scalebox-sdk 0.1.0__py3-none-any.whl

scalebox/test/run_all_validation_tests.py

@@ -0,0 +1,334 @@
+#!/usr/bin/env python3
+"""
+统一的测试运行器 - 运行所有沙箱验证测试
+
+这个脚本会依次运行所有的验证测试，并生成综合报告。
+支持选择性运行特定测试套件，并提供详细的性能和结果统计。
+"""
+
+import asyncio
+import logging
+import os
+import sys
+import time
+import traceback
+from pathlib import Path
+from typing import Any, Dict, List
+
+# 添加项目根目录到Python路径
+project_root = Path(__file__).parent.parent
+sys.path.insert(0, str(project_root))
+
+# 配置日志
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+    handlers=[
+        logging.StreamHandler(),
+        logging.FileHandler("/home/ubuntu/git_home/scalebox/test/test_results.log"),
+    ],
+)
+logger = logging.getLogger(__name__)
+
+
+class TestSuiteRunner:
+    """测试套件运行器"""
+
+    def __init__(self):
+        self.results: Dict[str, Dict[str, Any]] = {}
+        self.total_start_time = time.time()
+
+    def run_test_module(self, module_name: str, description: str) -> Dict[str, Any]:
+        """运行单个测试模块"""
+        logger.info(f"\n{'='*60}")
+        logger.info(f"开始运行: {description}")
+        logger.info(f"模块: {module_name}")
+        logger.info(f"{'='*60}")
+
+        start_time = time.time()
+        result = {
+            "module": module_name,
+            "description": description,
+            "success": False,
+            "duration": 0,
+            "error": None,
+            "details": {},
+        }
+
+        try:
+            if module_name == "test_sandbox_async_comprehensive":
+                from test_sandbox_async_comprehensive import AsyncSandboxValidator
+
+                validator = AsyncSandboxValidator()
+                asyncio.run(validator.run_all_tests())
+                result["details"] = {
+                    "total_tests": len(validator.test_results),
+                    "passed": sum(1 for r in validator.test_results if r["success"]),
+                    "failed": len(validator.failed_tests),
+                    "test_results": validator.test_results,
+                }
+
+            elif module_name == "test_sandbox_sync_comprehensive":
+                from test_sandbox_sync_comprehensive import SandboxValidator
+
+                validator = SandboxValidator()
+                validator.run_all_tests()
+                result["details"] = {
+                    "total_tests": len(validator.test_results),
+                    "passed": sum(1 for r in validator.test_results if r["success"]),
+                    "failed": len(validator.failed_tests),
+                    "test_results": validator.test_results,
+                }
+
+            elif module_name == "test_sandbox_stress_and_edge_cases":
+                from test_sandbox_stress_and_edge_cases import StressTestValidator
+
+                validator = StressTestValidator()
+                validator.run_all_tests()
+                result["details"] = {
+                    "total_tests": len(validator.test_results),
+                    "passed": sum(1 for r in validator.test_results if r["success"]),
+                    "failed": len(validator.failed_tests),
+                    "test_results": validator.test_results,
+                }
+
+            elif module_name == "test_sandbox_usage_examples":
+                # 使用示例不返回测试结果，只是演示
+                import test_sandbox_usage_examples
+
+                test_sandbox_usage_examples.main()
+                result["details"] = {
+                    "total_tests": 1,
+                    "passed": 1,
+                    "failed": 0,
+                    "note": "Usage examples completed successfully",
+                }
+
+            result["success"] = True
+
+        except Exception as e:
+            result["error"] = str(e)
+            result["traceback"] = traceback.format_exc()
+            logger.error(f"测试模块 {module_name} 运行失败: {e}")
+            logger.error(f"详细错误信息:\n{traceback.format_exc()}")
+
+        result["duration"] = time.time() - start_time
+
+        # 打印模块结果摘要
+        if result["success"]:
+            logger.info(f"✅ {description} - 完成")
+            if "total_tests" in result["details"]:
+                logger.info(f"   总测试: {result['details']['total_tests']}")
+                logger.info(f"   通过: {result['details']['passed']}")
+                logger.info(f"   失败: {result['details']['failed']}")
+            logger.info(f"   耗时: {result['duration']:.3f}秒")
+        else:
+            logger.error(f"❌ {description} - 失败")
+            logger.error(f"   错误: {result['error']}")
+            logger.error(f"   耗时: {result['duration']:.3f}秒")
+
+        return result
+
+    def run_all_tests(self, selected_tests: List[str] = None) -> Dict[str, Any]:
+        """运行所有或选定的测试"""
+        logger.info("ScaleBox 沙箱验证测试套件")
+        logger.info(f"开始时间: {time.strftime('%Y-%m-%d %H:%M:%S')}")
+
+        # 定义所有测试套件
+        test_suites = [
+            {
+                "module": "test_sandbox_async_comprehensive",
+                "description": "AsyncSandbox 综合功能验证",
+            },
+            {
+                "module": "test_sandbox_sync_comprehensive",
+                "description": "Sandbox 综合功能验证",
+            },
+            {
+                "module": "test_sandbox_stress_and_edge_cases",
+                "description": "压力测试和边界条件验证",
+            },
+            {
+                "module": "test_sandbox_usage_examples",
+                "description": "使用示例和最佳实践演示",
+            },
+        ]
+
+        # 过滤选定的测试
+        if selected_tests:
+            test_suites = [
+                suite for suite in test_suites if suite["module"] in selected_tests
+            ]
+
+        logger.info(f"将运行 {len(test_suites)} 个测试套件")
+
+        # 运行所有测试套件
+        for suite in test_suites:
+            result = self.run_test_module(suite["module"], suite["description"])
+            self.results[suite["module"]] = result
+
+        # 生成综合报告
+        total_duration = time.time() - self.total_start_time
+        return self.generate_final_report(total_duration)
+
+    def generate_final_report(self, total_duration: float) -> Dict[str, Any]:
+        """生成最终测试报告"""
+        logger.info(f"\n{'='*80}")
+        logger.info("ScaleBox 沙箱验证测试 - 最终报告")
+        logger.info(f"{'='*80}")
+
+        # 统计总体结果
+        total_suites = len(self.results)
+        successful_suites = sum(1 for r in self.results.values() if r["success"])
+        failed_suites = total_suites - successful_suites
+
+        total_tests = sum(
+            r["details"].get("total_tests", 0) for r in self.results.values()
+        )
+        total_passed = sum(r["details"].get("passed", 0) for r in self.results.values())
+        total_failed = sum(r["details"].get("failed", 0) for r in self.results.values())
+
+        logger.info(f"测试套件统计:")
+        logger.info(f"  总套件数: {total_suites}")
+        logger.info(f"  成功套件: {successful_suites}")
+        logger.info(f"  失败套件: {failed_suites}")
+        logger.info(f"  套件成功率: {(successful_suites/total_suites*100):.1f}%")
+
+        logger.info(f"\n测试用例统计:")
+        logger.info(f"  总测试数: {total_tests}")
+        logger.info(f"  通过测试: {total_passed}")
+        logger.info(f"  失败测试: {total_failed}")
+        logger.info(
+            f"  测试成功率: {(total_passed/total_tests*100):.1f}%"
+            if total_tests > 0
+            else "  测试成功率: N/A"
+        )
+
+        logger.info(f"\n性能统计:")
+        logger.info(f"  总运行时间: {total_duration:.3f}秒")
+
+        # 详细结果
+        logger.info(f"\n详细结果:")
+        for module, result in self.results.items():
+            status = "✅ 成功" if result["success"] else "❌ 失败"
+            logger.info(f"  {result['description']}: {status}")
+            logger.info(f"    模块: {module}")
+            logger.info(f"    耗时: {result['duration']:.3f}秒")
+
+            if "total_tests" in result["details"]:
+                logger.info(
+                    f"    测试: {result['details']['passed']}/{result['details']['total_tests']}"
+                )
+
+            if not result["success"] and result["error"]:
+                logger.info(f"    错误: {result['error']}")
+
+        # 失败的测试详情
+        if failed_suites > 0:
+            logger.info(f"\n失败的测试套件:")
+            for module, result in self.results.items():
+                if not result["success"]:
+                    logger.info(f"  ❌ {result['description']}")
+                    logger.info(f"     错误: {result['error']}")
+
+        # 性能对比（如果有同步和异步测试结果）
+        if (
+            "test_sandbox_async_comprehensive" in self.results
+            and "test_sandbox_sync_comprehensive" in self.results
+        ):
+            async_duration = self.results["test_sandbox_async_comprehensive"][
+                "duration"
+            ]
+            sync_duration = self.results["test_sandbox_sync_comprehensive"]["duration"]
+
+            logger.info(f"\n同步 vs 异步性能对比:")
+            logger.info(f"  异步版本耗时: {async_duration:.3f}秒")
+            logger.info(f"  同步版本耗时: {sync_duration:.3f}秒")
+
+            if async_duration > 0 and sync_duration > 0:
+                if async_duration < sync_duration:
+                    speedup = sync_duration / async_duration
+                    logger.info(f"  异步版本快 {speedup:.1f}x")
+                else:
+                    speedup = async_duration / sync_duration
+                    logger.info(f"  同步版本快 {speedup:.1f}x")
+
+        logger.info(f"\n{'='*80}")
+        logger.info(f"测试完成时间: {time.strftime('%Y-%m-%d %H:%M:%S')}")
+        logger.info(f"{'='*80}")
+
+        # 返回汇总报告
+        summary = {
+            "total_suites": total_suites,
+            "successful_suites": successful_suites,
+            "failed_suites": failed_suites,
+            "suite_success_rate": (
+                (successful_suites / total_suites * 100) if total_suites > 0 else 0
+            ),
+            "total_tests": total_tests,
+            "total_passed": total_passed,
+            "total_failed": total_failed,
+            "test_success_rate": (
+                (total_passed / total_tests * 100) if total_tests > 0 else 0
+            ),
+            "total_duration": total_duration,
+            "results": self.results,
+        }
+
+        return summary
+
+
+def main():
+    """主函数"""
+    import argparse
+
+    parser = argparse.ArgumentParser(description="ScaleBox 沙箱验证测试套件")
+    parser.add_argument(
+        "--tests",
+        nargs="+",
+        choices=[
+            "test_sandbox_async_comprehensive",
+            "test_sandbox_sync_comprehensive",
+            "test_sandbox_stress_and_edge_cases",
+            "test_sandbox_usage_examples",
+        ],
+        help="选择要运行的测试套件",
+    )
+    parser.add_argument("--log-level", default="INFO", help="日志级别")
+    parser.add_argument("--output", help="输出报告到文件")
+
+    args = parser.parse_args()
+
+    # 设置日志级别
+    logging.getLogger().setLevel(getattr(logging, args.log_level.upper()))
+
+    try:
+        # 运行测试
+        runner = TestSuiteRunner()
+        summary = runner.run_all_tests(args.tests)
+
+        # 保存报告到文件
+        if args.output:
+            import json
+
+            with open(args.output, "w", encoding="utf-8") as f:
+                json.dump(summary, f, indent=2, ensure_ascii=False, default=str)
+            logger.info(f"测试报告已保存到: {args.output}")
+
+        # 根据测试结果设置退出码
+        if summary["failed_suites"] > 0:
+            sys.exit(1)
+        else:
+            sys.exit(0)
+
+    except KeyboardInterrupt:
+        logger.info("用户中断测试")
+        sys.exit(2)
+    except Exception as e:
+        logger.error(f"测试运行器出现异常: {e}")
+        logger.error(traceback.format_exc())
+        sys.exit(3)
+
+
+if __name__ == "__main__":
+    main()

scalebox/test/run_code_interpreter_tests.sh

@@ -0,0 +1,67 @@
+#!/bin/bash
+
+# Code Interpreter 测试运行脚本
+
+echo "=========================================="
+echo "Code Interpreter 测试套件"
+echo "=========================================="
+
+# 检查Python版本
+echo "🐍 Python版本:"
+python3 --version
+
+echo ""
+echo "📋 可用的测试选项:"
+echo "1. 简单同步测试 (testcodeinterpreter_sync.py)"
+echo "2. 简单异步测试 (testcodeinterpreter_async.py)"
+echo "3. 综合同步测试 (test_code_interpreter_sync_comprehensive.py)"
+echo "4. 综合异步测试 (test_code_interpreter_async_comprehensive.py)"
+echo "5. 运行所有测试"
+echo ""
+
+# 询问用户选择
+echo "请选择要运行的测试 (1-5)，或按 Enter 运行简单同步测试："
+read choice
+
+case $choice in
+    1)
+        echo "🚀 运行简单同步测试..."
+        python3 testcodeinterpreter_sync.py
+        ;;
+    2)
+        echo "🚀 运行简单异步测试..."
+        python3 testcodeinterpreter_async.py
+        ;;
+    3)
+        echo "🚀 运行综合同步测试..."
+        python3 test_code_interpreter_sync_comprehensive.py
+        ;;
+    4)
+        echo "🚀 运行综合异步测试..."
+        python3 test_code_interpreter_async_comprehensive.py
+        ;;
+    5)
+        echo "🚀 运行所有测试..."
+        echo ""
+        echo "--- 简单同步测试 ---"
+        python3 testcodeinterpreter_sync.py
+        echo ""
+        echo "--- 简单异步测试 ---"
+        python3 testcodeinterpreter_async.py
+        echo ""
+        echo "--- 综合同步测试 ---"
+        python3 test_code_interpreter_sync_comprehensive.py
+        echo ""
+        echo "--- 综合异步测试 ---"
+        python3 test_code_interpreter_async_comprehensive.py
+        ;;
+    *)
+        echo "🚀 运行默认的简单同步测试..."
+        python3 testcodeinterpreter_sync.py
+        ;;
+esac
+
+echo ""
+echo "=========================================="
+echo "测试完成！"
+echo "=========================================="

scalebox/test/run_tests.sh

@@ -0,0 +1,230 @@
+#!/bin/bash
+
+# ScaleBox 沙箱验证测试运行脚本
+# 这个脚本提供了一个简单的方式来运行所有验证测试
+
+set -e  # 出错时立即退出
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 打印带颜色的消息
+print_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+print_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+print_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+print_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 检查Python环境
+check_python_env() {
+    print_info "检查Python环境..."
+    
+    if ! command -v python3 &> /dev/null; then
+        print_error "Python3 未安装"
+        exit 1
+    fi
+    
+    # 检查必要的模块是否可以导入
+    if ! python3 -c "import sys; sys.path.insert(0, '/home/ubuntu/git_home/scalebox'); import scalebox" 2>/dev/null; then
+        print_warning "ScaleBox模块路径可能有问题，但继续尝试运行测试"
+    else
+        print_success "Python环境检查通过"
+    fi
+}
+
+# 运行单个测试
+run_single_test() {
+    local test_name=$1
+    local description=$2
+    
+    print_info "开始运行: $description"
+    echo "========================================================"
+    
+    if python3 "$test_name"; then
+        print_success "$description 完成"
+        return 0
+    else
+        print_error "$description 失败"
+        return 1
+    fi
+}
+
+# 显示使用帮助
+show_help() {
+    echo "ScaleBox 沙箱验证测试运行脚本"
+    echo ""
+    echo "用法: $0 [选项]"
+    echo ""
+    echo "选项:"
+    echo "  -h, --help              显示此帮助信息"
+    echo "  -a, --async-only        仅运行异步测试"
+    echo "  -s, --sync-only         仅运行同步测试"
+    echo "  -S, --stress-only       仅运行压力测试"
+    echo "  -u, --usage-only        仅运行使用示例"
+    echo "  -q, --quick             快速测试（跳过压力测试）"
+    echo "  -v, --verbose           详细输出"
+    echo ""
+    echo "示例:"
+    echo "  $0                      运行所有测试"
+    echo "  $0 --async-only         仅运行异步测试"
+    echo "  $0 --quick              运行除压力测试外的所有测试"
+    echo ""
+}
+
+# 主函数
+main() {
+    local run_async=true
+    local run_sync=true
+    local run_stress=true
+    local run_usage=true
+    local verbose=false
+    
+    # 解析命令行参数
+    while [[ $# -gt 0 ]]; do
+        case $1 in
+            -h|--help)
+                show_help
+                exit 0
+                ;;
+            -a|--async-only)
+                run_sync=false
+                run_stress=false
+                run_usage=false
+                shift
+                ;;
+            -s|--sync-only)
+                run_async=false
+                run_stress=false
+                run_usage=false
+                shift
+                ;;
+            -S|--stress-only)
+                run_async=false
+                run_sync=false
+                run_usage=false
+                shift
+                ;;
+            -u|--usage-only)
+                run_async=false
+                run_sync=false
+                run_stress=false
+                shift
+                ;;
+            -q|--quick)
+                run_stress=false
+                shift
+                ;;
+            -v|--verbose)
+                verbose=true
+                shift
+                ;;
+            *)
+                print_error "未知选项: $1"
+                show_help
+                exit 1
+                ;;
+        esac
+    done
+    
+    # 设置详细输出
+    if [ "$verbose" = true ]; then
+        set -x
+    fi
+    
+    print_info "ScaleBox 沙箱验证测试开始"
+    print_info "开始时间: $(date)"
+    
+    # 检查环境
+    check_python_env
+    
+    # 切换到测试目录
+    cd "$(dirname "$0")"
+    
+    local total_tests=0
+    local failed_tests=0
+    local start_time=$(date +%s)
+    
+    # 运行异步测试
+    if [ "$run_async" = true ]; then
+        ((total_tests++))
+        if ! run_single_test "test_sandbox_async_comprehensive.py" "AsyncSandbox 综合功能验证"; then
+            ((failed_tests++))
+        fi
+        echo ""
+    fi
+    
+    # 运行同步测试
+    if [ "$run_sync" = true ]; then
+        ((total_tests++))
+        if ! run_single_test "test_sandbox_sync_comprehensive.py" "Sandbox 综合功能验证"; then
+            ((failed_tests++))
+        fi
+        echo ""
+    fi
+    
+    # 运行压力测试
+    if [ "$run_stress" = true ]; then
+        ((total_tests++))
+        print_warning "压力测试可能需要较长时间..."
+        if ! run_single_test "test_sandbox_stress_and_edge_cases.py" "压力测试和边界条件验证"; then
+            ((failed_tests++))
+        fi
+        echo ""
+    fi
+    
+    # 运行使用示例
+    if [ "$run_usage" = true ]; then
+        ((total_tests++))
+        if ! run_single_test "test_sandbox_usage_examples.py" "使用示例和最佳实践演示"; then
+            ((failed_tests++))
+        fi
+        echo ""
+    fi
+    
+    # 生成最终报告
+    local end_time=$(date +%s)
+    local duration=$((end_time - start_time))
+    
+    echo "========================================================"
+    print_info "ScaleBox 沙箱验证测试 - 最终报告"
+    echo "========================================================"
+    
+    print_info "测试统计:"
+    echo "  总测试套件: $total_tests"
+    echo "  成功套件: $((total_tests - failed_tests))"
+    echo "  失败套件: $failed_tests"
+    
+    if [ $total_tests -gt 0 ]; then
+        local success_rate=$(( (total_tests - failed_tests) * 100 / total_tests ))
+        echo "  成功率: ${success_rate}%"
+    fi
+    
+    echo "  总耗时: ${duration}秒"
+    echo "  完成时间: $(date)"
+    
+    # 根据结果设置退出状态
+    if [ $failed_tests -eq 0 ]; then
+        print_success "所有测试都通过了！"
+        exit 0
+    else
+        print_error "有 $failed_tests 个测试套件失败"
+        exit 1
+    fi
+}
+
+# 运行主函数
+main "$@"