fix: async subprocess + httpx — no more event loop blocking during scans

guarddog_nexus/harvester.py

@@ -66,7 +66,7 @@ async def harvest(
         scan.status = ScanStatus.SCANNING.value
         await session.commit()
 
-        downloaded = download_asset(download_url, tmpdir)
+        downloaded = await download_asset(download_url, tmpdir)
         if not downloaded:
             scan.status = ScanStatus.FAILED.value
             scan.error_message = "Download failed"
@@ -78,7 +78,7 @@ async def harvest(
         await session.commit()
 
         log.info("Scanning %s==%s", package_name, package_version)
-        result = scan_package(downloaded, ecosystem)
+        result = await scan_package(downloaded, ecosystem)
 
         findings_list = result.get("findings", [])
 

guarddog_nexus/nexus_client.py

@@ -1,25 +1,14 @@
-"""Sonatype Nexus REST API client."""
+"""Sonatype Nexus REST API client using httpx async."""
 
 import hashlib
 import os
-import subprocess
+
+import httpx
 
 from guarddog_nexus.config import config
 from guarddog_nexus.logging_setup import log
 
 SUPPORTED_EXTENSIONS = (".tar.gz", ".tgz", ".whl", ".zip")
-PACKAGE_FILE_PATTERNS = ("packages/",)
-
-
-def get_ecosystem_from_format(fmt: str) -> str | None:
-    mapping = {
-        "pypi": "pypi",
-        "npm": "npm",
-        "rubygems": "rubygems",
-        "go": "go",
-        "raw": None,
-    }
-    return mapping.get(fmt.lower() if fmt else "")
 
 
 def extract_pypi_info(asset_path: str) -> tuple[str, str] | None:
@@ -33,31 +22,28 @@ def extract_pypi_info(asset_path: str) -> tuple[str, str] | None:
     return None
 
 
-def download_asset(download_url: str, dest_dir: str) -> str | None:
-    """Download an asset from Nexus using curl (available in Docker)."""
+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]))
-    try:
-        result = subprocess.run(
-            [
-                "curl",
-                "-sfSL",
-                "-u",
-                f"{config.nexus_username}:{config.nexus_password}",
-                "-o",
-                dest_path,
-                download_url,
-            ],
-            capture_output=True,
-            text=True,
-            timeout=120,
-        )
-        if result.returncode != 0:
-            log.warning("Failed to download %s: %s", download_url, result.stderr)
+
+    auth = httpx.BasicAuth(config.nexus_username, config.nexus_password)
+    async with httpx.AsyncClient(auth=auth, timeout=120, follow_redirects=True) as client:
+        try:
+            response = await client.get(download_url)
+            response.raise_for_status()
+            with open(dest_path, "wb") as f:
+                f.write(response.content)
+            return dest_path
+        except Exception as e:
+            log.warning("Failed to download %s: %s", download_url, e)
             return None
-        return dest_path
-    except Exception as e:
-        log.error("Download error for %s: %s", download_url, e)
-        return None
+
+
+async def nexus_get(path: str) -> httpx.Response:
+    """Make an authenticated GET request to Nexus REST API."""
+    auth = httpx.BasicAuth(config.nexus_username, config.nexus_password)
+    async with httpx.AsyncClient(auth=auth, timeout=30) as client:
+        return await client.get(f"{config.nexus_url.rstrip('/')}{path}")
 
 
 def compute_sha256(filepath: str) -> str:

guarddog_nexus/scanner.py

@@ -1,8 +1,8 @@
-"""GuardDog CLI integration via subprocess."""
+"""GuardDog CLI integration via asyncio subprocess."""
 
+import asyncio
 import json
 import shutil
-import subprocess
 
 from guarddog_nexus.config import config
 from guarddog_nexus.logging_setup import log
@@ -10,39 +10,33 @@ from guarddog_nexus.logging_setup import log
 GUARDDOG_BIN = shutil.which("guarddog") or "guarddog"
 
 
-def scan_package(filepath: str, ecosystem: str = "pypi") -> dict:
+async def scan_package(filepath: str, ecosystem: str = "pypi") -> dict:
     """Run guarddog scan on a downloaded package file. Returns normalized dict."""
-    cmd = [
-        GUARDDOG_BIN,
-        ecosystem,
-        "scan",
-        filepath,
-        "--output-format",
-        "json",
-    ]
-
+    cmd = [GUARDDOG_BIN, ecosystem, "scan", filepath, "--output-format", "json"]
     log.info("Running: %s", " ".join(cmd))
 
     try:
-        result = subprocess.run(
-            cmd,
-            capture_output=True,
-            text=True,
-            timeout=config.scan_timeout_seconds,
+        proc = await asyncio.create_subprocess_exec(
+            *cmd,
+            stdout=asyncio.subprocess.PIPE,
+            stderr=asyncio.subprocess.PIPE,
         )
-    except subprocess.TimeoutExpired:
+        stdout, stderr = await asyncio.wait_for(
+            proc.communicate(), timeout=config.scan_timeout_seconds
+        )
+    except asyncio.TimeoutError:
         log.error("GuardDog scan timed out for %s", filepath)
         return {"findings": [], "errors": ["timeout"]}
     except FileNotFoundError:
         log.error("GuardDog binary not found at %s", GUARDDOG_BIN)
         return {"findings": [], "errors": ["guarddog_not_found"]}
 
-    if result.returncode not in (0, 1):
-        log.error("GuardDog exited %d: %s", result.returncode, result.stderr)
-        return {"findings": [], "errors": [result.stderr.strip()]}
+    if proc.returncode not in (0, 1):
+        log.error("GuardDog exited %d: %s", proc.returncode, stderr.decode())
+        return {"findings": [], "errors": [stderr.decode().strip()]}
 
     try:
-        data = json.loads(result.stdout)
+        data = json.loads(stdout.decode())
     except json.JSONDecodeError:
         log.error("GuardDog returned invalid JSON for %s", filepath)
         return {"findings": [], "errors": ["json_parse_error"]}

guarddog_nexus/webhooks.py

@@ -115,23 +115,16 @@ async def nexus_webhook(
 
 async def _scan_component(repository: str, name: str, version: str):
     """Look up component assets via Nexus API, then scan each package file."""
-    import subprocess
 
-    api_url = (
-        f"{config.nexus_url.rstrip('/')}/service/rest/v1/search"
-        f"?repository={repository}&name={name}&version={version}&format=pypi"
+    from guarddog_nexus.nexus_client import nexus_get
+
+    api_path = (
+        f"/service/rest/v1/search?repository={repository}&name={name}&version={version}&format=pypi"
     )
     try:
-        result = subprocess.run(
-            ["curl", "-sf", "-u", f"{config.nexus_username}:{config.nexus_password}", api_url],
-            capture_output=True,
-            text=True,
-            timeout=30,
-        )
-        if result.returncode != 0:
-            log.warning("Component lookup failed for %s==%s: %s", name, version, result.stderr)
-            return
-        data = json.loads(result.stdout)
+        resp = await nexus_get(api_path)
+        resp.raise_for_status()
+        data = resp.json()
     except Exception as e:
         log.warning("Component lookup error for %s==%s: %s", name, version, e)
         return