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 +1,125 @@
"""
Endpoint de recherche globale rapide — utilisé par la barre Cmd+K
"""
from fastapi import APIRouter, Query
from ..database import db
router = APIRouter(prefix="/api/search", tags=["search"])
IP_RE = r"^(\d{1,3}\.){0,3}\d{1,3}$"
@router.get("/quick")
async def quick_search(q: str = Query(..., min_length=1, max_length=100)):
"""
Recherche unifiée sur IPs, JA4, ASN, hosts.
Retourne jusqu'à 5 résultats par catégorie.
"""
q = q.strip()
pattern = f"%{q}%"
results = []
# ── IPs ──────────────────────────────────────────────────────────────────
ip_rows = db.query(
"""
SELECT
replaceRegexpAll(toString(src_ip), '^::ffff:', '') AS clean_ip,
count() AS hits,
max(detected_at) AS last_seen,
any(threat_level) AS threat_level
FROM ml_detected_anomalies
WHERE ilike(toString(src_ip), %(p)s)
AND detected_at >= now() - INTERVAL 24 HOUR
GROUP BY clean_ip
ORDER BY hits DESC
""",
{"p": pattern},
)
for r in ip_rows.result_rows:
ip = str(r[0])
results.append({
"type": "ip",
"value": ip,
"label": ip,
"meta": f"{r[1]} détections · {r[3]}",
"url": f"/detections/ip/{ip}",
"investigation_url": f"/investigation/{ip}",
})
# ── JA4 fingerprints ─────────────────────────────────────────────────────
ja4_rows = db.query(
"""
SELECT
ja4,
count() AS hits,
uniq(src_ip) AS unique_ips
FROM ml_detected_anomalies
WHERE ilike(ja4, %(p)s)
AND ja4 != ''
AND detected_at >= now() - INTERVAL 24 HOUR
GROUP BY ja4
ORDER BY hits DESC
""",
{"p": pattern},
)
for r in ja4_rows.result_rows:
results.append({
"type": "ja4",
"value": str(r[0]),
"label": str(r[0]),
"meta": f"{r[1]} détections · {r[2]} IPs",
"url": f"/investigation/ja4/{r[0]}",
})
# ── Hosts ─────────────────────────────────────────────────────────────────
host_rows = db.query(
"""
SELECT
host,
count() AS hits,
uniq(src_ip) AS unique_ips
FROM ml_detected_anomalies
WHERE ilike(host, %(p)s)
AND host != ''
AND detected_at >= now() - INTERVAL 24 HOUR
GROUP BY host
ORDER BY hits DESC
""",
{"p": pattern},
)
for r in host_rows.result_rows:
results.append({
"type": "host",
"value": str(r[0]),
"label": str(r[0]),
"meta": f"{r[1]} hits · {r[2]} IPs",
"url": f"/detections?search={r[0]}",
})
# ── ASN ───────────────────────────────────────────────────────────────────
asn_rows = db.query(
"""
SELECT
asn_org,
asn_number,
count() AS hits,
uniq(src_ip) AS unique_ips
FROM ml_detected_anomalies
WHERE (ilike(asn_org, %(p)s) OR ilike(asn_number, %(p)s))
AND asn_org != '' AND asn_number != ''
AND detected_at >= now() - INTERVAL 24 HOUR
GROUP BY asn_org, asn_number
ORDER BY hits DESC
""",
{"p": pattern},
)
for r in asn_rows.result_rows:
results.append({
"type": "asn",
"value": str(r[1]),
"label": f"AS{r[1]}{r[0]}",
"meta": f"{r[2]} hits · {r[3]} IPs",
"url": f"/detections?asn={r[1]}",
})
return {"query": q, "results": results}