fugue 0.9.7.dev1__tar.gz → 0.9.7.dev2__tar.gz

{fugue-0.9.7.dev1 → fugue-0.9.7.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fugue
-Version: 0.9.7.dev1
+Version: 0.9.7.dev2
 Summary: An abstraction layer for distributed computing
 Author-email: The Fugue Development Team <hello@fugue.ai>
 License: Apache-2.0
@@ -24,12 +24,12 @@ Requires-Dist: triad>=1.0.1
 Requires-Dist: adagio>=0.2.6
 Requires-Dist: pandas<3
 Provides-Extra: sql
-Requires-Dist: qpd>=0.4.4; extra == "sql"
-Requires-Dist: fugue-sql-antlr>=0.2.0; extra == "sql"
+Requires-Dist: duckdb>=0.5.0; extra == "sql"
+Requires-Dist: fugue-sql-antlr>=0.2.4; extra == "sql"
 Requires-Dist: sqlglot<28; extra == "sql"
 Requires-Dist: jinja2; extra == "sql"
 Provides-Extra: cpp-sql-parser
-Requires-Dist: fugue-sql-antlr[cpp]>=0.2.0; extra == "cpp-sql-parser"
+Requires-Dist: fugue-sql-antlr[cpp]>=0.2.4; extra == "cpp-sql-parser"
 Provides-Extra: spark
 Requires-Dist: pyspark>=3.1.1; extra == "spark"
 Requires-Dist: zstandard>=0.25.0; extra == "spark"
@@ -43,8 +43,7 @@ Requires-Dist: duckdb>=0.5.0; extra == "ray"
 Requires-Dist: pyarrow>=7.0.0; extra == "ray"
 Requires-Dist: pandas; extra == "ray"
 Provides-Extra: duckdb
-Requires-Dist: qpd>=0.4.4; extra == "duckdb"
-Requires-Dist: fugue-sql-antlr>=0.2.0; extra == "duckdb"
+Requires-Dist: fugue-sql-antlr>=0.2.4; extra == "duckdb"
 Requires-Dist: sqlglot<28; extra == "duckdb"
 Requires-Dist: jinja2; extra == "duckdb"
 Requires-Dist: duckdb>=0.5.0; extra == "duckdb"
@@ -52,8 +51,7 @@ Requires-Dist: numpy; extra == "duckdb"
 Provides-Extra: polars
 Requires-Dist: polars; extra == "polars"
 Provides-Extra: ibis
-Requires-Dist: qpd>=0.4.4; extra == "ibis"
-Requires-Dist: fugue-sql-antlr>=0.2.0; extra == "ibis"
+Requires-Dist: fugue-sql-antlr>=0.2.4; extra == "ibis"
 Requires-Dist: sqlglot<28; extra == "ibis"
 Requires-Dist: jinja2; extra == "ibis"
 Requires-Dist: ibis-framework[pandas]; extra == "ibis"
@@ -62,8 +60,7 @@ Requires-Dist: notebook; extra == "notebook"
 Requires-Dist: jupyterlab; extra == "notebook"
 Requires-Dist: ipython>=7.10.0; extra == "notebook"
 Provides-Extra: all
-Requires-Dist: qpd>=0.4.4; extra == "all"
-Requires-Dist: fugue-sql-antlr>=0.2.0; extra == "all"
+Requires-Dist: fugue-sql-antlr>=0.2.4; extra == "all"
 Requires-Dist: sqlglot<28; extra == "all"
 Requires-Dist: jinja2; extra == "all"
 Requires-Dist: pyspark>=3.1.1; extra == "all"

{fugue-0.9.7.dev1 → fugue-0.9.7.dev2}/fugue/__init__.py

@@ -55,7 +55,7 @@ from fugue.execution.factory import (
 from fugue.execution.native_execution_engine import (
     NativeExecutionEngine,
     PandasMapEngine,
-    QPDPandasEngine,
+    DefaultSQLEngine,
 )
 from fugue.extensions.creator import Creator, creator, register_creator
 from fugue.extensions.outputter import Outputter, outputter, register_outputter

{fugue-0.9.7.dev1 → fugue-0.9.7.dev2}/fugue/_utils/misc.py

@@ -23,6 +23,4 @@ def import_or_throw(package_name: str, message: str) -> Any:
 
 
 def import_fsql_dependency(package_name: str) -> Any:
-    return import_or_throw(
-        package_name, "Please try to install the package by `pip install fugue[sql]`."
-    )
+    return import_or_throw(package_name, "Please pip install with extra `fugue[sql]`.")

{fugue-0.9.7.dev1 → fugue-0.9.7.dev2}/fugue/constants.py

@@ -37,7 +37,7 @@ _FUGUE_GLOBAL_CONF = ParamDict(
         FUGUE_CONF_WORKFLOW_CONCURRENCY: 1,
         FUGUE_CONF_WORKFLOW_AUTO_PERSIST: False,
         FUGUE_CONF_WORKFLOW_EXCEPTION_HIDE: "fugue.,six,adagio.,pandas,"
-        "fugue_dask.,dask.,fugue_spark.,pyspark.,antlr4,_qpd_antlr,qpd,triad,"
+        "fugue_dask.,dask.,fugue_spark.,pyspark.,antlr4,triad,"
         "fugue_notebook.,ipython.,jupyter.,ipykernel,_pytest,pytest,fugue_ibis.",
         FUGUE_CONF_WORKFLOW_EXCEPTION_INJECT: 3,
         FUGUE_CONF_WORKFLOW_EXCEPTION_OPTIMIZE: True,

{fugue-0.9.7.dev1 → fugue-0.9.7.dev2}/fugue/dev.py

@@ -32,7 +32,7 @@ from fugue.execution.factory import (
     register_execution_engine,
     register_sql_engine,
 )
-from fugue.execution.native_execution_engine import PandasMapEngine, QPDPandasEngine
+from fugue.execution.native_execution_engine import PandasMapEngine, DefaultSQLEngine
 from fugue.rpc import (
     EmptyRPCHandler,
     RPCClient,

{fugue-0.9.7.dev1 → fugue-0.9.7.dev2}/fugue/execution/__init__.py

@@ -10,4 +10,4 @@ from .factory import (
     register_execution_engine,
     register_sql_engine,
 )
-from .native_execution_engine import NativeExecutionEngine, QPDPandasEngine
+from .native_execution_engine import NativeExecutionEngine, DefaultSQLEngine

{fugue-0.9.7.dev1 → fugue-0.9.7.dev2}/fugue/execution/native_execution_engine.py

@@ -11,7 +11,6 @@ from triad.utils.io import makedirs
 from triad.utils.pandas_like import PandasUtils
 
 from fugue._utils.io import load_df, save_df
-from fugue._utils.misc import import_fsql_dependency
 from fugue.collections.partition import (
     PartitionCursor,
     PartitionSpec,
@@ -21,6 +20,7 @@ from fugue.collections.sql import StructuredRawSQL
 from fugue.constants import KEYWORD_PARALLELISM, KEYWORD_ROWCOUNT
 from fugue.dataframe import (
     AnyDataFrame,
+    ArrowDataFrame,
     DataFrame,
     DataFrames,
     LocalBoundedDataFrame,
@@ -39,31 +39,53 @@ from .execution_engine import (
 )
 
 
-class QPDPandasEngine(SQLEngine):
-    """QPD execution implementation.
+class DefaultSQLEngine(SQLEngine):
+    """DuckDB SQL backend implementation.
 
     :param execution_engine: the execution engine this sql engine will run on
     """
 
     @property
     def dialect(self) -> Optional[str]:
-        return "spark"
-
-    def to_df(self, df: AnyDataFrame, schema: Any = None) -> DataFrame:
-        return _to_native_execution_engine_df(df, schema)
-
-    @property
-    def is_distributed(self) -> bool:
-        return False
+        return "duckdb"
 
     def select(self, dfs: DataFrames, statement: StructuredRawSQL) -> DataFrame:
-        qpd_pandas = import_fsql_dependency("qpd_pandas")
+        import duckdb
+
+        from fugue_duckdb.dataframe import _duck_as_arrow
 
         _dfs, _sql = self.encode(dfs, statement)
-        _dd = {k: self.to_df(v).as_pandas() for k, v in _dfs.items()}  # type: ignore
 
-        df = qpd_pandas.run_sql_on_pandas(_sql, _dd, ignore_case=True)
-        return self.to_df(df)
+        with duckdb.connect() as conn:
+            for k, v in _dfs.items():
+                duckdb.from_arrow(v.as_arrow(), connection=conn).create_view(k)
+            return ArrowDataFrame(_duck_as_arrow(conn.sql(_sql)))
+
+    def table_exists(self, table: str) -> bool:  # pragma: no cover
+        raise NotImplementedError(
+            "table_exists can only be used with DuckExecutionEngine"
+        )
+
+    def save_table(
+        self,
+        df: DataFrame,
+        table: str,
+        mode: str = "overwrite",
+        partition_spec: Optional[PartitionSpec] = None,
+        **kwargs: Any,
+    ) -> None:  # pragma: no cover
+        raise NotImplementedError(
+            "save_table can only be used with DuckExecutionEngine"
+        )
+
+    def load_table(self, table: str, **kwargs: Any) -> DataFrame:  # pragma: no cover
+        raise NotImplementedError(
+            "load_table can only be used with DuckExecutionEngine"
+        )
+
+    @property
+    def is_distributed(self) -> bool:
+        return False
 
 
 class PandasMapEngine(MapEngine):
@@ -148,8 +170,9 @@ class PandasMapEngine(MapEngine):
                 output_df = PandasDataFrame(output_df.native, output_schema)
             assert_or_throw(
                 output_df.schema == output_schema,
-                lambda: f"map output {output_df.schema} "
-                f"mismatches given {output_schema}",
+                lambda: (
+                    f"map output {output_df.schema} mismatches given {output_schema}"
+                ),
             )
             return self.to_df(output_df)  # type: ignore
 
@@ -194,7 +217,7 @@ class NativeExecutionEngine(ExecutionEngine):
         return False
 
     def create_default_sql_engine(self) -> SQLEngine:
-        return QPDPandasEngine(self)
+        return DefaultSQLEngine(self)
 
     def create_default_map_engine(self) -> MapEngine:
         return PandasMapEngine(self)

{fugue-0.9.7.dev1 → fugue-0.9.7.dev2}/fugue/registry.py

@@ -1,7 +1,7 @@
 from fugue.execution.factory import register_execution_engine, register_sql_engine
 from fugue.execution.native_execution_engine import (
+    DefaultSQLEngine,
     NativeExecutionEngine,
-    QPDPandasEngine,
 )
 
 
@@ -25,8 +25,5 @@ def _register_engines() -> None:
         "pandas", lambda conf: NativeExecutionEngine(conf), on_dup="ignore"
     )
     register_sql_engine(
-        "qpdpandas", lambda engine: QPDPandasEngine(engine), on_dup="ignore"
-    )
-    register_sql_engine(
-        "qpd_pandas", lambda engine: QPDPandasEngine(engine), on_dup="ignore"
+        "default", lambda engine: DefaultSQLEngine(engine), on_dup="ignore"
     )

{fugue-0.9.7.dev1 → fugue-0.9.7.dev2}/fugue.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fugue
-Version: 0.9.7.dev1
+Version: 0.9.7.dev2
 Summary: An abstraction layer for distributed computing
 Author-email: The Fugue Development Team <hello@fugue.ai>
 License: Apache-2.0
@@ -24,12 +24,12 @@ Requires-Dist: triad>=1.0.1
 Requires-Dist: adagio>=0.2.6
 Requires-Dist: pandas<3
 Provides-Extra: sql
-Requires-Dist: qpd>=0.4.4; extra == "sql"
-Requires-Dist: fugue-sql-antlr>=0.2.0; extra == "sql"
+Requires-Dist: duckdb>=0.5.0; extra == "sql"
+Requires-Dist: fugue-sql-antlr>=0.2.4; extra == "sql"
 Requires-Dist: sqlglot<28; extra == "sql"
 Requires-Dist: jinja2; extra == "sql"
 Provides-Extra: cpp-sql-parser
-Requires-Dist: fugue-sql-antlr[cpp]>=0.2.0; extra == "cpp-sql-parser"
+Requires-Dist: fugue-sql-antlr[cpp]>=0.2.4; extra == "cpp-sql-parser"
 Provides-Extra: spark
 Requires-Dist: pyspark>=3.1.1; extra == "spark"
 Requires-Dist: zstandard>=0.25.0; extra == "spark"
@@ -43,8 +43,7 @@ Requires-Dist: duckdb>=0.5.0; extra == "ray"
 Requires-Dist: pyarrow>=7.0.0; extra == "ray"
 Requires-Dist: pandas; extra == "ray"
 Provides-Extra: duckdb
-Requires-Dist: qpd>=0.4.4; extra == "duckdb"
-Requires-Dist: fugue-sql-antlr>=0.2.0; extra == "duckdb"
+Requires-Dist: fugue-sql-antlr>=0.2.4; extra == "duckdb"
 Requires-Dist: sqlglot<28; extra == "duckdb"
 Requires-Dist: jinja2; extra == "duckdb"
 Requires-Dist: duckdb>=0.5.0; extra == "duckdb"
@@ -52,8 +51,7 @@ Requires-Dist: numpy; extra == "duckdb"
 Provides-Extra: polars
 Requires-Dist: polars; extra == "polars"
 Provides-Extra: ibis
-Requires-Dist: qpd>=0.4.4; extra == "ibis"
-Requires-Dist: fugue-sql-antlr>=0.2.0; extra == "ibis"
+Requires-Dist: fugue-sql-antlr>=0.2.4; extra == "ibis"
 Requires-Dist: sqlglot<28; extra == "ibis"
 Requires-Dist: jinja2; extra == "ibis"
 Requires-Dist: ibis-framework[pandas]; extra == "ibis"
@@ -62,8 +60,7 @@ Requires-Dist: notebook; extra == "notebook"
 Requires-Dist: jupyterlab; extra == "notebook"
 Requires-Dist: ipython>=7.10.0; extra == "notebook"
 Provides-Extra: all
-Requires-Dist: qpd>=0.4.4; extra == "all"
-Requires-Dist: fugue-sql-antlr>=0.2.0; extra == "all"
+Requires-Dist: fugue-sql-antlr>=0.2.4; extra == "all"
 Requires-Dist: sqlglot<28; extra == "all"
 Requires-Dist: jinja2; extra == "all"
 Requires-Dist: pyspark>=3.1.1; extra == "all"

{fugue-0.9.7.dev1 → fugue-0.9.7.dev2}/fugue.egg-info/requires.txt

@@ -3,8 +3,7 @@ adagio>=0.2.6
 pandas<3
 
 [all]
-qpd>=0.4.4
-fugue-sql-antlr>=0.2.0
+fugue-sql-antlr>=0.2.4
 sqlglot<28
 jinja2
 pyspark>=3.1.1
@@ -23,7 +22,7 @@ polars
 ray[data]>=2.30.0
 
 [cpp_sql_parser]
-fugue-sql-antlr[cpp]>=0.2.0
+fugue-sql-antlr[cpp]>=0.2.4
 
 [dask]
 dask[dataframe,distributed]>=2024.4.0
@@ -31,16 +30,14 @@ pyarrow>=7.0.0
 pandas>=2.0.2
 
 [duckdb]
-qpd>=0.4.4
-fugue-sql-antlr>=0.2.0
+fugue-sql-antlr>=0.2.4
 sqlglot<28
 jinja2
 duckdb>=0.5.0
 numpy
 
 [ibis]
-qpd>=0.4.4
-fugue-sql-antlr>=0.2.0
+fugue-sql-antlr>=0.2.4
 sqlglot<28
 jinja2
 ibis-framework[pandas]
@@ -66,7 +63,7 @@ pyspark>=3.1.1
 zstandard>=0.25.0
 
 [sql]
-qpd>=0.4.4
-fugue-sql-antlr>=0.2.0
+duckdb>=0.5.0
+fugue-sql-antlr>=0.2.4
 sqlglot<28
 jinja2

{fugue-0.9.7.dev1 → fugue-0.9.7.dev2}/fugue_test/builtin_suite.py

@@ -1,10 +1,11 @@
 # pylint: disable-all
 try:
-    import qpd_pandas  # noqa: F401
+    import duckdb  # noqa: F401
+    import sqlglot  # noqa: F401
 
-    HAS_QPD = True
+    HAS_DEFAULT_SQL_ENGINE = True
 except ImportError:  # pragma: no cover
-    HAS_QPD = False
+    HAS_DEFAULT_SQL_ENGINE = False
 
 import datetime
 import os
@@ -29,6 +30,7 @@ from fugue import (
     CoTransformer,
     DataFrame,
     DataFrames,
+    DefaultSQLEngine,
     ExecutionEngine,
     FugueWorkflow,
     LocalDataFrame,
@@ -38,7 +40,6 @@ from fugue import (
     PandasDataFrame,
     PartitionSpec,
     Processor,
-    QPDPandasEngine,
     Schema,
     Transformer,
     cotransformer,
@@ -858,7 +859,9 @@ class BuiltInTests(object):
                 ).assert_eq(d)
             dag.run(self.engine)
 
-        @pytest.mark.skipif(not HAS_QPD, reason="qpd not working")
+        @pytest.mark.skipif(
+            not HAS_DEFAULT_SQL_ENGINE, reason="Default sql engine not available"
+        )
         def test_df_select(self):
             with FugueWorkflow() as dag:
                 # wildcard
@@ -910,7 +913,9 @@ class BuiltInTests(object):
                 dag.select("select * from", a).assert_eq(b)
             dag.run(self.engine, {"fugue.sql.compile.ignore_case": True})
 
-        @pytest.mark.skipif(not HAS_QPD, reason="qpd not working")
+        @pytest.mark.skipif(
+            not HAS_DEFAULT_SQL_ENGINE, reason="Default sql engine not available"
+        )
         def test_df_filter(self):
             with FugueWorkflow() as dag:
                 a = dag.df([[1, 10], [2, 20], [3, 30]], "x:int,y:int")
@@ -918,7 +923,9 @@ class BuiltInTests(object):
                 a.filter((col("y") > 15) & (col("y") < 25)).assert_eq(b)
             dag.run(self.engine)
 
-        @pytest.mark.skipif(not HAS_QPD, reason="qpd not working")
+        @pytest.mark.skipif(
+            not HAS_DEFAULT_SQL_ENGINE, reason="Default sql engine not available"
+        )
         def test_df_assign(self):
             with FugueWorkflow() as dag:
                 a = dag.df([[1, 10], [2, 20], [3, 30]], "x:int,y:int")
@@ -932,7 +939,9 @@ class BuiltInTests(object):
                 a.assign(lit("x").alias("y"), z=(col("y") + 1).cast(float)).assert_eq(b)
             dag.run(self.engine)
 
-        @pytest.mark.skipif(not HAS_QPD, reason="qpd not working")
+        @pytest.mark.skipif(
+            not HAS_DEFAULT_SQL_ENGINE, reason="Default sql engine not available"
+        )
         def test_aggregate(self):
             with FugueWorkflow() as dag:
                 a = dag.df([[1, 10], [1, 200], [3, 30]], "x:int,y:int")
@@ -946,9 +955,11 @@ class BuiltInTests(object):
                 ).assert_eq(c)
             dag.run(self.engine)
 
-        @pytest.mark.skipif(not HAS_QPD, reason="qpd not working")
+        @pytest.mark.skipif(
+            not HAS_DEFAULT_SQL_ENGINE, reason="Default sql engine not available"
+        )
         def test_select(self):
-            class MockEngine(QPDPandasEngine):
+            class MockEngine(DefaultSQLEngine):
                 def __init__(self, execution_engine, p: int = 0):
                     super().__init__(execution_engine)
                     self.p = p
@@ -985,7 +996,7 @@ class BuiltInTests(object):
                     "AS t1 INNER JOIN",
                     b,
                     "AS t2 ON t1.x=t2.x",
-                    sql_engine="qpdpandas",
+                    sql_engine="default",
                 ).assert_eq(c)
 
                 # specify sql engine and params
@@ -1059,7 +1070,6 @@ class BuiltInTests(object):
                         "x:long,y:double",
                     )
                 )
-                # TODO: INTERSECT ALL is not implemented (QPD issue)
                 # a.intersect(b, distinct=False).assert_eq(
                 #     ArrayDataFrame(
                 #         [[2, None], [2, None]],
@@ -1091,7 +1101,6 @@ class BuiltInTests(object):
                         "x:long,y:double",
                     )
                 )
-                # # TODO: EXCEPT ALL is not implemented (QPD issue)
                 # a.subtract(c, distinct=False).assert_eq(
                 #     ArrayDataFrame(
                 #         [[2, None], [2, None]],
@@ -1634,7 +1643,7 @@ class BuiltInTests(object):
                 df.partition(by=["a"]).out_transform(t12)
                 raises(
                     FugueInterfacelessError,
-                    lambda: (df.partition(by=["a"]).out_transform(t1)),
+                    lambda: df.partition(by=["a"]).out_transform(t1),
                 )  # for t1, callback must be provided
                 df.assert_eq(res)
             dag.run(self.engine)
@@ -1691,7 +1700,9 @@ class BuiltInTests(object):
 
             assert 4 == cb3.n
 
-        @pytest.mark.skipif(not HAS_QPD, reason="qpd not working")
+        @pytest.mark.skipif(
+            not HAS_DEFAULT_SQL_ENGINE, reason="Default sql engine not available"
+        )
         def test_sql_api(self):
             def tr(df: pd.DataFrame, n=1) -> pd.DataFrame:
                 return df + n
@@ -1738,7 +1749,9 @@ class BuiltInTests(object):
                 assert fa.is_local(sdf4)
 
         @pytest.mark.skipif(os.name == "nt", reason="Skip Windows")
-        @pytest.mark.skipif(not HAS_QPD, reason="qpd not working")
+        @pytest.mark.skipif(
+            not HAS_DEFAULT_SQL_ENGINE, reason="Default sql engine not available"
+        )
         def test_any_column_name(self):
             f_parquet = os.path.join(str(self.tmpdir), "a.parquet")
             f_csv = os.path.join(str(self.tmpdir), "a.csv")

{fugue-0.9.7.dev1 → fugue-0.9.7.dev2}/fugue_test/execution_suite.py

@@ -1,10 +1,11 @@
 # pylint: disable-all
 try:
-    import qpd_pandas  # noqa: F401
+    import duckdb  # noqa: F401
+    import sqlglot  # noqa: F401
 
-    HAS_QPD = True
+    HAS_DEFAULT_SQL_ENGINE = True
 except ImportError:  # pragma: no cover
-    HAS_QPD = False
+    HAS_DEFAULT_SQL_ENGINE = False
 
 import copy
 import os
@@ -81,7 +82,9 @@ class ExecutionEngineTests(object):
             pdf = pdf[pdf.a < 0]
             self.df_eq(o, fa.as_fugue_engine_df(e, pdf), throw=True)
 
-        @pytest.mark.skipif(not HAS_QPD, reason="qpd not working")
+        @pytest.mark.skipif(
+            not HAS_DEFAULT_SQL_ENGINE, reason="Default sql engine not available"
+        )
         def test_filter(self):
             a = ArrayDataFrame(
                 [[1, 2], [None, 2], [None, 1], [3, 4], [None, 4]],
@@ -94,7 +97,9 @@ class ExecutionEngineTests(object):
             c = fa.filter(a, col("a") + col("b") == 3)
             self.df_eq(c, [[1, 2]], "a:double,b:int", throw=True)
 
-        @pytest.mark.skipif(not HAS_QPD, reason="qpd not working")
+        @pytest.mark.skipif(
+            not HAS_DEFAULT_SQL_ENGINE, reason="Default sql engine not available"
+        )
         def test_select(self):
             a = ArrayDataFrame(
                 [[1, 2], [None, 2], [None, 1], [3, 4], [None, 4]], "a:double,b:int"
@@ -153,7 +158,9 @@ class ExecutionEngineTests(object):
                 b, [[1, "1", 2], [None, "1", 7]], "a:double,o:str,c:double", throw=True
             )
 
-        @pytest.mark.skipif(not HAS_QPD, reason="qpd not working")
+        @pytest.mark.skipif(
+            not HAS_DEFAULT_SQL_ENGINE, reason="Default sql engine not available"
+        )
         def test_assign(self):
             a = ArrayDataFrame(
                 [[1, 2], [None, 2], [None, 1], [3, 4], [None, 4]], "a:double,b:int"
@@ -173,7 +180,9 @@ class ExecutionEngineTests(object):
                 throw=True,
             )
 
-        @pytest.mark.skipif(not HAS_QPD, reason="qpd not working")
+        @pytest.mark.skipif(
+            not HAS_DEFAULT_SQL_ENGINE, reason="Default sql engine not available"
+        )
         def test_aggregate(self):
             a = ArrayDataFrame(
                 [[1, 2], [None, 2], [None, 1], [3, 4], [None, 4]], "a:double,b:int"
@@ -605,7 +614,6 @@ class ExecutionEngineTests(object):
                 "a:double,b:double,c:int",
                 throw=True,
             )
-            # TODO: EXCEPT ALL is not implemented (QPD issue)
             # c = fa.subtract(a, b, distinct=False)
             # self.df_eq(
             #     c,
@@ -648,7 +656,6 @@ class ExecutionEngineTests(object):
                 "a:double,b:double,c:int",
                 throw=True,
             )
-            # TODO: INTERSECT ALL is not implemented (QPD issue)
             # c = fa.intersect(a, b, distinct=False)
             # self.df_eq(
             #     c,

{fugue-0.9.7.dev1 → fugue-0.9.7.dev2}/pyproject.toml

@@ -4,14 +4,20 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "fugue"
-version = "0.9.7.dev1"
+version = "0.9.7.dev2"
 description = "An abstraction layer for distributed computing"
 readme = "README.md"
-license = {text = "Apache-2.0"}
-authors = [
-    {name = "The Fugue Development Team", email = "hello@fugue.ai"}
+license = { text = "Apache-2.0" }
+authors = [{ name = "The Fugue Development Team", email = "hello@fugue.ai" }]
+keywords = [
+    "distributed",
+    "spark",
+    "dask",
+    "ray",
+    "sql",
+    "dsl",
+    "domain specific language",
 ]
-keywords = ["distributed", "spark", "dask", "ray", "sql", "dsl", "domain specific language"]
 classifiers = [
     "Development Status :: 5 - Production/Stable",
     "Intended Audience :: Developers",
@@ -25,28 +31,16 @@ classifiers = [
     "Programming Language :: Python :: 3 :: Only",
 ]
 requires-python = ">=3.10"
-dependencies = [
-    "triad>=1.0.1",
-    "adagio>=0.2.6",
-    "pandas<3",
-]
+dependencies = ["triad>=1.0.1", "adagio>=0.2.6", "pandas<3"]
 
 [project.urls]
 Homepage = "http://github.com/fugue-project/fugue"
 Repository = "http://github.com/fugue-project/fugue"
 
 [project.optional-dependencies]
-sql = [
-    "qpd>=0.4.4",
-    "fugue-sql-antlr>=0.2.0",
-    "sqlglot<28",
-    "jinja2",
-]
-cpp_sql_parser = ["fugue-sql-antlr[cpp]>=0.2.0"]
-spark = [
-    "pyspark>=3.1.1",
-    "zstandard>=0.25.0",
-]
+sql = ["duckdb>=0.5.0", "fugue-sql-antlr>=0.2.4", "sqlglot<28", "jinja2"]
+cpp_sql_parser = ["fugue-sql-antlr[cpp]>=0.2.4"]
+spark = ["pyspark>=3.1.1", "zstandard>=0.25.0"]
 dask = [
     "dask[distributed,dataframe]>=2024.4.0",
     "pyarrow>=7.0.0",
@@ -59,8 +53,7 @@ ray = [
     "pandas",
 ]
 duckdb = [
-    "qpd>=0.4.4",
-    "fugue-sql-antlr>=0.2.0",
+    "fugue-sql-antlr>=0.2.4",
     "sqlglot<28",
     "jinja2",
     "duckdb>=0.5.0",
@@ -68,20 +61,14 @@ duckdb = [
 ]
 polars = ["polars"]
 ibis = [
-    "qpd>=0.4.4",
-    "fugue-sql-antlr>=0.2.0",
+    "fugue-sql-antlr>=0.2.4",
     "sqlglot<28",
     "jinja2",
     "ibis-framework[pandas]",
 ]
-notebook = [
-    "notebook",
-    "jupyterlab",
-    "ipython>=7.10.0",
-]
+notebook = ["notebook", "jupyterlab", "ipython>=7.10.0"]
 all = [
-    "qpd>=0.4.4",
-    "fugue-sql-antlr>=0.2.0",
+    "fugue-sql-antlr>=0.2.4",
     "sqlglot<28",
     "jinja2",
     "pyspark>=3.1.1",
@@ -116,7 +103,7 @@ dev = [
     "pytest",
     "pytest-cov",
     "pytest-mock",
-    "pytest-rerunfailures==10.2",
+    "pytest-rerunfailures>10.2",
     # Additional test dependencies
     "flask",
     "psutil",
@@ -148,7 +135,7 @@ fugue_test = "fugue_test"
 fugue_test_fixtures = "fugue_test.fixtures"
 
 [tool.setuptools]
-packages = {find = {include = ["fugue*"]}}
+packages = { find = { include = ["fugue*"] } }
 
 [tool.setuptools.package-data]
 fugue = ["py.typed"]
@@ -156,7 +143,8 @@ fugue_notebook = ["nbextension/*"]
 
 [tool.pytest.ini_options]
 addopts = [
-    "-p", "pytest_cov",
+    "-p",
+    "pytest_cov",
     "--cov=fugue",
     "--cov=fugue_test",
     "--cov=fugue_spark",