[PATCH v5 06/13] scripts: generate_rust_analyzer.py: add type hints

[Tamir Duberstein <tamird@gmail.com>]

Python type hints allow static analysis tools like mypy to detect type
errors during development, improving the developer experience.

Python type hints have been present in the kernel since 2019 at the
latest; see commit 6ebf5866f2e8 ("kunit: tool: add Python wrappers for
running KUnit tests").

Add a subclass of `argparse.Namespace` to get type checking on the CLI
arguments. Move parsing of `cfg` out of `generate_crates` to reduce the
number of variables in scope with `cfg` in their name. Use a defaultdict
to avoid `.get("key", [])`.

Run `mypy --strict scripts/generate_rust_analyzer.py --python-version
3.8` to verify. Note that `mypy` no longer supports python < 3.8.

Tested-by: Daniel Almeida <daniel.almeida@collabora.com>
Signed-off-by: Tamir Duberstein <tamird@gmail.com>
---
 scripts/generate_rust_analyzer.py | 166 +++++++++++++++++++++++++-------------
 1 file changed, 109 insertions(+), 57 deletions(-)

diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py
index 80eb21c0d082..b37d8345486a 100755
--- a/scripts/generate_rust_analyzer.py
+++ b/scripts/generate_rust_analyzer.py
@@ -10,16 +10,48 @@ import os
 import pathlib
 import subprocess
 import sys
+from collections import defaultdict
+from typing import DefaultDict, Dict, Iterable, List, Literal, Optional, TypedDict
 
-def args_crates_cfgs(cfgs):
-    crates_cfgs = {}
-    for cfg in cfgs:
-        crate, vals = cfg.split("=", 1)
-        crates_cfgs[crate] = vals.replace("--cfg", "").split()
 
-    return crates_cfgs
+class Dependency(TypedDict):
+    crate: int
+    name: str
 
-def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
+
+class Source(TypedDict):
+    include_dirs: List[str]
+    exclude_dirs: List[str]
+
+
+class Crate(TypedDict):
+    display_name: str
+    root_module: str
+    is_workspace_member: bool
+    deps: List[Dependency]
+    cfg: List[str]
+    edition: Literal["2021"]
+    env: Dict[str, str]
+
+
+# `NotRequired` fields on `Crate` would be better but `NotRequired` was added in 3.11.
+class ProcMacroCrate(Crate):
+    is_proc_macro: Literal[True]
+    proc_macro_dylib_path: Optional[str]  # `pathlib.Path` is not JSON serializable.
+
+
+# `NotRequired` fields on `Crate` would be better but `NotRequired` was added in 3.11.
+class CrateWithGenerated(Crate):
+    source: Optional[Source]
+
+
+def generate_crates(
+    srctree: pathlib.Path,
+    objtree: pathlib.Path,
+    sysroot_src: pathlib.Path,
+    external_src: pathlib.Path,
+    crates_cfgs: DefaultDict[str, List[str]],
+) -> List[Crate]:
     # Generate the configuration list.
     cfg = []
     with open(objtree / "include" / "generated" / "rustc_cfg") as fd:
@@ -31,17 +63,16 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
     # Now fill the crates list -- dependencies need to come first.
     #
     # Avoid O(n^2) iterations by keeping a map of indexes.
-    crates = []
-    crates_indexes = {}
-    crates_cfgs = args_crates_cfgs(cfgs)
+    crates: List[Crate] = []
+    crates_indexes: Dict[str, int] = {}
 
     def build_crate(
-        display_name,
-        root_module,
-        deps,
-        cfg=[],
-        is_workspace_member=True,
-    ):
+        display_name: str,
+        root_module: pathlib.Path,
+        deps: List[str],
+        cfg: List[str] = [],
+        is_workspace_member: bool = True,
+    ) -> Crate:
         return {
             "display_name": display_name,
             "root_module": str(root_module),
@@ -51,36 +82,30 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
             "edition": "2021",
             "env": {
                 "RUST_MODFILE": "This is only for rust-analyzer"
-            }
+            },
         }
 
-    def register_crate(crate):
+    def register_crate(crate: Crate) -> None:
         crates_indexes[crate["display_name"]] = len(crates)
         crates.append(crate)
 
     def append_crate(
-        display_name,
-        root_module,
-        deps,
-        cfg=[],
-        is_workspace_member=True,
-    ):
+        display_name: str,
+        root_module: pathlib.Path,
+        deps: List[str],
+        cfg: List[str] = [],
+        is_workspace_member: bool = True,
+    ) -> None:
         register_crate(
-            build_crate(
-                display_name,
-                root_module,
-                deps,
-                cfg,
-                is_workspace_member,
-            )
+            build_crate(display_name, root_module, deps, cfg, is_workspace_member)
         )
 
     def append_proc_macro_crate(
-        display_name,
-        root_module,
-        deps,
-        cfg=[],
-    ):
+        display_name: str,
+        root_module: pathlib.Path,
+        deps: List[str],
+        cfg: List[str] = [],
+    ) -> None:
         crate = build_crate(display_name, root_module, deps, cfg)
         proc_macro_dylib_name = (
             subprocess.check_output(
@@ -99,7 +124,7 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
             .decode("utf-8")
             .strip()
         )
-        proc_macro_crate = {
+        proc_macro_crate: ProcMacroCrate = {
             **crate,
             "is_proc_macro": True,
             "proc_macro_dylib_path": f"{objtree}/rust/{proc_macro_dylib_name}",
@@ -107,10 +132,10 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
         register_crate(proc_macro_crate)
 
     def append_sysroot_crate(
-        display_name,
-        deps,
-        cfg=[],
-    ):
+        display_name: str,
+        deps: List[str],
+        cfg: List[str] = [],
+    ) -> None:
         append_crate(
             display_name,
             sysroot_src / display_name / "src" / "lib.rs",
@@ -122,7 +147,7 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
     # NB: sysroot crates reexport items from one another so setting up our transitive dependencies
     # here is important for ensuring that rust-analyzer can resolve symbols. The sources of truth
     # for this dependency graph are `(sysroot_src / crate / "Cargo.toml" for crate in crates)`.
-    append_sysroot_crate("core", [], cfg=crates_cfgs.get("core", []))
+    append_sysroot_crate("core", [], cfg=crates_cfgs["core"])
     append_sysroot_crate("alloc", ["core"])
     append_sysroot_crate("std", ["alloc", "core"])
     append_sysroot_crate("proc_macro", ["core", "std"])
@@ -160,9 +185,9 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
     )
 
     def append_crate_with_generated(
-        display_name,
-        deps,
-    ):
+        display_name: str,
+        deps: List[str],
+    ) -> None:
         crate = build_crate(
             display_name,
             srctree / "rust" / display_name / "lib.rs",
@@ -170,20 +195,23 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
             cfg=cfg,
         )
         crate["env"]["OBJTREE"] = str(objtree.resolve(True))
-        crate["source"] = {
-            "include_dirs": [
-                str(srctree / "rust" / display_name),
-                str(objtree / "rust")
-            ],
-            "exclude_dirs": [],
+        crate_with_generated: CrateWithGenerated = {
+            **crate,
+            "source": {
+                "include_dirs": [
+                    str(srctree / "rust" / display_name),
+                    str(objtree / "rust")
+                ],
+                "exclude_dirs": [],
+            }
         }
-        register_crate(crate)
+        register_crate(crate_with_generated)
 
     append_crate_with_generated("bindings", ["core"])
     append_crate_with_generated("uapi", ["core"])
     append_crate_with_generated("kernel", ["core", "macros", "build_error", "bindings", "pin_init", "uapi"])
 
-    def is_root_crate(build_file, target):
+    def is_root_crate(build_file: pathlib.Path, target: str) -> bool:
         try:
             return f"{target}.o" in open(build_file).read()
         except FileNotFoundError:
@@ -192,7 +220,9 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
     # Then, the rest outside of `rust/`.
     #
     # We explicitly mention the top-level folders we want to cover.
-    extra_dirs = map(lambda dir: srctree / dir, ("samples", "drivers"))
+    extra_dirs: Iterable[pathlib.Path] = map(
+        lambda dir: srctree / dir, ("samples", "drivers")
+    )
     if external_src is not None:
         extra_dirs = [external_src]
     for folder in extra_dirs:
@@ -216,7 +246,7 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
     return crates
 
 
-def main():
+def main() -> None:
     parser = argparse.ArgumentParser()
     parser.add_argument("--verbose", "-v", action="store_true")
     parser.add_argument("--cfgs", action="append", default=[])
@@ -225,7 +255,17 @@ def main():
     parser.add_argument("sysroot", type=pathlib.Path)
     parser.add_argument("sysroot_src", type=pathlib.Path)
     parser.add_argument("exttree", type=pathlib.Path, nargs="?")
-    args = parser.parse_args()
+
+    class Args(argparse.Namespace):
+        verbose: bool
+        cfgs: List[str]
+        srctree: pathlib.Path
+        objtree: pathlib.Path
+        sysroot: pathlib.Path
+        sysroot_src: pathlib.Path
+        exttree: pathlib.Path
+
+    args = parser.parse_args(namespace=Args())
 
     logging.basicConfig(
         format="[%(asctime)s] [%(levelname)s] %(message)s",
@@ -236,7 +276,19 @@ def main():
     assert args.sysroot in args.sysroot_src.parents
 
     rust_project = {
-        "crates": generate_crates(args.srctree, args.objtree, args.sysroot_src, args.exttree, args.cfgs),
+        "crates": generate_crates(
+            args.srctree,
+            args.objtree,
+            args.sysroot_src,
+            args.exttree,
+            defaultdict(
+                list,
+                {
+                    crate: vals.lstrip("--cfg").split()
+                    for crate, vals in map(lambda cfg: cfg.split("=", 1), args.cfgs)
+                },
+            ),
+        ),
         "sysroot": str(args.sysroot),
     }
 

-- 
2.49.0