import os
from spire.doc import Document, FileFormat as DocFileFormat
from spire.pdf import PdfToMarkdownConverter
from spire.xls import Workbook, MarkdownOptions as XlsMarkdownOptions
from spire.presentation import Presentation, FileFormat as PresentationFileFormat


def convert_to_markdown(input_path: str, output_path: str = None) -> str:
    """将 Word、PDF、Excel 或 PowerPoint 文件转换为 Markdown。

    Args:
        input_path: 源文档路径。
        output_path: 输出 .md 文件路径。如果为 None，则使用
            输入文件名加 .md 扩展名，保存在同一目录下。

    Returns:
        生成的 Markdown 文件路径。
    """
    if not os.path.isfile(input_path):
        raise FileNotFoundError(f"输入文件不存在: {input_path}")

    ext = os.path.splitext(input_path)[1].lower()

    if output_path is None:
        output_path = os.path.splitext(input_path)[0] + ".md"

    if ext in (".doc", ".docx"):
        # Spire.Doc for Python: 加载并保存为 Markdown
        doc = Document()
        try:
            doc.LoadFromFile(input_path)
            doc.SaveToFile(output_path, DocFileFormat.Markdown)
        finally:
            doc.Close()

    elif ext == ".pdf":
        # Spire.PDF for Python: 使用 PdfToMarkdownConverter
        # IgnoreImage=True 跳过 PDF 中的图片；如果图表或截图
        # 包含重要信息，则设为 False。
        converter = PdfToMarkdownConverter(input_path)
        try:
            converter.MarkdownOptions.IgnoreImage = True
            converter.ConvertToMarkdown(output_path)
        finally:
            converter.Dispose()

    elif ext in (".xls", ".xlsx"):
        # Spire.XLS for Python: 使用 SaveToMarkdown 和 MarkdownOptions
        workbook = Workbook()
        try:
            workbook.LoadFromFile(input_path)
            options = XlsMarkdownOptions()
            options.SavePicInRelativePath = True
            options.SaveHyperlinkAsRef = False
            workbook.SaveToMarkdown(output_path, options)
        finally:
            workbook.Dispose()

    elif ext in (".ppt", ".pptx"):
        # Spire.Presentation for Python: 加载并保存为 Markdown
        presentation = Presentation()
        try:
            presentation.LoadFromFile(input_path)
            presentation.SaveToFile(output_path, PresentationFileFormat.Markdown)
        finally:
            presentation.Dispose()

    else:
        raise ValueError(
            f"不支持的文件扩展名: {ext}. "
            f"支持的格式: .doc, .docx, .pdf, .xls, .xlsx, .ppt, .pptx"
        )

    return output_path


# 示例用法
if __name__ == "__main__":
    result = convert_to_markdown("quarterly_report.docx")
    print(f"Markdown 已保存至: {result}")

    with open(result, "r", encoding="utf-8") as f:
        content = f.read()
    print(content[:500])  # 预览前 500 个字符

import os
from openai import OpenAI

# 步骤 1: 将文档转换为 Markdown
from convert_to_markdown import convert_to_markdown
md_path = convert_to_markdown("business_report.pdf")

# 步骤 2: 读取 Markdown 内容
with open(md_path, "r", encoding="utf-8") as f:
    markdown_content = f.read()

# 步骤 3: 构造任务指令并调用 LLM
client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))

response = client.chat.completions.create(
    model="gpt-6-luna",
    messages=[
        {
            "role": "system",
            "content": "You are a financial analyst. Read the document "
                       "and extract the three most important findings."
        },
        {
            "role": "user",
            "content": f"Here is the document content in Markdown:\n\n"
                       f"{markdown_content}\n\n"
                       f"Provide a concise summary of the key findings."
        }
    ],
    max_completion_tokens=1000
)

# 步骤 4: 读取并显示响应
summary = response.choices[0].message.content
print("=== LLM 摘要 ===")
print(summary)