pn-new-crm/tests/unit/dedup/migration-transform.test.ts

/**
 * Migration transform — fixture-based regression test.
 *
 * Feeds the transform a small frozen NocoDB snapshot containing one
 * representative row from each duplicate pattern documented in
 * docs/superpowers/specs/2026-05-03-dedup-and-migration-design.md §1.2,
 * and asserts the resulting plan matches the algorithm's expected
 * behavior. If any future change starts merging Pattern F (Etiennette
 * Clamouze) or stops merging Pattern A (Deepak Ramchandani), this
 * test fails immediately.
 */
import { describe, expect, it } from 'vitest';

import { transformSnapshot } from '@/lib/dedup/migration-transform';
import type { NocoDbRow, NocoDbSnapshot } from '@/lib/dedup/nocodb-source';

function row(fields: Partial<NocoDbRow> & { Id: number }): NocoDbRow {
  return fields as NocoDbRow;
}

const FIXTURE: NocoDbSnapshot = {
  fetchedAt: '2026-05-03T12:00:00.000Z',
  berths: [],
  residentialInterests: [],
  websiteInterestSubmissions: [],
  websiteContactFormSubmissions: [],
  websiteBerthEoiSupplements: [],
  interests: [
    // Pattern A: pure double-submit (Deepak Ramchandani #624/#625)
    row({
      Id: 624,
      'Full Name': 'Deepak Ramchandani',
      'Email Address': 'dannyrams8888@gmail.com',
      'Phone Number': '+17215868888',
      'Sales Process Level': 'General Qualified Interest',
    }),
    row({
      Id: 625,
      'Full Name': 'Deepak Ramchandani',
      'Email Address': 'dannyrams8888@gmail.com',
      'Phone Number': '+17215868888',
      'Sales Process Level': 'General Qualified Interest',
    }),

    // Pattern B: phone format variance (Howard Wiarda #236/#536)
    row({
      Id: 236,
      'Full Name': 'Howard Wiarda',
      'Email Address': 'hwiarda@hotmail.com',
      'Phone Number': '574-274-0548',
      'Place of Residence': 'USA',
      'Sales Process Level': 'General Qualified Interest',
    }),
    row({
      Id: 536,
      'Full Name': 'Howard Wiarda',
      'Email Address': 'hwiarda@hotmail.com',
      'Phone Number': '+15742740548',
      'Sales Process Level': 'General Qualified Interest',
    }),

    // Pattern C: name capitalization (Nicolas Ruiz #681/#682/#683 — three rows)
    row({
      Id: 681,
      'Full Name': 'Nicolas Ruiz',
      'Email Address': 'ruiz.nicolas@ufl.edu',
      'Phone Number': '+17862006617',
      'Sales Process Level': 'General Qualified Interest',
    }),
    row({
      Id: 682,
      'Full Name': 'Nicolas Ruiz',
      'Email Address': 'ruiz.nicolas@ufl.edu',
      'Phone Number': '+17862006617',
      'Sales Process Level': 'Specific Qualified Interest',
    }),
    row({
      Id: 683,
      'Full Name': 'Nicolas Ruiz',
      'Email Address': 'Ruiz.Nicolas@ufl.edu',
      'Phone Number': '+17862006617',
      'Sales Process Level': 'General Qualified Interest',
    }),

    // Pattern E: surname typo with same email + phone (Constanzo/Costanzo)
    row({
      Id: 336,
      'Full Name': 'Gianfranco Di Costanzo',
      'Email Address': 'gdc@nauticall.com',
      'Phone Number': '+17542628669',
      'Yacht Name': 'GEMINI',
      'Sales Process Level': 'Contract Signed',
    }),
    row({
      Id: 585,
      'Full Name': 'Gianfranco Di Constanzo',
      'Email Address': 'gdc@nauticall.com',
      'Phone Number': '+17542628669',
      'Yacht Name': 'CALYPSO',
      'Sales Process Level': 'Signed EOI and NDA',
    }),

    // Pattern F: same name, different country phones (Etiennette Clamouze)
    row({
      Id: 188,
      'Full Name': 'Etiennette Clamouze',
      'Email Address': 'clamouze.etiennette@gmail.com',
      'Phone Number': '+33767780640',
      'Sales Process Level': 'General Qualified Interest',
    }),
    row({
      Id: 717,
      'Full Name': 'Etiennette Clamouze',
      'Email Address': 'Etiennette@the-manoah.com',
      'Phone Number': '+12645815607',
      'Sales Process Level': 'General Qualified Interest',
    }),

    // Single isolated row to verify non-duplicates pass through
    row({
      Id: 999,
      'Full Name': 'Lone Wolf',
      'Email Address': 'lone@example.com',
      'Phone Number': '+15551234567',
      'Sales Process Level': 'General Qualified Interest',
    }),
  ],
};

describe('transformSnapshot — fixture regression', () => {
  it('produces the expected number of clients + interests', () => {
    const plan = transformSnapshot(FIXTURE);

    // 12 input rows → 7 unique clients (Deepak: 1, Wiarda: 1, Ruiz: 1,
    // Constanzo: 1, Etiennette x2: 2, Lone: 1). Etiennette stays as 2
    // because Pattern F is correctly NOT auto-merged.
    expect(plan.stats.outputClients).toBe(7);
    expect(plan.stats.outputInterests).toBe(12); // one per source row
  });

  it('auto-links every Pattern A–E cluster', () => {
    const plan = transformSnapshot(FIXTURE);
    const linkedSourceIds = new Set<number>();
    for (const link of plan.autoLinks) {
      linkedSourceIds.add(link.leadSourceId);
      for (const merged of link.mergedSourceIds) {
        linkedSourceIds.add(merged);
      }
    }

    // Pattern A: 624 + 625
    expect(linkedSourceIds.has(624) && linkedSourceIds.has(625)).toBe(true);
    // Pattern B: 236 + 536
    expect(linkedSourceIds.has(236) && linkedSourceIds.has(536)).toBe(true);
    // Pattern C: 681 + 682 + 683 (three-way)
    expect(linkedSourceIds.has(681) && linkedSourceIds.has(682) && linkedSourceIds.has(683)).toBe(
      true,
    );
    // Pattern E: 336 + 585
    expect(linkedSourceIds.has(336) && linkedSourceIds.has(585)).toBe(true);
  });

  it('does NOT auto-link Pattern F (Etiennette Clamouze, different country)', () => {
    const plan = transformSnapshot(FIXTURE);
    const linkedSourceIds = new Set<number>();
    for (const link of plan.autoLinks) {
      linkedSourceIds.add(link.leadSourceId);
      for (const merged of link.mergedSourceIds) {
        linkedSourceIds.add(merged);
      }
    }
    // Both Etiennette rows must remain as separate clients.
    expect(linkedSourceIds.has(188)).toBe(false);
    expect(linkedSourceIds.has(717)).toBe(false);
  });

  it('preserves every interest as its own row even when clients merge', () => {
    const plan = transformSnapshot(FIXTURE);
    const sourceIds = plan.interests.map((i) => i.sourceId).sort((a, b) => a - b);
    expect(sourceIds).toEqual([188, 236, 336, 536, 585, 624, 625, 681, 682, 683, 717, 999]);
  });

  it('maps the legacy 8-stage enum to new pipeline stages', () => {
    const plan = transformSnapshot(FIXTURE);
    const stagesById = new Map(plan.interests.map((i) => [i.sourceId, i.pipelineStage]));
    expect(stagesById.get(681)).toBe('open'); // General Qualified Interest
    expect(stagesById.get(682)).toBe('details_sent'); // Specific Qualified Interest
    expect(stagesById.get(336)).toBe('contract_signed'); // Contract Signed
    expect(stagesById.get(585)).toBe('eoi_signed'); // Signed EOI and NDA
  });

  it('attaches different yachts to one merged Constanzo client', () => {
    const plan = transformSnapshot(FIXTURE);
    const constanzoClient = plan.clients.find(
      (c) => c.sourceIds.includes(336) && c.sourceIds.includes(585),
    );
    expect(constanzoClient).toBeDefined();
    const yachtsForConstanzo = plan.interests
      .filter((i) => i.clientTempId === constanzoClient!.tempId)
      .map((i) => i.yachtName)
      .sort();
    expect(yachtsForConstanzo).toEqual(['CALYPSO', 'GEMINI']);
  });

  it('produces deterministic output (same input → same plan)', () => {
    // The transform is pure — running it twice should yield bit-identical
    // results. Catches order-dependent bugs in the dedup clustering.
    const a = transformSnapshot(FIXTURE);
    const b = transformSnapshot(FIXTURE);
    expect(JSON.stringify(a.stats)).toBe(JSON.stringify(b.stats));
    expect(a.autoLinks.length).toBe(b.autoLinks.length);
  });
});