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:
toto
2026-04-07 19:10:35 +02:00
parent b6391afbeb
commit 9f3e0621e5
46 changed files with 638 additions and 549 deletions

View File

@ -26,7 +26,7 @@
-- Quand l'UA correspond à enfant ET parent, c'est le nom de l'enfant qui
-- est retourné (l'enfant hérite ET surcharge les attributs du parent).
-- ----------------------------------------------------------------------------
CREATE TABLE IF NOT EXISTS mabase_prod.anubis_ua_rules
CREATE TABLE IF NOT EXISTS ja4_processing.anubis_ua_rules
(
id UInt64,
parent_id UInt64,
@ -46,7 +46,7 @@ ORDER BY id;
-- has_ua : 1 si la règle possède aussi une regex UA (croisement nécessaire)
-- category : catégorie Anubis (bots, crawlers, clients, policies…)
-- ----------------------------------------------------------------------------
CREATE TABLE IF NOT EXISTS mabase_prod.anubis_ip_rules
CREATE TABLE IF NOT EXISTS ja4_processing.anubis_ip_rules
(
prefix String,
bot_name LowCardinality(String),
@ -60,31 +60,31 @@ ORDER BY prefix;
-- ----------------------------------------------------------------------------
-- 3. DICTIONNAIRE UA — REGEXP_TREE
-- dictGet('mabase_prod.dict_anubis_ua', 'bot_name', header_user_agent)
-- dictGet('ja4_processing.dict_anubis_ua', 'bot_name', header_user_agent)
--
-- Le PRIMARY KEY est 'regexp' (String) — requis par ClickHouse 26.x.
-- Connexion interne (HOST localhost PORT 9000) pour éviter deadlock HTTP.
-- Remplacer 'admin' et le mot de passe par les credentials ClickHouse.
-- ----------------------------------------------------------------------------
DROP DICTIONARY IF EXISTS mabase_prod.dict_anubis_ua;
CREATE DICTIONARY mabase_prod.dict_anubis_ua
DROP DICTIONARY IF EXISTS ja4_processing.dict_anubis_ua;
CREATE DICTIONARY ja4_processing.dict_anubis_ua
(
regexp String,
bot_name String,
action String
)
PRIMARY KEY regexp
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'mabase_prod' TABLE 'anubis_ua_rules'))
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'ja4_processing' TABLE 'anubis_ua_rules'))
LAYOUT(REGEXP_TREE)
LIFETIME(MIN 300 MAX 600);
-- ----------------------------------------------------------------------------
-- 4. DICTIONNAIRE IP — IP_TRIE
-- dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', toIPv6(src_ip), '')
-- dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', toIPv6(src_ip), '')
-- Connexion interne (HOST localhost PORT 9000) — même raison que dict_anubis_ua.
-- ----------------------------------------------------------------------------
DROP DICTIONARY IF EXISTS mabase_prod.dict_anubis_ip;
CREATE DICTIONARY mabase_prod.dict_anubis_ip
DROP DICTIONARY IF EXISTS ja4_processing.dict_anubis_ip;
CREATE DICTIONARY ja4_processing.dict_anubis_ip
(
prefix String,
bot_name String,
@ -94,7 +94,7 @@ CREATE DICTIONARY mabase_prod.dict_anubis_ip
category String
)
PRIMARY KEY prefix
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'mabase_prod' TABLE 'anubis_ip_rules'))
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'ja4_processing' TABLE 'anubis_ip_rules'))
LAYOUT(IP_TRIE())
LIFETIME(MIN 300 MAX 600);
@ -102,7 +102,7 @@ LIFETIME(MIN 300 MAX 600);
-- 5. TABLE SOURCE — règles ASN (pour dictionnaire Flat)
-- Alimentée par botPolicies.yaml via fetch_rules.py → insert_asn_rules()
-- ----------------------------------------------------------------------------
CREATE TABLE IF NOT EXISTS mabase_prod.anubis_asn_rules
CREATE TABLE IF NOT EXISTS ja4_processing.anubis_asn_rules
(
asn UInt32,
bot_name LowCardinality(String),
@ -116,7 +116,7 @@ ORDER BY asn;
-- 6. TABLE SOURCE — règles pays ISO-3166 (pour dictionnaire Flat)
-- Alimentée par botPolicies.yaml via fetch_rules.py → insert_country_rules()
-- ----------------------------------------------------------------------------
CREATE TABLE IF NOT EXISTS mabase_prod.anubis_country_rules
CREATE TABLE IF NOT EXISTS ja4_processing.anubis_country_rules
(
country_code LowCardinality(String),
bot_name LowCardinality(String),
@ -128,10 +128,10 @@ ORDER BY country_code;
-- ----------------------------------------------------------------------------
-- 7. DICTIONNAIRE ASN — Flat
-- dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', src_asn, '')
-- dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', src_asn, '')
-- ----------------------------------------------------------------------------
DROP DICTIONARY IF EXISTS mabase_prod.dict_anubis_asn;
CREATE DICTIONARY mabase_prod.dict_anubis_asn
DROP DICTIONARY IF EXISTS ja4_processing.dict_anubis_asn;
CREATE DICTIONARY ja4_processing.dict_anubis_asn
(
asn UInt32,
bot_name String,
@ -139,16 +139,16 @@ CREATE DICTIONARY mabase_prod.dict_anubis_asn
category String
)
PRIMARY KEY asn
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'mabase_prod' TABLE 'anubis_asn_rules'))
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'ja4_processing' TABLE 'anubis_asn_rules'))
LAYOUT(FLAT())
LIFETIME(MIN 300 MAX 600);
-- ----------------------------------------------------------------------------
-- 8. DICTIONNAIRE PAYS — Flat
-- dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', src_country_code, '')
-- dictGetOrDefault('ja4_processing.dict_anubis_country', 'bot_name', src_country_code, '')
-- ----------------------------------------------------------------------------
DROP DICTIONARY IF EXISTS mabase_prod.dict_anubis_country;
CREATE DICTIONARY mabase_prod.dict_anubis_country
DROP DICTIONARY IF EXISTS ja4_processing.dict_anubis_country;
CREATE DICTIONARY ja4_processing.dict_anubis_country
(
country_code String,
bot_name String,
@ -156,7 +156,7 @@ CREATE DICTIONARY mabase_prod.dict_anubis_country
category String
)
PRIMARY KEY country_code
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'mabase_prod' TABLE 'anubis_country_rules'))
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'ja4_processing' TABLE 'anubis_country_rules'))
LAYOUT(FLAT())
LIFETIME(MIN 300 MAX 600);
@ -164,7 +164,7 @@ LIFETIME(MIN 300 MAX 600);
-- 9. AJOUT DES COLONNES ANUBIS dans http_logs
-- Idempotent : ne plante pas si déjà présentes
-- ----------------------------------------------------------------------------
ALTER TABLE mabase_prod.http_logs
ALTER TABLE ja4_logs.http_logs
ADD COLUMN IF NOT EXISTS anubis_bot_name LowCardinality(String) DEFAULT '',
ADD COLUMN IF NOT EXISTS anubis_bot_action LowCardinality(String) DEFAULT '',
ADD COLUMN IF NOT EXISTS anubis_bot_category LowCardinality(String) DEFAULT '';
@ -175,10 +175,10 @@ ALTER TABLE mabase_prod.http_logs
-- 1. UA regex (plus informatif — identifie le bot précis)
-- 2. IP/CIDR (fallback — identifie le réseau cloud)
-- ----------------------------------------------------------------------------
DROP VIEW IF EXISTS mabase_prod.mv_http_logs;
DROP VIEW IF EXISTS ja4_logs.mv_http_logs;
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
(
`time` DateTime,
`log_date` Date,
@ -241,13 +241,13 @@ AS SELECT
toDate(time) AS log_date,
toIPv4(coalesce(JSONExtractString(raw_json, 'src_ip'), '0.0.0.0')) AS src_ip,
toUInt16(coalesce(JSONExtractUInt(raw_json, 'src_port'), 0)) AS src_port,
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'asn', toIPv6(src_ip), toUInt32(0)) AS src_asn,
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'country_code', toIPv6(src_ip), '') AS src_country_code,
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'asn', toIPv6(src_ip), toUInt32(0)) AS src_asn,
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'country_code', toIPv6(src_ip), '') 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', toIPv6(src_ip), '') AS src_as_name,
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'org', toIPv6(src_ip), '') AS src_org,
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'domain', toIPv6(src_ip), '') AS src_domain,
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'name', toIPv6(src_ip), '') AS src_as_name,
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'org', toIPv6(src_ip), '') AS src_org,
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'domain', toIPv6(src_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,
@ -293,20 +293,20 @@ AS SELECT
-- ── Enrichissement Anubis ────────────────────────────────────────────────
-- Priorité : UA regex > IP/CIDR (UA identifie précisément le bot)
COALESCE(
nullIf(dictGet('mabase_prod.dict_anubis_ua', 'bot_name',
nullIf(dictGet('ja4_processing.dict_anubis_ua', 'bot_name',
coalesce(JSONExtractString(raw_json, 'header_User-Agent'), '')), ''),
nullIf(dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name',
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name',
toIPv6(toIPv4(coalesce(JSONExtractString(raw_json, 'src_ip'), '0.0.0.0'))), ''), ''),
''
) AS anubis_bot_name,
COALESCE(
nullIf(dictGet('mabase_prod.dict_anubis_ua', 'action',
nullIf(dictGet('ja4_processing.dict_anubis_ua', 'action',
coalesce(JSONExtractString(raw_json, 'header_User-Agent'), '')), ''),
nullIf(dictGetOrDefault('mabase_prod.dict_anubis_ip', 'action',
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'action',
toIPv6(toIPv4(coalesce(JSONExtractString(raw_json, 'src_ip'), '0.0.0.0'))), ''), ''),
''
) AS anubis_bot_action
FROM mabase_prod.http_logs_raw;
FROM ja4_logs.http_logs_raw;
-- ============================================================================
-- INTÉGRATION ML — Propagation Anubis vers le pipeline bot_detector
@ -315,7 +315,7 @@ FROM mabase_prod.http_logs_raw;
-- ----------------------------------------------------------------------------
-- 11. COLONNES ANUBIS dans ml_detected_anomalies
-- ----------------------------------------------------------------------------
ALTER TABLE mabase_prod.ml_detected_anomalies
ALTER TABLE ja4_processing.ml_detected_anomalies
ADD COLUMN IF NOT EXISTS anubis_bot_name LowCardinality(String) DEFAULT '',
ADD COLUMN IF NOT EXISTS anubis_bot_action LowCardinality(String) DEFAULT '',
ADD COLUMN IF NOT EXISTS anubis_bot_category LowCardinality(String) DEFAULT '';
@ -323,7 +323,7 @@ ALTER TABLE mabase_prod.ml_detected_anomalies
-- ----------------------------------------------------------------------------
-- 12. COLONNES ANUBIS dans ml_all_scores
-- ----------------------------------------------------------------------------
ALTER TABLE mabase_prod.ml_all_scores
ALTER TABLE ja4_processing.ml_all_scores
ADD COLUMN IF NOT EXISTS anubis_bot_name LowCardinality(String) DEFAULT '',
ADD COLUMN IF NOT EXISTS anubis_bot_action LowCardinality(String) DEFAULT '',
ADD COLUMN IF NOT EXISTS anubis_bot_category LowCardinality(String) DEFAULT '';