doc_parser_skill: - New: verify_flowchart.py (flowchart validation) - Updated: LLM.py (multi-provider: DeepSeek + DashScope) - Updated: image_parser.py (logic tree support, external prompts) - Updated: SKILL.md, prompts/image_prompt.md conflict_detection_skill: - Updated: LLM.py (multi-provider sync) - Updated: detect_conflicts.py (logic tree text conversion) ir_generation_skill: - Replaced old scripts/LLM.py + ir_generator.py with standalone project - New: main.py, config.py, step1-3_*.py, ensemble_merge.py - New: prompts/, tests/ subdirectories tests: - New: acceptance/ test suite with schema validation - Fixed: conftest no longer globally skips non-acceptance tests - Updated: test_sample.py for new ir_generation structure Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,232 @@
|
||||
"""
|
||||
Tests for Stage 3 (Merge & Audit).
|
||||
|
||||
Validates:
|
||||
- ir_final.json exists and is well-formed
|
||||
- No duplicate rule_ids
|
||||
- All rule_ids follow new hierarchical naming convention
|
||||
- All rules have path arrays
|
||||
- ir_audit_report.md exists and contains all required sections
|
||||
"""
|
||||
|
||||
import re
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from collections import Counter
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent))
|
||||
import config
|
||||
|
||||
|
||||
PASS = "[PASS]"
|
||||
FAIL = "[FAIL]"
|
||||
WARN = "[WARN]"
|
||||
|
||||
|
||||
def load_ir_final():
|
||||
"""Load ir_final.json."""
|
||||
try:
|
||||
return config.load_json(config.IR_FINAL_JSON)
|
||||
except FileNotFoundError:
|
||||
print(f"{FAIL} ir_final.json 未找到: {config.IR_FINAL_JSON}")
|
||||
print(" 请先运行 step3_merge_and_audit.py")
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
def load_audit_report():
|
||||
"""Load ir_audit_report.md if it exists."""
|
||||
try:
|
||||
with open(config.IR_AUDIT_REPORT_MD, "r", encoding="utf-8") as f:
|
||||
return f.read()
|
||||
except FileNotFoundError:
|
||||
print(f"{FAIL} ir_audit_report.md 未找到: {config.IR_AUDIT_REPORT_MD}")
|
||||
print(" 请先运行 step3_merge_and_audit.py")
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
def check_rule_ids(ir: dict) -> list[str]:
|
||||
"""Check for duplicate rule_ids and hierarchical naming convention.
|
||||
|
||||
Format: DRL-001-DOMESTIC-SYS-FG-INTERRUPT-01
|
||||
"""
|
||||
errors = []
|
||||
rules = ir.get("rules", [])
|
||||
rule_ids = [r.get("rule_id", "") for r in rules]
|
||||
|
||||
# No duplicates
|
||||
duplicates = [rid for rid, count in Counter(rule_ids).items() if count > 1]
|
||||
if duplicates:
|
||||
errors.append(f"重复 rule_id: {duplicates}")
|
||||
|
||||
# New hierarchical naming convention
|
||||
pattern = re.compile(
|
||||
r"^[A-Z]+-\d{3}-(DOMESTIC|OVERSEAS)-"
|
||||
r"(SYS|SDK|OTHER)-"
|
||||
r"(FG-INTERRUPT|BG-BLOCK|BG-PAUSE|NO-RESTRICT|SWITCH-OFF)-\d{2}$"
|
||||
)
|
||||
for rid in rule_ids:
|
||||
if rid and not pattern.match(rid):
|
||||
errors.append(
|
||||
f"rule_id 命名不规范: '{rid}' "
|
||||
f"(期望: FEATURE-SCOPE-METHOD-BEHAVIOR-NN)"
|
||||
)
|
||||
|
||||
return errors
|
||||
|
||||
|
||||
def check_top_level_structure(ir: dict) -> list[str]:
|
||||
"""Check that ir_final has the required top-level fields."""
|
||||
errors = []
|
||||
for field in ["feature", "feature_id", "rules"]:
|
||||
if field not in ir:
|
||||
errors.append(f"ir_final 缺少顶层字段: {field}")
|
||||
|
||||
if not isinstance(ir.get("rules"), list):
|
||||
errors.append("ir_final.rules 必须是数组")
|
||||
elif len(ir["rules"]) == 0:
|
||||
errors.append("ir_final.rules 为空")
|
||||
|
||||
return errors
|
||||
|
||||
|
||||
def check_rule_paths(rules: list[dict]) -> list[str]:
|
||||
"""Every rule must have a non-empty path array."""
|
||||
errors = []
|
||||
for rule in rules:
|
||||
rid = rule.get("rule_id", "?")
|
||||
path = rule.get("path", [])
|
||||
if not path:
|
||||
errors.append(f"{rid}: path 字段为空或缺失")
|
||||
return errors
|
||||
|
||||
|
||||
def check_rule_completeness(rules: list[dict]) -> list[str]:
|
||||
"""Check each rule has all required fields."""
|
||||
errors = []
|
||||
required_fields = [
|
||||
"rule_id", "description", "priority", "sources",
|
||||
"precondition", "trigger", "actions"
|
||||
]
|
||||
for i, rule in enumerate(rules):
|
||||
rid = rule.get("rule_id", f"rule[{i}]")
|
||||
for field in required_fields:
|
||||
if field not in rule:
|
||||
errors.append(f"{rid}: 缺少字段 '{field}'")
|
||||
if not rule.get("sources"):
|
||||
errors.append(f"{rid}: sources 为空")
|
||||
if not rule.get("actions"):
|
||||
errors.append(f"{rid}: actions 为空")
|
||||
# Check precondition fields
|
||||
precond = rule.get("precondition", {})
|
||||
if not precond.get("geographic_scope"):
|
||||
errors.append(f"{rid}: precondition.geographic_scope 缺失")
|
||||
if "screen_type" not in precond:
|
||||
errors.append(f"{rid}: precondition.screen_type 缺失")
|
||||
return errors
|
||||
|
||||
|
||||
def check_audit_report(report: str) -> list[str]:
|
||||
"""Check audit report has all required sections."""
|
||||
errors = []
|
||||
|
||||
required_sections = [
|
||||
"逻辑树路径覆盖率",
|
||||
"表格枚举覆盖",
|
||||
"开关状态",
|
||||
"一致性扫描报告",
|
||||
"自动补全摘要",
|
||||
"规则清单",
|
||||
]
|
||||
for section in required_sections:
|
||||
if section not in report:
|
||||
errors.append(f"审计报告缺少章节: {section}")
|
||||
|
||||
# Should have the human review notice
|
||||
if "人工审查" not in report:
|
||||
errors.append("审计报告缺少人工审查提示")
|
||||
|
||||
return errors
|
||||
|
||||
|
||||
def run_all_tests():
|
||||
print("=" * 60)
|
||||
print("Step 3 自检测试")
|
||||
print("=" * 60)
|
||||
|
||||
ir = load_ir_final()
|
||||
report = load_audit_report()
|
||||
rules = ir.get("rules", [])
|
||||
all_errors = []
|
||||
|
||||
# Test 1: Top-level structure
|
||||
errors = check_top_level_structure(ir)
|
||||
if errors:
|
||||
print(f"\n{FAIL} 顶层结构检查: {len(errors)} 个错误")
|
||||
for e in errors:
|
||||
print(f" - {e}")
|
||||
all_errors.extend(errors)
|
||||
else:
|
||||
print(f"\n{PASS} 顶层结构检查: 通过 "
|
||||
f"(feature={ir.get('feature')}, feature_id={ir.get('feature_id')})")
|
||||
|
||||
# Test 2: rule_id uniqueness and naming
|
||||
errors = check_rule_ids(ir)
|
||||
if errors:
|
||||
print(f"\n{FAIL} rule_id 检查: {len(errors)} 个错误")
|
||||
for e in errors:
|
||||
print(f" - {e}")
|
||||
all_errors.extend(errors)
|
||||
else:
|
||||
print(f"\n{PASS} rule_id 检查: 全部通过 ({len(rules)} 个唯一 ID, 层次化格式)")
|
||||
|
||||
# Test 3: Rule path fields
|
||||
errors = check_rule_paths(rules)
|
||||
if errors:
|
||||
print(f"\n{FAIL} 规则 path 字段: {len(errors)} 个错误")
|
||||
for e in errors[:10]:
|
||||
print(f" - {e}")
|
||||
all_errors.extend(errors)
|
||||
else:
|
||||
print(f"\n{PASS} 规则 path 字段: 全部通过")
|
||||
|
||||
# Test 4: Rule field completeness
|
||||
errors = check_rule_completeness(rules)
|
||||
if errors:
|
||||
print(f"\n{FAIL} 规则字段完整性: {len(errors)} 个错误")
|
||||
for e in errors[:10]:
|
||||
print(f" - {e}")
|
||||
if len(errors) > 10:
|
||||
print(f" ... 还有 {len(errors) - 10} 个")
|
||||
all_errors.extend(errors)
|
||||
else:
|
||||
print(f"\n{PASS} 规则字段完整性: 全部通过")
|
||||
|
||||
# Test 5: Audit report content
|
||||
errors = check_audit_report(report)
|
||||
if errors:
|
||||
print(f"\n{FAIL} 审计报告检查: {len(errors)} 个错误")
|
||||
for e in errors:
|
||||
print(f" - {e}")
|
||||
all_errors.extend(errors)
|
||||
else:
|
||||
print(f"\n{PASS} 审计报告检查: 全部通过 (6 个章节)")
|
||||
|
||||
# Summary
|
||||
print(f"\n{'='*60}")
|
||||
total_failures = len(all_errors)
|
||||
|
||||
if total_failures == 0:
|
||||
print(f"{PASS} 所有测试通过!")
|
||||
print(f"\n最终交付物:")
|
||||
print(f" - {config.IR_FINAL_JSON} ({len(rules)} 条规则)")
|
||||
print(f" - {config.IR_AUDIT_REPORT_MD}")
|
||||
else:
|
||||
print(f"{FAIL} 测试失败: {total_failures} 个错误")
|
||||
print("\n建议: 检查 ir_fragments.json 和合并逻辑，修复问题后重新运行 step3_merge_and_audit.py")
|
||||
|
||||
return total_failures == 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
success = run_all_tests()
|
||||
sys.exit(0 if success else 1)
|
||||
Reference in New Issue
Block a user