9f3e0621e5
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>
60 lines
2.2 KiB
SQL
60 lines
2.2 KiB
SQL
-- =============================================================================
|
|
-- 02_dictionaries.sql — ASN geo dictionary + bot reference tables
|
|
-- =============================================================================
|
|
|
|
-- -----------------------------------------------------------------------------
|
|
-- IPLocate ASN geo-location dictionary
|
|
-- CSV file must be placed at: /var/lib/clickhouse/user_files/iplocate-ip-to-asn.csv
|
|
-- -----------------------------------------------------------------------------
|
|
DROP DICTIONARY IF EXISTS ja4_processing.dict_iplocate_asn;
|
|
|
|
CREATE DICTIONARY IF NOT EXISTS ja4_processing.dict_iplocate_asn
|
|
(
|
|
network String,
|
|
asn UInt32,
|
|
country_code String,
|
|
name String,
|
|
org String,
|
|
domain String
|
|
)
|
|
PRIMARY KEY network
|
|
SOURCE(FILE(path '/var/lib/clickhouse/user_files/iplocate-ip-to-asn.csv' format 'CSVWithNames'))
|
|
LAYOUT(IP_TRIE())
|
|
LIFETIME(MIN 3600 MAX 7200);
|
|
|
|
|
|
-- -----------------------------------------------------------------------------
|
|
-- Bot network CIDR reference table (ReplacingMergeTree for upserts)
|
|
-- -----------------------------------------------------------------------------
|
|
CREATE TABLE IF NOT EXISTS ja4_processing.ref_bot_networks
|
|
(
|
|
network IPv6CIDR,
|
|
bot_name LowCardinality(String),
|
|
is_legitimate UInt8,
|
|
last_update DateTime
|
|
)
|
|
ENGINE = ReplacingMergeTree(last_update)
|
|
ORDER BY (network, bot_name);
|
|
|
|
|
|
-- -----------------------------------------------------------------------------
|
|
-- Bot IP flat table (CSV file engine)
|
|
-- CSV file must be placed at: /var/lib/clickhouse/user_files/bot_ip.csv
|
|
-- -----------------------------------------------------------------------------
|
|
CREATE TABLE IF NOT EXISTS ja4_processing.bot_ip
|
|
(
|
|
ip String
|
|
)
|
|
ENGINE = File(CSV, 'bot_ip.csv');
|
|
|
|
|
|
-- -----------------------------------------------------------------------------
|
|
-- Bot JA4 flat table (CSV file engine)
|
|
-- CSV file must be placed at: /var/lib/clickhouse/user_files/bot_ja4.csv
|
|
-- -----------------------------------------------------------------------------
|
|
CREATE TABLE IF NOT EXISTS ja4_processing.bot_ja4
|
|
(
|
|
ja4 String
|
|
)
|
|
ENGINE = File(CSV, 'bot_ja4.csv');
|