68 lines
2.7 KiB
Python
68 lines
2.7 KiB
Python
# services/invoice_processor_service.py
|
|
import logging
|
|
from typing import Dict, List, Any, Optional
|
|
|
|
from .gcp_document_ai_client import process_document_gcp
|
|
from .utils import data_cleaner
|
|
from core.config import settings
|
|
|
|
def _extract_specific_fields(
|
|
entities: List[Any],
|
|
# El nombre del parámetro aquí debe coincidir con el que se le pasa desde el router
|
|
default_confidence_override: Optional[float] = None
|
|
) -> Dict[str, str]:
|
|
"""
|
|
Filtra y normaliza entidades. Si se proporciona `default_confidence_override`,
|
|
se utiliza para el umbral por defecto. Los umbrales específicos de la
|
|
configuración siempre tienen prioridad.
|
|
"""
|
|
extracted_data = {field: "Not found or low confidence" for field in settings.REQUIRED_FIELDS}
|
|
|
|
# Determina el umbral por defecto para esta ejecución
|
|
default_threshold = default_confidence_override if default_confidence_override is not None else settings.CONFIDENCE_THRESHOLDS["__default__"]
|
|
|
|
for entity in entities:
|
|
entity_type = entity.type_
|
|
|
|
if entity_type in settings.REQUIRED_FIELDS:
|
|
# Lógica corregida: Prioriza el umbral específico del campo, si no, usa el por defecto.
|
|
threshold = settings.CONFIDENCE_THRESHOLDS.get(entity_type, default_threshold)
|
|
|
|
if entity.confidence >= threshold:
|
|
value = entity.mention_text.replace('\n', ' ').strip()
|
|
|
|
if entity_type == 'invoice_date':
|
|
normalized_date = data_cleaner.normalize_date(value)
|
|
value = normalized_date if normalized_date else f"Unparseable Date: '{value}'"
|
|
|
|
extracted_data[entity_type] = value
|
|
|
|
return extracted_data
|
|
|
|
def process_invoice_from_bytes(
|
|
file_bytes: bytes,
|
|
mime_type: str,
|
|
# El nombre del parámetro aquí debe coincidir con el del router
|
|
default_confidence_override: Optional[float] = None
|
|
) -> Dict[str, str]:
|
|
"""
|
|
Orquesta el proceso completo.
|
|
"""
|
|
try:
|
|
document = process_document_gcp(
|
|
project_id=settings.GCP_PROJECT_ID,
|
|
location=settings.GCP_LOCATION,
|
|
processor_id=settings.DOCAI_PROCESSOR_ID,
|
|
file_bytes=file_bytes,
|
|
mime_type=mime_type,
|
|
)
|
|
|
|
validated_data = _extract_specific_fields(document.entities, default_confidence_override)
|
|
|
|
log_threshold = default_confidence_override if default_confidence_override is not None else "config default"
|
|
logging.info(f"Documento procesado. Umbral por defecto usado: {log_threshold}.")
|
|
return validated_data
|
|
|
|
except Exception as e:
|
|
logging.error(f"Error en el flujo de procesamiento de factura: {e}", exc_info=True)
|
|
raise |