fix(nexus-db): UTF8-Encoding zur Installationszeit erzwingen (#8) #9

Merged
l.kirchner merged 2 commits from fix/nexus-db-utf8-encoding into main 2026-06-13 14:38:58 +02:00
3 changed files with 68 additions and 5 deletions
Showing only changes of commit bd4293f53e - Show all commits
+2
View File
@@ -41,6 +41,8 @@ Two files per app, both sourcing the shared libs via `curl`:
- **`ct/<app>.sh`** runs on the PVE host: prompts → unprivileged LXC → pushes a config env file into the container → bootstraps the installer. Apps that need Docker (authentik, runner) enable `nesting+keyctl` automatically. The standard prompts include an **SSH root login choice** (`SSH_ROOT_LOGIN`, default yes for homelab convenience; `no` keeps the Debian key-only default) — applied inside the container as an sshd drop-in by `configure_ssh_root_login`.
- **`install/<app>-install.sh`** runs inside the LXC: packages, unprivileged app user, secrets generated on-host (never printed), systemd units, a `/root/<app>.credentials` notes file — then shreds the bootstrap env. Idempotent where it matters: re-runs skip what exists. `setup_base_apt` also fixes the bare-template **locale situation**: `C.UTF-8` is exported up front (glibc built-in, covers the first apt run without perl warnings), then `en_US.UTF-8` is generated and set as the system default.
**DB installers** carry one extra rule: a PostgreSQL cluster/database freezes its encoding at initdb / `CREATE DATABASE` time and it can never be changed afterwards. A C (non-UTF-8) locale yields a `SQL_ASCII` cluster — psycopg3 then hands text back as bytes and SQLAlchemy crashes. So the pattern (helpers `ensure_utf8_locale_active` + `assert_db_encoding_utf8` in `lib/install.func`) is: make a UTF-8 locale **active** before the server package runs initdb, create the database **explicitly** with `TEMPLATE template0 ENCODING 'UTF8' LC_COLLATE/LC_CTYPE 'en_US.UTF-8'` (never inherit the cluster default), and **verify** `pg_encoding_to_char` returns `UTF8` before finishing — a wrong encoding aborts the install (it's DB damage, see wiki → Lessons). Maintenance examples use `su - postgres -c …`, not `sudo` — these minimal LXCs have no sudo.
Shared libs: [`lib/build.func`](lib/build.func) (host-side: prompts, LXC create, bootstrap) and [`lib/install.func`](lib/install.func) (in-container: apt, users, systemd, http-wait).
## Security conventions
+22 -5
View File
@@ -47,6 +47,12 @@ else
msg_warn "PGDG repo already present, skipping"
fi
# The server package runs initdb for the `main` cluster on install — its
# encoding is frozen there. Make a UTF-8 locale active for THIS process first
# so the cluster is never created as SQL_ASCII (issue #8: a pre-fix LXC was
# provisioned under LANG=C and ended up SQL_ASCII).
ensure_utf8_locale_active en_US.UTF-8
msg_info "Installing PostgreSQL $PG_MAJOR + pgvector..."
apt-get install -y -qq "postgresql-$PG_MAJOR" "postgresql-$PG_MAJOR-pgvector" >/dev/null
msg_ok "PostgreSQL $(psql --version | awk '{print $3}') installed"
@@ -114,14 +120,22 @@ else
fi
if [[ "$(run_psql -c "SELECT 1 FROM pg_database WHERE datname='$DB_NAME'")" != "1" ]]; then
run_psql -c "CREATE DATABASE $DB_NAME OWNER $DB_USER"
# Explicit encoding/collation from template0 — never inherit the cluster
# default, which may be SQL_ASCII if initdb ran under a broken locale
# (issue #8). template0 is required to override LC_COLLATE/LC_CTYPE.
run_psql -c "CREATE DATABASE $DB_NAME OWNER $DB_USER ENCODING 'UTF8' LC_COLLATE 'en_US.UTF-8' LC_CTYPE 'en_US.UTF-8' TEMPLATE template0"
# Only the owner may connect — no PUBLIC access.
run_psql -c "REVOKE CONNECT ON DATABASE $DB_NAME FROM PUBLIC"
msg_ok "Database $DB_NAME created (owner $DB_USER, PUBLIC revoked)"
msg_ok "Database $DB_NAME created (UTF8, owner $DB_USER, PUBLIC revoked)"
else
msg_warn "Database $DB_NAME already exists, skipping"
msg_warn "Database $DB_NAME already exists, skipping creation"
fi
# Encoding guard (issue #8): catch both a freshly mis-created DB and a
# pre-existing SQL_ASCII database from an old provisioning. Abort before the
# app ever connects — a wrong encoding is DB damage, not a warning.
assert_db_encoding_utf8 "$DB_NAME"
# pgvector: CREATE EXTENSION needs superuser; installed now (per ADR-0002:
# "Extension ab Tag 1 installiert, ungenutzt bis Phase 2").
run_psql -d "$DB_NAME" -c "CREATE EXTENSION IF NOT EXISTS vector" >/dev/null
@@ -141,9 +155,12 @@ Password: $DB_PASS
DSN for /etc/nexus/env on the nexus LXC (NEXUS_DATABASE_URL):
postgresql+psycopg://$DB_USER:$DB_PASS@$IP_SELF:$DB_PORT/$DB_NAME
Encoding: UTF8 (LC_COLLATE/LC_CTYPE en_US.UTF-8) — verified at install time.
Access policy (pg_hba): only $NEXUS_APP_IP/32 may connect; all other
hosts are rejected. Local socket stays peer-auth for maintenance:
pct exec <CTID> -- runuser -u postgres -- psql -d $DB_NAME
hosts are rejected. Local socket stays peer-auth for maintenance (these
minimal LXCs have no sudo — use su, not sudo):
pct exec <CTID> -- su - postgres -c "psql -d $DB_NAME"
EOF
chmod 600 "$CRED_FILE"
msg_ok "Credentials written to $CRED_FILE (chmod 600)"
+44
View File
@@ -54,6 +54,50 @@ apt_cleanup() {
apt-get autoclean -qq >/dev/null || true
}
# ── database installers: UTF-8 locale before initdb ──────────────────────────
# Pattern for every DB installer. A PostgreSQL cluster/database freezes its
# encoding at initdb / CREATE DATABASE time and it cannot be changed later —
# a C (non-UTF-8) locale yields a SQL_ASCII cluster. psycopg3 then returns
# text as bytes and SQLAlchemy crashes on server-version detection; the app
# reports "db: unreachable". So: GENERATE the UTF-8 locale AND make it active
# for THIS process before the server package runs its automatic initdb, then
# fail loudly if it is not actually available (generating alone is not enough
# — the locale must be active when initdb runs).
ensure_utf8_locale_active() {
local loc="${1:-en_US.UTF-8}"
msg_info "Ensuring $loc is generated and active (DB encoding is frozen at initdb)..."
if ! locale -a 2>/dev/null | tr 'A-Z' 'a-z' | grep -q '^en_us\.utf-\?8$'; then
sed -i 's/^# *en_US\.UTF-8 UTF-8/en_US.UTF-8 UTF-8/' /etc/locale.gen
locale-gen >/dev/null
fi
if ! locale -a 2>/dev/null | tr 'A-Z' 'a-z' | grep -q '^en_us\.utf-\?8$'; then
msg_err "Locale $loc not available after locale-gen — refusing to continue (initdb would create a SQL_ASCII cluster)"
return 1
fi
# Activate for the current process so any automatic initdb during the
# server package install inherits a UTF-8 locale, not the bare-template C.
export LANG="$loc" LC_ALL="$loc"
msg_ok "Locale active for initdb: LANG=$LANG"
}
# Post-install guard: a database MUST be UTF8. Encoding is irreversible, so a
# wrong value is database damage — abort with a clear, actionable message
# instead of shipping a broken cluster. Reads via `su - postgres -c` (minimal
# LXCs have no sudo).
assert_db_encoding_utf8() {
local db="$1" enc
enc="$(su - postgres -c "psql -X -qAt -c \"SELECT pg_encoding_to_char(encoding) FROM pg_database WHERE datname='$db'\"")"
if [[ "$enc" != "UTF8" ]]; then
msg_err "Database '$db' has encoding '${enc:-<not found>}', expected UTF8."
msg_err "Encoding is frozen at creation time — this is DB damage, not cosmetic."
msg_err "Fix: regenerate the locale (locale-gen en_US.UTF-8) and recreate the DB"
msg_err " with: CREATE DATABASE $db ... TEMPLATE template0 ENCODING 'UTF8'"
msg_err " LC_COLLATE 'en_US.UTF-8' LC_CTYPE 'en_US.UTF-8';"
return 1
fi
msg_ok "Encoding check: database '$db' is UTF8"
}
# ── ssh ──────────────────────────────────────────────────────────────────────
# SSH-Root-Login gemäß Host-Prompt (prompt_lxc_config setzt SSH_ROOT_LOGIN,
# bootstrap_install_script reicht es als Env durch; Default: yes).