datachain 0.30.5__py3-none-any.whl → 0.30.6__py3-none-any.whl

datachain/cli/commands/datasets.py

@@ -1,30 +1,41 @@
 import sys
-from typing import TYPE_CHECKING, Optional
+from collections.abc import Iterable, Iterator
+from typing import TYPE_CHECKING, Optional, Union
 
 from tabulate import tabulate
 
-if TYPE_CHECKING:
-    from datachain.catalog import Catalog
-
+from datachain import semver
 from datachain.catalog import is_namespace_local
 from datachain.cli.utils import determine_flavors
 from datachain.config import Config
 from datachain.error import DataChainError, DatasetNotFoundError
 from datachain.studio import list_datasets as list_datasets_studio
 
+if TYPE_CHECKING:
+    from datachain.catalog import Catalog
+
+
+def group_dataset_versions(
+    datasets: Iterable[tuple[str, str]], latest_only=True
+) -> dict[str, Union[str, list[str]]]:
+    grouped: dict[str, list[tuple[int, int, int]]] = {}
 
-def group_dataset_versions(datasets, latest_only=True):
-    grouped = {}
     # Sort to ensure groupby works as expected
     # (groupby expects consecutive items with the same key)
     for name, version in sorted(datasets):
-        grouped.setdefault(name, []).append(version)
+        grouped.setdefault(name, []).append(semver.parse(version))
 
     if latest_only:
         # For each dataset name, pick the highest version.
-        return {name: max(versions) for name, versions in grouped.items()}
+        return {
+            name: semver.create(*(max(versions))) for name, versions in grouped.items()
+        }
+
     # For each dataset name, return a sorted list of unique versions.
-    return {name: sorted(set(versions)) for name, versions in grouped.items()}
+    return {
+        name: [semver.create(*v) for v in sorted(set(versions))]
+        for name, versions in grouped.items()
+    }
 
 
 def list_datasets(
@@ -35,7 +46,7 @@ def list_datasets(
     team: Optional[str] = None,
     latest_only: bool = True,
     name: Optional[str] = None,
-):
+) -> None:
     token = Config().read().get("studio", {}).get("token")
     all, local, studio = determine_flavors(studio, local, all, token)
     if name:
@@ -95,27 +106,31 @@ def list_datasets(
     print(tabulate(rows, headers="keys"))
 
 
-def list_datasets_local(catalog: "Catalog", name: Optional[str] = None):
+def list_datasets_local(
+    catalog: "Catalog", name: Optional[str] = None
+) -> Iterator[tuple[str, str]]:
     if name:
         yield from list_datasets_local_versions(catalog, name)
         return
 
     for d in catalog.ls_datasets():
         for v in d.versions:
-            yield (d.full_name, v.version)
+            yield d.full_name, v.version
 
 
-def list_datasets_local_versions(catalog: "Catalog", name: str):
+def list_datasets_local_versions(
+    catalog: "Catalog", name: str
+) -> Iterator[tuple[str, str]]:
     namespace_name, project_name, name = catalog.get_full_dataset_name(name)
 
     ds = catalog.get_dataset(
         name, namespace_name=namespace_name, project_name=project_name
     )
     for v in ds.versions:
-        yield (name, v.version)
+        yield name, v.version
 
 
-def _datasets_tabulate_row(name, both, local_version, studio_version):
+def _datasets_tabulate_row(name, both, local_version, studio_version) -> dict[str, str]:
     row = {
         "Name": name,
     }
@@ -136,7 +151,7 @@ def rm_dataset(
     force: Optional[bool] = False,
     studio: Optional[bool] = False,
     team: Optional[str] = None,
-):
+) -> None:
     namespace_name, project_name, name = catalog.get_full_dataset_name(name)
 
     if studio:
@@ -166,7 +181,7 @@ def edit_dataset(
     description: Optional[str] = None,
     attrs: Optional[list[str]] = None,
     team: Optional[str] = None,
-):
+) -> None:
     from datachain.lib.dc.utils import is_studio
 
     namespace_name, project_name, name = catalog.get_full_dataset_name(name)

datachain/delta.py

@@ -4,7 +4,7 @@ from functools import wraps
 from typing import TYPE_CHECKING, Callable, Optional, TypeVar, Union
 
 import datachain
-from datachain.dataset import DatasetDependency
+from datachain.dataset import DatasetDependency, DatasetRecord
 from datachain.error import DatasetNotFoundError
 from datachain.project import Project
 
@@ -30,9 +30,10 @@ def delta_disabled(
 
     @wraps(method)
     def _inner(self: T, *args: "P.args", **kwargs: "P.kwargs") -> T:
-        if self.delta:
+        if self.delta and not self._delta_unsafe:
             raise NotImplementedError(
-                f"Delta update cannot be used with {method.__name__}"
+                f"Cannot use {method.__name__} with delta datasets - may cause"
+                " inconsistency. Use delta_unsafe flag to allow this operation."
             )
         return method(self, *args, **kwargs)
 
@@ -124,10 +125,19 @@ def _get_retry_chain(
     # Subtract also diff chain since some items might be picked
     # up by `delta=True` itself (e.g. records got modified AND are missing in the
     # result dataset atm)
-    return retry_chain.subtract(diff_chain, on=on) if retry_chain else None
+    on = [on] if isinstance(on, str) else on
+
+    return (
+        retry_chain.diff(
+            diff_chain, on=on, added=True, same=True, modified=False, deleted=False
+        ).distinct(*on)
+        if retry_chain
+        else None
+    )
 
 
 def _get_source_info(
+    source_ds: DatasetRecord,
     name: str,
     namespace_name: str,
     project_name: str,
@@ -154,25 +164,23 @@ def _get_source_info(
         indirect=False,
     )
 
-    dep = dependencies[0]
-    if not dep:
+    source_ds_dep = next((d for d in dependencies if d.name == source_ds.name), None)
+    if not source_ds_dep:
         # Starting dataset was removed, back off to normal dataset creation
         return None, None, None, None, None
 
-    source_ds_project = catalog.metastore.get_project(dep.project, dep.namespace)
-    source_ds_name = dep.name
-    source_ds_version = dep.version
-    source_ds_latest_version = catalog.get_dataset(
-        source_ds_name,
-        namespace_name=source_ds_project.namespace.name,
-        project_name=source_ds_project.name,
-    ).latest_version
+    # Refresh starting dataset to have new versions if they are created
+    source_ds = catalog.get_dataset(
+        source_ds.name,
+        namespace_name=source_ds.project.namespace.name,
+        project_name=source_ds.project.name,
+    )
 
     return (
-        source_ds_name,
-        source_ds_project,
-        source_ds_version,
-        source_ds_latest_version,
+        source_ds.name,
+        source_ds.project,
+        source_ds_dep.version,
+        source_ds.latest_version,
         dependencies,
     )
 
@@ -244,7 +252,14 @@ def delta_retry_update(
         source_ds_version,
         source_ds_latest_version,
         dependencies,
-    ) = _get_source_info(name, namespace_name, project_name, latest_version, catalog)
+    ) = _get_source_info(
+        dc._query.starting_step.dataset,  # type: ignore[union-attr]
+        name,
+        namespace_name,
+        project_name,
+        latest_version,
+        catalog,
+    )
 
     # If source_ds_name is None, starting dataset was removed
     if source_ds_name is None:
@@ -267,8 +282,9 @@ def delta_retry_update(
     if dependencies:
         dependencies = copy(dependencies)
         dependencies = [d for d in dependencies if d is not None]
+        source_ds_dep = next(d for d in dependencies if d.name == source_ds_name)
         # Update to latest version
-        dependencies[0].version = source_ds_latest_version  # type: ignore[union-attr]
+        source_ds_dep.version = source_ds_latest_version  # type: ignore[union-attr]
 
     # Handle retry functionality if enabled
     if delta_retry:

datachain/lib/dc/datachain.py

@@ -193,6 +193,7 @@ class DataChain:
         self._setup: dict = setup or {}
         self._sys = _sys
         self._delta = False
+        self._delta_unsafe = False
         self._delta_on: Optional[Union[str, Sequence[str]]] = None
         self._delta_result_on: Optional[Union[str, Sequence[str]]] = None
         self._delta_compare: Optional[Union[str, Sequence[str]]] = None
@@ -216,6 +217,7 @@ class DataChain:
         right_on: Optional[Union[str, Sequence[str]]] = None,
         compare: Optional[Union[str, Sequence[str]]] = None,
         delta_retry: Optional[Union[bool, str]] = None,
+        delta_unsafe: bool = False,
     ) -> "Self":
         """Marks this chain as delta, which means special delta process will be
         called on saving dataset for optimization"""
@@ -226,6 +228,7 @@ class DataChain:
         self._delta_result_on = right_on
         self._delta_compare = compare
         self._delta_retry = delta_retry
+        self._delta_unsafe = delta_unsafe
         return self
 
     @property
@@ -238,6 +241,10 @@ class DataChain:
         """Returns True if this chain is ran in "delta" update mode"""
         return self._delta
 
+    @property
+    def delta_unsafe(self) -> bool:
+        return self._delta_unsafe
+
     @property
     def schema(self) -> dict[str, DataType]:
         """Get schema of the chain."""
@@ -328,6 +335,7 @@ class DataChain:
                 right_on=self._delta_result_on,
                 compare=self._delta_compare,
                 delta_retry=self._delta_retry,
+                delta_unsafe=self._delta_unsafe,
             )
 
         return chain

datachain/lib/dc/datasets.py

@@ -40,6 +40,7 @@ def read_dataset(
     delta_result_on: Optional[Union[str, Sequence[str]]] = None,
     delta_compare: Optional[Union[str, Sequence[str]]] = None,
     delta_retry: Optional[Union[bool, str]] = None,
+    delta_unsafe: bool = False,
     update: bool = False,
 ) -> "DataChain":
     """Get data from a saved Dataset. It returns the chain itself.
@@ -80,6 +81,8 @@ def read_dataset(
         update: If True always checks for newer versions available on Studio, even if
             some version of the dataset exists locally already. If False (default), it
             will only fetch the dataset from Studio if it is not found locally.
+        delta_unsafe: Allow restricted ops in delta: merge, agg, union, group_by,
+            distinct.
 
 
     Example:
@@ -205,6 +208,7 @@ def read_dataset(
             right_on=delta_result_on,
             compare=delta_compare,
             delta_retry=delta_retry,
+            delta_unsafe=delta_unsafe,
         )
 
     return chain

datachain/lib/dc/storage.py

@@ -43,6 +43,7 @@ def read_storage(
     delta_result_on: Optional[Union[str, Sequence[str]]] = None,
     delta_compare: Optional[Union[str, Sequence[str]]] = None,
     delta_retry: Optional[Union[bool, str]] = None,
+    delta_unsafe: bool = False,
     client_config: Optional[dict] = None,
 ) -> "DataChain":
     """Get data from storage(s) as a list of file with all file attributes.
@@ -77,6 +78,9 @@ def read_storage(
               (error mode)
             - True: Reprocess records missing from the result dataset (missing mode)
             - None: No retry processing (default)
+        delta_unsafe: Allow restricted ops in delta: merge, agg, union, group_by,
+            distinct. Caller must ensure datasets are consistent and not partially
+            updated.
 
     Returns:
         DataChain: A DataChain object containing the file information.
@@ -218,6 +222,7 @@ def read_storage(
             right_on=delta_result_on,
             compare=delta_compare,
             delta_retry=delta_retry,
+            delta_unsafe=delta_unsafe,
         )
 
     return storage_chain

{datachain-0.30.5.dist-info → datachain-0.30.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.30.5
+Version: 0.30.6
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0

{datachain-0.30.5.dist-info → datachain-0.30.6.dist-info}/RECORD

@@ -4,7 +4,7 @@ datachain/asyn.py,sha256=RH_jFwJcTXxhEFomaI9yL6S3Onau6NZ6FSKfKFGtrJE,9689
 datachain/cache.py,sha256=ESVRaCJXEThMIfGEFVHx6wJPOZA7FYk9V6WxjyuqUBY,3626
 datachain/config.py,sha256=g8qbNV0vW2VEKpX-dGZ9pAn0DAz6G2ZFcr7SAV3PoSM,4272
 datachain/dataset.py,sha256=ATGa-CBTFoZeTN2V40-zHEzfMBcdYK0WuoJ6H2yEAvo,25268
-datachain/delta.py,sha256=dghGvD44LcglvL5-kUOIKk75ywBO0U7eikA3twKZC28,10202
+datachain/delta.py,sha256=X5Lw6GQ8MAYNl2YIExNvl0tPIkylQEWwnCw0We7NtHM,10693
 datachain/error.py,sha256=OWwWMkzZYJrkcoEDGhJHMf7SfKvxcsOLRF94mjPf29I,1609
 datachain/job.py,sha256=x5PB6d5sqx00hePNNkirESlOVAvnmkEM5ygUgQmAhsk,1262
 datachain/listing.py,sha256=aqayl5St3D9PwdwM6nR1STkpLSw-S3U8pudO9PWi3N8,7241
@@ -27,7 +27,7 @@ datachain/catalog/loader.py,sha256=53VnuSRkt_CO9RdlHWkzQsPF55qMxcXvEm3ecsZREw8,6
 datachain/cli/__init__.py,sha256=so3WxEQF03KdGvjav15Sw7a6-lriiE24uDSGbBDBp8o,8298
 datachain/cli/utils.py,sha256=wrLnAh7Wx8O_ojZE8AE4Lxn5WoxHbOj7as8NWlLAA74,3036
 datachain/cli/commands/__init__.py,sha256=zp3bYIioO60x_X04A4-IpZqSYVnpwOa1AdERQaRlIhI,493
-datachain/cli/commands/datasets.py,sha256=Q2zYbiWXYPjg6e_YHyUKaYRg1L6-lxv0L214bogwsUY,6565
+datachain/cli/commands/datasets.py,sha256=DAbONwcA__JM1qkcKVOP5sKukGbCGqLWCMBkBscA3_s,6971
 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
@@ -104,15 +104,15 @@ datachain/lib/convert/values_to_tuples.py,sha256=j5yZMrVUH6W7b-7yUvdCTGI7JCUAYUO
 datachain/lib/dc/__init__.py,sha256=UrUzmDH6YyVl8fxM5iXTSFtl5DZTUzEYm1MaazK4vdQ,900
 datachain/lib/dc/csv.py,sha256=q6a9BpapGwP6nwy6c5cklxQumep2fUp9l2LAjtTJr6s,4411
 datachain/lib/dc/database.py,sha256=F6EOjPKwSdp26kJsOKGq49D9OxqyKEalINHEwLQav2s,14716
-datachain/lib/dc/datachain.py,sha256=cJ0lbFteO5ync08M1QbriRrSAATOmU-nDkbxSH6SYgA,99462
-datachain/lib/dc/datasets.py,sha256=HKQXnCpIGFsYQ9ociLAUm8cwg2H0GaUmgWCF4FkKpbk,15180
+datachain/lib/dc/datachain.py,sha256=2UtDhtBzx5VejkDE0UTS3t1517jCGr7YEKvO5wqNU-Q,99709
+datachain/lib/dc/datasets.py,sha256=-Bvyyu4XXDXLiWa-bOnsp0Q11RSYXRO0j5DaX8ShaFs,15355
 datachain/lib/dc/hf.py,sha256=AP_MUHg6HJWae10PN9hD_beQVjrl0cleZ6Cvhtl1yoI,2901
 datachain/lib/dc/json.py,sha256=dNijfJ-H92vU3soyR7X1IiDrWhm6yZIGG3bSnZkPdAE,2733
 datachain/lib/dc/listings.py,sha256=V379Cb-7ZyquM0w7sWArQZkzInZy4GB7QQ1ZfowKzQY,4544
 datachain/lib/dc/pandas.py,sha256=ObueUXDUFKJGu380GmazdG02ARpKAHPhSaymfmOH13E,1489
 datachain/lib/dc/parquet.py,sha256=zYcSgrWwyEDW9UxGUSVdIVsCu15IGEf0xL8KfWQqK94,1782
 datachain/lib/dc/records.py,sha256=4N1Fq-j5r4GK-PR5jIO-9B2u_zTNX9l-6SmcRhQDAsw,3136
-datachain/lib/dc/storage.py,sha256=FXroEdxOZfbuEBIWfWTkbGwrI0D4_mrLZSRsIQm0WFE,7693
+datachain/lib/dc/storage.py,sha256=OMJE-9ob9Ku5le8W6O8J1W-XJ0pwHt2PsO-ZCcee1ZA,7950
 datachain/lib/dc/utils.py,sha256=9OMiFu2kXIbtMqzJTEr1qbCoCBGpOmTnkWImVgFTKgo,4112
 datachain/lib/dc/values.py,sha256=7l1n352xWrEdql2NhBcZ3hj8xyPglWiY4qHjFPjn6iw,1428
 datachain/model/__init__.py,sha256=R9faX5OHV1xh2EW-g2MPedwbtEqt3LodJRyluB-QylI,189
@@ -160,9 +160,9 @@ 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-0.30.5.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.30.5.dist-info/METADATA,sha256=90OhCbSbqZn245Dm4-9zgbyBxI6N2NF8jsIdEiw6PUs,13898
-datachain-0.30.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-datachain-0.30.5.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.30.5.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.30.5.dist-info/RECORD,,
+datachain-0.30.6.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.30.6.dist-info/METADATA,sha256=ZyXo8wdTrN08k--Soy3UHpCu_Jni_6ocO3_PbjCswCE,13898
+datachain-0.30.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+datachain-0.30.6.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.30.6.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.30.6.dist-info/RECORD,,