qc_ns_web/format_manual.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
格式化系统操作手册
"""

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

def add_page_break(doc):
    """添加分页符"""
    doc.add_page_break()

def set_font(run, font_name='宋体', font_size=12, bold=False):
    """设置字体"""
    run.font.name = font_name
    run.font.size = Pt(font_size)
    run.font.bold = bold
    # 设置中文字体
    run._element.rPr.rFonts.set(qn('w:eastAsia'), font_name)

def format_document(input_path, output_path):
    """格式化文档"""

    # 读取原文档
    doc = Document(input_path)

    # 创建新文档
    new_doc = Document()

    # 设置页边距
    for section in new_doc.sections:
        section.top_margin = Inches(1)
        section.bottom_margin = Inches(1)
        section.left_margin = Inches(1.25)
        section.right_margin = Inches(1.25)

    # ===== 第一页：标题页 =====
    title_para = new_doc.add_paragraph()
    title_para.alignment = WD_ALIGN_PARAGRAPH.CENTER
    # 添加一些空行使标题居中
    for _ in range(8):
        new_doc.add_paragraph()

    title_para = new_doc.add_paragraph()
    title_para.alignment = WD_ALIGN_PARAGRAPH.CENTER
    title_run = title_para.add_run('系统操作手册')
    set_font(title_run, font_name='黑体', font_size=28, bold=True)

    # 添加分页符
    add_page_break(new_doc)

    # ===== 第二页：目录 =====
    toc_title = new_doc.add_paragraph()
    toc_title.alignment = WD_ALIGN_PARAGRAPH.CENTER
    toc_run = toc_title.add_run('目  录')
    set_font(toc_run, font_name='黑体', font_size=18, bold=True)
    new_doc.add_paragraph()  # 空行

    # 目录内容
    toc_items = [
        ('1、系统登录', 2),
        ('1.1 系统登录', 3),
        ('1.2 系统首页', 3),
        ('2、数据管理', 2),
        ('2.1 检查列表', 3),
        ('2.1.1 影像上传', 4),
        ('2.1.2 查看影像数据详情', 4),
        ('2.2 部位列表', 3),
        ('2.3 患者信息', 3),
        ('3、质控管理', 2),
        ('3.1 全量质控', 3),
        ('3.2 质控任务', 3),
        ('3.3 质控结果', 3),
        ('3.4 部位结果', 3),
        ('4、字典管理', 2),
        ('4.1 质控标准', 3),
        ('4.2 质控因子', 3),
        ('4.3 检查项目', 3),
        ('5、系统管理', 2),
        ('5.1 用户管理', 3),
        ('5.2 对接设置', 3),
    ]

    for item_text, level in toc_items:
        toc_para = new_doc.add_paragraph()
        indent = (level - 2) * 0.5  # 缩进
        toc_para.paragraph_format.left_indent = Inches(indent)
        toc_run = toc_para.add_run(item_text)
        set_font(toc_run, font_name='宋体', font_size=12)

    # 添加分页符
    add_page_break(new_doc)

    # ===== 第三页开始：正文内容 =====
    # 收集原文档中的所有段落和图片
    content_started = False

    for para in doc.paragraphs:
        text = para.text.strip()

        # 跳过前面的空段落，直到找到第一个有内容的段落
        if not content_started and not text:
            continue

        if text:
            content_started = True

        # 判断段落类型并应用相应格式
        new_para = new_doc.add_paragraph()

        # 一级标题 (如: 1、系统登录, 2、数据管理)
        if text and (text.startswith('1、') or text.startswith('2、') or
                     text.startswith('3、') or text.startswith('4、') or
                     text.startswith('5、') or text == '系统登录'):
            new_para.style = 'Heading 1'
            run = new_para.add_run(text)
            set_font(run, font_name='黑体', font_size=16, bold=True)
            new_para.paragraph_format.space_before = Pt(12)
            new_para.paragraph_format.space_after = Pt(6)

        # 二级标题 (如: 1.1, 1.2, 2.1)
        elif text and len(text) > 2 and text[0].isdigit() and '.' in text[:4] and text.split()[0].count('.') == 1:
            new_para.style = 'Heading 2'
            run = new_para.add_run(text)
            set_font(run, font_name='黑体', font_size=14, bold=True)
            new_para.paragraph_format.space_before = Pt(10)
            new_para.paragraph_format.space_after = Pt(5)
            new_para.paragraph_format.left_indent = Inches(0)

        # 三级标题 (如: 2.1.1, 2.1.2)
        elif text and len(text) > 4 and text[0].isdigit() and text.split()[0].count('.') == 2:
            new_para.style = 'Heading 3'
            run = new_para.add_run(text)
            set_font(run, font_name='黑体', font_size=13, bold=True)
            new_para.paragraph_format.space_before = Pt(8)
            new_para.paragraph_format.space_after = Pt(4)
            new_para.paragraph_format.left_indent = Inches(0)

        # 普通段落
        else:
            run = new_para.add_run(text)
            set_font(run, font_name='宋体', font_size=11)
            new_para.paragraph_format.space_after = Pt(3)
            new_para.paragraph_format.line_spacing = 1.15

        # 复制图片
        if para._element.xpath('.//w:drawing'):
            # 如果段落包含图片，复制图片
            for run in para.runs:
                if 'graphicData' in run._element.xml:
                    try:
                        # 获取图片
                        inline = run._element.xpath('.//w:drawing//wp:inline')
                        if inline:
                            # 复制图片到新文档
                            new_para_img = new_doc.add_paragraph()
                            new_para_img.alignment = WD_ALIGN_PARAGRAPH.CENTER
                            # 注意：这里需要从原文档中提取图片数据
                            # 由于复杂性，我们先保留图片位置的空段落
                    except:
                        pass

    # 保存新文档
    new_doc.save(output_path)
    print(f"文档格式化完成！已保存到: {output_path}")


if __name__ == '__main__':
    input_file = '/Users/geng/Desktop/系统操作手册.docx'
    output_file = '/Users/geng/Desktop/系统操作手册_格式化.docx'

    format_document(input_file, output_file)