pre site table is now made

etl/db/hubSpotLoad.py

@@ -94,4 +94,6 @@ class HubspotTodb():
             # Loads Assessor information and Company information to db
             assessor = surveyedData.load_assessor_table(db_session)
             # Loads the pre site summary information
-            summary_info = surveyedData.load_pre_site_notes_summary_table(db_session)
+            summary_info = surveyedData.load_pre_site_notes_summary_table(db_session)
+            # Creates the a final pre site note table that links all information
+            surveyedData.create_pre_site_note_table(db_session, assessor, summary_info)

etl/surveyedData/surveryedData.py

@@ -1,7 +1,10 @@
 from etl.pdfReader.pdfReaderToText import pdfReaderToText
 from etl.pdfReader.reportType import ReportType
 import math
-from etl.transform.preSiteNoteTypes import AssessorInfo, CompanyInfo, PreSiteNotesSummaryInfo
+from etl.transform.preSiteNoteTypes import (
+    AssessorInfo, CompanyInfo, 
+    PreSiteNotesSummaryInfo, PreSiteNote,
+)
 
 class surveyedDataProcessor():
     def __init__(self, address, files):
@@ -15,7 +18,6 @@ class surveyedDataProcessor():
     def identify_files(self):
         for file in self.files:
             pdf = pdfReaderToText(file)
-            print(file)
             if pdf:
                 if pdf.type == ReportType.QUIDOS_PRESITE_NOTE:
                     self.pre_site_note = pdf.get_reader()
@@ -40,6 +42,24 @@ class surveyedDataProcessor():
             data_dict=company_data,
             lookup_field="trading_name"
         )
+
+    
+    def create_pre_site_note_table(
+        self, 
+        db_session,
+        assessor,
+        summary_info
+    ):
+        preSiteNote = PreSiteNote(
+            summary_info_id=summary_info.id,
+            assessor_id=assessor.id,
+        )
+        db_session.add(preSiteNote)
+        db_session.commit()
+
+        return preSiteNote
+        
+
         
     def upsert_record(
         self,
@@ -64,39 +84,45 @@ class surveyedDataProcessor():
         Returns:
             SQLAlchemy model instance.
         """
-        lookup_value = data_dict.get(lookup_field)
+        # Filter out private/internal fields like _sa_instance_state
+        clean_data = {
+            k: v for k, v in data_dict.items()
+            if not k.startswith('_') and hasattr(model_class, k)
+        }
+
+        # Merge additional fields if provided
+        if additional_fields:
+            clean_data.update(additional_fields)
+
+        lookup_value = clean_data.get(lookup_field)
         if not lookup_value:
             raise ValueError(f"Missing lookup field '{lookup_field}' in data.")
 
-        # Merge in additional fields if provided
-        if additional_fields:
-            data_dict.update(additional_fields)
-
         existing_record = db_session.query(model_class).filter(
             getattr(model_class, lookup_field) == lookup_value
         ).first()
 
         if existing_record:
             if update_if_exists:
-                for key, value in data_dict.items():
+                for key, value in clean_data.items():
                     setattr(existing_record, key, value)
                 db_session.commit()
             return existing_record
         else:
-            new_record = model_class(**data_dict)
+            new_record = model_class(**clean_data)
             db_session.add(new_record)
             db_session.commit()
             return new_record
         
     def load_assessor_table(self, db_session):
         company = self.load_company_table(db_session)
+        print(f"Company ID: {company.id}")
         assessor_data = self.pre_site_note.assessor_information.__dict__
         return self.upsert_record(
             db_session=db_session,
             model_class=AssessorInfo,
             data_dict=assessor_data,
             lookup_field="accreditation_number",
-            update_if_exists=True,
             additional_fields={"company_id": company.id}
         )
 

etl/transform/preSiteNoteTypes.py

@@ -4,6 +4,7 @@ from datetime import datetime
 from pydantic import field_validator, EmailStr
 from typing import Optional, List
 from sqlalchemy import Column
+from sqlalchemy.orm import relationship
 from sqlalchemy.dialects.postgresql import UUID
 
 class BaseModel(SQLModel):
@@ -52,6 +53,12 @@ class PreSiteNotesSummaryInfo(BaseModel, table=True):
     current_annual_emission_including_0925_multiplayer: str
     current_annual_energy_costs: str
     
+    pre_site_note: Optional["PreSiteNote"] = Relationship(
+        back_populates="summary_info",
+        sa_relationship=relationship("PreSiteNote", back_populates="summary_info", uselist=False)
+    )
+
+    
 class Walls(BaseModel):
     construction: str
     insulation: str
@@ -90,6 +97,8 @@ class AssessorInfo(BaseModel, table=True):
         foreign_key="companyinfo.id",  # Referencing CompanyInfo
         nullable=False
     )
+    
+    pre_site_notes: List["PreSiteNote"] = Relationship(back_populates="assessor")
 
 class VentilationAndCooling(BaseModel):
     no_of_open_fireplaces: int
@@ -213,10 +222,20 @@ class Insulation(BaseModel):
     type: str
 
 # One class to rule them all
-# class PreSiteNote(BaseModel, table=True):
-#     summary_info_id: uuid.UUID = Field(
-#         foreign_key="presitenotessummaryinfo.id",
-#         nullable=False
-#     )
-#     # Relationship to summary info
-#     summary_info: Optional["PreSiteNotesSummaryInfo"] = Relationship(back_populates="pre_site_notes")
+class PreSiteNote(BaseModel, table=True):
+    # Summary Info
+    summary_info_id: uuid.UUID = Field(
+        foreign_key="presitenotessummaryinfo.id",
+        nullable=False
+    )
+
+    summary_info: Optional["PreSiteNotesSummaryInfo"] = Relationship(back_populates="pre_site_note")
+
+
+    # Assessor Info
+    assessor_id: uuid.UUID = Field(
+        foreign_key="assessorinfo.id",
+        nullable=False
+    )
+
+    assessor: Optional["AssessorInfo"] = Relationship(back_populates="pre_site_notes")