pipeline: extract read_warnings for reuse by startup discovery

src/songtrace/pipeline.py

@@ -45,6 +45,12 @@ def song_slug(inp: SongInput) -> str:
     name = f"{inp.artist} - {inp.title}"
     return name.replace("/", "").replace("\0", "")
 
+def read_warnings(work: Path) -> list[str]:
+    notes_file = work / "notes_sec.json"
+    if not notes_file.exists():
+        return []
+    return json.loads(notes_file.read_text()).get("warnings", [])
+
 def _real_stages() -> list[Stage]:
     from . import stages
     return stages.all_stages()
@@ -69,8 +75,5 @@ def run_pipeline(inp: SongInput, cfg: Config, log=print,
             continue
         log(f"[{stage.name}] running")
         stage.run(ctx)
-    warnings = []
-    notes_file = work / "notes_sec.json"
-    if notes_file.exists():
-        warnings = json.loads(notes_file.read_text()).get("warnings", [])
-    return PipelineResult(output_dir=cfg.output_dir / song_slug(inp), warnings=warnings)
+    return PipelineResult(output_dir=cfg.output_dir / song_slug(inp),
+                          warnings=read_warnings(work))

tests/test_pipeline.py

@@ -1,7 +1,7 @@
 import json
 from pathlib import Path
 from songtrace.config import Config
-from songtrace.pipeline import SongInput, Stage, run_pipeline, song_slug
+from songtrace.pipeline import SongInput, Stage, read_warnings, run_pipeline, song_slug
 
 def make_cfg(tmp_path):
     return Config(whisper_url="http://x/v1", output_dir=tmp_path / "out",
@@ -46,3 +46,10 @@ def test_warnings_surfaced(tmp_path):
     st = Stage(name="n", outputs=lambda ctx: [ctx.work / "n.done"], run=run)
     result = run_pipeline(inp, cfg, log=lambda m: None, stages=[st])
     assert result.warnings == ["w1"]
+
+def test_read_warnings_is_empty_without_a_notes_file(tmp_path):
+    assert read_warnings(tmp_path) == []
+
+def test_read_warnings_reads_the_notes_file(tmp_path):
+    (tmp_path / "notes_sec.json").write_text(json.dumps({"warnings": ["w1", "w2"]}))
+    assert read_warnings(tmp_path) == ["w1", "w2"]