pixelarraylib 1.0.0__py3-none-any.whl

arraylib/scripts/__init__.py

@@ -0,0 +1,22 @@
+"""
+ArrayLib 脚本工具包
+包含各种实用的命令行工具和脚本
+"""
+
+__version__ = "1.0.0"
+__author__ = "Lu qi"
+
+# 导出主要的脚本函数
+from arraylib.scripts.create_test_case_files import main as create_test_case_files
+from arraylib.scripts.summary_code_count import main as summary_code_count
+from arraylib.scripts.collect_code_to_txt import main as collect_code_to_txt
+from arraylib.scripts.nginx_proxy_to_ecs import main as nginx_proxy_to_ecs
+from arraylib.scripts.remove_empty_lines import main as remove_empty_lines
+
+__all__ = [
+    "create_test_case_files",
+    "summary_code_count",
+    "collect_code_to_txt",
+    "nginx_proxy_to_ecs",
+    "remove_empty_lines",
+]

arraylib/scripts/collect_code_to_txt.py

@@ -0,0 +1,327 @@
+#!/usr/bin/env python3
+"""
+Git仓库代码收集工具
+该脚本用于收集当前目录下所有git仓库中提交的代码文件，并写入txt文件
+
+使用方法:
+1. 作为命令行工具：
+   arraylib collect_code_to_txt --output=all_code.txt
+   arraylib collect_code_to_txt --extensions="py,js,vue" --output=frontend_code.txt
+   arraylib collect_code_to_txt --since="2024-01-01" --output=recent_code.txt
+
+2. 作为Python模块：
+   from arraylib.scripts.collect_code_to_txt import collect_git_repos_code
+   collect_git_repos_code(output_file="code.txt")
+"""
+
+import os
+import subprocess
+import argparse
+from datetime import datetime, timedelta
+from pathlib import Path
+import hashlib
+
+
+class GitCodeCollector:
+    def __init__(self, base_dir="."):
+        self.base_dir = Path(base_dir).resolve()
+        self.collected_files = set()  # 用于去重
+        self.file_hashes = {}  # 用于检测重复内容
+        self.stats = {
+            "repos_found": 0,
+            "files_collected": 0,
+            "total_lines": 0,
+            "total_size": 0,
+            "errors": 0
+        }
+
+    def is_git_repo(self, path):
+        """检查目录是否为git仓库"""
+        return (Path(path) / ".git").exists()
+
+    def find_git_repos(self):
+        """查找当前目录下的所有git仓库"""
+        git_repos = []
+        
+        # 检查当前目录是否为git仓库
+        if self.is_git_repo(self.base_dir):
+            git_repos.append(self.base_dir)
+        
+        # 递归查找子目录中的git仓库
+        for item in self.base_dir.iterdir():
+            if item.is_dir() and not item.name.startswith('.'):
+                if self.is_git_repo(item):
+                    git_repos.append(item)
+        
+        return git_repos
+
+    def run_git_command(self, command, cwd):
+        """执行git命令"""
+        try:
+            result = subprocess.run(
+                command,
+                shell=True,
+                cwd=cwd,
+                capture_output=True,
+                text=True,
+                check=True
+            )
+            return result.stdout.strip()
+        except subprocess.CalledProcessError as e:
+            print(f"⚠️  Git命令执行失败: {command}")
+            print(f"   错误信息: {e.stderr}")
+            return ""
+
+    def get_committed_files(self, repo_path, since_date=None, until_date=None, extensions=None):
+        """获取git仓库中已提交的文件列表"""
+        # 获取所有提交的文件
+        command = "git ls-files"
+        if since_date:
+            command += f' --since="{since_date}"'
+        
+        output = self.run_git_command(command, repo_path)
+        if not output:
+            return []
+        
+        files = []
+        for line in output.split('\n'):
+            if line.strip():
+                file_path = Path(repo_path) / line.strip()
+                if file_path.exists() and file_path.is_file():
+                    # 检查文件扩展名
+                    if extensions:
+                        file_ext = file_path.suffix.lower()
+                        if file_ext not in extensions:
+                            continue
+                    files.append(file_path)
+        
+        return files
+
+    def get_file_content(self, file_path):
+        """读取文件内容，处理编码问题"""
+        try:
+            # 首先尝试UTF-8
+            with open(file_path, 'r', encoding='utf-8') as f:
+                content = f.read()
+            return content
+        except UnicodeDecodeError:
+            try:
+                # 尝试其他编码
+                with open(file_path, 'r', encoding='latin-1') as f:
+                    content = f.read()
+                return content
+            except Exception as e:
+                print(f"⚠️  无法读取文件 {file_path}: {e}")
+                return None
+        except Exception as e:
+            print(f"⚠️  读取文件失败 {file_path}: {e}")
+            return None
+
+    def calculate_file_hash(self, content):
+        """计算文件内容的哈希值"""
+        return hashlib.md5(content.encode('utf-8')).hexdigest()
+
+    def should_skip_file(self, file_path, content):
+        """判断是否应该跳过文件"""
+        # 跳过空文件
+        if not content or not content.strip():
+            return True
+        
+        # 跳过二进制文件（简单检测）
+        if '\x00' in content:
+            return True
+        
+        # 跳过过大的文件（超过1MB）
+        if len(content) > 1024 * 1024:
+            print(f"⚠️  跳过大文件: {file_path} ({len(content)} 字节)")
+            return True
+        
+        # 检查重复内容
+        content_hash = self.calculate_file_hash(content)
+        if content_hash in self.file_hashes:
+            print(f"⚠️  跳过重复文件: {file_path} (与 {self.file_hashes[content_hash]} 内容相同)")
+            return True
+        
+        self.file_hashes[content_hash] = str(file_path)
+        return False
+
+    def collect_repo_files(self, repo_path, output_file, extensions=None, since_date=None, until_date=None):
+        """收集单个git仓库的文件"""
+        repo_name = repo_path.name
+        print(f"📁 正在处理仓库: {repo_name}")
+        
+        files = self.get_committed_files(repo_path, since_date, until_date, extensions)
+        if not files:
+            print(f"   ⚠️  未找到符合条件的文件")
+            return
+        
+        print(f"   📄 找到 {len(files)} 个文件")
+        
+        repo_files_count = 0
+        repo_lines_count = 0
+        
+        for file_path in files:
+            try:
+                content = self.get_file_content(file_path)
+                if content is None:
+                    self.stats["errors"] += 1
+                    continue
+                
+                if self.should_skip_file(file_path, content):
+                    continue
+                
+                # 写入文件内容
+                relative_path = file_path.relative_to(self.base_dir)
+                output_file.write(f"\n\n{'='*80}\n")
+                output_file.write(f"文件: {relative_path}\n")
+                output_file.write(f"仓库: {repo_name}\n")
+                output_file.write(f"大小: {len(content)} 字节\n")
+                output_file.write(f"行数: {len(content.splitlines())}\n")
+                output_file.write(f"{'='*80}\n\n")
+                output_file.write(content)
+                output_file.write("\n")
+                
+                repo_files_count += 1
+                repo_lines_count += len(content.splitlines())
+                self.stats["files_collected"] += 1
+                self.stats["total_lines"] += len(content.splitlines())
+                self.stats["total_size"] += len(content)
+                
+            except Exception as e:
+                print(f"   ⚠️  处理文件失败 {file_path}: {e}")
+                self.stats["errors"] += 1
+        
+        print(f"   ✅ 收集了 {repo_files_count} 个文件，共 {repo_lines_count} 行")
+
+    def collect_all_repos(self, output_file_path, extensions=None, since_date=None, until_date=None):
+        """收集所有git仓库的代码文件"""
+        print("🔍 正在搜索Git仓库...")
+        git_repos = self.find_git_repos()
+        
+        if not git_repos:
+            print("❌ 未找到任何Git仓库")
+            return False
+        
+        self.stats["repos_found"] = len(git_repos)
+        print(f"📦 找到 {len(git_repos)} 个Git仓库")
+        
+        # 显示仓库列表
+        for i, repo in enumerate(git_repos, 1):
+            print(f"   {i}. {repo.name} ({repo})")
+        
+        print(f"\n📝 开始收集代码文件...")
+        print(f"📁 输出文件: {output_file_path}")
+        if extensions:
+            print(f"📄 文件类型: {', '.join(extensions)}")
+        if since_date:
+            print(f"📅 开始日期: {since_date}")
+        if until_date:
+            print(f"📅 结束日期: {until_date}")
+        
+        with open(output_file_path, 'w', encoding='utf-8') as output_file:
+            # 写入文件头
+            output_file.write("Git仓库代码收集报告\n")
+            output_file.write("=" * 80 + "\n")
+            output_file.write(f"收集时间: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n")
+            output_file.write(f"基础目录: {self.base_dir}\n")
+            output_file.write(f"仓库数量: {len(git_repos)}\n")
+            if extensions:
+                output_file.write(f"文件类型: {', '.join(extensions)}\n")
+            if since_date:
+                output_file.write(f"开始日期: {since_date}\n")
+            if until_date:
+                output_file.write(f"结束日期: {until_date}\n")
+            output_file.write("=" * 80 + "\n\n")
+            
+            # 收集每个仓库的文件
+            for repo_path in git_repos:
+                self.collect_repo_files(
+                    repo_path, 
+                    output_file, 
+                    extensions, 
+                    since_date, 
+                    until_date
+                )
+        
+        # 打印统计信息
+        self.print_stats(output_file_path)
+        return True
+
+    def print_stats(self, output_file_path):
+        """打印统计信息"""
+        print(f"\n📊 收集完成统计:")
+        print(f"   📦 处理的仓库数: {self.stats['repos_found']}")
+        print(f"   📄 收集的文件数: {self.stats['files_collected']}")
+        print(f"   📝 总代码行数: {self.stats['total_lines']:,}")
+        print(f"   💾 总文件大小: {self.stats['total_size']:,} 字节 ({self.stats['total_size']/1024/1024:.2f} MB)")
+        print(f"   ⚠️  错误数量: {self.stats['errors']}")
+        print(f"   📁 输出文件: {output_file_path}")
+
+
+def collect_git_repos_code(output_file="collected_code.txt", extensions=None, since_date=None, until_date=None, base_dir="."):
+    """
+    收集Git仓库代码的主函数
+    
+    Args:
+        output_file: 输出文件名
+        extensions: 文件扩展名列表，如 ['.py', '.js']
+        since_date: 开始日期 (YYYY-MM-DD)
+        until_date: 结束日期 (YYYY-MM-DD)
+        base_dir: 基础目录
+    """
+    collector = GitCodeCollector(base_dir)
+    
+    # 处理扩展名格式
+    if extensions and isinstance(extensions, str):
+        extensions = [ext.strip() for ext in extensions.split(',')]
+    
+    # 确保扩展名以点开头
+    if extensions:
+        extensions = [ext if ext.startswith('.') else f'.{ext}' for ext in extensions]
+    
+    success = collector.collect_all_repos(output_file, extensions, since_date, until_date)
+    return success
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Git仓库代码收集工具",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog=__doc__
+    )
+    
+    parser.add_argument("--output", "-o", default="collected_code.txt", 
+                       help="输出文件名 (默认: collected_code.txt)")
+    parser.add_argument("--extensions", "-e", 
+                       help="文件扩展名，用逗号分隔 (如: py,js,vue)")
+    parser.add_argument("--since", "-s", 
+                       help="开始日期 (格式: YYYY-MM-DD)")
+    parser.add_argument("--until", "-u", 
+                       help="结束日期 (格式: YYYY-MM-DD)")
+    parser.add_argument("--base-dir", "-d", default=".", 
+                       help="基础目录 (默认: 当前目录)")
+    
+    args = parser.parse_args()
+    
+    # 处理文件扩展名
+    extensions = None
+    if args.extensions:
+        extensions = [ext.strip() for ext in args.extensions.split(',')]
+    
+    # 执行收集
+    success = collect_git_repos_code(
+        output_file=args.output,
+        extensions=extensions,
+        since_date=args.since,
+        until_date=args.until,
+        base_dir=args.base_dir
+    )
+    
+    if success:
+        print(f"\n✅ 代码收集完成！文件已保存到: {args.output}")
+    else:
+        print(f"\n❌ 代码收集失败！")
+
+
+if __name__ == "__main__":
+    main()

arraylib/scripts/create_test_case_files.py

@@ -0,0 +1,100 @@
+"""
+本脚本用于一键创建所有测试用例文件
+使用方法：
+1. 作为命令行工具：
+   arraylib create_test_case_files
+   
+2. 作为Python模块：
+   from arraylib.scripts.create_test_case_files import main
+   main()
+"""
+
+import os
+import fnmatch
+
+
+def walk_dir(dir_path):
+    for file in os.listdir(dir_path):
+        if os.path.isfile(os.path.join(dir_path, file)):
+            yield os.path.join(dir_path, file)
+        else:
+            yield from walk_dir(os.path.join(dir_path, file))
+
+
+def main():
+    # step1: 检查是否存在test_case目录
+    if not os.path.exists("test_case"):
+        print("test_case目录不存在！创建test_case目录")
+        os.makedirs("test_case")
+    else:
+        print("test_case目录存在！")
+
+    # step2：找出所有需要创建的测试用例文件
+    not_need_dir = [
+        "test_case",
+        "scripts",
+        ".venv",
+        ".git",
+        ".idea",
+        "dist",
+        "build",
+        "docs",
+        "tests",
+        "src",
+        "tests",
+        "__pycache__",
+        ".pytest_cache",
+    ]
+    not_need_path = []
+    not_need_file = [
+        "__init__.py",
+        "__main__.py",
+        "wsgi.py",
+        "settings.py",
+        "local_settings.py",
+        "test.py",
+        "temp.py",
+        "base.py",
+        "main.py",
+        "setup.py",
+    ]
+    test_case_files = []
+    for file_path in filter(lambda x: x.endswith(".py"), walk_dir(os.getcwd())):
+        relative_path = os.path.relpath(file_path, os.getcwd())
+        dirs = os.path.dirname(relative_path).split("/")
+        # 检查是否匹配通配符路径
+        if any(
+            fnmatch.fnmatch(os.path.dirname(relative_path), path)
+            for path in not_need_path
+        ):
+            continue
+        if (
+            any(dir in not_need_dir for dir in dirs[::-1])
+            or os.path.basename(file_path) in not_need_file
+        ):
+            continue
+
+        test_case_files.append(
+            os.path.join(
+                "test_case",
+                os.path.dirname(relative_path),
+                "test_" + os.path.basename(file_path),
+            )
+        )
+
+    # step3: 检查并创建测试用例文件
+    created_test_case_files = []
+    for test_case_file_path in test_case_files:
+        if not os.path.exists(test_case_file_path):
+            os.makedirs(os.path.dirname(test_case_file_path), exist_ok=True)
+            open(test_case_file_path, "w").close()
+            created_test_case_files.append(test_case_file_path)
+
+    # step4: 打印创建的测试用例文件
+    print(f"已成功创建测试用例文件{len(created_test_case_files)}个，文件路径如下：")
+    for test_case_file_path in created_test_case_files:
+        print(test_case_file_path)
+
+
+if __name__ == "__main__":
+    main()

arraylib/scripts/nginx_proxy_to_ecs.py

@@ -0,0 +1,119 @@
+import argparse
+import base64
+from arraylib.system.common import execute_command_through_ssh
+from arraylib.aliyun.domain import DomainUtils
+
+
+def nginx_proxy_file_template(
+    domain_name: str, port_of_service: str, ssl_cert_path: str, ssl_key_path: str
+) -> str:
+    return f"""
+server {{
+    listen 80;
+    server_name {domain_name}.pixelarrayai.com;
+
+    # 将所有HTTP请求重定向到HTTPS
+    return 301 https://$host$request_uri;
+}}
+
+server {{
+    listen 443 ssl;
+    server_name {domain_name}.pixelarrayai.com;
+
+    ssl_certificate {ssl_cert_path};
+    ssl_certificate_key {ssl_key_path};
+
+    location / {{
+        proxy_pass http://localhost:{port_of_service};
+        proxy_http_version 1.1;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+    }}
+}}
+    """
+
+
+def add_a_record_to_dns(
+    domain_name: str, ecs_ip: str, access_key_id: str, access_key_secret: str
+) -> None:
+    domain_utils = DomainUtils(
+        access_key_id, access_key_secret, domain_name="pixelarrayai.com"
+    )
+    domain_utils.add_domain_record(
+        rr=domain_name,
+        type="A",
+        value=ecs_ip,
+    )
+    print("域名解析记录添加成功")
+
+
+def deploy(
+    ecs_ip: str,
+    domain_name: str,
+    port_of_service: str,
+    ssl_cert_path: str,
+    ssl_key_path: str,
+    access_key_id: str,
+    access_key_secret: str,
+) -> None:
+    execute_command_through_ssh(
+        ecs_ip,
+        f"sudo rm -f /etc/nginx/sites-available/{domain_name} && sudo rm -f /etc/nginx/sites-enabled/{domain_name}",
+    )
+    print("删除原有配置成功")
+    execute_command_through_ssh(
+        ecs_ip,
+        f"sudo touch /etc/nginx/sites-available/{domain_name}",
+    )
+    print("文件创建成功")
+    nginx_proxy_file_content = nginx_proxy_file_template(
+        domain_name, port_of_service, ssl_cert_path, ssl_key_path
+    )
+    # 使用 base64 编码来避免特殊字符问题
+    encoded_content = base64.b64encode(nginx_proxy_file_content.encode('utf-8')).decode('utf-8')
+    execute_command_through_ssh(
+        ecs_ip,
+        f"echo '{encoded_content}' | base64 -d | sudo tee /etc/nginx/sites-available/{domain_name} > /dev/null",
+    )
+    print("内容写入成功")
+    execute_command_through_ssh(
+        ecs_ip,
+        f"sudo ln -s /etc/nginx/sites-available/{domain_name} /etc/nginx/sites-enabled/{domain_name}",
+    )
+    print("nginx配置添加成功，准备重启")
+    execute_command_through_ssh(
+        ecs_ip, f"sudo nginx -t && sudo systemctl restart nginx"
+    )
+    print("重启成功，请检查配置是否生效")
+    add_a_record_to_dns(domain_name, ecs_ip, access_key_id, access_key_secret)
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Nginx反向代理配置到ECS",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog=__doc__,
+    )
+    parser.add_argument("--ecs_ip", "-e", help="服务IP地址")
+    parser.add_argument("--domain_name", "-d", help="需要代理的域名")
+    parser.add_argument("--port_of_service", "-p", help="端口或服务")
+    parser.add_argument("--access_key_id", "-a", help="阿里云AccessKeyID")
+    parser.add_argument("--access_key_secret", "-s", help="阿里云AccessKeySecret")
+
+    args = parser.parse_args()
+
+    deploy(
+        args.ecs_ip,
+        args.domain_name,
+        args.port_of_service,
+        "/var/pixelarray/ssl_auth/pixelarrayai.com.pem",
+        "/var/pixelarray/ssl_auth/pixelarrayai.com.key",
+        args.access_key_id,
+        args.access_key_secret,
+    )
+
+
+if __name__ == "__main__":
+    main()

arraylib/scripts/remove_empty_lines.py

@@ -0,0 +1,120 @@
+#!/usr/bin/env python3
+"""
+去除Markdown文档中的所有空行
+
+用法:
+    arraylib remove_empty_lines <input_file> [output_file]
+
+参数:
+    input_file    输入的Markdown文件路径
+    output_file   输出的文件路径（可选，默认覆盖原文件）
+
+示例:
+    arraylib remove_empty_lines test.md
+    arraylib remove_empty_lines test.md output.md
+"""
+
+import sys
+import argparse
+import os
+from pathlib import Path
+
+
+def remove_empty_lines(input_file, output_file=None):
+    """
+    去除文件中的所有空行
+    
+    Args:
+        input_file (str): 输入文件路径
+        output_file (str, optional): 输出文件路径，如果为None则覆盖原文件
+    """
+    try:
+        # 检查输入文件是否存在
+        if not os.path.exists(input_file):
+            print(f"错误：文件 '{input_file}' 不存在")
+            return False
+        
+        # 读取文件内容
+        with open(input_file, 'r', encoding='utf-8') as f:
+            lines = f.readlines()
+        
+        # 过滤掉空行（包括只包含空白字符的行）
+        filtered_lines = [line for line in lines if line.strip()]
+        
+        # 确定输出文件路径
+        if output_file is None:
+            output_file = input_file
+        
+        # 写入输出文件
+        with open(output_file, 'w', encoding='utf-8') as f:
+            f.writelines(filtered_lines)
+        
+        # 统计信息
+        original_lines = len(lines)
+        filtered_lines_count = len(filtered_lines)
+        removed_lines = original_lines - filtered_lines_count
+        
+        print(f"处理完成！")
+        print(f"原始行数: {original_lines}")
+        print(f"处理后行数: {filtered_lines_count}")
+        print(f"移除空行数: {removed_lines}")
+        print(f"输出文件: {output_file}")
+        
+        return True
+        
+    except Exception as e:
+        print(f"错误：处理文件时发生异常: {e}")
+        return False
+
+
+def main():
+    """主函数"""
+    parser = argparse.ArgumentParser(
+        description="去除Markdown文档中的所有空行",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+示例用法:
+  arraylib remove_empty_lines test.md                    # 去除test.md中的空行并覆盖原文件
+  arraylib remove_empty_lines test.md output.md          # 去除test.md中的空行并保存到output.md
+        """
+    )
+    
+    parser.add_argument(
+        "input_file",
+        help="输入的Markdown文件路径"
+    )
+    
+    parser.add_argument(
+        "output_file",
+        nargs="?",
+        help="输出的文件路径（可选，默认覆盖原文件）"
+    )
+    
+    # 如果没有命令行参数，显示帮助信息
+    if len(sys.argv) == 1:
+        parser.print_help()
+        return
+    
+    args = parser.parse_args()
+    
+    # 检查输入文件扩展名
+    input_path = Path(args.input_file)
+    if not input_path.suffix.lower() in ['.md', '.markdown', '.txt']:
+        print(f"警告：文件 '{args.input_file}' 不是标准的Markdown文件")
+        response = input("是否继续处理？(y/N): ")
+        if response.lower() not in ['y', 'yes']:
+            print("操作已取消")
+            return
+    
+    # 执行去除空行操作
+    success = remove_empty_lines(args.input_file, args.output_file)
+    
+    if success:
+        print("✅ 空行去除完成！")
+    else:
+        print("❌ 空行去除失败！")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()