"""文件解析服务：将上传的文件转换为纯文本"""

from pathlib import Path


# 支持的文件扩展名
ALLOWED_EXTENSIONS = {".txt", ".md", ".docx", ".pdf"}

# 最大文件大小 10MB
MAX_FILE_SIZE = 10 * 1024 * 1024


def parse_file(file_path: Path, mime_type: str) -> str:
    """解析文件为纯文本，返回文本内容"""
    ext = file_path.suffix.lower()

    if ext in (".txt", ".md"):
        return _parse_text(file_path)
    elif ext == ".docx":
        return _parse_docx(file_path)
    elif ext == ".pdf":
        return _parse_pdf(file_path)
    else:
        raise ValueError(f"不支持的文件格式: {ext}")


def _parse_text(file_path: Path) -> str:
    """解析纯文本文件，自动检测编码"""
    for encoding in ("utf-8", "gbk", "gb18030", "utf-16", "latin-1"):
        try:
            return file_path.read_text(encoding=encoding)
        except (UnicodeDecodeError, UnicodeError):
            continue
    # 最后用 errors='replace' 兜底
    return file_path.read_text(encoding="utf-8", errors="replace")


def _parse_docx(file_path: Path) -> str:
    """解析 Word 文档"""
    try:
        from docx import Document
    except ImportError:
        raise RuntimeError("需要安装 python-docx: pip install python-docx")

    doc = Document(str(file_path))
    paragraphs = [p.text for p in doc.paragraphs if p.text.strip()]
    return "\n\n".join(paragraphs)


def _parse_pdf(file_path: Path) -> str:
    """解析 PDF 文件"""
    try:
        import fitz  # pymupdf
    except ImportError:
        raise RuntimeError("需要安装 pymupdf: pip install pymupdf")

    doc = fitz.open(str(file_path))
    pages = []
    for page in doc:
        text = page.get_text().strip()
        if text:
            pages.append(text)
    doc.close()
    return "\n\n".join(pages)