feat(harness): make tht schema columns glob/pattern-aware

At F4 (schema_linking) a model asking for a whole table family, e.g. `fact_sost_impianto_*`, used to hit a bare "tabella non nel catalogo" and stall without recovering. Now a pattern (containing * ? [) resolves to every matching catalog table and returns their columns (JSON becomes an array of per-table objects); exact names keep the original single-object contract. A non-glob miss also suggests sibling tables sharing the leading segment, to aid recovery. Verified live: `fact_sost_impianto_*` resolves the 20-table family on the psd catalog. Harness suite green (811 passed). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-18 13:24:20 +02:00
parent ccfa3a18bf
commit 9fbca06f7c
2 changed files with 108 additions and 12 deletions
@@ -38,3 +38,62 @@ def test_schema_columns_json(tmp_path, monkeypatch):
    assert data["table"] == "dim_patient"
    assert data["description"] == "Anagrafica"
    assert {"name": "cod_paz", "description": "Codice paziente", "type": "bigint", "pk": True} in data["columns"]
+
+
+def _write_family_catalog(tmp_path):
+    def _t(comment):
+        return TablePhysical(
+            comment=comment,
+            columns={"cod_paz": ColumnPhysical(type="bigint", pk=True, comment="Codice paziente")},
+        )
+
+    phys = PhysicalSchema(
+        database="d", schema="s", introspected_at=datetime(2026, 1, 1),
+        tables={
+            "fact_sost_impianto_pmk": _t("Sost PMK"),
+            "fact_sost_impianto_crt_d": _t("Sost CRT-D"),
+            "fact_impianto_pacemaker": _t("Impianto PMK"),
+        },
+    )
+    out = tmp_path / "artifacts" / "mschema" / "physical.yaml"
+    phys.to_yaml(out)
+    return out
+
+
+def _cfg(tmp_path):
+    cfg = tmp_path / "workspace.yaml"
+    cfg.write_text(
+        "database: {database: d, schema: s, user: u, password: p, transport: direct}\n"
+        f"paths: {{artifacts: {tmp_path/'artifacts'}, indexes: {tmp_path/'i'}, sessions: {tmp_path/'s'}}}\n"
+    )
+    return cfg
+
+
+def test_schema_columns_glob_resolves_the_matching_family(tmp_path):
+    _write_family_catalog(tmp_path)
+    res = CliRunner().invoke(
+        app, ["schema", "columns", "fact_sost_impianto_*", "--json", "-c", str(_cfg(tmp_path))]
+    )
+    assert res.exit_code == 0, res.output
+    data = json.loads(res.output)
+    assert isinstance(data, list)  # a pattern yields an array of per-table objects
+    assert sorted(d["table"] for d in data) == ["fact_sost_impianto_crt_d", "fact_sost_impianto_pmk"]
+
+
+def test_schema_columns_glob_without_matches_errors(tmp_path):
+    _write_family_catalog(tmp_path)
+    res = CliRunner().invoke(
+        app, ["schema", "columns", "fact_assente_*", "-c", str(_cfg(tmp_path))]
+    )
+    assert res.exit_code == 1
+    assert "nessuna tabella corrisponde al pattern" in res.output
+
+
+def test_schema_columns_exact_miss_suggests_siblings(tmp_path):
+    _write_family_catalog(tmp_path)
+    res = CliRunner().invoke(
+        app, ["schema", "columns", "fact_sost_impianto_xyz", "-c", str(_cfg(tmp_path))]
+    )
+    assert res.exit_code == 1
+    assert "tabella non nel catalogo" in res.output
+    assert "fact_sost_impianto_crt_d" in res.output  # sibling suggested to aid recovery