portal/app/tests/Feature/Supplier/CsvReconcileJobTest.php

<?php

declare(strict_types=1);

use App\Exceptions\Supplier\SupplierTransientException;
use App\Jobs\RouteSupplierLeadJob;
use App\Jobs\Supplier\CsvReconcileJob;
use App\Jobs\Supplier\RefreshSupplierSessionJob;
use App\Mail\CsvDriftAlertMail;
use App\Models\SupplierLead;
use App\Services\Supplier\SupplierCsvParser;
use App\Services\Supplier\SupplierPortalClient;
use Illuminate\Contracts\Mail\Mailer;
use Illuminate\Foundation\Testing\DatabaseTransactions;
use Illuminate\Http\Client\Request;
use Illuminate\Support\Facades\Bus;
use Illuminate\Support\Facades\Cache;
use Illuminate\Support\Facades\DB;
use Illuminate\Support\Facades\Http;
use Illuminate\Support\Facades\Mail;
use Tests\Concerns\SharesSupplierPdo;

uses(DatabaseTransactions::class, SharesSupplierPdo::class);

function putSupplierSession(): void
{
    Cache::store('redis')->put(
        'supplier:session',
        ['phpsessid' => 'test', 'csrf' => 'test'],
        now()->addHour(),
    );
}

beforeEach(function (): void {
    Mail::fake();
    Bus::fake([RouteSupplierLeadJob::class]);
    app()->bind(RefreshSupplierSessionJob::class, fn () => new class
    {
        public function handle(): void
        {
            putSupplierSession();
        }
    });
    Cache::store('redis')->forget('supplier:csv_reconcile');
    putSupplierSession();
    config(['services.supplier.portal_url' => 'https://crm.bp-gr.ru']);
    config(['services.supplier.alert_email' => 'ops@liderra.ru']);
});

afterEach(function (): void {
    Cache::store('redis')->forget('supplier:csv_reconcile');
});

/**
 * 3-колоночный CSV «Запрос номеров»: Name;Tag;Phone.
 *
 * @param  array<int, array{project: string, phone: string}>  $rows
 */
function csvBody(array $rows): string
{
    $out = "Name;Tag;Phone\n";
    foreach ($rows as $r) {
        $out .= "{$r['project']};tag;{$r['phone']}\n";
    }

    return $out;
}

/**
 * Мокает весь async-флоу отчёта (реальные endpoint'ы — discovery T3 2026-05-19):
 *   POST /admin/report/save-report   → "OK"
 *   GET  /admin/report/load-reports  → array [{id, title, status:"1", ...}]  (id извлекается по title-match)
 *   GET  /admin/report/getfile?id=N  → raw CSV
 *
 * Title включает фактически использованные dateFrom/dateTo — захватываем их из save-report body
 * и возвращаем тот же диапазон в load-reports, чтобы матч requestNumbersReport состоялся.
 */
function fakeReportFlow(string $csv): void
{
    $captured = ['from' => '', 'to' => ''];

    Http::fake([
        'crm.bp-gr.ru/admin/report/save-report' => function (Request $r) use (&$captured) {
            $body = $r->data();
            $captured['from'] = (string) ($body['reportFilter']['dateFrom'] ?? '');
            $captured['to'] = (string) ($body['reportFilter']['dateTo'] ?? '');

            return Http::response('OK', 200);
        },
        'crm.bp-gr.ru/admin/report/load-reports' => function () use (&$captured) {
            $title = sprintf('Запрос номеров с %s по %s', $captured['from'], $captured['to']);

            return Http::response([
                ['id' => '700001', 'title' => $title, 'status' => '1', 'is_file' => '1', 'percent' => '100'],
            ], 200);
        },
        'crm.bp-gr.ru/admin/report/getfile*' => Http::response($csv, 200),
    ]);
}

function runCsvReconcile(): void
{
    app(CsvReconcileJob::class)->handle(
        app(SupplierPortalClient::class),
        app(SupplierCsvParser::class),
        app(Mailer::class),
    );
}

it('no missing leads — status=ok, no recovery, no alert', function (): void {
    for ($i = 0; $i < 10; $i++) {
        SupplierLead::create([
            'supplier_project_id' => null,
            'platform' => 'B1',
            'phone' => "7999000000{$i}",
            'vid' => 800000 + $i,
            'raw_payload' => ['project' => 'B1_a.com', 'phone' => "7999000000{$i}"],
            'received_at' => now()->subHour(),
            'source' => 'webhook',
        ]);
    }

    $rows = [];
    for ($i = 0; $i < 10; $i++) {
        $rows[] = ['project' => 'B1_a.com', 'phone' => "7999000000{$i}"];
    }
    fakeReportFlow(csvBody($rows));

    runCsvReconcile();

    $log = DB::table('supplier_csv_reconcile_log')->latest('id')->first();
    expect($log->status)->toBe('ok');
    expect((int) $log->total_csv_rows)->toBe(10);
    expect((int) $log->matched_count)->toBe(10);
    expect((int) $log->recovered_count)->toBe(0);

    Mail::assertNotSent(CsvDriftAlertMail::class); // scoped — TenantBusinessDriftAlertMail may fire on leaked snapshots
    Bus::assertNothingDispatched();
});

it('1 missing of 10 (drift 10%) — recovery + drift alert', function (): void {
    for ($i = 0; $i < 9; $i++) {
        SupplierLead::create([
            'supplier_project_id' => null,
            'platform' => 'B1',
            'phone' => "7999111000{$i}",
            'vid' => 810000 + $i,
            'raw_payload' => ['project' => 'B1_a.com', 'phone' => "7999111000{$i}"],
            'received_at' => now()->subHour(),
            'source' => 'webhook',
        ]);
    }

    $rows = [];
    for ($i = 0; $i < 10; $i++) {
        $rows[] = ['project' => 'B1_a.com', 'phone' => "7999111000{$i}"];
    }
    fakeReportFlow(csvBody($rows));

    runCsvReconcile();

    $log = DB::table('supplier_csv_reconcile_log')->latest('id')->first();
    expect($log->status)->toBe('drift_alert');
    expect((float) $log->drift_ratio)->toBeGreaterThan(0.05);
    expect((int) $log->recovered_count)->toBe(1);

    $recovered = SupplierLead::where('source', 'csv_recovery')->first();
    expect($recovered)->not->toBeNull();
    expect($recovered->vid)->toBeNull();
    expect($recovered->recovered_from_csv_at)->not->toBeNull();

    Mail::assertSent(CsvDriftAlertMail::class, 1);
    Bus::assertDispatched(RouteSupplierLeadJob::class, 1);
});

it('1 missing of 100 (drift 1%) — recovery without alert', function (): void {
    for ($i = 0; $i < 99; $i++) {
        SupplierLead::create([
            'supplier_project_id' => null,
            'platform' => 'B1',
            'phone' => '79992'.str_pad((string) $i, 6, '0', STR_PAD_LEFT),
            'vid' => 820000 + $i,
            'raw_payload' => ['project' => 'B1_a.com', 'phone' => '79992'.str_pad((string) $i, 6, '0', STR_PAD_LEFT)],
            'received_at' => now()->subHour(),
            'source' => 'webhook',
        ]);
    }

    $rows = [];
    for ($i = 0; $i < 100; $i++) {
        $rows[] = ['project' => 'B1_a.com', 'phone' => '79992'.str_pad((string) $i, 6, '0', STR_PAD_LEFT)];
    }
    fakeReportFlow(csvBody($rows));

    runCsvReconcile();

    $log = DB::table('supplier_csv_reconcile_log')->latest('id')->first();
    expect($log->status)->toBe('ok');
    expect((int) $log->recovered_count)->toBe(1);
    Mail::assertNotSent(CsvDriftAlertMail::class); // scoped — TenantBusinessDriftAlertMail may fire on leaked snapshots
});

it('dedup is keyed by (phone, project) — same phone on different project is NOT a duplicate', function (): void {
    SupplierLead::create([
        'supplier_project_id' => null,
        'platform' => 'B1',
        'phone' => '79995550000',
        'vid' => 830000,
        'raw_payload' => ['project' => 'B1_a.com', 'phone' => '79995550000'],
        'received_at' => now()->subHour(),
        'source' => 'webhook',
    ]);

    fakeReportFlow(csvBody([
        ['project' => 'B1_a.com', 'phone' => '79995550000'],
        ['project' => 'B2_b.com', 'phone' => '79995550000'],
    ]));

    runCsvReconcile();

    $log = DB::table('supplier_csv_reconcile_log')->latest('id')->first();
    expect((int) $log->matched_count)->toBe(1);
    expect((int) $log->recovered_count)->toBe(1);
});

it('empty CSV — status=ok, drift=0', function (): void {
    fakeReportFlow("Name;Tag;Phone\n");

    runCsvReconcile();

    $log = DB::table('supplier_csv_reconcile_log')->latest('id')->first();
    expect($log->status)->toBe('ok');
    expect((int) $log->total_csv_rows)->toBe(0);
});

it('overlap lock held — job skips, no log row', function (): void {
    $countBefore = DB::table('supplier_csv_reconcile_log')->count();

    $lock = Cache::store('redis')->lock('supplier:csv_reconcile', 600);
    $lock->get();

    try {
        runCsvReconcile();
    } finally {
        $lock->release();
    }

    expect(DB::table('supplier_csv_reconcile_log')->count())->toBe($countBefore);
});

it('SupplierTransientException — status=failed, error recorded, rethrown', function (): void {
    Http::fake(['crm.bp-gr.ru/*' => Http::response('Server Error', 500)]);

    expect(fn () => runCsvReconcile())->toThrow(SupplierTransientException::class);

    $log = DB::table('supplier_csv_reconcile_log')->latest('id')->first();
    expect($log->status)->toBe('failed');
    expect($log->error_message)->toContain('500');
});

it('unparseable CSV rows excluded from drift: 100 matched + 10 junk-project rows → status=ok, unparseable_count=10', function (): void {
    // 100 нормальных webhook-лидов.
    for ($i = 0; $i < 100; $i++) {
        SupplierLead::create([
            'supplier_project_id' => null,
            'platform' => 'B1',
            'phone' => '79993'.str_pad((string) $i, 6, '0', STR_PAD_LEFT),
            'vid' => 840000 + $i,
            'raw_payload' => ['project' => 'B1_a.com', 'phone' => '79993'.str_pad((string) $i, 6, '0', STR_PAD_LEFT)],
            'received_at' => now()->subHour(),
            'source' => 'webhook',
        ]);
    }

    // CSV: те же 100 (matched) + 10 строк с настоящим мусорным project (extractPlatform = null).
    // Phase 3 (2026-05-25): расширили DIRECT-распознавание — теперь цифровые callback-проекты
    // (79135551234) — валидный DIRECT, не junk. Реальный junk — это символы вне whitelist regex.
    $rows = [];
    for ($i = 0; $i < 100; $i++) {
        $rows[] = ['project' => 'B1_a.com', 'phone' => '79993'.str_pad((string) $i, 6, '0', STR_PAD_LEFT)];
    }
    $junkProjects = ['???', '!@#', '%%%', '$$$', '???!!!', '~~~', '***', '|||', '^^^', '&&&'];
    foreach ($junkProjects as $j => $junk) {
        $rows[] = ['project' => $junk, 'phone' => '7999500000'.$j];
    }
    fakeReportFlow(csvBody($rows));

    runCsvReconcile();

    $log = DB::table('supplier_csv_reconcile_log')->latest('id')->first();
    expect((int) $log->total_csv_rows)->toBe(110);
    expect((int) $log->matched_count)->toBe(100);
    expect((int) $log->recovered_count)->toBe(0);
    expect((int) $log->unparseable_count)->toBe(10);
    // Реального missing'а нет — только junk; drift должен быть 0, не 10/110.
    expect((float) $log->drift_ratio)->toBe(0.0);
    expect($log->status)->toBe('ok');

    Mail::assertNotSent(CsvDriftAlertMail::class); // scoped — TenantBusinessDriftAlertMail may fire on leaked snapshots
});

it('mixed: 95 matched + 5 junk + 3 real-missing → unparseable_count=5, recovered=3, drift по реальным', function (): void {
    for ($i = 0; $i < 95; $i++) {
        SupplierLead::create([
            'supplier_project_id' => null,
            'platform' => 'B1',
            'phone' => '79994'.str_pad((string) $i, 6, '0', STR_PAD_LEFT),
            'vid' => 850000 + $i,
            'raw_payload' => ['project' => 'B1_a.com', 'phone' => '79994'.str_pad((string) $i, 6, '0', STR_PAD_LEFT)],
            'received_at' => now()->subHour(),
            'source' => 'webhook',
        ]);
    }

    $rows = [];
    for ($i = 0; $i < 95; $i++) {
        $rows[] = ['project' => 'B1_a.com', 'phone' => '79994'.str_pad((string) $i, 6, '0', STR_PAD_LEFT)];
    }
    // Phase 3: реальный junk — символы вне whitelist (не \w/.-/cyrillic/digits/slash/parens/space/plus).
    $junkProjects = ['???', '!!!@@@', '%%%', '****', '???!!!'];
    foreach ($junkProjects as $j => $junk) {
        $rows[] = ['project' => $junk, 'phone' => '7999600000'.$j];
    }
    for ($k = 0; $k < 3; $k++) {
        $rows[] = ['project' => 'B1_a.com', 'phone' => '7999700000'.$k];
    }
    fakeReportFlow(csvBody($rows));

    runCsvReconcile();

    $log = DB::table('supplier_csv_reconcile_log')->latest('id')->first();
    expect((int) $log->total_csv_rows)->toBe(103);
    expect((int) $log->matched_count)->toBe(95);
    expect((int) $log->recovered_count)->toBe(3);
    expect((int) $log->unparseable_count)->toBe(5);
    // real_missing = (103 - 95) - 5 = 3; parseable_total = 103 - 5 = 98; drift = 3/98 ≈ 0.0306 < 5% → ok.
    expect((float) $log->drift_ratio)->toBeLessThan(0.05);
    expect((float) $log->drift_ratio)->toBeGreaterThan(0.0);
    expect($log->status)->toBe('ok');
});

// ---------------------------------------------------------------------------
// Stage 4 / Task 4.5 — R-05 (spec §4.4.4): business-drift second pass.
// After existing webhook-loss drift detection, CsvReconcileJob runs a second
// pass on project_routing_snapshots: per (snapshot_date, tenant_id) groups
// where (expected - delivered) / expected > 20% → TenantBusinessDriftAlertMail.
// This is orthogonal to webhook-loss drift (R-05.1) — same lead can be:
//   - delivered & webhook OK (no alerts)
//   - delivered & webhook miss (R-05.1 CsvDriftAlertMail)
//   - not delivered at all (R-05.2 TenantBusinessDriftAlertMail — this task)
// ---------------------------------------------------------------------------

function insertSnapshotForTenant(int $tenantId, string $date, int $expected, int $delivered): void
{
    $tenant = \App\Models\Tenant::find($tenantId) ?? \App\Models\Tenant::factory()->create();
    $project = \App\Models\Project::factory()
        ->for($tenant)
        ->asCallSignal('7977'.\Illuminate\Support\Str::random(7))
        ->create([
            'is_active' => true,
            'daily_limit_target' => max($expected, 1),
        ]);
    \Illuminate\Support\Facades\DB::connection('pgsql_supplier')
        ->table('project_routing_snapshots')
        ->insert([
            'snapshot_date' => $date,
            'project_id' => $project->id,
            'tenant_id' => $tenant->id,
            'daily_limit' => max($expected, 1),
            'delivery_days_mask' => 127,
            'regions' => '{}',
            'signal_type' => 'call',
            'signal_identifier' => $project->signal_identifier,
            'sms_senders' => null,
            'sms_keyword' => null,
            'expected_volume' => $expected,
            'delivered_count' => $delivered,
            'created_at' => now(),
        ]);
}

it('R-05 business-drift: tenant with shortfall > 20% → TenantBusinessDriftAlertMail sent', function (): void {
    $tenant = \App\Models\Tenant::factory()->create();
    // Yesterday's snapshot: expected 10, delivered 2 → shortfall 80% (>20% threshold).
    $yesterday = \Carbon\Carbon::yesterday('Europe/Moscow')->toDateString();
    insertSnapshotForTenant($tenant->id, $yesterday, 10, 2);

    // Empty CSV — primary drift pass is trivially OK; we exercise only the second pass.
    fakeReportFlow(csvBody([]));
    runCsvReconcile();

    Mail::assertSent(\App\Mail\TenantBusinessDriftAlertMail::class, function ($mail) use ($tenant) {
        return $mail->tenantId === $tenant->id
            && $mail->expected === 10
            && $mail->delivered === 2
            && $mail->shortfallRatio >= 0.79
            && $mail->shortfallRatio <= 0.81;
    });
});

it('R-05 business-drift: tenant with shortfall <= 20% → NO TenantBusinessDriftAlertMail', function (): void {
    $tenant = \App\Models\Tenant::factory()->create();
    // Yesterday's snapshot: expected 10, delivered 9 → shortfall 10% (<=20% threshold).
    $yesterday = \Carbon\Carbon::yesterday('Europe/Moscow')->toDateString();
    insertSnapshotForTenant($tenant->id, $yesterday, 10, 9);

    fakeReportFlow(csvBody([]));
    runCsvReconcile();

    // Scoped assertion: prior-run leaked snapshots may fire mails for other tenants;
    // this test only owns one tenant, so assert no mail was sent for IT.
    Mail::assertNotSent(\App\Mail\TenantBusinessDriftAlertMail::class, function ($mail) use ($tenant) {
        return $mail->tenantId === $tenant->id;
    });
});