Fix Sentry integration

Dockerfile

@@ -2,7 +2,6 @@ FROM public.ecr.aws/lambda/python:3.9
 
 # Copy function code
 COPY . ${LAMBDA_TASK_ROOT}/
-COPY . ${LAMBDA_TASK_ROOT}/
 
 # Install dependencies
 RUN pip3 install pipenv

ppod.py

@@ -1,3 +1,4 @@
+import json
 import logging
 import os
 import tarfile
@@ -8,17 +9,31 @@
 import sentry_sdk
 import smart_open
 from boto3 import client
+from sentry_sdk.integrations.aws_lambda import AwsLambdaIntegration
+
+logger = logging.getLogger(__name__)
+logging.basicConfig(level=logging.INFO)
+
+env = os.getenv("WORKSPACE")
+if sentry_dsn := os.getenv("SENTRY_DSN"):
+    sentry = sentry_sdk.init(
+        dsn=sentry_dsn,
+        environment=env,
+        integrations=[
+            AwsLambdaIntegration(),
+        ],
+        traces_sample_rate=1.0,
+    )
+    logger.info("Sentry DSN found, exceptions will be sent to Sentry with env=%s", env)
+else:
+    logger.info("No Sentry DSN found, exceptions will not be sent to Sentry")
 
 
 def lambda_handler(event: dict, context: object) -> dict:
-    logger = logging.getLogger(__name__)
-    logging.basicConfig(level=logging.INFO)
-    env = os.environ["WORKSPACE"]
-    if sentry_dsn := os.getenv("SENTRY_DSN"):
-        sentry_sdk.init(sentry_dsn, environment=env)
-        logger.info(
-            "Sentry DSN found, exceptions will be sent to Sentry with env=%s", env
-        )
+    logger.debug(json.dumps(event))
+
+    if not os.getenv("WORKSPACE"):
+        raise RuntimeError("Required env variable WORKSPACE is not set")
 
     bucket = os.environ["BUCKET"]
     ssm_client = client("ssm", region_name="us-east-1")

setup.cfg

@@ -14,4 +14,7 @@ ignore_missing_imports = True
 ignore_missing_imports = True
 
 [mypy-smart_open.*]
-ignore_missing_imports = True
+ignore_missing_imports = True
+
+[tool:pytest]
+log_level = INFO

test_ppod.py

@@ -1,8 +1,9 @@
-import logging
+from importlib import reload
 
 import pytest
 import requests
 
+import ppod
 from ppod import (
     add_namespaces_to_alma_marcxml,
     extract_files_from_tar,
@@ -12,25 +13,26 @@
 )
 
 
-def test_ppod_configures_sentry_if_dsn_present(
-    caplog, monkeypatch, request_data_matching_file
-):
+def test_ppod_configures_sentry_if_dsn_present(caplog, monkeypatch):
     monkeypatch.setenv("SENTRY_DSN", "https://1234567890@00000.ingest.sentry.io/123456")
-    caplog.set_level(logging.INFO)
-    lambda_handler(request_data_matching_file, {})
+    reload(ppod)
     assert (
         "Sentry DSN found, exceptions will be sent to Sentry with env=test"
         in caplog.text
     )
 
 
-def test_ppod_doesnt_configure_sentry_if_dsn_not_present(
-    caplog, monkeypatch, request_data_matching_file
-):
+def test_ppod_doesnt_configure_sentry_if_dsn_not_present(caplog, monkeypatch):
     monkeypatch.delenv("SENTRY_DSN", raising=False)
-    caplog.set_level(logging.INFO)
-    lambda_handler(request_data_matching_file, {})
-    assert "Sentry DSN found" not in caplog.text
+    reload(ppod)
+    assert "No Sentry DSN found, exceptions will not be sent to Sentry" in caplog.text
+
+
+def test_ppod_missing_workspace_env_raises_error(monkeypatch):
+    monkeypatch.delenv("WORKSPACE", raising=False)
+    with pytest.raises(RuntimeError) as e:
+        lambda_handler({}, {})
+    assert "Required env variable WORKSPACE is not set" in str(e)
 
 
 def test_ppod_matching_files(request_data_matching_file):