marcopan
eb3bde90e2
Ports the leaf data-layer modules and validates them: - mschema/ (models, eligibility, merge, render), db/ (connection, sampling, introspect, fetch_ca), rest/client.py -- renamed psdwp3->nsp, verbatim. - L0 (testcontainers, real Postgres): db connection read-only enforcement (psd_ro cannot CREATE/INSERT), introspect against a known schema (tables, columns, types, comments, FKs, enum, composite PK), sampling most-frequent values + truncation reporting. 15 tests, ~4s. - L1 (fake data): rest/client RPC contract (mocked transport -- X-API-Key header, payloads, base_url slash handling, HTTP/network error surfacing), mschema/render 3 formats (markdown, mschema-text, schema-dict) + eligibility rules (wide_text excluded, short_text/numeric/enum/temporal/ boolean eligible, annotation override wins). 25 tests. pyproject registers l0/l2 markers + addopts '-m not l2' (L2 opt-in). Deferred to their dependency-porting tasks: test_rrf.py (search needs vectorstore, B3) and the 11 CLI contract tests (need _guards/session, wired when each command lands). 'Not assumed reliable' now has real teeth for the data layer; CLI/search contracts follow.
91 lines
2.1 KiB
Python
91 lines
2.1 KiB
Python
from datetime import datetime
|
|
from pathlib import Path
|
|
from typing import Self
|
|
|
|
import yaml
|
|
from pydantic import BaseModel, Field
|
|
|
|
|
|
class _YamlModel(BaseModel):
|
|
def to_yaml(self, path: Path) -> None:
|
|
path.parent.mkdir(parents=True, exist_ok=True)
|
|
data = self.model_dump(by_alias=True, mode="json", exclude_defaults=False)
|
|
path.write_text(
|
|
yaml.safe_dump(data, sort_keys=False, allow_unicode=True, width=120)
|
|
)
|
|
|
|
@classmethod
|
|
def from_yaml(cls, path: Path) -> Self:
|
|
raw = yaml.safe_load(path.read_text())
|
|
return cls.model_validate(raw)
|
|
|
|
|
|
class ColumnPhysical(BaseModel):
|
|
type: str
|
|
nullable: bool = True
|
|
pk: bool = False
|
|
default: str | None = None
|
|
comment: str = ""
|
|
examples: list[str] = []
|
|
is_enum: bool = False
|
|
eligible: bool = True
|
|
eligibility_reason: str = ""
|
|
|
|
|
|
class ForeignKey(BaseModel):
|
|
columns: list[str]
|
|
ref_table: str
|
|
ref_columns: list[str]
|
|
name: str = ""
|
|
|
|
|
|
class Index(BaseModel):
|
|
name: str
|
|
columns: list[str]
|
|
unique: bool = False
|
|
primary: bool = False
|
|
type: str = "btree"
|
|
|
|
|
|
class TablePhysical(BaseModel):
|
|
comment: str = ""
|
|
row_count: int = 0 # stima da pg_class.reltuples
|
|
columns: dict[str, ColumnPhysical] = {}
|
|
foreign_keys: list[ForeignKey] = []
|
|
indexes: list[Index] = []
|
|
|
|
|
|
class PhysicalSchema(_YamlModel):
|
|
database: str
|
|
db_schema: str = Field(alias="schema")
|
|
introspected_at: datetime
|
|
tables: dict[str, TablePhysical] = {}
|
|
|
|
model_config = {"populate_by_name": True}
|
|
|
|
|
|
class ColumnAnnotation(BaseModel):
|
|
description: str = ""
|
|
synonyms: list[str] = []
|
|
concepts: list[str] = []
|
|
evidence: list[str] = []
|
|
notes: str = ""
|
|
eligible: bool | None = None
|
|
|
|
|
|
class TableAnnotation(BaseModel):
|
|
description: str = ""
|
|
concepts: list[str] = []
|
|
notes: str = ""
|
|
columns: dict[str, ColumnAnnotation] = {}
|
|
|
|
|
|
class Annotations(_YamlModel):
|
|
tables: dict[str, TableAnnotation] = {}
|
|
|
|
@classmethod
|
|
def from_yaml(cls, path: Path) -> "Annotations":
|
|
if not path.exists():
|
|
return cls()
|
|
return super().from_yaml(path)
|