member-console/internal/db/partitions_test.go

package db_test

// DB-backed idempotency test for EnsureWebhookEventPartitions
// (webhook-partition-maintenance, design.md D3/D4). Runs against
// TEST_DATABASE_URL under the same member_console role the running app and
// its boot pass use (D4: per-schema roles are in force, and this proves the
// role can CREATE in schema core rather than assuming it).

import (
	"context"
	"database/sql"
	"fmt"
	"os"
	"strings"
	"testing"
	"time"

	_ "github.com/jackc/pgx/v5/stdlib"

	"git.coopcloud.tech/wiki-cafe/member-console/internal/db"
)

// newPartitionsTestDB opens the test DB and runs core's migrations —
// core.webhook_events and its baseline partitions (0..2 months ahead) live
// entirely in the core schema, so db.BaseSources() is sufficient (mirrors
// internal/systemtenant/systemtenant_test.go's newTestDB).
func newPartitionsTestDB(t *testing.T) *sql.DB {
	t.Helper()
	dsn := os.Getenv("TEST_DATABASE_URL")
	if dsn == "" {
		t.Skip("TEST_DATABASE_URL not set, skipping integration test")
	}
	database, err := sql.Open("pgx", dsn)
	if err != nil {
		t.Fatalf("open db: %v", err)
	}
	t.Cleanup(func() { database.Close() })

	if err := db.RunMigrations(database, db.BaseSources()); err != nil {
		t.Fatalf("migrations: %v", err)
	}
	return database
}

// partitionTableName mirrors EnsureWebhookEventPartitions' and the baseline
// migration's naming exactly (core.webhook_events_YYYY_MM).
func partitionTableName(monthStart time.Time) string {
	return fmt.Sprintf("core.webhook_events_%04d_%02d", monthStart.Year(), int(monthStart.Month()))
}

// insertWebhookEvent inserts a minimal row timestamped at receivedAt,
// returning whatever error the partitioned table's routing produces (nil on
// success).
func insertWebhookEvent(ctx context.Context, database *sql.DB, providerEventID string, receivedAt time.Time) error {
	_, err := database.ExecContext(ctx, `
		INSERT INTO core.webhook_events (provider, provider_event_id, event_type, received_at)
		VALUES ('test-provider', $1, 'test.event', $2)`,
		providerEventID, receivedAt)
	return err
}

// tableExists reports whether the given core.<name> table exists.
func tableExists(t *testing.T, ctx context.Context, database *sql.DB, name string) bool {
	t.Helper()
	var exists bool
	err := database.QueryRowContext(ctx, `
		SELECT EXISTS (
			SELECT 1 FROM information_schema.tables
			WHERE table_schema = 'core' AND table_name = $1
		)`, name).Scan(&exists)
	if err != nil {
		t.Fatalf("check table existence for %s: %v", name, err)
	}
	return exists
}

// TestEnsureWebhookEventPartitions_ClosesTheGapAndIsIdempotent proves the
// bug (an insert into an unpartitioned-for month fails), that Ensure closes
// it, and that a second Ensure run is a no-op — the three scenarios in
// openspec/changes/purchase-path-blockers/specs/webhook-partition-maintenance/spec.md.
func TestEnsureWebhookEventPartitions_ClosesTheGapAndIsIdempotent(t *testing.T) {
	database := newPartitionsTestDB(t)
	ctx := context.Background()

	// A synthetic "now" far outside any real calendar month a concurrently
	// running test suite, or a prior un-reset run of this same test, could
	// have already ensured partitions for — the shared TEST_DATABASE_URL
	// database is reset between `make test` runs but not between bare
	// `go test` reruns, and this test must be able to prove "fails before,
	// succeeds after" regardless of that history.
	now := time.Date(2119, time.June, 15, 12, 0, 0, 0, time.UTC)
	monthStart := time.Date(now.Year(), now.Month(), 1, 0, 0, 0, 0, time.UTC)

	monthsAhead := db.DefaultWebhookPartitionMonthsAhead // 3
	targetMonth := monthStart.AddDate(0, monthsAhead, 0)
	targetPartition := partitionTableName(targetMonth)
	// Postgres table name only, without the "core." schema qualifier, for
	// information_schema lookups.
	targetPartitionUnqualified := strings.TrimPrefix(targetPartition, "core.")

	// Guarantee a clean slate for the "before" assertion: drop the target
	// partition (and, defensively, the whole synthetic month range) if a
	// previous unreset run left it behind.
	dropSyntheticPartitions := func() {
		for i := 0; i <= monthsAhead; i++ {
			name := partitionTableName(monthStart.AddDate(0, i, 0))
			if _, err := database.ExecContext(ctx, "DROP TABLE IF EXISTS "+name); err != nil {
				t.Fatalf("drop synthetic partition %s: %v", name, err)
			}
		}
	}
	dropSyntheticPartitions()
	t.Cleanup(dropSyntheticPartitions)

	// --- "Missing future partitions" scenario, negative half: before Ensure
	// runs, the target month (now + monthsAhead) has no partition, so the
	// insert fails with Postgres' partition-routing error. This is the bug
	// this change fixes: nothing but the baseline migration's initial
	// current+2 loop had ever created partitions.
	if err := insertWebhookEvent(ctx, database, "before-ensure", targetMonth.Add(time.Hour)); err == nil {
		t.Fatalf("insert into %s succeeded before Ensure ran; the partition gap this change fixes was not reproduced", targetPartition)
	} else if !strings.Contains(strings.ToLower(err.Error()), "partition") {
		t.Fatalf("insert into %s failed with an unexpected error (want a partition-routing error): %v", targetPartition, err)
	}
	if tableExists(t, ctx, database, targetPartitionUnqualified) {
		t.Fatalf("partition %s already exists before Ensure ran", targetPartition)
	}

	// --- Run Ensure: creates the current synthetic month through +monthsAhead.
	if err := db.EnsureWebhookEventPartitions(ctx, database, now, monthsAhead); err != nil {
		t.Fatalf("EnsureWebhookEventPartitions (first run): %v", err)
	}

	for i := 0; i <= monthsAhead; i++ {
		name := partitionTableName(monthStart.AddDate(0, i, 0))
		unqualified := strings.TrimPrefix(name, "core.")
		if !tableExists(t, ctx, database, unqualified) {
			t.Errorf("expected partition %s to exist after Ensure, it does not", name)
		}
	}

	// --- "Missing future partitions" scenario, positive half: the insert
	// that failed above now succeeds, in the correct partition.
	if err := insertWebhookEvent(ctx, database, "after-ensure", targetMonth.Add(time.Hour)); err != nil {
		t.Fatalf("insert into %s failed after Ensure ran: %v", targetPartition, err)
	}
	var rowCount int
	if err := database.QueryRowContext(ctx, "SELECT count(*) FROM "+targetPartition+" WHERE provider_event_id = 'after-ensure'").
		Scan(&rowCount); err != nil {
		t.Fatalf("count rows landed in %s: %v", targetPartition, err)
	}
	if rowCount != 1 {
		t.Errorf("row landed in %s = %d, want 1 (the row must be routed to the correct monthly partition)", targetPartition, rowCount)
	}

	// --- "Ensure is idempotent" scenario: a second run against the same
	// `now` succeeds and creates nothing new.
	var tableCountBefore int
	if err := database.QueryRowContext(ctx, `
		SELECT count(*) FROM information_schema.tables
		WHERE table_schema = 'core' AND table_name LIKE 'webhook_events_%'`).Scan(&tableCountBefore); err != nil {
		t.Fatalf("count webhook_events partitions before second Ensure: %v", err)
	}

	if err := db.EnsureWebhookEventPartitions(ctx, database, now, monthsAhead); err != nil {
		t.Fatalf("EnsureWebhookEventPartitions (second run): %v", err)
	}

	var tableCountAfter int
	if err := database.QueryRowContext(ctx, `
		SELECT count(*) FROM information_schema.tables
		WHERE table_schema = 'core' AND table_name LIKE 'webhook_events_%'`).Scan(&tableCountAfter); err != nil {
		t.Fatalf("count webhook_events partitions after second Ensure: %v", err)
	}
	if tableCountAfter != tableCountBefore {
		t.Errorf("second Ensure run changed the partition count: %d -> %d, want no-op", tableCountBefore, tableCountAfter)
	}

	// The insert-succeeds behavior still holds after the no-op second run.
	if err := insertWebhookEvent(ctx, database, "after-second-ensure", targetMonth.Add(2*time.Hour)); err != nil {
		t.Fatalf("insert into %s failed after second Ensure run: %v", targetPartition, err)
	}
}