feat: поддержка Go и npm экосистем

- setup-nexus.sh: создание go-proxy (proxy.golang.org) и npm-proxy (registry.npmjs.org)
- nexus_client.py: extract_go_info() и extract_npm_info() для парсинга путей
  Go:  packages/github.com/gorilla/mux/@v/v1.8.0.zip → name=github.com/gorilla/mux ver=v1.8.0
  npm: packages/lodash/-/lodash-4.17.21.tgz → name=lodash ver=4.17.21
- nexus_client.py: EXTRACTORS dict + extract_package_info() универсальный extractor
- webhooks.py: _detect_ecosystem() — определяет экосистему из asset.format
- harvester.py: использует extract_package_info() вместо extract_pypi_info()
- Всё в Docker-контейнере, на хосте ничего не ставится
- GuardDog поддерживает go и npm из коробки

guarddog_nexus/constants.py

@@ -15,6 +15,7 @@ PACKAGE_EXTENSIONS = (".tar.gz", ".tgz", ".whl", ".zip", ".gem")
 
 # Prefix used in PyPI-style asset paths ("/packages/name/ver/file")
 PYPI_PATH_PREFIX = "packages"
+NPM_PATH_PREFIX = "packages"
 
 # Metadata file patterns that should never be scanned
 METADATA_PATTERNS = (

guarddog_nexus/harvester.py

@@ -18,7 +18,7 @@ from guarddog_nexus.constants import (
 )
 from guarddog_nexus.logging_setup import log
 from guarddog_nexus.models import Finding, Scan, ScanStatus
-from guarddog_nexus.nexus_client import compute_sha256, download_asset, extract_pypi_info
+from guarddog_nexus.nexus_client import compute_sha256, download_asset, extract_package_info
 from guarddog_nexus.scanner import scan_package
 
 # Per-URL locks to avoid parallel scans of the same asset
@@ -36,14 +36,14 @@ async def harvest(
     asset_path: str,
     session: AsyncSession,
 ) -> Scan | None:
-    ecosystem = DEFAULT_ECOSYSTEM if format_ in (DEFAULT_ECOSYSTEM,) else format_
+    ecosystem = format_ if format_ else DEFAULT_ECOSYSTEM
 
     filename = os.path.basename(download_url.split("?")[0])
     if not filename.endswith(PACKAGE_EXTENSIONS):
         log.info("Skipping non-package asset: %s", filename)
         return None
 
-    info = extract_pypi_info(asset_path)
+    info = extract_package_info(asset_path, ecosystem)
     if info is None:
         log.warning("Could not parse package info from path: %s", asset_path)
         return None

guarddog_nexus/nexus_client.py

@@ -7,6 +7,7 @@ import httpx
 
 from guarddog_nexus.config import config
 from guarddog_nexus.constants import (
+    NPM_PATH_PREFIX,
     PYPI_PATH_PREFIX,
     SHA256_CHUNK_SIZE,
 )
@@ -24,6 +25,70 @@ def extract_pypi_info(asset_path: str) -> tuple[str, str] | None:
     return None
 
 
+def extract_go_info(asset_path: str) -> tuple[str, str] | None:
+    """Extract module and version from a Go proxy asset path.
+
+    Path format: packages/github.com/gin-gonic/gin/@v/v1.9.0.zip
+    """
+    cleaned = asset_path.strip("/")
+    # Find @v/ marker
+    idx = cleaned.find("/@v/")
+    if idx == -1:
+        return None
+    if cleaned.startswith(PYPI_PATH_PREFIX + "/"):
+        module = cleaned[len(PYPI_PATH_PREFIX) + 1 : idx]
+    else:
+        module = cleaned[:idx]
+    if not module:
+        return None
+    # Version: after @v/ up to the next / or end
+    ver_start = idx + 4  # len("/@v/")
+    rest = cleaned[ver_start:]
+    version = rest.split("/")[0] if "/" in rest else rest
+    if version.endswith(".zip"):
+        version = version[:-4]
+    return module, version
+
+
+def extract_npm_info(asset_path: str) -> tuple[str, str] | None:
+    """Extract package name and version from an npm proxy asset path.
+
+    Path format: packages/react/-/react-18.2.0.tgz
+    """
+    parts = asset_path.strip("/").split("/")
+    if len(parts) < 4 or parts[0] != NPM_PATH_PREFIX:
+        return None
+    name = parts[1]
+    # Last segment: <name>-<version>.tgz
+    last = parts[-1]
+    if last.startswith(name + "-"):
+        raw = last[len(name) + 1 :]
+        for ext in (".tgz", ".tar.gz"):
+            if raw.endswith(ext):
+                return name, raw[: -len(ext)]
+    return None
+
+
+# Map of ecosystem → extractor function
+EXTRACTORS = {
+    "pypi": extract_pypi_info,
+    "go": extract_go_info,
+    "npm": extract_npm_info,
+}
+
+
+def extract_package_info(asset_path: str, ecosystem: str) -> tuple[str, str] | None:
+    """Extract package name and version based on ecosystem."""
+    extractor = EXTRACTORS.get(ecosystem)
+    if extractor:
+        return extractor(asset_path)
+    # Fallback for unknown ecosystems — try simple parts split
+    parts = asset_path.strip("/").split("/")
+    if len(parts) >= 3:
+        return parts[1], parts[2]
+    return None
+
+
 async def download_asset(download_url: str, dest_dir: str) -> str | None:
     """Download an asset from Nexus using async httpx."""
     dest_path = os.path.join(dest_dir, os.path.basename(download_url.split("?")[0]))

guarddog_nexus/webhooks.py

@@ -49,6 +49,18 @@ def _extract_asset_path(asset: dict) -> str | None:
     return None
 
 
+def _detect_ecosystem(source: dict) -> str:
+    """Detect ecosystem from asset or component format field."""
+    fmt = source.get("format", "").lower()
+    if fmt in ("pypi", "pip", "python"):
+        return "pypi"
+    if fmt in ("go", "golang"):
+        return "go"
+    if fmt in ("npm", "node"):
+        return "npm"
+    return fmt or DEFAULT_ECOSYSTEM
+
+
 @router.post("/nexus")
 async def nexus_webhook(
     request: Request,
@@ -96,11 +108,12 @@ async def nexus_webhook(
         download_url = asset.get("downloadUrl") or _build_download_url(
             repository, asset_path
         )
+        ecosystem = _detect_ecosystem(asset)
 
-        log.info("Webhook: %s asset %s in %s", action, asset_path, repository)
+        log.info("Webhook: %s asset %s (%s) in %s", action, asset_path, ecosystem, repository)
 
         background_tasks.add_task(
-            _scan_in_background, download_url, repository, DEFAULT_ECOSYSTEM, asset_path
+            _scan_in_background, download_url, repository, ecosystem, asset_path
         )
         return {"status": WEBHOOK_STATUS_ACCEPTED, "asset": asset_path, "action": action}
 
@@ -113,7 +126,8 @@ async def nexus_webhook(
                 "reason": WEBHOOK_IGNORE_NO_NAME_OR_VERSION,
             }
 
-        background_tasks.add_task(_scan_component, repository, name, version)
+        ecosystem = _detect_ecosystem(component)
+        background_tasks.add_task(_scan_component, repository, name, version, ecosystem)
         return {
             "status": WEBHOOK_STATUS_ACCEPTED,
             "component": f"{name}=={version}",
@@ -126,12 +140,12 @@ async def nexus_webhook(
     }
 
 
-async def _scan_component(repository: str, name: str, version: str):
+async def _scan_component(repository: str, name: str, version: str, ecosystem: str):
     from guarddog_nexus.nexus_client import nexus_get
 
     api_path = (
         f"/service/rest/v1/search"
-        f"?repository={repository}&name={name}&version={version}&format={DEFAULT_ECOSYSTEM}"
+        f"?repository={repository}&name={name}&version={version}&format={ecosystem}"
     )
     try:
         resp = await nexus_get(api_path)
@@ -157,7 +171,7 @@ async def _scan_component(repository: str, name: str, version: str):
             log.info("Scanning component asset: %s", asset_path)
             async for session in get_session():
                 await harvest(
-                    download_url, repository, DEFAULT_ECOSYSTEM, asset_path, session
+                    download_url, repository, ecosystem, asset_path, session
                 )
                 break
 

scripts/setup-nexus.sh

@@ -30,37 +30,51 @@ if [ -f /nexus-data/admin.password ]; then
     echo "Using initial admin password from volume"
 fi
 
-echo "Creating PyPI proxy repository..."
+# Common proxy config
+_proxy_config() {
+    cat <<EOF
+{
+    "name": "$1",
+    "online": true,
+    "storage": {
+        "blobStoreName": "default",
+        "strictContentTypeValidation": true
+    },
+    "proxy": {
+        "remoteUrl": "$2",
+        "contentMaxAge": 1440,
+        "metadataMaxAge": 1440
+    },
+    "negativeCache": {
+        "enabled": true,
+        "timeToLive": 1440
+    },
+    "httpClient": {
+        "blocked": false,
+        "autoBlock": true,
+        "connection": {
+            "timeout": 60,
+            "retries": 3
+        }
+    }
+}
+EOF
+}
+
+_create_proxy() {
+    local name="$1" remote="$2" format="$3"
+    echo "Creating $name ($format proxy → $remote)..."
     curl -sf -u "admin:${AUTH_PASS}" \
         -H "Content-Type: application/json" \
         -X POST \
-    -d "{
+        -d "$(_proxy_config "$name" "$remote")" \
-        \"name\": \"pypi-proxy\",
+        "${NEXUS_URL}/service/rest/v1/repositories/${format}/proxy" 2>/dev/null && \
-        \"online\": true,
+        echo "  OK" || echo "  already exists or failed, continuing..."
-        \"storage\": {
-            \"blobStoreName\": \"default\",
-            \"strictContentTypeValidation\": true
-        },
-        \"proxy\": {
-            \"remoteUrl\": \"https://pypi.org\",
-            \"contentMaxAge\": 1440,
-            \"metadataMaxAge\": 1440
-        },
-        \"negativeCache\": {
-            \"enabled\": true,
-            \"timeToLive\": 1440
-        },
-        \"httpClient\": {
-            \"blocked\": false,
-            \"autoBlock\": true,
-            \"connection\": {
-                \"timeout\": 60,
-                \"retries\": 3
 }
-        }
+
-    }" \
+_create_proxy "pypi-proxy" "https://pypi.org" "pypi"
-    "${NEXUS_URL}/service/rest/v1/repositories/pypi/proxy" 2>/dev/null || \
+_create_proxy "go-proxy" "https://proxy.golang.org" "go"
-    echo "Proxy repo may already exist, continuing..."
+_create_proxy "npm-proxy" "https://registry.npmjs.org" "npm"
 
 echo ""
 echo "NOTE: Webhook setup is not available in Nexus OSS/Community edition."
@@ -68,7 +82,7 @@ echo "In Nexus Pro, configure:"
 echo "  Capability: Webhook: Repository"
 echo "  URL: ${WEBHOOK_URL}"
 echo "  Event types: repository.component, repository.asset"
-echo "  Repository filter: pypi-proxy"
+echo "  Repository filter: pypi-proxy, go-proxy, npm-proxy"
 echo ""
 
 if [ -f /nexus-data/admin.password ]; then