Add gazetteer to analyze worker

Pass a `Gazetteer` to the analyze worker to enable proper-name
correction. The gazetteer is loaded from disk at application startup. If
the directory is missing or unreadable, the worker will start without
proper-name correction capabilities.
This commit is contained in:
2026-04-16 17:27:09 +02:00
parent 1fd252f363
commit 5717b8f718
3 changed files with 36 additions and 3 deletions
+9 -1
View File
@@ -7,18 +7,26 @@ use tracing::{error, info, warn};
use super::{llm, prompt, AnalysisInput, AnalyzeReceiver, ANALYSIS_INPUT_FILE, DOCUMENT_FILE};
use crate::config::Config;
use crate::gazetteer::Gazetteer;
use crate::{BusyGuard, WorkerBusy};
/// Consume analyze jobs sequentially. The external LLM tolerates parallelism,
/// but sequential processing keeps the architecture simple and shields the
/// provider from bursts. Trivial to lift later via `tokio::spawn(process(..))`.
///
/// `_vocab` is the gazetteer for proper-name correction. Currently unused;
/// wired into `process()` in a follow-up step.
pub async fn run(
mut rx: AnalyzeReceiver,
config: Arc<Config>,
client: reqwest::Client,
worker_busy: WorkerBusy,
_vocab: Arc<Gazetteer>,
) {
info!("Analyze worker started");
info!(
vocab_entries = _vocab.len(),
"Analyze worker started"
);
let timeout = Duration::from_secs(config.llm_timeout_seconds);
while let Some(job) = rx.recv().await {