sausage/cli/src/cargo_actor.rs

//! The native `cargo` actor: builds Rust source folders into `.wasm` files.
//!
//! Request:  `{"type": "build", "source": "/actor/<id>/public/<folder>"}`
//! Replies:  `{"type": "built", "wasm": "/actor/cargo/public/builds/<n>/<name>.wasm", ...}`
//!           `{"type": "build_failed", "errors": "..."}`
//!
//! The broker knows nothing about Rust. This actor is one way to get a
//! `.wasm` file. Other actors can add other languages.
//!
//! Actors depend on the SDK with `sausage-actor = "0.1"`. The SDK is not
//! published: this actor copies the SDK of this host to `public/sdk/` (so
//! that every actor can read it), and points the dependency there in the
//! build copy of `Cargo.toml`.

use std::path::{Path, PathBuf};
use std::sync::Arc;
use std::time::Instant;

use anyhow::{Context, Result, anyhow, bail};
use serde_json::{Value, json};
use tokio::process::Command;
use tokio::sync::mpsc;

use include_dir::{Dir, include_dir};

use crate::broker::{Broker, Envelope};
use crate::world::{self, World};

pub const ID: &str = "cargo";
pub const TARGET: &str = "wasm32-wasip2";

/// The source of the `sausage-actor` SDK.
static SDK: Dir<'_> = include_dir!("$CARGO_MANIFEST_DIR/../sdk");

pub struct BuildOutput {
    /// Host path of the published `.wasm` file.
    pub wasm: PathBuf,
    pub seconds: f64,
    pub warnings: String,
}

/// All builds share one target folder, so they run one at a time.
pub struct Cargo {
    world: World,
}

impl Cargo {
    /// Create the actor and install the SDK of this host into `public/sdk/`.
    pub fn new(world: World) -> Result<Self> {
        write_dir(&SDK, &world.public_dir(ID).join("sdk"))?;
        Ok(Self { world })
    }

    /// Build the crate in `source` (a host path) and publish the `.wasm` file
    /// under `/actor/cargo/public/builds/<n>/`.
    pub async fn build(&self, source: &Path) -> Result<BuildOutput> {
        if !source.join("Cargo.toml").is_file() {
            bail!("{} has no Cargo.toml", source.display());
        }
        let started = Instant::now();
        let data = self.world.data_dir(ID);
        let build_dir = data.join("work");
        world::replace_source(source, &build_dir)?;
        let manifest = build_dir.join("Cargo.toml");
        std::fs::write(&manifest, prepare_manifest(&std::fs::read_to_string(&manifest)?, Some(&self.world.public_dir(ID).join("sdk")))?)?;

        let mut cmd = Command::new("cargo");
        cmd.arg("build")
            .arg("--release")
            .arg("--target")
            .arg(TARGET)
            .arg("--message-format=json-render-diagnostics")
            .arg("--target-dir")
            .arg(data.join("target"))
            .current_dir(&build_dir)
            .kill_on_drop(true);
        let out = cmd.output().await.context("cannot run cargo (is it on PATH, with the wasm32-wasip2 target?)")?;
        let stderr = String::from_utf8_lossy(&out.stderr).to_string();
        if !out.status.success() {
            bail!("{}", strip_progress(&stderr));
        }
        let mut artifact = None;
        for line in String::from_utf8_lossy(&out.stdout).lines() {
            if let Ok(v) = serde_json::from_str::<Value>(line)
                && v["reason"] == "compiler-artifact"
                && let Some(exe) = v["executable"].as_str()
            {
                artifact = Some(PathBuf::from(exe));
            }
        }
        let artifact = artifact.ok_or_else(|| anyhow!("cargo built no binary. Does the crate have a src/main.rs?"))?;

        let n = next_build_number(&self.world.public_dir(ID).join("builds"))?;
        let dest_dir = self.world.public_dir(ID).join("builds").join(n.to_string());
        let name = artifact.file_name().context("artifact has no file name")?;
        let dest = dest_dir.join(name);
        world::write_atomic(&dest, &std::fs::read(&artifact)?)?;
        Ok(BuildOutput { wasm: dest, seconds: started.elapsed().as_secs_f64(), warnings: strip_progress(&stderr) })
    }

    /// The native `cargo` actor. Builds run one at a time, in order.
    /// Replies (messages with `reply_to`) get no answer.
    pub async fn run_actor(self, broker: Arc<Broker>, mut mailbox: mpsc::Receiver<Envelope>) {
        while let Some(env) = mailbox.recv().await {
            if env.reply_to.is_some() {
                continue;
            }
            let body = self.handle(&broker, &env).await.unwrap_or_else(|e| {
                json!({"type": "build_failed", "source": env.body.get("source"), "errors": format!("{e:#}")})
            });
            broker.send(ID, Some(&env.from), None, Some(&env.id), body);
        }
    }

    async fn handle(&self, broker: &Broker, env: &Envelope) -> Result<Value> {
        match env.body.get("type").and_then(Value::as_str) {
            Some("build") => {
                let source_s = env.body.get("source").and_then(Value::as_str).ok_or_else(|| anyhow!("missing \"source\""))?;
                let source = broker.world.resolve(&env.from, source_s)?;
                let out = self.build(&source).await?;
                let wasm = self.world.global_path(&out.wasm).unwrap_or_else(|| out.wasm.display().to_string());
                Ok(json!({
                    "type": "built",
                    "wasm": wasm,
                    "source": source_s,
                    "built_by": ID,
                    "seconds": (out.seconds * 10.0).round() / 10.0,
                    "warnings": out.warnings,
                }))
            }
            other => bail!("unknown request {other:?}. Known: build"),
        }
    }
}

/// Point a `sausage-actor` dependency at `sdk` (keeping its features), and
/// add an empty `[workspace]`, so the crate never joins a parent workspace.
fn prepare_manifest(text: &str, sdk: Option<&Path>) -> Result<String> {
    let mut doc: toml_edit::DocumentMut = text.parse()?;
    if let Some(sdk) = sdk {
        for section in ["dependencies", "dev-dependencies", "build-dependencies"] {
            let Some(dep) = doc.get_mut(section).and_then(|t| t.get_mut("sausage-actor")) else { continue };
            let mut table = dep.as_inline_table().cloned().unwrap_or_default();
            for key in ["version", "path", "git", "branch", "tag", "rev", "registry"] {
                table.remove(key);
            }
            table.insert("path", sdk.display().to_string().into());
            *dep = toml_edit::value(table);
        }
    }
    if doc.get("workspace").is_none() {
        doc["workspace"] = toml_edit::table();
    }
    Ok(doc.to_string())
}

/// Write the files of `dir` below `to`. Skip files that did not change, so
/// that cargo does not rebuild the SDK at every start.
fn write_dir(dir: &Dir<'_>, to: &Path) -> Result<()> {
    for file in dir.files() {
        let dest = to.join(file.path());
        let contents = match file.path().file_name() {
            Some(n) if n == "Cargo.toml" => prepare_manifest(file.contents_utf8().context("Cargo.toml")?, None)?.into_bytes(),
            _ => file.contents().to_vec(),
        };
        if std::fs::read(&dest).ok() != Some(contents.clone()) {
            std::fs::create_dir_all(dest.parent().context("no parent")?)?;
            std::fs::write(&dest, contents)?;
        }
    }
    for sub in dir.dirs() {
        write_dir(sub, to)?;
    }
    Ok(())
}

fn next_build_number(dir: &Path) -> Result<u64> {
    std::fs::create_dir_all(dir)?;
    let max = std::fs::read_dir(dir)?
        .filter_map(|e| e.ok()?.file_name().to_str()?.parse::<u64>().ok())
        .max()
        .unwrap_or(0);
    Ok(max + 1)
}

/// Remove cargo's "Compiling ..." progress lines. Keep diagnostics.
fn strip_progress(stderr: &str) -> String {
    stderr
        .lines()
        .filter(|l| {
            let t = l.trim_start();
            !(t.starts_with("Compiling ")
                || t.starts_with("Downloaded ")
                || t.starts_with("Downloading ")
                || t.starts_with("Updating ")
                || t.starts_with("Locking ")
                || t.starts_with("Adding ")
                || t.starts_with("Blocking "))
        })
        .collect::<Vec<_>>()
        .join("\n")
}