chore(mypy): make python codebase strictly typed (#554)

* feat: use mypy strict mode and exclude tests

* chore(mypy): make python codebase strictly typed

* fix: fix unbound variable and already defined error

* refactor: update all deprecated usage of `Type`

Author: lemorage

pyproject.toml

@@ -33,5 +33,6 @@ dev = ["ruff"]
 
 [tool.mypy]
 python_version = "3.11"
-# Disable for not as we have missing type annotations. See https://github.com/cocoindex-io/cocoindex/issues/539
-#   strict = true
+strict = true
+files = "python/cocoindex"
+exclude = "python/cocoindex/tests"

python/cocoindex/auth_registry.py

@@ -24,6 +24,6 @@ def add_auth_entry(key: str, value: T) -> AuthEntryReference[T]:
     return AuthEntryReference(key)
 
 
-def ref_auth_entry(key: str) -> AuthEntryReference:
+def ref_auth_entry(key: str) -> AuthEntryReference[T]:
     """Reference an auth entry by its key."""
     return AuthEntryReference(key)

python/cocoindex/cli.py

@@ -10,6 +10,7 @@
 from rich.console import Console
 from rich.panel import Panel
 from rich.table import Table
+from typing import Any
 
 from . import flow, lib, setting
 from .setup import sync_setup, drop_setup, flow_names_with_setup, apply_setup_changes
@@ -127,7 +128,7 @@ def _load_user_app(app_target: str) -> types.ModuleType:
     default=None,
     show_default=False,
 )
-def cli(env_file: str | None):
+def cli(env_file: str | None) -> None:
     """
     CLI for Cocoindex.
     """
@@ -147,7 +148,7 @@ def cli(env_file: str | None):
 
 @cli.command()
 @click.argument("app_target", type=str, required=False)
-def ls(app_target: str | None):
+def ls(app_target: str | None) -> None:
     """
     List all flows.
 
@@ -199,7 +200,7 @@ def ls(app_target: str | None):
     "--color/--no-color", default=True, help="Enable or disable colored output."
 )
 @click.option("--verbose", is_flag=True, help="Show verbose output with full details.")
-def show(app_flow_specifier: str, color: bool, verbose: bool):
+def show(app_flow_specifier: str, color: bool, verbose: bool) -> None:
     """
     Show the flow spec and schema.
 
@@ -236,7 +237,7 @@ def show(app_flow_specifier: str, color: bool, verbose: bool):
 
 @cli.command()
 @click.argument("app_target", type=str)
-def setup(app_target: str):
+def setup(app_target: str) -> None:
     """
     Check and apply backend setup changes for flows, including the internal and target storage
     (to export).
@@ -274,7 +275,7 @@ def setup(app_target: str):
     "even if not defined in the current process."
     "If used, APP_TARGET and any listed flow names are ignored.",
 )
-def drop(app_target: str | None, flow_name: tuple[str, ...], drop_all: bool):
+def drop(app_target: str | None, flow_name: tuple[str, ...], drop_all: bool) -> None:
     """
     Drop the backend setup for flows.
 
@@ -355,7 +356,7 @@ def drop(app_target: str | None, flow_name: tuple[str, ...], drop_all: bool):
     default=False,
     help="Avoid printing anything to the standard output, e.g. statistics.",
 )
-def update(app_flow_specifier: str, live: bool, quiet: bool):
+def update(app_flow_specifier: str, live: bool, quiet: bool) -> Any:
     """
     Update the index to reflect the latest data from data sources.
 
@@ -390,7 +391,9 @@ def update(app_flow_specifier: str, live: bool, quiet: bool):
     default=True,
     help="Use already-cached intermediate data if available.",
 )
-def evaluate(app_flow_specifier: str, output_dir: str | None, cache: bool = True):
+def evaluate(
+    app_flow_specifier: str, output_dir: str | None, cache: bool = True
+) -> None:
     """
     Evaluate the flow and dump flow outputs to files.
 
@@ -473,7 +476,7 @@ def server(
     cors_origin: str | None,
     cors_cocoindex: bool,
     cors_local: int | None,
-):
+) -> None:
     """
     Start a HTTP server providing REST APIs.
 

python/cocoindex/convert.py

@@ -41,7 +41,7 @@ def encode_engine_value(value: Any) -> Any:
 def make_engine_value_decoder(
     field_path: list[str],
     src_type: dict[str, Any],
-    dst_annotation,
+    dst_annotation: Any,
 ) -> Callable[[Any], Any]:
     """
     Make a decoder from an engine value to a Python value.
@@ -102,7 +102,7 @@ def make_engine_value_decoder(
                 field_path, engine_fields_schema[1:], elem_type_info.struct_type
             )
 
-            def decode(value):
+            def decode(value: Any) -> Any | None:
                 if value is None:
                     return None
                 return {key_decoder(v[0]): value_decoder(v[1:]) for v in value}
@@ -111,7 +111,7 @@ def decode(value):
                 field_path, engine_fields_schema, elem_type_info.struct_type
             )
 
-            def decode(value):
+            def decode(value: Any) -> Any | None:
                 if value is None:
                     return None
                 return [elem_decoder(v) for v in value]
@@ -129,7 +129,7 @@ def _make_engine_struct_value_decoder(
     field_path: list[str],
     src_fields: list[dict[str, Any]],
     dst_struct_type: type,
-) -> Callable[[list], Any]:
+) -> Callable[[list[Any]], Any]:
     """Make a decoder from an engine field values to a Python value."""
 
     src_name_to_idx = {f["name"]: i for i, f in enumerate(src_fields)}
@@ -156,7 +156,7 @@ def _make_engine_struct_value_decoder(
 
     def make_closure_for_value(
         name: str, param: inspect.Parameter
-    ) -> Callable[[list], Any]:
+    ) -> Callable[[list[Any]], Any]:
         src_idx = src_name_to_idx.get(name)
         if src_idx is not None:
             field_path.append(f".{name}")