"""读取项目关键文件用于 AI 审查"""
import os
from pathlib import Path

SKIP_DIRS = {
    "node_modules", ".git", "venv", ".venv", "__pycache__", "dist", "build",
    "target", ".idea", ".vscode", "vendor", "env",
}
SKIP_SUFFIXES = {
    ".png", ".jpg", ".jpeg", ".gif", ".ico", ".pdf", ".zip", ".tar", ".gz",
    ".whl", ".jar", ".class", ".pyc", ".so", ".dll", ".exe", ".bin", ".woff",
    ".woff2", ".ttf", ".eot", ".mp4", ".mp3",
}
MAX_FILE_CHARS = 8000


def iter_source_files(root: str):
    for dirpath, dirnames, filenames in os.walk(root):
        dirnames[:] = [d for d in dirnames if d not in SKIP_DIRS]
        for name in sorted(filenames):
            path = Path(dirpath) / name
            if path.suffix.lower() in SKIP_SUFFIXES:
                continue
            try:
                if path.stat().st_size > 512 * 1024:
                    continue
                if not path.is_file():
                    continue
            except OSError:
                continue
            yield path


def read_key_files(root: str, max_chars: int = 12000) -> str:
    parts = []
    total = 0
    for path in iter_source_files(root):
        try:
            text = path.read_text(encoding="utf-8", errors="replace")
        except (OSError, UnicodeDecodeError):
            continue
        if len(text) > MAX_FILE_CHARS:
            text = text[:MAX_FILE_CHARS] + "\n... (截断)"
        rel = os.path.relpath(path, root)
        block = f"### 文件: {rel}\n```\n{text}\n```"
        if total + len(block) > max_chars:
            break
        parts.append(block)
        total += len(block)
        if len(parts) >= 25:
            break
    if not parts:
        return "(未找到可读源码文件)"
    return "\n\n".join(parts)