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
2026-04-07 16:42:59 +02:00
commit d469e39da7
278 changed files with 1621301 additions and 0 deletions

View File

@ -0,0 +1,141 @@
"""
Endpoints pour l'analyse des attaques par force brute sur les formulaires
"""
from fastapi import APIRouter, HTTPException, Query
from ..database import db
router = APIRouter(prefix="/api/bruteforce", tags=["bruteforce"])
@router.get("/targets")
async def get_bruteforce_targets():
"""Liste des hôtes ciblés par brute-force, triés par total_hits DESC."""
try:
sql = """
SELECT
host,
uniq(src_ip) AS unique_ips,
sum(hits) AS total_hits,
sum(query_params_count) AS total_params,
groupArray(3)(ja4) AS top_ja4s
FROM mabase_prod.view_form_bruteforce_detected
GROUP BY host
ORDER BY total_hits DESC
"""
result = db.query(sql)
items = []
for row in result.result_rows:
host = str(row[0])
unique_ips = int(row[1])
total_hits = int(row[2])
total_params= int(row[3])
top_ja4s = [str(j) for j in (row[4] or [])]
attack_type = (
"credential_stuffing"
if total_hits > 0 and total_params / total_hits > 0.5
else "enumeration"
)
items.append({
"host": host,
"unique_ips": unique_ips,
"total_hits": total_hits,
"total_params":total_params,
"attack_type": attack_type,
"top_ja4s": top_ja4s,
})
return {"items": items, "total": len(items)}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.get("/attackers")
async def get_bruteforce_attackers(limit: int = Query(50, ge=1, le=500)):
"""Top IPs attaquantes triées par total_hits DESC."""
try:
sql = """
SELECT
replaceRegexpAll(toString(src_ip), '^::ffff:', '') AS ip,
uniq(host) AS distinct_hosts,
sum(hits) AS total_hits,
sum(query_params_count) AS total_params,
argMax(ja4, hits) AS ja4
FROM mabase_prod.view_form_bruteforce_detected
GROUP BY src_ip
ORDER BY total_hits DESC
LIMIT %(limit)s
"""
result = db.query(sql, {"limit": limit})
items = []
for row in result.result_rows:
items.append({
"ip": str(row[0]),
"distinct_hosts":int(row[1]),
"total_hits": int(row[2]),
"total_params": int(row[3]),
"ja4": str(row[4]),
})
return {"items": items, "total": len(items)}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.get("/timeline")
async def get_bruteforce_timeline():
"""Hits par heure (dernières 72h) depuis agg_host_ip_ja4_1h."""
try:
sql = """
SELECT
toHour(window_start) AS hour,
sum(hits) AS hits,
uniq(replaceRegexpAll(toString(src_ip), '^::ffff:', '')) AS ips
FROM mabase_prod.agg_host_ip_ja4_1h
WHERE window_start >= now() - INTERVAL 72 HOUR
GROUP BY hour
ORDER BY hour ASC
"""
result = db.query(sql)
hours = []
for row in result.result_rows:
hours.append({
"hour": int(row[0]),
"hits": int(row[1]),
"ips": int(row[2]),
})
return {"hours": hours}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.get("/host/{host:path}/attackers")
async def get_host_attackers(host: str, limit: int = Query(20, ge=1, le=200)):
"""Top IPs attaquant un hôte spécifique, avec JA4 et type d'attaque."""
try:
sql = """
SELECT
replaceRegexpAll(toString(src_ip), '^::ffff:', '') AS ip,
sum(hits) AS total_hits,
sum(query_params_count) AS total_params,
argMax(ja4, hits) AS ja4,
max(hits) AS max_hits_per_window
FROM mabase_prod.view_form_bruteforce_detected
WHERE host = %(host)s
GROUP BY src_ip
ORDER BY total_hits DESC
LIMIT %(limit)s
"""
result = db.query(sql, {"host": host, "limit": limit})
items = []
for row in result.result_rows:
total_hits = int(row[1])
total_params = int(row[2])
items.append({
"ip": str(row[0]),
"total_hits": total_hits,
"total_params":total_params,
"ja4": str(row[3] or ""),
"attack_type": "credential_stuffing" if total_hits > 0 and total_params / total_hits > 0.5 else "enumeration",
})
return {"host": host, "items": items, "total": len(items)}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))