lyxy-document/readers/pptx/python_pptx.py

"""使用 python-pptx 库解析 PPTX 文件"""

from typing import Any, List, Optional, Tuple

from core import build_markdown_table, flush_list_stack


def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
    """使用 python-pptx 库解析 PPTX 文件"""
    try:
        from pptx import Presentation
        from pptx.enum.shapes import MSO_SHAPE_TYPE
    except ImportError:
        return None, "python-pptx 库未安装"

    _A_NS = {"a": "http://schemas.openxmlformats.org/drawingml/2006/main"}

    def extract_formatted_text(runs: List[Any]) -> str:
        """从 PPTX 文本运行中提取带有格式的文本"""
        result = []
        for run in runs:
            if not run.text:
                continue

            text = run.text

            font = run.font
            is_bold = getattr(font, "bold", False) or False
            is_italic = getattr(font, "italic", False) or False

            if is_bold and is_italic:
                text = f"***{text}***"
            elif is_bold:
                text = f"**{text}**"
            elif is_italic:
                text = f"*{text}*"

            result.append(text)

        return "".join(result).strip()

    def convert_table_to_md(table: Any) -> str:
        """将 PPTX 表格转换为 Markdown 格式"""
        rows_data = []
        for row in table.rows:
            row_data = []
            for cell in row.cells:
                cell_content = []
                for para in cell.text_frame.paragraphs:
                    text = extract_formatted_text(para.runs)
                    if text:
                        cell_content.append(text)
                cell_text = " ".join(cell_content).strip()
                row_data.append(cell_text if cell_text else "")
            rows_data.append(row_data)
        return build_markdown_table(rows_data)

    try:
        prs = Presentation(file_path)
        md_content = []

        for slide_num, slide in enumerate(prs.slides, 1):
            md_content.append(f"\n## Slide {slide_num}\n")

            list_stack = []

            for shape in slide.shapes:
                if shape.shape_type == MSO_SHAPE_TYPE.PICTURE:
                    continue

                if hasattr(shape, "has_table") and shape.has_table:
                    if list_stack:
                        flush_list_stack(list_stack, md_content)

                    table_md = convert_table_to_md(shape.table)
                    md_content.append(table_md)

                if hasattr(shape, "text_frame"):
                    for para in shape.text_frame.paragraphs:
                        pPr = para._element.pPr
                        is_list = False
                        if pPr is not None:
                            is_list = (
                                para.level > 0
                                or pPr.find(".//a:buChar", namespaces=_A_NS) is not None
                                or pPr.find(".//a:buAutoNum", namespaces=_A_NS) is not None
                            )

                        if is_list:
                            level = para.level

                            while len(list_stack) <= level:
                                list_stack.append("")

                            text = extract_formatted_text(para.runs)
                            if text:
                                is_ordered = (
                                    pPr is not None
                                    and pPr.find(".//a:buAutoNum", namespaces=_A_NS) is not None
                                )
                                marker = "1. " if is_ordered else "- "
                                indent = "  " * level
                                list_stack[level] = f"{indent}{marker}{text}"

                                for i in range(len(list_stack)):
                                    if list_stack[i]:
                                        md_content.append(list_stack[i] + "\n")
                                        list_stack[i] = ""
                        else:
                            if list_stack:
                                flush_list_stack(list_stack, md_content)

                            text = extract_formatted_text(para.runs)
                            if text:
                                md_content.append(f"{text}\n")

            if list_stack:
                flush_list_stack(list_stack, md_content)

            md_content.append("---\n")

        content = "\n".join(md_content)
        if not content.strip():
            return None, "文档为空"
        return content, None
    except Exception as e:
        return None, f"python-pptx 解析失败: {str(e)}"