fugue 0.9.0.dev3__py3-none-any.whl → 0.9.1__py3-none-any.whl

fugue/collections/sql.py

@@ -15,7 +15,7 @@ class TempTableName:
     """Generating a temporary, random and globaly unique table name"""
 
     def __init__(self):
-        self.key = "_" + str(uuid4())[:5]
+        self.key = "_" + str(uuid4())[:5].upper()
 
     def __repr__(self) -> str:
         return _TEMP_TABLE_EXPR_PREFIX + self.key + _TEMP_TABLE_EXPR_SUFFIX

fugue/dataframe/function_wrapper.py

@@ -20,6 +20,7 @@ from triad.collections.function_wrapper import (
     PositionalParam,
     function_wrapper,
 )
+from triad.utils.convert import compare_annotations
 from triad.utils.iter import EmptyAwareIterable, make_empty_aware
 
 from ..constants import FUGUE_ENTRYPOINT
@@ -37,6 +38,14 @@ from .iterable_dataframe import IterableDataFrame
 from .pandas_dataframe import PandasDataFrame
 
 
+def _compare_iter(tp: Any) -> Any:
+    return lambda x: compare_annotations(
+        x, Iterable[tp]  # type:ignore
+    ) or compare_annotations(
+        x, Iterator[tp]  # type:ignore
+    )
+
+
 @function_wrapper(FUGUE_ENTRYPOINT)
 class DataFrameFunctionWrapper(FunctionWrapper):
     @property
@@ -228,10 +237,7 @@ class _ListListParam(_LocalNoSchemaDataFrameParam):
         return len(df)
 
 
-@fugue_annotated_param(
-    Iterable[List[Any]],
-    matcher=lambda x: x == Iterable[List[Any]] or x == Iterator[List[Any]],
-)
+@fugue_annotated_param(Iterable[List[Any]], matcher=_compare_iter(List[Any]))
 class _IterableListParam(_LocalNoSchemaDataFrameParam):
     @no_type_check
     def to_input_data(self, df: DataFrame, ctx: Any) -> Iterable[List[Any]]:
@@ -288,10 +294,7 @@ class _ListDictParam(_LocalNoSchemaDataFrameParam):
         return len(df)
 
 
-@fugue_annotated_param(
-    Iterable[Dict[str, Any]],
-    matcher=lambda x: x == Iterable[Dict[str, Any]] or x == Iterator[Dict[str, Any]],
-)
+@fugue_annotated_param(Iterable[Dict[str, Any]], matcher=_compare_iter(Dict[str, Any]))
 class _IterableDictParam(_LocalNoSchemaDataFrameParam):
     @no_type_check
     def to_input_data(self, df: DataFrame, ctx: Any) -> Iterable[Dict[str, Any]]:
@@ -360,10 +363,7 @@ class _PandasParam(LocalDataFrameParam):
         return "pandas"
 
 
-@fugue_annotated_param(
-    Iterable[pd.DataFrame],
-    matcher=lambda x: x == Iterable[pd.DataFrame] or x == Iterator[pd.DataFrame],
-)
+@fugue_annotated_param(Iterable[pd.DataFrame], matcher=_compare_iter(pd.DataFrame))
 class _IterablePandasParam(LocalDataFrameParam):
     @no_type_check
     def to_input_data(self, df: DataFrame, ctx: Any) -> Iterable[pd.DataFrame]:
@@ -419,10 +419,7 @@ class _PyArrowTableParam(LocalDataFrameParam):
         return "pyarrow"
 
 
-@fugue_annotated_param(
-    Iterable[pa.Table],
-    matcher=lambda x: x == Iterable[pa.Table] or x == Iterator[pa.Table],
-)
+@fugue_annotated_param(Iterable[pa.Table], matcher=_compare_iter(pa.Table))
 class _IterableArrowParam(LocalDataFrameParam):
     @no_type_check
     def to_input_data(self, df: DataFrame, ctx: Any) -> Iterable[pa.Table]:

fugue/dataframe/utils.py

@@ -21,22 +21,6 @@ normalize_dataframe_column_names = normalize_column_names
 rename_dataframe_column_names = rename
 
 
-def _pa_type_eq(t1: pa.DataType, t2: pa.DataType) -> bool:
-    # should ignore the name difference of list
-    # e.g. list<item: string> == list<l: string>
-    if pa.types.is_list(t1) and pa.types.is_list(t2):  # pragma: no cover
-        return _pa_type_eq(t1.value_type, t2.value_type)
-    return t1 == t2
-
-
-def _schema_eq(s1: Schema, s2: Schema) -> bool:
-    if s1 == s2:
-        return True
-    return s1.names == s2.names and all(
-        _pa_type_eq(f1.type, f2.type) for f1, f2 in zip(s1.fields, s2.fields)
-    )
-
-
 def _df_eq(
     df: DataFrame,
     data: Any,
@@ -46,6 +30,7 @@ def _df_eq(
     check_schema: bool = True,
     check_content: bool = True,
     no_pandas: bool = False,
+    equal_type_groups: Optional[List[List[Any]]] = None,
     throw=False,
 ) -> bool:
     """Compare if two dataframes are equal. Is for internal, unit test
@@ -66,6 +51,7 @@ def _df_eq(
     :param no_pandas: if true, it will compare the string representations of the
       dataframes, otherwise, it will convert both to pandas dataframe to compare,
       defaults to False
+    :param equal_type_groups: the groups to treat as equal types, defaults to None.
     :param throw: if to throw error if not equal, defaults to False
     :return: if they equal
     """
@@ -78,8 +64,8 @@ def _df_eq(
         assert (
             df1.count() == df2.count()
         ), f"count mismatch {df1.count()}, {df2.count()}"
-        assert not check_schema or _schema_eq(
-            df.schema, df2.schema
+        assert not check_schema or df.schema.is_like(
+            df2.schema, equal_groups=equal_type_groups
         ), f"schema mismatch {df.schema.pa_schema}, {df2.schema.pa_schema}"
         if not check_content:
             return True

fugue/test/plugins.py

@@ -2,7 +2,7 @@ from contextlib import contextmanager
 from dataclasses import dataclass
 from pathlib import Path
 from typing import Any, Dict, Iterator, List, Optional, Tuple, Type
-
+from fugue.dataframe.utils import _df_eq
 from triad import assert_or_throw, run_once
 from triad.utils.entry_points import load_entry_point
 
@@ -160,6 +160,7 @@ class FugueTestSuite:
 
     backend: Any
     tmp_path: Path
+    equal_type_groups: Any = None
 
     __test__ = False
     _test_context: Any = None
@@ -180,6 +181,15 @@ class FugueTestSuite:
         """The engine object inside the ``FugueTestContext``"""
         return self.context.engine
 
+    def get_equal_type_groups(self) -> Optional[List[List[Any]]]:
+        return None  # pragma: no cover
+
+    def df_eq(self, *args: Any, **kwargs: Any) -> bool:
+        """A wrapper of :func:`~fugue.dataframe.utils.df_eq`"""
+        if "equal_type_groups" not in kwargs:
+            kwargs["equal_type_groups"] = self.equal_type_groups
+        return _df_eq(*args, **kwargs)
+
 
 def fugue_test_suite(backend: Any, mark_test: Optional[bool] = None) -> Any:
     def deco(cls: Type["FugueTestSuite"]) -> Type["FugueTestSuite"]:

{fugue-0.9.0.dev3.dist-info → fugue-0.9.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: fugue
-Version: 0.9.0.dev3
+Version: 0.9.1
 Summary: An abstraction layer for distributed computation
 Home-page: http://github.com/fugue-project/fugue
 Author: The Fugue Development Team
@@ -20,7 +20,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3 :: Only
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
-Requires-Dist: triad >=0.9.4
+Requires-Dist: triad >=0.9.7
 Requires-Dist: adagio >=0.2.4
 Provides-Extra: all
 Requires-Dist: qpd >=0.4.4 ; extra == 'all'
@@ -30,7 +30,7 @@ Requires-Dist: jinja2 ; extra == 'all'
 Requires-Dist: pyspark >=3.1.1 ; extra == 'all'
 Requires-Dist: dask[dataframe,distributed] >=2023.5.0 ; extra == 'all'
 Requires-Dist: dask-sql ; extra == 'all'
-Requires-Dist: ray[data] >=2.4.0 ; extra == 'all'
+Requires-Dist: ray[data] >=2.5.0 ; extra == 'all'
 Requires-Dist: notebook ; extra == 'all'
 Requires-Dist: jupyterlab ; extra == 'all'
 Requires-Dist: ipython >=7.10.0 ; extra == 'all'
@@ -45,6 +45,7 @@ Provides-Extra: dask
 Requires-Dist: dask[dataframe,distributed] >=2023.5.0 ; extra == 'dask'
 Requires-Dist: pyarrow >=7.0.0 ; extra == 'dask'
 Requires-Dist: pandas >=2.0.2 ; extra == 'dask'
+Requires-Dist: dask[dataframe,distributed] >=2024.4.0 ; (python_version >= "3.11.9") and extra == 'dask'
 Provides-Extra: duckdb
 Requires-Dist: qpd >=0.4.4 ; extra == 'duckdb'
 Requires-Dist: fugue-sql-antlr >=0.2.0 ; extra == 'duckdb'
@@ -58,6 +59,7 @@ Requires-Dist: fugue-sql-antlr >=0.2.0 ; extra == 'ibis'
 Requires-Dist: sqlglot ; extra == 'ibis'
 Requires-Dist: jinja2 ; extra == 'ibis'
 Requires-Dist: ibis-framework ; extra == 'ibis'
+Requires-Dist: pandas <2.2 ; extra == 'ibis'
 Provides-Extra: notebook
 Requires-Dist: notebook ; extra == 'notebook'
 Requires-Dist: jupyterlab ; extra == 'notebook'
@@ -65,9 +67,9 @@ Requires-Dist: ipython >=7.10.0 ; extra == 'notebook'
 Provides-Extra: polars
 Requires-Dist: polars ; extra == 'polars'
 Provides-Extra: ray
-Requires-Dist: ray[data] >=2.4.0 ; extra == 'ray'
+Requires-Dist: ray[data] >=2.5.0 ; extra == 'ray'
 Requires-Dist: duckdb >=0.5.0 ; extra == 'ray'
-Requires-Dist: pyarrow >=6.0.1 ; extra == 'ray'
+Requires-Dist: pyarrow >=7.0.0 ; extra == 'ray'
 Requires-Dist: pandas <2.2 ; extra == 'ray'
 Provides-Extra: spark
 Requires-Dist: pyspark >=3.1.1 ; extra == 'spark'

{fugue-0.9.0.dev3.dist-info → fugue-0.9.1.dist-info}/RECORD

@@ -18,7 +18,7 @@ fugue/bag/array_bag.py,sha256=b0UdDPmZpEAI3R0SBbZVOLVLAwMQnBCFeYDEpFWen14,1111
 fugue/bag/bag.py,sha256=sNBAzPmEh5fEm8ME8NEEOOre6l58ri6oouVBWwafqTc,3018
 fugue/collections/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 fugue/collections/partition.py,sha256=rPkU-3y6E598Q7wvE-jTSbSwWh3fzIVxdwPpbQvWS-M,17257
-fugue/collections/sql.py,sha256=mXxgOr_BAwPWb5DAd0PZuNtCWpMWxIFp8uulVikvlZ8,4947
+fugue/collections/sql.py,sha256=3MjnuQMPuUMq55n-EypikkRqcpOCZtOjp7S2fs7ujAA,4955
 fugue/collections/yielded.py,sha256=KAvCXAZpeuErGww7Y217_F7M2zv9G5hfdl2AWiO7wEM,2040
 fugue/column/__init__.py,sha256=aoZwwzyJtNL-duLxzU2sNGoaKikWd-yesbigE_Wj29s,208
 fugue/column/expressions.py,sha256=fdGX9oPCqJBuROFZqrOYVcwkjghdXT9ngaSTG5tW_i8,26544
@@ -31,10 +31,10 @@ fugue/dataframe/arrow_dataframe.py,sha256=r5zcZBX_N6XO5dmixBkTCPgLcMmgDF022piZvr
 fugue/dataframe/dataframe.py,sha256=xmyG85i14A6LDRkNmPt29oYq7PJsq668s1QvFHK8PV4,16964
 fugue/dataframe/dataframe_iterable_dataframe.py,sha256=lx71KfaI4lsVKI-79buc-idaeT20JEMBOq21SQcAiY8,7259
 fugue/dataframe/dataframes.py,sha256=tBSpHsENgbcdOJ0Jgst6PTKbjG7_uoFJch96oTlaQIs,4160
-fugue/dataframe/function_wrapper.py,sha256=V1eQMOn27UroEYT7_YiwoEF0RjZYIM0zkD3vfaMAQFs,14813
+fugue/dataframe/function_wrapper.py,sha256=hOZF3GmwpxqwqKi9-pEOAPZSW1ZFyB47hLxRrGyOiuM,14855
 fugue/dataframe/iterable_dataframe.py,sha256=TcOoNKa4jNbHbvAZ0XAhtMmGcioygIHPxI9budDtenQ,4758
 fugue/dataframe/pandas_dataframe.py,sha256=0L0wYCGhD2BpQbruoT07Ox9iQM5YLHLNrcgzudc-yKs,11633
-fugue/dataframe/utils.py,sha256=shN1eHYTnPhb38BHEpLlCdLSzX_qpoQ3-fsDgu1hCzQ,10840
+fugue/dataframe/utils.py,sha256=bA_otOJt9oju1yq5gtn21L_GDT_pUgNc6luYuBIhbUQ,10488
 fugue/dataset/__init__.py,sha256=5f2CAJ4xst6Z2o9Q2e2twfDOGUw8ZJoE2ild4JEU2pg,112
 fugue/dataset/api.py,sha256=DacI4L2w5NJ-eZ6nFxNMqmReEnb0WUXswbjVp7BeErk,2794
 fugue/dataset/dataset.py,sha256=jWXZqy3msMPFFkhas2PYJEX55ZAI3gk3Txq5f4-Qya4,4759
@@ -73,7 +73,7 @@ fugue/sql/api.py,sha256=l2I9CAy_W2oFFTct9fDPLyXF0LiDxQhMx5O8jBHTAxU,10050
 fugue/sql/workflow.py,sha256=S1pOhp0b0t6johFAJWmj6xUB7Ti5LQgNABpAzmLGjrQ,3010
 fugue/test/__init__.py,sha256=hvVrNbJYkWI_6otpILneyTjUafxURaA4obK6AoDyCUw,250
 fugue/test/pandas_tester.py,sha256=_w6rFqlzZKjBtmFf-08a4C97W5xtqGw5XorLhj6Zyoo,622
-fugue/test/plugins.py,sha256=VlVTAOiz2vnOI0G5CB408Bm77HMIcJS0gCQIh8Wb3b0,11866
+fugue/test/plugins.py,sha256=GLZia5GCmy0eBVGNbIqTbX7Ou3euf2SY4litKgdigwY,12318
 fugue/workflow/__init__.py,sha256=tXM_KYO8Q358W6qAVlwhIQIaYNRDgZtTubrIEX4QMgM,229
 fugue/workflow/_checkpoint.py,sha256=tt5Iv7c5ZStC0MD1inItksQ0GuK0ViniA3nvrgym-5c,5681
 fugue/workflow/_tasks.py,sha256=Zq_jXJO_VaF8DrWUuBiwO2Y3OVuhsiOQdzP4VBsp7Fo,11826
@@ -89,14 +89,14 @@ fugue_contrib/viz/__init__.py,sha256=osgZx63Br-yMZImyEfYf9MVzJNM2Cqqke_-WsuDmG5M
 fugue_contrib/viz/_ext.py,sha256=Lu_DlS5DcmrFz27fHcKTCkhKyknVWcfS5kzZVVuO9xM,1345
 fugue_dask/__init__.py,sha256=2CcJ0AsN-k_f7dZ-yAyYpaICfUMPfH3l0FvUJSBzTr0,161
 fugue_dask/_constants.py,sha256=35UmTVITk21GhRyRlbJOwPPdQsytM_p_2NytOXEay18,510
-fugue_dask/_io.py,sha256=HmL3Q2lRSptX1-GwiB3MN2VpjTRfmVKD8TDZkhS4x5c,5818
-fugue_dask/_utils.py,sha256=n70N3wPPMz13Jh0GWJM3Je-TCYpU36yGP_YCwIHqUrc,8908
+fugue_dask/_io.py,sha256=pl4F7mbVgP7Rwh1FFG7xfOz2TBZRUj1l3lLvDY4jOf4,6020
+fugue_dask/_utils.py,sha256=1uplEqvpCDZDp2YdwJxa6cuGScpgG9VvN3057J02bys,8956
 fugue_dask/dataframe.py,sha256=MuG9TqCND7qI66lPvxzuomfE7yA4sW7DjrvbyvE6XEU,13471
 fugue_dask/execution_engine.py,sha256=60IiwYRBVhN-pX3v6i9BZ8Pa4bcSh5UoklvCScM_XAM,21361
 fugue_dask/registry.py,sha256=jepWKH55VWNIWV3pOF5vpCl2OpO0rI1IULx5GM2Gk6w,2274
 fugue_dask/tester.py,sha256=E7BZjgFpJgrHsLMKzvSO5im5OwocYcratjzulJSQZl0,718
 fugue_duckdb/__init__.py,sha256=ZzhmAWbROR1YL9Kmlt7OlwkgPZzFhsSdwLV2pFmAqGI,268
-fugue_duckdb/_io.py,sha256=E35_GoD1uGuuAMOY4H8E2j-UazdAgTmLp4lLWqJrNsE,8437
+fugue_duckdb/_io.py,sha256=vnd8m8C6XeMCBJBbAdA5h695NMfsduQrvONyS0HcEFA,8475
 fugue_duckdb/_utils.py,sha256=ElKbHUyn5fWSPGXsK57iqMzcqKtCf0c8pBVBYGe5Ql4,5020
 fugue_duckdb/dask.py,sha256=agoLzeB7Swxj2kVWfmXFbWD1NS2lbbTlnrjSkR8kKWY,5014
 fugue_duckdb/dataframe.py,sha256=LRfTv7Y46wMM_IDYSP1R-5OXuHuBg8GHjPGFFt8u7l0,8444
@@ -107,7 +107,7 @@ fugue_ibis/__init__.py,sha256=z7TkK7M2_0p9XO6jQATNDgT0aHXn5k69Ttz2ga-eQG8,190
 fugue_ibis/_compat.py,sha256=zKdTaTfuC02eUIzZPkcd7oObnVBi_X5mQjQf7SDme3Y,246
 fugue_ibis/_utils.py,sha256=BUL5swA5FE4eQu0t5Z17hZVu9a2MFfxlFH6Ymy9xifg,6607
 fugue_ibis/dataframe.py,sha256=k4Q6qBLBIADF5YhbvaDplXO7OkMZSHuf_Wg5o-AusEI,7796
-fugue_ibis/execution_engine.py,sha256=cBU71BK6JuG_CAvPOZLhVetccwz1JAwX_x1iZ7SEgA4,18366
+fugue_ibis/execution_engine.py,sha256=5I-ou5xPdomVu-srdvidvP8f7wDYbGrCV_lGffZa_ac,18679
 fugue_notebook/__init__.py,sha256=9r_-2uxu1lBeZ8GgpYCKom_OZy2soIOYZajg7JDO-HY,4326
 fugue_notebook/env.py,sha256=TYiTxYPFi-BVJJY49jDsvw9mddhK8WrifeRxBke30I8,4773
 fugue_notebook/nbextension/README.md,sha256=QLnr957YeGfwzy2r4c4qbZPaXyCbyGrKPvcqSBQYSnU,123
@@ -119,15 +119,15 @@ fugue_polars/_utils.py,sha256=7rGGWgB1-VqFwh4PcBLYk_5VNjd8FNOS4TDFyDVz2sg,159
 fugue_polars/polars_dataframe.py,sha256=8LQ0IB-JFFdjW2ltDzq8DfIbUC_jjjDr1YM29usJag0,8831
 fugue_polars/registry.py,sha256=gd6qQ-OxYtTAQFyvYbLDPXmSvCR-LW6n5K5ylgMY_7A,2950
 fugue_ray/__init__.py,sha256=HzEHfG2mpc0ugf3nf1Pdy15Bhg35K6maZpYejn1aoyI,119
-fugue_ray/_constants.py,sha256=vu5l1w-Wi-2V_nm0HLXKOYhh5HdWRCc5yQktO2XzhOg,569
+fugue_ray/_constants.py,sha256=RHlaVKyjQnwdbo5mFO_GBtQZcz5GvWcCbkOkLfVTQ1A,565
 fugue_ray/dataframe.py,sha256=7asw2qf9vm6vLBSzqghm9pUcNAppJOz5CkT7XyR0S5g,12514
-fugue_ray/execution_engine.py,sha256=NT_mnacijp1zskFbtganUwA3JNRPU-FNNvJswA6U_Yg,12607
+fugue_ray/execution_engine.py,sha256=PZlWbmdCwTPfZJhN2I-44JW7so8NVCFFumaKIhJLfoI,12566
 fugue_ray/registry.py,sha256=TS-HWy2IUozp6_A0vqc8_ZdVUT_Z9yVjG6e1gbbgy2A,1757
 fugue_ray/tester.py,sha256=oTA_xOzvQhJU3ohc4hsVpZc0zv4bwJn1c8a9u8kcuIs,537
 fugue_ray/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 fugue_ray/_utils/cluster.py,sha256=3T3Gyra6lAHlzktta-Ro35j6YZQfH6fNrj2hC5ATF9k,621
-fugue_ray/_utils/dataframe.py,sha256=_EadzS4rPom1A_cF0pqoPlwrNYZTfTwcyyu86_fFsqU,4400
-fugue_ray/_utils/io.py,sha256=fj6aVt2qnFRGCm7SkHOd25KKXU3kd8yO18Z6y9Sib20,8862
+fugue_ray/_utils/dataframe.py,sha256=5c4duGV--mdLkKrbJRgjDWvVcp9BegA3yX16pmYDYLE,3954
+fugue_ray/_utils/io.py,sha256=3hFNDeBuh4bfCud40ZsGrGZLSvCSuxL_1VlqCTnn6RA,9794
 fugue_spark/__init__.py,sha256=rvrMpFs9socMgyH_58gLbnAqmirBf5oidXoO4cekW6U,165
 fugue_spark/_constants.py,sha256=K2uLQfjvMxXk75K-7_Wn47Alpwq5rW57BtECAUrOeqA,177
 fugue_spark/dataframe.py,sha256=lYa8FizM3p_lsKYFR49FazkVZMJKyi2LABKTpP5YBLo,12006
@@ -137,20 +137,20 @@ fugue_spark/tester.py,sha256=VX003yGNlBukaZTQSN-w7XvgSk4rqxrWQIzno0dWrXg,2481
 fugue_spark/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 fugue_spark/_utils/convert.py,sha256=eRWkDYA4UO-FQu-2y4O80WEdawx7X_rIrWg55AlOiRc,10007
 fugue_spark/_utils/io.py,sha256=OdUezKpB29Lx9aUS2k9x0xUAGZrmgMZyQYGPEeHk7rQ,5574
-fugue_spark/_utils/misc.py,sha256=o8dZmXOHnA7D_ps37vgGXTPTiSEG9LQzPKq7l-MG-qM,860
+fugue_spark/_utils/misc.py,sha256=9LsbBp6nOEhqXFLr8oWTc3VKzKk-vuVyixlRoquGnEs,858
 fugue_spark/_utils/partition.py,sha256=iaesyO5f4uXhj1W-p91cD5ecPiGlu0bzh8gl2ce2Uvg,3618
 fugue_sql/__init__.py,sha256=Cmr7w0Efr7PzoXdQzdJfc4Dgqd69qKqcHZZodENq7EU,287
 fugue_sql/exceptions.py,sha256=ltS0MC8gMnVVrJbQiOZ0kRUWvVQ2LTx33dCW3ugqtb0,260
 fugue_test/__init__.py,sha256=xoQuVobhU64uyODRdnzf6MSWe9lw5khkhpJ2atvADoc,2315
 fugue_test/bag_suite.py,sha256=WbDCFjuAHYoJh4GXSPiSJxOoOwE1VMtYpJ3lQrsUK-Y,2483
-fugue_test/builtin_suite.py,sha256=uE5cP8PBT-VLG0OXbdCj-gVu5VyDrq7if8tJb2fX2Pg,77940
-fugue_test/dataframe_suite.py,sha256=YhircCw7Le27rESYTWiRoS5rOpcnmNc83UFK7F2_HI4,19029
-fugue_test/execution_suite.py,sha256=RyDJeXjqXqPMaRtdetcKnIAAFl3bA8eOjx3mZm36AZI,47969
+fugue_test/builtin_suite.py,sha256=cOkZG6w1RHhWWxtjQhZClZQaGT6haNd576BoUmNC_cA,77960
+fugue_test/dataframe_suite.py,sha256=7ym4sshDUly6004cq1UlppqDVtbwxD6CKxR4Lu70i0s,18994
+fugue_test/execution_suite.py,sha256=jcSSoKqTGbeWzTxkyYU-8i2zJAjzuXn7BqE8ul-JjIc,48646
 fugue_test/fixtures.py,sha256=8Pev-mxRZOWwTFlsGjcSZ0iIs78zyWbp5tq4KG1wyvk,1432
-fugue_version/__init__.py,sha256=H9NWRZb7NbeRRPLP_V1fARmLNXranorVM-OOY-8_2ug,22
-fugue-0.9.0.dev3.dist-info/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
-fugue-0.9.0.dev3.dist-info/METADATA,sha256=giFBHER9khAwE2zSWd0YwgWzJpjXBezFrmQE4Jor8b0,18235
-fugue-0.9.0.dev3.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-fugue-0.9.0.dev3.dist-info/entry_points.txt,sha256=kiRuUkKOnnHFvlWpYSfVUZiXJW3hOez6gjYoOhGht3Q,302
-fugue-0.9.0.dev3.dist-info/top_level.txt,sha256=y1eCfzGdQ1_RkgcShcfbvXs-bopD3DwJcIOxP9EFXno,140
-fugue-0.9.0.dev3.dist-info/RECORD,,
+fugue_version/__init__.py,sha256=UwJXM8JY2T3tE2id0K2k_lEaVThbRTrGO1mNibyzIz8,22
+fugue-0.9.1.dist-info/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
+fugue-0.9.1.dist-info/METADATA,sha256=zu44QGPIwk28QyKe9H4Si2ANByy1sJ9cmauNrhCg4bc,18380
+fugue-0.9.1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+fugue-0.9.1.dist-info/entry_points.txt,sha256=kiRuUkKOnnHFvlWpYSfVUZiXJW3hOez6gjYoOhGht3Q,302
+fugue-0.9.1.dist-info/top_level.txt,sha256=y1eCfzGdQ1_RkgcShcfbvXs-bopD3DwJcIOxP9EFXno,140
+fugue-0.9.1.dist-info/RECORD,,

{fugue-0.9.0.dev3.dist-info → fugue-0.9.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.42.0)
+Generator: bdist_wheel (0.43.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

fugue_dask/_io.py

@@ -6,7 +6,7 @@ from fsspec import AbstractFileSystem
 from triad.collections.dict import ParamDict
 from triad.collections.schema import Schema
 from triad.utils.assertion import assert_or_throw
-from triad.utils.io import join, makedirs, url_to_fs
+from triad.utils.io import isfile, join, makedirs, url_to_fs
 
 from fugue._utils.io import FileParser, _get_single_files
 from fugue_dask.dataframe import DaskDataFrame
@@ -100,9 +100,11 @@ def _save_csv(df: DaskDataFrame, p: FileParser, **kwargs: Any) -> None:
 
 
 def _safe_load_csv(path: str, **kwargs: Any) -> dd.DataFrame:
+    if not isfile(path):
+        return dd.read_csv(join(path, "*.csv"), **kwargs)
     try:
         return dd.read_csv(path, **kwargs)
-    except (IsADirectoryError, PermissionError):
+    except (IsADirectoryError, PermissionError):  # pragma: no cover
         return dd.read_csv(join(path, "*.csv"), **kwargs)
 
 
@@ -148,11 +150,12 @@ def _save_json(df: DaskDataFrame, p: FileParser, **kwargs: Any) -> None:
 
 
 def _safe_load_json(path: str, **kwargs: Any) -> dd.DataFrame:
+    if not isfile(path):
+        return dd.read_json(join(path, "*.json"), **kwargs)
     try:
         return dd.read_json(path, **kwargs)
-    except (IsADirectoryError, PermissionError):
-        x = dd.read_json(join(path, "*.json"), **kwargs)
-        return x
+    except (IsADirectoryError, PermissionError):  # pragma: no cover
+        return dd.read_json(join(path, "*.json"), **kwargs)
 
 
 def _load_json(

fugue_dask/_utils.py

@@ -53,7 +53,7 @@ def hash_repartition(df: dd.DataFrame, num: int, cols: List[Any]) -> dd.DataFram
     if num < 1:
         return df
     if num == 1:
-        return df.repartition(1)
+        return df.repartition(npartitions=1)
     df = df.reset_index(drop=True).clear_divisions()
     idf, ct = _add_hash_index(df, num, cols)
     return _postprocess(idf, ct, num)
@@ -76,7 +76,7 @@ def even_repartition(df: dd.DataFrame, num: int, cols: List[Any]) -> dd.DataFram
         the number of partitions will be the number of groups.
     """
     if num == 1:
-        return df.repartition(1)
+        return df.repartition(npartitions=1)
     if len(cols) == 0 and num <= 0:
         return df
     df = df.reset_index(drop=True).clear_divisions()
@@ -111,7 +111,7 @@ def rand_repartition(
     if num < 1:
         return df
     if num == 1:
-        return df.repartition(1)
+        return df.repartition(npartitions=1)
     df = df.reset_index(drop=True).clear_divisions()
     if len(cols) == 0:
         idf, ct = _add_random_index(df, num=num, seed=seed)
@@ -124,7 +124,7 @@ def rand_repartition(
 def _postprocess(idf: dd.DataFrame, ct: int, num: int) -> dd.DataFrame:
     parts = min(ct, num)
     if parts <= 1:
-        return idf.repartition(1)
+        return idf.repartition(npartitions=1)
     divisions = list(np.arange(ct, step=math.ceil(ct / parts)))
     divisions.append(ct - 1)
     return idf.repartition(divisions=divisions, force=True)

fugue_duckdb/_io.py

@@ -140,6 +140,7 @@ class DuckDBIO:
         else:
             if header:
                 kw["ALL_VARCHAR"] = 1
+                kw["auto_detect"] = 1
                 if columns is None:
                     cols = "*"
                 elif isinstance(columns, list):

fugue_ibis/execution_engine.py

@@ -23,8 +23,8 @@ from ._compat import IbisTable
 from ._utils import to_ibis_schema
 from .dataframe import IbisDataFrame
 
-_JOIN_RIGHT_SUFFIX = "_ibis_y__"
-_GEN_TABLE_NAMES = (f"_fugue_temp_table_{i:d}" for i in itertools.count())
+_JOIN_RIGHT_SUFFIX = "_ibis_y__".upper()
+_GEN_TABLE_NAMES = (f"_fugue_temp_table_{i:d}".upper() for i in itertools.count())
 
 
 class IbisSQLEngine(SQLEngine):
@@ -224,7 +224,7 @@ class IbisSQLEngine(SQLEngine):
             _presort = parse_presort_exp(presort)
         else:
             _presort = partition_spec.presort
-        tbn = "_temp"
+        tbn = "_TEMP"
         idf = self.to_df(df)
 
         if len(_presort) == 0:
@@ -233,9 +233,10 @@ class IbisSQLEngine(SQLEngine):
             pcols = ", ".join(
                 self.encode_column_name(x) for x in partition_spec.partition_by
             )
+            dummy_order_by = self._dummy_window_order_by()
             sql = (
                 f"SELECT * FROM ("
-                f"SELECT *, ROW_NUMBER() OVER (PARTITION BY {pcols}) "
+                f"SELECT *, ROW_NUMBER() OVER (PARTITION BY {pcols} {dummy_order_by}) "
                 f"AS __fugue_take_param FROM {tbn}"
                 f") WHERE __fugue_take_param<={n}"
             )
@@ -290,6 +291,12 @@ class IbisSQLEngine(SQLEngine):
     def load_table(self, table: str, **kwargs: Any) -> DataFrame:
         return self.to_df(self.backend.table(table))
 
+    def _dummy_window_order_by(self) -> str:
+        """Return a dummy window order by clause, this is required for
+        some SQL backends when there is no real order by clause in window
+        """
+        return ""
+
 
 class IbisMapEngine(MapEngine):
     """IbisExecutionEngine's MapEngine, it is a wrapper of the map engine

fugue_ray/_constants.py

@@ -1,6 +1,7 @@
 from typing import Any, Dict
 
 import ray
+from packaging import version
 
 FUGUE_RAY_CONF_SHUFFLE_PARTITIONS = "fugue.ray.shuffle.partitions"
 FUGUE_RAY_DEFAULT_PARTITIONS = "fugue.ray.default.partitions"
@@ -12,8 +13,6 @@ FUGUE_RAY_DEFAULT_CONF: Dict[str, Any] = {
     FUGUE_RAY_DEFAULT_PARTITIONS: 0,
     FUGUE_RAY_ZERO_COPY: True,
 }
+RAY_VERSION = version.parse(ray.__version__)
 
-if ray.__version__ >= "2.3":
-    _ZERO_COPY: Dict[str, Any] = {"zero_copy_batch": True}
-else:  # pragma: no cover
-    _ZERO_COPY = {}
+_ZERO_COPY: Dict[str, Any] = {"zero_copy_batch": True}

fugue_ray/_utils/dataframe.py

@@ -3,7 +3,6 @@ from typing import Any, Dict, List, Optional, Tuple
 
 import pandas as pd
 import pyarrow as pa
-import ray
 import ray.data as rd
 from triad import Schema
 
@@ -31,31 +30,21 @@ def get_dataset_format(df: rd.Dataset) -> Tuple[Optional[str], rd.Dataset]:
     df = materialize(df)
     if df.count() == 0:
         return None, df
-    if ray.__version__ < "2.5.0":  # pragma: no cover
-        if hasattr(df, "_dataset_format"):  # pragma: no cover
-            return df._dataset_format(), df  # ray<2.2
-        ctx = rd.context.DatasetContext.get_current()
-        ctx.use_streaming_executor = False
-        return df.dataset_format(), df  # ray>=2.2
-    else:
-        schema = df.schema(fetch_if_missing=True)
-        if schema is None:  # pragma: no cover
-            return None, df
-        if isinstance(schema.base_schema, pa.Schema):
-            return "arrow", df
-        return "pandas", df
+    schema = df.schema(fetch_if_missing=True)
+    if schema is None:  # pragma: no cover
+        return None, df
+    if isinstance(schema.base_schema, pa.Schema):
+        return "arrow", df
+    return "pandas", df
 
 
 def to_schema(schema: Any) -> Schema:  # pragma: no cover
     if isinstance(schema, pa.Schema):
         return Schema(schema)
-    if ray.__version__ >= "2.5.0":
-        if isinstance(schema, rd.Schema):
-            if hasattr(schema, "base_schema") and isinstance(
-                schema.base_schema, pa.Schema
-            ):
-                return Schema(schema.base_schema)
-            return Schema(list(zip(schema.names, schema.types)))
+    if isinstance(schema, rd.Schema):
+        if hasattr(schema, "base_schema") and isinstance(schema.base_schema, pa.Schema):
+            return Schema(schema.base_schema)
+        return Schema(list(zip(schema.names, schema.types)))
     raise ValueError(f"{schema} is not supported")
 
 

fugue_ray/_utils/io.py

@@ -3,15 +3,15 @@ import pathlib
 from typing import Any, Callable, Dict, Iterable, List, Optional, Union
 
 import pyarrow as pa
-import ray
 import ray.data as rd
+from packaging import version
 from pyarrow import csv as pacsv
 from pyarrow import json as pajson
 from ray.data.datasource import FileExtensionFilter
 from triad.collections import Schema
 from triad.collections.dict import ParamDict
 from triad.utils.assertion import assert_or_throw
-from triad.utils.io import exists, makedirs, rm
+from triad.utils.io import exists, makedirs, rm, isfile
 
 from fugue import ExecutionEngine
 from fugue._utils.io import FileParser, save_df
@@ -19,6 +19,8 @@ from fugue.collections.partition import PartitionSpec
 from fugue.dataframe import DataFrame
 from fugue_ray.dataframe import RayDataFrame
 
+from .._constants import RAY_VERSION
+
 
 class RayIO(object):
     def __init__(self, engine: ExecutionEngine):
@@ -149,6 +151,18 @@ class RayIO(object):
         if infer_schema and columns is not None and not isinstance(columns, list):
             raise ValueError("can't set columns as a schema when infer schema is true")
 
+        if RAY_VERSION >= version.parse("2.10"):
+            if len(p) == 1 and isfile(p[0]):  # TODO: very hacky
+                params: Dict[str, Any] = {}
+            else:
+                params = {"file_extensions": ["csv"]}
+        else:  # pragma: no cover
+            params = {
+                "partition_filter": _FileFiler(
+                    file_extensions=["csv"], exclude=["_SUCCESS"]
+                ),
+            }
+
         def _read_csv(to_str: bool) -> RayDataFrame:
             res = rd.read_csv(
                 p,
@@ -156,9 +170,7 @@ class RayIO(object):
                 read_options=pacsv.ReadOptions(**read_options),
                 parse_options=pacsv.ParseOptions(**parse_options),
                 convert_options=pacsv.ConvertOptions(**convert_options),
-                partition_filter=_FileFiler(
-                    file_extensions=["csv"], exclude=["_SUCCESS"]
-                ),
+                **params,
             )
             if to_str:
                 _schema = res.schema(fetch_if_missing=True)
@@ -196,20 +208,31 @@ class RayIO(object):
         read_options: Dict[str, Any] = {"use_threads": False}
         parse_options: Dict[str, Any] = {}
 
-        def _read_json() -> RayDataFrame:
-            if ray.__version__ >= "2.9":
-                params: Dict[str, Any] = {"file_extensions": None}
+        def _read_json() -> RayDataFrame:  # pragma: no cover
+            if RAY_VERSION >= version.parse("2.10"):
+                if len(p) == 1 and isfile(p[0]):  # TODO: very hacky
+                    params: Dict[str, Any] = {"file_extensions": None}
+                else:
+                    params = {"file_extensions": ["json"]}
+            elif RAY_VERSION >= version.parse("2.9"):  # pragma: no cover
+                params = {
+                    "file_extensions": None,
+                    "partition_filter": _FileFiler(
+                        file_extensions=["json"], exclude=["_SUCCESS"]
+                    ),
+                }
             else:  # pragma: no cover
-                params = {}
+                params = {
+                    "partition_filter": _FileFiler(
+                        file_extensions=["json"], exclude=["_SUCCESS"]
+                    ),
+                }
             return RayDataFrame(
                 rd.read_json(
                     p,
                     ray_remote_args=self._remote_args(),
                     read_options=pajson.ReadOptions(**read_options),
                     parse_options=pajson.ParseOptions(**parse_options),
-                    partition_filter=_FileFiler(
-                        file_extensions=["json"], exclude=["_SUCCESS"]
-                    ),
                     **params,
                 )
             )
@@ -227,7 +250,7 @@ class RayIO(object):
         return {"num_cpus": 1}
 
 
-class _FileFiler(FileExtensionFilter):
+class _FileFiler(FileExtensionFilter):  # pragma: no cover
     def __init__(self, file_extensions: Union[str, List[str]], exclude: Iterable[str]):
         super().__init__(file_extensions, allow_if_no_extension=True)
         self._exclude = set(exclude)

fugue_ray/execution_engine.py

@@ -191,8 +191,7 @@ class RayMapEngine(MapEngine):
             mb_args["batch_size"] = self.conf.get_or_throw(
                 FUGUE_RAY_DEFAULT_BATCH_SIZE, int
             )
-        if ray.__version__ >= "2.3":
-            mb_args["zero_copy_batch"] = self.conf.get(FUGUE_RAY_ZERO_COPY, True)
+        mb_args["zero_copy_batch"] = self.conf.get(FUGUE_RAY_ZERO_COPY, True)
         sdf = rdf.native.map_batches(
             _udf,
             batch_format="pyarrow",

fugue_spark/_utils/misc.py

@@ -3,7 +3,7 @@ from typing import Any
 try:
     from pyspark.sql.connect.session import SparkSession as SparkConnectSession
     from pyspark.sql.connect.dataframe import DataFrame as SparkConnectDataFrame
-except ImportError:  # pragma: no cover
+except Exception:  # pragma: no cover
     SparkConnectSession = None
     SparkConnectDataFrame = None
 import pyspark.sql as ps