adjust local runner

backend/pashub_fetcher/pashub_service.py

@@ -1,7 +1,10 @@
+import base64
 import os
 from datetime import datetime, timezone
 from typing import List, NamedTuple, Optional, cast
 
+import requests
+
 from backend.app.db.connection import db_session
 from backend.app.db.models.uploaded_file import (
     FileSourceEnum,
@@ -20,6 +23,7 @@ from datatypes.epc.domain.epc_property_data import EpcPropertyData
 from utils.logger import setup_logger
 from utils.s3 import upload_file_to_s3
 from utils.sharepoint.domna_sharepoint_client import DomnaSharepointClient
+from utils.sharepoint.sharepoint_client import SharePointClient
 
 logger = setup_logger()
 
@@ -146,12 +150,34 @@ class PashubService:
                     f"Failed to parse site notes {record.file_path}", exc_info=True
                 )
 
+    def _resolve_sharepoint_sharing_link(self, sharing_url: str) -> str:
+        encoded = base64.urlsafe_b64encode(sharing_url.encode()).rstrip(b"=").decode()
+        share_id = f"u!{encoded}"
+
+        sp = SharePointClient(
+            tenant_id=os.getenv("SHAREPOINT_TENANT_ID"),
+            client_id=os.getenv("SHAREPOINT_CLIENT_ID"),
+            client_secret=os.getenv("SHAREPOINT_CLIENT_SECRET"),
+            site_id=self._sharepoint_client.sharepoint_drive.value,
+        )
+
+        r = requests.get(
+            f"https://graph.microsoft.com/v1.0/shares/{share_id}/driveItem",
+            params={"$select": "name,parentReference"},
+            headers=sp.headers,
+        )
+        r.raise_for_status()
+        data = r.json()
+        parent_path = data["parentReference"]["path"].split("root:/", 1)[1]
+        return f"{parent_path}/{data['name']}"
+
     def _upload_to_sharepoint(
         self,
         sharepoint_link: str,
         job_files: List[str],
     ) -> None:
-        assessment_path = f"{sharepoint_link}/{SharepointSubfolders.ASSESSMENT.value}"
+        resolved_path = self._resolve_sharepoint_sharing_link(sharepoint_link)
+        assessment_path = f"{resolved_path}/2. RA Coordinator Info"
 
         for file_path in job_files:
             filename = file_path.split("/")[-1]

backend/pashub_fetcher/token_getter.py

@@ -17,10 +17,12 @@ def get_token_from_local_storage(
 
         browser = p.chromium.launch(
             headless=True,
+            env={"DISPLAY": ""},
             args=[
                 "--no-sandbox",
                 "--disable-dev-shm-usage",
                 "--disable-gpu",
+                "--disable-vulkan",
                 "--single-process",
                 "--no-zygote",
             ],

backend/pashub_fetcher/trigger_lambda_from_file.py

@@ -10,17 +10,16 @@ from backend.pashub_fetcher.pashub_to_ara_trigger_request import (
 )
 from backend.pashub_fetcher.handler.handler import handler
 
-
 if __name__ == "__main__":
     BASE_DIR = os.path.dirname(os.path.dirname(__file__))
     filepath: str = os.path.join(
         BASE_DIR,
         "pashub_fetcher",
-        "The_Guinness_Partnership_AtkinsR_alis_Coordination_Design_Board_1774881298.xlsx",
+        "NCHA_SHDF_Wave_3_Main_Operation_Board_PASHUB RAs.xlsx",
     )
 
     wb = load_workbook(filepath, data_only=True)
-    ws = wb["filtered_2"]
+    ws = wb["filtered"]
 
     HEADER_ROW = 3
 
@@ -30,18 +29,27 @@ if __name__ == "__main__":
         if value:
             headers[value.strip()] = col
 
-    name_col = headers["Name"]
-    link_col = headers["PasHub Link"]
-    hubspot_deal_id_col = headers["HubSpot ID"]
+    name_col = headers.get("Name")
+    link_col = headers.get("PasHub Link")
+    hubspot_deal_id_col = headers.get("HubSpot ID")
+    sharepoint_link_col = headers.get("Sharepoint")
 
     trigger_requests: List[PashubToAraTriggerRequest] = []
 
     for row in range(HEADER_ROW + 1, ws.max_row + 1):
-        name = ws.cell(row=row, column=name_col).value
-        link = ws.cell(row=row, column=link_col).value
-        hubspot_deal_id = ws.cell(row=row, column=hubspot_deal_id_col).value
-
-        if not name or not link or not hubspot_deal_id:
+        name = ws.cell(row=row, column=name_col).value if name_col else None
+        link = ws.cell(row=row, column=link_col).value if link_col else None
+        hubspot_deal_id = (
+            ws.cell(row=row, column=hubspot_deal_id_col).value
+            if hubspot_deal_id_col
+            else None
+        )
+        sharepoint_link = (
+            ws.cell(row=row, column=sharepoint_link_col).value
+            if sharepoint_link_col
+            else None
+        )
+        if not name or not link:
             continue
 
         match = re.search(r"/jobs/([0-9a-fA-F\-]+)/", str(link))
@@ -50,13 +58,18 @@ if __name__ == "__main__":
 
         trigger_requests.append(
             PashubToAraTriggerRequest(
-                pashub_link=str(link), hubspot_deal_id=str(hubspot_deal_id)
+                pashub_link=str(link),
+                hubspot_deal_id=str(hubspot_deal_id),
+                sharepoint_link=str(sharepoint_link),
             )
         )
 
     # ---- Build fake SQS event ----
     event: Dict[str, Any] = {
-        "Records": [{"body": json.dumps(req.model_dump())} for req in trigger_requests]
+        "Records": [
+            {"body": json.dumps(req.model_dump()), "messageId": str(i)}
+            for i, req in enumerate(trigger_requests)
+        ]
     }
 
     context = None