feat: split ClickHouse into dual configurable databases (ja4_logs / ja4_processing)
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>
This commit is contained in:
@ -1,11 +1,11 @@
|
||||
CREATE MATERIALIZED VIEW mabase_prod.mv_http_logs
|
||||
TO mabase_prod.http_logs
|
||||
CREATE MATERIALIZED VIEW ja4_logs.mv_http_logs
|
||||
TO ja4_logs.http_logs
|
||||
AS
|
||||
WITH
|
||||
coalesce(JSONExtractString(raw_json, 'header_User-Agent'), '') AS _ua,
|
||||
toIPv6(toIPv4(coalesce(JSONExtractString(raw_json, 'src_ip'), '0.0.0.0'))) AS _ip,
|
||||
toUInt32(dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'asn', _ip, toUInt32(0))) AS _asn,
|
||||
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'country_code', _ip, '') AS _cc
|
||||
toUInt32(dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'asn', _ip, toUInt32(0))) AS _asn,
|
||||
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'country_code', _ip, '') AS _cc
|
||||
SELECT
|
||||
parseDateTimeBestEffort(coalesce(JSONExtractString(raw_json, 'time'), '1970-01-01T00:00:00Z')) AS time,
|
||||
toDate(time) AS log_date,
|
||||
@ -15,9 +15,9 @@ SELECT
|
||||
_cc AS src_country_code,
|
||||
toIPv4(coalesce(JSONExtractString(raw_json, 'dst_ip'), '0.0.0.0')) AS dst_ip,
|
||||
toUInt16(coalesce(JSONExtractUInt(raw_json, 'dst_port'), 0)) AS dst_port,
|
||||
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'name', _ip, '') AS src_as_name,
|
||||
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'org', _ip, '') AS src_org,
|
||||
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'domain', _ip, '') AS src_domain,
|
||||
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'name', _ip, '') AS src_as_name,
|
||||
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'org', _ip, '') AS src_org,
|
||||
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'domain', _ip, '') AS src_domain,
|
||||
coalesce(JSONExtractString(raw_json, 'method'), '') AS method,
|
||||
coalesce(JSONExtractString(raw_json, 'scheme'), '') AS scheme,
|
||||
coalesce(JSONExtractString(raw_json, 'host'), '') AS host,
|
||||
@ -64,63 +64,63 @@ SELECT
|
||||
-- Anubis enrichment : logique de correspondance combinée UA+IP
|
||||
-- Priorité : (1) UA+IP [même rule_id] > (2) UA seul > (3) IP seul > (4) ASN > (5) Pays
|
||||
CASE
|
||||
WHEN dictGet('mabase_prod.dict_anubis_ua', 'has_ip', _ua) = '1'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('mabase_prod.dict_anubis_ua', 'rule_id', _ua))
|
||||
= dictGetOrDefault('mabase_prod.dict_anubis_ip', 'rule_id', _ip, toUInt64(0))
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua)
|
||||
WHEN dictGet('mabase_prod.dict_anubis_ua', 'has_ip', _ua) = '0'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua)
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'has_ua', _ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', _asn, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', _asn, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', _cc, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', _cc, '')
|
||||
WHEN dictGet('ja4_processing.dict_anubis_ua', 'has_ip', _ua) = '1'
|
||||
AND dictGet('ja4_processing.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
AND dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('ja4_processing.dict_anubis_ua', 'rule_id', _ua))
|
||||
= dictGetOrDefault('ja4_processing.dict_anubis_ip', 'rule_id', _ip, toUInt64(0))
|
||||
THEN dictGet('ja4_processing.dict_anubis_ua', 'bot_name', _ua)
|
||||
WHEN dictGet('ja4_processing.dict_anubis_ua', 'has_ip', _ua) = '0'
|
||||
AND dictGet('ja4_processing.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
THEN dictGet('ja4_processing.dict_anubis_ua', 'bot_name', _ua)
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_ip', 'has_ua', _ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', _ip, '')
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', _asn, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', _asn, '')
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_country', 'bot_name', _cc, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_country', 'bot_name', _cc, '')
|
||||
ELSE ''
|
||||
END AS anubis_bot_name,
|
||||
|
||||
CASE
|
||||
WHEN dictGet('mabase_prod.dict_anubis_ua', 'has_ip', _ua) = '1'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('mabase_prod.dict_anubis_ua', 'rule_id', _ua))
|
||||
= dictGetOrDefault('mabase_prod.dict_anubis_ip', 'rule_id', _ip, toUInt64(0))
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'action', _ua)
|
||||
WHEN dictGet('mabase_prod.dict_anubis_ua', 'has_ip', _ua) = '0'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'action', _ua)
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'has_ua', _ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'action', _ip, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', _asn, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'action', _asn, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', _cc, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'action', _cc, '')
|
||||
WHEN dictGet('ja4_processing.dict_anubis_ua', 'has_ip', _ua) = '1'
|
||||
AND dictGet('ja4_processing.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
AND dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('ja4_processing.dict_anubis_ua', 'rule_id', _ua))
|
||||
= dictGetOrDefault('ja4_processing.dict_anubis_ip', 'rule_id', _ip, toUInt64(0))
|
||||
THEN dictGet('ja4_processing.dict_anubis_ua', 'action', _ua)
|
||||
WHEN dictGet('ja4_processing.dict_anubis_ua', 'has_ip', _ua) = '0'
|
||||
AND dictGet('ja4_processing.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
THEN dictGet('ja4_processing.dict_anubis_ua', 'action', _ua)
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_ip', 'has_ua', _ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_ip', 'action', _ip, '')
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', _asn, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_asn', 'action', _asn, '')
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_country', 'bot_name', _cc, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_country', 'action', _cc, '')
|
||||
ELSE ''
|
||||
END AS anubis_bot_action,
|
||||
|
||||
CASE
|
||||
WHEN dictGet('mabase_prod.dict_anubis_ua', 'has_ip', _ua) = '1'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('mabase_prod.dict_anubis_ua', 'rule_id', _ua))
|
||||
= dictGetOrDefault('mabase_prod.dict_anubis_ip', 'rule_id', _ip, toUInt64(0))
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'category', _ua)
|
||||
WHEN dictGet('mabase_prod.dict_anubis_ua', 'has_ip', _ua) = '0'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'category', _ua)
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'has_ua', _ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'category', _ip, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', _asn, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'category', _asn, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', _cc, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'category', _cc, '')
|
||||
WHEN dictGet('ja4_processing.dict_anubis_ua', 'has_ip', _ua) = '1'
|
||||
AND dictGet('ja4_processing.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
AND dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('ja4_processing.dict_anubis_ua', 'rule_id', _ua))
|
||||
= dictGetOrDefault('ja4_processing.dict_anubis_ip', 'rule_id', _ip, toUInt64(0))
|
||||
THEN dictGet('ja4_processing.dict_anubis_ua', 'category', _ua)
|
||||
WHEN dictGet('ja4_processing.dict_anubis_ua', 'has_ip', _ua) = '0'
|
||||
AND dictGet('ja4_processing.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
THEN dictGet('ja4_processing.dict_anubis_ua', 'category', _ua)
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_ip', 'has_ua', _ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_ip', 'category', _ip, '')
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', _asn, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_asn', 'category', _asn, '')
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_country', 'bot_name', _cc, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_country', 'category', _cc, '')
|
||||
ELSE ''
|
||||
END AS anubis_bot_category
|
||||
|
||||
FROM mabase_prod.http_logs_raw
|
||||
FROM ja4_logs.http_logs_raw
|
||||
|
||||
Reference in New Issue
Block a user