junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-06-08 11:17:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

pulling out other file types from s3 during energy assessment upload

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-09-04 11:02:56 +01:00
parent 92564be655
commit 64b423ad2e
1 changed files with 41 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

43
backend/app/energy_assessments/router.py
View file

@ -13,7 +13,10 @@ from sqlalchemy.orm import sessionmaker
from backend.app.db.functions.energy_assessment_functions import bulk_insert_energy_assessments
from sqlalchemy.orm import sessionmaker
from backend.app.db.connection import db_engine
from utils.s3 import read_from_s3, list_files_and_subfolders_in_s3_folder, list_xmls_in_s3_folder, save_csv_to_s3
from utils.s3 import (
read_from_s3, list_files_and_subfolders_in_s3_folder, list_xmls_in_s3_folder, save_csv_to_s3,
list_files_in_s3_folder
)
from utils.logger import setup_logger
from etl.xml_survey_extraction.XmlParser import XmlParser
import os
@ -68,8 +71,44 @@ async def upload(body: EnergyAssessmentUploadPayload):
bucket_name=get_settings().ENERGY_ASSESSMENTS_BUCKET,
folder_name=os.path.join(assessment, "docs & plans")
)
energy_assessment_files = list_files_in_s3_folder(
bucket_name=get_settings().ENERGY_ASSESSMENTS_BUCKET,
folder_name=os.path.join(assessment, "docs & plans")
)
# Remove xmls from the list of files
energy_assessment_files = [file for file in energy_assessment_files if file not in uploaded_xmls]
# We now split this into the different types of files
# EPR
eprs = [
file for file in energy_assessment_files if "EPR.pdf" in file.split("/")[-1].replace(" ", "").lower()
]
# Condition report
condition_reports = [
file for file in energy_assessment_files if "cr.pdf" in file.split("/")[-1].replace(" ", "").lower()
]
# Evidence report
evidence_reports = [
file for file in energy_assessment_files
if "evidence.pdf" in file.split("/")[-1].replace(" ", "").lower()
]
# Summary report
summary_reports = [
file for file in energy_assessment_files
if "sn.pdf" in file.split("/")[-1].replace(" ", "").lower()
]
# Floor plans - these are just the jpgs
floor_plans = [file for file in energy_assessment_files if file.endswith(".jpg")]
uprn = int(assessment.rstrip("/").split("/")[-1])
assessments_map[uprn] = uploaded_xmls
assessments_map[uprn] = {
"xmls": uploaded_xmls,
"eprs": eprs,
"condition_reports": condition_reports,
"evidence_reports": evidence_reports,
"summary_reports": summary_reports,
"floor_plans": floor_plans
}
logger.info(f"Exatracted XMLS for the energy assessments")