Architecture: - ja4_logs: raw log ingestion (http_logs_raw, http_logs, mv_http_logs) - ja4_processing: analytics, aggregation, ML, dictionaries, audit Configuration (env vars): - CLICKHOUSE_DB_LOGS (default: ja4_logs) - CLICKHOUSE_DB_PROCESSING (default: ja4_processing) Changes: - SQL migrations (10 files): all mabase_prod refs → ja4_logs or ja4_processing with correct cross-database references (MVs, views, dicts) - deploy_schema.sh: substitutes DB names from env vars at deploy time - Python shared settings: added CLICKHOUSE_DB_LOGS + CLICKHOUSE_DB_PROCESSING - Dashboard routes (19 files): replaced ~80 hardcoded mabase_prod refs with settings.CLICKHOUSE_DB_LOGS / settings.CLICKHOUSE_DB_PROCESSING - Bot-detector: DB → CLICKHOUSE_DB_PROCESSING, fetch_rules.py configurable - Correlator: DSN example updated to ja4_logs - Docker-compose + .env files: new env vars with defaults - All documentation updated (14 markdown files) All tests pass: sentinel 10/10, correlator 67.1%, bot-detector 11, dashboard 20, ja4_common 18 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
68 lines
2.2 KiB
Bash
Executable File
68 lines
2.2 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# =============================================================================
|
|
# deploy_schema.sh — Apply ClickHouse schema migrations with configurable
|
|
# database names via environment variables.
|
|
#
|
|
# Usage:
|
|
# CLICKHOUSE_DB_LOGS=my_logs CLICKHOUSE_DB_PROCESSING=my_proc ./deploy_schema.sh
|
|
#
|
|
# Env vars:
|
|
# CLICKHOUSE_DB_LOGS — logs database name (default: ja4_logs)
|
|
# CLICKHOUSE_DB_PROCESSING — processing database name (default: ja4_processing)
|
|
# CLICKHOUSE_HOST — ClickHouse host (default: localhost)
|
|
# CLICKHOUSE_PORT — ClickHouse native port (default: 9000)
|
|
# CLICKHOUSE_USER — ClickHouse user (default: default)
|
|
# CLICKHOUSE_PASSWORD — ClickHouse password (default: empty)
|
|
# =============================================================================
|
|
set -euo pipefail
|
|
|
|
CLICKHOUSE_DB_LOGS="${CLICKHOUSE_DB_LOGS:-ja4_logs}"
|
|
CLICKHOUSE_DB_PROCESSING="${CLICKHOUSE_DB_PROCESSING:-ja4_processing}"
|
|
CLICKHOUSE_HOST="${CLICKHOUSE_HOST:-localhost}"
|
|
CLICKHOUSE_PORT="${CLICKHOUSE_PORT:-9000}"
|
|
CLICKHOUSE_USER="${CLICKHOUSE_USER:-default}"
|
|
CLICKHOUSE_PASSWORD="${CLICKHOUSE_PASSWORD:-}"
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
|
|
CH_ARGS=(
|
|
--host "$CLICKHOUSE_HOST"
|
|
--port "$CLICKHOUSE_PORT"
|
|
--user "$CLICKHOUSE_USER"
|
|
)
|
|
if [[ -n "$CLICKHOUSE_PASSWORD" ]]; then
|
|
CH_ARGS+=(--password "$CLICKHOUSE_PASSWORD")
|
|
fi
|
|
|
|
SQL_FILES=(
|
|
00_database.sql
|
|
01_raw_tables.sql
|
|
02_dictionaries.sql
|
|
03_anubis_tables.sql
|
|
04_mv_http_logs.sql
|
|
05_aggregation_tables.sql
|
|
06_ml_tables.sql
|
|
07_ai_features_view.sql
|
|
08_users.sql
|
|
09_audit_table.sql
|
|
)
|
|
|
|
for f in "${SQL_FILES[@]}"; do
|
|
filepath="${SCRIPT_DIR}/${f}"
|
|
if [[ ! -f "$filepath" ]]; then
|
|
echo "WARN: ${f} not found, skipping" >&2
|
|
continue
|
|
fi
|
|
|
|
echo ">>> Applying ${f} ..."
|
|
sed \
|
|
-e "s/ja4_logs/${CLICKHOUSE_DB_LOGS}/g" \
|
|
-e "s/ja4_processing/${CLICKHOUSE_DB_PROCESSING}/g" \
|
|
"$filepath" \
|
|
| clickhouse-client "${CH_ARGS[@]}" --multiquery
|
|
done
|
|
|
|
echo "=== Schema deployment complete ==="
|
|
echo " logs db: ${CLICKHOUSE_DB_LOGS}"
|
|
echo " processing db: ${CLICKHOUSE_DB_PROCESSING}"
|