[PATCH v2 4/7] scripts: generate_rust_analyzer.py: add type hints

[Tamir Duberstein]

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").

Run `uv tool run mypy --strict scripts/generate_rust_analyzer.py` to
verify.

This removes `"is_proc_macro": false` from `rust-project.json` in
exchange for stricter types. This field is interpreted as false if
absent[1] so this doesn't change the behavior of rust-analyzer.

Link: https://github.com/rust-lang/rust-analyzer/blob/8d01570b5e812a49daa1f08404269f6ea5dd73a1/crates/project-model/src/project_json.rs#L372-L373 [1]
Signed-off-by: Tamir Duberstein <tamird@xxxxxxxxx>
---
 scripts/generate_rust_analyzer.py | 130 ++++++++++++++++++++++++++++----------
 1 file changed, 96 insertions(+), 34 deletions(-)

diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py
index 7e78b926e61f..c73ea8d116a4 100755
--- a/scripts/generate_rust_analyzer.py
+++ b/scripts/generate_rust_analyzer.py
@@ -10,8 +10,10 @@ import os
 import pathlib
 import subprocess
 import sys
+import typing as T
 
-def args_crates_cfgs(cfgs):
+
+def args_crates_cfgs(cfgs: T.Iterable[str]) -> dict[str, list[str]]:
     crates_cfgs = {}
     for cfg in cfgs:
         crate, vals = cfg.split("=", 1)
@@ -19,7 +21,45 @@ def args_crates_cfgs(cfgs):
 
     return crates_cfgs
 
-def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
+
+class Dependency(T.TypedDict):
+    crate: int
+    name: str
+
+
+class Source(T.TypedDict):
+    include_dirs: list[str]
+    exclude_dirs: list[str]
+
+
+class Crate(T.TypedDict):
+    display_name: str
+    root_module: str
+    is_workspace_member: bool
+    deps: list[Dependency]
+    cfg: list[str]
+    edition: T.Literal["2021"]
+    env: dict[str, str]
+
+
+# `T.NotRequired` fields on `Crate` would be better but `T.NotRequired` was added in 3.11.
+class ProcMacroCrate(Crate):
+    is_proc_macro: T.Literal[True]
+    proc_macro_dylib_path: T.Optional[str]  # `pathlib.Path` is not JSON serializable.
+
+
+# `T.NotRequired` fields on `Crate` would be better but `T.NotRequired` was added in 3.11.
+class CrateWithGenerated(Crate):
+    source: T.Optional[Source]
+
+
+def generate_crates(
+    srctree: pathlib.Path,
+    objtree: pathlib.Path,
+    sysroot_src: pathlib.Path,
+    external_src: pathlib.Path,
+    cfgs: list[str],
+) -> list[Crate]:
     # Generate the configuration list.
     cfg = []
     with open(objtree / "include" / "generated" / "rustc_cfg") as fd:
@@ -31,37 +71,53 @@ 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: list[Crate] = []
+    crates_indexes: dict[str, int] = {}
     crates_cfgs = args_crates_cfgs(cfgs)
 
-    def append_crate(display_name, root_module, deps, cfg=[], is_workspace_member=True, is_proc_macro=False):
-        crate = {
+    def append_crate(
+        display_name: str,
+        root_module: pathlib.Path,
+        deps: list[str],
+        cfg: list[str] = [],
+        is_workspace_member: bool = True,
+    ) -> None:
+        crates_indexes[display_name] = len(crates)
+        crates.append({
             "display_name": display_name,
             "root_module": str(root_module),
             "is_workspace_member": is_workspace_member,
-            "is_proc_macro": is_proc_macro,
             "deps": [{"crate": crates_indexes[dep], "name": dep} for dep in deps],
             "cfg": cfg,
             "edition": "2021",
             "env": {
                 "RUST_MODFILE": "This is only for rust-analyzer"
-            }
+            },
+        })
+
+    def append_proc_macro_crate(
+        display_name: str,
+        root_module: pathlib.Path,
+        deps: list[str],
+        cfg: list[str] = [],
+    ) -> None:
+        append_crate(display_name, root_module, deps, cfg)
+        proc_macro_dylib_name = subprocess.check_output(
+            [os.environ["RUSTC"], "--print", "file-names", "--crate-name", display_name, "--crate-type", "proc-macro", "-"],
+            stdin=subprocess.DEVNULL,
+        ).decode('utf-8').strip()
+        crate: ProcMacroCrate = {
+            **crates[-1],
+            "is_proc_macro": True,
+            "proc_macro_dylib_path": f"{objtree}/rust/{proc_macro_dylib_name}",
         }
-        if is_proc_macro:
-            proc_macro_dylib_name = subprocess.check_output(
-                [os.environ["RUSTC"], "--print", "file-names", "--crate-name", display_name, "--crate-type", "proc-macro", "-"],
-                stdin=subprocess.DEVNULL,
-            ).decode('utf-8').strip()
-            crate["proc_macro_dylib_path"] = f"{objtree}/rust/{proc_macro_dylib_name}"
-        crates_indexes[display_name] = len(crates)
-        crates.append(crate)
+        crates[-1] = 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",
@@ -84,11 +140,10 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
         [],
     )
 
-    append_crate(
+    append_proc_macro_crate(
         "macros",
         srctree / "rust" / "macros" / "lib.rs",
         ["std", "proc_macro"],
-        is_proc_macro=True,
     )
 
     append_crate(
@@ -98,9 +153,9 @@ 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:
         append_crate(
             display_name,
             srctree / "rust" / display_name / "lib.rs",
@@ -108,19 +163,23 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
             cfg=cfg,
         )
         crates[-1]["env"]["OBJTREE"] = str(objtree.resolve(True))
-        crates[-1]["source"] = {
-            "include_dirs": [
-                str(srctree / "rust" / display_name),
-                str(objtree / "rust")
-            ],
-            "exclude_dirs": [],
+        crate: CrateWithGenerated = {
+            **crates[-1],
+            "source": {
+                "include_dirs": [
+                    str(srctree / "rust" / display_name),
+                    str(objtree / "rust")
+                ],
+                "exclude_dirs": [],
+            }
         }
+        crates[-1] = crate
 
     append_crate_with_generated("bindings", ["core"])
     append_crate_with_generated("uapi", ["core"])
     append_crate_with_generated("kernel", ["core", "macros", "build_error", "bindings", "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:
@@ -129,7 +188,9 @@ 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: T.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:
@@ -152,7 +213,8 @@ 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=[])

-- 
2.48.1