Compare commits

..
Author SHA1 Message Date
beardthelion 5da280b6ff fix(node): propagate for-each-ref failures in resolve_issue_id 2026-09-10 23:08:58 -05:00
beardthelion f2b6cebdc1 fix(node): propagate for-each-ref failures in list_issues 2026-09-10 22:56:25 -05:00
beardthelion b5048f749f fix(node): read issue refs via cat-file --batch on stdin, resolve absence by enumeration 2026-09-10 22:00:08 -05:00
beardthelion 326f5e55ac fix(node): bound issue ref names and propagate rev-parse probe failures 2026-09-10 21:30:04 -05:00
beardthelion 4fa108160a fix(node): split absent ref from unreadable object in issue reads
get_issue folded every cat-file failure into Ok(None), so a corrupt or
unreadable object store looked identical to a missing issue. close_issue
then hit that None right after resolve_issue_id had proven the ref
exists and panicked on the expect.

A shared read_issue_blob helper now re-resolves the ref with rev-parse
(which does not read the object) when cat-file fails: unresolved means
genuinely absent (Ok(None)), resolved means a real read failure
(propagated as Err). list_issues applies the same split so a degraded
store errors the listing instead of silently under-reporting, and
close_issue treats a ref deleted between resolve and read as not-found
instead of panicking.

Closes #426.
2026-09-10 19:59:12 -05:00
4 changed files with 442 additions and 459 deletions

No files matched your search

+6 -285
View File
@@ -287,10 +287,8 @@ fn handle_connect<R: Read>(
// this into one POST deadlocks a multi-round fetch (#117).
//
// git-receive-pack (push):
// Git sends the ref-update command list (pkt-lines ending in a flush),
// then the complete PACK blob only when a command has a non-zero new-oid.
// A delete-only push sends no pack, and git holds its write pipe open for
// the report-status response, so EOF cannot delimit the request (#369).
// Git sends ref-update commands + the complete PACK blob, then closes its
// write pipe. read_to_end is safe and correct here, a single POST.
let post_url = format!("{}/{}", repo_base, service);
@@ -298,7 +296,10 @@ fn handle_connect<R: Read>(
return negotiate_upload_pack(&client, &post_url, service, signing_key, stdin, &mut stdout);
}
let request_body = read_receive_pack_request(stdin)?;
let mut request_body = Vec::new();
stdin
.read_to_end(&mut request_body)
.context("reading receive-pack request")?;
tracing::debug!("pack request: {} bytes from git", request_body.len());
if request_body.is_empty() {
@@ -534,108 +535,6 @@ fn read_upload_pack_round<R: Read>(stdin: &mut R) -> Result<(Vec<u8>, RoundEnd)>
}
}
/// Read one git-receive-pack request: optional `shallow` lines, then EITHER a
/// command list (pkt-lines terminated by a flush) or a push-cert block
/// (pkt-lines terminated by a "push-cert-end" line), then the negotiated
/// push-options block, then the pack ONLY when a command carries a non-zero
/// new-oid.
///
/// A delete-only push sends no pack, and git holds its write pipe open waiting
/// for the report-status response, so a plain read_to_end deadlocks the two
/// (#369). A signed push is the other trap: when the client sends a push-cert
/// it sends NO command list at all (the commands live inside the cert), so the
/// request starts with a "push-cert" line and no flush ever arrives. The
/// negotiated capability list is on the push-cert line, or on the first
/// command line after its NUL when there is no cert. EOF at any point also
/// ends the read, covering git versions that close the pipe early.
fn read_receive_pack_request<R: Read>(stdin: &mut R) -> Result<Vec<u8>> {
/// Read one pkt-line into `body` (length prefix + data), returning its data
/// or `None` on flush or EOF. Malformed lengths bail rather than collapse
/// into a synthesized flush (#192 F5).
fn read_pkt<R: Read>(stdin: &mut R, body: &mut Vec<u8>) -> Result<Option<Vec<u8>>> {
let mut len_bytes = [0u8; 4];
match stdin.read_exact(&mut len_bytes) {
Ok(()) => {}
Err(e) if e.kind() == io::ErrorKind::UnexpectedEof => return Ok(None),
Err(e) => return Err(e.into()),
}
let Ok(len_hex) = std::str::from_utf8(&len_bytes) else {
bail!("malformed pkt-line length prefix: non-UTF-8 bytes {len_bytes:02x?}");
};
let Ok(pkt_len) = usize::from_str_radix(len_hex, 16) else {
bail!("malformed pkt-line length prefix: non-hex {len_hex:?}");
};
body.extend_from_slice(&len_bytes);
if pkt_len == 0 {
return Ok(None);
}
if pkt_len < 4 {
bail!("invalid pkt-line length: {pkt_len}");
}
let mut data = vec![0u8; pkt_len - 4];
stdin
.read_exact(&mut data)
.context("reading pkt-line data")?;
body.extend_from_slice(&data);
Ok(Some(data))
}
/// "<40-hex old> <40-hex new> <refname>" — the command shape, whether it
/// appears in a command list or inside a push-cert.
fn is_command(data: &[u8]) -> bool {
data.len() >= 82
&& data[..40].iter().all(|b| b.is_ascii_hexdigit())
&& data[40] == b' '
&& data[41..81].iter().all(|b| b.is_ascii_hexdigit())
&& data[81] == b' '
}
let mut body = Vec::new();
let mut caps = String::new();
let mut pack_expected = false;
let mut in_cert = false;
loop {
let Some(data) = read_pkt(stdin, &mut body)? else {
// Flush ends a command list; EOF ends anything. A cert has no
// legal flush inside it, so the same break covers malformed
// input without hanging.
break;
};
if !in_cert && data.starts_with(b"push-cert") {
in_cert = true;
if let Some(nul) = data.iter().position(|&b| b == 0) {
caps = String::from_utf8_lossy(&data[nul + 1..]).into_owned();
}
continue;
}
if in_cert && data == b"push-cert-end\n" {
break;
}
if is_command(&data) {
if caps.is_empty() {
if let Some(nul) = data.iter().position(|&b| b == 0) {
caps = String::from_utf8_lossy(&data[nul + 1..]).into_owned();
}
}
if data[41..81].iter().any(|&b| b != b'0') {
pack_expected = true;
}
}
}
// When both are negotiated the push-options block follows the cert; when
// only options are negotiated it follows the command flush. Either way it
// is pkt-lines to a flush.
if caps.split(' ').any(|c| c.starts_with("push-options")) {
while read_pkt(stdin, &mut body)?.is_some() {}
}
if pack_expected {
stdin
.read_to_end(&mut body)
.context("reading receive-pack pack")?;
}
Ok(body)
}
/// POST one self-contained stateless-RPC request body and stream the response to
/// `stdout`. Signs the request when `signing_key` is present, so every round of a
/// private-repo fetch carries the caller's signature (the node visibility-gates
@@ -2118,184 +2017,6 @@ mod tests {
assert!(help.ends_with('\n'));
}
// ── #369 delete-only push deadlock ───────────────────────────────────────
/// A delete-only receive-pack request ends at the command flush; git then
/// holds the write pipe open for the report and sends no pack. A reader that
/// blocks after the command list reproduces the hang that a Cursor (EOF)
/// hides. The read must return at the flush, inside the timeout.
#[test]
fn delete_only_receive_pack_request_returns_at_command_flush() {
let old = "a".repeat(40);
let zero = "0".repeat(40);
let mut seed = Vec::new();
seed.extend_from_slice(&pkt(&format!("{old} {zero} refs/heads/gone\n")));
seed.extend_from_slice(b"0000"); // command-list flush; git then blocks
let (tx, rx) = std::sync::mpsc::channel::<()>();
let mut reader = BlockAfterSeed {
seed: io::Cursor::new(seed),
gate: rx,
};
let (done_tx, done_rx) = std::sync::mpsc::channel::<Vec<u8>>();
let handle = std::thread::spawn(move || {
let _ = done_tx.send(read_receive_pack_request(&mut reader).unwrap());
});
let got = done_rx.recv_timeout(std::time::Duration::from_secs(2));
let _ = tx.send(()); // unblock the reader so the thread can exit
let _ = handle.join();
let body = got.expect(
"read_receive_pack_request blocked past the command flush waiting for \
a pack a delete-only push never sends (#369)",
);
assert!(
body.ends_with(b"0000"),
"the request body keeps the command list and its flush terminator"
);
}
/// A push carrying objects still reads the pack through to EOF, and the
/// command flush sits between the commands and the pack in the body.
#[test]
fn receive_pack_request_with_pack_reads_through_eof() {
let old = "a".repeat(40);
let new = "b".repeat(40);
let mut stream = Vec::new();
stream.extend_from_slice(&pkt(&format!(
"{old} {new} refs/heads/main\0 report-status-v2\n"
)));
stream.extend_from_slice(b"0000");
stream.extend_from_slice(b"PACK\x00\x00\x00\x02fakepack");
let mut stdin = io::Cursor::new(stream);
let body = read_receive_pack_request(&mut stdin).unwrap();
let pos = body.windows(4).position(|w| w == b"0000").unwrap();
assert_eq!(
&body[pos + 4..],
b"PACK\x00\x00\x00\x02fakepack",
"a non-zero new-oid means the pack follows the flush"
);
}
/// A signed delete-only push sends NO command list: the request starts
/// with the "push-cert" line, the commands live inside the cert, and the
/// cert ends with a "push-cert-end" pkt-line (not a flush). The reader
/// must return after push-cert-end without waiting on the pipe.
#[test]
fn signed_delete_only_push_returns_after_push_cert_end() {
let old = "a".repeat(40);
let zero = "0".repeat(40);
let mut seed = Vec::new();
seed.extend_from_slice(&pkt("push-cert\0 report-status-v2 push-cert\n"));
seed.extend_from_slice(&pkt("certificate version 0.1\n"));
seed.extend_from_slice(&pkt("pusher did:key:z6Mk\n"));
seed.extend_from_slice(&pkt("\n")); // empty line ends the headers
seed.extend_from_slice(&pkt(&format!("{old} {zero} refs/heads/gone\n")));
seed.extend_from_slice(&pkt("sig-line\n"));
seed.extend_from_slice(&pkt("push-cert-end\n"));
// git now blocks for the report; the pipe stays open.
let (tx, rx) = std::sync::mpsc::channel::<()>();
let mut reader = BlockAfterSeed {
seed: io::Cursor::new(seed),
gate: rx,
};
let (done_tx, done_rx) = std::sync::mpsc::channel::<Vec<u8>>();
let handle = std::thread::spawn(move || {
let _ = done_tx.send(read_receive_pack_request(&mut reader).unwrap());
});
let got = done_rx.recv_timeout(std::time::Duration::from_secs(2));
let _ = tx.send(());
let _ = handle.join();
let body = got.expect(
"read_receive_pack_request blocked past push-cert-end on a signed \
delete-only push (#369)",
);
assert!(
body.windows(6).any(|w| w == b"pusher"),
"the cert block is part of the request body"
);
}
/// A signed pack-bearing push: cert with the commands inside, then the
/// pack. Everything must land in the body.
#[test]
fn signed_pack_push_keeps_cert_and_pack() {
let old = "a".repeat(40);
let new = "b".repeat(40);
let mut stream = Vec::new();
stream.extend_from_slice(&pkt("push-cert\0 report-status-v2 push-cert\n"));
stream.extend_from_slice(&pkt("certificate version 0.1\n"));
stream.extend_from_slice(&pkt("\n"));
stream.extend_from_slice(&pkt(&format!("{old} {new} refs/heads/main\n")));
stream.extend_from_slice(&pkt("push-cert-end\n"));
stream.extend_from_slice(b"PACK\x00\x00\x00\x02fakepack");
let mut stdin = io::Cursor::new(stream);
let body = read_receive_pack_request(&mut stdin).unwrap();
assert!(
body.windows(5).any(|w| w == b"PACK\x00"),
"the pack follows the cert into the body"
);
}
/// A negotiated push-options block is pkt-lines ending in its own flush.
/// With no cert it follows the command flush; with a cert it follows
/// push-cert-end.
#[test]
fn receive_pack_request_consumes_a_push_options_block() {
let old = "a".repeat(40);
let new = "b".repeat(40);
let mut stream = Vec::new();
stream.extend_from_slice(&pkt(&format!(
"{old} {new} refs/heads/main\0 report-status-v2 push-options\n"
)));
stream.extend_from_slice(b"0000"); // command flush
stream.extend_from_slice(&pkt("ci.skip\n"));
stream.extend_from_slice(b"0000"); // options flush
stream.extend_from_slice(b"PACK\x00\x00\x00\x02fakepack");
let mut stdin = io::Cursor::new(stream);
let body = read_receive_pack_request(&mut stdin).unwrap();
assert!(body.windows(7).any(|w| w == b"ci.skip"), "options survived");
assert!(
body.ends_with(b"PACK\x00\x00\x00\x02fakepack"),
"the pack lands after the options block"
);
}
/// Cert and options together: the cert comes first and the options block
/// sits between push-cert-end and the pack.
#[test]
fn signed_push_with_options_reads_cert_then_options_then_pack() {
let old = "a".repeat(40);
let new = "b".repeat(40);
let mut stream = Vec::new();
stream.extend_from_slice(&pkt(
"push-cert\0 report-status-v2 push-cert push-options\n",
));
stream.extend_from_slice(&pkt("certificate version 0.1\n"));
stream.extend_from_slice(&pkt("\n"));
stream.extend_from_slice(&pkt(&format!("{old} {new} refs/heads/main\n")));
stream.extend_from_slice(&pkt("push-cert-end\n"));
stream.extend_from_slice(&pkt("ci.skip\n"));
stream.extend_from_slice(b"0000"); // options flush
stream.extend_from_slice(b"PACK\x00\x00\x00\x02fakepack");
let mut stdin = io::Cursor::new(stream);
let body = read_receive_pack_request(&mut stdin).unwrap();
assert!(body.windows(7).any(|w| w == b"ci.skip"), "options survived");
assert!(
body.ends_with(b"PACK\x00\x00\x00\x02fakepack"),
"the pack lands after the options block"
);
}
// ── #117 multi-round fetch negotiation ───────────────────────────────────
/// Encode a git pkt-line: 4-byte hex length (incl. the 4 bytes) + data.
@@ -95,36 +95,6 @@ fn upload_pack(repo: &Path, advertise: bool, input: &[u8]) -> Vec<u8> {
out.stdout
}
/// Run `git receive-pack --stateless-rpc [--advertise-refs] <repo>`, optionally
/// feeding `input` on stdin. Returns raw stdout (the wire bytes). The receive
/// half of `upload_pack`, used so the shim can serve a real push.
fn receive_pack(repo: &Path, advertise: bool, input: &[u8]) -> Vec<u8> {
let mut cmd = Command::new("git");
cmd.arg("receive-pack").arg("--stateless-rpc");
if advertise {
cmd.arg("--advertise-refs");
}
cmd.arg(repo)
.stdin(Stdio::piped())
.stdout(Stdio::piped())
.stderr(Stdio::piped());
let mut child = cmd.spawn().expect("spawn git receive-pack");
let mut stdin = child.stdin.take().unwrap();
let input = input.to_vec();
let writer = std::thread::spawn(move || {
let _ = stdin.write_all(&input);
// drop closes stdin
});
let out = child.wait_with_output().expect("wait receive-pack");
writer.join().ok();
assert!(
out.status.success(),
"git receive-pack failed: {}",
String::from_utf8_lossy(&out.stderr)
);
out.stdout
}
#[derive(Clone, Copy)]
enum ShimMode {
/// Faithful v0 serving: pipe each POST to `git upload-pack --stateless-rpc`.
@@ -248,21 +218,7 @@ fn handle_conn(stream: TcpStream, repo: &Path, mode: ShimMode, posts: &AtomicUsi
reader.read_exact(&mut body).ok();
}
let (content_type, payload) = if method == "GET" && target.contains("service=git-receive-pack")
{
// Receive-pack advertisement, same wrapper shape as upload-pack.
let adv = receive_pack(repo, true, b"");
let mut wrapped = pkt(b"# service=git-receive-pack\n");
wrapped.extend_from_slice(b"0000");
wrapped.extend_from_slice(&adv);
("application/x-git-receive-pack-advertisement", wrapped)
} else if method == "POST" && target.ends_with("/git-receive-pack") {
posts.fetch_add(1, Ordering::SeqCst);
(
"application/x-git-receive-pack-result",
receive_pack(repo, false, &body),
)
} else if method == "GET" && target.contains("/info/refs") {
let (content_type, payload) = if method == "GET" && target.contains("/info/refs") {
// v0 advertisement, wrapped exactly as the node's info_refs does.
let adv = upload_pack(repo, true, b"");
let mut wrapped = pkt(b"# service=git-upload-pack\n");
@@ -337,34 +293,6 @@ fn fetch_with_helper(clone: &Path, node_url: &str) -> (bool, std::process::Outpu
run_bounded(cmd, Duration::from_secs(30))
}
/// Run `git push` in `local` through the helper, same wiring and hard timeout as
/// [`fetch_with_helper`]. `args` carries the push spec, e.g.
/// `["--delete", "doomed"]`.
fn push_with_helper(local: &Path, node_url: &str, args: &[&str]) -> (bool, std::process::Output) {
let helper_bin = PathBuf::from(env!("CARGO_BIN_EXE_git-remote-gitlawb"));
let helper_dir = helper_bin.parent().unwrap().to_path_buf();
let path_env = match std::env::var_os("PATH") {
Some(p) => {
let mut dirs = vec![helper_dir.clone()];
dirs.extend(std::env::split_paths(&p));
std::env::join_paths(dirs).unwrap()
}
None => helper_dir.clone().into_os_string(),
};
let mut cmd = Command::new("git");
cmd.arg("-C")
.arg(local)
.arg("push")
.arg("origin")
.args(args)
.env("PATH", path_env)
.env("LC_ALL", "C")
.env("GITLAWB_NODE", node_url)
.env("GITLAWB_KEY", "/nonexistent-key-for-anon-push");
run_bounded(cmd, Duration::from_secs(30))
}
/// A synthetic non-success `ExitStatus` used only on the unix timeout path, where
/// `reap_group` has already consumed the child and the later `wait` returns ECHILD.
/// The timeout branch already reports `completed == false`, so the exact status is
@@ -1314,77 +1242,3 @@ fn run_bounded_bounds_join_when_leader_exits_leaving_a_pipe_holder() {
held pipes do not stall the joins)"
);
}
/// #369 end-to-end: a real `git push --delete` through the helper completes.
/// The receive-pack request for a delete-only push is commands + flush with NO
/// pack, and git holds its write pipe open for the report — so a helper that
/// reads stdin to EOF deadlocks against it. The shim pipes the POST to a real
/// `git receive-pack --stateless-rpc`, so the branch actually has to be deleted
/// server-side for the assertions to pass.
#[test]
fn real_git_push_delete_completes() {
let dir = tempfile::tempdir().unwrap();
let server = dir.path().join("server.git");
let local = dir.path().join("local");
// A bare repo holding the doomed branch, plus a live one.
git(
dir.path(),
&[
"init",
"--bare",
server.to_str().unwrap(),
"--initial-branch=main",
],
);
let work = dir.path().join("work");
git(
dir.path(),
&["init", work.to_str().unwrap(), "--initial-branch=main"],
);
git(&work, &["config", "user.email", "t@t"]);
git(&work, &["config", "user.name", "t"]);
std::fs::write(work.join("f"), "x").unwrap();
git(&work, &["add", "f"]);
git(&work, &["commit", "-m", "c"]);
git(&work, &["branch", "doomed"]);
git(&work, &["push", server.to_str().unwrap(), "main", "doomed"]);
// The pusher: a local repo whose origin is the gitlawb remote pointing at
// the shim. Nothing needs to be fetched first; git takes the old-oid from
// the receive-pack advertisement.
git(
dir.path(),
&["init", local.to_str().unwrap(), "--initial-branch=main"],
);
git(
&local,
&["remote", "add", "origin", "gitlawb://did:key:z6MkTest/repo"],
);
let shim = start_shim(server.clone(), ShimMode::Normal);
let (completed, out) = push_with_helper(&local, &shim.base_url, &["--delete", "doomed"]);
let posts = shim.posts.load(Ordering::SeqCst);
assert!(
completed,
"git push --delete did not complete within the timeout (deadlock signature). stderr:\n{}",
String::from_utf8_lossy(&out.stderr)
);
assert!(
out.status.success(),
"git push --delete failed. stderr:\n{}",
String::from_utf8_lossy(&out.stderr)
);
assert_eq!(posts, 1, "a delete-only push is exactly one POST");
let gone = Command::new("git")
.arg("-C")
.arg(&server)
.args(["rev-parse", "--verify", "--quiet", "refs/heads/doomed"])
.output()
.unwrap();
assert!(
!gone.status.success(),
"refs/heads/doomed must be deleted in the server repo"
);
}
+195
View File
@@ -449,3 +449,198 @@ mod lock_pool_shed_tests {
);
}
}
/// #426: end-to-end at the handler seam. A corrupt object store behind a
/// resolving issue ref used to look identical to an absent issue: get returned
/// a fake 404, close returned a fake 404 after releasing the write guard, and
/// list silently under-reported. All three must now surface a git error.
#[cfg(test)]
mod corrupt_store_tests {
use super::*;
use axum::response::IntoResponse;
use sqlx::PgPool;
use tempfile::TempDir;
fn seed_repo(owner_did: &str, name: &str) -> crate::db::RepoRecord {
let now = Utc::now();
crate::db::RepoRecord {
id: Uuid::new_v4().to_string(),
name: name.to_string(),
owner_did: owner_did.to_string(),
description: None,
is_public: true,
default_branch: "main".to_string(),
created_at: now,
updated_at: now,
disk_path: format!("/tmp/{name}"),
forked_from: None,
machine_id: None,
}
}
/// A state whose repo store roots in `repos_dir`, so the test can lay down
/// a real repo and then corrupt it without touching /tmp.
async fn state_with_repos_dir(pool: &PgPool, repos_dir: &std::path::Path) -> AppState {
let mut state = crate::test_support::test_state(pool.clone()).await;
state.repo_store =
crate::git::repo_store::RepoStore::for_testing(repos_dir.to_path_buf(), pool.clone());
state
}
/// Bare repo at the store's expected path, holding one issue ref.
fn bare_repo_with_issue(
repos_dir: &std::path::Path,
owner: &str,
name: &str,
) -> (std::path::PathBuf, String) {
let repo_path = repos_dir
.join(owner.replace([':', '/'], "_"))
.join(format!("{name}.git"));
std::fs::create_dir_all(&repo_path).unwrap();
let out = std::process::Command::new("git")
.args(["init", "--bare"])
.arg(&repo_path)
.output()
.unwrap();
assert!(out.status.success());
let issue_id = "aaaabbbb-0000-0000-0000-000000000000".to_string();
git_issues::create_issue(
&repo_path,
&issue_id,
&serde_json::json!({
"id": issue_id,
"title": "t",
"status": "open",
})
.to_string(),
)
.unwrap();
(repo_path, issue_id)
}
/// Delete the blob object behind the issue ref and put garbage in its
/// place: `cat-file` fails while `rev-parse` still resolves the ref.
fn corrupt_issue_object(repo_path: &std::path::Path, issue_id: &str) {
let out = std::process::Command::new("git")
.args(["rev-parse", &format!("refs/gitlawb/issues/{issue_id}")])
.current_dir(repo_path)
.output()
.unwrap();
let oid = String::from_utf8(out.stdout).unwrap().trim().to_string();
let obj = repo_path.join("objects").join(&oid[..2]).join(&oid[2..]);
std::fs::remove_file(&obj).unwrap();
std::fs::write(&obj, b"garbage").unwrap();
}
/// The regression: closing over a corrupt store used to return a fake 404
/// (or panic deeper in). It must reach the caller as a git 500, and the
/// handler must return rather than unwind.
#[sqlx::test]
async fn close_issue_on_corrupt_store_returns_git_error_not_panic(pool: PgPool) {
let owner = "did:key:zISSUECORRUPTCCCCCCCCCCCCCCCCCCCCCCCCC";
let dir = TempDir::new().unwrap();
let state = state_with_repos_dir(&pool, dir.path()).await;
state
.db
.create_repo(&seed_repo(owner, "corrupt-close"))
.await
.expect("seed repo");
let (repo_path, issue_id) = bare_repo_with_issue(dir.path(), owner, "corrupt-close");
corrupt_issue_object(&repo_path, &issue_id);
let err = close_issue(
State(state),
Extension(AuthenticatedDid(owner.to_string())),
Path((owner.to_string(), "corrupt-close".to_string(), issue_id)),
)
.await
.expect_err("a corrupt store must error, not panic or 404");
assert_eq!(
err.into_response().status(),
StatusCode::INTERNAL_SERVER_ERROR,
"a read failure is a git 500, not a fake not-found"
);
}
/// get on a corrupt store: 500, not the 404 the fold used to produce.
#[sqlx::test]
async fn get_issue_on_corrupt_store_returns_500_not_404(pool: PgPool) {
let owner = "did:key:zISSUECORRUPTGETDDDDDDDDDDDDDDDDDDDDDDD";
let dir = TempDir::new().unwrap();
let state = state_with_repos_dir(&pool, dir.path()).await;
state
.db
.create_repo(&seed_repo(owner, "corrupt-get"))
.await
.expect("seed repo");
let (repo_path, issue_id) = bare_repo_with_issue(dir.path(), owner, "corrupt-get");
corrupt_issue_object(&repo_path, &issue_id);
let err = get_issue(
State(state),
Path((owner.to_string(), "corrupt-get".to_string(), issue_id)),
None,
)
.await
.expect_err("a corrupt store must error, not 404");
assert_eq!(
err.into_response().status(),
StatusCode::INTERNAL_SERVER_ERROR,
);
}
/// list on a corrupt store must fail outright; a 200 that silently drops
/// the unreadable issue is the other half of the fold.
#[sqlx::test]
async fn list_issues_on_corrupt_store_returns_git_error(pool: PgPool) {
let owner = "did:key:zISSUECORRUPTLISTEEEEEEEEEEEEEEEEEEEEEE";
let dir = TempDir::new().unwrap();
let state = state_with_repos_dir(&pool, dir.path()).await;
state
.db
.create_repo(&seed_repo(owner, "corrupt-list"))
.await
.expect("seed repo");
let (repo_path, issue_id) = bare_repo_with_issue(dir.path(), owner, "corrupt-list");
corrupt_issue_object(&repo_path, &issue_id);
let err = list_issues(
State(state),
Path((owner.to_string(), "corrupt-list".to_string())),
None,
)
.await
.expect_err("a corrupt store must error, not under-report");
assert_eq!(
err.into_response().status(),
StatusCode::INTERNAL_SERVER_ERROR,
);
}
/// Must-not direction: a genuinely absent issue still gets the 404.
#[sqlx::test]
async fn get_issue_on_absent_ref_still_returns_404(pool: PgPool) {
let owner = "did:key:zISSUEABSENTFFFFFFFFFFFFFFFFFFFFFFFFFFF";
let dir = TempDir::new().unwrap();
let state = state_with_repos_dir(&pool, dir.path()).await;
state
.db
.create_repo(&seed_repo(owner, "absent-get"))
.await
.expect("seed repo");
bare_repo_with_issue(dir.path(), owner, "absent-get");
let err = get_issue(
State(state),
Path((
owner.to_string(),
"absent-get".to_string(),
"ffffffff-0000-0000-0000-000000000000".to_string(),
)),
None,
)
.await
.expect_err("a missing issue is still not-found");
assert_eq!(err.into_response().status(), StatusCode::NOT_FOUND);
}
}
+240 -27
View File
@@ -61,6 +61,119 @@ pub fn create_issue(repo_path: &Path, issue_id: &str, json: &str) -> Result<()>
Ok(())
}
/// Issue ids are UUIDs; refs under `refs/gitlawb/issues/` only ever carry
/// `[0-9a-zA-Z_-]` names. Anything else is not a value we pass to git.
fn issue_ref_name_is_safe(ref_name: &str) -> bool {
let Some(id) = ref_name.strip_prefix("refs/gitlawb/issues/") else {
return false;
};
!id.is_empty()
&& id
.chars()
.all(|c| c.is_ascii_alphanumeric() || c == '-' || c == '_')
}
/// Resolve a ref name without putting it on a command line: enumerate refs
/// (constant argv) and match in memory. A nonzero exit propagates, so "cannot
/// determine" is an error rather than a quiet `false`.
fn ref_name_resolves(repo_path: &Path, ref_name: &str) -> Result<bool> {
// allow-unbounded-git: failure-path existence recheck, module convention.
let out = Command::new("git")
.args(["for-each-ref", "--format=%(refname)"])
.current_dir(repo_path)
.output()
.context("failed to run git for-each-ref")?;
if !out.status.success() {
let stderr = String::from_utf8_lossy(&out.stderr);
anyhow::bail!("git for-each-ref failed: {}", stderr.trim());
}
let stdout = String::from_utf8_lossy(&out.stdout);
Ok(stdout.lines().any(|line| line.trim() == ref_name))
}
/// Read the blob behind an issue ref.
///
/// `Ok(None)` means the ref itself is absent. A ref that resolves but whose
/// object cannot be read (corrupt object, unreadable store, a mid-read gc) is
/// an error, not an absence (#426).
///
/// The ref name reaches git on stdin, never argv: `cat-file --batch` answers
/// `<oid> <type> <size>\n<body>\n` for a readable object and
/// `<spec> missing\n` for an absent ref or an unreadable object alike, so the
/// `missing` case is re-resolved by name enumeration to tell them apart.
fn read_issue_blob(repo_path: &Path, ref_name: &str) -> Result<Option<String>> {
if !issue_ref_name_is_safe(ref_name) {
anyhow::bail!("refusing issue ref outside the issues namespace: {ref_name}");
}
// allow-unbounded-git: this module's spawns predate the bounded runner and
// its callers run inside issue handlers that already hold the repo guard.
let mut child = Command::new("git")
.args(["cat-file", "--batch"])
.current_dir(repo_path)
.stdin(std::process::Stdio::piped())
.stdout(std::process::Stdio::piped())
.stderr(std::process::Stdio::piped())
.spawn()
.context("failed to spawn git cat-file --batch")?;
use std::io::Write;
// Reap the child even when the write fails so a stdin error cannot drop an
// unwaited Child and leak a zombie (#53).
let write_result = match child.stdin.take() {
Some(mut stdin) => stdin
.write_all(ref_name.as_bytes())
.and_then(|()| stdin.write_all(b"\n")),
None => Err(std::io::Error::new(
std::io::ErrorKind::BrokenPipe,
"git cat-file --batch stdin unavailable",
)),
};
let output = child
.wait_with_output()
.context("git cat-file --batch failed")?;
write_result.context("failed to write ref name to git cat-file stdin")?;
if !output.status.success() {
let stderr = String::from_utf8_lossy(&output.stderr);
anyhow::bail!("git cat-file --batch failed: {}", stderr.trim());
}
// "<spec> missing\n" covers an absent ref and an unreadable object; only a
// ref that still resolves is the error case.
let missing = format!("{ref_name} missing\n");
if output.stdout.as_slice() == missing.as_bytes() {
return match ref_name_resolves(repo_path, ref_name)? {
true => anyhow::bail!("issue ref resolves but its object is unreadable: {ref_name}"),
false => Ok(None),
};
}
// Header: "<oid> <type> <size>\n" then exactly <size> bytes plus a newline.
let header_end = output
.stdout
.iter()
.position(|b| *b == b'\n')
.context("unexpected git cat-file --batch output")?;
let header = String::from_utf8_lossy(&output.stdout[..header_end]);
let mut parts = header.split(' ');
parts.next();
let obj_type = parts.next().unwrap_or("");
if obj_type != "blob" {
anyhow::bail!("issue ref {ref_name} resolves to a non-blob object");
}
let size: usize = parts
.next()
.and_then(|s| s.parse().ok())
.context("unexpected git cat-file --batch header")?;
let body = &output.stdout[header_end + 1..];
anyhow::ensure!(
body.len() >= size,
"truncated git cat-file --batch body for {ref_name}"
);
Ok(Some(String::from_utf8_lossy(&body[..size]).to_string()))
}
/// List all issue refs and return their JSON content.
pub fn list_issues(repo_path: &Path) -> Result<Vec<String>> {
// List all refs under refs/gitlawb/issues/
@@ -74,9 +187,11 @@ pub fn list_issues(repo_path: &Path) -> Result<Vec<String>> {
.output()
.context("failed to run git for-each-ref")?;
// for-each-ref exits 0 with empty output when no refs match, so a nonzero
// exit is a real enumeration failure, not "no issues yet".
if !list_output.status.success() {
// No issues yet
return Ok(vec![]);
let stderr = String::from_utf8_lossy(&list_output.stderr);
anyhow::bail!("git for-each-ref failed: {}", stderr.trim());
}
let refs_str = String::from_utf8_lossy(&list_output.stdout);
@@ -88,16 +203,12 @@ pub fn list_issues(repo_path: &Path) -> Result<Vec<String>> {
continue;
}
// Read the blob content
let cat_output = Command::new("git")
.args(["cat-file", "blob", ref_name])
.current_dir(repo_path)
.output()
.context("failed to run git cat-file")?;
if cat_output.status.success() {
let content = String::from_utf8_lossy(&cat_output.stdout).to_string();
issues.push(content);
// Read the blob content. A ref that vanished between for-each-ref and
// here is skipped; a ref that resolves but fails to read propagates so
// a degraded object store errors the listing instead of under-reporting.
match read_issue_blob(repo_path, ref_name)? {
Some(content) => issues.push(content),
None => continue,
}
}
@@ -127,8 +238,12 @@ pub fn resolve_issue_id(repo_path: &Path, id_or_prefix: &str) -> Result<Option<S
.output()
.context("failed to run git for-each-ref")?;
// for-each-ref exits 0 with empty output when nothing matches, so a
// nonzero exit is a real enumeration failure (e.g. not a repo), not
// "issue not found".
if !list.status.success() {
return Ok(None);
let stderr = String::from_utf8_lossy(&list.stderr);
anyhow::bail!("git for-each-ref failed: {}", stderr.trim());
}
let output = String::from_utf8_lossy(&list.stdout);
@@ -161,8 +276,12 @@ pub fn close_issue(repo_path: &Path, issue_id: &str) -> Result<Option<String>> {
None => return Ok(None),
};
let raw = get_issue(repo_path, &full_id)?
.expect("ref existed in resolve but not in get — should be impossible");
// A ref that resolved and is now absent was deleted between the two calls;
// any other read failure propagates as an error rather than panic (#426).
let raw = match get_issue(repo_path, &full_id)? {
Some(raw) => raw,
None => return Ok(None),
};
let mut issue: serde_json::Value =
serde_json::from_str(&raw).context("invalid issue JSON in git ref")?;
@@ -181,18 +300,7 @@ pub fn get_issue(repo_path: &Path, issue_id: &str) -> Result<Option<String>> {
};
let ref_name = format!("refs/gitlawb/issues/{full_id}");
let cat_output = Command::new("git")
.args(["cat-file", "blob", &ref_name])
.current_dir(repo_path)
.output()
.context("failed to run git cat-file")?;
if !cat_output.status.success() {
return Ok(None);
}
let content = String::from_utf8_lossy(&cat_output.stdout).to_string();
Ok(Some(content))
read_issue_blob(repo_path, &ref_name)
}
#[cfg(test)]
@@ -294,4 +402,109 @@ mod tests {
let v: serde_json::Value = serde_json::from_str(&updated).unwrap();
assert_eq!(v["status"], "closed");
}
/// Overwrite the loose object behind an issue ref with garbage, so
/// `cat-file` fails while `rev-parse` still resolves the ref (#426).
fn corrupt_issue_object(dir: &TempDir, full_id: &str) {
let oid_out = Command::new("git")
.args(["rev-parse", &format!("refs/gitlawb/issues/{full_id}")])
.current_dir(dir.path())
.output()
.unwrap();
let oid = String::from_utf8(oid_out.stdout)
.unwrap()
.trim()
.to_string();
let obj = dir
.path()
.join(".git/objects")
.join(&oid[..2])
.join(&oid[2..]);
std::fs::remove_file(&obj).unwrap();
std::fs::write(&obj, b"garbage").unwrap();
}
#[test]
fn test_get_and_close_missing_issue_return_none() {
let dir = TempDir::new().unwrap();
init_repo(&dir);
assert_eq!(get_issue(dir.path(), "nosuch00").unwrap(), None);
assert_eq!(close_issue(dir.path(), "nosuch00").unwrap(), None);
}
// #426: a directory that is not a repo makes `cat-file --batch` exit
// nonzero; that failure is an error, not a quiet None.
#[test]
fn test_issue_read_on_non_repo_errors_instead_of_none() {
let dir = TempDir::new().unwrap();
let not_a_repo = dir.path().join("not-a-repo");
std::fs::create_dir_all(&not_a_repo).unwrap();
assert!(read_issue_blob(&not_a_repo, "refs/gitlawb/issues/deadbeef").is_err());
}
// #426: the ref name is constrained to the issues namespace and a safe
// charset before it is fed to git, even on stdin (a newline would smuggle
// a second `--batch` spec).
#[test]
fn test_issue_read_rejects_ref_outside_issues_namespace() {
let dir = TempDir::new().unwrap();
init_repo(&dir);
assert!(read_issue_blob(dir.path(), "refs/heads/main").is_err());
assert!(read_issue_blob(dir.path(), "refs/gitlawb/issues/../x").is_err());
}
// #426: a failed for-each-ref enumeration is an error, not an empty list.
#[test]
fn test_list_issues_on_non_repo_errors_instead_of_empty() {
let dir = TempDir::new().unwrap();
let not_a_repo = dir.path().join("not-a-repo");
std::fs::create_dir_all(&not_a_repo).unwrap();
assert!(list_issues(&not_a_repo).is_err());
}
// #426: the same enumeration failure inside resolve_issue_id must reach
// get_issue/close_issue as an error, not a "not found" None.
#[test]
fn test_get_and_close_on_non_repo_error_instead_of_none() {
let dir = TempDir::new().unwrap();
let not_a_repo = dir.path().join("not-a-repo");
std::fs::create_dir_all(&not_a_repo).unwrap();
assert!(get_issue(&not_a_repo, "nosuch00").is_err());
assert!(close_issue(&not_a_repo, "nosuch00").is_err());
}
// #426: a ref that resolves but whose object is corrupt is a read error,
// not an absent issue. `close_issue` used to `expect()` on that None and
// panic inside a request handler holding the write guard.
#[test]
fn test_corrupt_issue_object_errors_instead_of_panicking() {
let dir = TempDir::new().unwrap();
init_repo(&dir);
let full_id = "bad00000-0000-0000-0000-000000000000";
create_issue(dir.path(), full_id, r#"{"status":"open"}"#).unwrap();
corrupt_issue_object(&dir, full_id);
assert!(get_issue(dir.path(), full_id).is_err());
assert!(close_issue(dir.path(), full_id).is_err());
assert!(list_issues(dir.path()).is_err());
}
#[test]
fn test_list_issues_returns_all() {
let dir = TempDir::new().unwrap();
init_repo(&dir);
create_issue(
dir.path(),
"aaa00000-0000-0000-0000-000000000000",
r#"{"status":"open"}"#,
)
.unwrap();
create_issue(
dir.path(),
"bbb00000-0000-0000-0000-000000000000",
r#"{"status":"open"}"#,
)
.unwrap();
assert_eq!(list_issues(dir.path()).unwrap().len(), 2);
}
}