from pathlib import Path from studio.domain import normalize_catalog, parse_quota, select_score_lines from studio.database import Database def raw_catalog(): return { "dwdm": "10001", "dwmc": "北京大学", "szss": "北京", "zydm": "081200", "zymc": "计算机科学与技术", "xwlxmc": "学术学位", "yxsdm": "001", "yxsmc": "计算机学院", "yjfxdm": "01", "yjfxmc": "人工智能", "xxfs": "1", "ksfsmc": "全国统考", "nzsrsstr": "专业:6(不含推免)", "kskmz": [ {"km1Vo": {"kskmmc": "101思想政治理论"}, "km2Vo": {"kskmmc": "201英语(一)"}, "km3Vo": {"kskmmc": "301数学(一)"}, "km4Vo": {"kskmmc": "408计算机学科专业基础"}}, {"km1Vo": {"kskmmc": "101思想政治理论"}, "km2Vo": {"kskmmc": "203日语"}, "km3Vo": {"kskmmc": "301数学(一)"}, "km4Vo": {"kskmmc": "408计算机学科专业基础"}}, ], } def test_distinct_exam_combinations_are_preserved(): records = normalize_catalog(raw_catalog(), 2027) assert len(records) == 2 assert records[0]["subjects"][1] == "201英语(一)" assert records[1]["subjects"][1] == "203日语" assert records[0]["record_key"] != records[1]["record_key"] def test_ambiguous_quota_is_not_converted_to_major_total(): assert parse_quota("专业:6(不含推免)") == (6, "major") assert parse_quota("学院:100(含推免80)") == (None, "college") assert parse_quota("研究方向:6") == (None, "direction") assert parse_quota("拟招人数待定") == (None, "unknown") assert parse_quota("专业:0(不含推免)") == (0, "major") def test_history_is_preserved_across_years_and_reruns(tmp_path: Path): db = Database(tmp_path / "studio.db") db.upsert_catalog(normalize_catalog(raw_catalog(), 2026)) db.upsert_catalog(normalize_catalog(raw_catalog(), 2027)) db.upsert_catalog(normalize_catalog(raw_catalog(), 2027)) assert db.query_catalog({})["total"] == 4 result = db.query_catalog({"year": 2027, "subject": "203"}) assert result["total"] == 1 rid = result["items"][0]["id"] db.favorite(rid, True) assert db.query_catalog({"favorites": True})["total"] == 1 def test_score_line_match_does_not_promote_category_to_major(): rows = [{"code": "08", "total": "300"}, {"code": "0812", "total": "310"}, {"code": "081200", "total": "320"}] scores = select_score_lines(rows, "081200", "10001", "北京大学", 2026) assert len(scores) == 1 assert scores[0]["total"] == 320 assert scores[0]["scope"] == "major" fallback = select_score_lines(rows[:1], "081200", "10001", "北京大学", 2025)[0] assert fallback["scope"] == "category" assert fallback["raw_code"] == "08" def test_same_year_different_college_lines_are_not_attached_arbitrarily(tmp_path: Path): db = Database(tmp_path / "studio.db") db.upsert_catalog(normalize_catalog(raw_catalog(), 2026)) rows = [{"code": "081200", "total": "350", "depart_id": "999", "depart_name": "其他学院"}] db.upsert_scores(select_score_lines(rows, "081200", "10001", "北京大学", 2026)) assert db.query_catalog({"year": 2026})["items"][0]["score_total"] is None def test_special_plan_score_does_not_overwrite_regular_admission_line(tmp_path): db = Database(tmp_path / "studio.db") db.upsert_catalog(normalize_catalog(raw_catalog(), 2026)) rows = [{"code": "081200", "total": "320", "depart_id": "001", "note": ""}, {"code": "081200", "total": "260", "depart_id": "001", "note": "少干专项计划"}] db.upsert_scores(select_score_lines(rows, "081200", "10001", "北京大学", 2026)) assert db.overview()["scores"] == 2 assert db.query_catalog({})["items"][0]["score_total"] == 320 def test_special_plan_full_names_are_not_used_as_regular_reference_line(tmp_path): db = Database(tmp_path / 'studio.db') db.upsert_catalog(normalize_catalog(raw_catalog(), 2026)) rows = [{'code': '081200', 'total': 320, 'depart_id': '001', 'note': ''}, {'code': '081200', 'total': 260, 'depart_id': '001', 'note': '少数民族骨干计划'}, {'code': '081200', 'total': 250, 'depart_id': '001', 'note': '退役大学生士兵计划'}] db.upsert_scores(select_score_lines(rows, '081200', '10001', '北京大学', 2026)) assert db.query_catalog({})['items'][0]['score_total'] == 320 def test_spreadsheet_roundtrip_preserves_record_identity(tmp_path): from studio.imports import export_sheet, import_file db = Database(tmp_path / 'studio.db') records = normalize_catalog(raw_catalog(), 2027) db.upsert_catalog(records) for kind in ('csv', 'xlsx'): path = tmp_path / ('data.' + kind) path.write_bytes(export_sheet(records, kind)) imported, _ = import_file(path) db.upsert_catalog(imported) assert db.query_catalog({})['total'] == 2 def test_known_historical_school_levels_are_available_in_filters(tmp_path): db = Database(tmp_path / 'studio.db') db.upsert_catalog(normalize_catalog(raw_catalog(), 2027)) assert db.query_catalog({'level': '985'})['total'] == 2 assert db.query_catalog({'level': '211'})['total'] == 2 def test_imported_college_quota_cannot_be_promoted_by_numeric_column(): from studio.imports import row_record row = row_record({'school_name':'Test','major_code':'081200','enrollment_text':'学院:100','enrollment_count':100},2026) assert row['quota'] is None assert row['quota_scope'] == 'college' def test_job_school_keyword_does_not_match_department_names(tmp_path): db = Database(tmp_path / 'studio.db') item = raw_catalog() item['yxsmc'] = '信息学院' db.upsert_catalog(normalize_catalog(item, 2027)) assert db.query_catalog({'school_keyword': '信息'})['total'] == 0 def test_yam_reference_books_are_arrays_for_the_detail_view(): from studio.imports import row_record row = row_record({'school_name':'Test','major_code':'081200','reference_books':'[]'},2026) assert row['reference_books'] == []