Initial commit

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

scripts/era1/01_test_data_engine.py

@@ -0,0 +1,77 @@
+#!/usr/bin/env python3
+"""
+测试脚本：验证数据引擎能正确读取和解析Excel数据
+"""
+import sys
+from pathlib import Path
+
+# 添加项目路径
+sys.path.insert(0, str(Path(__file__).parent.parent / "backend"))
+
+from app.engines.data_engine import DataEngine
+from app.config import DIMENSION_FRAMEWORK, SCHOOL_TYPE_MAP
+import json
+
+
+def main():
+    print("=" * 80)
+    print("数据引擎测试")
+    print("=" * 80)
+
+    engine = DataEngine()
+    engine.load_all()
+
+    # 1. 基本信息
+    summary = engine.summary()
+    print(f"\n📊 数据摘要:")
+    print(f"   学校数量: {summary['school_count']}")
+    print(f"   学校列表: {summary['schools']}")
+    print(f"   基础信息行数: {summary['basic_info_rows']}")
+    print(f"   课程实施行数: {summary['course_impl_rows']}")
+    print(f"   学科课程行数: {summary['subject_impl_rows']}")
+
+    # 2. 测试单校数据
+    test_school = "延安中学"
+    print(f"\n🏫 {test_school} 基本信息:")
+    info = engine.get_school_basic_info(test_school)
+    for k, v in info.items():
+        print(f"   {k}: {v}")
+
+    # 3. 测试课程数据
+    print(f"\n📚 {test_school} 课程实施数据:")
+    course_df = engine.get_school_course_data(test_school)
+    print(f"   总行数: {len(course_df)}")
+    print(f"   涉及学科: {sorted(course_df['学科'].unique().tolist())}")
+    print(f"   涉及题号: {sorted(course_df['题号'].unique().tolist())[:20]}...")
+
+    # 4. 测试学科数据
+    print(f"\n🔬 {test_school} 学科课程数据:")
+    subject_df = engine.get_school_subject_data(test_school)
+    print(f"   总行数: {len(subject_df)}")
+    print(f"   涉及学科: {sorted(subject_df['学科'].unique().tolist())}")
+
+    # 5. 测试周课时数据
+    print(f"\n⏰ {test_school} 周课时数据（前10行）:")
+    hours = engine.get_weekly_hours(test_school)
+    if len(hours) > 0:
+        print(hours[["学科", "年级", "学期", "字段名称", "字段取值"]].head(10).to_string())
+    else:
+        print("   无课时数据")
+
+    # 6. 测试课程规范数据
+    print(f"\n📋 {test_school} 课程规范数据（前5条）:")
+    norms = engine.get_course_norms(test_school)
+    for n in norms[:5]:
+        print(f"   {n['字段名称']}: {n['字段取值']}")
+
+    # 7. 所有学校类型
+    print(f"\n🏷️ 学校类型:")
+    for school in engine.schools:
+        info = SCHOOL_TYPE_MAP.get(school, {})
+        print(f"   {school}: {info.get('type', '未知')} ({info.get('nature', '')}) [{info.get('feature', '')}]")
+
+    print("\n✅ 数据引擎测试完成!")
+
+
+if __name__ == "__main__":
+    main()