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>
107 lines
3.4 KiB
Python
107 lines
3.4 KiB
Python
"""
|
||
质量门禁 — 执行前检查测试数据是否满足覆盖率和边界要求。
|
||
|
||
Phase 1 可用: 决策点覆盖、段落覆盖
|
||
Phase 2 启用: HINA 必须项、字段覆盖
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
from typing import Any
|
||
|
||
|
||
def check(
|
||
complete_tests: list,
|
||
hina_result: dict,
|
||
coverage: dict,
|
||
decision_threshold: float = 0.90,
|
||
paragraph_threshold: float = 1.0,
|
||
) -> dict:
|
||
"""质量门禁检查。
|
||
|
||
Args:
|
||
complete_tests: 完整的测试数据集
|
||
hina_result: HINA 分类结果
|
||
coverage: check_coverage() 输出的覆盖率数据
|
||
decision_threshold: 决策点覆盖率阈值
|
||
paragraph_threshold: 段落覆盖率阈值
|
||
|
||
Returns:
|
||
dict with: passed, score, issues
|
||
"""
|
||
issues = {}
|
||
|
||
branch_rate = coverage.get("branch_rate", 0.0)
|
||
if branch_rate < decision_threshold:
|
||
issues["decision_gaps"] = coverage.get("uncovered_decision_ids", [])
|
||
|
||
paragraph_rate = coverage.get("paragraph_rate", 0.0)
|
||
if paragraph_rate < paragraph_threshold:
|
||
issues.setdefault("paragraph_gaps", []).append(
|
||
f"段落覆盖率不足: {paragraph_rate:.0%}"
|
||
)
|
||
|
||
if not complete_tests:
|
||
issues["no_data"] = True
|
||
|
||
passed = len(issues) == 0
|
||
score = _compute_score(coverage, hina_result)
|
||
|
||
return {"passed": passed, "score": score, "issues": issues}
|
||
|
||
|
||
def _compute_score(coverage: dict, hina_result: dict) -> float:
|
||
"""质量评分公式（COBOL 版）。
|
||
|
||
评分 = 覆盖质量 × 0.6 + 边界质量 × 0.4
|
||
覆盖质量 = 段落覆盖率 × 0.5 + 分支覆盖率 × 0.5
|
||
边界质量 = HINA 必须项覆盖率（Phase 2 后启用，默认 1.0）
|
||
"""
|
||
paragraph_rate = coverage.get("paragraph_rate", 0.0)
|
||
branch_rate = coverage.get("branch_rate", 0.0)
|
||
|
||
coverage_quality = paragraph_rate * 0.5 + branch_rate * 0.5
|
||
boundary_quality = 1.0
|
||
|
||
return round(coverage_quality * 0.6 + boundary_quality * 0.4, 2)
|
||
|
||
|
||
def compute_quality_score(
|
||
static_coverage: dict[str, Any],
|
||
gcov_coverage: dict[str, Any] | None = None,
|
||
confidence: float = 0.5,
|
||
) -> float:
|
||
"""双模式质量评分。
|
||
|
||
模式 1 — gcov 未启用 (gcov_coverage is None):
|
||
score = branch_rate × 0.5 + paragraph_rate × 0.5 + confidence × 0.4
|
||
其中 confidence 作为加分项（最高 +0.4）
|
||
|
||
模式 2 — gcov 启用:
|
||
score = static_cov × 0.3 + gcov_cov × 0.4 + confidence × 0.3
|
||
其中 static_cov = branch_rate × 0.5 + paragraph_rate × 0.5
|
||
|
||
Args:
|
||
static_coverage: 静态覆盖率数据
|
||
{"branch_rate": float, "paragraph_rate": float, ...}
|
||
gcov_coverage: gcov 动态覆盖率数据，None 表示未启用
|
||
{"gcov_cov": float, ...} 或 None
|
||
confidence: 确信度 (0.0 ~ 1.0)
|
||
|
||
Returns:
|
||
float: 质量评分 (0.0 ~ 1.0)
|
||
"""
|
||
branch_rate = static_coverage.get("branch_rate", 0.0)
|
||
paragraph_rate = static_coverage.get("paragraph_rate", 0.0)
|
||
static_cov = branch_rate * 0.5 + paragraph_rate * 0.5
|
||
|
||
if gcov_coverage is not None:
|
||
# 模式 2: gcov 启用
|
||
gcov_cov = gcov_coverage.get("gcov_cov", 0.0)
|
||
score = static_cov * 0.3 + gcov_cov * 0.4 + confidence * 0.3
|
||
else:
|
||
# 模式 1: gcov 未启用 — confidence 作为加分
|
||
score = branch_rate * 0.5 + paragraph_rate * 0.5 + confidence * 0.4
|
||
|
||
return round(min(score, 1.0), 4)
|