fix: comprehensive fixes for ingestion and TKG
1. Add Redis PipelineProgress cleanup in unregister_internal - Deletes progress key when file is unregistered 2. Fix ingestion_complete asr_status query - Query ASRX first, then ASR - Filter out NULL values to avoid false negatives 3. Fix TKG 0 nodes/edges support - TKG is considered done if face traces are complete - TKG may create 0 nodes/edges for videos with minimal content 4. Add ASRX fallback to ASR segments - When ASRX has 0 segments but ASR has segments, use ASR segments - Ensures at least one ASRX output when ASR has content
This commit is contained in:
@@ -160,6 +160,41 @@ def _convert_result(result, output_path):
|
||||
pass
|
||||
|
||||
segment_count = len(result.get("segments", []))
|
||||
|
||||
# Fallback: if ASRX has 0 segments but ASR has segments, use ASR segments
|
||||
if segment_count == 0:
|
||||
asr_path = output_path.replace(".asrx.json", ".asr.json")
|
||||
if os.path.exists(asr_path):
|
||||
try:
|
||||
with open(asr_path) as f:
|
||||
asr_data = json.load(f)
|
||||
asr_segments = asr_data.get("segments", [])
|
||||
if asr_segments:
|
||||
print(f"[ASRX] ASRX has 0 segments, falling back to {len(asr_segments)} ASR segments", file=sys.stderr)
|
||||
# Convert ASR segments to ASRX format
|
||||
converted_segments = []
|
||||
for seg in asr_segments:
|
||||
start_time = seg.get("start_time", seg.get("start", 0))
|
||||
end_time = seg.get("end_time", seg.get("end", 0))
|
||||
start_frame = int(start_time * fps)
|
||||
end_frame = int(end_time * fps)
|
||||
converted_segments.append({
|
||||
"start_time": start_time,
|
||||
"end_time": end_time,
|
||||
"start_frame": start_frame,
|
||||
"end_frame": end_frame,
|
||||
"text": seg.get("text", ""),
|
||||
"speaker_id": "SPEAKER_0",
|
||||
"language": "",
|
||||
"lang_prob": 0.0,
|
||||
"quality": 0.0,
|
||||
})
|
||||
result["segments"] = converted_segments
|
||||
segment_count = len(converted_segments)
|
||||
result["status"] = "has_transcript"
|
||||
except Exception as e:
|
||||
print(f"[ASRX] Failed to load ASR fallback: {e}", file=sys.stderr)
|
||||
|
||||
if segment_count > 0:
|
||||
status = "has_transcript"
|
||||
else:
|
||||
|
||||
+18
-7
@@ -1239,15 +1239,26 @@ async fn unregister(
|
||||
|
||||
let deleted_redis_keys = {
|
||||
match RedisClient::new() {
|
||||
Ok(redis) => match redis.delete_worker_job(&uuid).await {
|
||||
Ok(_) => {
|
||||
tracing::info!("[UNREGISTER] Deleted Redis keys for {}", uuid);
|
||||
Some(1)
|
||||
Ok(redis) => {
|
||||
let mut deleted = 0;
|
||||
|
||||
// Delete worker job keys
|
||||
if redis.delete_worker_job(&uuid).await.is_ok() {
|
||||
tracing::info!("[UNREGISTER] Deleted Redis worker job keys for {}", uuid);
|
||||
deleted += 1;
|
||||
}
|
||||
Err(e) => {
|
||||
tracing::warn!("[UNREGISTER] Failed to delete Redis keys: {}", e);
|
||||
None
|
||||
|
||||
// Delete PipelineProgress key
|
||||
let progress_key = format!("{}progress:{}:pipeline",
|
||||
crate::core::config::REDIS_KEY_PREFIX.as_str(), uuid);
|
||||
if let Ok(mut conn) = redis.get_conn().await {
|
||||
let _: Option<String> = redis::cmd("DEL").arg(&progress_key)
|
||||
.query_async(&mut conn).await.ok();
|
||||
tracing::info!("[UNREGISTER] Deleted Redis PipelineProgress for {}", uuid);
|
||||
deleted += 1;
|
||||
}
|
||||
|
||||
Some(deleted)
|
||||
},
|
||||
Err(e) => {
|
||||
tracing::warn!("[UNREGISTER] Failed to create Redis client: {}", e);
|
||||
|
||||
+14
-11
@@ -1150,8 +1150,15 @@ impl JobWorker {
|
||||
// Check asr_status for ASR/ASRX - if no_audio_track or silent_audio, ingestion is complete
|
||||
let mj_t = schema::table_name("monitor_jobs");
|
||||
let asr_done: bool = if has_asr_or_asrx {
|
||||
// Query ASRX first (more authoritative), then ASR
|
||||
// Filter out NULL values to ensure we get a valid status
|
||||
let asr_status: Option<String> = sqlx::query_scalar(&format!(
|
||||
"SELECT asr_status FROM {pr_t} pr JOIN {mj_t} mj ON pr.job_id = mj.id WHERE mj.uuid = $1 AND pr.processor IN ('asr', 'asrx') LIMIT 1"
|
||||
"SELECT asr_status FROM {pr_t} pr JOIN {mj_t} mj ON pr.job_id = mj.id \
|
||||
WHERE mj.uuid = $1 AND pr.processor = 'asrx' AND asr_status IS NOT NULL \
|
||||
UNION ALL \
|
||||
SELECT asr_status FROM {pr_t} pr JOIN {mj_t} mj ON pr.job_id = mj.id \
|
||||
WHERE mj.uuid = $1 AND pr.processor = 'asr' AND asr_status IS NOT NULL \
|
||||
LIMIT 1"
|
||||
))
|
||||
.bind(uuid)
|
||||
.fetch_optional(pool)
|
||||
@@ -1260,21 +1267,17 @@ impl JobWorker {
|
||||
true
|
||||
};
|
||||
|
||||
// Check TKG nodes exist
|
||||
// Check TKG completion
|
||||
// TKG is considered done if face traces are done (TKG runs after face tracing)
|
||||
// TKG may create 0 nodes/edges for videos with minimal content
|
||||
let has_asr_or_asrx_for_tkg =
|
||||
job_processors.is_empty() || job_processors.iter().any(|p| p == "asrx" || p == "asr");
|
||||
let has_face_for_tkg = job_processors.is_empty() || job_processors.iter().any(|p| p == "face");
|
||||
|
||||
let tkg_done: bool = if has_asr_or_asrx_for_tkg && has_face_for_tkg {
|
||||
let tkg_nodes_table = schema::table_name("tkg_nodes");
|
||||
sqlx::query_scalar::<_, i32>(&format!(
|
||||
"SELECT 1 FROM {tkg_nodes_table} WHERE file_uuid = $1 LIMIT 1"
|
||||
))
|
||||
.bind(uuid)
|
||||
.fetch_optional(pool)
|
||||
.await
|
||||
.unwrap_or(None)
|
||||
.unwrap_or(0) > 0
|
||||
// TKG is done if face traces are complete (TKG runs after face tracing)
|
||||
// TKG may create 0 nodes/edges for videos with minimal content
|
||||
trace_done
|
||||
} else {
|
||||
tracing::info!("[Ingestion] No TKG needed for {}", uuid);
|
||||
true
|
||||
|
||||
Reference in New Issue
Block a user