hangshuo652
bc1d56d1a4
P0.6: gcov infrastructure P1: extract_structure output expansion (11 new feature fields) P2: Confusion group rule engine (8 pairs + contradiction + backtrack) P3: 4-factor confidence calculation + quality gate update P4: 33+2 COBOL program type test samples (22 files, 7 categories) P5: parametrized/ test data generation engine P6: japanese_data.py lookup tables P7-10: Type-specific test suites (~159 parametrized tests) P11: Full classification pipeline (classify_program) + orchestrator integration P12: Documentation (module-interfaces, test-plan v3.0, coverage-matrix) Architecture decisions: - classification_pipeline/ merged to hina/pipeline/ - parametrized/ as independent module - japanese_data.py as root-level file - hina/__all__ only exports classify_program() Co-Authored-By: Claude <noreply@anthropic.com>
67 lines
2.1 KiB
Python
67 lines
2.1 KiB
Python
"""测试数据模型 — 测试用例 + 测试套件 + Spark 配置
|
||
|
||
使用例:
|
||
tc = TestCase(id="TC-001", fields={"TX-AMOUNT": 1500000})
|
||
suite = TestSuite(test_cases=[tc], spark_config=SparkConfig(num_records=1000))
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
from dataclasses import dataclass, field
|
||
from typing import Optional
|
||
|
||
|
||
@dataclass
|
||
class SparkConfig:
|
||
"""Spark 测试数据生成配置。
|
||
|
||
────────── 字段说明 ──────────
|
||
num_records — 生成的记录数
|
||
replication — 复制策略: "key_varied" / "exact_copy"
|
||
key_field — 键字段名（key_varied 用）
|
||
edge_cases — 边缘 case: ["null","max","min","empty"]
|
||
"""
|
||
num_records: int = 100
|
||
replication: str = "key_varied"
|
||
key_field: str = ""
|
||
edge_cases: list[str] = field(default_factory=list)
|
||
|
||
|
||
@dataclass
|
||
class TestCase:
|
||
"""单条测试用例 — 一条待验证的字段值组合。
|
||
|
||
────────── 字段说明 ──────────
|
||
id — 用例 ID（如 "TC-001"）
|
||
fields — {字段名: 值}
|
||
coverage_targets — 覆盖的决策点 ID 列表
|
||
"""
|
||
id: str
|
||
fields: dict = field(default_factory=dict)
|
||
coverage_targets: list[str] = field(default_factory=list)
|
||
|
||
|
||
@dataclass
|
||
class TestSuite:
|
||
"""测试套件 — 多条用例 + 可选 Spark 配置。
|
||
|
||
────────── 字段说明 ──────────
|
||
schema — 可选的字段 schema
|
||
test_cases — 测试用例列表
|
||
spark_config — None 表示非 Spark 模式
|
||
"""
|
||
schema: Optional[dict] = None
|
||
test_cases: list[TestCase] = field(default_factory=list)
|
||
spark_config: Optional[SparkConfig] = None
|
||
|
||
@property
|
||
def has_spark(self) -> bool:
|
||
return self.spark_config is not None
|
||
|
||
|
||
_tc = TestCase(id="TC-001", fields={"BR-AMT": 1500000})
|
||
assert _tc.id == "TC-001"
|
||
assert _tc.fields["BR-AMT"] == 1500000
|
||
|
||
_ts = TestSuite(test_cases=[_tc], spark_config=SparkConfig(num_records=1000))
|
||
assert _ts.spark_config.num_records == 1000
|