fix: stream transfers and close gaps against the Python client

A review against the Python client, which shares this client's config
and login cache, found the transfers holding whole files in memory and
several commands answering differently from their Python counterparts.

- Stream uploads and downloads instead of buffering the whole file, so
  memory no longer scales with file size times concurrency. Uploads
  still declare a Content-Length rather than going out chunked.
- Write a download beside its destination and move it into place once
  complete, and refuse a destination that cannot be written, so a
  failed transfer leaves what was already there untouched.
- Report the server's own error detail instead of the bare status.
- List locked sub-folders in `ls --json --recursive` using the given
  password and skip only those that cannot be unlocked, instead of
  failing the whole listing.
- Name each folder's laboratory in JSON output and sort its entries,
  matching the Python client's schema and order.
- Ask the server who is logged in for `whoami`, rather than trusting
  the cached name.
- Collapse repeated separators and refuse `..` in remote paths.
- Fall back to the API when a laboratory is missing from the cache, so
  a newly added one no longer needs a fresh login.
- Verify the login cache digest on read, as the Python client does.
- Accept `-e` as the short form of `--exclude`.
- Satisfy clippy and rustfmt across the crate.
This commit is contained in:
2026-09-04 16:31:14 +09:00
parent c24a285cf5
commit a16f73543d
26 changed files with 899 additions and 324 deletions
+67 -6
View File
@@ -139,14 +139,32 @@ fn write_cache_file(cache_path: &Path, cache: &Cache) -> Result<(), anyhow::Erro
}
fn parse_cache(remote: &str, data: &str) -> Result<Cache, anyhow::Error> {
serde_json::from_str::<Cache>(data).map_err(|e| {
let cache = serde_json::from_str::<Cache>(data).map_err(|e| {
anyhow!(
"Cache for `{}` is invalid or outdated ({}). Run `mdrs login {}` to refresh it.",
remote,
e,
remote
)
})
})?;
// The digest is what says the file is still the one this client wrote. The Python
// client checks it on every read and the two share the file, so a cache one of them
// would refuse must not be honoured by the other.
let expected = compute_digest(
cache.user.as_ref(),
&cache.token.access,
&cache.token.refresh,
&cache.laboratories,
);
if cache.digest != expected {
bail!(
"Cache for `{}` has been altered or was written by an incompatible version. \
Run `mdrs login {}` to refresh it.",
remote,
remote
);
}
Ok(cache)
}
fn load_cache_from_dir(remote: &str, config_dir: &Path) -> Result<Cache, anyhow::Error> {
@@ -213,7 +231,11 @@ fn load_cache_if_present_from_dir(
};
let cache = match parse_cache(remote, &data) {
Ok(cache) => cache,
Err(_) => {
Err(e) => {
// Said out loud before the credentials go. The alternative is a command that
// quietly carries on anonymously and fails later for a reason that looks
// unrelated to the cache it just threw away.
eprintln!("{e}");
remove_cache_in_dir(remote, config_dir)?;
return Ok(None);
}
@@ -290,6 +312,9 @@ pub async fn load_cache_with_token_refresh(remote: &str) -> Result<Cache, anyhow
let lock_file = fs::OpenOptions::new()
.write(true)
.create(true)
// Nothing is ever written into it: the file exists only to be flocked, and
// truncating it would touch a file other processes are holding open.
.truncate(false)
.open(&lock_path)?;
lock_file.lock_exclusive()?;
@@ -331,6 +356,9 @@ async fn load_cache_with_token_refresh_optional_from_dir(
let lock_file = fs::OpenOptions::new()
.write(true)
.create(true)
// Nothing is ever written into it: the file exists only to be flocked, and
// truncating it would touch a file other processes are holding open.
.truncate(false)
.open(&lock_path)?;
lock_file.lock_exclusive()?;
@@ -443,7 +471,7 @@ mod tests {
use tempfile::tempdir;
fn sample_cache(username: &str) -> Cache {
Cache {
let mut cache = Cache {
user: Some(CacheUser {
id: 1,
username: username.to_string(),
@@ -462,8 +490,15 @@ mod tests {
full_name: "Laboratory".to_string(),
}],
},
digest: format!("digest-{username}"),
}
digest: String::new(),
};
cache.digest = compute_digest(
cache.user.as_ref(),
&cache.token.access,
&cache.token.refresh,
&cache.laboratories,
);
cache
}
fn remote_name(prefix: &str, config_dir: &Path) -> String {
@@ -575,6 +610,25 @@ mod tests {
assert!(loaded.is_none());
}
/// A cache whose contents no longer match its digest is not a session to act on.
#[test]
fn load_cache_refuses_a_tampered_cache() {
let dir = tempdir().unwrap();
let remote = remote_name("tampered", dir.path());
let mut cache = sample_cache("alice");
persist_cache_in_dir(&remote, dir.path(), &cache).unwrap();
// Someone edits the stored token but leaves the digest as it was.
cache.token.access = "someone-elses-access".to_string();
let cache_path = cache_file_path_in(dir.path(), &remote);
fs::write(&cache_path, serde_json::to_vec_pretty(&cache).unwrap()).unwrap();
invalidate_cached_entry(dir.path(), &remote);
let err = load_cache_from_dir(&remote, dir.path()).unwrap_err();
assert!(err.to_string().contains("has been altered"));
}
#[test]
fn load_cache_if_present_clears_invalid_cache() {
let dir = tempdir().unwrap();
@@ -597,6 +651,13 @@ mod tests {
let mut cache = sample_cache("alice");
cache.token.access = make_jwt_with_exp(0);
cache.token.refresh = make_jwt_with_exp(0);
// Re-stamped, so this exercises the expired session rather than the digest check.
cache.digest = compute_digest(
cache.user.as_ref(),
&cache.token.access,
&cache.token.refresh,
&cache.laboratories,
);
persist_cache_in_dir(&remote, dir.path(), &cache).unwrap();
let loaded = load_cache_with_token_refresh_optional_from_dir(&remote, dir.path())