63 lines
2.2 KiB
Python
63 lines
2.2 KiB
Python
from pathlib import Path
|
|
from typing import Literal
|
|
|
|
import yaml
|
|
from pydantic import BaseModel, ValidationError
|
|
|
|
|
|
class EvidenceError(Exception):
|
|
pass
|
|
|
|
|
|
class EvidenceDoc(BaseModel):
|
|
id: str
|
|
title: str
|
|
# tier e status sono opzionali: la sola presenza di un documento basta a
|
|
# vettorizzarlo, quindi l'autore ETL non e' obbligato a compilarli.
|
|
tier: Literal["structural", "concept"] = "structural"
|
|
status: Literal["auto", "draft", "reviewed"] = "reviewed"
|
|
sources: list[str] = []
|
|
tables: list[str] = []
|
|
concepts: list[str] = []
|
|
body: str = ""
|
|
path: Path | None = None # valorizzato al load, escluso dal dump
|
|
|
|
@classmethod
|
|
def parse(cls, text: str, path: Path | None = None) -> "EvidenceDoc":
|
|
if not text.startswith("---\n"):
|
|
raise EvidenceError(f"frontmatter mancante in {path or '<testo>'}")
|
|
try:
|
|
_, fm, body = text.split("---\n", 2)
|
|
except ValueError as e:
|
|
raise EvidenceError(f"frontmatter malformato in {path or '<testo>'}") from e
|
|
meta = yaml.safe_load(fm)
|
|
if not isinstance(meta, dict):
|
|
raise EvidenceError(f"frontmatter non valido in {path or '<testo>'}")
|
|
try:
|
|
return cls.model_validate({**meta, "body": body.strip("\n"), "path": path})
|
|
except ValidationError as e:
|
|
raise EvidenceError(f"evidence non valida in {path or '<testo>'}:\n{e}") from e
|
|
|
|
def dump(self) -> str:
|
|
meta = self.model_dump(exclude={"body", "path"}, mode="json")
|
|
fm = yaml.safe_dump(meta, sort_keys=False, allow_unicode=True)
|
|
return f"---\n{fm}---\n{self.body}\n"
|
|
|
|
def save(self, path: Path) -> None:
|
|
path.parent.mkdir(parents=True, exist_ok=True)
|
|
path.write_text(self.dump())
|
|
self.path = path
|
|
|
|
|
|
def load_evidence_dir(root: Path) -> list[EvidenceDoc]:
|
|
"""Carica ricorsivamente tutte le evidence sotto `root`, preservando la
|
|
gerarchia per dominio. I file README (di sola navigazione) sono ignorati."""
|
|
docs: list[EvidenceDoc] = []
|
|
if not root.is_dir():
|
|
return docs
|
|
for f in sorted(root.rglob("*.md")):
|
|
if f.name.upper().startswith("README"):
|
|
continue
|
|
docs.append(EvidenceDoc.parse(f.read_text(), path=f))
|
|
return docs
|