nac3/nac3core/build.rs

use std::ffi::OsStr;
use std::{
    env,
    fs::File,
    io::Write,
    path::Path,
    process::{Command, Stdio},
};

use itertools::Itertools;
use regex::Regex;

/// Extracts the extension-less filename from a [`Path`].
fn path_to_extless_filename(path: &Path) -> &str {
    path.file_name().map(Path::new).and_then(Path::file_stem).and_then(OsStr::to_str).unwrap()
}

/// Compiles a source C file into LLVM bitcode.
fn compile_file_to_ir(path: &Path, filename_without_ext: &str) {
    /*
     * HACK: Sadly, clang doesn't let us emit generic LLVM bitcode.
     * Compiling for WASM32 and filtering the output with regex is the closest we can get.
     */
    let flags: &[&str] = &[
        "--target=wasm32",
        path.to_str().unwrap(),
        "-x",
        "c++",
        "-fno-discard-value-names",
        "-fno-exceptions",
        "-fno-rtti",
        match env::var("PROFILE").as_deref() {
            Ok("debug") => "-O0",
            Ok("release") => "-O3",
            flavor => panic!("Unknown or missing build flavor {flavor:?}"),
        },
        "-emit-llvm",
        "-S",
        "-Wall",
        "-Wextra",
        "-o",
        "-",
    ];

    println!("cargo:rerun-if-changed={}", path.to_str().unwrap());
    let out_dir = env::var("OUT_DIR").unwrap();
    let out_path = Path::new(&out_dir);

    let output = Command::new("clang-irrt")
        .args(flags)
        .output()
        .map(|o| {
            assert!(o.status.success(), "{}", std::str::from_utf8(&o.stderr).unwrap());
            o
        })
        .unwrap();

    let output = std::str::from_utf8(&output.stdout).unwrap();
    let mut filtered_output = String::with_capacity(output.len());

    let regex_filter = Regex::new(r"(?ms:^define.*?\}$)|(?m:^declare.*?$)").unwrap();
    for f in regex_filter.captures_iter(output) {
        assert_eq!(f.len(), 1);
        filtered_output.push_str(&f[0]);
        filtered_output.push('\n');
    }

    let filtered_output = Regex::new("(#\\d+)|(, *![0-9A-Za-z.]+)|(![0-9A-Za-z.]+)|(!\".*?\")")
        .unwrap()
        .replace_all(&filtered_output, "");

    println!("cargo:rerun-if-env-changed=DEBUG_DUMP_IRRT");
    if env::var("DEBUG_DUMP_IRRT").is_ok() {
        let mut file = File::create(out_path.join(format!("{filename_without_ext}.ll"))).unwrap();
        file.write_all(output.as_bytes()).unwrap();
        let mut file =
            File::create(out_path.join(format!("{filename_without_ext}-filtered.ll"))).unwrap();
        file.write_all(filtered_output.as_bytes()).unwrap();
    }

    let mut llvm_as = Command::new("llvm-as-irrt")
        .stdin(Stdio::piped())
        .arg("-o")
        .arg(out_path.join(format!("{filename_without_ext}.bc")))
        .spawn()
        .unwrap();
    llvm_as.stdin.as_mut().unwrap().write_all(filtered_output.as_bytes()).unwrap();
    assert!(llvm_as.wait().unwrap().success());
}

fn main() {
    const IRRT_SOURCE_PATHS: &[&str] =
        &["src/codegen/irrt/irrt.cpp", "src/codegen/tracert/tracert.cpp"];

    assert!(IRRT_SOURCE_PATHS.iter().map(Path::new).map(path_to_extless_filename).all_unique());

    for path in IRRT_SOURCE_PATHS {
        let path = Path::new(path);

        compile_file_to_ir(path, path_to_extless_filename(path))
    }
}