0.22.0.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.22.0.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.22.0.dist-info/RECORD,,
+datachain-0.23.0.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.23.0.dist-info/METADATA,sha256=cS34xnVaaqHRes2oZ1uJnJVtDZ8L_jIBq6bXyTno8aI,13281
+datachain-0.23.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+datachain-0.23.0.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.23.0.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.23.0.dist-info/RECORD,,