feat: ja4-platform monorepo — 5 services unified, tests & RPM builds standardized
Services: - ja4sentinel: TLS/JA4 fingerprint capture daemon (Go, libpcap) - logcorrelator: JA4 log correlation engine (Go, ClickHouse) - mod_reqin_log: Apache module (C, JSON request logging) - bot_detector: ML bot detection pipeline (Python) - dashboard: FastAPI/Streamlit analytics UI (Python) Shared libraries: - shared/go/ja4common: logger, config, shutdown, ipfilter (Go module) - shared/python/ja4_common: ClickHouseClient, ClickHouseSettings (Python package) - shared/clickhouse/: canonical SQL migrations (10 files) Build & packaging: - Unified 3-stage Dockerfile.package for Go RPMs (el8/el9/el10) - go.work workspace linking sentinel, correlator, ja4common - Makefile with test-all, build-all, rpm-* targets Fixes applied: - go.work: 1.21 → 1.24.6 (required by sentinel) - correlator Dockerfiles: golang:1.21 → golang:1.24 - replace directives in go.mod for ja4common local path - pyproject.toml: setuptools.backends → setuptools.build_meta - Removed static libpcap linking (unavailable on Rocky 9) - Fixed data races in output/writers_test.go (sync.Mutex + atomic.Int32) - Rewrote corrupted test files (logger_test.go × 2) Test coverage: - correlator: 67.1% total (unixsocket 80.5%, config 91.7%, app 83.3%, multi 87.7%, stdout 100%) - sentinel: all 10 packages pass (api, capture, config, fingerprint, ipfilter, logging, output, tlsparse) Documentation: - README.md + docs/ (architecture, development, 5 services, shared libs, DB schema & migrations) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
toto
139
shared/clickhouse/03_anubis_tables.sql
Normal file
139
shared/clickhouse/03_anubis_tables.sql
Normal file
@ -0,0 +1,139 @@
|
||||
-- =============================================================================
|
||||
-- 03_anubis_tables.sql — Anubis crawler rule tables and dictionaries
|
||||
-- Items 1–8 from bot_detector/anubis/deploy_schema.sql
|
||||
-- =============================================================================
|
||||
|
||||
-- -----------------------------------------------------------------------------
|
||||
-- 1. TABLE SOURCE — User-Agent rules (for REGEXP_TREE dictionary)
|
||||
-- -----------------------------------------------------------------------------
|
||||
CREATE TABLE IF NOT EXISTS mabase_prod.anubis_ua_rules
|
||||
(
|
||||
id UInt64,
|
||||
parent_id UInt64,
|
||||
regexp String,
|
||||
keys Array(String),
|
||||
values Array(String)
|
||||
)
|
||||
ENGINE = ReplacingMergeTree()
|
||||
ORDER BY id;
|
||||
|
||||
|
||||
-- -----------------------------------------------------------------------------
|
||||
-- 2. TABLE SOURCE — IP/CIDR rules (for IP_TRIE dictionary)
|
||||
-- -----------------------------------------------------------------------------
|
||||
CREATE TABLE IF NOT EXISTS mabase_prod.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. DICTIONARY — UA REGEXP_TREE
|
||||
-- dictGet('mabase_prod.dict_anubis_ua', 'bot_name', header_user_agent)
|
||||
-- NOTE: Change 'CHANGE_ME' to the actual ClickHouse admin password before use.
|
||||
-- -----------------------------------------------------------------------------
|
||||
DROP DICTIONARY IF EXISTS mabase_prod.dict_anubis_ua;
|
||||
CREATE DICTIONARY mabase_prod.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'))
|
||||
LAYOUT(REGEXP_TREE)
|
||||
LIFETIME(MIN 300 MAX 600);
|
||||
|
||||
|
||||
-- -----------------------------------------------------------------------------
|
||||
-- 4. DICTIONARY — IP IP_TRIE
|
||||
-- dictGetOrDefault('mabase_prod.dict_anubis_ip', 'bot_name', toIPv6(src_ip), '')
|
||||
-- NOTE: Change 'CHANGE_ME' to the actual ClickHouse admin password before use.
|
||||
-- -----------------------------------------------------------------------------
|
||||
DROP DICTIONARY IF EXISTS mabase_prod.dict_anubis_ip;
|
||||
CREATE DICTIONARY mabase_prod.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 'mabase_prod' TABLE 'anubis_ip_rules'))
|
||||
LAYOUT(IP_TRIE())
|
||||
LIFETIME(MIN 300 MAX 600);
|
||||
|
||||
|
||||
-- -----------------------------------------------------------------------------
|
||||
-- 5. TABLE SOURCE — ASN rules (for Flat dictionary)
|
||||
-- -----------------------------------------------------------------------------
|
||||
CREATE TABLE IF NOT EXISTS mabase_prod.anubis_asn_rules
|
||||
(
|
||||
asn UInt32,
|
||||
bot_name LowCardinality(String),
|
||||
action LowCardinality(String),
|
||||
category LowCardinality(String)
|
||||
)
|
||||
ENGINE = ReplacingMergeTree()
|
||||
ORDER BY asn;
|
||||
|
||||
|
||||
-- -----------------------------------------------------------------------------
|
||||
-- 6. TABLE SOURCE — Country rules (for Flat dictionary)
|
||||
-- -----------------------------------------------------------------------------
|
||||
CREATE TABLE IF NOT EXISTS mabase_prod.anubis_country_rules
|
||||
(
|
||||
country_code LowCardinality(String),
|
||||
bot_name LowCardinality(String),
|
||||
action LowCardinality(String),
|
||||
category LowCardinality(String)
|
||||
)
|
||||
ENGINE = ReplacingMergeTree()
|
||||
ORDER BY country_code;
|
||||
|
||||
|
||||
-- -----------------------------------------------------------------------------
|
||||
-- 7. DICTIONARY — ASN Flat
|
||||
-- dictGetOrDefault('mabase_prod.dict_anubis_asn', 'bot_name', src_asn, '')
|
||||
-- NOTE: Change 'CHANGE_ME' to the actual ClickHouse admin password before use.
|
||||
-- -----------------------------------------------------------------------------
|
||||
DROP DICTIONARY IF EXISTS mabase_prod.dict_anubis_asn;
|
||||
CREATE DICTIONARY mabase_prod.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 'mabase_prod' TABLE 'anubis_asn_rules'))
|
||||
LAYOUT(FLAT())
|
||||
LIFETIME(MIN 300 MAX 600);
|
||||
|
||||
|
||||
-- -----------------------------------------------------------------------------
|
||||
-- 8. DICTIONARY — Country Flat
|
||||
-- dictGetOrDefault('mabase_prod.dict_anubis_country', 'bot_name', src_country_code, '')
|
||||
-- NOTE: Change 'CHANGE_ME' to the actual ClickHouse admin password before use.
|
||||
-- -----------------------------------------------------------------------------
|
||||
DROP DICTIONARY IF EXISTS mabase_prod.dict_anubis_country;
|
||||
CREATE DICTIONARY mabase_prod.dict_anubis_country
|
||||
(
|
||||
country_code String,
|
||||
bot_name String,
|
||||
action String,
|
||||
category String
|
||||
)
|
||||
PRIMARY KEY country_code
|
||||
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'admin' PASSWORD 'CHANGE_ME' DB 'mabase_prod' TABLE 'anubis_country_rules'))
|
||||
LAYOUT(FLAT())
|
||||
LIFETIME(MIN 300 MAX 600);
|
||||
Reference in New Issue
Block a user