_select_other_files returns non-core evidence files 🟥

backend/pashub_fetcher/pashub_client.py

@@ -92,6 +92,12 @@ class PashubClient:
             )
             return None
 
+    def _select_other_files(
+        self,
+        files: List[EvidenceFileData],
+    ) -> List[EvidenceFileData]:
+        raise NotImplementedError
+
     def _select_latest_core_files(
         self,
         files: List[EvidenceFileData],
@@ -106,16 +112,16 @@ class PashubClient:
                 continue
             grouped[core_type].append(file)
 
-        latest_files: Dict[CoreFiles, EvidenceFileData] = {}
+        latest_core_files: Dict[CoreFiles, EvidenceFileData] = {}
 
         for core_type, group in grouped.items():
             if core_type == CoreFiles.RETROFIT_DESIGN_DOC and len(group) > 1:
                 osm_candidates = [f for f in group if "-OSM-" in f.file_name]
                 group = osm_candidates if osm_candidates else group
             latest = max(group, key=lambda f: datetime.fromisoformat(f.created_utc))
-            latest_files[core_type] = latest
+            latest_core_files[core_type] = latest
 
-        return latest_files
+        return latest_core_files
 
     def _get_evidence_list(self, job_id: str) -> List[EvidenceFileData]:
         url = f"{self.base}/jobs/{job_id}/evidence"

backend/pashub_fetcher/pashub_service.py

@@ -75,14 +75,14 @@ class PashubService:
             logger.info(f"No UPRN found for job {job_id}")
 
         try:
-            job_files: List[str] = active_client.get_core_evidence_files_by_job_id(
+            core_files: List[str] = active_client.get_core_evidence_files_by_job_id(
                 job_id
             )
         except UnauthorizedError:
             if active_client is not self._pashub_client:
                 raise
             active_client = self._get_coordination_client()
-            job_files = active_client.get_core_evidence_files_by_job_id(job_id)
+            core_files = active_client.get_core_evidence_files_by_job_id(job_id)
 
         if uprn or hubspot_deal_id:
             logger.info("Uploading files to s3")
@@ -92,7 +92,7 @@ class PashubService:
                 else FileSourceEnum.COORDINATION_HUB
             )
             upload_records = self._upload_to_s3_and_update_db(
-                job_files, uprn, hubspot_deal_id, file_source
+                core_files, uprn, hubspot_deal_id, file_source
             )
             self._save_site_notes(upload_records)
 
@@ -101,13 +101,13 @@ class PashubService:
         # if request.sharepoint_link:
         #     self._upload_to_sharepoint(request.sharepoint_link, job_files)
 
-        for file_path in job_files:
+        for file_path in core_files:
             try:
                 os.remove(file_path)
             except OSError:
                 logger.warning(f"Failed to delete temp file {file_path}")
 
-        return job_files
+        return core_files
 
     def _upload_to_s3_and_update_db(
         self,

backend/pashub_fetcher/pashub_to_ara_trigger_request.py

@@ -14,6 +14,8 @@ class PashubToAraTriggerRequest(BaseModel):
     hubspot_listing_id: Optional[int] = None
     hubspot_deal_id: Optional[str] = None
 
+    get_other_files: Optional[bool] = False
+
     @property
     def pashub_job_id(self) -> str:
         match = re.search(r"/jobs/([^/]+)", self.pashub_link)

backend/pashub_fetcher/tests/test_pashub_client.py

@@ -25,6 +25,31 @@ def make_file(
     )
 
 
+# ---------------------------------------------------------------------------
+# _select_other_files
+# ---------------------------------------------------------------------------
+
+
+def test_select_other_files_returns_non_core_files_only() -> None:
+    # Arrange
+    client = make_client()
+    files = [
+        make_file(file_name="SiteNote_001.pdf"),
+        make_file(file_name="some_unknown_document.pdf"),
+        make_file(file_name="another_random_file.docx"),
+        make_file(file_name="Photopack_002.pdf"),
+    ]
+
+    # Act
+    result = client._select_other_files(files)
+
+    # Assert
+    assert [f.file_name for f in result] == [
+        "some_unknown_document.pdf",
+        "another_random_file.docx",
+    ]
+
+
 # ---------------------------------------------------------------------------
 # _select_latest_core_files
 # ---------------------------------------------------------------------------