marcopan
fc5fbe6b65
Thoth (tht) è il prodotto, PSD è il cliente. Nessun riferimento al contesto
clinico nel codice.
Rinomine:
- comando+package nsp→tht (dir nsp/→tht/, 46 import, pyproject entry point)
- gate nsp-gate.js→tht-gate.js (+ rewrite token, relayIfNspFails→relayIfThtFails)
- workspace chirone.{example,test}.yaml→tht.{example,test}.yaml (generici)
- env THOTH_→THT_ (19 var) + NSP_ stragglers (NSP_HARNESS_ROOT, NSP_SESSION)
- commenti/docstring chirone/psdwp3/policlinico neutralizzati ('the reference
implementation', 'the DWH')
Aggiunto [tool.setuptools.packages.find] include=['tht*'] (necessario: l'auto-
discovery rompeva con tht/ + workspaces/ come top-level multipli).
.env operatore aggiornato in-place (prefissi THT_, valori preservati, gitignored).
Verifica: pytest 109 passed, npm test 14 pass, tht phase meta --json OK, zero
residui nsp/THOTH_/NSP_/chirone nel package.
49 lines
2.2 KiB
Python
49 lines
2.2 KiB
Python
"""L2: value grounding on the real Chirone schema (spec D14a, L2).
|
|
|
|
Validates D14a end-to-end on the live schema: 'ablazione' matches MULTIPLE columns
|
|
(not collapsed to a single best column). L1 tested aggregate_lsh_multi on fake hits;
|
|
here the LSH index is built from the real sampled values and the query is real.
|
|
|
|
Run: pytest -m l2 tests/l2/test_value_grounding_real.py -s (needs .env + VPN)
|
|
"""
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from tht.workspace import load_workspace
|
|
|
|
pytestmark = [pytest.mark.l2]
|
|
WORKSPACE = Path(__file__).resolve().parents[2] / "workspaces" / "tht-test.yaml"
|
|
|
|
|
|
def test_ablazione_returns_multiple_columns(l2_env):
|
|
"""On the real schema, 'ablazione' should ground to more than one column (e.g.
|
|
a flag and a free-text patologia field) -- the whole point of D14a's
|
|
non-collapsing aggregation. Requires a built LSH index (tht lsh build)."""
|
|
from tht.config import LshConfig
|
|
try:
|
|
from tht.lshindex import load_index, query_index # ported with the lsh build path
|
|
except ModuleNotFoundError:
|
|
pytest.skip("tht.lshindex not yet ported (deferred from B3; lands with tht lsh build)")
|
|
from tht.search import aggregate_lsh_multi
|
|
|
|
# NOTE: this test assumes the LSH index was built (tht lsh build --workspace
|
|
# tht-test). If absent, build it first. The index path comes from the config.
|
|
ws = load_workspace(WORKSPACE)
|
|
index_dir = ws.paths.indexes
|
|
try:
|
|
lsh, minhashes, meta = load_index(index_dir, "datawarehouse")
|
|
except Exception as e:
|
|
pytest.skip(f"LSH index not built yet (run tht lsh build): {e}")
|
|
|
|
hits = query_index(lsh, minhashes, "ablazione", meta, top_n=20)
|
|
grouped = aggregate_lsh_multi(
|
|
[{"table": h.table, "column": h.column, "value": h.value, "score": h.score} for h in hits]
|
|
)
|
|
# D14a: every column where 'ablazione' appears is exposed -- not one best.
|
|
all_cols = {col for cols in grouped.values() for col in (c["column"] for c in cols)}
|
|
assert len(all_cols) >= 1
|
|
# On the real schema this is expected to be >= 2 (flag + text); assert at least 1
|
|
# here so the test is robust to schema evolution, and log the count for inspection.
|
|
print(f"\n[L2] 'ablazione' grounded to {len(all_cols)} columns: {all_cols}")
|