PCM_Report/convert_md_to_docx.py

"""
将 Markdown 文件转换为 DOCX 格式
使用 python-docx 库生成格式化的 Word 文档
"""

from docx import Document
from docx.shared import Pt, RGBColor, Inches
from docx.enum.text import WD_ALIGN_PARAGRAPH
from docx.oxml.ns import qn
import re
from pathlib import Path


def parse_markdown_to_docx(md_file: str, docx_file: str):
    """将 Markdown 文件转换为 DOCX 文档"""
    
    # 创建文档
    doc = Document()
    
    # 设置中文字体
    doc.styles['Normal'].font.name = '宋体'
    doc.styles['Normal']._element.rPr.rFonts.set(qn('w:eastAsia'), '宋体')
    doc.styles['Normal'].font.size = Pt(10.5)
    
    # 读取 Markdown 文件
    with open(md_file, 'r', encoding='utf-8') as f:
        lines = f.readlines()
    
    # 解析并转换
    i = 0
    in_code_block = False
    code_lines = []
    in_table = False
    table_lines = []
    
    while i < len(lines):
        line = lines[i].rstrip()
        
        # 代码块处理
        if line.startswith('```'):
            if not in_code_block:
                in_code_block = True
                code_lines = []
            else:
                # 结束代码块
                in_code_block = False
                if code_lines:
                    p = doc.add_paragraph()
                    p.style = 'Normal'
                    run = p.add_run('\n'.join(code_lines))
                    run.font.name = 'Consolas'
                    run.font.size = Pt(9)
                    run.font.color.rgb = RGBColor(0, 0, 0)
                    # 设置背景色（浅灰色）
                    p.paragraph_format.left_indent = Inches(0.5)
                    p.paragraph_format.right_indent = Inches(0.5)
            i += 1
            continue
        
        if in_code_block:
            code_lines.append(line)
            i += 1
            continue
        
        # 表格处理
        if line.startswith('|') and '|' in line[1:]:
            if not in_table:
                in_table = True
                table_lines = []
            table_lines.append(line)
            i += 1
            # 检查下一行是否还是表格
            if i < len(lines) and not lines[i].strip().startswith('|'):
                # 表格结束，创建表格
                create_table_from_markdown(doc, table_lines)
                in_table = False
                table_lines = []
            continue
        
        # 空行
        if not line.strip():
            doc.add_paragraph()
            i += 1
            continue
        
        # 一级标题
        if line.startswith('# '):
            heading = doc.add_heading(line[2:], level=1)
            heading.alignment = WD_ALIGN_PARAGRAPH.CENTER
            for run in heading.runs:
                run.font.name = '黑体'
                run._element.rPr.rFonts.set(qn('w:eastAsia'), '黑体')
                run.font.size = Pt(18)
                run.font.color.rgb = RGBColor(0, 0, 0)
        
        # 二级标题
        elif line.startswith('## '):
            heading = doc.add_heading(line[3:], level=2)
            for run in heading.runs:
                run.font.name = '黑体'
                run._element.rPr.rFonts.set(qn('w:eastAsia'), '黑体')
                run.font.size = Pt(16)
                run.font.color.rgb = RGBColor(0, 0, 128)
        
        # 三级标题
        elif line.startswith('### '):
            heading = doc.add_heading(line[4:], level=3)
            for run in heading.runs:
                run.font.name = '黑体'
                run._element.rPr.rFonts.set(qn('w:eastAsia'), '黑体')
                run.font.size = Pt(14)
                run.font.color.rgb = RGBColor(0, 0, 128)
        
        # 四级标题
        elif line.startswith('#### '):
            heading = doc.add_heading(line[5:], level=4)
            for run in heading.runs:
                run.font.name = '黑体'
                run._element.rPr.rFonts.set(qn('w:eastAsia'), '黑体')
                run.font.size = Pt(12)
        
        # 无序列表
        elif line.startswith('- ') or line.startswith('* '):
            text = line[2:]
            # 处理加粗
            text = process_bold_text(text)
            p = doc.add_paragraph(style='List Bullet')
            add_formatted_text(p, text)
        
        # 有序列表
        elif re.match(r'^\d+\.\s', line):
            text = re.sub(r'^\d+\.\s', '', line)
            text = process_bold_text(text)
            p = doc.add_paragraph(style='List Number')
            add_formatted_text(p, text)
        
        # 分隔线
        elif line.startswith('---'):
            doc.add_paragraph('_' * 50)
        
        # 普通段落
        else:
            text = process_bold_text(line)
            p = doc.add_paragraph()
            add_formatted_text(p, text)
        
        i += 1
    
    # 保存文档
    doc.save(docx_file)
    print(f"文档已生成: {docx_file}")


def create_table_from_markdown(doc, table_lines):
    """从 Markdown 表格行创建 Word 表格"""
    if len(table_lines) < 2:
        return
    
    # 解析表头
    header_line = table_lines[0]
    headers = [cell.strip() for cell in header_line.split('|')[1:-1]]
    
    # 跳过分隔线
    data_lines = table_lines[2:] if len(table_lines) > 2 else []
    
    # 解析数据行
    rows_data = []
    for line in data_lines:
        cells = [cell.strip() for cell in line.split('|')[1:-1]]
        rows_data.append(cells)
    
    # 创建表格
    table = doc.add_table(rows=1 + len(rows_data), cols=len(headers))
    table.style = 'Light Grid Accent 1'
    
    # 填充表头
    header_cells = table.rows[0].cells
    for i, header in enumerate(headers):
        header_cells[i].text = header
        # 设置表头样式
        for paragraph in header_cells[i].paragraphs:
            for run in paragraph.runs:
                run.font.bold = True
                run.font.name = '黑体'
                run._element.rPr.rFonts.set(qn('w:eastAsia'), '黑体')
    
    # 填充数据
    for row_idx, row_data in enumerate(rows_data, start=1):
        row_cells = table.rows[row_idx].cells
        for col_idx, cell_data in enumerate(row_data):
            # 处理特殊符号
            cell_text = cell_data.replace('**', '').replace('`', '')
            row_cells[col_idx].text = cell_text


def process_bold_text(text):
    """处理加粗文本标记"""
    return text


def add_formatted_text(paragraph, text):
    """添加格式化文本到段落"""
    # 处理加粗 **text**
    parts = re.split(r'(\*\*.*?\*\*)', text)
    
    for part in parts:
        if part.startswith('**') and part.endswith('**'):
            # 加粗文本
            run = paragraph.add_run(part[2:-2])
            run.font.bold = True
            run.font.name = '宋体'
            run._element.rPr.rFonts.set(qn('w:eastAsia'), '宋体')
        elif part.startswith('`') and part.endswith('`'):
            # 代码文本
            run = paragraph.add_run(part[1:-1])
            run.font.name = 'Consolas'
            run.font.size = Pt(9)
        else:
            # 普通文本
            # 处理内联代码 `code`
            code_parts = re.split(r'(`.*?`)', part)
            for code_part in code_parts:
                if code_part.startswith('`') and code_part.endswith('`'):
                    run = paragraph.add_run(code_part[1:-1])
                    run.font.name = 'Consolas'
                    run.font.size = Pt(9)
                else:
                    # 处理表情符号和特殊字符
                    run = paragraph.add_run(code_part)
                    run.font.name = '宋体'
                    run._element.rPr.rFonts.set(qn('w:eastAsia'), '宋体')


if __name__ == '__main__':
    # 转换文件
    md_file = Path(__file__).parent / 'Docx报告生成器使用说明书V2.0.md'
    docx_file = Path(__file__).parent / 'Docx报告生成器使用说明书V2.0.docx'
    
    print(f"开始转换: {md_file.name}")
    parse_markdown_to_docx(str(md_file), str(docx_file))
    print(f"转换完成!")
    print(f"输出文件: {docx_file}")