update db after loading file to s3

backend/app/db/models/uploaded_file.py

@@ -22,10 +22,10 @@ class FileSourceEnum(enum.Enum):
     HUBSPOT = "hubspot"
 
 
-class UploadedFiles(Base):
+class UploadedFile(Base):
     __tablename__ = "uploaded_files"
 
-    id = Column(BigInteger, primary_key=True)
+    id = Column(BigInteger, primary_key=True, autoincrement=True)
 
     s3_file_bucket = Column(Text, nullable=False)
     s3_file_key = Column(Text, nullable=False)
@@ -39,6 +39,6 @@ class UploadedFiles(Base):
         SqlEnum(FileTypeEnum, name="file_type", create_type=False), nullable=True
     )
 
-    source = Column(
+    file_source = Column(
         SqlEnum(FileSourceEnum, name="file_source", create_type=False), nullable=True
     )

backend/pashub_fetcher/core_files.py

@@ -1,4 +1,7 @@
 from enum import Enum
+from typing import Optional
+
+from backend.app.db.models.uploaded_file import FileTypeEnum
 
 
 class CoreFiles(Enum):
@@ -11,3 +14,23 @@ class CoreFiles(Enum):
     PAR_PHOTOPACK = "PAR Photo Pack"
     PAS2023_PROPERTY = "PAS 2023 Property Assessment Report"
     PAS2023_OCCUPANCY = "PAS 2023 Occupancy Assessment Report"
+
+
+CORE_TO_FILETYPE_MAP = {
+    CoreFiles.PHOTOPACK: FileTypeEnum.PHOTO_PACK.value,
+    CoreFiles.SITENOTE: FileTypeEnum.SITE_NOTE.value,
+    CoreFiles.RDSAP_SITENOTE: FileTypeEnum.RD_SAP_SITE_NOTE.value,
+    CoreFiles.PAS2023_VENTILATION: FileTypeEnum.PAS_2023_VENTILATION.value,
+    CoreFiles.PAS2023_CONDITION: FileTypeEnum.PAS_2023_CONDITION.value,
+    CoreFiles.PAS_SIGNIFICANCE: FileTypeEnum.PAS_SIGNIFICANCE.value,
+    CoreFiles.PAR_PHOTOPACK: FileTypeEnum.PAR_PHOTO_PACK.value,
+    CoreFiles.PAS2023_PROPERTY: FileTypeEnum.PAS_2023_PROPERTY.value,
+    CoreFiles.PAS2023_OCCUPANCY: FileTypeEnum.PAS_2023_OCCUPANCY.value,
+}
+
+
+def infer_file_type(filename: str) -> Optional[str]:
+    for core_file, file_type in CORE_TO_FILETYPE_MAP.items():
+        if filename.startswith(core_file.value):
+            return file_type
+    return None

backend/pashub_fetcher/handler/handler.py

@@ -1,8 +1,15 @@
+from datetime import datetime, timezone
 import os
 import re
 from typing import Any, Dict, List, Mapping, Optional
 from openpyxl import load_workbook
 
+from backend.app.db.connection import db_session
+from backend.app.db.models.uploaded_file import (
+    FileSourceEnum,
+    UploadedFile,
+)
+from backend.pashub_fetcher.core_files import infer_file_type
 from backend.pashub_fetcher.job import Job
 from backend.pashub_fetcher.pashub_client import PashubClient, UnauthorizedError
 from backend.pashub_fetcher.sharepoint_subfolders import SharepointSubfolders
@@ -88,17 +95,35 @@ def upload_job_to_sharepoint(
         )
 
 
-def upload_job_to_s3(job_files: List[str], uprn: str) -> None:
-    bucket = "retrofit-energy-assessments-dev"  # TODO: create new bucket
+def upload_job_to_s3_and_update_db(job_files: List[str], uprn: str) -> None:
+    bucket = "retrofit-energy-assessments-dev"
 
     base_path = f"documents/uprn/{uprn}"
 
+    uploaded_files: List[UploadedFile] = []
+
     for file_path in job_files:
         filename = os.path.basename(file_path)
         file_key = f"{base_path}/{filename}"
 
         upload_file_to_s3(file_path, bucket, file_key)
 
+        # load row to db
+        uploaded_files.append(
+            UploadedFile(
+                s3_file_bucket=bucket,
+                s3_file_key=file_key,
+                s3_upload_timestamp=datetime.now(timezone.utc),
+                uprn=int(uprn),
+                file_source=FileSourceEnum.PAS_HUB.value,
+                file_type=infer_file_type(filename),
+            )
+        )
+
+    with db_session() as session:
+        session.add_all(uploaded_files)
+        session.commit()
+
     pass
 
 
@@ -120,7 +145,9 @@ def process_job(
 
     if uprn:
         logger.info("Uploading files to s3")
-        upload_job_to_s3(job_files, uprn)
+        upload_job_to_s3_and_update_db(job_files, uprn)
+
+        # add record of new file in db
 
     upload_job_to_sharepoint(sharepoint_client, base_path, job, job_files)