Files
ja4-platform/services/bot-detector/anubis/mv_http_logs.sql
toto 98289ccf04 fix: ASN dictionary pipeline + verbose bot-detector logging
- Fix dict_iplocate_asn: remove non-existent org/domain columns (4→4 cols)
- Add CSV header to iplocate-ip-to-asn.csv (CSVWithNames format)
- Replace org/domain dictGet calls with empty string literals in MV
- Full 714K CIDR stub for complete ASN resolution in tests
- Add header generation to generate_asn_data.py
- Verbose bot-detector stdout: data summary, triage breakdown, model
  training details, scoring stats, browser classification, boxed results
- Fix IPv6 filter in traffic seeder (_ips_from_cidrs)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-04-08 17:43:55 +02:00

127 lines
9.7 KiB
SQL

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,
'' AS src_org,
'' 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 : 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('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