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

@ -1,6 +1,6 @@
DROP TABLE IF EXISTS mabase_prod.ref_bot_networks;
DROP TABLE IF EXISTS ja4_processing.ref_bot_networks;
CREATE TABLE mabase_prod.ref_bot_networks (
CREATE TABLE ja4_processing.ref_bot_networks (
-- On utilise IPv6CIDR car il accepte aussi les IPv4 au format ::ffff:1.2.3.4/120
network IPv6CIDR,
bot_name LowCardinality(String),
@ -11,11 +11,11 @@ ORDER BY (network, bot_name);
-- Création de la table lisant le fichier des IPs
CREATE TABLE mabase_prod.bot_ip (
CREATE TABLE ja4_processing.bot_ip (
ip String
) ENGINE = File(CSV, 'bot_ip.csv');
-- Création de la table lisant le fichier des signatures JA4
CREATE TABLE mabase_prod.bot_ja4 (
CREATE TABLE ja4_processing.bot_ja4 (
ja4 String
) ENGINE = File(CSV, 'bot_ja4.csv');

View File

@ -11,13 +11,14 @@
-- -----------------------------------------------------------------------------
-- Base de données
-- -----------------------------------------------------------------------------
CREATE DATABASE IF NOT EXISTS mabase_prod;
CREATE DATABASE IF NOT EXISTS ja4_logs;
CREATE DATABASE IF NOT EXISTS ja4_processing;
-- -----------------------------------------------------------------------------
-- Table brute : cible directe des inserts du service
-- Le service n'insère que dans cette table (colonne raw_json).
-- -----------------------------------------------------------------------------
CREATE TABLE IF NOT EXISTS mabase_prod.http_logs_raw
CREATE TABLE IF NOT EXISTS ja4_logs.http_logs_raw
(
`raw_json` String CODEC(ZSTD(3)),
`ingest_time` DateTime DEFAULT now()
@ -34,7 +35,7 @@ SETTINGS
-- Table parsée : alimentée automatiquement par la vue matérialisée
-- -----------------------------------------------------------------------------
CREATE TABLE mabase_prod.http_logs
CREATE TABLE ja4_logs.http_logs
(
-- Temporel
`time` DateTime,
@ -118,10 +119,10 @@ SETTINGS
-- -----------------------------------------------------------------------------
-- Vue matérialisée : parse le JSON de http_logs_raw vers http_logs
-- -----------------------------------------------------------------------------
DROP VIEW IF EXISTS mabase_prod.mv_http_logs;
DROP VIEW IF EXISTS ja4_logs.mv_http_logs;
CREATE MATERIALIZED VIEW IF NOT EXISTS mabase_prod.mv_http_logs
TO mabase_prod.http_logs
CREATE MATERIALIZED VIEW IF NOT EXISTS ja4_logs.mv_http_logs
TO ja4_logs.http_logs
AS
SELECT
parseDateTimeBestEffort(coalesce(JSONExtractString(raw_json, 'time'), '1970-01-01T00:00:00Z')) AS time,
@ -133,31 +134,31 @@ SELECT
toUInt16(coalesce(JSONExtractUInt(raw_json, 'dst_port'), 0)) AS dst_port,
dictGetOrDefault(
'mabase_prod.dict_iplocate_asn',
'ja4_processing.dict_iplocate_asn',
'asn',
IPv4ToIPv6(IPv4StringToNum(toString(src_ip))),
toUInt32(0)
) AS src_asn,
dictGetOrDefault(
'mabase_prod.dict_iplocate_asn',
'ja4_processing.dict_iplocate_asn',
'country_code',
IPv4ToIPv6(IPv4StringToNum(toString(src_ip))),
''
) AS src_country_code,
dictGetOrDefault(
'mabase_prod.dict_iplocate_asn',
'ja4_processing.dict_iplocate_asn',
'name',
IPv4ToIPv6(IPv4StringToNum(toString(src_ip))),
''
) AS src_as_name,
dictGetOrDefault(
'mabase_prod.dict_iplocate_asn',
'ja4_processing.dict_iplocate_asn',
'org',
IPv4ToIPv6(IPv4StringToNum(toString(src_ip))),
''
) AS src_org,
dictGetOrDefault(
'mabase_prod.dict_iplocate_asn',
'ja4_processing.dict_iplocate_asn',
'domain',
IPv4ToIPv6(IPv4StringToNum(toString(src_ip))),
''
@ -211,7 +212,7 @@ SELECT
coalesce(JSONExtractString(raw_json, 'header_Sec-Fetch-Mode'), '') AS header_sec_fetch_mode,
coalesce(JSONExtractString(raw_json, 'header_Sec-Fetch-Site'), '') AS header_sec_fetch_site
FROM mabase_prod.http_logs_raw;
FROM ja4_logs.http_logs_raw;
-- -----------------------------------------------------------------------------
-- Utilisateurs et permissions
@ -220,15 +221,15 @@ CREATE USER IF NOT EXISTS data_writer IDENTIFIED WITH plaintext_password BY 'Cha
CREATE USER IF NOT EXISTS analyst IDENTIFIED WITH plaintext_password BY 'ChangeMe';
-- data_writer : INSERT uniquement sur la table brute
GRANT INSERT ON mabase_prod.http_logs_raw TO data_writer;
GRANT SELECT ON mabase_prod.http_logs_raw TO data_writer;
GRANT INSERT ON ja4_logs.http_logs_raw TO data_writer;
GRANT SELECT ON ja4_logs.http_logs_raw TO data_writer;
-- analyst : lecture sur la table parsée
GRANT SELECT ON mabase_prod.http_logs TO analyst;
GRANT SELECT ON ja4_logs.http_logs TO analyst;
-- -----------------------------------------------------------------------------
-- Vérifications post-installation
-- -----------------------------------------------------------------------------
-- SELECT count(*), min(ingest_time), max(ingest_time) FROM mabase_prod.http_logs_raw;
-- SELECT count(*), min(time), max(time) FROM mabase_prod.http_logs;
-- SELECT time, src_ip, dst_ip, method, host, path, ja4 FROM mabase_prod.http_logs ORDER BY time DESC LIMIT 10;
-- SELECT count(*), min(ingest_time), max(ingest_time) FROM ja4_logs.http_logs_raw;
-- SELECT count(*), min(time), max(time) FROM ja4_logs.http_logs;
-- SELECT time, src_ip, dst_ip, method, host, path, ja4 FROM ja4_logs.http_logs ORDER BY time DESC LIMIT 10;

View File

@ -1,6 +1,6 @@
DROP DICTIONARY IF EXISTS mabase_prod.dict_iplocate_asn;
DROP DICTIONARY IF EXISTS ja4_processing.dict_iplocate_asn;
CREATE DICTIONARY IF NOT EXISTS mabase_prod.dict_iplocate_asn
CREATE DICTIONARY IF NOT EXISTS ja4_processing.dict_iplocate_asn
(
network String,
asn UInt32,
@ -17,10 +17,10 @@ LIFETIME(MIN 3600 MAX 7200);
-- Suppression si existe pour reconfiguration
DROP TABLE IF EXISTS mabase_prod.ref_bot_networks;
DROP TABLE IF EXISTS ja4_processing.ref_bot_networks;
-- Table optimisée pour le filtrage binaire de CIDR
CREATE TABLE mabase_prod.ref_bot_networks (
CREATE TABLE ja4_processing.ref_bot_networks (
network IPv6CIDR, -- Gère nativement '1.2.3.0/24' et '2001:db8::/32'
bot_name LowCardinality(String),
is_legitimate UInt8, -- 1 = Whitelist, 0 = Blacklist