pn-new-crm/tests/unit/dedup/normalize.test.ts

/**
 * Normalization library — unit tests.
 *
 * Every fixture here comes from real dirty values observed in the legacy
 * NocoDB Interests table during the 2026-05-03 audit (see
 * docs/superpowers/specs/2026-05-03-dedup-and-migration-design.md §1.3).
 * The point is regression-prevention: if any of these patterns ever
 * stops normalizing the way it should, dedup quality silently drops.
 */
import { describe, expect, it } from 'vitest';

import {
  normalizeName,
  normalizeEmail,
  normalizePhone,
  resolveCountry,
} from '@/lib/dedup/normalize';

describe('normalizeName', () => {
  it('returns null fields for empty / null input', () => {
    expect(normalizeName('')).toEqual({ display: '', normalized: '', surnameToken: undefined });
    expect(normalizeName('   ')).toEqual({
      display: '',
      normalized: '',
      surnameToken: undefined,
    });
  });

  it('trims leading/trailing whitespace', () => {
    expect(normalizeName('  Marcus Laurent  ')).toMatchObject({
      display: 'Marcus Laurent',
      normalized: 'marcus laurent',
    });
  });

  it('collapses repeated internal whitespace to a single space', () => {
    // From real data: "Arthur  Matthews" (#183), "Corinne  Roche" (#208).
    expect(normalizeName('Arthur  Matthews').display).toBe('Arthur Matthews');
    expect(normalizeName('Corinne   Roche').display).toBe('Corinne Roche');
  });

  it('replaces embedded carriage returns and newlines with single spaces', () => {
    // From real data: "Andrei \nVAGNANOV" (#178), "Daniel\r PRZEDBORSKI" (#175).
    expect(normalizeName('Andrei \nVAGNANOV').display).toBe('Andrei Vagnanov');
    expect(normalizeName('Daniel\r PRZEDBORSKI').display).toBe('Daniel Przedborski');
  });

  it('title-cases ALL-CAPS surnames while keeping given name title-cased', () => {
    // From real data: "Jona ANDERSEN" (#232), "Duane SALTSGAVER" (#227),
    // "Marcos DALLA PRIA" (#165).
    expect(normalizeName('Jona ANDERSEN').display).toBe('Jona Andersen');
    expect(normalizeName('Duane SALTSGAVER').display).toBe('Duane Saltsgaver');
    // Particle 'dalla' stays lowercase mid-name.
    expect(normalizeName('Marcos DALLA PRIA').display).toBe('Marcos dalla Pria');
  });

  it('title-cases lowercased entries', () => {
    // From real data: "antony amaral" (#665), "david rosenbloom" (#239),
    // "john Tickner" (#247).
    expect(normalizeName('antony amaral').display).toBe('Antony Amaral');
    expect(normalizeName('david rosenbloom').display).toBe('David Rosenbloom');
    expect(normalizeName('john Tickner').display).toBe('John Tickner');
  });

  it('keeps Romance and Germanic particles lowercase mid-name', () => {
    // From real data: "Olav van Velsen" (#526), "Bruno Joyerot" (#18),
    // "OLIVIER DAIN" (#677). Also synthetic "Carla de la Cruz".
    expect(normalizeName('Olav van Velsen').display).toBe('Olav van Velsen');
    expect(normalizeName('Carla de la Cruz').display).toBe('Carla de la Cruz');
    expect(normalizeName('OLIVIER DAIN').display).toBe('Olivier Dain');
  });

  it('preserves O‘-prefixed Irish surnames as title-case', () => {
    expect(normalizeName("liam o'brien").display).toBe("Liam O'Brien");
  });

  it('keeps the slash-with-company structure intact', () => {
    // From real data: "Daniel Wainstein / 7 Knots, LLC" (#637),
    // "Bruno Joyerot / SAS TIKI" (#18).
    expect(normalizeName('Daniel Wainstein / 7 Knots, LLC').display).toBe(
      'Daniel Wainstein / 7 Knots, LLC',
    );
    expect(normalizeName('Bruno Joyerot / SAS TIKI').display).toBe('Bruno Joyerot / SAS TIKI');
  });

  it('exposes the last non-particle token as surnameToken (lowercase) for blocking', () => {
    expect(normalizeName('Marcus Laurent').surnameToken).toBe('laurent');
    expect(normalizeName('Olav van Velsen').surnameToken).toBe('velsen');
    expect(normalizeName('Carla de la Cruz').surnameToken).toBe('cruz');
    expect(normalizeName("Liam O'Brien").surnameToken).toBe("o'brien");
  });

  it('handles single-token names — surnameToken is the only token', () => {
    expect(normalizeName('Madonna').surnameToken).toBe('madonna');
  });

  it('produces a normalized form that is always lowercase', () => {
    expect(normalizeName('Andrei VAGNANOV').normalized).toBe('andrei vagnanov');
    expect(normalizeName('Daniel Wainstein / 7 Knots, LLC').normalized).toBe(
      'daniel wainstein / 7 knots, llc',
    );
  });
});

describe('normalizeEmail', () => {
  it('returns null for empty / null inputs', () => {
    expect(normalizeEmail('')).toBeNull();
    expect(normalizeEmail('   ')).toBeNull();
  });

  it('lowercases and trims', () => {
    // From real data: "Arthur@laser-align.com" vs "arthur@laser-align.com" (#183/#686).
    expect(normalizeEmail('Arthur@laser-align.com')).toBe('arthur@laser-align.com');
    expect(normalizeEmail('  marcus@example.com  ')).toBe('marcus@example.com');
  });

  it('lowercases capitalized localparts', () => {
    // From real data: "Bmalone850@gmail.com" (#489), "Hef355@yahoo.com" (#533),
    // "Donclaytonmusic@gmail.com" (#679).
    expect(normalizeEmail('Bmalone850@gmail.com')).toBe('bmalone850@gmail.com');
    expect(normalizeEmail('Hef355@yahoo.com')).toBe('hef355@yahoo.com');
  });

  it('preserves plus-aliases — both legitimate and tricks', () => {
    // Per design §3.2: "+aliases" are not stripped. Compare by full localpart.
    expect(normalizeEmail('marcus+sales@example.com')).toBe('marcus+sales@example.com');
  });

  it('returns null for invalid email shapes', () => {
    expect(normalizeEmail('not-an-email')).toBeNull();
    expect(normalizeEmail('@example.com')).toBeNull();
    expect(normalizeEmail('user@')).toBeNull();
    expect(normalizeEmail('user@.com')).toBeNull();
  });
});

describe('normalizePhone', () => {
  it('returns null for empty / whitespace / null', () => {
    expect(normalizePhone('', 'AI')).toBeNull();
    expect(normalizePhone('   ', 'AI')).toBeNull();
  });

  it('parses a plain E.164 number', () => {
    expect(normalizePhone('+15742740548', 'US')).toMatchObject({
      e164: '+15742740548',
      country: 'US',
    });
  });

  it('strips embedded carriage returns and trailing whitespace', () => {
    // From real data: "+1-264-235-8840\r" (#19), "+1-264-772-3272\r" (#20).
    const out = normalizePhone('+1-264-235-8840\r', 'AI');
    expect(out?.e164).toBe('+12642358840');
  });

  it('strips dashes, dots, parens, single quotes, spaces in a single pass', () => {
    // From real data: "'+1.214.603.4235" (#205), "574-274-0548" (#236),
    // "+1-264-235-8840" (#19), "+1 (212) 555-0123" (synthetic).
    expect(normalizePhone("'+1.214.603.4235", 'US')?.e164).toBe('+12146034235');
    expect(normalizePhone('574-274-0548', 'US')?.e164).toBe('+15742740548');
    expect(normalizePhone('+1 (212) 555-0123', 'US')?.e164).toBe('+12125550123');
  });

  it('converts a leading 00 prefix to + (international dialling)', () => {
    // From real data: "00447956657022" (#216), "0033651381036" (#702).
    expect(normalizePhone('00447956657022', 'GB')?.e164).toBe('+447956657022');
    expect(normalizePhone('0033651381036', 'FR')?.e164).toBe('+33651381036');
  });

  it('uses defaultCountry when input has no international prefix', () => {
    // From real data: "0690699699" (#203, French local), "0651381036" (#701).
    expect(normalizePhone('0690699699', 'FR')?.e164).toBe('+33690699699');
    expect(normalizePhone('0651381036', 'FR')?.e164).toBe('+33651381036');
  });

  it('returns null when there is no prefix AND no defaultCountry', () => {
    // The migration script flags these for human review.
    const out = normalizePhone('5742740548');
    expect(out?.e164 ?? null).toBeNull();
  });

  it('flags placeholder all-zeros numbers and returns null', () => {
    // From real data: "+447000000000" (#641, "Milos Vitkovic" — clearly fake).
    const out = normalizePhone('+447000000000', 'GB');
    expect(out?.flagged).toBe('placeholder');
    expect(out?.e164).toBeNull();
  });

  it('flags multi-number fields and uses the first segment', () => {
    // From real data: "0677580750/0690511494" (#209). Other separators: ; ,
    const slash = normalizePhone('0677580750/0690511494', 'FR');
    expect(slash?.flagged).toBe('multi_number');
    expect(slash?.e164).toBe('+33677580750');

    const semi = normalizePhone('+33611111111;+33622222222', 'FR');
    expect(semi?.flagged).toBe('multi_number');
    expect(semi?.e164).toBe('+33611111111');
  });

  it('flags genuinely unparseable input as `unparseable`', () => {
    const out = normalizePhone('xyz-not-a-phone', 'US');
    expect(out?.flagged).toBe('unparseable');
    expect(out?.e164).toBeNull();
  });

  it('strips an apostrophe-prefix without breaking the parse', () => {
    // From real data: leading "'" copy-pasted from spreadsheets escapes
    // numeric-cell coercion. Should be invisible to dedup.
    expect(normalizePhone("'0690699699", 'FR')?.e164).toBe('+33690699699');
  });

  it('returns the country alongside the E.164 form', () => {
    expect(normalizePhone('+33690699699', 'FR')).toMatchObject({
      e164: '+33690699699',
      country: 'FR',
    });
  });
});

describe('resolveCountry', () => {
  it('returns null for empty / nullish input', () => {
    expect(resolveCountry('')).toEqual({ iso: null, confidence: null });
    expect(resolveCountry('   ')).toEqual({ iso: null, confidence: null });
  });

  it('exact-matches a canonical English country name', () => {
    expect(resolveCountry('Anguilla')).toEqual({ iso: 'AI', confidence: 'exact' });
    expect(resolveCountry('United Kingdom')).toEqual({ iso: 'GB', confidence: 'exact' });
    expect(resolveCountry('United States')).toEqual({ iso: 'US', confidence: 'exact' });
  });

  it('matches case-insensitively', () => {
    expect(resolveCountry('anguilla').iso).toBe('AI');
    expect(resolveCountry('UNITED KINGDOM').iso).toBe('GB');
  });

  it('matches values with surrounding whitespace', () => {
    expect(resolveCountry('  United States  ').iso).toBe('US');
  });

  it('handles diacritic variants of Saint-Barthélemy', () => {
    // From real data: "Saint barthelemy" (#203), "St Barth" (#208), "Saint-Barthélemy".
    expect(resolveCountry('Saint-Barthélemy').iso).toBe('BL');
    expect(resolveCountry('Saint Barthelemy').iso).toBe('BL');
    expect(resolveCountry('saint barthelemy').iso).toBe('BL');
    expect(resolveCountry('St Barth').iso).toBe('BL');
  });

  it('resolves common abbreviations', () => {
    expect(resolveCountry('USA').iso).toBe('US');
    expect(resolveCountry('UK').iso).toBe('GB');
  });

  it('falls back to a city → country mapping for high-frequency cities', () => {
    // From real data: "Kansas City" (#198), "Sag Harbor Y" (#239).
    expect(resolveCountry('Kansas City').iso).toBe('US');
    expect(resolveCountry('Sag Harbor Y').iso).toBe('US');
  });

  it('marks the confidence tier appropriately', () => {
    expect(resolveCountry('Anguilla').confidence).toBe('exact');
    expect(resolveCountry('Kansas City').confidence).toBe('city');
  });

  it('returns null + null for unresolvable values', () => {
    // Migration script flags these for human review rather than guessing.
    expect(resolveCountry('asdfghjkl xyz')).toEqual({ iso: null, confidence: null });
    expect(resolveCountry('Mars')).toEqual({ iso: null, confidence: null });
  });
});