feat: 实现干扰小时指标自动处理

tests/test_pipeline.py

@@ -0,0 +1,118 @@
+from __future__ import annotations
+
+import csv
+from datetime import datetime
+import io
+import json
+from pathlib import Path
+import tempfile
+import unittest
+import zipfile
+
+from openpyxl import Workbook
+
+import main
+
+
+COMPLETE_WINDOW = "2026073110001100"
+INCOMPLETE_WINDOW = "2026073111001200"
+
+
+class PipelineTest(unittest.TestCase):
+    def test_latest_complete_window_is_converted_and_merged(self) -> None:
+        with tempfile.TemporaryDirectory() as temp:
+            root = Path(temp) / "source"
+            output = Path(temp) / "output"
+            for source_type in main.EXPECTED_TYPES:
+                create_archive(root, source_type, COMPLETE_WINDOW)
+            create_archive(root, main.EXPECTED_TYPES[0], INCOMPLETE_WINDOW)
+
+            result = main.process(main.LocalSource(root), output, lookback_days=3)
+
+            self.assertEqual(result.name, COMPLETE_WINDOW)
+            converted = sorted((result / "converted").glob("*.csv"))
+            self.assertEqual(len(converted), 7)
+            with (result / f"interference_summary_{COMPLETE_WINDOW}.csv").open(encoding="utf-8-sig", newline="") as file:
+                rows = list(csv.DictReader(file))
+            self.assertEqual(len(rows), 7)
+            self.assertEqual({row["source_type"] for row in rows}, set(main.EXPECTED_TYPES))
+            self.assertIn("460-00-100-1", {row["cgi"] for row in rows})
+            self.assertIn("46000-100-1", {row["cgi"] for row in rows})
+            self.assertTrue(all(row["interference_dbm"] == "-100.5" for row in rows))
+
+            manifest = json.loads((result / "manifest.json").read_text(encoding="utf-8"))
+            self.assertEqual(manifest["source_file_count"], 7)
+            self.assertEqual(manifest["summary_rows"], 7)
+            self.assertEqual(len(manifest["warnings"]), 1)
+            self.assertIn(INCOMPLETE_WINDOW, manifest["warnings"][0])
+
+    def test_requested_incomplete_window_is_rejected(self) -> None:
+        with tempfile.TemporaryDirectory() as temp:
+            root = Path(temp) / "source"
+            create_archive(root, main.EXPECTED_TYPES[0], INCOMPLETE_WINDOW)
+
+            with self.assertRaisesRegex(main.ProcessingError, "Requested window is incomplete"):
+                main.process(main.LocalSource(root), Path(temp) / "output", 3, INCOMPLETE_WINDOW)
+
+    def test_schema_change_is_rejected(self) -> None:
+        with tempfile.TemporaryDirectory() as temp:
+            root = Path(temp) / "source"
+            for source_type in main.EXPECTED_TYPES:
+                create_archive(root, source_type, COMPLETE_WINDOW, bad_header=source_type == main.EXPECTED_TYPES[0])
+
+            with self.assertRaisesRegex(main.ProcessingError, "Unexpected Sheet0 header"):
+                main.process(main.LocalSource(root), Path(temp) / "output", 3)
+
+    def test_cross_midnight_window(self) -> None:
+        self.assertEqual(
+            main.window_bounds("2026073023000000"),
+            ("2026-07-30 23:00:00", "2026-07-31 00:00:00"),
+        )
+
+
+def create_archive(root: Path, source_type: str, window: str, bad_header: bool = False) -> None:
+    date_dir = root / f"{window[:4]}-{window[4:6]}-{window[6:8]}"
+    date_dir.mkdir(parents=True, exist_ok=True)
+    filename = f"{source_type}_LWP_每小时_过滤110_{window}"
+    workbook = Workbook()
+    sheet = workbook.active
+    sheet.title = "Sheet0"
+    header = list(main.EXPECTED_HEADERS[source_type])
+    if bad_header:
+        header[-1] = "unexpected"
+    sheet.append(header)
+    sheet.append(mock_row(source_type, window))
+    metadata = workbook.create_sheet("指标(计数器)")
+    metadata.append(["指标或计数器", "指标或计数器描述", "指标公式", "指标或计数器状态"])
+    content = io.BytesIO()
+    workbook.save(content)
+    workbook.close()
+    with zipfile.ZipFile(date_dir / f"{filename}.zip", "w", zipfile.ZIP_DEFLATED) as archive:
+        archive.writestr(f"{filename}.xlsx", content.getvalue())
+
+
+def mock_row(source_type: str, window: str) -> list[object]:
+    header = main.EXPECTED_HEADERS[source_type]
+    values: dict[str, object] = {column: "mock" for column in header}
+    values.update(
+        {
+            "开始时间": datetime.strptime(window[:12], "%Y%m%d%H%M"),
+            "粒度": "1 小时",
+            "eNodeBId": 100,
+            "eNodeBID": 100,
+            "cellId": 1,
+            "小区ID": 1,
+            "masterOperatorId": "46000-100-1",
+            "E-UTRAN FDD小区名称": f"{source_type}-小区",
+            "E-UTRAN TDD小区名称": f"{source_type}-小区",
+            "CU小区配置名称": f"{source_type}-小区",
+            "小区名称": f"{source_type}-小区",
+            "载波平均噪声干扰(dBm)": -100.5,
+            "小区上行平均干扰电平(dBm)": -100.5,
+        }
+    )
+    return [values[column] for column in header]
+
+
+if __name__ == "__main__":
+    unittest.main()