98289ccf04
- 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>
58 lines
2.1 KiB
SQL
58 lines
2.1 KiB
SQL
-- =============================================================================
|
|
-- 02_dictionaries.sql — ASN geo dictionary + bot reference tables
|
|
-- =============================================================================
|
|
|
|
-- -----------------------------------------------------------------------------
|
|
-- IPLocate ASN geo-location dictionary
|
|
-- CSV file must be placed at: /var/lib/clickhouse/user_files/iplocate-ip-to-asn.csv
|
|
-- -----------------------------------------------------------------------------
|
|
DROP DICTIONARY IF EXISTS ja4_processing.dict_iplocate_asn;
|
|
|
|
CREATE DICTIONARY IF NOT EXISTS ja4_processing.dict_iplocate_asn
|
|
(
|
|
network String,
|
|
asn UInt32,
|
|
country_code String,
|
|
name String
|
|
)
|
|
PRIMARY KEY network
|
|
SOURCE(FILE(path '/var/lib/clickhouse/user_files/iplocate-ip-to-asn.csv' format 'CSVWithNames'))
|
|
LAYOUT(IP_TRIE())
|
|
LIFETIME(MIN 3600 MAX 7200);
|
|
|
|
|
|
-- -----------------------------------------------------------------------------
|
|
-- Bot network CIDR reference table (ReplacingMergeTree for upserts)
|
|
-- -----------------------------------------------------------------------------
|
|
CREATE TABLE IF NOT EXISTS ja4_processing.ref_bot_networks
|
|
(
|
|
network String,
|
|
bot_name LowCardinality(String),
|
|
is_legitimate UInt8,
|
|
last_update DateTime
|
|
)
|
|
ENGINE = ReplacingMergeTree(last_update)
|
|
ORDER BY (network, bot_name);
|
|
|
|
|
|
-- -----------------------------------------------------------------------------
|
|
-- Bot IP flat table (CSV file engine)
|
|
-- CSV file must be placed at: /var/lib/clickhouse/user_files/bot_ip.csv
|
|
-- -----------------------------------------------------------------------------
|
|
CREATE TABLE IF NOT EXISTS ja4_processing.bot_ip
|
|
(
|
|
ip String
|
|
)
|
|
ENGINE = File(CSV, 'bot_ip.csv');
|
|
|
|
|
|
-- -----------------------------------------------------------------------------
|
|
-- Bot JA4 flat table (CSV file engine)
|
|
-- CSV file must be placed at: /var/lib/clickhouse/user_files/bot_ja4.csv
|
|
-- -----------------------------------------------------------------------------
|
|
CREATE TABLE IF NOT EXISTS ja4_processing.bot_ja4
|
|
(
|
|
ja4 String
|
|
)
|
|
ENGINE = File(CSV, 'bot_ja4.csv');
|