Model/applications/pashub_fetcher/trigger_local_lambda_from_file.py
Daniel Roth ae1da26558 Move the PasHub fetcher into the DDD layer structure 🟪
The service was the last one living wholly under backend/. It now follows
the same layering as abri and the other newer services:

  domain/pashub_fetcher/          core file classification, subfolders
  infrastructure/pashub_fetcher/  PasHub client, token getter, wire DTOs
  orchestration/                  PashubFetcherOrchestrator (was PashubService)
  applications/pashub_fetcher/    lambda handler, trigger request, dev tooling

core_files.py is split along the layer boundary: the domain module keeps the
filename/evidence-category classification rules and no longer imports
infrastructure.postgres, while the CoreFiles -> FileTypeEnum translation moves
to infrastructure/pashub_fetcher/core_file_types.py.

Tests move into the tests/ tree by layer. Note this puts them in the only
suite CI currently runs (unit_tests.yml is disabled), so these 73 tests now
execute on PRs for the first time; they were previously reachable only via
the legacy pytest.ini testpaths.

sharepoint_renamer's image now copies just domain/pashub_fetcher/ rather than
the whole service, since SharepointSubfolders is all it needed.

Behaviour is unchanged. tests/ goes 9927 -> 10000 passed (+73, exactly the
tests that moved in); the legacy suite keeps its same 17 pre-existing failures
and 11 errors. tests/test_lambda_packaging.py confirms both changed
Dockerfiles still copy their handler's full import closure.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-22 13:35:54 +00:00

66 lines
1.8 KiB
Python

import json
import os
import re
from typing import Any, Dict, List
from openpyxl import load_workbook
from applications.pashub_fetcher.pashub_to_ara_trigger_request import (
PashubToAraTriggerRequest,
)
from applications.pashub_fetcher.handler import handler
if __name__ == "__main__":
BASE_DIR = os.path.dirname(os.path.dirname(__file__))
filepath: str = os.path.join(
BASE_DIR,
"pashub_fetcher",
"local_run_02-06-2026",
"ECO_Approach_Coordination_Design_KN.xlsx",
)
wb = load_workbook(filepath, data_only=True)
ws = wb["filtered"]
HEADER_ROW = 1
headers: Dict[str, int] = {}
for col in range(1, ws.max_column + 1):
value = str(ws.cell(row=HEADER_ROW, column=col).value)
if value:
headers[value.strip()] = col
name_col = headers["Name"]
link_col = headers["PasHub ID"]
hubspot_deal_id_col = headers["HubSpot ID"]
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:
continue
match = re.search(r"/jobs/([0-9a-fA-F\-]+)/", str(link))
if not match:
continue
trigger_requests.append(
PashubToAraTriggerRequest(
pashub_link=str(link),
hubspot_deal_id=str(hubspot_deal_id),
address=str(name),
get_other_files=True,
)
)
# ---- Build fake SQS event ----
event: Dict[str, Any] = {
"Records": [{"body": json.dumps(req.model_dump())} for req in trigger_requests]
}
context = None
handler(event, context)