From 3fc3d3fcffadb8c37fbdff80174ac010c2129bbd Mon Sep 17 00:00:00 2001
From: Ian Kretz <44385082+ikretz@users.noreply.github.com>
Date: Wed, 17 Jul 2024 12:10:29 +0200
Subject: [PATCH] Eliminate redundant archive check

---
 guarddog/scanners/pypi_package_scanner.py | 21 ++++++++-------------
 guarddog/scanners/scanner.py              |  8 +++-----
 2 files changed, 11 insertions(+), 18 deletions(-)

diff --git a/guarddog/scanners/pypi_package_scanner.py b/guarddog/scanners/pypi_package_scanner.py
index 09a8f0cb..e6d7015b 100644
--- a/guarddog/scanners/pypi_package_scanner.py
+++ b/guarddog/scanners/pypi_package_scanner.py
@@ -4,7 +4,7 @@
 from guarddog.analyzer.analyzer import Analyzer
 from guarddog.ecosystems import ECOSYSTEM
 from guarddog.scanners.scanner import PackageScanner
-from guarddog.utils.archives import is_tar_archive, is_zip_archive
+from guarddog.utils.archives import is_supported_archive
 from guarddog.utils.package_info import get_package_info
 
 
@@ -43,25 +43,20 @@ def download_package(self, package_name, directory, version=None) -> str:
             raise Exception(f"Version {version} for package {package_name} doesn't exist.")
 
         files = releases[version]
-        url = None
-        file_extension = None
+        url, file_extension = None, None
 
         for file in files:
-            # Store url to compressed package and appropriate file extension
-            if is_tar_archive(file["filename"]):
+            if is_supported_archive(file["filename"]):
                 url = file["url"]
-                file_extension = ".tar.gz"
+                _, file_extension = os.path.splitext(file["filename"])
+                break
 
-            if is_zip_archive(file["filename"]):
-                url = file["url"]
-                file_extension = ".zip"
-
-        if not (url or file_extension):
+        if not (url and file_extension):
             raise Exception(f"Compressed file for {package_name} does not exist on PyPI.")
 
         # Path to compressed package
         zippath = os.path.join(directory, package_name + file_extension)
-        unzippedpath = zippath.removesuffix(file_extension)
-
+        unzippedpath = os.path.join(directory, package_name)
         self.download_compressed(url, zippath, unzippedpath)
+
         return unzippedpath
diff --git a/guarddog/scanners/scanner.py b/guarddog/scanners/scanner.py
index 389ff288..f23cdafe 100644
--- a/guarddog/scanners/scanner.py
+++ b/guarddog/scanners/scanner.py
@@ -11,7 +11,7 @@
 import requests
 
 from guarddog.analyzer.analyzer import Analyzer
-from guarddog.utils.archives import is_supported_archive, safe_extract
+from guarddog.utils.archives import safe_extract
 from guarddog.utils.config import PARALLELISM
 
 log = logging.getLogger("guarddog")
@@ -248,14 +248,12 @@ def scan_local(
         results = None
         if os.path.isdir(path):
             results = self.analyzer.analyze_sourcecode(path, rules=rules)
-        elif (os.path.isfile(path) and is_supported_archive(path)):
+        elif os.path.isfile(path):
             with tempfile.TemporaryDirectory() as tempdir:
                 safe_extract(path, tempdir)
                 results = self.analyzer.analyze_sourcecode(tempdir, rules=rules)
         else:
-            raise Exception(
-                f"Path {path} is not a directory nor an archive supported by GuardDog."
-            )
+            raise Exception(f"Local scan target {path} is neither a directory nor a file.")
 
         callback(results)