aicodestat 0.0.1__py3-none-any.whl

compute/metrics_service.py

@@ -0,0 +1,362 @@
+"""指标服务层：对外提供统一指标计算接口"""
+import logging
+from pathlib import Path
+from typing import Dict, Any, List, Optional
+from storage.models import get_session_summaries, get_code_diff_lines
+from compute.lcs_engine import lcs_calculate, calculate_adoption_rate, calculate_generation_rate
+from compute.cache import get_cache
+
+logger = logging.getLogger(__name__)
+
+
+def read_file_lines(file_path: str) -> List[str]:
+    """
+    从文件系统读取最新文件内容，分割为行
+    
+    Args:
+        file_path: 文件路径
+    
+    Returns:
+        文件行列表
+    """
+    try:
+        file = Path(file_path)
+        if not file.exists():
+            logger.warning(f"File not found: {file_path}")
+            return []
+        
+        with open(file, 'r', encoding='utf-8', errors='ignore') as f:
+            return f.readlines()
+    except Exception as e:
+        logger.error(f"Failed to read file {file_path}: {e}")
+        return []
+
+
+def calculate_session_metrics(session_id: str) -> Dict[str, Any]:
+    """
+    计算会话维度的指标
+    
+    Args:
+        session_id: 会话ID
+    
+    Returns:
+        指标字典，包含：
+        - ai_total_lines: AI生成总行数
+        - adopted_lines: 采纳行数
+        - adoption_rate: 采纳率
+        - generation_rate: 生成率（按所有涉及文件的总行数计算）
+        - file_count: 涉及文件数
+        - summaries: 会话汇总列表
+        - diff_lines: 差异行列表
+    """
+    cache = get_cache()
+    cache_key = f"session_metrics:{session_id}"
+    
+    # 检查缓存
+    cached_result = cache.get(cache_key)
+    if cached_result is not None:
+        logger.debug(f"Using cached metrics for session {session_id}")
+        return cached_result
+    
+    # 获取会话汇总
+    summaries = get_session_summaries(session_id=session_id)
+    
+    if not summaries:
+        return {
+            "session_id": session_id,
+            "ai_total_lines": 0,
+            "adopted_lines": 0,
+            "adoption_rate": 0.0,
+            "generation_rate": 0.0,
+            "file_count": 0,
+            "summaries": [],
+            "diff_lines": []
+        }
+    
+    # 获取所有差异行
+    all_diff_lines = get_code_diff_lines(session_id=session_id)
+    
+    # 计算AI生成总行数
+    ai_total_lines = len(all_diff_lines)
+    
+    # 按文件分组计算采纳行数
+    file_groups: Dict[str, List[Dict[str, Any]]] = {}
+    for diff_line in all_diff_lines:
+        file_path = diff_line["file_path"]
+        if file_path not in file_groups:
+            file_groups[file_path] = []
+        file_groups[file_path].append(diff_line)
+    
+    total_adopted_lines = 0
+    total_file_lines = 0
+    
+    for file_path, diff_lines in file_groups.items():
+        # 读取文件最新内容
+        latest_lines = read_file_lines(file_path)
+        total_file_lines += len(latest_lines)
+        
+        # 提取AI生成的差异行内容
+        ai_diff_content = [d["line_content"] for d in diff_lines]
+        
+        # 计算LCS（采纳行数）
+        adopted = lcs_calculate(ai_diff_content, latest_lines)
+        total_adopted_lines += adopted
+    
+    # 计算指标
+    adoption_rate = calculate_adoption_rate(ai_total_lines, total_adopted_lines)
+    generation_rate = calculate_generation_rate(ai_total_lines, total_file_lines) if total_file_lines > 0 else 0.0
+    
+    result = {
+        "session_id": session_id,
+        "ai_total_lines": ai_total_lines,
+        "adopted_lines": total_adopted_lines,
+        "adoption_rate": adoption_rate,
+        "generation_rate": generation_rate,
+        "file_count": len(file_groups),
+        "summaries": summaries,
+        "diff_lines": all_diff_lines
+    }
+    
+    # 缓存结果
+    cache.set(cache_key, result)
+    
+    return result
+
+
+def calculate_file_metrics(file_path: str) -> Dict[str, Any]:
+    """
+    计算文件维度的指标
+    
+    Args:
+        file_path: 文件路径
+    
+    Returns:
+        指标字典
+    """
+    cache = get_cache()
+    cache_key = f"file_metrics:{file_path}"
+    
+    # 检查缓存
+    cached_result = cache.get(cache_key)
+    if cached_result is not None:
+        logger.debug(f"Using cached metrics for file {file_path}")
+        return cached_result
+    
+    # 获取文件相关的所有会话汇总
+    summaries = get_session_summaries(file_path=file_path)
+    
+    if not summaries:
+        return {
+            "file_path": file_path,
+            "ai_total_lines": 0,
+            "adopted_lines": 0,
+            "adoption_rate": 0.0,
+            "generation_rate": 0.0,
+            "session_count": 0,
+            "summaries": [],
+            "diff_lines": []
+        }
+    
+    # 获取所有差异行
+    all_diff_lines = get_code_diff_lines(file_path=file_path)
+    
+    # 计算AI生成总行数
+    ai_total_lines = len(all_diff_lines)
+    
+    # 读取文件最新内容
+    latest_lines = read_file_lines(file_path)
+    total_file_lines = len(latest_lines)
+    
+    # 提取AI生成的差异行内容
+    ai_diff_content = [d["line_content"] for d in all_diff_lines]
+    
+    # 计算LCS（采纳行数）
+    adopted_lines = lcs_calculate(ai_diff_content, latest_lines)
+    
+    # 计算指标
+    adoption_rate = calculate_adoption_rate(ai_total_lines, adopted_lines)
+    generation_rate = calculate_generation_rate(ai_total_lines, total_file_lines) if total_file_lines > 0 else 0.0
+    
+    result = {
+        "file_path": file_path,
+        "ai_total_lines": ai_total_lines,
+        "adopted_lines": adopted_lines,
+        "adoption_rate": adoption_rate,
+        "generation_rate": generation_rate,
+        "session_count": len(summaries),
+        "summaries": summaries,
+        "diff_lines": all_diff_lines
+    }
+    
+    # 缓存结果
+    cache.set(cache_key, result)
+    
+    return result
+
+
+def calculate_project_metrics(project_root: str) -> Dict[str, Any]:
+    """
+    计算项目维度的指标
+    
+    Args:
+        project_root: 项目根目录路径
+    
+    Returns:
+        指标字典
+    """
+    cache = get_cache()
+    cache_key = f"project_metrics:{project_root}"
+    
+    # 检查缓存
+    cached_result = cache.get(cache_key)
+    if cached_result is not None:
+        logger.debug(f"Using cached metrics for project {project_root}")
+        return cached_result
+    
+    # 获取所有会话汇总
+    all_summaries = get_session_summaries()
+    
+    # 过滤出项目内的文件
+    project_path = Path(project_root).resolve()
+    project_summaries = [
+        s for s in all_summaries
+        if Path(s["file_path"]).resolve().is_relative_to(project_path)
+    ]
+    
+    if not project_summaries:
+        return {
+            "project_root": project_root,
+            "ai_total_lines": 0,
+            "adopted_lines": 0,
+            "adoption_rate": 0.0,
+            "generation_rate": 0.0,
+            "file_count": 0,
+            "session_count": 0,
+            "summaries": [],
+            "diff_lines": []
+        }
+    
+    # 获取所有相关差异行
+    project_files = {s["file_path"] for s in project_summaries}
+    all_diff_lines = []
+    for file_path in project_files:
+        all_diff_lines.extend(get_code_diff_lines(file_path=file_path))
+    
+    # 计算AI生成总行数
+    ai_total_lines = len(all_diff_lines)
+    
+    # 按文件分组计算采纳行数
+    total_adopted_lines = 0
+    total_file_lines = 0
+    
+    file_groups: Dict[str, List[Dict[str, Any]]] = {}
+    for diff_line in all_diff_lines:
+        file_path = diff_line["file_path"]
+        if file_path not in file_groups:
+            file_groups[file_path] = []
+        file_groups[file_path].append(diff_line)
+    
+    for file_path, diff_lines in file_groups.items():
+        latest_lines = read_file_lines(file_path)
+        total_file_lines += len(latest_lines)
+        
+        ai_diff_content = [d["line_content"] for d in diff_lines]
+        adopted = lcs_calculate(ai_diff_content, latest_lines)
+        total_adopted_lines += adopted
+    
+    # 计算指标
+    adoption_rate = calculate_adoption_rate(ai_total_lines, total_adopted_lines)
+    generation_rate = calculate_generation_rate(ai_total_lines, total_file_lines) if total_file_lines > 0 else 0.0
+    
+    result = {
+        "project_root": project_root,
+        "ai_total_lines": ai_total_lines,
+        "adopted_lines": total_adopted_lines,
+        "adoption_rate": adoption_rate,
+        "generation_rate": generation_rate,
+        "file_count": len(file_groups),
+        "session_count": len(set(s["session_id"] for s in project_summaries)),
+        "summaries": project_summaries,
+        "diff_lines": all_diff_lines
+    }
+    
+    # 缓存结果
+    cache.set(cache_key, result)
+    
+    return result
+
+
+def calculate_global_metrics() -> Dict[str, Any]:
+    """
+    计算全局（所有项目 / 会话）的总体指标，用于全局看板。
+    """
+    cache = get_cache()
+    cache_key = "global_metrics"
+
+    cached_result = cache.get(cache_key)
+    if cached_result is not None:
+        logger.debug("Using cached global metrics")
+        return cached_result
+
+    # 获取所有会话汇总
+    all_summaries = get_session_summaries()
+    if not all_summaries:
+        result = {
+            "ai_total_lines": 0,
+            "adopted_lines": 0,
+            "adoption_rate": 0.0,
+            "generation_rate": 0.0,
+            "file_count": 0,
+            "session_count": 0,
+            "summaries": [],
+            "diff_lines": [],
+        }
+        cache.set(cache_key, result)
+        return result
+
+    # 关联所有文件与差异行
+    all_files = {s["file_path"] for s in all_summaries}
+    all_diff_lines: List[Dict[str, Any]] = []
+    for file_path in all_files:
+        all_diff_lines.extend(get_code_diff_lines(file_path=file_path))
+
+    ai_total_lines = len(all_diff_lines)
+
+    total_adopted_lines = 0
+    total_file_lines = 0
+    file_groups: Dict[str, List[Dict[str, Any]]] = {}
+
+    for diff_line in all_diff_lines:
+        file_path = diff_line["file_path"]
+        if file_path not in file_groups:
+            file_groups[file_path] = []
+        file_groups[file_path].append(diff_line)
+
+    for file_path, diff_lines in file_groups.items():
+        latest_lines = read_file_lines(file_path)
+        total_file_lines += len(latest_lines)
+
+        ai_diff_content = [d["line_content"] for d in diff_lines]
+        adopted = lcs_calculate(ai_diff_content, latest_lines)
+        total_adopted_lines += adopted
+
+    adoption_rate = calculate_adoption_rate(ai_total_lines, total_adopted_lines)
+    generation_rate = (
+        calculate_generation_rate(ai_total_lines, total_file_lines)
+        if total_file_lines > 0
+        else 0.0
+    )
+
+    result = {
+        "ai_total_lines": ai_total_lines,
+        "adopted_lines": total_adopted_lines,
+        "adoption_rate": adoption_rate,
+        "generation_rate": generation_rate,
+        "file_count": len(file_groups),
+        "session_count": len(set(s["session_id"] for s in all_summaries)),
+        "summaries": all_summaries,
+        "diff_lines": all_diff_lines,
+    }
+
+    cache.set(cache_key, result)
+    return result

config.py

@@ -0,0 +1,120 @@
+"""配置管理模块，支持从config.json和环境变量加载配置"""
+import json
+import os
+from pathlib import Path
+from typing import Any, Dict
+import logging
+
+logger = logging.getLogger(__name__)
+
+# 全局配置缓存
+_config: Dict[str, Any] = None
+
+
+def get_config_path() -> Path:
+    """获取配置文件路径"""
+    config_file = Path(__file__).parent / "config.json"
+    return config_file
+
+
+def load_config() -> Dict[str, Any]:
+    """加载配置文件，支持环境变量覆盖"""
+    global _config
+    
+    if _config is not None:
+        return _config
+    
+    config_path = get_config_path()
+    
+    # 默认配置
+    default_config = {
+        "server": {
+            "host": "127.0.0.1",
+            "port": 54546,
+            "log_level": "info",
+            "log_file": "~/.local-mcp-server/server.log"
+        },
+        "database": {
+            "path": "~/.local-mcp-server/db.sqlite",
+            "backup_path": "~/.local-mcp-server/backup/",
+            "clean_cycle": 30
+        },
+        "cli": {
+            "cache_time": 300,
+            "default_time_range": 7
+        }
+    }
+    
+    # 从文件加载配置
+    if config_path.exists():
+        try:
+            with open(config_path, 'r', encoding='utf-8') as f:
+                file_config = json.load(f)
+                default_config.update(file_config)
+        except Exception as e:
+            logger.warning(f"Failed to load config file: {e}, using defaults")
+    else:
+        logger.info(f"Config file not found at {config_path}, using defaults")
+    
+    # 环境变量覆盖
+    env_mappings = {
+        "MCP_SERVER_HOST": ("server", "host"),
+        "MCP_SERVER_PORT": ("server", "port"),
+        "MCP_SERVER_LOG_LEVEL": ("server", "log_level"),
+        "MCP_SERVER_LOG_FILE": ("server", "log_file"),
+        "MCP_DB_PATH": ("database", "path"),
+        "MCP_DB_BACKUP_PATH": ("database", "backup_path"),
+        "MCP_DB_CLEAN_CYCLE": ("database", "clean_cycle"),
+        "MCP_CLI_CACHE_TIME": ("cli", "cache_time"),
+        "MCP_CLI_DEFAULT_TIME_RANGE": ("cli", "default_time_range"),
+    }
+    
+    for env_key, (section, key) in env_mappings.items():
+        env_value = os.getenv(env_key)
+        if env_value is not None:
+            if key in ["port", "clean_cycle", "cache_time", "default_time_range"]:
+                try:
+                    env_value = int(env_value)
+                except ValueError:
+                    logger.warning(f"Invalid integer value for {env_key}: {env_value}")
+                    continue
+            default_config[section][key] = env_value
+    
+        # 展开路径中的 ~
+        if "database" in default_config:
+            db_path = default_config["database"]["path"]
+            if db_path.startswith("~"):
+                default_config["database"]["path"] = os.path.expanduser(db_path)
+            
+            backup_path = default_config["database"]["backup_path"]
+            if backup_path.startswith("~"):
+                default_config["database"]["backup_path"] = os.path.expanduser(backup_path)
+        
+        if "server" in default_config and "log_file" in default_config["server"]:
+            log_file = default_config["server"]["log_file"]
+            if log_file and log_file.startswith("~"):
+                default_config["server"]["log_file"] = os.path.expanduser(log_file)
+    
+    _config = default_config
+    return _config
+
+
+def get_config() -> Dict[str, Any]:
+    """获取配置（懒加载）"""
+    return load_config()
+
+
+def get_server_config() -> Dict[str, Any]:
+    """获取服务器配置"""
+    return get_config()["server"]
+
+
+def get_database_config() -> Dict[str, Any]:
+    """获取数据库配置"""
+    return get_config()["database"]
+
+
+def get_cli_config() -> Dict[str, Any]:
+    """获取CLI配置"""
+    return get_config()["cli"]
+