refactor handler

backend/pashub_fetcher/handler/handler.py

@@ -39,94 +39,136 @@ def extract_jobs(filepath: str) -> List[Job]:
         if not name or not link:
             continue
 
-        link = str(link)
-
-        match = re.search(r"/jobs/([0-9a-fA-F\-]+)/", link)
+        match = re.search(r"/jobs/([0-9a-fA-F\-]+)/", str(link))
         if not match:
             continue
 
-        job_id = match.group(1)
-
-        jobs.append({"id": job_id, "address": str(name)})
+        jobs.append(
+            {
+                "id": match.group(1),
+                "address": str(name),
+            }
+        )
 
     return jobs
 
 
+def get_pashub_client(email: str, password: str) -> PashubClient:
+    token = get_token_from_local_storage(email, password)
+    logger.info("Token extracted successfully")
+    return PashubClient(token=token)
+
+
+def upload_job_to_sharepoint(
+    sharepoint_client: DomnaSharepointClient,
+    base_path: str,
+    job: Job,
+    job_files: List[str],
+) -> None:
+    job_path = f"{base_path}/{job['address']}"
+
+    # Create main job folder
+    sharepoint_client.makedir(job["address"], base_path)
+
+    # Create subfolders
+    for folder in SharepointSubfolders:
+        sharepoint_client.makedir(folder.value, job_path)
+
+    # Upload into assessment folder
+    assessment_path = f"{job_path}/{SharepointSubfolders.ASSESSMENT.value}"
+
+    for file_path in job_files:
+        filename = file_path.split("/")[-1]
+
+        sharepoint_client.upload_file(
+            file_path,
+            assessment_path,
+            filename,
+        )
+
+
+def upload_job_to_s3(
+    job: Job,
+    job_files: List[str],
+) -> None:
+    # Example:
+    # for file_path in job_files:
+    #     s3_client.upload_file(...)
+    pass
+
+
+def process_job(
+    job: Job,
+    pashub_client: PashubClient,
+    sharepoint_client: DomnaSharepointClient,
+    base_path: str,
+) -> List[str]:
+    job_id = job["id"]
+
+    uprn: Optional[str] = pashub_client.get_uprn_by_job_id(job_id)
+    logger.info(f"Got UPRN {uprn} for job {job_id}")
+
+    job_files: List[str] = pashub_client.get_core_evidence_files_by_job_id(job_id)
+
+    upload_job_to_sharepoint(sharepoint_client, base_path, job, job_files)
+    upload_job_to_s3(job, job_files)
+
+    return job_files
+
+
 def handler(event: Mapping[str, Any], context: Any) -> None:
     BASE_DIR = os.path.dirname(os.path.dirname(__file__))
     filepath = os.path.join(BASE_DIR, "Watford_Warm_Homes_Wave_3_RA Downloads .xlsx")
 
     jobs: List[Job] = extract_jobs(filepath)
-
     logger.info("Successfully loaded jobs from spreadsheet")
 
-    pas_hub_email = "random@test.com"
-    pas_hub_password = "my_fake_password"
+    # pas_hub_email = "random@test.com"
+    # pas_hub_password = "my_fake_password"
 
-    try:
-        token: str = get_token_from_local_storage(pas_hub_email, pas_hub_password)
-        logger.info(f"Token extracted successfully")
-    except:
-        logger.error("Error getting auth token from Pas Hub")
-        raise
+    pas_hub_email = "sebastian@osmosis-acd.com"
+    pas_hub_password = "Osmosis2025!"
+
+    pashub_client = get_pashub_client(pas_hub_email, pas_hub_password)
 
-    pashub_client = PashubClient(token=token)
     sharepoint_client = DomnaSharepointClient(
         sharepoint_location=DomnaSites.SOCIAL_HOUSING_WAVE_3
     )
 
+    BASE_PATH = "/Osmosis-ACD Projects/Watford Warm Homes/Watford Property Folders (Shared with Client)"
+
     saved_file_paths: List[str] = []
-    BASE_PATH = "/Osmosis-ACD Projects/Watford Warm Homes/Watford Property Folders (Shared with Client)"  # TODO: get from request body
 
     for job in jobs:
         try:
-            job_id = job["id"]
-            uprn: Optional[str] = pashub_client.get_uprn_by_job_id(job_id)
-            logger.info(f"Got UPRN {uprn} for job {job_id}")
-
-            job_files: List[str] = pashub_client.get_core_evidence_files_by_job_id(
-                job_id
+            files = process_job(
+                job,
+                pashub_client,
+                sharepoint_client,
+                BASE_PATH,
             )
-
-            # Upload files to s3
-
-            # Upload files to sharepoint
-            job_path = f"{BASE_PATH}/{job['address']}"
-
-            sharepoint_client.makedir(job["address"], BASE_PATH)
-
-            for folder in SharepointSubfolders:
-                sharepoint_client.makedir(folder.value, job_path)
-
-            assessment_path = f"{job_path}/{SharepointSubfolders.ASSESSMENT.value}"
-
-            for file_path in job_files:
-                filename = file_path.split("/")[-1]
-
-                sharepoint_client.upload_file(
-                    file_path,
-                    assessment_path,
-                    filename,
-                )
-
-            saved_file_paths.extend(job_files)
+            saved_file_paths.extend(files)
 
         except UnauthorizedError:
             logger.warning("Token expired - refreshing")
 
-            token = get_token_from_local_storage(pas_hub_email, pas_hub_password)
-
-            pashub_client = PashubClient(token=token)
-
-            # retry once
-            saved_file_paths.extend(
-                pashub_client.get_core_evidence_files_by_job_id(job["id"])
+            pashub_client = get_pashub_client(
+                pas_hub_email,
+                pas_hub_password,
             )
 
-    print(f"saved {len(saved_file_paths)} files")
+            # retry once
+            files = process_job(
+                job,
+                pashub_client,
+                sharepoint_client,
+                BASE_PATH,
+            )
+            saved_file_paths.extend(files)
+
+    logger.info(f"Saved {len(saved_file_paths)} files")
 
 
 if __name__ == "__main__":
     event = {"Records": [{"body": "{}"}]}
-
     handler(event, None)