feat: initial commit for merica-pipeline delivery

2026-10-08 19:33:15 +07:00
commit 42fedab752
46 changed files with 5484 additions and 0 deletions
@@ -0,0 +1,248 @@
+"""
+Unit tests for MericaAlertHook: multi-channel alerting, governance enrichment,
+and anti-alert fatigue throttling engine.
+"""
+import pytest
+from unittest.mock import patch, MagicMock
+from helpers.merica_alert_hook import MericaAlertHook, _ALERT_SUPPRESSION_CACHE
+
+
+@pytest.fixture(autouse=True)
+def clean_alert_cache():
+    """Clear suppression cache before and after every test."""
+    MericaAlertHook.clear_suppression_cache()
+    yield
+    MericaAlertHook.clear_suppression_cache()
+
+
+class TestMericaAlertHookChannels:
+    """Test individual dispatch channels for Telegram, Slack, Discord, SITOMAT."""
+
+    @patch("urllib.request.urlopen")
+    def test_send_webhook_success(self, mock_urlopen):
+        mock_resp = MagicMock()
+        mock_resp.status = 200
+        mock_urlopen.return_value.__enter__.return_value = mock_resp
+
+        result = MericaAlertHook.send_webhook("http://example.com/webhook", {"test": "data"})
+        assert result is True
+        mock_urlopen.assert_called_once()
+
+    @patch("urllib.request.urlopen")
+    def test_send_webhook_failure(self, mock_urlopen):
+        mock_urlopen.side_effect = Exception("Connection refused")
+        result = MericaAlertHook.send_webhook("http://example.com/webhook", {"test": "data"})
+        assert result is False
+
+    @patch("urllib.request.urlopen")
+    def test_send_telegram_alert(self, mock_urlopen):
+        mock_resp = MagicMock()
+        mock_resp.status = 200
+        mock_urlopen.return_value.__enter__.return_value = mock_resp
+
+        result = MericaAlertHook.send_telegram_alert(
+            bot_token="bot123456:ABC-DEF",
+            chat_id="-100987654321",
+            message="<b>Test Alert</b>"
+        )
+        assert result is True
+        args, kwargs = mock_urlopen.call_args
+        req = args[0]
+        assert "api.telegram.org/botbot123456:ABC-DEF/sendMessage" in req.full_url
+        assert b"-100987654321" in req.data
+
+    @patch("urllib.request.urlopen")
+    def test_send_slack_alert(self, mock_urlopen):
+        mock_resp = MagicMock()
+        mock_resp.status = 200
+        mock_urlopen.return_value.__enter__.return_value = mock_resp
+
+        result = MericaAlertHook.send_slack_alert(
+            webhook_url="https://hooks.slack.com/services/T00/B00/X00",
+            payload={"text": "Test Slack"}
+        )
+        assert result is True
+        args, kwargs = mock_urlopen.call_args
+        req = args[0]
+        assert "hooks.slack.com" in req.full_url
+
+    @patch("urllib.request.urlopen")
+    def test_send_discord_alert(self, mock_urlopen):
+        mock_resp = MagicMock()
+        mock_resp.status = 204
+        mock_urlopen.return_value.__enter__.return_value = mock_resp
+
+        result = MericaAlertHook.send_discord_alert(
+            webhook_url="https://discord.com/api/webhooks/123/abc",
+            payload={"content": "Test Discord"}
+        )
+        assert result is True
+
+    @patch("urllib.request.urlopen")
+    def test_send_sitomat_alert(self, mock_urlopen):
+        mock_resp = MagicMock()
+        mock_resp.status = 200
+        mock_urlopen.return_value.__enter__.return_value = mock_resp
+
+        result = MericaAlertHook.send_sitomat_alert(
+            endpoint_url="http://sitomat:8080/api/v1/lakehouse/webhook",
+            incident_payload={"incidentType": "TASK_FAILURE"},
+            api_key="secret-api-key"
+        )
+        assert result is True
+        args, kwargs = mock_urlopen.call_args
+        req = args[0]
+        assert req.headers.get("X-api-key") == "secret-api-key" or req.headers.get("Authorization") == "Bearer secret-api-key"
+
+
+class TestAntiAlertFatigue:
+    """Test suppression and throttling of duplicate/cascading incident alerts."""
+
+    def test_anti_alert_fatigue_throttling(self):
+        cache_key = "dag_permits:task_silver:TASK_FAILURE"
+
+        # Panggilan 1: Belum pernah terlihat, harus lolos (suppressed = False)
+        is_suppressed, count = MericaAlertHook.check_and_record_suppression(cache_key, window_seconds=300)
+        assert is_suppressed is False
+        assert count == 1
+
+        # Panggilan 2: Terjadi dalam 300s window, harus dibatasi (suppressed = True)
+        is_suppressed, count = MericaAlertHook.check_and_record_suppression(cache_key, window_seconds=300)
+        assert is_suppressed is True
+        assert count == 2
+
+        # Panggilan 3: Masih dalam window
+        is_suppressed, count = MericaAlertHook.check_and_record_suppression(cache_key, window_seconds=300)
+        assert is_suppressed is True
+        assert count == 3
+
+        # Reset cache manual
+        MericaAlertHook.clear_suppression_cache()
+        is_suppressed, count = MericaAlertHook.check_and_record_suppression(cache_key, window_seconds=300)
+        assert is_suppressed is False
+        assert count == 1
+
+
+class TestGovernanceEnrichment:
+    """Test governance metadata extraction and severity routing."""
+
+    def test_context_extraction_tier1_p0(self):
+        mock_dag = MagicMock()
+        mock_dag.dag_id = "gold_analytics_pipeline"
+        mock_dag.params = {
+            "domain": "TataLingkunganPerizinan",
+            "owner": "dlh_data_engineering_group",
+            "tier": "Tier.Tier1"
+        }
+
+        mock_ti = MagicMock()
+        mock_ti.task_id = "dbt_gold_mart"
+        mock_ti.try_number = 2
+        mock_ti.max_tries = 3
+        mock_ti.duration = 42.5
+        mock_ti.log_url = "http://localhost:8088/log/123"
+
+        context = {
+            "dag": mock_dag,
+            "task_instance": mock_ti,
+            "exception": Exception("Table locked by concurrent vacuum process")
+        }
+
+        data = MericaAlertHook.extract_context(context)
+        assert data["dag_id"] == "gold_analytics_pipeline"
+        assert data["task_id"] == "dbt_gold_mart"
+        assert data["try_number"] == 2
+        assert data["domain"] == "TataLingkunganPerizinan"
+        assert data["tier"] == "Tier.Tier1"
+        assert "P0 (CRITICAL)" in data["severity"]
+        assert data["color_hex"] == "#E01E5A"
+        assert "Table locked" in data["error_msg"]
+
+    def test_context_extraction_tier2_p1(self):
+        mock_dag = MagicMock()
+        mock_dag.dag_id = "silver_cleaning_pipeline"
+        mock_dag.params = {"tier": "Tier.Tier2"}
+
+        mock_ti = MagicMock()
+        mock_ti.task_id = "cleanse_task"
+        mock_ti.try_number = 1
+        mock_ti.duration = 10.0
+
+        context = {
+            "dag": mock_dag,
+            "task_instance": mock_ti,
+            "exception": Exception("Syntax error")
+        }
+
+        data = MericaAlertHook.extract_context(context)
+        assert "P1 (WARNING)" in data["severity"]
+        assert data["color_hex"] == "#ECB22E"
+
+
+class TestAirflowLifecycleCallbacks:
+    """Test failure, SLA miss, and quality breach lifecycle handlers."""
+
+    @patch("helpers.merica_alert_hook.MericaAlertHook.send_telegram_alert")
+    @patch("helpers.merica_alert_hook.MericaAlertHook.send_slack_alert")
+    def test_on_failure_callback_dispatches_channels(self, mock_slack, mock_tg, monkeypatch):
+        monkeypatch.setenv("ALERT_TELEGRAM_BOT_TOKEN", "mock_bot_token")
+        monkeypatch.setenv("ALERT_TELEGRAM_CHAT_ID", "mock_chat_id")
+        monkeypatch.setenv("ALERT_SLACK_WEBHOOK_URL", "https://hooks.slack.com/mock")
+
+        mock_slack.return_value = True
+        mock_tg.return_value = True
+
+        mock_dag = MagicMock()
+        mock_dag.dag_id = "permits_medallion"
+        mock_dag.params = {"tier": "Tier.Tier1", "domain": "Perizinan", "owner": "DE"}
+
+        mock_ti = MagicMock()
+        mock_ti.task_id = "quality_gate_silver"
+        mock_ti.duration = 15.0
+
+        context = {
+            "dag": mock_dag,
+            "task_instance": mock_ti,
+            "exception": Exception("Check constraint violated: status must be in set")
+        }
+
+        results = MericaAlertHook.on_failure_callback(context)
+        assert results.get("telegram") is True
+        assert results.get("slack") is True
+        mock_tg.assert_called_once()
+        mock_slack.assert_called_once()
+
+    @patch("helpers.merica_alert_hook.MericaAlertHook.dispatch_alert")
+    def test_sla_miss_callback(self, mock_dispatch):
+        mock_dispatch.return_value = {"telegram": True}
+        mock_dag = MagicMock()
+        mock_dag.dag_id = "sla_test_dag"
+
+        res = MericaAlertHook.sla_miss_callback(
+            dag=mock_dag,
+            task_list=["task_1"],
+            blocking_task_list=["task_1"],
+            slas=[30],
+            blocking_tis=[]
+        )
+        assert res == {"telegram": True}
+        mock_dispatch.assert_called_once()
+        call_args = mock_dispatch.call_args[0]
+        assert call_args[0] == "SLA_MISS"
+        assert call_args[1]["dag_id"] == "sla_test_dag"
+
+    @patch("helpers.merica_alert_hook.MericaAlertHook.dispatch_alert")
+    def test_on_quality_gate_breach(self, mock_dispatch):
+        mock_dispatch.return_value = {"slack": True}
+        context = {
+            "dag": MagicMock(dag_id="spku_iot_pipeline", params={"tier": "Tier.Tier2"}),
+            "task_instance": MagicMock(task_id="ge_pm25_check")
+        }
+        failed_rules = [{"rule": "expect_column_values_to_be_between", "column": "pm25"}]
+
+        res = MericaAlertHook.on_quality_gate_breach(context, failed_rules, 75.0)
+        assert res == {"slack": True}
+        call_args = mock_dispatch.call_args[0]
+        assert call_args[0] == "QUALITY_GATE_BREACH"
+        assert "75.0%" in call_args[1]["error_msg"]
+        assert "pm25" in call_args[1]["error_msg"]