Files
ja4-platform/shared/clickhouse/04_mv_http_logs.sql
toto 9f3e0621e5 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>
2026-04-07 19:10:35 +02:00

235 lines
14 KiB
SQL

-- =============================================================================
-- 04_mv_http_logs.sql — Canonical http_logs target table + mv_http_logs MV
--
-- Canonical version — supersedes services/correlator/sql/init.sql base version.
-- This version includes full Anubis enrichment (anubis_bot_name, anubis_bot_action,
-- anubis_bot_category) with combined UA+IP priority logic from
-- bot_detector/anubis/mv_http_logs.sql.
-- =============================================================================
-- -----------------------------------------------------------------------------
-- http_logs — parsed destination table (populated by mv_http_logs)
-- Includes Anubis enrichment columns added by deploy_schema.sql items 9+
-- -----------------------------------------------------------------------------
CREATE TABLE IF NOT EXISTS ja4_logs.http_logs
(
-- Temporal
`time` DateTime,
`log_date` Date DEFAULT toDate(time),
-- Network
`src_ip` IPv4,
`src_port` UInt16,
`dst_ip` IPv4,
`dst_port` UInt16,
-- IPLocate enrichment
`src_asn` UInt32,
`src_country_code` LowCardinality(String),
`src_as_name` LowCardinality(String),
`src_org` LowCardinality(String),
`src_domain` LowCardinality(String),
-- HTTP
`method` LowCardinality(String),
`scheme` LowCardinality(String),
`host` LowCardinality(String),
`path` String CODEC(ZSTD(3)),
`query` String CODEC(ZSTD(3)),
`http_version` LowCardinality(String),
-- Correlation
`orphan_side` LowCardinality(String),
`correlated` UInt8,
`keepalives` UInt16,
`a_timestamp` UInt64,
`b_timestamp` UInt64,
`conn_id` String CODEC(ZSTD(3)),
-- IP metadata
`ip_meta_df` UInt8,
`ip_meta_id` UInt16,
`ip_meta_total_length` UInt16,
`ip_meta_ttl` UInt8,
-- TCP metadata
`tcp_meta_options` LowCardinality(String),
`tcp_meta_window_size` UInt32,
`tcp_meta_mss` UInt16,
`tcp_meta_window_scale` UInt8,
`syn_to_clienthello_ms` Int32,
-- TLS / fingerprints
`tls_version` LowCardinality(String),
`tls_sni` LowCardinality(String),
`tls_alpn` LowCardinality(String),
`ja3` String CODEC(ZSTD(3)),
`ja3_hash` String CODEC(ZSTD(3)),
`ja4` String CODEC(ZSTD(3)),
-- HTTP headers
`client_headers` String CODEC(ZSTD(3)),
`header_user_agent` String CODEC(ZSTD(3)),
`header_accept` String CODEC(ZSTD(3)),
`header_accept_encoding` String CODEC(ZSTD(3)),
`header_accept_language` String CODEC(ZSTD(3)),
`header_content_type` String CODEC(ZSTD(3)),
`header_x_request_id` String CODEC(ZSTD(3)),
`header_x_trace_id` String CODEC(ZSTD(3)),
`header_x_forwarded_for` String CODEC(ZSTD(3)),
`header_sec_ch_ua` String CODEC(ZSTD(3)),
`header_sec_ch_ua_mobile` String CODEC(ZSTD(3)),
`header_sec_ch_ua_platform` String CODEC(ZSTD(3)),
`header_sec_fetch_dest` String CODEC(ZSTD(3)),
`header_sec_fetch_mode` String CODEC(ZSTD(3)),
`header_sec_fetch_site` String CODEC(ZSTD(3)),
-- Anubis enrichment columns
`anubis_bot_name` LowCardinality(String) DEFAULT '',
`anubis_bot_action` LowCardinality(String) DEFAULT '',
`anubis_bot_category` LowCardinality(String) DEFAULT ''
)
ENGINE = MergeTree
PARTITION BY log_date
ORDER BY (time, src_ip, dst_ip, ja4)
TTL log_date + INTERVAL 7 DAY
SETTINGS
index_granularity = 8192,
ttl_only_drop_parts = 1;
-- -----------------------------------------------------------------------------
-- mv_http_logs — canonical materialized view with full Anubis enrichment
-- Priority logic: (1) UA+IP combined [same rule_id] > (2) UA only > (3) IP only
-- > (4) ASN > (5) Country
-- Uses WITH clause CTEs for clean intermediate values.
-- -----------------------------------------------------------------------------
DROP VIEW IF EXISTS ja4_logs.mv_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('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,
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,
_asn AS src_asn,
_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('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,
coalesce(JSONExtractString(raw_json, 'path'), '') AS path,
coalesce(JSONExtractString(raw_json, 'query'), '') AS query,
coalesce(JSONExtractString(raw_json, 'http_version'), '') AS http_version,
coalesce(JSONExtractString(raw_json, 'orphan_side'), '') AS orphan_side,
toUInt8(coalesce(JSONExtractBool(raw_json, 'correlated'), 0)) AS correlated,
toUInt16(coalesce(JSONExtractUInt(raw_json, 'keepalives'), 0)) AS keepalives,
coalesce(JSONExtractUInt(raw_json, 'a_timestamp'), 0) AS a_timestamp,
coalesce(JSONExtractUInt(raw_json, 'b_timestamp'), 0) AS b_timestamp,
coalesce(JSONExtractString(raw_json, 'conn_id'), '') AS conn_id,
toUInt8(coalesce(JSONExtractBool(raw_json, 'ip_meta_df'), 0)) AS ip_meta_df,
toUInt16(coalesce(JSONExtractUInt(raw_json, 'ip_meta_id'), 0)) AS ip_meta_id,
toUInt16(coalesce(JSONExtractUInt(raw_json, 'ip_meta_total_length'), 0)) AS ip_meta_total_length,
toUInt8(coalesce(JSONExtractUInt(raw_json, 'ip_meta_ttl'), 0)) AS ip_meta_ttl,
coalesce(JSONExtractString(raw_json, 'tcp_meta_options'), '') AS tcp_meta_options,
toUInt32(coalesce(JSONExtractUInt(raw_json, 'tcp_meta_window_size'), 0)) AS tcp_meta_window_size,
toUInt16(coalesce(JSONExtractUInt(raw_json, 'tcp_meta_mss'), 0)) AS tcp_meta_mss,
toUInt8(coalesce(JSONExtractUInt(raw_json, 'tcp_meta_window_scale'), 0)) AS tcp_meta_window_scale,
toInt32(coalesce(JSONExtractInt(raw_json, 'syn_to_clienthello_ms'), 0)) AS syn_to_clienthello_ms,
coalesce(JSONExtractString(raw_json, 'tls_version'), '') AS tls_version,
coalesce(JSONExtractString(raw_json, 'tls_sni'), '') AS tls_sni,
coalesce(JSONExtractString(raw_json, 'tls_alpn'), '') AS tls_alpn,
coalesce(JSONExtractString(raw_json, 'ja3'), '') AS ja3,
coalesce(JSONExtractString(raw_json, 'ja3_hash'), '') AS ja3_hash,
coalesce(JSONExtractString(raw_json, 'ja4'), '') AS ja4,
coalesce(JSONExtractString(raw_json, 'client_headers'), '') AS client_headers,
coalesce(JSONExtractString(raw_json, 'header_User-Agent'), '') AS header_user_agent,
coalesce(JSONExtractString(raw_json, 'header_Accept'), '') AS header_accept,
coalesce(JSONExtractString(raw_json, 'header_Accept-Encoding'), '') AS header_accept_encoding,
coalesce(JSONExtractString(raw_json, 'header_Accept-Language'), '') AS header_accept_language,
coalesce(JSONExtractString(raw_json, 'header_Content-Type'), '') AS header_content_type,
coalesce(JSONExtractString(raw_json, 'header_X-Request-Id'), '') AS header_x_request_id,
coalesce(JSONExtractString(raw_json, 'header_X-Trace-Id'), '') AS header_x_trace_id,
coalesce(JSONExtractString(raw_json, 'header_X-Forwarded-For'), '') AS header_x_forwarded_for,
coalesce(JSONExtractString(raw_json, 'header_Sec-CH-UA'), '') AS header_sec_ch_ua,
coalesce(JSONExtractString(raw_json, 'header_Sec-CH-UA-Mobile'), '') AS header_sec_ch_ua_mobile,
coalesce(JSONExtractString(raw_json, 'header_Sec-CH-UA-Platform'), '') AS header_sec_ch_ua_platform,
coalesce(JSONExtractString(raw_json, 'header_Sec-Fetch-Dest'), '') AS header_sec_fetch_dest,
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,
-- Anubis enrichment: combined UA+IP priority logic
-- Priority: (1) UA+IP [same rule_id] > (2) UA only > (3) IP only > (4) ASN > (5) Country
CASE
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('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('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 ja4_logs.http_logs_raw;