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>
59 lines
2.0 KiB
Python
59 lines
2.0 KiB
Python
import subprocess
|
|
import logging
|
|
from pathlib import Path
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def collect_gcov(cobol_src: Path, work_dir: Path) -> dict:
|
|
try:
|
|
cd = str(work_dir)
|
|
gcda_files = list(Path(cd).glob("*.gcda"))
|
|
if not gcda_files:
|
|
logger.warning("[gcov] 未找到 .gcda 文件，可能未启用插桩编译")
|
|
return {"available": False, "reason": "no_gcda_files"}
|
|
|
|
result = subprocess.run(
|
|
["gcov", cobol_src.name],
|
|
capture_output=True, text=True, timeout=30,
|
|
cwd=cd,
|
|
)
|
|
|
|
if result.returncode != 0:
|
|
logger.warning(f"[gcov] gcov 执行失败: {result.stderr[:200]}")
|
|
return {"available": False, "reason": "gcov_failed"}
|
|
|
|
gcov_file = Path(cd) / f"{cobol_src.stem}.cbl.gcov"
|
|
if not gcov_file.exists():
|
|
gcov_file = Path(cd) / f"{cobol_src.stem}.gcov"
|
|
|
|
if not gcov_file.exists():
|
|
logger.warning("[gcov] .gcov 文件未生成")
|
|
return {"available": False, "reason": "no_gcov_output"}
|
|
|
|
total_lines = 0
|
|
executed_lines = 0
|
|
with open(str(gcov_file), encoding="utf-8", errors="replace") as f:
|
|
for line in f:
|
|
stripped = line.strip()
|
|
if stripped and not stripped.startswith("-"):
|
|
total_lines += 1
|
|
if not stripped.startswith("#"):
|
|
executed_lines += 1
|
|
|
|
line_rate = executed_lines / max(total_lines, 1)
|
|
|
|
return {
|
|
"available": True,
|
|
"line_rate": round(line_rate, 4),
|
|
"total_lines": total_lines,
|
|
"executed_lines": executed_lines,
|
|
}
|
|
|
|
except FileNotFoundError:
|
|
logger.warning("[gcov] gcov 命令未找到，降级为仅静态分析")
|
|
return {"available": False, "reason": "gcov_not_installed"}
|
|
except Exception as e:
|
|
logger.warning(f"[gcov] 采集异常: {e}")
|
|
return {"available": False, "reason": str(e)[:100]}
|