feat(preprocess): add resumable DWH jobs

harness/tht/cli/schema_cmd.py

@@ -44,6 +44,16 @@ def annotations_path(cfg) -> Path:
     return cfg.paths.artifacts / "mschema" / "annotations.yaml"
 
 
+def refresh_catalog(cfg, *, dwh=None):
+    """Run the existing catalog algorithm and persist its canonical output."""
+    target = dwh if dwh is not None else build_dwh(cfg)
+    physical = target.introspect()
+    _add_examples(target, physical, cfg.examples)
+    classify_all(physical, cfg.eligibility)
+    physical.to_yaml(physical_path(cfg))
+    return physical
+
+
 @schema_app.command("introspect")
 def introspect_cmd(
     config: Path = CONFIG_OPT,
@@ -80,14 +90,10 @@ def introspect_cmd(
             )
             return
     try:
-        dwh = build_dwh(cfg)
-        phys = dwh.introspect()
-        _add_examples(dwh, phys, cfg.examples)
-        classify_all(phys, cfg.eligibility)
+        phys = refresh_catalog(cfg)
     except Exception as e:
         typer.secho(f"ERRORE: {e}", fg=typer.colors.RED, err=True)
         raise typer.Exit(code=1)
-    phys.to_yaml(out)
     n_cols = sum(len(t.columns) for t in phys.tables.values())
     n_ignored = sum(
         1 for t in phys.tables.values() for c in t.columns.values() if not c.eligible