调整列名并添加输入验证

.dockerignore

@@ -1,16 +1,16 @@
-__pycache__/
+.git
+.agents
+.codex
+__pycache__
 *.pyc
 *.pyo
-.git/
-.agents/
-.codex/
-node_modules/
-.env
-
-app.log
-server.out.log
-server.err.log
-data/
+.pytest_cache
+node_modules
+data
+uploads
+static/images
 pipe_survival_0331.db
-uploads/
-static/images/
+app.log
+server.err.log
+server.out.log
+.env

Dockerfile

@@ -22,6 +22,7 @@ COPY templates ./templates
 COPY static ./static
 COPY main.py .
 COPY example.xlsx .
+COPY 20260630标准文本——供水管道健康状态与剩余寿命评估技术导则.pdf .
 COPY my_survival_forest_model_quxi-10-0331.joblib .
 
 RUN mkdir -p data static/images uploads

app/prediction.py

@@ -57,7 +57,17 @@ FEATURES = [
 ]
 
 ID_COLUMN = "管道编号"
-PIPE_AGE_COLUMN = "管龄"
+PIPE_AGE_COLUMN = "管龄（年）"
+LEGACY_PIPE_AGE_COLUMN = "管龄"
+STATUS_COLUMN = "状态"
+EVENT_AGE_COLUMN = "事件/观察管龄（年）"
+INPUT_COLUMNS = [
+    ID_COLUMN,
+    PIPE_AGE_COLUMN,
+    STATUS_COLUMN,
+    EVENT_AGE_COLUMN,
+    *FEATURES,
+]
 MATERIAL_COLUMN = "管材"
 MATERIAL_CODE_OPTIONS = [
     (1, "镀锌"),
@@ -183,11 +193,19 @@ def secure_upload_name(original_filename: str, run_id: str) -> tuple[str, str]:
 def read_input_file(path: Path, suffix: str) -> pd.DataFrame:
     try:
         if suffix == ".csv":
-            return pd.read_csv(path, dtype={ID_COLUMN: "string"})
-        return pd.read_excel(path, dtype={ID_COLUMN: "string"})
+            df = pd.read_csv(path, dtype={ID_COLUMN: "string"})
+        else:
+            df = pd.read_excel(path, dtype={ID_COLUMN: "string"})
     except Exception as exc:
         logging.exception("文件解析失败: %s", exc)
         raise PredictionError("文件解析失败，请检查编码或表格格式。")
+    return normalize_input_columns(df)
+
+
+def normalize_input_columns(df: pd.DataFrame) -> pd.DataFrame:
+    if PIPE_AGE_COLUMN not in df.columns and LEGACY_PIPE_AGE_COLUMN in df.columns:
+        return df.rename(columns={LEGACY_PIPE_AGE_COLUMN: PIPE_AGE_COLUMN})
+    return df
 
 
 def normalize_id_value(value: Any, fallback: str) -> str:
@@ -201,8 +219,7 @@ def normalize_id_value(value: Any, fallback: str) -> str:
 def validate_input_frame(df: pd.DataFrame) -> None:
     if df.empty:
         raise PredictionError("上传文件没有可预测的数据。")
-    required_columns = [ID_COLUMN, *FEATURES]
-    missing = [col for col in required_columns if col not in df.columns]
+    missing = [col for col in INPUT_COLUMNS if col not in df.columns]
     if missing:
         raise PredictionError(f"缺少必要字段: {', '.join(missing)}")
 
@@ -447,8 +464,8 @@ def render_survival_chart(df: pd.DataFrame, curves, image_path: Path) -> tuple[l
         )
         summary_sheet_rows.append(
             {
-                "管道编号": pipe_id,
-                "管龄": pipe_age,
+                ID_COLUMN: pipe_id,
+                PIPE_AGE_COLUMN: pipe_age,
                 "健康等级": grade_label,
             }
         )

tests/test_prediction.py

@@ -11,6 +11,7 @@ from openpyxl import load_workbook
 from app.prediction import (
     FEATURES,
     ID_COLUMN,
+    INPUT_COLUMNS,
     PIPE_AGE_COLUMN,
     PredictionError,
     estimate_remaining_life,
@@ -59,6 +60,18 @@ class PredictionHelpersTest(unittest.TestCase):
 
         self.assertIn("缺少必要字段", ctx.exception.message)
 
+    def test_validate_input_frame_accepts_current_template_columns(self) -> None:
+        df = pd.DataFrame([{column: 1 for column in INPUT_COLUMNS}])
+
+        validate_input_frame(df)
+
+    def test_example_workbook_columns_match_backend_contract(self) -> None:
+        workbook = load_workbook(Path(__file__).resolve().parents[1] / "example.xlsx", read_only=True)
+        worksheet = workbook["Template"]
+        headers = [cell.value for cell in next(worksheet.iter_rows(min_row=1, max_row=1))]
+
+        self.assertEqual(headers, INPUT_COLUMNS)
+
     def test_read_input_file_preserves_text_pipe_ids(self) -> None:
         with TemporaryDirectory() as temp_dir:
             output_path = Path(temp_dir) / "input.xlsx"
@@ -97,8 +110,8 @@ class PredictionHelpersTest(unittest.TestCase):
         ]
         summary_rows = [{"pipe_id": "P001"}, {"pipe_id": "P002"}]
         summary_sheet_rows = [
-            {"管道编号": "P001", "管龄": "10 年", "健康概率": 0.7, "预计剩余寿命": 2.0, "健康等级": "IV级"},
-            {"管道编号": "P002", "管龄": "12 年", "健康概率": 0.6, "预计剩余寿命": 1.5, "健康等级": "III级"},
+            {ID_COLUMN: "P001", PIPE_AGE_COLUMN: "10 年", "健康概率": 0.7, "预计剩余寿命": 2.0, "健康等级": "IV级"},
+            {ID_COLUMN: "P002", PIPE_AGE_COLUMN: "12 年", "健康概率": 0.6, "预计剩余寿命": 1.5, "健康等级": "III级"},
         ]
 
         with TemporaryDirectory() as temp_dir: