Seconda parte della replica soccorso istruttorio speculare al BE Gepafin.
Completata: scheduler cron (expire + reminder), upload documenti istruttore
e benef, fix duplicati config.
==SCHEDULER (app/scheduler.py NUOVO)==
APScheduler BackgroundScheduler integrato nel lifespan FastAPI.
Due cron attivi (timezone Europe/Rome):
expire_amendments() - cron 01:05 ogni notte
Speculare a ApplicationAmendmentScheduler.processAmendmentExpirationScheduler.
Trova amendment AWAITING con deadline < today, passa a EXPIRED.
Rimette pratica a UNDER_REVIEW se non ha altri amendment aperti.
Ritorna dict stats per logging/test.
queue_reminders() - cron 09:00 ogni mattina
Speculare a ExpirationScheduler.processAmendmentExpiration (data-driven).
Legge remission_expiration_config (type='AMENDMENT', interval_days=N),
per ogni riga trova amendment con deadline esattamente today+N e setta
pec_retry_after (marker che il BE vede via /internal pending-reminder).
Multipli row = multipli reminder (seed: 7gg + 2gg).
Il microservizio aggiorna solo stato DB. L invio effettivo di email
reminder lo fa il BE Gepafin tramite polling, tenant-aware.
==UPLOAD DOCUMENTI==
3 nuovi endpoint nel router istruttoria:
POST /instructor/{pid}/amendment/{aid}/upload-document
- Istruttore allega PDF al soccorso (motivazione, scheda tecnica).
- Consentito in DRAFT o AWAITING. Sostituisce precedente se esiste.
- Popola amendment_document_path + amendment_document_type.
DELETE /instructor/{pid}/amendment/{aid}/upload-document
- Rimuove allegato (solo in DRAFT).
POST /instructor/{pid}/amendment/{aid}/upload-response-document
- Benef allega PDF come supporto alla risposta.
- Consentito in AWAITING/RESPONSE_RECEIVED, solo proprietario.
- Popola response_document_path + response_document_type.
Riusa save_upload() esistente con entity_type dedicati.
==FIX storage.py==
Whitelist entity_type estesa con 'amendment-instructor-doc' +
'amendment-response-doc' (prima accettava solo invoice/ula/document,
bloccando l'upload con StorageError).
==FIX migration dedup==
Scoperto in test: migration 8 faceva INSERT ON CONFLICT DO NOTHING su
remission_expiration_config ma senza UNIQUE constraint. Ogni restart
inseriva duplicati (16 righe in DB invece di 2). Fix in migration 9:
DELETE duplicati + ADD UNIQUE (type, interval_days) + re-seed pulito.
==REQUIREMENTS==
APScheduler==3.10.4
==TEST E2E==
/tmp/test_amendment_r2_fixed.py passa su tutto:
[A] upload amendment_document istruttore + response_document benef + respond
[B] amendment scaduto artificiale -> expire_amendments lo marca EXPIRED,
pratica torna UNDER_REVIEW
[C] amendment a +2gg e +7gg -> queue_reminders accoda 2 reminder,
/internal pending-reminder li espone entrambi
160 lines
5.1 KiB
Python
160 lines
5.1 KiB
Python
"""
|
|
Storage adapter per file upload.
|
|
|
|
Implementazione attuale: filesystem locale con bind mount /var/uploads.
|
|
Struttura: /var/uploads/{application_id}/{entity_type}/{entity_id}/{sha256}-{filename}
|
|
|
|
Migrazione futura a S3/MinIO: cambiare solo questa classe.
|
|
"""
|
|
import hashlib
|
|
import os
|
|
import shutil
|
|
from pathlib import Path
|
|
from typing import BinaryIO, Optional, Tuple
|
|
from uuid import UUID
|
|
|
|
BASE_PATH = Path(os.environ.get("RENDIC_UPLOAD_BASE", "/var/uploads"))
|
|
MAX_SIZE_BYTES = 15 * 1024 * 1024 # 15 MB
|
|
|
|
ALLOWED_MIMES = {
|
|
"application/pdf": ".pdf",
|
|
"image/jpeg": ".jpg",
|
|
"image/png": ".png",
|
|
}
|
|
|
|
|
|
class StorageError(Exception):
|
|
pass
|
|
|
|
|
|
class FileTooLargeError(StorageError):
|
|
pass
|
|
|
|
|
|
class MimeNotAllowedError(StorageError):
|
|
pass
|
|
|
|
|
|
def _safe_filename(name: str, max_len: int = 120) -> str:
|
|
"""Rimuove caratteri pericolosi, tronca."""
|
|
keep = "-_.() "
|
|
clean = "".join(c if (c.isalnum() or c in keep) else "_" for c in name)
|
|
clean = clean.strip().replace(" ", "_")
|
|
if len(clean) > max_len:
|
|
root, ext = os.path.splitext(clean)
|
|
clean = root[: max_len - len(ext)] + ext
|
|
return clean or "file"
|
|
|
|
|
|
def save_upload(
|
|
application_id: int,
|
|
entity_type: str, # invoice | ula | document | amendment-instructor-doc | amendment-response-doc
|
|
entity_id: UUID,
|
|
file_obj: BinaryIO,
|
|
original_filename: str,
|
|
content_type: Optional[str],
|
|
) -> Tuple[str, int, str, str, str]:
|
|
"""
|
|
Salva il file su FS e ritorna (storage_path, size_bytes, sha256, mime, safe_filename).
|
|
storage_path è RELATIVO a BASE_PATH (es: "1/invoice/xxx/yyy-fattura.pdf").
|
|
|
|
Valida:
|
|
- mime in ALLOWED_MIMES (usa content_type del client, fallback su estensione)
|
|
- dimensione <= MAX_SIZE_BYTES
|
|
"""
|
|
if entity_type not in ("invoice", "ula", "document", "amendment-instructor-doc", "amendment-response-doc"):
|
|
raise StorageError(f"entity_type non valido: {entity_type}")
|
|
|
|
safe_name = _safe_filename(original_filename)
|
|
ext = os.path.splitext(safe_name)[1].lower()
|
|
|
|
# Risolvi mime: prima content_type client, poi da estensione
|
|
mime = (content_type or "").lower().split(";")[0].strip()
|
|
if mime not in ALLOWED_MIMES:
|
|
# Fallback da estensione
|
|
ext_to_mime = {v: k for k, v in ALLOWED_MIMES.items()}
|
|
mime = ext_to_mime.get(ext, "")
|
|
if mime not in ALLOWED_MIMES:
|
|
raise MimeNotAllowedError(
|
|
f"MIME non consentito: '{content_type}' / estensione '{ext}'. "
|
|
f"Accettati: {list(ALLOWED_MIMES.keys())}"
|
|
)
|
|
|
|
# Calcola sha256 e size streaming per non tenere tutto in RAM
|
|
hasher = hashlib.sha256()
|
|
size = 0
|
|
# Salva in tmp poi rename atomico
|
|
target_dir = BASE_PATH / str(application_id) / entity_type / str(entity_id)
|
|
target_dir.mkdir(parents=True, exist_ok=True)
|
|
tmp_path = target_dir / f".tmp-{entity_id}"
|
|
|
|
try:
|
|
with open(tmp_path, "wb") as out:
|
|
while True:
|
|
chunk = file_obj.read(65536)
|
|
if not chunk:
|
|
break
|
|
size += len(chunk)
|
|
if size > MAX_SIZE_BYTES:
|
|
raise FileTooLargeError(
|
|
f"File {size} byte oltre limite {MAX_SIZE_BYTES}"
|
|
)
|
|
hasher.update(chunk)
|
|
out.write(chunk)
|
|
|
|
digest = hasher.hexdigest()
|
|
final_name = f"{digest[:12]}-{safe_name}"
|
|
final_path = target_dir / final_name
|
|
|
|
# Se già esiste (dedup per sha+nome) rimuovi tmp e usa esistente
|
|
if final_path.exists():
|
|
tmp_path.unlink(missing_ok=True)
|
|
else:
|
|
os.replace(tmp_path, final_path)
|
|
|
|
rel_path = str(final_path.relative_to(BASE_PATH))
|
|
return rel_path, size, digest, mime, safe_name
|
|
except Exception:
|
|
# cleanup tmp in caso di errore
|
|
try:
|
|
tmp_path.unlink(missing_ok=True)
|
|
except Exception:
|
|
pass
|
|
raise
|
|
|
|
|
|
def delete_file(storage_path: str) -> bool:
|
|
"""Elimina fisicamente il file. Ritorna True se rimosso."""
|
|
if not storage_path:
|
|
return False
|
|
abs_path = BASE_PATH / storage_path
|
|
# hardening: resta sotto BASE_PATH
|
|
try:
|
|
abs_path.resolve().relative_to(BASE_PATH.resolve())
|
|
except ValueError:
|
|
raise StorageError(f"Path fuori da BASE_PATH: {storage_path}")
|
|
if abs_path.exists():
|
|
abs_path.unlink()
|
|
# prova a rimuovere directory vuote (entity_id/entity_type)
|
|
try:
|
|
abs_path.parent.rmdir()
|
|
abs_path.parent.parent.rmdir()
|
|
except OSError:
|
|
pass
|
|
return True
|
|
return False
|
|
|
|
|
|
def open_file(storage_path: str) -> Path:
|
|
"""Ritorna Path assoluto del file. Solleva FileNotFoundError se mancante."""
|
|
if not storage_path:
|
|
raise FileNotFoundError("storage_path vuoto")
|
|
abs_path = BASE_PATH / storage_path
|
|
try:
|
|
abs_path.resolve().relative_to(BASE_PATH.resolve())
|
|
except ValueError:
|
|
raise StorageError(f"Path fuori da BASE_PATH: {storage_path}")
|
|
if not abs_path.is_file():
|
|
raise FileNotFoundError(f"File non trovato: {storage_path}")
|
|
return abs_path
|