chore: Run mypy on the EDK (#49)

* chore: Run mypy on the EDK

* Add quotes to `3.10`

.github/workflows/test.yml

@@ -36,3 +36,27 @@ jobs:
       - name: Test with pytest
         run: |
           poetry run pytest
+
+  mypy:
+    name: Static type checking with mypy
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+
+      - name: Install Poetry
+        run: |
+          pipx install poetry
+          poetry --version
+
+      - name: Install dependencies
+        run: |
+          poetry env use 3.10
+          poetry install
+
+      - name: Run mypy
+        run: |
+          poetry run mypy --namespace-packages -p meltano.edk

meltano/edk/extension.py

@@ -76,7 +76,7 @@ def describe(self) -> models.Describe:
         """
         pass
 
-    def describe_formatted(
+    def describe_formatted(  # type: ignore[return]
         self, output_format: DescribeFormat = DescribeFormat.text
     ) -> str:
         """Return a formatted description of the extensions commands and capabilities.

meltano/edk/logging.py

@@ -4,6 +4,7 @@
 import logging
 import os
 import sys
+from typing import Callable
 
 import structlog
 
@@ -18,7 +19,36 @@
 DEFAULT_LEVEL = "info"
 
 
-def parse_log_level(log_level: dict[str, int]) -> int:
+def strtobool(val: str) -> bool:
+    """Convert a string representation of truth to true (1) or false (0).
+
+    True values are 'y', 'yes', 't', 'true', 'on', and '1'; false values
+    are 'n', 'no', 'f', 'false', 'off', and '0'.  Raises ValueError if
+    'val' is anything else.
+
+    Case is ignored in string comparisons.
+
+    Re-implemented from distutils.util.strtobool to avoid importing distutils.
+
+    Args:
+        val: The string to convert to a boolean.
+
+    Returns:
+        True if the string represents a truthy value, False otherwise.
+
+    Raises:
+        ValueError: If the string is not a valid representation of a boolean.
+    """
+    val = val.lower()
+    if val in {"y", "yes", "t", "true", "on", "1"}:
+        return True
+    elif val in {"n", "no", "f", "false", "off", "0"}:
+        return False
+
+    raise ValueError(f"invalid truth value {val!r}")
+
+
+def parse_log_level(log_level: str) -> int:
     """Parse a level descriptor into an logging level.
 
     Args:
@@ -44,12 +74,18 @@ def default_logging_config(
         levels: include levels in the log.
         json_format: if True, use JSON format, otherwise use human-readable format.
     """
-    processors = []
+    processors: list[Callable] = []
     if timestamps:
         processors.append(structlog.processors.TimeStamper(fmt="iso"))
     if levels:
         processors.append(structlog.processors.add_log_level)
 
+    renderer: structlog.processors.JSONRenderer | structlog.dev.ConsoleRenderer = (
+        structlog.processors.JSONRenderer()
+        if json_format
+        else structlog.dev.ConsoleRenderer(colors=False)
+    )
+
     processors.extend(
         [
             # If log level is too low, abort pipeline and throw away log entry.
@@ -65,9 +101,7 @@ def default_logging_config(
             structlog.processors.UnicodeDecoder(),
             structlog.processors.ExceptionPrettyPrinter(),
             # Render the final event dict as JSON.
-            structlog.processors.JSONRenderer()
-            if json_format
-            else structlog.dev.ConsoleRenderer(colors=False),
+            renderer,
         ]
     )
 
@@ -100,13 +134,13 @@ def pass_through_logging_config() -> None:
     and MELTANO_LOG_JSON env vars.
     """
     log_level = os.environ.get("LOG_LEVEL", "INFO")
-    log_timestamps = os.environ.get("LOG_TIMESTAMPS", False)
-    log_levels = os.environ.get("LOG_LEVELS", False)
-    meltano_log_json = os.environ.get("MELTANO_LOG_JSON", False)
+    log_timestamps = os.environ.get("LOG_TIMESTAMPS", "False")
+    log_levels = os.environ.get("LOG_LEVELS", "False")
+    meltano_log_json = os.environ.get("MELTANO_LOG_JSON", "False")
 
     default_logging_config(
         level=parse_log_level(log_level),
-        timestamps=log_timestamps,
-        levels=log_levels,
-        json_format=meltano_log_json,
+        timestamps=strtobool(log_timestamps),
+        levels=strtobool(log_levels),
+        json_format=strtobool(meltano_log_json),
     )

meltano/edk/process.py

@@ -4,11 +4,12 @@
 import asyncio
 import os
 import subprocess
-from typing import IO, Any
+from typing import IO, Any, Union
 
 import structlog
 
 log = structlog.get_logger()
+_ExecArg = Union[str, bytes]
 
 
 def log_subprocess_error(
@@ -37,8 +38,8 @@ class Invoker:
     def __init__(
         self,
         bin: str,
-        cwd: str = None,
-        env: dict[str, any] | None = None,
+        cwd: str | None = None,
+        env: dict[str, Any] | None = None,
     ) -> None:
         """Minimal invoker for running subprocesses.
 
@@ -53,7 +54,7 @@ def __init__(
 
     def run(
         self,
-        *args: str | bytes | os.PathLike[str] | os.PathLike[bytes],
+        *args: _ExecArg,
         stdout: None | int | IO = subprocess.PIPE,
         stderr: None | int | IO = subprocess.PIPE,
         text: bool = True,
@@ -113,9 +114,9 @@ async def _log_stdio(reader: asyncio.streams.StreamReader) -> None:
     async def _exec(
         self,
         sub_command: str | None = None,
-        *args: str | bytes | os.PathLike[str] | os.PathLike[bytes],
+        *args: _ExecArg,
     ) -> asyncio.subprocess.Process:
-        popen_args = []
+        popen_args: list[_ExecArg] = []
         if sub_command:
             popen_args.append(sub_command)
         if args:
@@ -130,9 +131,16 @@ async def _exec(
             env=self.popen_env,
         )
 
+        streams: list[asyncio.streams.StreamReader] = []
+
+        if p.stderr:
+            streams.append(p.stderr)
+
+        if p.stdout:
+            streams.append(p.stdout)
+
         results = await asyncio.gather(
-            asyncio.create_task(self._log_stdio(p.stderr)),
-            asyncio.create_task(self._log_stdio(p.stdout)),
+            *[asyncio.create_task(self._log_stdio(stream)) for stream in streams],
             return_exceptions=True,
         )
 
@@ -146,7 +154,7 @@ async def _exec(
     def run_and_log(
         self,
         sub_command: str | None = None,
-        *args: str | bytes | os.PathLike[str] | os.PathLike[bytes],
+        *args: _ExecArg,
     ) -> None:
         """Run a subprocess and stream the output to the logger.
 

pyproject.toml

@@ -78,6 +78,7 @@ flake8-docstrings = "^1.6.0"
 
 [tool.poetry.group.dev.dependencies]
 copier = "^6.2.0"
+types-pyyaml = "^6.0.12.2"
 
 [tool.isort]
 profile = "black"