chore: remove deprecated distutils (#24001)

.pylintrc

@@ -300,7 +300,7 @@ ignore-mixin-members=yes
 # (useful for modules/projects where namespaces are manipulated during runtime
 # and thus existing member attributes cannot be deduced by static analysis. It
 # supports qualified module names, as well as Unix pattern matching.
-ignored-modules=numpy,pandas,alembic.op,sqlalchemy,alembic.context,flask_appbuilder.security.sqla.PermissionView.role,flask_appbuilder.Model.metadata,flask_appbuilder.Base.metadata,distutils
+ignored-modules=numpy,pandas,alembic.op,sqlalchemy,alembic.context,flask_appbuilder.security.sqla.PermissionView.role,flask_appbuilder.Model.metadata,flask_appbuilder.Base.metadata
 
 # List of class names for which member attributes should not be checked (useful
 # for classes with dynamically set attributes). This supports the use of

requirements/base.txt

@@ -193,6 +193,7 @@ ordered-set==4.1.0
     # via flask-limiter
 packaging==23.1
     # via
+    #   apache-superset
     #   deprecation
     #   limits
 pandas==1.5.3

setup.py

@@ -101,6 +101,7 @@ setup(
         "msgpack>=1.0.0, <1.1",
         "nh3>=0.2.11, <0.3",
         "numpy==1.23.5",
+        "packaging",
         "pandas>=1.5.3, <1.6",
         "parsedatetime",
         "pgsanity",

superset/db_engine_specs/elasticsearch.py

@@ -16,9 +16,9 @@
 # under the License.
 import logging
 from datetime import datetime
-from distutils.version import StrictVersion
 from typing import Any, Dict, Optional, Type
 
+from packaging.version import Version
 from sqlalchemy import types
 
 from superset.db_engine_specs.base import BaseEngineSpec
@@ -79,9 +79,7 @@ class ElasticSearchEngineSpec(BaseEngineSpec):  # pylint: disable=abstract-metho
             supports_dttm_parse = False
             try:
                 if es_version:
-                    supports_dttm_parse = StrictVersion(es_version) >= StrictVersion(
+                    supports_dttm_parse = Version(es_version) >= Version("7.8")
-                        "7.8"
-                    )
             except Exception as ex:  # pylint: disable=broad-except
                 logger.error("Unexpected error while convert es_version", exc_info=True)
                 logger.exception(ex)

superset/db_engine_specs/presto.py

@@ -23,7 +23,6 @@ import time
 from abc import ABCMeta
 from collections import defaultdict, deque
 from datetime import datetime
-from distutils.version import StrictVersion
 from textwrap import dedent
 from typing import (
     Any,
@@ -43,6 +42,7 @@ import pandas as pd
 import simplejson as json
 from flask import current_app
 from flask_babel import gettext as __, lazy_gettext as _
+from packaging.version import Version
 from sqlalchemy import Column, literal_column, types
 from sqlalchemy.engine.base import Engine
 from sqlalchemy.engine.reflection import Inspector
@@ -470,8 +470,7 @@ class PrestoBaseEngineSpec(BaseEngineSpec, metaclass=ABCMeta):
         # Default to the new syntax if version is unset.
         partition_select_clause = (
             f'SELECT * FROM "{table_name}$partitions"'
-            if not presto_version
+            if not presto_version or Version(presto_version) >= Version("0.199")
-            or StrictVersion(presto_version) >= StrictVersion("0.199")
             else f"SHOW PARTITIONS FROM {table_name}"
         )
 
@@ -705,7 +704,7 @@ class PrestoEngineSpec(PrestoBaseEngineSpec):
     @classmethod
     def get_allow_cost_estimate(cls, extra: Dict[str, Any]) -> bool:
         version = extra.get("version")
-        return version is not None and StrictVersion(version) >= StrictVersion("0.319")
+        return version is not None and Version(version) >= Version("0.319")
 
     @classmethod
     def update_impersonation_config(

superset/utils/core.py

@@ -38,7 +38,6 @@ import zlib
 from contextlib import contextmanager
 from dataclasses import dataclass
 from datetime import date, datetime, time, timedelta
-from distutils.util import strtobool
 from email.mime.application import MIMEApplication
 from email.mime.image import MIMEImage
 from email.mime.multipart import MIMEMultipart
@@ -1191,6 +1190,7 @@ def merge_extra_filters(form_data: Dict[str, Any]) -> None:
             "__time_grain": "time_grain_sqla",
             "__granularity": "granularity",
         }
+
         # Grab list of existing filters 'keyed' on the column and operator
 
         def get_filter_key(f: Dict[str, Any]) -> str:
@@ -1788,7 +1788,7 @@ def indexed(
 
 
 def is_test() -> bool:
-    return strtobool(os.environ.get("SUPERSET_TESTENV", "false"))  # type: ignore
+    return parse_boolean_string(os.environ.get("SUPERSET_TESTENV", "false"))
 
 
 def get_time_filter_status(
@@ -1952,10 +1952,7 @@ def parse_boolean_string(bool_str: Optional[str]) -> bool:
     """
     if bool_str is None:
         return False
-    try:
+    return bool_str.lower() in ("y", "Y", "yes", "True", "t", "true", "On", "on", "1")
-        return bool(strtobool(bool_str.lower()))
-    except ValueError:
-        return False
 
 
 def apply_max_row_limit(

superset/utils/pandas_postprocessing/flatten.py

@@ -15,10 +15,10 @@
 # specific language governing permissions and limitations
 # under the License.
 
-from typing import Sequence, Union
+from collections.abc import Iterable
+from typing import Any, Sequence, Union
 
 import pandas as pd
-from numpy.distutils.misc_util import is_sequence
 
 from superset.utils.pandas_postprocessing.utils import (
     _is_multi_index_on_columns,
@@ -27,6 +27,13 @@ from superset.utils.pandas_postprocessing.utils import (
 )
 
 
+def is_sequence(seq: Any) -> bool:
+    if isinstance(seq, str):
+        return False
+
+    return isinstance(seq, Iterable)
+
+
 def flatten(
     df: pd.DataFrame,
     reset_index: bool = True,
@@ -85,7 +92,7 @@ def flatten(
         _columns = []
         for series in df.columns.to_flat_index():
             _cells = []
-            for cell in series if is_sequence(series) else [series]:  # type: ignore
+            for cell in series if is_sequence(series) else [series]:
                 if pd.notnull(cell):
                     # every cell should be converted to string and escape comma
                     _cells.append(escape_separator(str(cell)))

tests/unit_tests/utils/test_core.py

@@ -15,11 +15,17 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
-from typing import Any, Dict
+import os
+from typing import Any, Dict, Optional
 
 import pytest
 
-from superset.utils.core import QueryObjectFilterClause, remove_extra_adhoc_filters
+from superset.utils.core import (
+    is_test,
+    parse_boolean_string,
+    QueryObjectFilterClause,
+    remove_extra_adhoc_filters,
+)
 
 ADHOC_FILTER: QueryObjectFilterClause = {
     "col": "foo",
@@ -84,3 +90,46 @@ def test_remove_extra_adhoc_filters(
 ) -> None:
     remove_extra_adhoc_filters(original)
     assert expected == original
+
+
+def test_is_test():
+    orig_value = os.getenv("SUPERSET_TESTENV")
+
+    os.environ["SUPERSET_TESTENV"] = "true"
+    assert is_test()
+    os.environ["SUPERSET_TESTENV"] = "false"
+    assert not is_test()
+    os.environ["SUPERSET_TESTENV"] = ""
+    assert not is_test()
+
+    if orig_value is not None:
+        os.environ["SUPERSET_TESTENV"] = orig_value
+
+
+@pytest.mark.parametrize(
+    "test_input,expected",
+    [
+        ("y", True),
+        ("Y", True),
+        ("yes", True),
+        ("True", True),
+        ("t", True),
+        ("true", True),
+        ("On", True),
+        ("on", True),
+        ("1", True),
+        ("n", False),
+        ("N", False),
+        ("no", False),
+        ("False", False),
+        ("f", False),
+        ("false", False),
+        ("Off", False),
+        ("off", False),
+        ("0", False),
+        ("foo", False),
+        (None, False),
+    ],
+)
+def test_parse_boolean_string(test_input: Optional[str], expected: bool):
+    assert parse_boolean_string(test_input) == expected