From 3ca373175c86d052af7f27fe91b34da6c191535f Mon Sep 17 00:00:00 2001
From: Jun-te Kim <junte@domna.homes>
Date: Mon, 28 Apr 2025 15:36:00 +0000
Subject: [PATCH] datbase work sve so far

---
 etl/db/hubSpotLoad.py             | 16 ++++++++++++----
 etl/hubspot_to_db.py              |  2 +-
 etl/surveyedData/surveryedData.py | 19 +++++++++++++++++++
 3 files changed, 32 insertions(+), 5 deletions(-)

diff --git a/etl/db/hubSpotLoad.py b/etl/db/hubSpotLoad.py
index 6763a04..a2b19cb 100644
--- a/etl/db/hubSpotLoad.py
+++ b/etl/db/hubSpotLoad.py
@@ -2,12 +2,14 @@ from etl.hubSpotClient.hubspot import HubSpotClient, DealStage
 from etl.surveyPrice.surveyPrice import SurveyPrice
 from etl.surveyedData.surveryedData import surveyedDataProcessor
 from etl.scraper.scraper import SharePointScraper, SharePointInstaller
+from etl.db.db import get_db_session, init_db
 
 from urllib.parse import unquote
 
 
 class HubspotTodb():
     def __init__(self):
+        init_db()
         self.hubspot = HubSpotClient()
         self.deals_in_hubspot = None
         self.data_in_sharepoint = []
@@ -80,10 +82,16 @@ class HubspotTodb():
 
             for add, file_loc in data_loc.items():
                 self.data_in_sharepoint.append(surveyedDataProcessor(add, file_loc))
-
-    def print_address(self):
+    
+    def load_all(self):
         self.gather_data_from_each_sharepoint()
-        for dp in self.data_in_sharepoint:
-            print(dp.address)
+        with get_db_session() as session:
+            self.load_pre_site_note(session)
+            session.commit()
+
+    def load_pre_site_note(self, db_session):
+        for surveyedData in self.data_in_sharepoint:
+            surveyedData.load_assessor_table(db_session)
+            
 
 
diff --git a/etl/hubspot_to_db.py b/etl/hubspot_to_db.py
index 11ea79b..f5b14ea 100644
--- a/etl/hubspot_to_db.py
+++ b/etl/hubspot_to_db.py
@@ -10,4 +10,4 @@ from etl.db.hubSpotLoad import HubspotTodb
 
 dbLoader = HubspotTodb()
 
-dbLoader.print_address()
\ No newline at end of file
+dbLoader.load_all()
\ No newline at end of file
diff --git a/etl/surveyedData/surveryedData.py b/etl/surveyedData/surveryedData.py
index 1b5248e..ec1acb6 100644
--- a/etl/surveyedData/surveryedData.py
+++ b/etl/surveyedData/surveryedData.py
@@ -1,6 +1,7 @@
 from etl.pdfReader.pdfReaderToText import pdfReaderToText
 from etl.pdfReader.reportType import ReportType
 import math
+from etl.transform.preSiteNoteTypes import AssessorInfo
 
 class surveyedDataProcessor():
     def __init__(self, address, files):
@@ -22,6 +23,24 @@ class surveyedDataProcessor():
                 elif pdf.type == ReportType.CHARTED_SURVEYOR_REPORT:
                     self.csr = pdf.get_reader()
 
+    def load_assessor_table(self, db_session):
+        assessor_data = self.pre_site_note.assessor_information.__dict__
+        accreditation_number = assessor_data.get('accreditation_number')
+
+        existing_assessor = db_session.query(AssessorInfo).filter_by(
+            accreditation_number=accreditation_number
+        ).first()
+
+        if existing_assessor:
+            # Update existing record
+            for key, value in assessor_data.items():
+                setattr(existing_assessor, key, value)
+        else:
+            # Insert new record
+            db_session.add(AssessorInfo(**assessor_data))
+
+        db_session.commit()
+
     def get_insulation_info(self):
         if self.csr:
             if self.csr.insulation_info: