Merge pull request #448 from Iamrodos/fix/attachment-duplicate-downloads

fix: Prevent duplicate attachment downloads (with tests)

Author: josegonzalez

.github/workflows/test.yml

@@ -0,0 +1,33 @@
+---
+name: "test"
+
+# yamllint disable-line rule:truthy
+on:
+  pull_request:
+    branches:
+      - "*"
+  push:
+    branches:
+      - "main"
+      - "master"
+
+jobs:
+  test:
+    name: test
+    runs-on: ubuntu-24.04
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v5
+        with:
+          fetch-depth: 0
+      - name: Setup Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "pip"
+      - run: pip install -r release-requirements.txt
+      - run: pytest tests/ -v

github_backup/github_backup.py

@@ -919,12 +919,6 @@ def download_attachment_file(url, path, auth, as_app=False, fine=False):
         "error": None,
     }
 
-    if os.path.exists(path):
-        metadata["success"] = True
-        metadata["http_status"] = 200  # Assume success if already exists
-        metadata["size_bytes"] = os.path.getsize(path)
-        return metadata
-
     # Create simple request (no API query params)
     request = Request(url)
     request.add_header("Accept", "application/octet-stream")
@@ -1337,10 +1331,10 @@ def download_attachments(
     attachments_dir = os.path.join(item_cwd, "attachments", str(number))
     manifest_path = os.path.join(attachments_dir, "manifest.json")
 
-    # Load existing manifest if skip_existing is enabled
+    # Load existing manifest to prevent duplicate downloads
     existing_urls = set()
     existing_metadata = []
-    if args.skip_existing and os.path.exists(manifest_path):
+    if os.path.exists(manifest_path):
         try:
             with open(manifest_path, "r") as f:
                 existing_manifest = json.load(f)
@@ -1395,9 +1389,6 @@ def download_attachments(
         filename = get_attachment_filename(url)
         filepath = os.path.join(attachments_dir, filename)
 
-        # Check for collision BEFORE downloading
-        filepath = resolve_filename_collision(filepath)
-
         # Download and get metadata
         metadata = download_attachment_file(
             url,

pytest.ini

@@ -0,0 +1,6 @@
+[pytest]
+testpaths = tests
+python_files = test_*.py
+python_classes = Test*
+python_functions = test_*
+addopts = -v

release-requirements.txt

@@ -8,6 +8,7 @@ colorama==0.4.6
 docutils==0.22.3
 flake8==7.3.0
 gitchangelog==3.0.4
+pytest==8.3.3
 idna==3.11
 importlib-metadata==8.7.0
 jaraco.classes==3.4.0

tests/__init__.py

@@ -0,0 +1 @@
+"""Tests for python-github-backup."""