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:
@ -26,7 +26,7 @@
|
||||
-- Quand l'UA correspond à enfant ET parent, c'est le nom de l'enfant qui
|
||||
-- est retourné (l'enfant hérite ET surcharge les attributs du parent).
|
||||
-- ----------------------------------------------------------------------------
|
||||
CREATE TABLE IF NOT EXISTS mabase_prod.anubis_ua_rules
|
||||
CREATE TABLE IF NOT EXISTS ja4_processing.anubis_ua_rules
|
||||
(
|
||||
id UInt64,
|
||||
parent_id UInt64,
|
||||
@ -46,7 +46,7 @@ ORDER BY id;
|
||||
-- has_ua : 1 si la règle possède aussi une regex UA (croisement nécessaire)
|
||||
-- category : catégorie Anubis (bots, crawlers, clients, policies…)
|
||||
-- ----------------------------------------------------------------------------
|
||||
CREATE TABLE IF NOT EXISTS mabase_prod.anubis_ip_rules
|
||||
CREATE TABLE IF NOT EXISTS ja4_processing.anubis_ip_rules
|
||||
(
|
||||
prefix String,
|
||||
bot_name LowCardinality(String),
|
||||
@ -60,31 +60,31 @@ ORDER BY prefix;
|
||||
|
||||
-- ----------------------------------------------------------------------------
|
||||
-- 3. DICTIONNAIRE UA — REGEXP_TREE
|
||||
-- dictGet('mabase_prod.dict_anubis_ua', 'bot_name', header_user_agent)
|
||||
-- dictGet('ja4_processing.dict_anubis_ua', 'bot_name', header_user_agent)
|
||||
--
|
||||
-- Le PRIMARY KEY est 'regexp' (String) — requis par ClickHouse 26.x.
|
||||
-- Connexion interne (HOST localhost PORT 9000) pour éviter deadlock HTTP.
|
||||
-- Remplacer 'admin' et le mot de passe par les credentials ClickHouse.
|
||||
-- ----------------------------------------------------------------------------
|
||||
DROP DICTIONARY IF EXISTS mabase_prod.dict_anubis_ua;
|
||||
CREATE DICTIONARY mabase_prod.dict_anubis_ua
|
||||
DROP DICTIONARY IF EXISTS ja4_processing.dict_anubis_ua;
|
||||
CREATE DICTIONARY ja4_processing.dict_anubis_ua
|
||||
(
|
||||
regexp String,
|
||||
bot_name String,
|
||||
action String
|
||||
)
|
||||
PRIMARY KEY regexp
|
||||
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'mabase_prod' TABLE 'anubis_ua_rules'))
|
||||
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'ja4_processing' TABLE 'anubis_ua_rules'))
|
||||
LAYOUT(REGEXP_TREE)
|
||||
LIFETIME(MIN 300 MAX 600);
|
||||
|
||||
-- ----------------------------------------------------------------------------
|
||||
-- 4. DICTIONNAIRE IP — IP_TRIE
|
||||
-- dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', toIPv6(src_ip), '')
|
||||
-- dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', toIPv6(src_ip), '')
|
||||
-- Connexion interne (HOST localhost PORT 9000) — même raison que dict_anubis_ua.
|
||||
-- ----------------------------------------------------------------------------
|
||||
DROP DICTIONARY IF EXISTS mabase_prod.dict_anubis_ip;
|
||||
CREATE DICTIONARY mabase_prod.dict_anubis_ip
|
||||
DROP DICTIONARY IF EXISTS ja4_processing.dict_anubis_ip;
|
||||
CREATE DICTIONARY ja4_processing.dict_anubis_ip
|
||||
(
|
||||
prefix String,
|
||||
bot_name String,
|
||||
@ -94,7 +94,7 @@ CREATE DICTIONARY mabase_prod.dict_anubis_ip
|
||||
category String
|
||||
)
|
||||
PRIMARY KEY prefix
|
||||
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'mabase_prod' TABLE 'anubis_ip_rules'))
|
||||
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'ja4_processing' TABLE 'anubis_ip_rules'))
|
||||
LAYOUT(IP_TRIE())
|
||||
LIFETIME(MIN 300 MAX 600);
|
||||
|
||||
@ -102,7 +102,7 @@ LIFETIME(MIN 300 MAX 600);
|
||||
-- 5. TABLE SOURCE — règles ASN (pour dictionnaire Flat)
|
||||
-- Alimentée par botPolicies.yaml via fetch_rules.py → insert_asn_rules()
|
||||
-- ----------------------------------------------------------------------------
|
||||
CREATE TABLE IF NOT EXISTS mabase_prod.anubis_asn_rules
|
||||
CREATE TABLE IF NOT EXISTS ja4_processing.anubis_asn_rules
|
||||
(
|
||||
asn UInt32,
|
||||
bot_name LowCardinality(String),
|
||||
@ -116,7 +116,7 @@ ORDER BY asn;
|
||||
-- 6. TABLE SOURCE — règles pays ISO-3166 (pour dictionnaire Flat)
|
||||
-- Alimentée par botPolicies.yaml via fetch_rules.py → insert_country_rules()
|
||||
-- ----------------------------------------------------------------------------
|
||||
CREATE TABLE IF NOT EXISTS mabase_prod.anubis_country_rules
|
||||
CREATE TABLE IF NOT EXISTS ja4_processing.anubis_country_rules
|
||||
(
|
||||
country_code LowCardinality(String),
|
||||
bot_name LowCardinality(String),
|
||||
@ -128,10 +128,10 @@ ORDER BY country_code;
|
||||
|
||||
-- ----------------------------------------------------------------------------
|
||||
-- 7. DICTIONNAIRE ASN — Flat
|
||||
-- dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', src_asn, '')
|
||||
-- dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', src_asn, '')
|
||||
-- ----------------------------------------------------------------------------
|
||||
DROP DICTIONARY IF EXISTS mabase_prod.dict_anubis_asn;
|
||||
CREATE DICTIONARY mabase_prod.dict_anubis_asn
|
||||
DROP DICTIONARY IF EXISTS ja4_processing.dict_anubis_asn;
|
||||
CREATE DICTIONARY ja4_processing.dict_anubis_asn
|
||||
(
|
||||
asn UInt32,
|
||||
bot_name String,
|
||||
@ -139,16 +139,16 @@ CREATE DICTIONARY mabase_prod.dict_anubis_asn
|
||||
category String
|
||||
)
|
||||
PRIMARY KEY asn
|
||||
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'mabase_prod' TABLE 'anubis_asn_rules'))
|
||||
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'ja4_processing' TABLE 'anubis_asn_rules'))
|
||||
LAYOUT(FLAT())
|
||||
LIFETIME(MIN 300 MAX 600);
|
||||
|
||||
-- ----------------------------------------------------------------------------
|
||||
-- 8. DICTIONNAIRE PAYS — Flat
|
||||
-- dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', src_country_code, '')
|
||||
-- dictGetOrDefault('ja4_processing.dict_anubis_country', 'bot_name', src_country_code, '')
|
||||
-- ----------------------------------------------------------------------------
|
||||
DROP DICTIONARY IF EXISTS mabase_prod.dict_anubis_country;
|
||||
CREATE DICTIONARY mabase_prod.dict_anubis_country
|
||||
DROP DICTIONARY IF EXISTS ja4_processing.dict_anubis_country;
|
||||
CREATE DICTIONARY ja4_processing.dict_anubis_country
|
||||
(
|
||||
country_code String,
|
||||
bot_name String,
|
||||
@ -156,7 +156,7 @@ CREATE DICTIONARY mabase_prod.dict_anubis_country
|
||||
category String
|
||||
)
|
||||
PRIMARY KEY country_code
|
||||
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'mabase_prod' TABLE 'anubis_country_rules'))
|
||||
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'ja4_processing' TABLE 'anubis_country_rules'))
|
||||
LAYOUT(FLAT())
|
||||
LIFETIME(MIN 300 MAX 600);
|
||||
|
||||
@ -164,7 +164,7 @@ LIFETIME(MIN 300 MAX 600);
|
||||
-- 9. AJOUT DES COLONNES ANUBIS dans http_logs
|
||||
-- Idempotent : ne plante pas si déjà présentes
|
||||
-- ----------------------------------------------------------------------------
|
||||
ALTER TABLE mabase_prod.http_logs
|
||||
ALTER TABLE ja4_logs.http_logs
|
||||
ADD COLUMN IF NOT EXISTS anubis_bot_name LowCardinality(String) DEFAULT '',
|
||||
ADD COLUMN IF NOT EXISTS anubis_bot_action LowCardinality(String) DEFAULT '',
|
||||
ADD COLUMN IF NOT EXISTS anubis_bot_category LowCardinality(String) DEFAULT '';
|
||||
@ -175,10 +175,10 @@ ALTER TABLE mabase_prod.http_logs
|
||||
-- 1. UA regex (plus informatif — identifie le bot précis)
|
||||
-- 2. IP/CIDR (fallback — identifie le réseau cloud)
|
||||
-- ----------------------------------------------------------------------------
|
||||
DROP VIEW IF EXISTS mabase_prod.mv_http_logs;
|
||||
DROP VIEW IF EXISTS ja4_logs.mv_http_logs;
|
||||
|
||||
CREATE MATERIALIZED VIEW mabase_prod.mv_http_logs
|
||||
TO mabase_prod.http_logs
|
||||
CREATE MATERIALIZED VIEW ja4_logs.mv_http_logs
|
||||
TO ja4_logs.http_logs
|
||||
(
|
||||
`time` DateTime,
|
||||
`log_date` Date,
|
||||
@ -241,13 +241,13 @@ AS SELECT
|
||||
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,
|
||||
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'asn', toIPv6(src_ip), toUInt32(0)) AS src_asn,
|
||||
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'country_code', toIPv6(src_ip), '') AS src_country_code,
|
||||
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'asn', toIPv6(src_ip), toUInt32(0)) AS src_asn,
|
||||
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'country_code', toIPv6(src_ip), '') 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('mabase_prod.dict_iplocate_asn', 'name', toIPv6(src_ip), '') AS src_as_name,
|
||||
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'org', toIPv6(src_ip), '') AS src_org,
|
||||
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'domain', toIPv6(src_ip), '') AS src_domain,
|
||||
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'name', toIPv6(src_ip), '') AS src_as_name,
|
||||
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'org', toIPv6(src_ip), '') AS src_org,
|
||||
dictGetOrDefault('ja4_processing.dict_iplocate_asn', 'domain', toIPv6(src_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,
|
||||
@ -293,20 +293,20 @@ AS SELECT
|
||||
-- ── Enrichissement Anubis ────────────────────────────────────────────────
|
||||
-- Priorité : UA regex > IP/CIDR (UA identifie précisément le bot)
|
||||
COALESCE(
|
||||
nullIf(dictGet('mabase_prod.dict_anubis_ua', 'bot_name',
|
||||
nullIf(dictGet('ja4_processing.dict_anubis_ua', 'bot_name',
|
||||
coalesce(JSONExtractString(raw_json, 'header_User-Agent'), '')), ''),
|
||||
nullIf(dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name',
|
||||
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name',
|
||||
toIPv6(toIPv4(coalesce(JSONExtractString(raw_json, 'src_ip'), '0.0.0.0'))), ''), ''),
|
||||
''
|
||||
) AS anubis_bot_name,
|
||||
COALESCE(
|
||||
nullIf(dictGet('mabase_prod.dict_anubis_ua', 'action',
|
||||
nullIf(dictGet('ja4_processing.dict_anubis_ua', 'action',
|
||||
coalesce(JSONExtractString(raw_json, 'header_User-Agent'), '')), ''),
|
||||
nullIf(dictGetOrDefault('mabase_prod.dict_anubis_ip', 'action',
|
||||
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'action',
|
||||
toIPv6(toIPv4(coalesce(JSONExtractString(raw_json, 'src_ip'), '0.0.0.0'))), ''), ''),
|
||||
''
|
||||
) AS anubis_bot_action
|
||||
FROM mabase_prod.http_logs_raw;
|
||||
FROM ja4_logs.http_logs_raw;
|
||||
|
||||
-- ============================================================================
|
||||
-- INTÉGRATION ML — Propagation Anubis vers le pipeline bot_detector
|
||||
@ -315,7 +315,7 @@ FROM mabase_prod.http_logs_raw;
|
||||
-- ----------------------------------------------------------------------------
|
||||
-- 11. COLONNES ANUBIS dans ml_detected_anomalies
|
||||
-- ----------------------------------------------------------------------------
|
||||
ALTER TABLE mabase_prod.ml_detected_anomalies
|
||||
ALTER TABLE ja4_processing.ml_detected_anomalies
|
||||
ADD COLUMN IF NOT EXISTS anubis_bot_name LowCardinality(String) DEFAULT '',
|
||||
ADD COLUMN IF NOT EXISTS anubis_bot_action LowCardinality(String) DEFAULT '',
|
||||
ADD COLUMN IF NOT EXISTS anubis_bot_category LowCardinality(String) DEFAULT '';
|
||||
@ -323,7 +323,7 @@ ALTER TABLE mabase_prod.ml_detected_anomalies
|
||||
-- ----------------------------------------------------------------------------
|
||||
-- 12. COLONNES ANUBIS dans ml_all_scores
|
||||
-- ----------------------------------------------------------------------------
|
||||
ALTER TABLE mabase_prod.ml_all_scores
|
||||
ALTER TABLE ja4_processing.ml_all_scores
|
||||
ADD COLUMN IF NOT EXISTS anubis_bot_name LowCardinality(String) DEFAULT '',
|
||||
ADD COLUMN IF NOT EXISTS anubis_bot_action LowCardinality(String) DEFAULT '',
|
||||
ADD COLUMN IF NOT EXISTS anubis_bot_category LowCardinality(String) DEFAULT '';
|
||||
|
||||
@ -13,7 +13,7 @@ Usage (depuis le container dashboard_web) :
|
||||
python /tmp/fetch_rules.py
|
||||
|
||||
Variables d'environnement :
|
||||
CLICKHOUSE_HOST, CLICKHOUSE_DB, CLICKHOUSE_USER, CLICKHOUSE_PASSWORD
|
||||
CLICKHOUSE_HOST, CLICKHOUSE_DB, CLICKHOUSE_DB_PROCESSING, CLICKHOUSE_USER, CLICKHOUSE_PASSWORD
|
||||
"""
|
||||
|
||||
import json
|
||||
@ -336,17 +336,20 @@ def collect_all_rules() -> tuple[list, list, list, list]:
|
||||
def get_ch_client():
|
||||
return clickhouse_connect.get_client(
|
||||
host=os.environ.get("CLICKHOUSE_HOST", "clickhouse"),
|
||||
database=os.environ.get("CLICKHOUSE_DB", "mabase_prod"),
|
||||
database=os.environ.get("CLICKHOUSE_DB_PROCESSING", os.environ.get("CLICKHOUSE_DB", "ja4_processing")),
|
||||
username=os.environ.get("CLICKHOUSE_USER", "admin"),
|
||||
password=os.environ.get("CLICKHOUSE_PASSWORD", ""),
|
||||
)
|
||||
|
||||
|
||||
DB_PROC = os.environ.get("CLICKHOUSE_DB_PROCESSING", os.environ.get("CLICKHOUSE_DB", "ja4_processing"))
|
||||
|
||||
|
||||
def insert_ua_rules(client, rules: list[dict]) -> None:
|
||||
if not rules:
|
||||
print("[INFO] Aucune règle UA.")
|
||||
return
|
||||
client.command("TRUNCATE TABLE mabase_prod.anubis_ua_rules")
|
||||
client.command(f"TRUNCATE TABLE {DB_PROC}.anubis_ua_rules")
|
||||
# REGEXP_TREE format : id, parent_id, regexp, keys[], values[]
|
||||
# keys = ['bot_name', 'action', 'has_ip', 'rule_id', 'category']
|
||||
data = [
|
||||
@ -357,7 +360,7 @@ def insert_ua_rules(client, rules: list[dict]) -> None:
|
||||
]
|
||||
for r in rules
|
||||
]
|
||||
client.insert("mabase_prod.anubis_ua_rules", data,
|
||||
client.insert(f"{DB_PROC}.anubis_ua_rules", data,
|
||||
column_names=["id", "parent_id", "regexp", "keys", "values"])
|
||||
print(f"[OK] {len(rules)} règles UA insérées.")
|
||||
|
||||
@ -366,13 +369,13 @@ def insert_ip_rules(client, rules: list[dict]) -> None:
|
||||
if not rules:
|
||||
print("[INFO] Aucune règle IP.")
|
||||
return
|
||||
client.command("TRUNCATE TABLE mabase_prod.anubis_ip_rules")
|
||||
client.command(f"TRUNCATE TABLE {DB_PROC}.anubis_ip_rules")
|
||||
data = [
|
||||
[r["prefix"], r["bot_name"], r["action"],
|
||||
r["rule_id"], r["has_ua"], r["category"]]
|
||||
for r in rules
|
||||
]
|
||||
client.insert("mabase_prod.anubis_ip_rules", data,
|
||||
client.insert(f"{DB_PROC}.anubis_ip_rules", data,
|
||||
column_names=["prefix", "bot_name", "action", "rule_id", "has_ua", "category"])
|
||||
print(f"[OK] {len(rules)} règles IP insérées.")
|
||||
|
||||
@ -381,9 +384,9 @@ def insert_asn_rules(client, rules: list[dict]) -> None:
|
||||
if not rules:
|
||||
print("[INFO] Aucune règle ASN.")
|
||||
return
|
||||
client.command("TRUNCATE TABLE mabase_prod.anubis_asn_rules")
|
||||
client.command(f"TRUNCATE TABLE {DB_PROC}.anubis_asn_rules")
|
||||
data = [[r["asn"], r["bot_name"], r["action"], r["category"]] for r in rules]
|
||||
client.insert("mabase_prod.anubis_asn_rules", data,
|
||||
client.insert(f"{DB_PROC}.anubis_asn_rules", data,
|
||||
column_names=["asn", "bot_name", "action", "category"])
|
||||
print(f"[OK] {len(rules)} règles ASN insérées.")
|
||||
|
||||
@ -392,19 +395,19 @@ def insert_country_rules(client, rules: list[dict]) -> None:
|
||||
if not rules:
|
||||
print("[INFO] Aucune règle pays.")
|
||||
return
|
||||
client.command("TRUNCATE TABLE mabase_prod.anubis_country_rules")
|
||||
client.command(f"TRUNCATE TABLE {DB_PROC}.anubis_country_rules")
|
||||
data = [[r["country_code"], r["bot_name"], r["action"], r["category"]] for r in rules]
|
||||
client.insert("mabase_prod.anubis_country_rules", data,
|
||||
client.insert(f"{DB_PROC}.anubis_country_rules", data,
|
||||
column_names=["country_code", "bot_name", "action", "category"])
|
||||
print(f"[OK] {len(rules)} règles pays insérées.")
|
||||
|
||||
|
||||
def reload_dicts(client) -> None:
|
||||
dicts = [
|
||||
"mabase_prod.dict_anubis_ua",
|
||||
"mabase_prod.dict_anubis_ip",
|
||||
"mabase_prod.dict_anubis_asn",
|
||||
"mabase_prod.dict_anubis_country",
|
||||
f"{DB_PROC}.dict_anubis_ua",
|
||||
f"{DB_PROC}.dict_anubis_ip",
|
||||
f"{DB_PROC}.dict_anubis_asn",
|
||||
f"{DB_PROC}.dict_anubis_country",
|
||||
]
|
||||
for d in dicts:
|
||||
try:
|
||||
|
||||
@ -1,11 +1,11 @@
|
||||
CREATE MATERIALIZED VIEW mabase_prod.mv_http_logs
|
||||
TO mabase_prod.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('mabase_prod.dict_iplocate_asn', 'asn', _ip, toUInt32(0))) AS _asn,
|
||||
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'country_code', _ip, '') AS _cc
|
||||
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,
|
||||
@ -15,9 +15,9 @@ SELECT
|
||||
_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('mabase_prod.dict_iplocate_asn', 'name', _ip, '') AS src_as_name,
|
||||
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'org', _ip, '') AS src_org,
|
||||
dictGetOrDefault('mabase_prod.dict_iplocate_asn', 'domain', _ip, '') AS src_domain,
|
||||
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,
|
||||
@ -64,63 +64,63 @@ SELECT
|
||||
-- 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('mabase_prod.dict_anubis_ua', 'has_ip', _ua) = '1'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('mabase_prod.dict_anubis_ua', 'rule_id', _ua))
|
||||
= dictGetOrDefault('mabase_prod.dict_anubis_ip', 'rule_id', _ip, toUInt64(0))
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua)
|
||||
WHEN dictGet('mabase_prod.dict_anubis_ua', 'has_ip', _ua) = '0'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua)
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'has_ua', _ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', _asn, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', _asn, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', _cc, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', _cc, '')
|
||||
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('mabase_prod.dict_anubis_ua', 'has_ip', _ua) = '1'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('mabase_prod.dict_anubis_ua', 'rule_id', _ua))
|
||||
= dictGetOrDefault('mabase_prod.dict_anubis_ip', 'rule_id', _ip, toUInt64(0))
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'action', _ua)
|
||||
WHEN dictGet('mabase_prod.dict_anubis_ua', 'has_ip', _ua) = '0'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'action', _ua)
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'has_ua', _ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'action', _ip, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', _asn, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'action', _asn, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', _cc, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'action', _cc, '')
|
||||
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('mabase_prod.dict_anubis_ua', 'has_ip', _ua) = '1'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('mabase_prod.dict_anubis_ua', 'rule_id', _ua))
|
||||
= dictGetOrDefault('mabase_prod.dict_anubis_ip', 'rule_id', _ip, toUInt64(0))
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'category', _ua)
|
||||
WHEN dictGet('mabase_prod.dict_anubis_ua', 'has_ip', _ua) = '0'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', _ua) != ''
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'category', _ua)
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'has_ua', _ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', _ip, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'category', _ip, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', _asn, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'category', _asn, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', _cc, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'category', _cc, '')
|
||||
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 mabase_prod.http_logs_raw
|
||||
FROM ja4_logs.http_logs_raw
|
||||
|
||||
@ -1,73 +1,73 @@
|
||||
CREATE OR REPLACE VIEW mabase_prod.view_ai_features_1h AS
|
||||
CREATE OR REPLACE VIEW ja4_processing.view_ai_features_1h AS
|
||||
WITH base_data AS (
|
||||
SELECT
|
||||
a.window_start, a.src_ip, a.ja4, a.host,
|
||||
toString(a.src_asn) AS asn_number,
|
||||
a.src_as_name AS asn_org, a.src_org AS asn_detail, a.src_domain AS asn_domain,
|
||||
a.src_country_code AS country_code,
|
||||
dictGetOrDefault('mabase_prod.dict_asn_reputation', 'label', toUInt64(a.src_asn), 'unknown') AS asn_label,
|
||||
dictGetOrDefault('ja4_processing.dict_asn_reputation', 'label', toUInt64(a.src_asn), 'unknown') AS asn_label,
|
||||
-- Bot connu via JA4/IP (dictionnaires existants)
|
||||
COALESCE(
|
||||
nullIf(dictGetOrDefault('mabase_prod.dict_bot_ip', 'bot_name', a.src_ip, ''), ''),
|
||||
nullIf(dictGetOrDefault('mabase_prod.dict_bot_ja4', 'bot_name', tuple(a.ja4), ''), ''),
|
||||
nullIf(dictGetOrDefault('ja4_processing.dict_bot_ip', 'bot_name', a.src_ip, ''), ''),
|
||||
nullIf(dictGetOrDefault('ja4_processing.dict_bot_ja4', 'bot_name', tuple(a.ja4), ''), ''),
|
||||
''
|
||||
) AS bot_name,
|
||||
-- Anubis : logique combinée UA+IP (même rule_id) > UA seul > IP seul > ASN > Pays
|
||||
CASE
|
||||
WHEN dictGet('mabase_prod.dict_anubis_ua', 'has_ip', a.first_ua) = '1'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', a.first_ua) != ''
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', a.src_ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('mabase_prod.dict_anubis_ua', 'rule_id', a.first_ua))
|
||||
= dictGetOrDefault('mabase_prod.dict_anubis_ip', 'rule_id', a.src_ip, toUInt64(0))
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'bot_name', a.first_ua)
|
||||
WHEN dictGet('mabase_prod.dict_anubis_ua', 'has_ip', a.first_ua) = '0'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', a.first_ua) != ''
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'bot_name', a.first_ua)
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'has_ua', a.src_ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', a.src_ip, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', a.src_ip, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', toUInt32(a.src_asn), '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', toUInt32(a.src_asn), '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', a.src_country_code, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', a.src_country_code, '')
|
||||
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('mabase_prod.dict_anubis_ua', 'has_ip', a.first_ua) = '1'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', a.first_ua) != ''
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', a.src_ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('mabase_prod.dict_anubis_ua', 'rule_id', a.first_ua))
|
||||
= dictGetOrDefault('mabase_prod.dict_anubis_ip', 'rule_id', a.src_ip, toUInt64(0))
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'action', a.first_ua)
|
||||
WHEN dictGet('mabase_prod.dict_anubis_ua', 'has_ip', a.first_ua) = '0'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', a.first_ua) != ''
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'action', a.first_ua)
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'has_ua', a.src_ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', a.src_ip, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'action', a.src_ip, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', toUInt32(a.src_asn), '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'action', toUInt32(a.src_asn), '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', a.src_country_code, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'action', a.src_country_code, '')
|
||||
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('mabase_prod.dict_anubis_ua', 'has_ip', a.first_ua) = '1'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', a.first_ua) != ''
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', a.src_ip, '') != ''
|
||||
AND toUInt64OrZero(dictGet('mabase_prod.dict_anubis_ua', 'rule_id', a.first_ua))
|
||||
= dictGetOrDefault('mabase_prod.dict_anubis_ip', 'rule_id', a.src_ip, toUInt64(0))
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'category', a.first_ua)
|
||||
WHEN dictGet('mabase_prod.dict_anubis_ua', 'has_ip', a.first_ua) = '0'
|
||||
AND dictGet('mabase_prod.dict_anubis_ua', 'bot_name', a.first_ua) != ''
|
||||
THEN dictGet('mabase_prod.dict_anubis_ua', 'category', a.first_ua)
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'has_ua', a.src_ip, toUInt8(0)) = 0
|
||||
AND dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', a.src_ip, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_ip', 'category', a.src_ip, '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', toUInt32(a.src_asn), '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_asn', 'category', toUInt32(a.src_asn), '')
|
||||
WHEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', a.src_country_code, '') != ''
|
||||
THEN dictGetOrDefault('mabase_prod.dict_anubis_country', 'category', a.src_country_code, '')
|
||||
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,
|
||||
a.hits AS hits,
|
||||
@ -160,7 +160,7 @@ WITH base_data AS (
|
||||
sum(count_correlated) AS count_correlated_val,
|
||||
sum(count_no_accept_enc) AS count_no_accept_enc_val,
|
||||
sum(count_http_scheme) AS count_http_scheme_val
|
||||
FROM mabase_prod.agg_host_ip_ja4_1h
|
||||
FROM ja4_processing.agg_host_ip_ja4_1h
|
||||
WHERE window_start >= now() - INTERVAL 24 HOUR
|
||||
GROUP BY window_start, src_ip, ja4, host, src_asn
|
||||
) a
|
||||
@ -171,7 +171,7 @@ WITH base_data AS (
|
||||
max(has_cookie) AS has_cookie, max(has_referer) AS has_referer,
|
||||
max(modern_browser_score) AS modern_browser_score, max(ua_ch_mismatch) AS ua_ch_mismatch,
|
||||
any(sec_fetch_mode) AS sec_fetch_mode, any(sec_fetch_dest) AS sec_fetch_dest
|
||||
FROM mabase_prod.agg_header_fingerprint_1h
|
||||
FROM ja4_processing.agg_header_fingerprint_1h
|
||||
WHERE window_start >= now() - INTERVAL 24 HOUR
|
||||
GROUP BY window_start, src_ip
|
||||
) h ON a.src_ip = h.src_ip AND a.window_start = h.window_start
|
||||
|
||||
Reference in New Issue
Block a user