Load FST using memory-mapped file

.github/workflows/ci.yml

@@ -0,0 +1,53 @@
+name: Rust CI
+
+on:
+  workflow_dispatch:
+  pull_request:
+  push:
+    branches:
+      - main
+
+jobs:
+  build-test:
+    name: Run test and build
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - os: ubuntu-latest
+            target: x86_64-unknown-linux-gnu
+
+          - os: ubuntu-24.04-arm
+            target: aarch64-unknown-linux-gnu
+
+          - os: macos-14
+            target: aarch64-apple-darwin
+
+          - os: macos-15
+            target: aarch64-apple-darwin
+
+          - os: macos-15-intel
+            target: x86_64-apple-darwin
+
+          - os: windows-latest
+            target: x86_64-pc-windows-msvc
+
+    runs-on: ${{ matrix.os }}
+
+    steps:
+      - name: Checkout source
+        uses: actions/checkout@v4
+
+      - name: Install Rust
+        uses: dtolnay/rust-toolchain@stable
+        with:
+          components: rustfmt, clippy
+
+      - name: Check fmt and linting
+        run: make check
+
+      - name: Run tests
+        run: cargo test --target ${{ matrix.target }} --verbose
+
+      - name: Build
+        run: cargo build --target ${{ matrix.target }} --verbose

Cargo.toml

@@ -23,6 +23,7 @@ crate-type = ["rlib"]
 
 [dependencies]
 fst = "0.4.7"
+memmap2 = "0.9.9"
 once_cell = "1.21"
 
 [[bin]]

Makefile

@@ -1,10 +1,20 @@
 build-fst:
 	cargo run --bin fst_builder
 
-
 clean:
 	cargo clean
 	rm -f purls.fst
 	rm -rf target
 
-.PHONY:  build-fst clean
+test:
+	cargo test
+
+valid:
+	cargo fmt --all
+	cargo clippy --all-targets --all-features
+
+check:
+	cargo fmt --all -- --check
+	cargo clippy --all-targets --all-features -- -D warnings
+
+.PHONY:  build-fst clean test valid check

README.md

@@ -2,7 +2,7 @@
 
 [![License](https://img.shields.io/badge/License-Apache--2.0-blue.svg?style=for-the-badge)](https://opensource.org/licenses/Apache-2.0)
 [![Version](https://img.shields.io/github/v/release/aboutcode-org/purl-validator-rust?style=for-the-badge)](https://github.com/aboutcode-org/purl-validator-rust/releases)
-[![Test](https://img.shields.io/github/actions/workflow/status/aboutcode-org/purl-validator-rust/run-test.yml?style=for-the-badge&logo=github)](https://github.com/aboutcode-org/purl-validator-rust/actions)
+[![Test](https://img.shields.io/github/actions/workflow/status/aboutcode-org/purl-validator-rust/ci.yml?style=for-the-badge&logo=github)](https://github.com/aboutcode-org/purl-validator-rust/actions)
 
 **purl-validator** is a Rust library for validating [Package URLs (PURLs)](https://github.com/package-url/purl-spec). It works fully offline, including in **air-gapped** or **restricted environments**, and answers one key question: **Does the package this PURL represents actually exist?**
 
@@ -53,6 +53,12 @@ Run tests:
 make test
 ```
 
+Fix formatting and linting:
+
+```bash
+make valid
+```
+
 ## License
 
 SPDX-License-Identifier: Apache-2.0

src/lib.rs

@@ -1,12 +1,25 @@
 use fst::Set;
+use memmap2::Mmap;
 use once_cell::sync::Lazy;
+use std::env;
+use std::fs::File;
+use std::path::Path;
 
-static FST_BYTES: &[u8] = include_bytes!(concat!(env!("CARGO_MANIFEST_DIR"), "/purls.fst"));
+static VALIDATOR: Lazy<Set<Mmap>> = Lazy::new(|| {
+    let path = Path::new(env!("CARGO_MANIFEST_DIR")).join("purls.fst");
+    load_fst(&path)
+});
 
-static VALIDATOR: Lazy<Set<&[u8]>> =
-    Lazy::new(|| Set::new(FST_BYTES).expect("Failed to load FST from embedded bytes"));
+fn load_fst(path: &Path) -> Set<Mmap> {
+    let file = File::open(path).expect("Failed to open FST file");
+    let mmap = unsafe { Mmap::map(&file).expect("Failed to mmap FST file") };
+    Set::new(mmap).expect("Failed to load FST from mmap")
+}
 
 pub fn validate(packageurl: &str) -> bool {
     let trimmed_packageurl = packageurl.trim_end_matches("/");
     VALIDATOR.contains(trimmed_packageurl)
 }
+
+#[cfg(test)]
+mod validate_tests;

src/validate_tests.rs

@@ -0,0 +1,11 @@
+use super::*;
+use std::path::Path;
+
+#[test]
+fn test_validate_with_custom_file() {
+    let test_path = Path::new(env!("CARGO_MANIFEST_DIR")).join("tests/data/test_purls.fst");
+    let validator = load_fst(&test_path);
+
+    assert!(validator.contains("pkg:nuget/FluentUtils.EnumExtensions"));
+    assert!(!validator.contains("pkg:example/nonexistent"));
+}