register events to avoid processing duplicate events

.github/workflows/tests.yaml

@@ -2,17 +2,17 @@ name: Run tests
 on: [push, pull_request]
 jobs:
   test:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-20.04
     strategy:
       matrix:
         python: [3.6, 3.7, 3.8, 3.9, '3.10']
       fail-fast: false
     steps:
       - name: Check out repository code
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
 
       - name: Setup Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
           python-version: ${{matrix.python}}
 

pyghee/lib.py

@@ -84,6 +84,26 @@ def __init__(self, *args, **kwargs):
         else:
             del os.environ['GITHUB_APP_SECRET_TOKEN']
 
+        self.registered_events = []
+
+    def register_event(self, event_id):
+        """
+        Register event by ID.
+        Returns True if event is new, False is event is not new.
+        """
+        if event_id in self.registered_events:
+            return False
+        else:
+            self.registered_events.append(event_id)
+
+            # keep size of list of registered events under control,
+            # trim in half if maximum size has been reached
+            max_size = 10000
+            if len(self.registered_events) >= max_size:
+                self.registered_events = self.registered_events[max_size//2:]
+
+            return True
+
     def handle_event(self, event_info, log_file=None):
         """
         Handle event
@@ -164,10 +184,14 @@ def process_event(self, request, abort_function,
         """
         try:
             event_info = get_event_info(request)
-            self.log_event(event_info, events_log_dir=events_log_dir, log_file=log_file)
-            if verify:
-                self.verify_request(event_info, abort_function, log_file=log_file)
-            self.handle_event(event_info, log_file=log_file)
+            event_id = event_info['id']
+            if self.register_event(event_id):
+                self.log_event(event_info, events_log_dir=events_log_dir, log_file=log_file)
+                if verify:
+                    self.verify_request(event_info, abort_function, log_file=log_file)
+                self.handle_event(event_info, log_file=log_file)
+            else:
+                log("Duplicate event received, id: %s" % event_id)
         except Exception as err:
             if raise_error:
                 raise

pyghee/main.py

@@ -37,4 +37,5 @@ def handle_issue_comment_event(self, event_info, log_file=None):
 if __name__ == '__main__':
     app = create_app(klass=ExamplePyGHee)
     log("App started!")
-    waitress.serve(app, listen='*:3000')
+    # stick to single thread so we can avoid processing duplicate event deliveries multiple times
+    waitress.serve(app, listen='*:3000', threads=1)

setup.py

@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name="PyGHee",
-    version="0.0.3",
+    version="0.0.4",
     author="Kenneth Hoste",
     author_email="kenneth.hoste@ugent.be",
     description="PyGHee (pronounced as 'piggy') is the GitHub Event Executor, a Python library to facilitate creating a GitHub App implemented in Python to process [events from GitHub",

tests/event_data.py

@@ -16,6 +16,7 @@
 EVENT_TYPE_ISSUE_COMMENT = 'issue_comment'
 
 REQUEST_ID_001 = 'd3ed7694-8a6c-4008-a93f-b92aa86a95a8'
+REQUEST_ID_002 = 'e4fe8783-7b7d-5119-b84e-c83bb97b86b9'
 TIMESTAMP_001 = '1645367007403'  # 2022-02-20T15:23:27
 
 CREATE_BRANCH_REQUEST = Request(
@@ -41,7 +42,7 @@
         'Timestamp': TIMESTAMP_001,
         'X-GitHub-Event': EVENT_TYPE_ISSUE_COMMENT,
         'X-Hub-Signature': 'sha1=0123456789abcedf0123456789abcedf01234567',  # fake signature!
-        'X-Github-Delivery': REQUEST_ID_001,
+        'X-Github-Delivery': REQUEST_ID_002,
     }, {
         # request.json
         'action': ACTION_CREATED,

tests/test_events.py

@@ -15,10 +15,11 @@
 from pyghee.main import ExamplePyGHee
 from requests.structures import CaseInsensitiveDict
 
-from tests.event_data import REQUEST_ID_001, TIMESTAMP_001
+from tests.event_data import REQUEST_ID_001, REQUEST_ID_002, TIMESTAMP_001
 from tests.event_data import CREATE_BRANCH_REQUEST, ISSUE_COMMENT_CREATED_REQUEST
 
 TEST_REQUESTS = (CREATE_BRANCH_REQUEST, ISSUE_COMMENT_CREATED_REQUEST)
+REQUEST_IDS = (REQUEST_ID_001, REQUEST_ID_002)
 
 TEST_SECRET_TOKEN = '0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef'
 
@@ -28,11 +29,11 @@ def dummy_abort_function(abort_code):
 
 
 def test_get_event_info():
-    for request in TEST_REQUESTS:
+    for idx, request in enumerate(TEST_REQUESTS):
         res = get_event_info(request)
         event_action = request.json.get('action', 'UNKNOWN')
         assert res['action'] == event_action
-        assert res['id'] == REQUEST_ID_001
+        assert res['id'] == REQUEST_IDS[idx]
         event_type = request.headers['X-GitHub-Event']
         assert res['type'] == event_type
 
@@ -68,7 +69,7 @@ def test_process_event(tmpdir):
     os.environ['GITHUB_APP_SECRET_TOKEN'] = 'fake_app_secret_token'
     pyghee = ExamplePyGHee()
 
-    for request in TEST_REQUESTS:
+    for idx, request in enumerate(TEST_REQUESTS):
         event_info = get_event_info(request)
         event_action, event_type = event_info['action'], event_info['type']
 
@@ -79,15 +80,16 @@ def test_process_event(tmpdir):
         event_data_dir = os.path.join(events_log_dir, event_type, event_action, '2022-02-20')
         assert os.path.isdir(event_data_dir)
 
-        header_fp = '2022-02-20T14-23-27_%s_headers.json' % REQUEST_ID_001
-        body_fp = '2022-02-20T14-23-27_%s_body.json' % REQUEST_ID_001
+        request_id = REQUEST_IDS[idx]
+        header_fp = '2022-02-20T14-23-27_%s_headers.json' % request_id
+        body_fp = '2022-02-20T14-23-27_%s_body.json' % request_id
         assert sorted(os.listdir(event_data_dir)) == [body_fp, header_fp]
 
         # verify saved event header
         expected_header = {
             'Timestamp': TIMESTAMP_001,
             'X-GitHub-Event': event_type,
-            'X-Github-Delivery': REQUEST_ID_001,
+            'X-Github-Delivery': request_id,
         }
         with open(os.path.join(event_data_dir, header_fp), 'r') as fp:
             header_data = json.load(fp)