code_public/ja4-platform
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
8180f4af0459c2f07f7a442959f2cb5c1e3cda3b
ja4-platform/services/bot-detector/anubis/mv_http_logs.sql
toto 8180f4af04 refactor(anubis): simplify to IP/CIDR + ASN only, remove UA and Country rules 
- Remove UA regex extraction (extract_ua_regex, _extract_ua_from_all/any)
- Remove Country rule collection from parse_bot_policies_inline
- Simplify fetch_rules.py: collect_all_rules returns (ip_rules, asn_rules)
- Remove insert_ua_rules and insert_country_rules functions
- reload_dicts now only reloads dict_anubis_ip + dict_anubis_asn
- Simplify CASE blocks in 04_mv_http_logs.sql, 07_ai_features_view.sql,
  view_ai_features_anubis.sql, mv_http_logs.sql: IP > ASN (was 5-level
  UA+IP > UA > IP > ASN > Country cascade)
- Remove dict_anubis_country + dict_anubis_ua from 03_anubis_tables.sql
  (UA table kept as stub for REGEXP_TREE catch-all compatibility)
- Remove anubis_country_rules table from schema
- Remove Anubis UA and Country tabs from dashboard reflists page
- Remove anubis_ua_rules/country_rules from API reflist queries
- deploy_schema.sql simplified from 339 to 122 lines
- 764 lines removed across 9 files

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-04-09 15:25:33 +02:00

84 lines
6.1 KiB
SQL
Raw Blame History

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: IP/CIDR > ASN (simplified — UA and Country rules removed)
COALESCE(
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', _ip, ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', _asn, ''), ''),
''
) AS anubis_bot_name,
COALESCE(
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'action', _ip, ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_asn', 'action', _asn, ''), ''),
''
) AS anubis_bot_action,
COALESCE(
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'category', _ip, ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_asn', 'category', _asn, ''), ''),
''
) AS anubis_bot_category
FROM ja4_logs.http_logs_raw
Reference in New Issue View Git Blame Copy Permalink