Add manual Collect Workflow

.github/workflows/manual.yaml

@@ -0,0 +1,42 @@
+name: Manual collection
+
+on:
+  workflow_dispatch:
+    inputs:
+      project:
+        description: 'Name of the project to collect'
+        required: true
+        default: ''
+      repositories:
+        description: 'List of repositories to collect, separated by spaces'
+        required: false
+        default: ''
+      extras:
+        description: 'Extra arguments to pass (e.g. --not-incremental --add-metrics)'
+        required: false
+        default: '--not-incremental --add-metrics'
+
+jobs:
+  collect:
+    runs-on: ubuntu-latest
+    timeout-minutes: 120
+    steps:
+    - uses: actions/checkout@v6
+    - name: Install uv
+      uses: astral-sh/setup-uv@v7
+      with:
+        enable-cache: true
+        activate-environment: true
+    - name: Install dependencies
+      run: |
+        uv pip install .
+    - name: Collect Github Data
+      run: |
+        uv run gitmetrics collect -v -q \
+          -t ${{ secrets.GITHUB_TOKEN }} \
+          -p ${{ github.event.inputs.project }} \
+          -r ${{ github.event.inputs.repositories }} \
+          -o gdrive://${{ secrets.MANUAL_OUTPUT_FOLDER }} \
+          ${{ github.event.inputs.extras }}
+      env:
+        PYDRIVE_CREDENTIALS: ${{ secrets.PYDRIVE_CREDENTIALS }}

gitmetrics/__main__.py

@@ -67,7 +67,11 @@ def _collect(args, parser):
         elif len(args.projects) > 1:
             parser.error('If repositories are given, only one project name must be provided.')
 
-        projects = {args.projects[0]: args.repositories}
+        projects = {
+            args.projects[0]: [
+                f'{args.projects[0]}/{repository}' for repository in args.repositories
+            ]
+        }
 
     elif not args.projects:
         projects = config_projects

gitmetrics/main.py

@@ -8,7 +8,7 @@
 
 from gitmetrics.constants import METRICS_SHEET_NAME
 from gitmetrics.drive import get_or_create_gdrive_folder
-from gitmetrics.github.repository import RepositoryClient
+from gitmetrics.github.repository import STARGAZERS_COLUMNS, RepositoryClient
 from gitmetrics.github.repository_owner import RepositoryOwnerClient
 from gitmetrics.github.traffic import TrafficClient
 from gitmetrics.github.users import UsersClient
@@ -61,7 +61,14 @@ def _get_repository_data(token, repository, previous=None, quiet=False):
     pull_requests = repo_client.get_pull_requests()
     pull_requests.insert(1, 'repository', repository)
 
-    stargazers = repo_client.get_stargazers()
+    try:
+        stargazers = repo_client.get_stargazers()
+    except Exception:
+        # Stargazer information is available only for repositories that we own
+        # In order to continue with the flow without breaking we create an empty
+        # dataframe with the expected columns.
+        stargazers = pd.DataFrame(columns=STARGAZERS_COLUMNS)
+
     stargazers.insert(1, 'repository', repository)
 
     return issues, pull_requests, stargazers