fix(preprocess): restrict DWH root claims to writers

This commit is contained in:
2026-07-12 07:00:51 +02:00
parent c4dd6c8900
commit 22e806a41b
6 changed files with 238 additions and 49 deletions
+16 -2
View File
@@ -5,6 +5,8 @@ from types import SimpleNamespace
from typer.testing import CliRunner
from tht.cli import app
from tht.config import load_config
from tht.jobs.dwh_pipeline import DwhPreprocessPipeline, config_dwh_binding
from tht.mschema.models import ColumnPhysical, PhysicalSchema, TablePhysical
from tht.vectorstore.embeddings import EmbeddingsError
@@ -43,11 +45,11 @@ class _FakeSearcher:
def _workspace(tmp_path, with_session=None):
PhysicalSchema(
physical = PhysicalSchema(
database="d", schema="s", introspected_at=datetime(2026, 1, 1),
tables={"fact_ablazione": TablePhysical(
comment="Ablazioni", columns={"cod_paz": ColumnPhysical(type="bigint")})},
).to_yaml(tmp_path / "artifacts" / "mschema" / "physical.yaml")
)
cfg = tmp_path / "workspace.yaml"
cfg.write_text(
"database: {database: d, schema: s, user: u, password: p, transport: direct}\n"
@@ -56,6 +58,18 @@ def _workspace(tmp_path, with_session=None):
f"paths: {{artifacts: {tmp_path/'artifacts'}, indexes: {tmp_path/'i'}, "
f"sessions: {tmp_path/'sessions'}}}\n"
)
binding = config_dwh_binding(load_config(cfg))
DwhPreprocessPipeline(
workspace_id=binding["workspace_id"], workspace_root=tmp_path,
config_fingerprint=binding["config_fingerprint"],
input_fingerprint=binding["input_fingerprint"],
introspect=lambda output: physical.to_yaml(output),
build_lsh=lambda _physical, output: [
(output / name).write_text("index")
for name in ("s_lsh.pkl", "s_minhashes.pkl", "s_meta.json")
],
lsh_filenames=("s_lsh.pkl", "s_minhashes.pkl", "s_meta.json"),
).run()
if with_session:
sdir = tmp_path / "sessions" / with_session
sdir.mkdir(parents=True)