d469e39da7
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>
60 lines
2.1 KiB
SQL
60 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 mabase_prod.dict_iplocate_asn;
|
|
|
|
CREATE DICTIONARY IF NOT EXISTS mabase_prod.dict_iplocate_asn
|
|
(
|
|
network String,
|
|
asn UInt32,
|
|
country_code String,
|
|
name String,
|
|
org String,
|
|
domain 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 mabase_prod.ref_bot_networks
|
|
(
|
|
network IPv6CIDR,
|
|
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 mabase_prod.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 mabase_prod.bot_ja4
|
|
(
|
|
ja4 String
|
|
)
|
|
ENGINE = File(CSV, 'bot_ja4.csv');
|