GitBaby/tests/archive.rs

use std::path::{Path, PathBuf};
use std::process::Command;
use std::sync::Arc;
use std::sync::atomic::{AtomicU32, Ordering};

use async_trait::async_trait;

use gitbaby::GitBaby;
use gitbaby::archive::{ArchiveFormat, BundleRequest, GetArchiveRequest};
use gitbaby::error::BabyError;
use gitbaby::repo::RepositoryFacade;

static COUNTER: AtomicU32 = AtomicU32::new(0);

struct TestFacade {
    dir: PathBuf,
}

#[async_trait]
impl RepositoryFacade for TestFacade {
    async fn git_repo_dir(&self) -> Result<PathBuf, BabyError> {
        Ok(self.dir.clone())
    }

    async fn git_alternate_object_directories(&self) -> Result<Vec<PathBuf>, BabyError> {
        Ok(Vec::new())
    }

    async fn gix_repo(&self) -> Result<gix::Repository, BabyError> {
        gix::open(&self.dir).map_err(|e| BabyError::Custom(e.to_string()))
    }
}

fn temp_repo() -> PathBuf {
    let n = COUNTER.fetch_add(1, Ordering::SeqCst);
    let dir = std::env::temp_dir().join(format!("gitbaby-archive-test-{}-{n}", std::process::id()));
    let _ = std::fs::remove_dir_all(&dir);
    std::fs::create_dir_all(&dir).expect("mkdir repo");
    let out = Command::new("git")
        .args(["init", "-q"])
        .current_dir(&dir)
        .output()
        .expect("git init failed");
    assert!(out.status.success(), "git init: {:?}", out);
    dir
}

fn cleanup(repo: &Path) {
    let _ = std::fs::remove_dir_all(repo);
}

fn git_commit(repo: &Path, msg: &str) {
    let out = Command::new("git")
        .args([
            "-c",
            "user.name=T",
            "-c",
            "user.email=t@e",
            "commit",
            "-q",
            "-m",
            msg,
        ])
        .current_dir(repo)
        .output()
        .expect("git commit failed");
    assert!(out.status.success(), "git commit `{msg}`: {:?}", out);
}

fn write_file(repo: &Path, rel: &str, content: &str) {
    let p = repo.join(rel);
    std::fs::create_dir_all(p.parent().expect("parent")).expect("mkdir");
    std::fs::write(p, content).expect("write");
}

fn index_commit(repo: &Path, msg: &str) {
    let out = Command::new("git")
        .args(["add", "-A"])
        .current_dir(repo)
        .output()
        .expect("git add failed");
    assert!(out.status.success(), "git add: {:?}", out);
    git_commit(repo, msg);
}

async fn baby_of(repo: PathBuf) -> GitBaby {
    GitBaby::new(Arc::new(TestFacade { dir: repo }))
}

fn archive_dir(repo: &Path) -> PathBuf {
    repo.join("archive")
}

fn archive_files(repo: &Path) -> Vec<PathBuf> {
    let mut files: Vec<PathBuf> = std::fs::read_dir(archive_dir(repo))
        .expect("read archive dir")
        .filter_map(|e| e.ok())
        .map(|e| e.path())
        .filter(|p| p.is_file())
        .collect();
    files.sort();
    files
}

#[tokio::test]
async fn get_archive_persists_and_hits_cache() {
    let repo = temp_repo();
    write_file(&repo, "a.txt", "one");
    write_file(&repo, "b.txt", "bee");
    index_commit(&repo, "first");

    let baby = baby_of(repo.clone()).await;
    let req = || GetArchiveRequest {
        commit: "HEAD".to_string(),
        format: ArchiveFormat::Tar,
        prefix: None,
        path: None,
        exclude: Vec::new(),
    };

    let first_bytes = baby
        .get_archive(req())
        .await
        .expect("get_archive")
        .read_to_end()
        .await
        .expect("read archive body");

    let files = archive_files(&repo);
    assert_eq!(files.len(), 1, "one cached archive expected");
    assert_eq!(
        files[0].extension().and_then(|e| e.to_str()),
        Some("tar"),
        "cached file: {:?}",
        files[0]
    );
    let on_disk = std::fs::read(&files[0]).expect("read cached file");
    assert_eq!(on_disk, first_bytes, "cached bytes match streamed bytes");

    let direct = Command::new("git")
        .args(["archive", "--format=tar", "HEAD"])
        .current_dir(&repo)
        .output()
        .expect("git archive direct");
    assert!(direct.status.success(), "git archive direct: {:?}", direct);
    assert_eq!(direct.stdout, first_bytes, "matches raw git archive output");

    let second_bytes = baby
        .get_archive(req())
        .await
        .expect("get_archive cached")
        .read_to_end()
        .await
        .expect("read archive body");
    assert_eq!(second_bytes, first_bytes, "cache hit returns same bytes");
    assert_eq!(archive_files(&repo).len(), 1);

    cleanup(&repo);
}

#[tokio::test]
async fn get_archive_keys_differ_by_options() {
    let repo = temp_repo();
    write_file(&repo, "a.txt", "one");
    index_commit(&repo, "first");

    let baby = baby_of(repo.clone()).await;
    let base = GetArchiveRequest {
        commit: "HEAD".to_string(),
        format: ArchiveFormat::Tar,
        prefix: None,
        path: None,
        exclude: Vec::new(),
    };

    let plain = baby
        .get_archive(base.clone())
        .await
        .expect("plain")
        .read_to_end()
        .await
        .expect("plain body");

    let prefixed = baby
        .get_archive(GetArchiveRequest {
            prefix: Some("p/".to_string()),
            ..base.clone()
        })
        .await
        .expect("prefixed")
        .read_to_end()
        .await
        .expect("prefixed body");

    let excluded = baby
        .get_archive(GetArchiveRequest {
            exclude: vec!["a.txt".to_string()],
            ..base.clone()
        })
        .await
        .expect("excluded")
        .read_to_end()
        .await
        .expect("excluded body");

    assert_ne!(plain, prefixed);
    assert_ne!(plain, excluded);
    assert_ne!(prefixed, excluded);

    let files = archive_files(&repo);
    assert_eq!(files.len(), 3, "three distinct keys cached");

    let zipped = baby
        .get_archive(GetArchiveRequest {
            format: ArchiveFormat::Zip,
            ..base
        })
        .await
        .expect("zip")
        .read_to_end()
        .await
        .expect("zip body");
    let files = archive_files(&repo);
    assert_eq!(files.len(), 4);
    assert!(
        files
            .iter()
            .any(|p| p.extension().and_then(|e| e.to_str()) == Some("zip")),
        "zip file present: {:?}",
        files
    );
    assert!(zipped.starts_with(b"PK"), "zip magic");
    assert_ne!(zipped, plain);

    cleanup(&repo);
}

#[tokio::test]
async fn get_archive_new_commit_new_key() {
    let repo = temp_repo();
    write_file(&repo, "a.txt", "one");
    index_commit(&repo, "first");

    let baby = baby_of(repo.clone()).await;
    let req = || GetArchiveRequest {
        commit: "HEAD".to_string(),
        format: ArchiveFormat::Tar,
        prefix: None,
        path: None,
        exclude: Vec::new(),
    };

    let _ = baby
        .get_archive(req())
        .await
        .expect("first revision")
        .read_to_end()
        .await
        .expect("body");
    assert_eq!(archive_files(&repo).len(), 1);

    write_file(&repo, "a.txt", "two");
    index_commit(&repo, "second");

    let _ = baby
        .get_archive(req())
        .await
        .expect("second revision")
        .read_to_end()
        .await
        .expect("body");
    let files = archive_files(&repo);
    assert_eq!(files.len(), 2, "new commit produces new cached key");

    cleanup(&repo);
}

#[tokio::test]
async fn create_bundle_persists_and_hits_cache() {
    let repo = temp_repo();
    write_file(&repo, "a.txt", "one");
    index_commit(&repo, "first");

    let baby = baby_of(repo.clone()).await;
    let req = || BundleRequest {
        refs: vec!["HEAD".to_string()],
    };

    let first = baby
        .create_bundle(req())
        .await
        .expect("create_bundle")
        .read_to_end()
        .await
        .expect("bundle body");

    let files = archive_files(&repo);
    assert_eq!(files.len(), 1, "one cached bundle expected");
    assert_eq!(
        files[0].extension().and_then(|e| e.to_str()),
        Some("bundle"),
        "cached file: {:?}",
        files[0]
    );
    let on_disk = std::fs::read(&files[0]).expect("read cached file");
    assert_eq!(on_disk, first, "cached bundle bytes match streamed bytes");

    let second = baby
        .create_bundle(req())
        .await
        .expect("create_bundle cached")
        .read_to_end()
        .await
        .expect("bundle body");
    assert_eq!(second, first, "cache hit returns same bundle bytes");
    assert_eq!(archive_files(&repo).len(), 1);

    cleanup(&repo);
}