chore(roles): add validation script for migration

script on Ed's sandbox, adapt values accordingly your environment
This commit is contained in:
Edouard Vanbelle
2026-06-17 23:26:17 +02:00
parent f168c4578f
commit ae219b81fc
2 changed files with 543 additions and 0 deletions
+215
View File
@@ -0,0 +1,215 @@
-- ════════════════════════════════════════════════════════════════════════════
-- audit-grants-bundle-shape.sql — Pre-D-Prep diagnostic
-- ════════════════════════════════════════════════════════════════════════════
-- Purpose: confirm the assumption that >99% of existing `storage.access_grants`
-- rows already cluster into the standard role bundles
-- (viewer / commenter / contributor / editor / owner). The answer determines
-- whether the access_grants → role_grants migration is fully mechanical (just
-- run the backfill) or whether per-row decisions are needed for some edge
-- cases.
--
-- READ-ONLY. Safe to run against any environment including production.
--
-- Usage:
-- psql "$DATABASE_URL" -f tools/audit-grants-bundle-shape.sql
--
-- Reference role bundles (mirror `Role::expand()` in
-- `src/application/dtos/grant_dto.rs`):
-- viewer = {read}
-- commenter = {read, comment} ← reserved variant
-- contributor = {read, create} ← new in D-Prep
-- editor = {read, comment, create, update}
-- owner = {read, comment, create, update, share, delete}
-- (post-D-Prep: + manage, when Group-as-Resource lands)
-- ════════════════════════════════════════════════════════════════════════════
\echo ''
\echo '─────────────────────────────────────────────────────────────────────────'
\echo ' 0. Total population'
\echo '─────────────────────────────────────────────────────────────────────────'
SELECT count(*) AS total_grant_rows,
count(DISTINCT (subject_type, subject_id, resource_type, resource_id))
AS distinct_clusters,
ROUND(
count(*)::numeric
/ NULLIF(count(DISTINCT (subject_type, subject_id, resource_type, resource_id)), 0),
2
) AS avg_rows_per_cluster
FROM storage.access_grants;
\echo ''
\echo '─────────────────────────────────────────────────────────────────────────'
\echo ' 1. Bundle distribution — which permission sets exist, how popular?'
\echo '─────────────────────────────────────────────────────────────────────────'
\echo ' Each row = a unique permission set; cluster_count = how many (subject,'
\echo ' resource) pairs have exactly that set.'
WITH cluster AS (
SELECT subject_type,
subject_id,
resource_type,
resource_id,
array_agg(permission ORDER BY permission) AS perms
FROM storage.access_grants
GROUP BY 1, 2, 3, 4
),
known_bundles AS (
SELECT ARRAY['read']::text[] AS perms, 'viewer' AS role
UNION ALL SELECT ARRAY['comment','read']::text[], 'commenter'
UNION ALL SELECT ARRAY['create','read']::text[], 'contributor'
UNION ALL SELECT ARRAY['comment','create','read','update']::text[], 'editor'
UNION ALL SELECT ARRAY['comment','create','delete','read','share','update']::text[], 'owner'
)
SELECT cluster.perms,
count(*) AS cluster_count,
ROUND(100.0 * count(*) / SUM(count(*)) OVER (), 2) AS pct,
COALESCE(known_bundles.role, '(non-bundle)') AS maps_to_role
FROM cluster
LEFT JOIN known_bundles ON known_bundles.perms = cluster.perms
GROUP BY cluster.perms, known_bundles.role
ORDER BY cluster_count DESC;
\echo ''
\echo '─────────────────────────────────────────────────────────────────────────'
\echo ' 2. Bundle-shaped vs not — the headline number'
\echo '─────────────────────────────────────────────────────────────────────────'
WITH cluster AS (
SELECT subject_type,
subject_id,
resource_type,
resource_id,
array_agg(permission ORDER BY permission) AS perms
FROM storage.access_grants
GROUP BY 1, 2, 3, 4
),
known_bundles AS (
SELECT ARRAY['read']::text[] AS perms
UNION ALL SELECT ARRAY['comment','read']::text[]
UNION ALL SELECT ARRAY['create','read']::text[]
UNION ALL SELECT ARRAY['comment','create','read','update']::text[]
UNION ALL SELECT ARRAY['comment','create','delete','read','share','update']::text[]
),
shape AS (
SELECT CASE WHEN cluster.perms = ANY(SELECT kb.perms FROM known_bundles kb)
THEN 'bundle-shaped'
ELSE 'NON-bundle (needs per-row decision)'
END AS shape
FROM cluster
)
SELECT shape,
count(*) AS clusters,
ROUND(100.0 * count(*) / SUM(count(*)) OVER (), 2) AS pct
FROM shape
GROUP BY shape
ORDER BY clusters DESC;
\echo ''
\echo '─────────────────────────────────────────────────────────────────────────'
\echo ' 3. Non-bundle clusters in detail (the <1% — investigate each)'
\echo '─────────────────────────────────────────────────────────────────────────'
\echo ' If this returns 0 rows, the migration is FULLY mechanical. Otherwise'
\echo ' eyeball each row and decide: closest role + audit log entry, or'
\echo ' refuse-to-migrate (rare).'
WITH cluster AS (
SELECT subject_type,
subject_id,
resource_type,
resource_id,
array_agg(permission ORDER BY permission) AS perms
FROM storage.access_grants
GROUP BY 1, 2, 3, 4
),
known_bundles AS (
SELECT ARRAY['read']::text[] AS perms
UNION ALL SELECT ARRAY['comment','read']::text[]
UNION ALL SELECT ARRAY['create','read']::text[]
UNION ALL SELECT ARRAY['comment','create','read','update']::text[]
UNION ALL SELECT ARRAY['comment','create','delete','read','share','update']::text[]
)
SELECT cluster.subject_type,
cluster.subject_id,
cluster.resource_type,
cluster.resource_id,
cluster.perms
FROM cluster
WHERE NOT (cluster.perms = ANY(SELECT kb.perms FROM known_bundles kb))
ORDER BY cluster.resource_type, cluster.resource_id
LIMIT 200;
\echo ''
\echo '─────────────────────────────────────────────────────────────────────────'
\echo ' 4. Sanity checks — invariants that should be true today'
\echo '─────────────────────────────────────────────────────────────────────────'
\echo ''
\echo ' 4a. Clusters with no Read permission (broken? if >0, investigate)'
WITH cluster AS (
SELECT subject_type, subject_id, resource_type, resource_id,
array_agg(permission ORDER BY permission) AS perms
FROM storage.access_grants
GROUP BY 1, 2, 3, 4
)
SELECT count(*) AS clusters_without_read
FROM cluster
WHERE NOT ('read' = ANY(perms));
\echo ''
\echo ' 4b. Subject-type distribution (sanity check on token / external counts)'
SELECT subject_type,
count(*) AS rows,
count(DISTINCT subject_id) AS distinct_subjects,
count(DISTINCT (resource_type, resource_id)) AS distinct_resources
FROM storage.access_grants
GROUP BY subject_type
ORDER BY subject_type;
\echo ''
\echo ' 4c. Resource-type distribution'
SELECT resource_type, count(*) AS rows
FROM storage.access_grants
GROUP BY resource_type
ORDER BY rows DESC;
\echo ''
\echo ' 4d. Permission distribution (total rows per permission value)'
SELECT permission, count(*) AS rows
FROM storage.access_grants
GROUP BY permission
ORDER BY rows DESC;
\echo ''
\echo '─────────────────────────────────────────────────────────────────────────'
\echo ' 5. Migration cost estimate'
\echo '─────────────────────────────────────────────────────────────────────────'
\echo ' role_grants will have ~ (distinct clusters) rows, replacing ~ (total)'
\echo ' rows in access_grants. The ratio is the per-row reduction factor.'
WITH cluster AS (
SELECT subject_type, subject_id, resource_type, resource_id
FROM storage.access_grants
GROUP BY 1, 2, 3, 4
)
SELECT (SELECT count(*) FROM storage.access_grants) AS access_grants_rows_today,
(SELECT count(*) FROM cluster) AS role_grants_rows_after,
ROUND(
(SELECT count(*) FROM storage.access_grants)::numeric
/ NULLIF((SELECT count(*) FROM cluster), 0),
2
) AS reduction_factor;
\echo ''
\echo '─────────────────────────────────────────────────────────────────────────'
\echo ' DONE — share section 2 (headline) and section 3 (non-bundle detail)'
\echo ' to make the D-Prep PR scope decision.'
\echo '─────────────────────────────────────────────────────────────────────────'
\echo ''
+328
View File
@@ -0,0 +1,328 @@
#!/usr/bin/env bash
# ════════════════════════════════════════════════════════════════════════════
# d-prep-real-db-smoke.sh — Validate D-Prep migration against sandbox data
# ════════════════════════════════════════════════════════════════════════════
# Reads from your sandbox DB (real data — but it's a sandbox, not prod), dumps
# it, restores into an isolated parallel DB, applies the D-Prep migration
# (`20260730000000_role_grants.sql`), and verifies the backfill against the
# pre-recorded audit numbers from `tools/audit-grants-bundle-shape.sql`.
#
# The sandbox DB itself is NEVER MODIFIED — everything happens in the parallel
# `oxicloud_dprep_smoke` DB which is dropped at the start of each run.
#
# Usage:
# tools/d-prep-real-db-smoke.sh # uses $DATABASE_URL
# tools/d-prep-real-db-smoke.sh --keep # leave smoke DB for poking after
# tools/d-prep-real-db-smoke.sh --help
#
# Requirements:
# - pg_dump / pg_restore / psql (PostgreSQL 14+ should be fine; sandbox version-matched)
# - DATABASE_URL pointing at the sandbox DB
#
# PATH gotcha (Mac brew): `brew install postgresql@18` is keg-only; if pg_dump
# isn't on PATH, run:
# export PATH="$(brew --prefix postgresql@18)/bin:$PATH"
#
# Expected audit numbers (from your audit run on 2026-06-17):
# - 73 access_grants rows clustering into 38 (subject, resource) pairs
# - 29 viewer / 5 editor / 4 owner
# These are encoded as assertions below. If your sandbox data has shifted
# since the audit, update EXPECTED_* variables OR re-run the audit script
# first.
#
# Memory cross-refs:
# - bug_pg_dump_folders_circular_fk.md — circular FK on `folders` forces
# `pg_restore --disable-triggers`
# - project_drive_sequence_a.md — D-Prep scope + audit data
# ════════════════════════════════════════════════════════════════════════════
set -euo pipefail
# ── Config ──────────────────────────────────────────────────────────────────
SMOKE_DB_NAME="oxicloud_dprep_smoke"
DUMP_FILE="${TMPDIR:-/tmp}/oxicloud-sandbox-${SMOKE_DB_NAME}.dump"
MIGRATION_FILE="migrations/20260730000000_role_grants.sql"
# Expected values from the audit (tools/audit-grants-bundle-shape.sql run
# on 2026-06-17). Bump these if you re-run the audit and see different
# numbers — they are intentionally HARDCODED so a silent drift gets caught.
EXPECTED_DISTINCT_CLUSTERS=38
EXPECTED_VIEWER=29
EXPECTED_EDITOR=5
EXPECTED_OWNER=4
KEEP_DB=0
# ── Arg parsing ─────────────────────────────────────────────────────────────
usage() {
sed -n '2,/^$/p' "$0" | sed 's/^# \{0,1\}//'
exit "${1:-0}"
}
for arg in "$@"; do
case "$arg" in
--keep|--keep-db) KEEP_DB=1 ;;
-h|--help) usage 0 ;;
*) echo "Unknown arg: $arg" >&2 ; usage 2 ;;
esac
done
# ── Pre-flight ──────────────────────────────────────────────────────────────
if [[ -z "${DATABASE_URL:-}" ]]; then
echo "ERROR: \$DATABASE_URL must be set and point at the sandbox DB." >&2
exit 2
fi
for bin in pg_dump pg_restore psql; do
if ! command -v "$bin" >/dev/null 2>&1; then
echo "ERROR: '$bin' not found on PATH." >&2
echo "Hint: brew-installed postgresql is keg-only. Run:" >&2
echo " export PATH=\"\$(brew --prefix postgresql@18)/bin:\$PATH\"" >&2
exit 2
fi
done
if [[ ! -f "$MIGRATION_FILE" ]]; then
echo "ERROR: migration file not found: $MIGRATION_FILE" >&2
echo "Run this script from the repo root." >&2
exit 2
fi
# Derive connection URLs for the maintenance DB (where we'll issue
# DROP/CREATE DATABASE) and the smoke DB itself, by splicing
# $SMOKE_DB_NAME into $DATABASE_URL. Avoids relying on libpq's
# default local Unix socket — `dropdb`/`createdb`/`psql` without an
# explicit -d won't read $DATABASE_URL and try /tmp/.s.PGSQL.5432
# (which fails on Mac brew where the server runs on a non-default
# socket / port).
URL_NO_QUERY="${DATABASE_URL%%\?*}"
URL_QUERY="${DATABASE_URL:${#URL_NO_QUERY}}" # "" or "?…"
SOURCE_DB_NAME="${URL_NO_QUERY##*/}"
URL_BASE="${URL_NO_QUERY%/"$SOURCE_DB_NAME"}"
MAINTENANCE_URL="${URL_BASE}/postgres${URL_QUERY}"
SMOKE_URL="${URL_BASE}/${SMOKE_DB_NAME}${URL_QUERY}"
if [[ "$SOURCE_DB_NAME" == "$SMOKE_DB_NAME" ]]; then
echo "ERROR: DATABASE_URL appears to point at '$SMOKE_DB_NAME' — refusing" >&2
echo "to dump-and-restore on top of itself. Set DATABASE_URL to the sandbox." >&2
exit 2
fi
# ── Helpers ─────────────────────────────────────────────────────────────────
log() { echo "[smoke] $*"; }
fail() { echo "[smoke] FAIL: $*" >&2 ; exit 1; }
pass() { echo "[smoke] PASS: $*"; }
# Run a query against the smoke DB and capture a single scalar.
scalar() {
psql -tAX -d "$SMOKE_URL" -c "$1"
}
# Run a query and check the result equals an expected scalar.
expect_scalar() {
local query="$1" expected="$2" label="$3"
local actual
actual=$(scalar "$query")
if [[ "$actual" == "$expected" ]]; then
pass "$label: $actual"
else
fail "$label: expected $expected, got '$actual'"
fi
}
# ── 1. Snapshot the sandbox ─────────────────────────────────────────────────
log "Dumping sandbox DB → $DUMP_FILE"
log "(custom format, so pg_restore --disable-triggers can side-step the"
log " circular FK on storage.folders.parent_id — see bug memory.)"
pg_dump "$DATABASE_URL" --format=custom --no-owner --no-privileges \
--file="$DUMP_FILE"
log "Dumped $(du -h "$DUMP_FILE" | awk '{print $1}')"
# ── 2. Recreate the smoke DB ────────────────────────────────────────────────
log "Dropping smoke DB '$SMOKE_DB_NAME' if it exists"
psql -d "$MAINTENANCE_URL" -c "DROP DATABASE IF EXISTS \"$SMOKE_DB_NAME\""
log "Creating fresh smoke DB '$SMOKE_DB_NAME'"
psql -d "$MAINTENANCE_URL" -c "CREATE DATABASE \"$SMOKE_DB_NAME\""
# ── 3. Restore sandbox into smoke DB ────────────────────────────────────────
log "Restoring sandbox dump into smoke DB"
# --disable-triggers handles the storage.folders parent_id circular FK without
# wrapping every COPY in SET CONSTRAINTS ALL DEFERRED.
# --no-owner --no-privileges already on dump side; --single-transaction makes
# the restore atomic so a mid-flight failure leaves no half-state.
pg_restore --dbname="$SMOKE_URL" --disable-triggers \
--single-transaction --no-owner --no-privileges \
"$DUMP_FILE"
# ── 4. Wipe any prior role_grants state from the smoke DB ──────────────────
# The sandbox may already have role_grants if the server has been booted
# with the D-Prep migration applied (auto-migrate on startup). For the
# smoke we want to exercise the migration FRESHLY — same as a brand-new
# install — so drop both the migration's tables and let it recreate them
# from scratch against the access_grants snapshot.
log "Wiping any prior role_grants state from smoke DB (so we test the migration freshly)"
psql -d "$SMOKE_URL" --set ON_ERROR_STOP=1 -c "
DROP TABLE IF EXISTS storage.role_grants_migration_log CASCADE;
DROP TABLE IF EXISTS storage.role_grants CASCADE;
"
# ── 5. Pre-migration sanity ────────────────────────────────────────────────
log "Pre-migration sanity checks"
expect_scalar "SELECT count(*) FROM storage.access_grants" \
"73" "access_grants row count matches audit"
if [[ $(scalar "SELECT to_regclass('storage.role_grants') IS NULL") != "t" ]]; then
fail "storage.role_grants survived the drop — something is wrong."
fi
pass "storage.role_grants does not exist (clean slate)"
# ── 5. Apply the D-Prep migration ───────────────────────────────────────────
log "Applying D-Prep migration: $MIGRATION_FILE"
# Wrap in a transaction so a constraint failure rolls back cleanly; the
# migration itself has BEGIN/COMMIT semantics via -1 to psql.
psql -d "$SMOKE_URL" --set ON_ERROR_STOP=1 -1 -f "$MIGRATION_FILE"
log "Migration applied"
# ── 6. Post-migration assertions ────────────────────────────────────────────
log "Post-migration verification"
# Row count: should match `distinct_clusters` from the audit
expect_scalar "SELECT count(*) FROM storage.role_grants" \
"$EXPECTED_DISTINCT_CLUSTERS" "role_grants row count"
# Role distribution
expect_scalar "SELECT count(*) FROM storage.role_grants WHERE role = 'viewer'" \
"$EXPECTED_VIEWER" "viewer count"
expect_scalar "SELECT count(*) FROM storage.role_grants WHERE role = 'editor'" \
"$EXPECTED_EDITOR" "editor count"
expect_scalar "SELECT count(*) FROM storage.role_grants WHERE role = 'owner'" \
"$EXPECTED_OWNER" "owner count"
# Zero NULL roles, zero non-bundle roles (the CHECK constraint should
# already enforce this, but proving it here too)
expect_scalar "SELECT count(*) FROM storage.role_grants WHERE role IS NULL" \
"0" "no NULL roles"
expect_scalar "SELECT count(*) FROM storage.role_grants WHERE role NOT IN ('viewer','commenter','contributor','editor','owner')" \
"0" "no unknown roles"
# access_grants is untouched
expect_scalar "SELECT count(*) FROM storage.access_grants" \
"73" "access_grants row count unchanged (dual-write safety net intact)"
# ── 7. Equivalence check (strongest assertion) ──────────────────────────────
# For every role_grants row, the corresponding (subject, resource) cluster
# in access_grants must have exactly the role's bundle as its permission
# set. If any row's bundle doesn't match what `Role::expand()` says, the
# backfill mis-mapped and the equivalence count goes non-zero.
log "Bundle equivalence check: role_grants ↔ access_grants"
EQUIVALENCE_MISMATCHES=$(scalar "
WITH expected AS (
SELECT 'viewer'::text AS role, ARRAY['read']::text[] AS perms
UNION ALL SELECT 'commenter', ARRAY['comment','read']::text[]
UNION ALL SELECT 'contributor', ARRAY['create','read']::text[]
UNION ALL SELECT 'editor', ARRAY['comment','create','read','update']::text[]
UNION ALL SELECT 'owner', ARRAY['comment','create','delete','read','share','update']::text[]
),
actual AS (
SELECT subject_type, subject_id, resource_type, resource_id,
array_agg(permission ORDER BY permission) AS perms
FROM storage.access_grants
GROUP BY 1, 2, 3, 4
)
SELECT count(*)
FROM storage.role_grants rg
JOIN actual a USING (subject_type, subject_id, resource_type, resource_id)
JOIN expected e ON e.role = rg.role
WHERE a.perms <> e.perms
")
if [[ "$EQUIVALENCE_MISMATCHES" == "0" ]]; then
pass "every role_grants row's bundle matches access_grants exactly"
else
log ""
log "MISMATCH DETAIL (first 10):"
psql -d "$SMOKE_URL" -c "
WITH expected AS (
SELECT 'viewer'::text AS role, ARRAY['read']::text[] AS perms
UNION ALL SELECT 'commenter', ARRAY['comment','read']::text[]
UNION ALL SELECT 'contributor', ARRAY['create','read']::text[]
UNION ALL SELECT 'editor', ARRAY['comment','create','read','update']::text[]
UNION ALL SELECT 'owner', ARRAY['comment','create','delete','read','share','update']::text[]
),
actual AS (
SELECT subject_type, subject_id, resource_type, resource_id,
array_agg(permission ORDER BY permission) AS perms
FROM storage.access_grants
GROUP BY 1, 2, 3, 4
)
SELECT rg.subject_type, rg.subject_id, rg.resource_type, rg.resource_id,
rg.role,
a.perms AS access_grants_perms,
e.perms AS expected_perms
FROM storage.role_grants rg
JOIN actual a USING (subject_type, subject_id, resource_type, resource_id)
JOIN expected e ON e.role = rg.role
WHERE a.perms <> e.perms
LIMIT 10
"
fail "$EQUIVALENCE_MISMATCHES role_grants rows have a bundle that diverges from their access_grants cluster"
fi
# ── 8. Migration audit log shape ────────────────────────────────────────────
# `role_grants_migration_log` is the one-shot table created by the migration
# to record any demotions. With 100%-bundle-shaped data (the audit says so),
# it should be EMPTY — nothing was demoted.
if [[ $(scalar "SELECT to_regclass('storage.role_grants_migration_log') IS NOT NULL") == "t" ]]; then
expect_scalar "SELECT count(*) FROM storage.role_grants_migration_log" \
"0" "migration audit log empty (no demotions, as expected for 100% bundle-shaped data)"
fi
# ── 9. Cleanup ──────────────────────────────────────────────────────────────
log ""
log "─────────────────────────────────────────────────────────"
log " ALL ASSERTIONS PASSED"
log "─────────────────────────────────────────────────────────"
log ""
if [[ "$KEEP_DB" == "1" ]]; then
log "Leaving smoke DB '$SMOKE_DB_NAME' for inspection."
log "Poke at it with:"
log " psql \"$SMOKE_URL\""
log ""
log "Drop when done:"
log " psql -d \"$MAINTENANCE_URL\" -c 'DROP DATABASE \"$SMOKE_DB_NAME\"'"
else
log "Dropping smoke DB '$SMOKE_DB_NAME'"
psql -d "$MAINTENANCE_URL" -c "DROP DATABASE \"$SMOKE_DB_NAME\""
fi
log "Dump file kept at $DUMP_FILE (delete with: rm '$DUMP_FILE')"