From cc07706fc124899d06d66bb220a829bfcc22597e Mon Sep 17 00:00:00 2001
From: Jun-te Kim <junte@domna.homes>
Date: Mon, 14 Apr 2025 15:47:35 +0000
Subject: [PATCH] merge pdf works now

---
 etl/hubspot_to_invoice.py      |  6 ++++--
 etl/surveyPrice/surveyPrice.py | 37 ++++++++++++++++++++++++++++++----
 2 files changed, 37 insertions(+), 6 deletions(-)

diff --git a/etl/hubspot_to_invoice.py b/etl/hubspot_to_invoice.py
index 9bee806..3c3e2fe 100644
--- a/etl/hubspot_to_invoice.py
+++ b/etl/hubspot_to_invoice.py
@@ -13,5 +13,7 @@ from etl.surveyPrice.surveyPrice import SurveyPrice
 sp = SurveyPrice()
 sp.get_cavity_pricing_table("JJC - EMPTIES")
 
-df = sp.get_all_surveys_from_hubspot()
-df = sp.get_all_surveyed_data_from_sharepoint()
\ No newline at end of file
+hubspot_df = sp.get_all_surveys_from_hubspot()
+sharepoint_df = sp.get_all_surveyed_data_from_sharepoint()
+
+df = sp.merge_hub_spot_and_survey_information()
\ No newline at end of file
diff --git a/etl/surveyPrice/surveyPrice.py b/etl/surveyPrice/surveyPrice.py
index 7e437f0..dd8c45e 100644
--- a/etl/surveyPrice/surveyPrice.py
+++ b/etl/surveyPrice/surveyPrice.py
@@ -12,6 +12,7 @@ class SurveyPrice():
         self.warmfront_sharepoint_client = SharePointScraper(SharePointInstaller.WARMFRONT)
         self.master_rate_card_path = None
         self.all_hubspot_submissions = None
+        self.all_survey_info_from_sharepoint = None
         self.download_price_card()
         self.required_sheets = [
             'JJC - EMPTIES',
@@ -103,7 +104,8 @@ class SurveyPrice():
         return self.all_hubspot_submissions
     
     def get_all_surveyed_data_from_sharepoint(self):
-        self.sharepoint_data_for_jjc()
+        self.all_survey_info_from_sharepoint =  self.sharepoint_data_for_jjc()
+        return self.all_survey_info_from_sharepoint
     
     def sharepoint_data_for_jjc(self):
         jjc_sp = SharePointScraper(SharePointInstaller.JJC, development=True)
@@ -117,13 +119,14 @@ class SurveyPrice():
         all_survey_info = []
         for surveyInfo in jjc_surveys:
             info = {
-                "SHAREPOINT INSTALLER": "J & J Crumps",
+                "SHAREPOINT INSTALLER": "J & J CRUMP",
                 "SHAREPOINT PRE_SITE_NOTES FOUND": True if surveyInfo.pre_site_note else False,
                 "SHAREPOINT CSR FOUND": True if surveyInfo.csr else False,
                 "SHAREPOINT TOTAL_FLOOR_AREA": "NO PRE SITE NOTES FOUND",
                 "SHAREPOINT FLOOR_AREA_BANDING": "NO PRE SITE NOTES FOUND",
                 "SHAREPOINT PRE_INSTALL_SAP_SCORE": "NO PRE SITE NOTES FOUND",
                 "SHAREPOINT INSULATION MATERIAL": None,
+                "SHAREPOINT ADDRESS": address
             }
 
             if surveyInfo.pre_site_note:
@@ -139,10 +142,36 @@ class SurveyPrice():
                     "SHAREPOINT INSULATION MATERIAL": surveyInfo.get_insulation_info(),
                 })
 
+            all_survey_info.append(info)
 
-        return jjc_surveys
+        return pd.DataFrame(all_survey_info)
+    
+    def merge_hub_spot_and_survey_information(self):
+        if self.all_survey_info_from_sharepoint is None:
+            raise RuntimeError("No survey information found from Sharepoint")
+        if self.all_hubspot_submissions is None:
+            raise RuntimeError("No information found from Hubspot")
+
+        self.all_survey_info_from_sharepoint['clean_address'] = self.all_survey_info_from_sharepoint['SHAREPOINT ADDRESS'].apply(
+            lambda x: x.lower().replace(',', '').strip()
+        ) 
+
+        self.all_hubspot_submissions['clean_address'] = self.all_hubspot_submissions['HUBSPOT_DEAL_ADDRESS'].apply(
+            lambda x: x.lower().replace(',', '').strip()
+        )
+
+        merged_df = pd.merge(
+            self.all_survey_info_from_sharepoint, 
+            self.all_hubspot_submissions, 
+            left_on=['clean_address', 'SHAREPOINT INSTALLER'], 
+            right_on=['clean_address', 'HUBSPOT_INSTALLER'], 
+            how='inner'
+        )
+
+        merged_df.drop(columns=['clean_address'], inplace=True)
+
+        return merged_df
 
-