#!/bin/bash
# =============================================================================
# clickhouse-init.sh — Pre-process shared SQL files for integration testing
#
# Copies SQL from /initdb-src/ to /tmp, patches credentials, then executes.
# =============================================================================
set -e

SRC_DIR="/initdb-src"
TMP_DIR="/tmp/initdb-patched"
mkdir -p "$TMP_DIR"

for f in "$SRC_DIR"/*.sql; do
    [ -f "$f" ] || continue
    base=$(basename "$f")
    echo "[init] Patching $base"
    sed \
        -e "s/USER 'admin'/USER 'default'/g" \
        -e "s/PASSWORD 'CHANGE_ME'/PASSWORD ''/g" \
        -e "s/PASSWORD 'ChangeMe'/PASSWORD ''/g" \
        "$f" > "$TMP_DIR/$base"
done

for f in "$TMP_DIR"/*.sql; do
    [ -f "$f" ] || continue
    base=$(basename "$f")
    echo "[init] Executing $base"
    # 10_perf_indexes.sql uses ALTER TABLE ADD INDEX which may fail if index
    # already exists — allow non-zero exit for migration/perf scripts
    if [[ "$base" == 10_* ]]; then
        clickhouse-client --multiquery < "$f" || echo "[init] WARNING: $base had errors (expected for duplicate indexes)"
    else
        clickhouse-client --multiquery < "$f"
    fi
done

# ---------------------------------------------------------------------------
# Seed data required for dictionaries to function
# REGEXP_TREE dictionaries require at least one rule; without it, any INSERT
# into http_logs_raw fails because the MV mv_http_logs calls dictGet() on
# the empty dict.  Insert a catch-all "unknown" rule so the pipeline works.
# ---------------------------------------------------------------------------
echo "[init] Seeding anubis_ua_rules (REGEXP_TREE needs ≥1 rule)..."
clickhouse-client --multiquery <<'SEED'
INSERT INTO ja4_processing.anubis_ua_rules (id, parent_id, regexp, keys, values) VALUES
    (1, 0, '.*', ['bot_name','action','has_ip','rule_id','category'], ['','','0','0','']);
SEED

echo "[init] All SQL files executed and seed data inserted"