[stubgen] Introduce an object-oriented design for C extension stub generation

Author: chadrik

docs/source/stubgen.rst

@@ -127,12 +127,22 @@ alter the default behavior:
     unwanted side effects, such as the running of tests. Stubgen tries to skip test
     modules even without this option, but this does not always work.
 
-.. option:: --parse-only
+.. option:: --no-analysis
 
     Don't perform semantic analysis of source files. This may generate
     worse stubs -- in particular, some module, class, and function aliases may
     be represented as variables with the ``Any`` type. This is generally only
-    useful if semantic analysis causes a critical mypy error.
+    useful if semantic analysis causes a critical mypy error.  Does not apply to
+    C extension modules.  Incompatible with :option:`--inspect-mode`.
+
+.. option:: --inspect-mode
+
+    Import and inspect modules instead of parsing source code. This is the default
+    behavior for c modules and pyc-only packages.  The flag is useful to force
+    inspection for pure python modules that make use of dynamically generated
+    members that would otherwiswe be omitted when using the default behavior of
+    code parsing.  Implies :option:`--no-analysis` as analysis requires source
+    code.
 
 .. option:: --doc-dir PATH
 

mypy/moduleinspect.py

@@ -39,6 +39,10 @@ def is_c_module(module: ModuleType) -> bool:
     return os.path.splitext(module.__dict__["__file__"])[-1] in [".so", ".pyd", ".dll"]
 
 
+def is_pyc_only(file: str | None) -> bool:
+    return bool(file and file.endswith(".pyc") and not os.path.exists(file[:-1]))
+
+
 class InspectError(Exception):
     pass
 

mypy/stubdoc.py

@@ -8,6 +8,7 @@
 
 import contextlib
 import io
+import keyword
 import re
 import tokenize
 from typing import Any, Final, MutableMapping, MutableSequence, NamedTuple, Sequence, Tuple
@@ -35,12 +36,16 @@ class ArgSig:
 
     def __init__(self, name: str, type: str | None = None, default: bool = False):
         self.name = name
-        if type and not is_valid_type(type):
-            raise ValueError("Invalid type: " + type)
         self.type = type
         # Does this argument have a default value?
         self.default = default
 
+    def is_star_arg(self) -> bool:
+        return self.name.startswith("*") and not self.name.startswith("**")
+
+    def is_star_kwarg(self) -> bool:
+        return self.name.startswith("**")
+
     def __repr__(self) -> str:
         return "ArgSig(name={}, type={}, default={})".format(
             repr(self.name), repr(self.type), repr(self.default)
@@ -59,7 +64,68 @@ def __eq__(self, other: Any) -> bool:
 class FunctionSig(NamedTuple):
     name: str
     args: list[ArgSig]
-    ret_type: str
+    ret_type: str | None
+
+    def is_special_method(self) -> bool:
+        return bool(
+            self.name.startswith("__")
+            and self.name.endswith("__")
+            and self.args
+            and self.args[0].name in ("self", "cls")
+        )
+
+    def has_catchall_args(self) -> bool:
+        """Return if this signature has catchall args: (*args, **kwargs)"""
+        if self.args and self.args[0].name in ("self", "cls"):
+            args = self.args[1:]
+        else:
+            args = self.args
+        return (
+            len(args) == 2
+            and all(a.type in (None, "Any", "typing.Any") for a in args)
+            and args[0].is_star_arg()
+            and args[1].is_star_kwarg()
+        )
+
+    def is_identity(self) -> bool:
+        """Return if this signature is the catchall identity: (*args, **kwargs) -> Any"""
+        return self.has_catchall_args() and self.ret_type in (None, "Any", "typing.Any")
+
+    def format_sig(self, any_val: str | None = None, suffix: str = ": ...") -> str:
+        args: list[str] = []
+        for arg in self.args:
+            arg_def = arg.name
+
+            if arg_def in keyword.kwlist:
+                arg_def = "_" + arg_def
+
+            if (
+                arg.type is None
+                and any_val is not None
+                and arg.name not in ("self", "cls")
+                and not arg.name.startswith("*")
+            ):
+                arg_type: str | None = any_val
+            else:
+                arg_type = arg.type
+            if arg_type:
+                arg_def += ": " + arg_type
+                if arg.default:
+                    arg_def += " = ..."
+
+            elif arg.default:
+                arg_def += "=..."
+
+            args.append(arg_def)
+
+        retfield = ""
+        ret_type = self.ret_type if self.ret_type else any_val
+        if ret_type is not None:
+            retfield = " -> " + ret_type
+
+        return "def {name}({args}){ret}{suffix}".format(
+            name=self.name, args=", ".join(args), ret=retfield, suffix=suffix
+        )
 
 
 # States of the docstring parser.
@@ -176,17 +242,17 @@ def add_token(self, token: tokenize.TokenInfo) -> None:
 
             # arg_name is empty when there are no args. e.g. func()
             if self.arg_name:
-                try:
+                if self.arg_type and not is_valid_type(self.arg_type):
+                    # wrong type, use Any
+                    self.args.append(
+                        ArgSig(name=self.arg_name, type=None, default=bool(self.arg_default))
+                    )
+                else:
                     self.args.append(
                         ArgSig(
                             name=self.arg_name, type=self.arg_type, default=bool(self.arg_default)
                         )
                     )
-                except ValueError:
-                    # wrong type, use Any
-                    self.args.append(
-                        ArgSig(name=self.arg_name, type=None, default=bool(self.arg_default))
-                    )
             self.arg_name = ""
             self.arg_type = None
             self.arg_default = None
@@ -240,7 +306,7 @@ def args_kwargs(signature: FunctionSig) -> bool:
 
 
 def infer_sig_from_docstring(docstr: str | None, name: str) -> list[FunctionSig] | None:
-    """Convert function signature to list of TypedFunctionSig
+    """Convert function signature to list of FunctionSig
 
     Look for function signatures of function in docstring. Signature is a string of
     the format <function_name>(<signature>) -> <return type> or perhaps without