Bump black to 22.3.0 (#443)

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/psf/black
-    rev: 19.10b0
+    rev: 22.3.0
     hooks:
       - id: black
         language_version: python3

continuous_integration/environment-3.10-jdk11-dev.yaml

@@ -5,7 +5,7 @@ channels:
 dependencies:
 - adagio>=0.2.3
 - antlr4-python3-runtime>=4.9.2
-- black=19.10b0
+- black=22.3.0
 - ciso8601>=2.2.0
 - dask-ml>=2022.1.22
 - dask>=2021.11.1

continuous_integration/environment-3.10-jdk8-dev.yaml

@@ -5,7 +5,7 @@ channels:
 dependencies:
 - adagio>=0.2.3
 - antlr4-python3-runtime>=4.9.2
-- black=19.10b0
+- black=22.3.0
 - ciso8601>=2.2.0
 - dask-ml>=2022.1.22
 - dask>=2021.11.1

continuous_integration/environment-3.8-jdk11-dev.yaml

@@ -5,7 +5,7 @@ channels:
 dependencies:
 - adagio>=0.2.3
 - antlr4-python3-runtime>=4.9.2
-- black=19.10b0
+- black=22.3.0
 - ciso8601>=2.2.0
 - dask-ml>=2022.1.22
 - dask>=2021.11.1

continuous_integration/environment-3.8-jdk8-dev.yaml

@@ -5,7 +5,7 @@ channels:
 dependencies:
 - adagio>=0.2.3
 - antlr4-python3-runtime>=4.9.2
-- black=19.10b0
+- black=22.3.0
 - ciso8601>=2.2.0
 - dask-ml>=2022.1.22
 - dask>=2021.11.1

continuous_integration/environment-3.9-jdk11-dev.yaml

@@ -5,7 +5,7 @@ channels:
 dependencies:
 - adagio>=0.2.3
 - antlr4-python3-runtime>=4.9.2
-- black=19.10b0
+- black=22.3.0
 - ciso8601>=2.2.0
 - dask-ml>=2022.1.22
 - dask>=2021.11.1

continuous_integration/environment-3.9-jdk8-dev.yaml

@@ -5,7 +5,7 @@ channels:
 dependencies:
 - adagio>=0.2.3
 - antlr4-python3-runtime>=4.9.2
-- black=19.10b0
+- black=22.3.0
 - ciso8601>=2.2.0
 - dask-ml>=2022.1.22
 - dask>=2021.11.1

dask_sql/cmd.py

@@ -78,8 +78,8 @@ def _parse_meta_command(sql):
 
 def _meta_commands(sql: str, context: Context, client: Client) -> Union[bool, Client]:
     """
-     parses metacommands and prints their result
-     returns True if meta commands detected
+    parses metacommands and prints their result
+    returns True if meta commands detected
     """
     cmd, schema_name = _parse_meta_command(sql)
     available_commands = [
@@ -147,7 +147,10 @@ def _meta_commands(sql: str, context: Context, client: Client) -> Union[bool, Cl
 
 
 def cmd_loop(
-    context: Context = None, client: Client = None, startup=False, log_level=None,
+    context: Context = None,
+    client: Client = None,
+    startup=False,
+    log_level=None,
 ):  # pragma: no cover
     """
     Run a REPL for answering SQL queries using ``dask-sql``.

dask_sql/context.py

@@ -908,7 +908,8 @@ def _register_callable(
             if replace:
                 schema.function_lists = list(
                     filter(
-                        lambda f: f.name.lower() != lower_name, schema.function_lists,
+                        lambda f: f.name.lower() != lower_name,
+                        schema.function_lists,
                     )
                 )
                 del schema.functions[lower_name]

dask_sql/input_utils/convert.py

@@ -55,7 +55,11 @@ def to_dc(
         maybe persist them to cluster memory before.
         """
         filled_get_dask_dataframe = lambda *args: cls._get_dask_dataframe(
-            *args, table_name=table_name, format=format, gpu=gpu, **kwargs,
+            *args,
+            table_name=table_name,
+            format=format,
+            gpu=gpu,
+            **kwargs,
         )
 
         if isinstance(input_item, list):

dask_sql/java.py

@@ -86,7 +86,10 @@ def _set_or_check_java_home():
 
 logger.debug(f"Starting JVM from path {jvmpath}...")
 jpype.startJVM(
-    *jvmArgs, ignoreUnrecognized=True, convertStrings=False, jvmpath=jvmpath,
+    *jvmArgs,
+    ignoreUnrecognized=True,
+    convertStrings=False,
+    jvmpath=jvmpath,
 )
 
 logger.debug("...having started JVM")

dask_sql/physical/rel/custom/analyze.py

@@ -61,7 +61,10 @@ def convert(
             )
         )
         statistics = statistics.append(
-            pd.Series({col: col for col in columns}, name="col_name",)
+            pd.Series(
+                {col: col for col in columns},
+                name="col_name",
+            )
         )
 
         cc = ColumnContainer(statistics.columns)

dask_sql/physical/rel/logical/aggregate.py

@@ -179,7 +179,10 @@ def convert(
 
         # Do all aggregates
         df_result, output_column_order = self._do_aggregations(
-            rel, dc, group_columns, context,
+            rel,
+            dc,
+            group_columns,
+            context,
         )
 
         # SQL does not care about the index, but we do not want to have any multiindices

dask_sql/physical/rel/logical/join.py

@@ -100,7 +100,11 @@ def convert(
             # The resulting dataframe will contain all (renamed) columns from the lhs and rhs
             # plus the added columns
             df = self._join_on_columns(
-                df_lhs_renamed, df_rhs_renamed, lhs_on, rhs_on, join_type,
+                df_lhs_renamed,
+                df_rhs_renamed,
+                lhs_on,
+                rhs_on,
+                join_type,
             )
         else:
             # 5. We are in the complex join case

dask_sql/physical/rel/logical/window.py

@@ -176,7 +176,8 @@ def map_on_each_group(
         upper_bound.is_current_row or upper_bound.offset == 0
     ):
         windowed_group = partitioned_group.rolling(
-            window=lower_bound.offset + 1, min_periods=0,
+            window=lower_bound.offset + 1,
+            min_periods=0,
         )
     else:
         lower_offset = lower_bound.offset if not lower_bound.is_current_row else 0

dask_sql/physical/rex/core/call.py

@@ -246,7 +246,10 @@ class IsFalseOperation(Operation):
     def __init__(self):
         super().__init__(self.false_)
 
-    def false_(self, df: SeriesOrScalar,) -> SeriesOrScalar:
+    def false_(
+        self,
+        df: SeriesOrScalar,
+    ) -> SeriesOrScalar:
         """
         Returns true where `df` is false (where `df` can also be just a scalar).
         Returns false on nan.
@@ -263,7 +266,10 @@ class IsTrueOperation(Operation):
     def __init__(self):
         super().__init__(self.true_)
 
-    def true_(self, df: SeriesOrScalar,) -> SeriesOrScalar:
+    def true_(
+        self,
+        df: SeriesOrScalar,
+    ) -> SeriesOrScalar:
         """
         Returns true where `df` is true (where `df` can also be just a scalar).
         Returns false on nan.
@@ -280,7 +286,10 @@ class NotOperation(Operation):
     def __init__(self):
         super().__init__(self.not_)
 
-    def not_(self, df: SeriesOrScalar,) -> SeriesOrScalar:
+    def not_(
+        self,
+        df: SeriesOrScalar,
+    ) -> SeriesOrScalar:
         """
         Returns not `df` (where `df` can also be just a scalar).
         """
@@ -296,7 +305,10 @@ class IsNullOperation(Operation):
     def __init__(self):
         super().__init__(self.null)
 
-    def null(self, df: SeriesOrScalar,) -> SeriesOrScalar:
+    def null(
+        self,
+        df: SeriesOrScalar,
+    ) -> SeriesOrScalar:
         """
         Returns true where `df` is null (where `df` can also be just a scalar).
         """
@@ -328,7 +340,10 @@ def __init__(self):
         super().__init__(self.regex)
 
     def regex(
-        self, test: SeriesOrScalar, regex: str, escape: str = None,
+        self,
+        test: SeriesOrScalar,
+        regex: str,
+        escape: str = None,
     ) -> SeriesOrScalar:
         """
         Returns true, if the string test matches the given regex

dask_sql/physical/utils/filter.py

@@ -90,7 +90,8 @@ def attempt_predicate_pushdown(ddf: dd.DataFrame) -> dd.DataFrame:
     # Regenerate collection with filtered IO layer
     try:
         return dsk.layers[name]._regenerate_collection(
-            dsk, new_kwargs={io_layer: {"filters": filters}},
+            dsk,
+            new_kwargs={io_layer: {"filters": filters}},
         )
     except ValueError as err:
         # Most-likely failed to apply filters in read_parquet.
@@ -198,7 +199,10 @@ def __init__(self, layer, creation_info):
         self.creation_info = creation_info
 
     def _regenerate_collection(
-        self, dsk, new_kwargs: dict = None, _regen_cache: dict = None,
+        self,
+        dsk,
+        new_kwargs: dict = None,
+        _regen_cache: dict = None,
     ):
         """Regenerate a Dask collection for this layer using the
         provided inputs and key-word arguments
@@ -223,7 +227,9 @@ def _regenerate_collection(
             else:
                 inputs.append(
                     dsk.layers[key]._regenerate_collection(
-                        dsk, new_kwargs=new_kwargs, _regen_cache=_regen_cache,
+                        dsk,
+                        new_kwargs=new_kwargs,
+                        _regen_cache=_regen_cache,
                     )
                 )
 
@@ -334,7 +340,12 @@ def _blockwise_comparison_dnf(op, indices: list, dsk: RegenerableGraph):
     right = _get_blockwise_input(1, indices, dsk)
 
     def _inv(symbol: str):
-        return {">": "<", "<": ">", ">=": "<=", "<=": ">=",}.get(symbol, symbol)
+        return {
+            ">": "<",
+            "<": ">",
+            ">=": "<=",
+            "<=": ">=",
+        }.get(symbol, symbol)
 
     if is_arraylike(left) and hasattr(left, "item") and left.size == 1:
         left = left.item()

dask_sql/server/app.py

@@ -272,7 +272,9 @@ def main():  # pragma: no cover
 
 
 def _init_app(
-    app: FastAPI, context: Context = None, client: dask.distributed.Client = None,
+    app: FastAPI,
+    context: Context = None,
+    client: dask.distributed.Client = None,
 ):
     app.c = context or Context()
     app.future_list = {}

docker/conda.txt

@@ -20,5 +20,5 @@ dask-ml>=2022.1.22
 scikit-learn>=0.24.2
 intake>=0.6.0
 pre-commit>=2.11.1
-black=19.10b0
+black=22.3.0
 isort=5.7.0

setup.py

@@ -109,7 +109,7 @@ def build(self):
             "scikit-learn>=0.24.2",
             "intake>=0.6.0",
             "pre-commit",
-            "black==19.10b0",
+            "black==22.3.0",
             "isort==5.7.0",
         ],
         "fugue": ["fugue[sql]>=0.5.3"],
@@ -122,5 +122,9 @@ def build(self):
     },
     zip_safe=False,
     cmdclass=cmdclass,
-    command_options={"build_sphinx": {"source_dir": ("setup.py", "docs"),}},
+    command_options={
+        "build_sphinx": {
+            "source_dir": ("setup.py", "docs"),
+        }
+    },
 )

tests/integration/fixtures.py

@@ -57,7 +57,10 @@ def df_wide():
 def df():
     np.random.seed(42)
     return pd.DataFrame(
-        {"a": [1.0] * 100 + [2.0] * 200 + [3.0] * 400, "b": 10 * np.random.rand(700),}
+        {
+            "a": [1.0] * 100 + [2.0] * 200 + [3.0] * 400,
+            "b": 10 * np.random.rand(700),
+        }
     )
 
 

tests/integration/test_cmd.py

@@ -100,7 +100,8 @@ def test_meta_commands(c, client, capsys):
     assert "Schema not_exists not available\n" == captured.out
 
     with pytest.raises(
-        OSError, match="Timed out .* to tcp://localhost:8787 after 5 s",
+        OSError,
+        match="Timed out .* to tcp://localhost:8787 after 5 s",
     ):
         with dask_config.set({"distributed.comm.timeouts.connect": 5}):
             client = _meta_commands("\\dsc localhost:8787", context=c, client=client)

tests/integration/test_create.py

@@ -35,7 +35,11 @@ def test_create_from_csv(c, df, temporary_data_file, gpu):
 
 
 @pytest.mark.parametrize(
-    "gpu", [False, pytest.param(True, marks=pytest.mark.gpu),],
+    "gpu",
+    [
+        False,
+        pytest.param(True, marks=pytest.mark.gpu),
+    ],
 )
 def test_cluster_memory(client, c, df, gpu):
     client.publish_dataset(df=dd.from_pandas(df, npartitions=1))