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 +1,144 @@
"""
Endpoints pour la heatmap temporelle (hits par heure / hôte)
"""
from collections import defaultdict
from fastapi import APIRouter, HTTPException, Query
from ..database import db
router = APIRouter(prefix="/api/heatmap", tags=["heatmap"])
@router.get("/hourly")
async def get_heatmap_hourly():
"""Hits agrégés par heure sur les 72 dernières heures."""
try:
sql = """
SELECT
toHour(window_start) AS hour,
sum(hits) AS hits,
uniq(replaceRegexpAll(toString(src_ip), '^::ffff:', '')) AS unique_ips,
max(max_requests_per_sec) AS max_rps
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 = [
{
"hour": int(row[0]),
"hits": int(row[1]),
"unique_ips": int(row[2]),
"max_rps": int(row[3]),
}
for row in result.result_rows
]
return {"hours": hours}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.get("/top-hosts")
async def get_heatmap_top_hosts(limit: int = Query(20, ge=1, le=100)):
"""Hôtes les plus ciblés avec répartition horaire sur 24h."""
try:
# Aggregate overall stats per host
agg_sql = """
SELECT
host,
sum(hits) AS total_hits,
uniq(replaceRegexpAll(toString(src_ip), '^::ffff:', '')) AS unique_ips,
uniq(ja4) AS unique_ja4s
FROM mabase_prod.agg_host_ip_ja4_1h
WHERE window_start >= now() - INTERVAL 72 HOUR
GROUP BY host
ORDER BY total_hits DESC
LIMIT %(limit)s
"""
agg_res = db.query(agg_sql, {"limit": limit})
top_hosts = [str(r[0]) for r in agg_res.result_rows]
host_stats = {
str(r[0]): {
"host": str(r[0]),
"total_hits": int(r[1]),
"unique_ips": int(r[2]),
"unique_ja4s":int(r[3]),
}
for r in agg_res.result_rows
}
if not top_hosts:
return {"items": []}
# Hourly breakdown per host
hourly_sql = """
SELECT
host,
toHour(window_start) AS hour,
sum(hits) AS hits
FROM mabase_prod.agg_host_ip_ja4_1h
WHERE window_start >= now() - INTERVAL 72 HOUR
AND host IN %(hosts)s
GROUP BY host, hour
"""
hourly_res = db.query(hourly_sql, {"hosts": top_hosts})
hourly_map: dict = defaultdict(lambda: [0] * 24)
for row in hourly_res.result_rows:
h = str(row[0])
hour = int(row[1])
hits = int(row[2])
hourly_map[h][hour] += hits
items = []
for host in top_hosts:
entry = dict(host_stats[host])
entry["hourly_hits"] = hourly_map[host]
items.append(entry)
return {"items": items}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@router.get("/matrix")
async def get_heatmap_matrix():
"""Matrice top-15 hôtes × 24 heures (sum hits) sur les 72 dernières heures."""
try:
top_sql = """
SELECT host, sum(hits) AS total_hits
FROM mabase_prod.agg_host_ip_ja4_1h
WHERE window_start >= now() - INTERVAL 72 HOUR
GROUP BY host
ORDER BY total_hits DESC
"""
top_res = db.query(top_sql)
top_hosts = [str(r[0]) for r in top_res.result_rows]
if not top_hosts:
return {"hosts": [], "matrix": []}
cell_sql = """
SELECT
host,
toHour(window_start) AS hour,
sum(hits) AS hits
FROM mabase_prod.agg_host_ip_ja4_1h
WHERE window_start >= now() - INTERVAL 72 HOUR
AND host IN %(hosts)s
GROUP BY host, hour
"""
cell_res = db.query(cell_sql, {"hosts": top_hosts})
matrix_map: dict = defaultdict(lambda: [0] * 24)
for row in cell_res.result_rows:
h = str(row[0])
hour = int(row[1])
hits = int(row[2])
matrix_map[h][hour] += hits
matrix = [matrix_map[h] for h in top_hosts]
return {"hosts": top_hosts, "matrix": matrix}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))