refactor: move lexicon hashing to rust

- hash_lexicons now implemented in rust with sha2 crate
- exposed to python via pyo3
- update justfile to use uvx maturin

Cargo.lock

···
 checksum = "9e1b586273c5702936fe7b7d6896644d8be71e6314cfe09d3167c95f712589e8"
 
 [[package]]
+name = "block-buffer"
+version = "0.10.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71"
+dependencies = [
+ "generic-array",
+]
+
+[[package]]
 name = "bumpalo"
 version = "3.19.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
···
 version = "0.8.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
+
+[[package]]
+name = "cpufeatures"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "crypto-common"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "78c8292055d1c1df0cce5d180393dc8cce0abec0a7102adb6c7b1eef6016d60a"
+dependencies = [
+ "generic-array",
+ "typenum",
+]
 
 [[package]]
 name = "darling"
···
 ]
 
 [[package]]
+name = "digest"
+version = "0.10.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
+dependencies = [
+ "block-buffer",
+ "crypto-common",
+]
+
+[[package]]
 name = "find-msvc-tools"
 version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
···
 checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
 
 [[package]]
+name = "generic-array"
+version = "0.14.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a"
+dependencies = [
+ "typenum",
+ "version_check",
+]
+
+[[package]]
 name = "hashbrown"
 version = "0.12.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
···
 dependencies = [
  "atrium-lex",
  "heck",
+ "hex",
  "pyo3",
  "serde",
  "serde_json",
+ "sha2",
  "thiserror",
+ "walkdir",
 ]
 
 [[package]]
···
 checksum = "28d3b2b1366ec20994f1fd18c3c594f05c5dd4bc44d8bb0c1c632c8d6829481f"
 
 [[package]]
+name = "same-file"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502"
+dependencies = [
+ "winapi-util",
+]
+
+[[package]]
 name = "serde"
 version = "1.0.228"
 source = "registry+https://github.com/rust-lang/crates.io-index"
···
 ]
 
 [[package]]
+name = "sha2"
+version = "0.10.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
+dependencies = [
+ "cfg-if",
+ "cpufeatures",
+ "digest",
+]
+
+[[package]]
 name = "shlex"
 version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
···
 ]
 
 [[package]]
+name = "typenum"
+version = "1.19.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "562d481066bde0658276a35467c4af00bdc6ee726305698a55b86e61d7ad82bb"
+
+[[package]]
 name = "unicode-ident"
 version = "1.0.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
···
 checksum = "7264e107f553ccae879d21fbea1d6724ac785e8c3bfc762137959b5802826ef3"
 
 [[package]]
+name = "version_check"
+version = "0.9.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
+
+[[package]]
+name = "walkdir"
+version = "2.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29790946404f91d9c5d06f9874efddea1dc06c5efe94541a7d6863108e3a5e4b"
+dependencies = [
+ "same-file",
+ "winapi-util",
+]
+
+[[package]]
 name = "wasm-bindgen"
 version = "0.2.106"
 source = "registry+https://github.com/rust-lang/crates.io-index"
···
 ]
 
 [[package]]
+name = "winapi-util"
+version = "0.1.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
+dependencies = [
+ "windows-sys",
+]
+
+[[package]]
 name = "windows-core"
 version = "0.62.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
···
 dependencies = [
  "windows-link",
 ]
+
+[[package]]
+name = "windows-sys"
+version = "0.61.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ae137229bcbd6cdf0f7b80a31df61766145077ddf49416a728b02cb3921ff3fc"
+dependencies = [
+ "windows-link",
+]

Cargo.toml

···
 serde_json = "1.0"
 heck = "0.5"
 thiserror = "2.0"
+sha2 = "0.10"
+hex = "0.4"
+walkdir = "2.5"
 
 [profile.release]
 lto = true

justfile

···
-# build rust extension
+# build rust extension in dev mode
+dev:
+    uvx maturin develop
+
+# run tests
+test: dev
+    uv run pytest -v
+
+# build release wheels
 build:
-    uv run maturin develop
+    uvx maturin build --release
 
-# run tests (requires build first)
-test: build
-    uv run pytest
-
-# lint python
+# lint
 lint:
-    uv run ruff check
-    uv run ruff format --check
+    uv run ruff check .
+    uv run ruff format --check .
 
-# format python
+# format
 fmt:
-    uv run ruff format
+    uv run ruff check --fix .
+    uv run ruff format .
+
+# clean build artifacts
+clean:
+    rm -rf target dist *.egg-info

python/pmgfal/__init__.py

···
 from __future__ import annotations
 
 import argparse
-import hashlib
 import os
 import shutil
 import sys
 from pathlib import Path
 
-from pmgfal._pmgfal import __version__, generate
+from pmgfal._pmgfal import __version__, generate, hash_lexicons
 
-__all__ = ["__version__", "generate", "main", "get_cache_dir"]
+__all__ = ["__version__", "generate", "hash_lexicons", "main", "get_cache_dir"]
 
 
 def get_cache_dir() -> Path:
···
     else:
         base = Path(os.environ.get("XDG_CACHE_HOME", Path.home() / ".cache"))
     return base / "pmgfal"
-
-
-def hash_lexicons(lexicon_dir: Path, prefix: str | None = None) -> str:
-    """compute a hash of all lexicon files in a directory."""
-    hasher = hashlib.sha256()
-
-    # include version in hash so cache invalidates on upgrades
-    hasher.update(__version__.encode())
-
-    # include prefix in hash
-    if prefix:
-        hasher.update(prefix.encode())
-
-    # hash all json files in sorted order for determinism
-    json_files = sorted(lexicon_dir.rglob("*.json"))
-    for path in json_files:
-        hasher.update(path.name.encode())
-        hasher.update(path.read_bytes())
-
-    return hasher.hexdigest()[:16]
 
 
 def main(args: list[str] | None = None) -> int:
···
         return 1
 
     try:
-        # compute hash of lexicons
-        lexicon_hash = hash_lexicons(lexicon_dir, parsed.prefix)
+        # compute hash of lexicons (in rust)
+        lexicon_hash = hash_lexicons(str(lexicon_dir), parsed.prefix)
         cache_dir = get_cache_dir() / lexicon_hash
 
         # check cache

src/lib.rs

···
 mod parser;
 mod types;
 
+use std::fs;
 use std::path::Path;
 
 use pyo3::prelude::*;
+use sha2::{Digest, Sha256};
+
+/// compute a hash of all lexicon files in a directory
+#[pyfunction]
+#[pyo3(signature = (lexicon_dir, namespace_prefix=None))]
+fn hash_lexicons(lexicon_dir: &str, namespace_prefix: Option<&str>) -> PyResult<String> {
+    let lexicon_path = Path::new(lexicon_dir);
+
+    let mut hasher = Sha256::new();
+
+    // include version in hash so cache invalidates on upgrades
+    hasher.update(env!("CARGO_PKG_VERSION").as_bytes());
+
+    // include prefix in hash
+    if let Some(prefix) = namespace_prefix {
+        hasher.update(prefix.as_bytes());
+    }
+
+    // collect and sort json files for deterministic hashing
+    let mut json_files: Vec<_> = walkdir::WalkDir::new(lexicon_path)
+        .into_iter()
+        .filter_map(|e| e.ok())
+        .filter(|e| e.path().extension().is_some_and(|ext| ext == "json"))
+        .collect();
+
+    json_files.sort_by(|a, b| a.path().cmp(b.path()));
+
+    for entry in json_files {
+        let path = entry.path();
+        if let Some(name) = path.file_name() {
+            hasher.update(name.as_encoded_bytes());
+        }
+        if let Ok(content) = fs::read(path) {
+            hasher.update(&content);
+        }
+    }
+
+    let result = hasher.finalize();
+    Ok(hex::encode(&result[..8])) // 16 hex chars
+}
 
 /// generate pydantic models from lexicon files
 #[pyfunction]
···
 #[pymodule]
 fn _pmgfal(m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_function(wrap_pyfunction!(generate, m)?)?;
+    m.add_function(wrap_pyfunction!(hash_lexicons, m)?)?;
     m.add("__version__", env!("CARGO_PKG_VERSION"))?;
     Ok(())
 }