"""文件解析服务。

Excel/PDF 文件解析 → 文本提取。
"""


async def parse_excel(file_bytes: bytes) -> str:
    """解析 Excel 文件，提取文本内容。"""
    try:
        import openpyxl
        import io
        wb = openpyxl.load_workbook(io.BytesIO(file_bytes), read_only=True)
        texts: list[str] = []
        for sheet in wb.sheetnames:
            ws = wb[sheet]
            for row in ws.iter_rows(values_only=True):
                row_text = " | ".join(str(c) for c in row if c is not None)
                if row_text.strip():
                    texts.append(row_text)
        return "\n".join(texts)
    except Exception:
        return ""


async def parse_pdf(file_bytes: bytes) -> str:
    """解析 PDF 文件，提取文本内容。"""
    try:
        import fitz
        import io
        doc = fitz.open(stream=io.BytesIO(file_bytes), filetype="pdf")
        texts: list[str] = []
        for page in doc:
            texts.append(page.get_text())
        return "\n".join(texts)
    except Exception:
        return ""


async def parse_file(file_bytes: bytes, filename: str) -> str:
    """根据文件类型选择解析器。"""
    if filename.endswith((".xlsx", ".xls")):
        return await parse_excel(file_bytes)
    elif filename.endswith(".pdf"):
        return await parse_pdf(file_bytes)
    elif filename.endswith((".txt", ".md", ".csv")):
        return file_bytes.decode("utf-8", errors="ignore")
    return ""