Add stage-2 metadata enrichment pipeline for known files
Known-classified files now flow to a second queue with its own worker pool that extracts metadata via exiftool and writes a normalized JSON sidecar next to the file in done/, leaving the original bytes untouched. - Two-stage pipeline: spool/ → classify → known/ → enrich → done/; unknowns park in unknown/ as a seam for a future pool - src/metadata.jl: exiftool -json -G -n with timeout, normalized schema (file_type, mime_type, author, created_by, dimensions, ...) + raw dump; degraded sidecar on extraction failure rather than quarantine - Sidecar-first commit so a file in done/ always has its sidecar - Parametrized worker_loop with classify/enrich handlers; blocking backpressure on a full known queue (never drop a classified file) - Stage-aware recovery: spool/ and known/ resume at their correct stage - Ordered drain: close stage-1 and wait its workers (the known queue's only producer) before closing the known queue - exiftool required at startup (fail-fast); new FS_KNOWN_*/FS_UNKNOWN_DIR/ FS_EXIFTOOL_TIMEOUT config knobs; combined-pool thread warning
This commit is contained in:
@@ -7,10 +7,18 @@ Base.@kwdef struct Config
|
||||
port::Int = 8080
|
||||
worker_count::Int = Threads.nthreads()
|
||||
queue_capacity::Int = 1000
|
||||
spool_dir::String = "data/spool" # files land here on intake (pending)
|
||||
done_dir::String = "data/done" # files move here after successful processing
|
||||
# Stage 2 (enrichment) has its own pool + queue: exiftool work is process-spawn
|
||||
# and I/O bound, a different cost profile than the CPU-bound Lux classify, so
|
||||
# the two pools are tuned independently.
|
||||
known_worker_count::Int = Threads.nthreads()
|
||||
known_queue_capacity::Int = 1000
|
||||
spool_dir::String = "data/spool" # files land here on intake (pending classification)
|
||||
known_dir::String = "data/known" # classified-known, awaiting enrichment (stage 2)
|
||||
unknown_dir::String = "data/unknown" # classified-unknown, parked for a future pipeline
|
||||
done_dir::String = "data/done" # fully enriched known files (+ .meta.json sidecars)
|
||||
failed_dir::String = "data/failed" # files move here if a worker throws
|
||||
model_path::String = "model/classifier.jld2" # committed classifier artifact, loaded at startup
|
||||
exiftool_timeout::Int = 30 # seconds before a stuck exiftool is killed → degraded sidecar
|
||||
end
|
||||
|
||||
"""
|
||||
@@ -22,26 +30,35 @@ and for `FileServer.run(; port=...)`).
|
||||
|
||||
Recognised variables:
|
||||
FS_HOST, FS_PORT, FS_WORKERS, FS_QUEUE_CAPACITY,
|
||||
FS_SPOOL_DIR, FS_DONE_DIR, FS_FAILED_DIR, FS_MODEL_PATH
|
||||
FS_KNOWN_WORKERS, FS_KNOWN_QUEUE_CAPACITY,
|
||||
FS_SPOOL_DIR, FS_KNOWN_DIR, FS_UNKNOWN_DIR, FS_DONE_DIR, FS_FAILED_DIR,
|
||||
FS_MODEL_PATH, FS_EXIFTOOL_TIMEOUT
|
||||
"""
|
||||
function config_from_env(; host=nothing, port=nothing, worker_count=nothing,
|
||||
queue_capacity=nothing, spool_dir=nothing,
|
||||
done_dir=nothing, failed_dir=nothing, model_path=nothing)
|
||||
queue_capacity=nothing, known_worker_count=nothing,
|
||||
known_queue_capacity=nothing, spool_dir=nothing,
|
||||
known_dir=nothing, unknown_dir=nothing, done_dir=nothing,
|
||||
failed_dir=nothing, model_path=nothing, exiftool_timeout=nothing)
|
||||
Config(
|
||||
host = something(host, get(ENV, "FS_HOST", "127.0.0.1")),
|
||||
port = something(port, parse(Int, get(ENV, "FS_PORT", "8080"))),
|
||||
worker_count = something(worker_count, parse(Int, get(ENV, "FS_WORKERS", string(Threads.nthreads())))),
|
||||
queue_capacity = something(queue_capacity, parse(Int, get(ENV, "FS_QUEUE_CAPACITY", "1000"))),
|
||||
spool_dir = something(spool_dir, get(ENV, "FS_SPOOL_DIR", "data/spool")),
|
||||
done_dir = something(done_dir, get(ENV, "FS_DONE_DIR", "data/done")),
|
||||
failed_dir = something(failed_dir, get(ENV, "FS_FAILED_DIR", "data/failed")),
|
||||
model_path = something(model_path, get(ENV, "FS_MODEL_PATH", "model/classifier.jld2")),
|
||||
host = something(host, get(ENV, "FS_HOST", "127.0.0.1")),
|
||||
port = something(port, parse(Int, get(ENV, "FS_PORT", "8080"))),
|
||||
worker_count = something(worker_count, parse(Int, get(ENV, "FS_WORKERS", string(Threads.nthreads())))),
|
||||
queue_capacity = something(queue_capacity, parse(Int, get(ENV, "FS_QUEUE_CAPACITY", "1000"))),
|
||||
known_worker_count = something(known_worker_count, parse(Int, get(ENV, "FS_KNOWN_WORKERS", string(Threads.nthreads())))),
|
||||
known_queue_capacity = something(known_queue_capacity, parse(Int, get(ENV, "FS_KNOWN_QUEUE_CAPACITY", "1000"))),
|
||||
spool_dir = something(spool_dir, get(ENV, "FS_SPOOL_DIR", "data/spool")),
|
||||
known_dir = something(known_dir, get(ENV, "FS_KNOWN_DIR", "data/known")),
|
||||
unknown_dir = something(unknown_dir, get(ENV, "FS_UNKNOWN_DIR", "data/unknown")),
|
||||
done_dir = something(done_dir, get(ENV, "FS_DONE_DIR", "data/done")),
|
||||
failed_dir = something(failed_dir, get(ENV, "FS_FAILED_DIR", "data/failed")),
|
||||
model_path = something(model_path, get(ENV, "FS_MODEL_PATH", "model/classifier.jld2")),
|
||||
exiftool_timeout = something(exiftool_timeout, parse(Int, get(ENV, "FS_EXIFTOOL_TIMEOUT", "30"))),
|
||||
)
|
||||
end
|
||||
|
||||
"Create the spool/done/failed directories if they don't already exist."
|
||||
"Create all the pipeline-stage directories if they don't already exist."
|
||||
function ensure_dirs(cfg::Config)
|
||||
for d in (cfg.spool_dir, cfg.done_dir, cfg.failed_dir)
|
||||
for d in (cfg.spool_dir, cfg.known_dir, cfg.unknown_dir, cfg.done_dir, cfg.failed_dir)
|
||||
mkpath(d)
|
||||
end
|
||||
return nothing
|
||||
|
||||
Reference in New Issue
Block a user