#!/usr/bin/env python3
"""
将 Markdown 文章转换为 Word 文档，嵌入图片
"""

import os
import re
from docx import Document
from docx.shared import Inches, Pt, RGBColor
from docx.enum.text import WD_ALIGN_PARAGRAPH

# 路径配置
MARKDOWN_FILE = "/root/.openclaw/workspaces/yzr-yxl/projects/yu-zhi-ran/content/published/2026-04-14-上海阳台种菜一年/final-article.md"
IMAGES_DIR = "/root/.openclaw/workspaces/yzr-yxl/projects/yu-zhi-ran/content/publishing/images"
OUTPUT_DOCX = "/root/.openclaw/workspaces/yzr-yxl/projects/yu-zhi-ran/content/published/2026-04-14-上海阳台种菜一年/上海阳台种菜一年_最终版.docx"

# 读取 Markdown
with open(MARKDOWN_FILE, "r", encoding="utf-8") as f:
    lines = f.readlines()

doc = Document()
doc.styles['Normal'].font.name = '微软雅黑'
doc.styles['Normal'].font.size = Pt(11)

# 样式函数
def add_heading(text, level=1):
    heading = doc.add_heading(text, level=level)
    heading.alignment = WD_ALIGN_PARAGRAPH.LEFT
    return heading

def add_paragraph(text, bold=False, italic=False):
    p = doc.add_paragraph()
    run = p.add_run(text)
    run.bold = bold
    run.italic = italic
    return p

# 解析 Markdown
in_code_block = False
in_table = False
table_data = []

for i, line in enumerate(lines):
    line = line.rstrip('\n')

    # 代码块跳过
    if line.startswith('```'):
        in_code_block = not in_code_block
        continue
    if in_code_block:
        continue

    # 标题
    if line.startswith('# '):
        add_heading(line[2:], level=1)
        continue
    if line.startswith('## '):
        add_heading(line[3:], level=2)
        continue
    if line.startswith('### '):
        add_heading(line[4:], level=3)
        continue

    # 表格处理（简化：将表格转为文本，图片位置用占位）
    if line.startswith('|'):
        in_table = True
        table_data.append(line)
        continue
    if in_table and not line.startswith('|'):
        in_table = False
        # 可以在此转换表格，为简化直接跳过
        continue

    # 图片：![alt](path)
    img_match = re.match(r'!\[(.*?)\]\((images/.*?)\)', line)
    if img_match:
        alt, path = img_match.groups()
        img_full_path = os.path.join(os.path.dirname(MARKDOWN_FILE), path)
        if os.path.exists(img_full_path):
            try:
                # 插入图片，宽度 6 英寸（约 15cm）
                doc.add_picture(img_full_path, width=Inches(6))
                # 居中
                last_para = doc.paragraphs[-1]
                last_para.alignment = WD_ALIGN_PARAGRAPH.CENTER
                # 添加图片说明（可选）
                if alt:
                    cap = doc.add_paragraph(alt)
                    cap.alignment = WD_ALIGN_PARAGRAPH.CENTER
                    cap.style = 'Caption'
            except Exception as e:
                doc.add_paragraph(f"[图片加载失败: {path}]")
        else:
            doc.add_paragraph(f"[图片缺失: {img_full_path}]")
        continue

    # 引用
    if line.startswith('> '):
        p = doc.add_paragraph(line[2:])
        p.paragraph_format.left_indent = Inches(0.5)
        p.italic = True
        continue

    # 列表
    if re.match(r'^[-*] ', line):
        p = doc.add_paragraph(line[2:], style='List Bullet')
        continue
    if re.match(r'^\d+\. ', line):
        p = doc.add_paragraph(line[line.find('.')+2:], style='List Number')
        continue

    # 分隔线
    if line.strip() == '---':
        doc.add_paragraph('_' * 50)
        continue

    # 普通段落
    if line.strip():
        # 处理行内加粗、斜体
        p = doc.add_paragraph()
        parts = re.split(r'(\*\*[^*]+\*\*|\*[^*]+\*)', line)
        for part in parts:
            if part.startswith('**') and part.endswith('**'):
                run = p.add_run(part[2:-2])
                run.bold = True
            elif part.startswith('*') and part.endswith('*'):
                run = p.add_run(part[1:-1])
                run.italic = True
            else:
                run = p.add_run(part)
    else:
        doc.add_paragraph()  # 空行

# 保存文档
doc.save(OUTPUT_DOCX)
print(f"✅ Word 文档已生成: {OUTPUT_DOCX}")
print(f"📄 页数: {len(doc.paragraphs)} 段落")
print(f"🖼️  图片路径: {IMAGES_DIR}")