Files
pn-new-crm/tests/unit/dedup/find-matches.test.ts

380 lines
13 KiB
TypeScript
Raw Permalink Normal View History

feat(dedup): normalization + match-finding library (P1) The pure-logic spine of the client deduplication system spec'd in docs/superpowers/specs/2026-05-03-dedup-and-migration-design.md. Two modules, JSX-free, vitest-tested against fixtures drawn directly from real dirty values observed in the legacy NocoDB Interests audit. src/lib/dedup/normalize.ts - normalizeName: trims whitespace, replaces \r/\n/\t, intelligently title-cases ALL-CAPS surnames while keeping particles (van / de / dalla / etc.) lowercase mid-name. Preserves Irish O' surnames and the "slash-with-company" structure ("Daniel Wainstein / 7 Knots, LLC") seen in production. Returns a surnameToken (lowercased last non-particle token) for use as a dedup blocking key. - normalizeEmail: trim + lowercase + zod email validation. Plus-aliases preserved; null on invalid. - normalizePhone: pre-cleans the input (strips spreadsheet apostrophes, carriage returns, dots/dashes/parens, converts 00 prefix to +) then delegates to libphonenumber-js. Detects multi-number fields ("a/b", "a;b") and placeholder fakes (8+ consecutive zeros, e.g. +447000000000). Flags every quirk so the migration report and runtime audit log can surface it. - resolveCountry: maps free-text country/region input to ISO-3166-1 alpha-2 via alias → exact (vs. Intl-derived names) → city → fuzzy (Levenshtein ≤ 2). Fuzzy is gated by length so 4-char inputs ("Mars") don't false-positive against short country names. - levenshtein: standard iterative implementation, exported for reuse by find-matches. src/lib/dedup/find-matches.ts - findClientMatches: builds three blocking indexes off the pool (email / phone / surname-token), gathers the comparison set via union, and scores each candidate via the rule set in design §4.2: Email match +60 Phone E.164 match +50 (≥ 8 digits, excludes placeholder zeros) Name exact match +20 Surname + given fuzzy +15 (Levenshtein ≤ 1) Negative: shared email but different phone country −15 Negative: name match but no shared contact −20 Score is clamped to [0,100]. Confidence tier ('high' / 'medium' / 'low') is derived from configurable thresholds passed in by the caller — defaults are highScore=90, mediumScore=50. tests/unit/dedup/normalize.test.ts (38 cases) Every dirty-data pattern from design §1.3 has a fixture: carriage returns in names, ALL-CAPS surnames, lowercase entries, particles, slash-with-company, plus-aliases, capitalized email localparts, spreadsheet-apostrophe phones, multi-number phones, placeholder phones, 00-prefix phones, French/UK local-format phones, Saint-Barthélemy diacritic variants, Kansas City fallback. tests/unit/dedup/find-matches.test.ts (12 cases) Each duplicate cluster from design §1.2 has a test: - Pattern A (Deepak Ramchandani — pure double-submit) → high - Pattern B (Howard Wiarda — phone format variance) → high - Pattern C (Nicolas Ruiz — name capitalization) → high - Pattern D (Chris/Christopher Allen — name shortening) → high - Pattern E (Christopher Camazou — typo on resubmit) → high or medium - Pattern E (Constanzo/Costanzo — surname typo, multi-yacht) → high - Pattern F (Etiennette Clamouze — same name, different country) → must NOT auto-merge - Pattern F (Bruno+Bruce — shared household contact) → no match - Negative evidence (same email, different phone country) → medium - Blocking (no shared keys → 0 matches) - Sort order (high before low) - Empty pool Total: 50 new tests, all green. Zero changes to runtime behavior or schema; unblocks P2 (runtime surfaces) and P3 (NocoDB migration). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-03 14:28:59 +02:00
/**
* Match-finding library unit tests.
*
* Each duplicate cluster from the legacy NocoDB Interests audit (see
* docs/superpowers/specs/2026-05-03-dedup-and-migration-design.md §1.2)
* is encoded as a fixture here. The expected scoring tier (high / medium
* / low) is the design contract if the algorithm starts returning
* "high" for a Pattern F case (Etiennette / Bruno+Bruce) it has lost
* the false-positive guard and we'll know immediately.
*/
import { describe, expect, it } from 'vitest';
import { findClientMatches, type MatchCandidate } from '@/lib/dedup/find-matches';
// Sensible defaults for tests — match the design's recommended thresholds.
const THRESHOLDS = {
highScore: 90,
mediumScore: 50,
};
function candidate(partial: Partial<MatchCandidate> & { id: string }): MatchCandidate {
return {
id: partial.id,
fullName: partial.fullName ?? null,
surnameToken: partial.surnameToken ?? null,
emails: partial.emails ?? [],
phonesE164: partial.phonesE164 ?? [],
countryIso: partial.countryIso ?? null,
};
}
describe('findClientMatches', () => {
describe('Pattern A — pure double-submit (high confidence)', () => {
it('flags identical email + phone as high', () => {
// From real data: Deepak Ramchandani #624/#625, identical fields.
const incoming = candidate({
id: 'b',
fullName: 'Deepak Ramchandani',
surnameToken: 'ramchandani',
emails: ['dannyrams8888@gmail.com'],
phonesE164: ['+17215868888'],
});
const pool = [
candidate({
id: 'a',
fullName: 'Deepak Ramchandani',
surnameToken: 'ramchandani',
emails: ['dannyrams8888@gmail.com'],
phonesE164: ['+17215868888'],
}),
];
const matches = findClientMatches(incoming, pool, THRESHOLDS);
expect(matches).toHaveLength(1);
expect(matches[0]!.candidate.id).toBe('a');
expect(matches[0]!.score).toBeGreaterThanOrEqual(90);
expect(matches[0]!.confidence).toBe('high');
expect(matches[0]!.reasons).toEqual(expect.arrayContaining(['email match', 'phone match']));
});
});
describe('Pattern B — same email, different phone format (high)', () => {
it('high confidence when phones already normalize-equal', () => {
// From real data: Howard Wiarda #236/#536, "574-274-0548" vs "+15742740548".
// After normalization both phones are the same E.164, so the rule fires.
const incoming = candidate({
id: 'b',
fullName: 'Howard Wiarda',
surnameToken: 'wiarda',
emails: ['hwiarda@hotmail.com'],
phonesE164: ['+15742740548'],
});
const pool = [
candidate({
id: 'a',
fullName: 'Howard Wiarda',
surnameToken: 'wiarda',
emails: ['hwiarda@hotmail.com'],
phonesE164: ['+15742740548'],
}),
];
const matches = findClientMatches(incoming, pool, THRESHOLDS);
expect(matches[0]!.confidence).toBe('high');
expect(matches[0]!.score).toBeGreaterThanOrEqual(90);
});
});
describe('Pattern C — name capitalization variant (high)', () => {
it('treats lowercase + uppercase as the same person when surname-token + email + phone all match', () => {
// From real data: Nicolas Ruiz #681/#682/#683, email differs only by case.
const incoming = candidate({
id: 'b',
fullName: 'Nicolas Ruiz',
surnameToken: 'ruiz',
emails: ['ruiz.nicolas@ufl.edu'],
phonesE164: ['+17862006617'],
});
const pool = [
candidate({
id: 'a',
fullName: 'Nicolas Ruiz',
surnameToken: 'ruiz',
emails: ['ruiz.nicolas@ufl.edu'],
phonesE164: ['+17862006617'],
}),
];
const matches = findClientMatches(incoming, pool, THRESHOLDS);
expect(matches[0]!.confidence).toBe('high');
});
});
describe('Pattern D — name shortening (high)', () => {
it('Chris vs Christopher with same email + phone scores high', () => {
// From real data: Chris Allen #700 vs Christopher Allen #534.
const incoming = candidate({
id: 'b',
fullName: 'Chris Allen',
surnameToken: 'allen',
emails: ['chris@thundercatsports.com'],
phonesE164: ['+17814548950'],
});
const pool = [
candidate({
id: 'a',
fullName: 'Christopher Allen',
surnameToken: 'allen',
emails: ['chris@thundercatsports.com'],
phonesE164: ['+17814548950'],
}),
];
const matches = findClientMatches(incoming, pool, THRESHOLDS);
expect(matches[0]!.confidence).toBe('high');
});
});
describe('Pattern E — typo on resubmit', () => {
it('same email + nearly-identical phone (typo in last digits) scores high', () => {
// Christopher Camazou #649/#650 — phone differs in last 4 digits but
// everything else matches. Exact phone equality fails; email exact
// match alone (60) + name-token match (20) puts us in medium tier.
// The user can confirm the merge.
const incoming = candidate({
id: 'b',
fullName: 'Christopher Camazou',
surnameToken: 'camazou',
emails: ['camazou11@gmail.com'],
phonesE164: ['+33608334455'],
});
const pool = [
candidate({
id: 'a',
fullName: 'Christopher Camazou',
surnameToken: 'camazou',
emails: ['camazou11@gmail.com'],
phonesE164: ['+33608336549'],
}),
];
const matches = findClientMatches(incoming, pool, THRESHOLDS);
expect(matches).toHaveLength(1);
// Email + name match without phone match — strong but not certain.
expect(matches[0]!.confidence).toMatch(/^(high|medium)$/);
expect(matches[0]!.score).toBeGreaterThanOrEqual(70);
});
it('Constanzo / Costanzo surname typo with same email + phone scores high', () => {
// Gianfranco Di Constanzo #585 vs Di Costanzo #336 — same email + phone
// and only a 1-letter surname typo. This is a strong "same client,
// multiple yachts" signal — the design's signature win.
const incoming = candidate({
id: 'b',
fullName: 'Gianfranco Di Constanzo',
surnameToken: 'constanzo',
emails: ['gdc@nauticall.com'],
phonesE164: ['+17542628669'],
});
const pool = [
candidate({
id: 'a',
fullName: 'Gianfranco Di Costanzo',
surnameToken: 'costanzo',
emails: ['gdc@nauticall.com'],
phonesE164: ['+17542628669'],
}),
];
const matches = findClientMatches(incoming, pool, THRESHOLDS);
expect(matches[0]!.confidence).toBe('high');
expect(matches[0]!.score).toBeGreaterThanOrEqual(90);
});
});
describe('Pattern F — hard cases (must NOT auto-merge)', () => {
it('same name with different country phone + different email scores at most medium', () => {
// Etiennette Clamouze #188/#717 — same name but completely different
// email + phone (and the phones are in different country codes,
// suggesting either a relative, a coworker, or a name-collision).
// We must NOT classify this as "high" or it would force-merge two
// distinct people.
const incoming = candidate({
id: 'b',
fullName: 'Etiennette Clamouze',
surnameToken: 'clamouze',
emails: ['etiennette@the-manoah.com'],
phonesE164: ['+12645815607'],
countryIso: 'AI',
});
const pool = [
candidate({
id: 'a',
fullName: 'Etiennette Clamouze',
surnameToken: 'clamouze',
emails: ['clamouze.etiennette@gmail.com'],
phonesE164: ['+33767780640'],
countryIso: 'FR',
}),
];
const matches = findClientMatches(incoming, pool, THRESHOLDS);
// Surname-token + name-exact match should score in medium tier so
// the pair lands in the review queue but doesn't auto-merge.
if (matches.length > 0) {
expect(matches[0]!.confidence).not.toBe('high');
expect(matches[0]!.score).toBeLessThan(90);
}
});
it('shared email between two clearly different names is medium not high', () => {
// Bruno Joyerot #18 vs Bruce Hearn #19 — Bruno's row shows email
// belonging to "catherine elaine hearn" (Bruce's spouse). Same
// household phone area code. Name overlap is partial. Don't merge.
const incoming = candidate({
id: 'b',
fullName: 'Bruce Hearn',
surnameToken: 'hearn',
emails: ['bhearn1063@gmail.com'],
phonesE164: ['+12642358840'],
});
const pool = [
candidate({
id: 'a',
fullName: 'Bruno Joyerot',
surnameToken: 'joyerot',
emails: ['catherineelainehearn@gmail.com'],
phonesE164: ['+12642352816'],
}),
];
const matches = findClientMatches(incoming, pool, THRESHOLDS);
// Names don't match, emails don't match, phones differ — there's
// no reason for this to surface at all. Either no match or low.
if (matches.length > 0) {
expect(matches[0]!.confidence).toBe('low');
}
});
});
describe('Negative evidence — same email but different country phone', () => {
it('reduces score when email matches but phone country differs', () => {
// Constructed: same email, but one phone is +33 (FR) and the other
// is +1 (US). Likely a shared-inbox spouse situation. We want
// medium tier so it lands in review, not high tier.
const incoming = candidate({
id: 'b',
fullName: 'Test User',
surnameToken: 'user',
emails: ['shared@example.com'],
phonesE164: ['+15551234567'],
countryIso: 'US',
});
const pool = [
candidate({
id: 'a',
fullName: 'Test User',
surnameToken: 'user',
emails: ['shared@example.com'],
phonesE164: ['+33611111111'],
countryIso: 'FR',
}),
];
const matches = findClientMatches(incoming, pool, THRESHOLDS);
// Email match alone would be 60 + name token match 20 = 80 (medium).
// Negative evidence (different phone country) brings it down further.
expect(matches[0]!.confidence).toBe('medium');
});
});
describe('Blocking — only relevant candidates are scored', () => {
it('does not score candidates with no shared emails / phones / surname token', () => {
const incoming = candidate({
id: 'newbie',
fullName: 'Alice Smith',
surnameToken: 'smith',
emails: ['alice@example.com'],
phonesE164: ['+15551234567'],
});
const pool = [
candidate({
id: 'unrelated1',
fullName: 'Bob Jones',
surnameToken: 'jones',
emails: ['bob@example.org'],
phonesE164: ['+33611111111'],
}),
candidate({
id: 'unrelated2',
fullName: 'Carol White',
surnameToken: 'white',
emails: ['carol@example.net'],
phonesE164: ['+447700900111'],
}),
];
const matches = findClientMatches(incoming, pool, THRESHOLDS);
expect(matches).toHaveLength(0);
});
});
describe('Empty pool', () => {
it('returns no matches when the pool is empty', () => {
const incoming = candidate({
id: 'a',
fullName: 'Alice',
emails: ['alice@example.com'],
});
expect(findClientMatches(incoming, [], THRESHOLDS)).toEqual([]);
});
});
describe('Sort order', () => {
it('returns matches sorted by score descending', () => {
const incoming = candidate({
id: 'incoming',
fullName: 'John Smith',
surnameToken: 'smith',
emails: ['john@example.com'],
phonesE164: ['+15551234567'],
});
const pool = [
candidate({
// High match — same email + phone
id: 'high-match',
fullName: 'John Smith',
surnameToken: 'smith',
emails: ['john@example.com'],
phonesE164: ['+15551234567'],
}),
candidate({
// Medium match — same email only
id: 'medium-match',
fullName: 'Different Person',
surnameToken: 'person',
emails: ['john@example.com'],
phonesE164: ['+33611111111'],
}),
];
const matches = findClientMatches(incoming, pool, THRESHOLDS);
expect(matches.length).toBeGreaterThanOrEqual(2);
expect(matches[0]!.candidate.id).toBe('high-match');
expect(matches[0]!.score).toBeGreaterThan(matches[1]!.score);
});
});
});