ci: Streamline CI tools and workflows (#65)

* ci: Streamline CI tools

* style: Fix code formatting

.flake8

@@ -1,5 +1,5 @@
 [flake8]
 ignore = D105,D203,D213,W503
 docstring-convention = google
-max-line-length = 120
-max-complexity = 10
+max-line-length = 88
+max-complexity = 15

.github/workflows/release.yml

@@ -37,4 +37,4 @@ jobs:
     - name: Deploy to PyPI
       run: |
         poetry publish -r testpypi -u "__token__" -p "${{ secrets.TEST_PYPI_TOKEN }}"
-        poetry publish -u "__token__" -p "${{ secrets.PYPI_TOKEN }}"
+        poetry publish -u "__token__" -p "${{ secrets.PYPI_TOKEN }}"

.github/workflows/test.yml

@@ -37,3 +37,6 @@ jobs:
     - name: Test with pytest
       run: |
         poetry run pytest
+    - name: Lint with tox
+      run: |
+        poetry run tox -e lint

.pre-commit-config.yaml

@@ -0,0 +1,34 @@
+ci:
+  autofix_prs: false
+  autoupdate_schedule: weekly
+  autoupdate_commit_msg: 'chore: pre-commit autoupdate'
+
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.5.0
+  hooks:
+  - id: check-json
+  - id: check-toml
+    exclude: |
+        (?x)^(
+            copier_template/.*/pyproject.toml
+        )$
+  - id: end-of-file-fixer
+    exclude: (copier_template/.*|docs/.*|samples/.*\.json)
+  - id: trailing-whitespace
+
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  rev: v0.2.1
+  hooks:
+  - id: ruff
+    args: [--fix]
+  - id: ruff-format
+
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: 'v1.8.0'
+  hooks:
+  - id: mypy
+    exclude: tests
+    additional_dependencies:
+    - types-sqlalchemy
+    - types-jsonschema

.vscode/extensions.json

@@ -5,4 +5,4 @@
     "ms-python.flake8",
     "ms-python.black-formatter"
   ]
-}
+}

.vscode/settings.json

@@ -1,3 +1,3 @@
 {
     "editor.defaultFormatter": "ms-python.black-formatter"
-}
+}

pyproject.toml

@@ -2,12 +2,17 @@
 name = "tap-ibm-db2"
 version = "0.0.0"
 description = "`Tap-DB2` is a Singer tap for IBM DB2 data sources."
-readme = "README.md"
 authors = ["Daniel Purtov"]
+license = "MIT"
+readme = "README.md"
+homepage = "https://meltano.com"
+repository = "https://github.com/danielptv/tap-db2"
 keywords = [
-    "ELT",
+    "DB2",
     "IBM DB2",
-    "DB2"
+    "ELT",
+    "Meltano",
+    "Meltano SDK"
 ]
 classifiers = [
     "Intended Audience :: Developers",
@@ -19,62 +24,61 @@ classifiers = [
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: Implementation :: CPython",
 ]
-license = "MIT"
 packages = [
     { include = "tap_db2" },
 ]
 
 [tool.poetry.dependencies]
 python = ">=3.8,<3.12"
-singer-sdk = { version=">=0.31.1,<0.36.0" }
+singer-sdk = "0.35.1"
 ibm-db-sa = "0.4.0"
 sqlalchemy = "2.0.27"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "8.0.0"
-singer-sdk = { version=">=0.31.1,<0.36.0", extras = ["testing"] }
-black = "24.2.0"
-deptry = "0.12.0"
 faker = "23.2.1"
-isort = "5.13.2"
 tox = "4.12.1"
+mypy = "1.8.0"
+ruff = "0.2.1"
+types-sqlalchemy = "1.4.53.38"
+types-jsonschema = "^4.21.0.20240118"
 
 [tool.mypy]
-python_version = "3.9"
-warn_unused_configs = true
-plugins = "sqlmypy"
-
-[tool.black]
-line-length = 120
-
-[tool.ruff]
-ignore = [
-    "ANN101",  # missing-type-self
-    "ANN102",  # missing-type-cls
-]
-select = ["ALL"]
-src = ["tap_db2"]
-target-version = "py37"
-
-
-[tool.ruff.flake8-annotations]
-allow-star-arg-any = true
-
-[tool.ruff.isort]
-known-first-party = ["tap_db2"]
-
-[tool.ruff.pydocstyle]
-convention = "google"
+exclude = "tests"
 
 [build-system]
 requires = ["poetry-core==1.8.1", "poetry-dynamic-versioning==1.2.0"]
 build-backend = "poetry_dynamic_versioning.backend"
 
+[tool.poetry.scripts]
+# CLI declaration
+tap-db2 = 'tap_db2.tap:TapDB2.cli'
+
 [tool.poetry-dynamic-versioning]
 enable = true
 vcs = "git"
 style = "semver"
 
-[tool.poetry.scripts]
-# CLI declaration
-tap-db2 = 'tap_db2.tap:TapDB2.cli'
+[tool.ruff]
+target-version = "py38"
+
+[tool.ruff.lint]
+select = [
+  "F",   # Pyflakes
+  "W",   # pycodestyle warnings
+  "E",   # pycodestyle errors
+  "I",   # isort
+  "N",   # pep8-naming
+  "D",   # pydocsyle
+  "ICN", # flake8-import-conventions
+  "RUF", # ruff
+]
+
+[tool.ruff.lint.flake8-import-conventions]
+banned-from = ["sqlalchemy"]
+
+[tool.ruff.lint.flake8-import-conventions.extend-aliases]
+sqlalchemy = "sa"
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"

tap_db2/connector.py

@@ -5,10 +5,11 @@
 import re
 import typing as t
 
-import sqlalchemy  # noqa: TCH002
+import sqlalchemy as sa
 from singer_sdk import SQLConnector
 from singer_sdk import typing as th
 from sqlalchemy.engine import Engine
+from sqlalchemy.types import TypeEngine
 
 SUPPLIED_USER_TABLES_PATTERN = r"^(DSN_|PLAN_TABLE)"
 
@@ -28,37 +29,36 @@ def get_sqlalchemy_url(self, config: dict) -> str:
         connection_url = (
             f"ibm_db_sa://{config['user']}:"
             f"{config['password']}@{config['host']}"
-            f":{str(config['port'])}/"
+            f":{config['port']!s}/"
             f"{config['database']};"
         )
         if "encryption" in config:
             connection_url += "SECURITY=SSL;"
             if "ssl_server_certificate" in config["encryption"]:
-                connection_url += f"SSLServerCertificate={config['encryption']['ssl_server_certificate']};"
+                connection_url += f"SSLServerCertificate={config['encryption']['ssl_server_certificate']};"  # noqa: E501
             if "ssl_client_key_store_db" in config["encryption"]:
-                connection_url += f"SSLClientKeyStoreDB={config['encryption']['ssl_client_key_store_db']['database']};"
+                connection_url += f"SSLClientKeyStoreDB={config['encryption']['ssl_client_key_store_db']['database']};"  # noqa: E501
                 if "password" in config["encryption"]["ssl_client_key_store_db"]:
-                    connection_url += (
-                        f"SSLClientKeyStoreDBPassword={config['encryption']['ssl_client_key_store_db']['password']};"
-                    )
+                    connection_url += f"SSLClientKeyStoreDBPassword={config['encryption']['ssl_client_key_store_db']['password']};"  # noqa: E501
                 if "key_stash" in config["encryption"]["ssl_client_key_store_db"]:
-                    connection_url += (
-                        f"SSLClientKeyStash={config['encryption']['ssl_client_key_store_db']['key_stash']};"
-                    )
+                    connection_url += f"SSLClientKeyStash={config['encryption']['ssl_client_key_store_db']['key_stash']};"  # noqa: E501
         if "connection_parameters" in config:
             for key, value in config["connection_parameters"].items():
                 connection_url += f"{key}={value};"
         return connection_url
 
     def create_engine(self) -> Engine:
+        """Creates and returns a new engine."""
         if "sqlalchemy_execution_options" in self.config:
-            sqlalchemy_connection_kwargs = {"execution_options": self.config["sqlalchemy_execution_options"]}
-            return sqlalchemy.create_engine(self.sqlalchemy_url, **sqlalchemy_connection_kwargs)
-        return sqlalchemy.create_engine(self.sqlalchemy_url)
+            sqlalchemy_connection_kwargs = {
+                "execution_options": self.config["sqlalchemy_execution_options"]
+            }
+            return sa.create_engine(self.sqlalchemy_url, **sqlalchemy_connection_kwargs)
+        return sa.create_engine(self.sqlalchemy_url)
 
     @staticmethod
     def to_jsonschema_type(
-        sql_type: str | sqlalchemy.types.TypeEngine | type[sqlalchemy.types.TypeEngine] | t.Any,  # noqa: ANN401
+        sql_type: str | TypeEngine | type[TypeEngine] | t.Any,
     ) -> dict:
         """Return a JSON Schema representation of the provided type.
 
@@ -69,7 +69,7 @@ def to_jsonschema_type(
             The JSON Schema representation of the provided type.
         """
         # Map DATE to date-time in JSON Schema
-        if isinstance(sql_type, sqlalchemy.DATE):
+        if isinstance(sql_type, sa.DATE):
             return th.DateTimeType.type_dict
 
         return SQLConnector.to_jsonschema_type(sql_type)
@@ -82,24 +82,36 @@ def discover_catalog_entries(self) -> list[dict]:
         """
         result: list[dict] = []
         engine = self._engine
-        inspected = sqlalchemy.inspect(engine)
+        inspected = sa.inspect(engine)
         for schema_name in self.get_schema_names(engine, inspected):
             # Iterate through each table and view
             for table_name, is_view in self.get_object_names(
                 engine,
                 inspected,
                 schema_name,
             ):
-                if is_view and "ignore_views" in self.config and self.config["ignore_views"]:
+                if (
+                    is_view
+                    and "ignore_views" in self.config
+                    and self.config["ignore_views"]
+                ):
                     continue
-                if not re.match(SUPPLIED_USER_TABLES_PATTERN, table_name, re.IGNORECASE) or (
-                    "ignore_supplied_tables" in self.config and not self.config["ignore_supplied_tables"]
+                if not re.match(
+                    SUPPLIED_USER_TABLES_PATTERN, table_name, re.IGNORECASE
+                ) or (
+                    "ignore_supplied_tables" in self.config
+                    and not self.config["ignore_supplied_tables"]
                 ):
                     # Filter by schema
                     # Connection parameter 'CURRENTSCHEMA=mySchema;' doesn't work
                     # https://www.ibm.com/support/pages/525-error-nullidsysstat-package-when-trying-set-current-schema-against-db2-zos-database
-                    target_schema = self.config["schema"] if "schema" in self.config else None
-                    if target_schema is None or target_schema.strip().lower() == schema_name.strip().lower():
+                    target_schema = (
+                        self.config["schema"] if "schema" in self.config else None
+                    )
+                    if (
+                        target_schema is None
+                        or target_schema.strip().lower() == schema_name.strip().lower()
+                    ):
                         catalog_entry = self.discover_catalog_entry(
                             engine,
                             inspected,