9ea36ad22e
Schema cleanup:
- Remove anubis_ua_rules table stub from 03_anubis_tables.sql
- Remove anubis_ua_rules from bot-detector deploy_schema.sql
- Remove UA seed step from clickhouse-init.sh (no more REGEXP_TREE dependency)
- Drop dict_anubis_ua, dict_anubis_country, anubis_ua_rules, anubis_country_rules
New scripts:
- scripts/init-stack.sh: comprehensive ClickHouse init (13 SQL files + migrations
+ validation + cleanup of obsolete tables). Supports --reset, --import-prod.
- scripts/import-prod-data.sh: imports pre-exported prod data (Native format)
with dynamic date shift (max(time) → now). Supports --shift, --no-truncate.
- scripts/data/prod-export/: directory for cached Native format exports
Makefile targets: init-stack, import-prod-data, init-and-import
Tested: init-stack.sh passes all 13 SQL + 7 critical tables + 7 dicts
import-prod-data.sh: 3M rows in ~37s with auto date shift
Dashboard: 55 routes OK, bot-detector: 36/36 tests pass
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
74 lines
2.7 KiB
SQL
74 lines
2.7 KiB
SQL
-- =============================================================================
|
|
-- 03_anubis_tables.sql — Anubis crawler rule tables and dictionaries
|
|
-- Only IP/CIDR and ASN rules are used. UA and Country have been removed.
|
|
-- =============================================================================
|
|
|
|
-- -----------------------------------------------------------------------------
|
|
-- 1. TABLE SOURCE — IP/CIDR rules (for IP_TRIE dictionary)
|
|
-- Populated by fetch_rules.py from Anubis GitHub data.
|
|
-- -----------------------------------------------------------------------------
|
|
CREATE TABLE IF NOT EXISTS ja4_processing.anubis_ip_rules
|
|
(
|
|
prefix String,
|
|
bot_name LowCardinality(String),
|
|
action LowCardinality(String),
|
|
rule_id UInt64,
|
|
has_ua UInt8,
|
|
category LowCardinality(String)
|
|
)
|
|
ENGINE = ReplacingMergeTree()
|
|
ORDER BY prefix;
|
|
|
|
|
|
-- -----------------------------------------------------------------------------
|
|
-- 3. TABLE SOURCE — ASN rules (for Flat dictionary)
|
|
-- Populated by fetch_rules.py from botPolicies.yaml.
|
|
-- -----------------------------------------------------------------------------
|
|
CREATE TABLE IF NOT EXISTS ja4_processing.anubis_asn_rules
|
|
(
|
|
asn UInt32,
|
|
bot_name LowCardinality(String),
|
|
action LowCardinality(String),
|
|
category LowCardinality(String)
|
|
)
|
|
ENGINE = ReplacingMergeTree()
|
|
ORDER BY asn;
|
|
|
|
|
|
-- -----------------------------------------------------------------------------
|
|
-- 4. DICTIONARY — IP IP_TRIE (active)
|
|
-- dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', toIPv6(src_ip), '')
|
|
-- -----------------------------------------------------------------------------
|
|
DROP DICTIONARY IF EXISTS ja4_processing.dict_anubis_ip;
|
|
CREATE DICTIONARY ja4_processing.dict_anubis_ip
|
|
(
|
|
prefix String,
|
|
bot_name String,
|
|
action String,
|
|
rule_id UInt64,
|
|
has_ua UInt8,
|
|
category String
|
|
)
|
|
PRIMARY KEY prefix
|
|
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);
|
|
|
|
|
|
-- -----------------------------------------------------------------------------
|
|
-- 5. DICTIONARY — ASN Flat (active)
|
|
-- dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', src_asn, '')
|
|
-- -----------------------------------------------------------------------------
|
|
DROP DICTIONARY IF EXISTS ja4_processing.dict_anubis_asn;
|
|
CREATE DICTIONARY ja4_processing.dict_anubis_asn
|
|
(
|
|
asn UInt32,
|
|
bot_name String,
|
|
action String,
|
|
category String
|
|
)
|
|
PRIMARY KEY asn
|
|
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);
|