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>
This commit is contained in:
@ -18,64 +18,22 @@ WITH base_data AS (
|
||||
''
|
||||
) AS bot_name,
|
||||
dictGetOrDefault('ja4_processing.dict_browser_ja4', 'browser_family', tuple(a.ja4), '') AS browser_family,
|
||||
-- Anubis: combined UA+IP priority logic > UA only > IP only > ASN > Country
|
||||
CASE
|
||||
WHEN dictGet('ja4_processing.dict_anubis_ua', 'has_ip', a.first_ua) = '1'
|
||||
AND dictGet('ja4_processing.dict_anubis_ua', 'bot_name', a.first_ua) != ''
|
||||
AND dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', a.src_ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('ja4_processing.dict_anubis_ua', 'rule_id', a.first_ua))
|
||||
= dictGetOrDefault('ja4_processing.dict_anubis_ip', 'rule_id', a.src_ip, toUInt64(0))
|
||||
THEN dictGet('ja4_processing.dict_anubis_ua', 'bot_name', a.first_ua)
|
||||
WHEN dictGet('ja4_processing.dict_anubis_ua', 'has_ip', a.first_ua) = '0'
|
||||
AND dictGet('ja4_processing.dict_anubis_ua', 'bot_name', a.first_ua) != ''
|
||||
THEN dictGet('ja4_processing.dict_anubis_ua', 'bot_name', a.first_ua)
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_ip', 'has_ua', a.src_ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', a.src_ip, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', a.src_ip, '')
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', toUInt32(a.src_asn), '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', toUInt32(a.src_asn), '')
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_country', 'bot_name', a.src_country_code, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_country', 'bot_name', a.src_country_code, '')
|
||||
ELSE ''
|
||||
END AS anubis_bot_name,
|
||||
CASE
|
||||
WHEN dictGet('ja4_processing.dict_anubis_ua', 'has_ip', a.first_ua) = '1'
|
||||
AND dictGet('ja4_processing.dict_anubis_ua', 'bot_name', a.first_ua) != ''
|
||||
AND dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', a.src_ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('ja4_processing.dict_anubis_ua', 'rule_id', a.first_ua))
|
||||
= dictGetOrDefault('ja4_processing.dict_anubis_ip', 'rule_id', a.src_ip, toUInt64(0))
|
||||
THEN dictGet('ja4_processing.dict_anubis_ua', 'action', a.first_ua)
|
||||
WHEN dictGet('ja4_processing.dict_anubis_ua', 'has_ip', a.first_ua) = '0'
|
||||
AND dictGet('ja4_processing.dict_anubis_ua', 'bot_name', a.first_ua) != ''
|
||||
THEN dictGet('ja4_processing.dict_anubis_ua', 'action', a.first_ua)
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_ip', 'has_ua', a.src_ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', a.src_ip, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_ip', 'action', a.src_ip, '')
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', toUInt32(a.src_asn), '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_asn', 'action', toUInt32(a.src_asn), '')
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_country', 'bot_name', a.src_country_code, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_country', 'action', a.src_country_code, '')
|
||||
ELSE ''
|
||||
END AS anubis_bot_action,
|
||||
CASE
|
||||
WHEN dictGet('ja4_processing.dict_anubis_ua', 'has_ip', a.first_ua) = '1'
|
||||
AND dictGet('ja4_processing.dict_anubis_ua', 'bot_name', a.first_ua) != ''
|
||||
AND dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', a.src_ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('ja4_processing.dict_anubis_ua', 'rule_id', a.first_ua))
|
||||
= dictGetOrDefault('ja4_processing.dict_anubis_ip', 'rule_id', a.src_ip, toUInt64(0))
|
||||
THEN dictGet('ja4_processing.dict_anubis_ua', 'category', a.first_ua)
|
||||
WHEN dictGet('ja4_processing.dict_anubis_ua', 'has_ip', a.first_ua) = '0'
|
||||
AND dictGet('ja4_processing.dict_anubis_ua', 'bot_name', a.first_ua) != ''
|
||||
THEN dictGet('ja4_processing.dict_anubis_ua', 'category', a.first_ua)
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_ip', 'has_ua', a.src_ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', a.src_ip, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_ip', 'category', a.src_ip, '')
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', toUInt32(a.src_asn), '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_asn', 'category', toUInt32(a.src_asn), '')
|
||||
WHEN dictGetOrDefault('ja4_processing.dict_anubis_country', 'bot_name', a.src_country_code, '') != ''
|
||||
THEN dictGetOrDefault('ja4_processing.dict_anubis_country', 'category', a.src_country_code, '')
|
||||
ELSE ''
|
||||
END AS anubis_bot_category,
|
||||
-- Anubis: IP/CIDR > ASN (simplified — UA and Country rules removed)
|
||||
COALESCE(
|
||||
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', a.src_ip, ''), ''),
|
||||
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', toUInt32(a.src_asn), ''), ''),
|
||||
''
|
||||
) AS anubis_bot_name,
|
||||
COALESCE(
|
||||
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'action', a.src_ip, ''), ''),
|
||||
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_asn', 'action', toUInt32(a.src_asn), ''), ''),
|
||||
''
|
||||
) AS anubis_bot_action,
|
||||
COALESCE(
|
||||
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'category', a.src_ip, ''), ''),
|
||||
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_asn', 'category', toUInt32(a.src_asn), ''), ''),
|
||||
''
|
||||
) AS anubis_bot_category,
|
||||
a.hits AS hits,
|
||||
sum(a.hits) OVER (PARTITION BY a.src_ip) AS total_ip_hits,
|
||||
a.correlated AS correlated,
|
||||
|
||||
Reference in New Issue
Block a user