internal/adapters/store/uploaded_transcripts_isolation_test.go

@@ -0,0 +1,196 @@
+package store_test
+
+import (
+	"context"
+	"sort"
+	"testing"
+
+	"github.com/jackc/pgx/v5/pgxpool"
+	"github.com/stretchr/testify/require"
+)
+
+// Isolation proof for ADR-033: an uploaded transcript is PRIVATE content owned by
+// one user, so it lives in its own RLS-scoped table — never in the shared,
+// non-RLS `transcripts` (ADR-021). These tests drive the database directly (raw
+// SQL as the non-superuser `app` role) so they observe row-level security itself,
+// not any application-layer WHERE clause. The superuser pool is used only to seed
+// and to read pg_catalog; it bypasses RLS and so must never be the pool whose
+// answers the assertions rest on.
+
+// seedUploadedTranscript inserts one finished upload for userID as the superuser
+// (RLS bypassed so both users' rows land regardless of any GUC) and returns its id.
+// The text is synthetic — this repo is public, and a real transcript must never
+// appear in it (#33).
+func seedUploadedTranscript(t *testing.T, super *pgxpool.Pool, userID, text string) string {
+	t.Helper()
+	ctx := context.Background()
+	_, err := super.Exec(ctx, `INSERT INTO users (id) VALUES ($1) ON CONFLICT DO NOTHING`, userID)
+	require.NoError(t, err)
+	var id string
+	require.NoError(t, super.QueryRow(ctx,
+		`INSERT INTO uploaded_transcripts (user_id, title, status, content)
+		 VALUES ($1, 'synthetic fixture', 'done', $2) RETURNING id`,
+		userID, text).Scan(&id))
+	return id
+}
+
+func TestUploadedTranscriptsRLS_ScopedReadsSeeOnlyOwnRows(t *testing.T) {
+	newStore(t)
+	super := rawPool(t)
+	resetDB(t, super)
+	seedUploadedTranscript(t, super, userA, "text owned by A")
+	seedUploadedTranscript(t, super, userB, "text owned by B")
+	app := appPool(t, super)
+
+	require.Equal(t, 0, scopedCount(t, app, "", "uploaded_transcripts"),
+		"no tapir.current_user_id must be deny-all: this proves RLS is live, not bypassed")
+	require.Equal(t, 1, scopedCount(t, app, userA, "uploaded_transcripts"),
+		"user A must see exactly its own upload")
+	require.Equal(t, 1, scopedCount(t, app, userB, "uploaded_transcripts"),
+		"user B must see exactly its own upload")
+
+	// Count alone cannot distinguish "A's row" from "B's row" — read the content.
+	var got string
+	ctx := context.Background()
+	tx, err := app.Begin(ctx)
+	require.NoError(t, err)
+	defer tx.Rollback(ctx) //nolint:errcheck
+	_, err = tx.Exec(ctx, `SELECT set_config('tapir.current_user_id', $1, true)`, userA)
+	require.NoError(t, err)
+	require.NoError(t, tx.QueryRow(ctx, `SELECT content FROM uploaded_transcripts`).Scan(&got))
+	require.Equal(t, "text owned by A", got, "A's scoped read must return A's text, never B's")
+}
+
+func TestUploadedTranscriptsRLS_CrossUserWritesAffectZeroRows(t *testing.T) {
+	newStore(t)
+	super := rawPool(t)
+	resetDB(t, super)
+	seedUploadedTranscript(t, super, userA, "text owned by A")
+	bID := seedUploadedTranscript(t, super, userB, "text owned by B")
+	app := appPool(t, super)
+
+	require.Equal(t, int64(0), scopedRowsAffected(t, app, userA,
+		`UPDATE uploaded_transcripts SET content = 'hacked' WHERE id = $1`, bID),
+		"user A scoped UPDATE must touch zero of B's uploads")
+	require.Equal(t, int64(0), scopedRowsAffected(t, app, userA,
+		`DELETE FROM uploaded_transcripts WHERE id = $1`, bID),
+		"user A scoped DELETE must touch zero of B's uploads")
+
+	var content string
+	require.NoError(t, super.QueryRow(context.Background(),
+		`SELECT content FROM uploaded_transcripts WHERE id = $1`, bID).Scan(&content))
+	require.Equal(t, "text owned by B", content, "B's upload must survive A's writes unchanged")
+}
+
+func TestUploadedTranscriptsRLS_InsertForAnotherUserIsRejected(t *testing.T) {
+	newStore(t)
+	super := rawPool(t)
+	resetDB(t, super)
+	seedUploadedTranscript(t, super, userA, "text owned by A")
+	_, err := super.Exec(context.Background(), `INSERT INTO users (id) VALUES ($1)`, userB)
+	require.NoError(t, err)
+	app := appPool(t, super)
+
+	ctx := context.Background()
+	tx, err := app.Begin(ctx)
+	require.NoError(t, err)
+	defer tx.Rollback(ctx) //nolint:errcheck
+	_, err = tx.Exec(ctx, `SELECT set_config('tapir.current_user_id', $1, true)`, userA)
+	require.NoError(t, err)
+
+	// Scoped as A, plant a row that claims to belong to B. The policy's WITH CHECK
+	// (defaulting to USING under FOR ALL) must refuse it.
+	_, err = tx.Exec(ctx,
+		`INSERT INTO uploaded_transcripts (user_id, title, status, content)
+		 VALUES ($1, 'planted', 'done', 'planted')`, userB)
+	require.Error(t, err, "a row scoped as A must not be insertable on behalf of B")
+	require.Contains(t, err.Error(), "row-level security")
+}
+
+func TestUploadedTranscripts_RowSecurityIsEnabledForcedAndKeyedByUser(t *testing.T) {
+	newStore(t)
+	super := rawPool(t)
+	ctx := context.Background()
+
+	var enabled, forced bool
+	require.NoError(t, super.QueryRow(ctx,
+		`SELECT relrowsecurity, relforcerowsecurity FROM pg_class
+		  WHERE oid = 'public.uploaded_transcripts'::regclass`).Scan(&enabled, &forced))
+	require.True(t, enabled, "uploaded_transcripts must have row-level security enabled")
+	require.True(t, forced,
+		"FORCE is what binds the table-owner role tapir; without it the policy is dead in production")
+
+	var userIDNotNull bool
+	require.NoError(t, super.QueryRow(ctx,
+		`SELECT is_nullable = 'NO' FROM information_schema.columns
+		  WHERE table_name = 'uploaded_transcripts' AND column_name = 'user_id'`).Scan(&userIDNotNull))
+	require.True(t, userIDNotNull, "an upload with no owner would match no policy and be unreachable")
+}
+
+func TestUploadedTranscripts_DeleteUserRemovesTheirUploads(t *testing.T) {
+	s := newStore(t)
+	super := rawPool(t)
+	resetDB(t, super)
+	seedUploadedTranscript(t, super, userA, "text owned by A")
+	bID := seedUploadedTranscript(t, super, userB, "text owned by B")
+
+	require.NoError(t, s.DeleteUser(context.Background(), userA))
+
+	var aRows, bRows int
+	ctx := context.Background()
+	require.NoError(t, super.QueryRow(ctx,
+		`SELECT count(*) FROM uploaded_transcripts WHERE user_id = $1`, userA).Scan(&aRows))
+	require.NoError(t, super.QueryRow(ctx,
+		`SELECT count(*) FROM uploaded_transcripts WHERE id = $1`, bID).Scan(&bRows))
+	require.Equal(t, 0, aRows, "deleting a user must remove their private transcripts (ON DELETE CASCADE)")
+	require.Equal(t, 1, bRows, "deleting A must not touch B's transcripts")
+}
+
+// rowSecurityOffTables are the public-schema tables that deliberately have row
+// security OFF. The list is exact on purpose: a NEW table added without RLS must
+// fail this test and force a decision, instead of passing CI by omission — the
+// failure mode ADR-033 names, where a naive reuse "leaks private content across
+// tenants and passes CI green".
+//
+//   - transcripts: shared public caption content, the single exception for CONTENT
+//     (ADR-021). It is the one that must never gain a private row.
+//   - user_identities: the Dex-subject -> user_id map, read at login before any
+//     user is known (migration 004). Holds no user content.
+//   - invitations: exists before the user does, so there is no user to scope by;
+//     the single-use token is the capability (migration 009).
+//   - schema_migrations: golang-migrate bookkeeping.
+//
+// #33 describes `transcripts` as "the only non-RLS table". That is true of content
+// and false of tables; this test asserts the real set.
+var rowSecurityOffTables = []string{
+	"invitations",
+	"schema_migrations",
+	"transcripts",
+	"user_identities",
+}
+
+func TestRowSecurityOffTablesAreExactlyTheKnownSet(t *testing.T) {
+	newStore(t)
+	super := rawPool(t)
+
+	rows, err := super.Query(context.Background(),
+		`SELECT c.relname FROM pg_class c
+		   JOIN pg_namespace n ON n.oid = c.relnamespace
+		  WHERE n.nspname = 'public' AND c.relkind IN ('r', 'p') AND NOT c.relrowsecurity
+		  ORDER BY c.relname`)
+	require.NoError(t, err)
+	defer rows.Close()
+	var got []string
+	for rows.Next() {
+		var name string
+		require.NoError(t, rows.Scan(&name))
+		got = append(got, name)
+	}
+	require.NoError(t, rows.Err())
+
+	want := append([]string{}, rowSecurityOffTables...)
+	sort.Strings(want)
+	require.Equal(t, want, got,
+		"every public table must have row security ON unless it is in rowSecurityOffTables; "+
+			"adding a table here is a decision that needs an ADR")
+}