Spaces:
Running
Running
| """ | |
| check_duplicate_leads.py -- read-only: lists every company_name that has more than one Lead row. | |
| Investigating a user report (2026-09-22): "Key West Boats" showing twice on the Pipeline tab. Confirmed: | |
| every duplicate found so far is source="Manual entry", created 2026-09-15/17 -- crud.is_duplicate() (the | |
| case-insensitive company_name check) wasn't wired into the "Add a Lead" popover's endpoint until it went | |
| live 2026-09-17 (see app/api/leads.py create_lead()'s own docstring), so a rep could accidentally submit | |
| the same company twice before that fix landed. It's already wired into every creation path now (manual, | |
| AI discovery, CSV import, Google Maps) -- these groups are historical leftovers from just before the fix, | |
| not an ongoing bug. | |
| uv run python scripts/check_duplicate_leads.py | |
| Read-only -- prints what it finds, changes nothing. Prints enough per row (deal value, category, meeting/ | |
| callback dates) to tell which one is the real record before deciding which to delete. | |
| """ | |
| from __future__ import annotations | |
| import sys | |
| from collections import defaultdict | |
| from pathlib import Path | |
| sys.path.insert(0, str(Path(__file__).resolve().parent.parent)) | |
| from sqlalchemy import select # noqa: E402 | |
| from app.database import SessionLocal # noqa: E402 | |
| from app.models import Lead # noqa: E402 | |
| def main() -> int: | |
| db = SessionLocal() | |
| try: | |
| leads = list(db.scalars(select(Lead).order_by(Lead.company_name, Lead.created_at)).all()) | |
| groups: dict[str, list[Lead]] = defaultdict(list) | |
| for lead in leads: | |
| key = (lead.company_name or "").strip().lower() | |
| if key: | |
| groups[key].append(lead) | |
| dupes = {k: v for k, v in groups.items() if len(v) > 1} | |
| if not dupes: | |
| print("No duplicate company names found.") | |
| return 0 | |
| print(f"{len(dupes)} company name(s) with more than one lead row:\n") | |
| for key, rows in sorted(dupes.items(), key=lambda kv: -len(kv[1])): | |
| print(f"'{rows[0].company_name}' -- {len(rows)} rows:") | |
| for lead in rows: | |
| print( | |
| f" #{lead.id:<6} stage={lead.pipeline_stage:<15} " | |
| f"deal_value={lead.deal_value} industry_tag={lead.industry_tag!r}" | |
| ) | |
| print( | |
| f" meeting_at={lead.meeting_at} callback_at={lead.callback_at} " | |
| f"sent_to_desk_at={lead.sent_to_desk_at} hidden_at={lead.hidden_at}" | |
| ) | |
| print( | |
| f" created_at={lead.created_at} source={lead.source_prompt!r} " | |
| f"notes={'yes' if (lead.notes or '').strip() else 'no'}" | |
| ) | |
| print() | |
| return 0 | |
| finally: | |
| db.close() | |
| if __name__ == "__main__": | |
| sys.exit(main()) | |