Files
marcopan fc5fbe6b65 refactor(harness): renaming prodotto tht (Onda -1)
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.
2026-06-27 10:33:16 +02:00

203 lines
7.5 KiB
Python

from datetime import UTC, datetime
from sqlalchemy import Engine, text
from tht.mschema.models import (
ColumnPhysical,
ForeignKey,
Index,
PhysicalSchema,
TablePhysical,
)
# Query adattate da thoth_sqldb2 (Apache 2.0) — vedi src/tht/vendor/VENDORED.md.
_TABLES_Q = text("""
SELECT c.relname AS table_name,
COALESCE(d.description, '') AS comment,
GREATEST(c.reltuples::bigint, 0) AS row_count
FROM pg_class c
JOIN pg_namespace n ON n.oid = c.relnamespace
LEFT JOIN pg_description d ON d.objoid = c.oid AND d.objsubid = 0
WHERE c.relkind IN ('r', 'p') AND n.nspname = :schema
ORDER BY c.relname
""")
_COLUMNS_Q = text("""
SELECT a.attname AS column_name,
format_type(a.atttypid, a.atttypmod) AS data_type,
(NOT a.attnotnull) AS is_nullable,
pg_get_expr(d.adbin, d.adrelid) AS column_default,
COALESCE(pgd.description, '') AS comment,
(ty.typtype = 'e') AS is_enum,
EXISTS (
SELECT 1 FROM pg_index i
WHERE i.indrelid = c.oid AND i.indisprimary AND a.attnum = ANY (i.indkey)
) AS is_pk
FROM pg_class c
JOIN pg_namespace n ON n.oid = c.relnamespace
JOIN pg_attribute a ON a.attrelid = c.oid
JOIN pg_type ty ON ty.oid = a.atttypid
LEFT JOIN pg_attrdef d ON d.adrelid = c.oid AND d.adnum = a.attnum
LEFT JOIN pg_description pgd ON pgd.objoid = c.oid AND pgd.objsubid = a.attnum
WHERE c.relname = :table_name AND n.nspname = :schema
AND a.attnum > 0 AND NOT a.attisdropped
ORDER BY a.attnum
""")
_FOREIGN_KEYS_Q = text("""
SELECT con.conname AS constraint_name,
rel.relname AS source_table,
a.attname AS source_column,
frel.relname AS target_table,
fa.attname AS target_column,
src.ord
FROM pg_constraint con
JOIN pg_class rel ON rel.oid = con.conrelid
JOIN pg_namespace ns ON ns.oid = rel.relnamespace
JOIN pg_class frel ON frel.oid = con.confrelid
JOIN unnest(con.conkey) WITH ORDINALITY AS src(attnum, ord) ON true
JOIN pg_attribute a ON a.attrelid = con.conrelid AND a.attnum = src.attnum
JOIN unnest(con.confkey) WITH ORDINALITY AS dst(attnum, ord) ON dst.ord = src.ord
JOIN pg_attribute fa ON fa.attrelid = con.confrelid AND fa.attnum = dst.attnum
WHERE con.contype = 'f' AND ns.nspname = :schema
ORDER BY rel.relname, con.conname, src.ord
""")
_INDEXES_Q = text("""
SELECT i.relname AS index_name,
t.relname AS table_name,
ix.indisunique AS is_unique,
ix.indisprimary AS is_primary,
am.amname AS index_type,
array_agg(a.attname ORDER BY a.attnum) AS columns
FROM pg_index ix
JOIN pg_class i ON i.oid = ix.indexrelid
JOIN pg_class t ON t.oid = ix.indrelid
JOIN pg_namespace n ON n.oid = t.relnamespace
JOIN pg_am am ON am.oid = i.relam
JOIN pg_attribute a ON a.attrelid = t.oid AND a.attnum = ANY (ix.indkey)
WHERE n.nspname = :schema
GROUP BY i.relname, t.relname, ix.indisunique, ix.indisprimary, am.amname
ORDER BY t.relname, i.relname
""")
class IntrospectionError(Exception):
pass
def introspect(engine: Engine, database: str, schema: str) -> PhysicalSchema:
with engine.connect() as conn:
exists = conn.execute(
text("SELECT 1 FROM pg_namespace WHERE nspname = :schema"), {"schema": schema}
).scalar()
if not exists:
raise IntrospectionError(f"Schema inesistente: {schema}")
tables: dict[str, TablePhysical] = {}
for trow in conn.execute(_TABLES_Q, {"schema": schema}):
columns: dict[str, ColumnPhysical] = {}
for crow in conn.execute(
_COLUMNS_Q, {"table_name": trow.table_name, "schema": schema}
):
columns[crow.column_name] = ColumnPhysical(
type=crow.data_type,
nullable=bool(crow.is_nullable),
pk=bool(crow.is_pk),
default=crow.column_default,
comment=crow.comment,
is_enum=bool(crow.is_enum),
)
tables[trow.table_name] = TablePhysical(
comment=trow.comment, row_count=trow.row_count, columns=columns
)
# FK raggruppate per (tabella, constraint), ordinate per posizione
grouped: dict[tuple[str, str], ForeignKey] = {}
for row in conn.execute(_FOREIGN_KEYS_Q, {"schema": schema}):
key = (row.source_table, row.constraint_name)
fk = grouped.setdefault(
key,
ForeignKey(
columns=[], ref_table=row.target_table, ref_columns=[],
name=row.constraint_name,
),
)
fk.columns.append(row.source_column)
fk.ref_columns.append(row.target_column)
for (table_name, _), fk in grouped.items():
if table_name in tables:
tables[table_name].foreign_keys.append(fk)
for row in conn.execute(_INDEXES_Q, {"schema": schema}):
if row.table_name in tables:
tables[row.table_name].indexes.append(
Index(
name=row.index_name,
columns=list(row.columns),
unique=bool(row.is_unique),
primary=bool(row.is_primary),
type=row.index_type,
)
)
return PhysicalSchema(
database=database,
schema=schema,
introspected_at=datetime.now(UTC),
tables=tables,
)
def introspect_rest(client, database: str, schema: str) -> PhysicalSchema:
"""Introspezione via REST (rpc `list_tables`/`table_columns`/`table_comments`/
`table_foreign_keys`). Limiti rispetto al diretto: niente indici (nessun rpc) e
`is_enum` non disponibile (default False)."""
tables: dict[str, TablePhysical] = {}
for trow in client.list_tables(schema):
if trow.get("type") != "TABLE":
continue # le viste sono fuori scope (come l'introspezione diretta)
table_name = trow["table"]
col_comments = {
c["name"]: (c.get("comment") or "")
for c in client.table_comments(schema, table_name)
if c.get("object") == "COLUMN"
}
columns: dict[str, ColumnPhysical] = {}
for crow in client.table_columns(schema, table_name):
name = crow["column"]
columns[name] = ColumnPhysical(
type=crow["type"],
nullable=bool(crow.get("nullable", True)),
pk=bool(crow.get("pk", False)),
default=crow.get("default"),
comment=col_comments.get(name, ""),
)
foreign_keys: list[ForeignKey] = []
for fk in client.table_foreign_keys(schema, table_name):
foreign_keys.append(
ForeignKey(
columns=fk.get("columns") or [fk["column"]],
ref_table=fk.get("ref_table") or fk["target_table"],
ref_columns=fk.get("ref_columns") or [fk["target_column"]],
name=fk.get("name", ""),
)
)
tables[table_name] = TablePhysical(
comment=trow.get("comment") or "",
row_count=int(trow.get("rows") or 0),
columns=columns,
foreign_keys=foreign_keys,
)
return PhysicalSchema(
database=database,
schema=schema,
introspected_at=datetime.now(UTC),
tables=tables,
)