build: bump python to 3.12 (#101)

* build: allow python 3.12 install with DVE

deal with typing issue on get_type_hints generated from bumping from 3.11 to 3.12

* style: upgrade pylint and dependencies and fix linting following upgrade

* build: upgrade pydantic from 1.10.16 -> 1.10.19

removed previous typing fix as pydantic upgrade fixes the typing issues in 3.12

* refactor: remove previously missed typing fix no longer needed

* build: lock all dependency versions

* build: upgrade moto to a supported python 3.12 version

* build: upgrade isort to version supported by python 3.12

* build: upgrade mypy to version supporting python 3.12

* build: update xlsx2csv to supported python 3.12 version and removed faker dependency

Author: georgeRobertson2

.mise.toml

@@ -1,4 +1,4 @@
 [tools]
-python="3.11"
+python="3.12"
 poetry="2.3.3"
 java="liberica-1.8.0"

poetry.lock

@@ -30,21 +30,21 @@ packages = [
 ]
 
 [tool.poetry.dependencies]
-python = ">=3.10,<3.12"
+python = ">=3.10,<3.13"  # breaking changes beyond 3.12
 boto3 = ">=1.34.162,<1.36"  # breaking change beyond 1.36
 botocore = ">=1.34.162,<1.36"  # breaking change beyond 1.36
 delta-spark = "2.4.*"
-duckdb = "1.1.*"  # breaking changes beyond 1.1
-Jinja2 = "3.1.*"
-lxml = "^4.9.1"
+duckdb = "1.1.3"  # breaking changes beyond 1.1
+Jinja2 = "3.1.6"
+lxml = "4.9.4"
 numpy = "1.26.4"
-openpyxl = "^3.1"
-pandas = "^2.2.2"
-polars = "0.20.*"
-pyarrow = "^17.0.0"
-pydantic = "1.10.16"
+openpyxl = "3.1.5"
+pandas = "2.3.3"
+polars = "0.20.31"
+pyarrow = "17.0.0"
+pydantic = "1.10.19"
 pyspark = "3.4.*"
-typing_extensions = "^4.6.2"
+typing_extensions = "4.15.0"
 
 [tool.poetry.group.dev]
 optional = true
@@ -58,30 +58,29 @@ commitizen = "4.9.1"
 pre-commit = "4.3.0"
 charset-normalizer = "3.4.6"
 python-discovery = "1.2.0"
-requests = "2.33.0"
 
 [tool.poetry.group.test]
 optional = true
 
 [tool.poetry.group.test.dependencies]
-faker = "18.11.1"
 behave = "1.3.3"
 coverage = "7.11.0"
-moto = {extras = ["s3"], version = "4.0.13"}
+moto = {extras = ["s3"], version = "4.2.14"}
+requests = "2.33.0"  # dependency of `moto`
 Werkzeug = "3.1.6"
 pytest = "8.4.2"
 pytest-lazy-fixtures = "1.4.0"  # switched from https://github.com/TvoroG/pytest-lazy-fixture as it's no longer supported
-xlsx2csv = "0.8.2"
+xlsx2csv = "0.8.4"  # polars requirement
 
 [tool.poetry.group.lint]
 optional = true
 
 [tool.poetry.group.lint.dependencies]
 black = "24.3.0"
-astroid = "2.14.2"
-isort = "5.11.5"
-pylint = "2.16.4"
-mypy = "0.991"
+astroid = "3.3.9"
+isort = "5.13.2"
+pylint = "3.3.9"
+mypy = "1.11.2"
 boto3-stubs = {extras = ["essential"], version = "1.26.72"}
 botocore-stubs = "1.29.72"
 pandas-stubs = "1.2.0.62"
@@ -100,7 +99,7 @@ optional = true
 
 [tool.poetry.group.docs.dependencies]
 click = "8.2.1"
-mkdocs = "^1.6.1"
+mkdocs = "1.6.1"
 mkdocstrings = { version = "1.0.3", extras = ["python"] }
 griffelib = "2.0.1"
 pymdown-extensions = "10.21.2"
@@ -142,10 +141,6 @@ source_pkgs = [
 [tool.coverage.report]
 show_missing = true
 
-[tool.pylint]
-init-hook = "import sys; sys.path.append('./pylint_checkers')"
-load-plugins = "check_typing_imports"
-
 [tool.pylint.main]
 extension-pkg-allow-list = ["pyspark", "lxml", "pydantic"]
 fail-under = 10.0
@@ -194,7 +189,7 @@ max-statements = 50
 min-public-methods = 2
 
 [tool.pylint.exceptions]
-overgeneral-exceptions = ["BaseException", "Exception"]
+overgeneral-exceptions = ["builtins.BaseException", "builtins.Exception"]
 
 [tool.pylint.format]
 ignore-long-lines = "^\\s*(# )?<?https?://\\S+>?$"
@@ -229,6 +224,8 @@ disable = [
     "use-symbolic-message-instead",
     "logging-fstring-interpolation",
     "fixme",
+    "too-many-positional-arguments",
+    "too-many-arguments",
 ]
 enable = ["c-extension-no-member"]
 

pylint_checkers/check_typing_imports.py

@@ -152,7 +152,7 @@ def _add_cnst_field(rel: DuckDBPyRelation) -> tuple[str, DuckDBPyRelation]:
             group_pl = entity.pl().pivot(
                 columns=[config.pivot_column],
                 values=agg_cols,
-                index=(group_cols or [const_fld]),
+                index=(group_cols or [const_fld]),  # pylint: disable=E0606
                 aggregate_function=config.agg_function,
             )
             if const_fld in group_pl.columns:

pyproject.toml

@@ -44,8 +44,8 @@ def schemas(self) -> dict[EntityName, type[BaseModel]]:
         """The per-entity schemas, as pydantic models."""
         if not self._schemas:
             for entity_name, validator in self.validators.items():
-                self._schemas[entity_name] = validator.model  # type: ignore
-        return self._schemas.copy()
+                self._schemas[entity_name] = validator.model # type: ignore # pylint: disable=E1137
+        return self._schemas.copy()  # pylint: disable=E1101
 
     @root_validator(allow_reuse=True)
     @classmethod

src/dve/core_engine/backends/implementations/duckdb/rules.py

@@ -52,7 +52,7 @@ def stringify_type(type_: Union[type, GenericAlias]) -> type:
 
     origin = get_origin(type_)
     if origin is None:  # A non-generic container type, return as-is
-        return type_
+        return type_  # type: ignore
 
     type_args = get_args(type_)
     if not type_args:

src/dve/core_engine/backends/metadata/contract.py

@@ -38,7 +38,7 @@
 
 FieldName = str
 """The name of a field within a model/schema."""
-TypeOrDef = Union[
+TypeOrDef = Union[  # pylint: disable=C0103
     TypeName, "_CallableTypeDefinition", "_ModelTypeDefinition", "_TypeAliasDefinition"
 ]
 """The name or definition of a type."""
@@ -181,7 +181,7 @@ class V1EngineConfig(BaseEngineConfig):
     @validate_arguments
     def _update_rule_store(self, rule_store: dict[RuleName, BusinessComponentSpecConfigUnion]):
         """Update the rule store rules to add/override the rules from the new store."""
-        self._rule_store_rules.update(rule_store)
+        self._rule_store_rules.update(rule_store)  # pylint: disable=E1101
 
     def _load_rule_store(self, uri: URI):
         """Load a JSON rule store from the provided URI and update the stored
@@ -198,7 +198,7 @@ def _load_rule_store(self, uri: URI):
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
         uri_prefix = self.location.rsplit("/", 1)[0]
-        for rule_store_config in self.transformations.rule_stores:
+        for rule_store_config in self.transformations.rule_stores:  # pylint: disable=E1101
             uri = joinuri(uri_prefix, rule_store_config.filename)
             self._load_rule_store(uri)
 
@@ -281,7 +281,7 @@ def _load_rules_and_vars(self) -> tuple[list[Rule], list[TemplateVariables]]:
         rules, local_variable_list = [], []
         added_rules: set[RuleName] = set()
 
-        for index, complex_rule_config in enumerate(self.transformations.complex_rules):
+        for index, complex_rule_config in enumerate(self.transformations.complex_rules):  # pylint: disable=E1101
             rule, local_params, deps = self._resolve_business_rule(complex_rule_config)
             missing_rules = deps - added_rules
             if missing_rules:
@@ -295,9 +295,9 @@ def _load_rules_and_vars(self) -> tuple[list[Rule], list[TemplateVariables]]:
 
         rule, local_params = self._create_rule(
             name="root",
-            rules=self.transformations.rules,
-            filters=self.transformations.filters,
-            post_filter_rules=self.transformations.post_filter_rules,
+            rules=self.transformations.rules,  # pylint: disable=E1101
+            filters=self.transformations.filters,  # pylint: disable=E1101
+            post_filter_rules=self.transformations.post_filter_rules,  # pylint: disable=E1101
         )
         rules.append(rule)
         local_variable_list.append(local_params)
@@ -338,14 +338,14 @@ def load_error_message_info(self, uri):
 
     def get_reference_data_config(self) -> dict[EntityName, ReferenceConfig]:  # type: ignore
         """Gets the reference data configuration from the transformations"""
-        return self.transformations.reference_data
+        return self.transformations.reference_data  # pylint: disable=E1101
 
     def get_rule_metadata(self) -> RuleMetadata:
         """Gets the rule metadata from the Engine configuration"""
         rules, local_variables = self._load_rules_and_vars()
         return RuleMetadata(
             rules=rules,
             local_variables=local_variables,
-            global_variables=self.transformations.parameters,
+            global_variables=self.transformations.parameters,  # pylint: disable=E1101
             reference_data_config=self.get_reference_data_config(),
         )

src/dve/core_engine/backends/utilities.py

@@ -137,7 +137,7 @@ def build(
             debug=debug,
             **kwargs,
         )
-        self.main_log.info(f"Output path: {self.output_prefix_uri!r}")
+        self.main_log.info(f"Output path: {self.output_prefix_uri!r}")  # pylint: disable=E1101
         return self
 
     @classmethod
@@ -155,13 +155,13 @@ def build_from_model(cls, model_str: JSONstring):
         return cls.build(**EngineRunValidation(**json.loads(model_str)).dict())
 
     def __enter__(self) -> "CoreEngine":
-        self.main_log.info("Entering pipeline context.")
+        self.main_log.info("Entering pipeline context.")  # pylint: disable=E1101
         if self._cache_dir is not None:
             raise ValueError("Pipeline already within context")
 
         self._cache_dir = TemporaryPrefix(self.cache_prefix_uri)
         self._cache_dir.__enter__()
-        self.main_log.info(f"Pipeline will cache to {self.cache_prefix!r}")
+        self.main_log.info(f"Pipeline will cache to {self.cache_prefix!r}")  # pylint: disable=E1101
         return self
 
     def __exit__(
@@ -170,14 +170,14 @@ def __exit__(
         exc_value: Optional[Exception],
         traceback: Optional[TracebackType],
     ) -> None:
-        self.main_log.info(f"Exiting pipeline context, clearing {self.cache_prefix!r}")
+        self.main_log.info(f"Exiting pipeline context, clearing {self.cache_prefix!r}")  # pylint: disable=E1101
         cache_dir = self._cache_dir
         self._cache_dir = None
 
         if cache_dir is not None:
             cache_dir.__exit__(exc_type, exc_value, traceback)
 
-        self.main_log.info("Cleared cache.")
+        self.main_log.info("Cleared cache.")  # pylint: disable=E1101
 
     @property
     def cache_prefix(self) -> URI:
@@ -198,17 +198,17 @@ def _write_entity_outputs(self, entities: SparkEntities) -> SparkEntities:
         """
         output_entities = {}
 
-        self.main_log.info(f"Writing entities to the output location: {self.output_prefix_uri}")
+        self.main_log.info(f"Writing entities to the output location: {self.output_prefix_uri}")  # pylint: disable=E1101
         for entity_name, entity in entities.items():
             entity = entity.drop(RECORD_INDEX_COLUMN_NAME)
 
-            self.main_log.info(f"Entity: {entity_name} {type(entity)}")
+            self.main_log.info(f"Entity: {entity_name} {type(entity)}")  # pylint: disable=E1101
 
             output_uri = joinuri(self.output_prefix_uri, entity_name)
             if get_resource_exists(output_uri):
-                self.main_log.info(f"{output_uri} already exists - will be overwritten")
+                self.main_log.info(f"{output_uri} already exists - will be overwritten")  # pylint: disable=E1101
 
-            self.main_log.info(f"+ Writing parquet output to {output_uri!r}")
+            self.main_log.info(f"+ Writing parquet output to {output_uri!r}")  # pylint: disable=E1101
             entity.write.mode("overwrite").parquet(output_uri)
             spark_session = SparkSession.builder.getOrCreate()
             output_entities[entity_name] = spark_session.read.format("parquet").load(
@@ -228,7 +228,7 @@ def _write_outputs(self, entities: SparkEntities) -> SparkEntities:
 
     def _show_available_entities(self, entities: SparkEntities, *, verbose: bool = False) -> None:
         """Print current entities."""
-        self.main_log.info("Displaying available dataframes in this run:")
+        self.main_log.info("Displaying available dataframes in this run:")  # pylint: disable=E1101
 
         for entity_name, entity in entities.items():
             # FIXME: Currently a print statement because log messages