Brummel
c15590f3e0
This commit changes the way transcriptions are stored and accessed. Instead of using plain text files (`.transcript.txt`), transcriptions will now be part of a JSON metadata file (`<stem>.json`). This allows for richer metadata to be stored alongside the transcript, such as duration, and provides a more robust mechanism for tracking transcription states. The changes include: - Updating documentation and code to reflect the new `.json` file extension. - Modifying file handling logic to read and write JSON metadata. - Adjusting tests to accommodate the new file format.
111 lines
4.1 KiB
Rust
111 lines
4.1 KiB
Rust
//! Regression test: a case whose recordings are all `.m4a.failed`
|
|
//! (permanent transcription failures — ffmpeg corrupt audio or Whisper
|
|
//! 4xx) must produce an `OnelinerState::Empty` automatically, so the UI
|
|
//! has a durable terminal state instead of relying on the on-render
|
|
//! `compute_oneliner_display` fallback.
|
|
//!
|
|
//! The historical bug path: `.m4a.failed`-only cases were skipped by the
|
|
//! recovery scan because `has_any_transcript` only looked for transcript
|
|
//! sidecars and ignored failure markers. `update_oneliner` therefore
|
|
//! never ran, so no `oneliner.json` was written. The UI masked the
|
|
//! symptom with its `non_failed_count == 0` fallback — but a future
|
|
//! refactor of that fallback would regress the case. The fix makes
|
|
//! `has_any_transcript` count `.m4a.failed` too, so `update_oneliner`
|
|
//! runs, sees no content transcripts, and settles the case to `Empty`
|
|
//! through the same terminal branch used for silent-only cases.
|
|
|
|
mod common;
|
|
|
|
use std::sync::Arc;
|
|
use std::sync::atomic::{AtomicBool, Ordering};
|
|
use std::time::Duration;
|
|
|
|
use doctate_common::oneliners::OnelinerState;
|
|
use doctate_server::events;
|
|
use doctate_server::gazetteer::Gazetteer;
|
|
use doctate_server::{
|
|
AnalyzeBusy, OnelinerHealBusy, PipelineState, TranscribeBusy, WorkerBusy, analyze, transcribe,
|
|
};
|
|
use tempfile::tempdir;
|
|
use wiremock::matchers::{method, path as wm_path};
|
|
use wiremock::{Mock, MockServer, ResponseTemplate};
|
|
|
|
use common::{ONELINER_FILENAME, TestConfig};
|
|
|
|
#[tokio::test]
|
|
async fn failed_only_case_settles_to_empty_without_llm_call() {
|
|
let data = tempdir().unwrap();
|
|
let slug = "dr_test";
|
|
let user_root = data.path().join(slug);
|
|
let case_dir = user_root.join("case-failed");
|
|
std::fs::create_dir_all(&case_dir).unwrap();
|
|
// Seed: only a `.m4a.failed` file. No transcript, no plain .m4a.
|
|
std::fs::write(case_dir.join("2026-04-15T20-30-00Z.m4a.failed"), b"x").unwrap();
|
|
|
|
// Ollama must NOT be called — nothing to summarize for a failed-only
|
|
// case. `.expect(0)` fails the test (on MockServer drop) if any
|
|
// request arrived.
|
|
let mock = MockServer::start().await;
|
|
Mock::given(method("POST"))
|
|
.and(wm_path("/api/chat"))
|
|
.respond_with(ResponseTemplate::new(200))
|
|
.expect(0)
|
|
.mount(&mock)
|
|
.await;
|
|
|
|
let (_config, settings) = TestConfig::new()
|
|
.with_data_path(data.path().to_path_buf())
|
|
.with_ollama(mock.uri())
|
|
.build_pair();
|
|
|
|
let vocab = Arc::new(Gazetteer::empty());
|
|
let events_tx = events::channel();
|
|
let http_client = reqwest::Client::new();
|
|
let (tx_a, _rx_a) = analyze::channel();
|
|
let (tx_t, _rx_t) = transcribe::channel();
|
|
|
|
let heal_busy: WorkerBusy = Arc::new(AtomicBool::new(false));
|
|
let pipeline = PipelineState {
|
|
analyze_busy: AnalyzeBusy(Arc::new(AtomicBool::new(false))),
|
|
analyze_tx: tx_a,
|
|
transcribe_busy: TranscribeBusy(Arc::new(AtomicBool::new(false))),
|
|
transcribe_tx: tx_t,
|
|
oneliner_heal_busy: OnelinerHealBusy(heal_busy.clone()),
|
|
oneliner_locks: doctate_server::oneliner_locks::OnelinerLocks::new(),
|
|
};
|
|
|
|
pipeline
|
|
.heal_orphans_if_idle(
|
|
&user_root,
|
|
slug,
|
|
&http_client,
|
|
&settings,
|
|
&vocab,
|
|
&events_tx,
|
|
)
|
|
.await;
|
|
|
|
// Heal spawn drops the busy flag on completion — poll until idle.
|
|
let start = std::time::Instant::now();
|
|
while heal_busy.load(Ordering::Acquire) {
|
|
if start.elapsed() > Duration::from_secs(5) {
|
|
panic!("oneliner heal did not finish within 5s");
|
|
}
|
|
tokio::time::sleep(Duration::from_millis(25)).await;
|
|
}
|
|
|
|
let path = case_dir.join(ONELINER_FILENAME);
|
|
assert!(
|
|
path.exists(),
|
|
"expected oneliner.json to be written for failed-only case"
|
|
);
|
|
let bytes = std::fs::read(&path).unwrap();
|
|
let state: OnelinerState = serde_json::from_slice(&bytes).unwrap();
|
|
assert!(
|
|
matches!(state, OnelinerState::Empty { .. }),
|
|
"expected OnelinerState::Empty, got {state:?}"
|
|
);
|
|
|
|
// Mock.drop() runs here — `.expect(0)` panics if Ollama was touched.
|
|
}
|