1515 } ,
1616 hexoVersion : '6.3.0'
1717} </ script > < link rel ="alternate " href ="/atom.xml " title ="布多的博客 " type ="application/atom+xml ">
18- </ head > < body > < canvas class ="fireworks "> </ canvas > < i class ="fa fa-arrow-right " id ="toggle-sidebar " aria-hidden ="true "> </ i > < div id ="sidebar " data-display ="true "> < div class ="toggle-sidebar-info text-center "> < span data-toggle ="切换文章详情 "> 切换站点概览</ span > < hr > </ div > < div class ="sidebar-toc "> < div class ="sidebar-toc__title "> 目录</ div > < div class ="sidebar-toc__progress "> < span class ="progress-notice "> 你已经读了</ span > < span class ="progress-num "> 0</ span > < span class ="progress-percentage "> %</ span > < div class ="sidebar-toc__progress-bar "> </ div > </ div > < div class ="sidebar-toc__content "> < ol class ="toc "> < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#%E5%AD%97%E7%AC%A6%E7%BC%96%E7%A0%81%E7%9A%84%E8%B5%B7%E6%BA%90 "> < span class ="toc-number "> 1.</ span > < span class ="toc-text "> 字符编码的起源</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#Unicode-%E7%9A%84%E8%AF%9E%E7%94%9F%E4%B8%8E%E5%8F%91%E5%B1%95 "> < span class ="toc-number "> 2.</ span > < span class ="toc-text "> Unicode 的诞生与发展</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#Unicode-%E7%9A%84%E5%86%85%E9%83%A8%E7%BB%93%E6%9E%84%E4%B8%8E%E7%89%B9%E6%80%A7 "> < span class ="toc-number "> 3.</ span > < span class ="toc-text "> Unicode 的内部结构与特性</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#UTF-%E7%9A%84%E8%AF%9E%E7%94%9F "> < span class ="toc-number "> 4.</ span > < span class ="toc-text "> UTF 的诞生</ span > </ a > < ol class ="toc-child "> < li class ="toc-item toc-level-3 "> < a class ="toc-link " href ="#UTF-8 "> < span class ="toc-number "> 4.1.</ span > < span class ="toc-text "> UTF-8</ span > </ a > </ li > < li class ="toc-item toc-level-3 "> < a class ="toc-link " href ="#UTF-16 "> < span class ="toc-number "> 4.2.</ span > < span class ="toc-text "> UTF-16</ span > </ a > </ li > < li class ="toc-item toc-level-3 "> < a class ="toc-link " href ="#UTF-32 "> < span class ="toc-number "> 4.3.</ span > < span class ="toc-text "> UTF-32</ span > </ a > </ li > </ ol > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#UTF-%E5%90%84%E4%B8%AA%E7%BC%96%E7%A0%81%E6%96%B9%E6%A1%88%E7%9A%84%E5%AF%B9%E6%AF%94 "> < span class ="toc-number "> 5.</ span > < span class ="toc-text "> UTF 各个编码方案的对比</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#%E5%AD%97%E8%8A%82%E5%BA%8F "> < span class ="toc-number "> 6.</ span > < span class ="toc-text "> 字节序</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#%E6%B3%A8%E6%84%8F%E4%BA%8B%E9%A1%B9 "> < span class ="toc-number "> 7.</ span > < span class ="toc-text "> 注意事项</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#%E6%80%BB%E7%BB%93 "> < span class ="toc-number "> 8.</ span > < span class ="toc-text "> 总结</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#%E5%8F%82%E8%80%83 "> < span class ="toc-number "> 9.</ span > < span class ="toc-text "> 参考</ span > </ a > </ li > </ ol > </ div > </ div > < div class ="author-info hide "> < div class ="author-info__avatar text-center "> < img src ="/images/avatar.jpg "> </ div > < div class ="author-info__name text-center "> 布多</ div > < div class ="author-info__description text-center "> 前进！前进！！不择手段地前进！！！</ div > < div class ="follow-button "> < a target ="_blank " rel ="noopener " href ="https://github.com/internetwei "> Follow Me</ a > </ div > < hr > < div class ="author-info-articles "> < a class ="author-info-articles__archives article-meta " href ="/archives "> < span class ="pull-left "> 文章</ span > < span class ="pull-right "> 20</ span > </ a > < a class ="author-info-articles__tags article-meta " href ="/tags "> < span class ="pull-left "> 标签</ span > < span class ="pull-right "> 14</ span > </ a > < a class ="author-info-articles__categories article-meta " href ="/categories "> < span class ="pull-left "> 分类</ span > < span class ="pull-right "> 4</ span > </ a > </ div > < hr > < div class ="author-info-links "> < div class ="author-info-links__title text-center "> 友链</ div > < a class ="author-info-links__name text-center " target ="_blank " rel ="noopener " href ="https://www.coderqi.com/ "> 齐小胖之家</ a > </ div > </ div > </ div > < div id ="content-outer "> < div id ="top-container " style ="background-image: url(/images/backgroundImage.jpg) "> < div id ="page-header "> < span class ="pull-left "> < a id ="site-name " href ="/ "> 布多的博客</ a > </ span > < i class ="fa fa-bars toggle-menu pull-right " aria-hidden ="true "> </ i > < span class ="pull-right menus "> < a class ="site-page " href ="/ "> 首页</ a > < a class ="site-page " href ="/tags "> 标签</ a > < a class ="site-page " href ="/categories "> 分类</ a > < a class ="site-page " href ="/archives "> 归档</ a > < a class ="site-page " href ="/about "> 关于</ a > </ span > < span class ="pull-right "> < a class ="site-page social-icon search "> < i class ="fa fa-search "> </ i > < span > 搜索</ span > </ a > </ span > </ div > < div id ="post-info "> < div id ="post-title "> 字符编码的秘密：Unicode 和 UTF 到底是什么？</ div > < div id ="post-meta "> < time class ="post-meta__date "> < i class ="fa fa-calendar " aria-hidden ="true "> </ i > 2025-05-21</ time > < span class ="post-meta__separator "> |</ span > < i class ="fa fa-inbox post-meta__icon " aria-hidden ="true "> </ i > < a class ="post-meta__categories " href ="/categories/%E8%AE%A1%E7%AE%97%E6%9C%BA%E5%9F%BA%E7%A1%80/ "> 计算机基础</ a > < div class ="post-meta-wordcount "> < span > 字数总计: </ span > < span class ="word-count "> 5.5k</ span > < span class ="post-meta__separator "> |</ span > < span > 阅读时长: 17 分钟</ span > </ div > </ div > </ div > </ div > < div class ="layout " id ="content-inner "> < article id ="post "> < div class ="article-container " id ="post-content "> < blockquote >
19- < p > 由 布多(budo) 发布于 2025-05-21，更新于 2025-05-22 </ p >
18+ </ head > < body > < canvas class ="fireworks "> </ canvas > < i class ="fa fa-arrow-right " id ="toggle-sidebar " aria-hidden ="true "> </ i > < div id ="sidebar " data-display ="true "> < div class ="toggle-sidebar-info text-center "> < span data-toggle ="切换文章详情 "> 切换站点概览</ span > < hr > </ div > < div class ="sidebar-toc "> < div class ="sidebar-toc__title "> 目录</ div > < div class ="sidebar-toc__progress "> < span class ="progress-notice "> 你已经读了</ span > < span class ="progress-num "> 0</ span > < span class ="progress-percentage "> %</ span > < div class ="sidebar-toc__progress-bar "> </ div > </ div > < div class ="sidebar-toc__content "> < ol class ="toc "> < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#%E5%AD%97%E7%AC%A6%E7%BC%96%E7%A0%81%E7%9A%84%E8%B5%B7%E6%BA%90 "> < span class ="toc-number "> 1.</ span > < span class ="toc-text "> 字符编码的起源</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#Unicode-%E7%9A%84%E8%AF%9E%E7%94%9F%E4%B8%8E%E5%8F%91%E5%B1%95 "> < span class ="toc-number "> 2.</ span > < span class ="toc-text "> Unicode 的诞生与发展</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#Unicode-%E7%9A%84%E5%86%85%E9%83%A8%E7%BB%93%E6%9E%84%E4%B8%8E%E7%89%B9%E6%80%A7 "> < span class ="toc-number "> 3.</ span > < span class ="toc-text "> Unicode 的内部结构与特性</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#UTF-%E7%9A%84%E8%AF%9E%E7%94%9F "> < span class ="toc-number "> 4.</ span > < span class ="toc-text "> UTF 的诞生</ span > </ a > < ol class ="toc-child "> < li class ="toc-item toc-level-3 "> < a class ="toc-link " href ="#UTF-8 "> < span class ="toc-number "> 4.1.</ span > < span class ="toc-text "> UTF-8</ span > </ a > </ li > < li class ="toc-item toc-level-3 "> < a class ="toc-link " href ="#UTF-16 "> < span class ="toc-number "> 4.2.</ span > < span class ="toc-text "> UTF-16</ span > </ a > </ li > < li class ="toc-item toc-level-3 "> < a class ="toc-link " href ="#UTF-32 "> < span class ="toc-number "> 4.3.</ span > < span class ="toc-text "> UTF-32</ span > </ a > </ li > </ ol > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#UTF-%E5%90%84%E4%B8%AA%E7%BC%96%E7%A0%81%E6%96%B9%E6%A1%88%E7%9A%84%E5%AF%B9%E6%AF%94 "> < span class ="toc-number "> 5.</ span > < span class ="toc-text "> UTF 各个编码方案的对比</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#%E5%AD%97%E8%8A%82%E5%BA%8F "> < span class ="toc-number "> 6.</ span > < span class ="toc-text "> 字节序</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#%E6%B3%A8%E6%84%8F%E4%BA%8B%E9%A1%B9 "> < span class ="toc-number "> 7.</ span > < span class ="toc-text "> 注意事项</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#%E6%80%BB%E7%BB%93 "> < span class ="toc-number "> 8.</ span > < span class ="toc-text "> 总结</ span > </ a > </ li > < li class ="toc-item toc-level-2 "> < a class ="toc-link " href ="#%E5%8F%82%E8%80%83 "> < span class ="toc-number "> 9.</ span > < span class ="toc-text "> 参考</ span > </ a > </ li > </ ol > </ div > </ div > < div class ="author-info hide "> < div class ="author-info__avatar text-center "> < img src ="/images/avatar.jpg "> </ div > < div class ="author-info__name text-center "> 布多</ div > < div class ="author-info__description text-center "> 前进！前进！！不择手段地前进！！！</ div > < div class ="follow-button "> < a target ="_blank " rel ="noopener " href ="https://github.com/internetwei "> Follow Me</ a > </ div > < hr > < div class ="author-info-articles "> < a class ="author-info-articles__archives article-meta " href ="/archives "> < span class ="pull-left "> 文章</ span > < span class ="pull-right "> 20</ span > </ a > < a class ="author-info-articles__tags article-meta " href ="/tags "> < span class ="pull-left "> 标签</ span > < span class ="pull-right "> 14</ span > </ a > < a class ="author-info-articles__categories article-meta " href ="/categories "> < span class ="pull-left "> 分类</ span > < span class ="pull-right "> 4</ span > </ a > </ div > < hr > < div class ="author-info-links "> < div class ="author-info-links__title text-center "> 友链</ div > < a class ="author-info-links__name text-center " target ="_blank " rel ="noopener " href ="https://www.coderqi.com/ "> 齐小胖之家</ a > </ div > </ div > </ div > < div id ="content-outer "> < div id ="top-container " style ="background-image: url(/images/backgroundImage.jpg) "> < div id ="page-header "> < span class ="pull-left "> < a id ="site-name " href ="/ "> 布多的博客</ a > </ span > < i class ="fa fa-bars toggle-menu pull-right " aria-hidden ="true "> </ i > < span class ="pull-right menus "> < a class ="site-page " href ="/ "> 首页</ a > < a class ="site-page " href ="/tags "> 标签</ a > < a class ="site-page " href ="/categories "> 分类</ a > < a class ="site-page " href ="/archives "> 归档</ a > < a class ="site-page " href ="/about "> 关于</ a > </ span > < span class ="pull-right "> < a class ="site-page social-icon search "> < i class ="fa fa-search "> </ i > < span > 搜索</ span > </ a > </ span > </ div > < div id ="post-info "> < div id ="post-title "> 字符编码的秘密：Unicode 和 UTF 到底是什么？</ div > < div id ="post-meta "> < time class ="post-meta__date "> < i class ="fa fa-calendar " aria-hidden ="true "> </ i > 2025-05-21</ time > < span class ="post-meta__separator "> |</ span > < i class ="fa fa-inbox post-meta__icon " aria-hidden ="true "> </ i > < a class ="post-meta__categories " href ="/categories/%E8%AE%A1%E7%AE%97%E6%9C%BA%E5%9F%BA%E7%A1%80/ "> 计算机基础</ a > < div class ="post-meta-wordcount "> < span > 字数总计: </ span > < span class ="word-count "> 6.1k</ span > < span class ="post-meta__separator "> |</ span > < span > 阅读时长: 19 分钟</ span > </ div > </ div > </ div > </ div > < div class ="layout " id ="content-inner "> < article id ="post "> < div class ="article-container " id ="post-content "> < blockquote >
19+ < p > 由 布多(budo) 发布于 2025-05-21，更新于 2025-12-19 </ p >
2020</ blockquote >
2121< h2 id ="字符编码的起源 "> < a href ="#字符编码的起源 " class ="headerlink " title ="字符编码的起源 "> </ a > 字符编码的起源</ h2 > < p > 在计算机的世界里，所有信息最终都被转换成二进制数据存储。每个二进制位（bit）只有 0 和 1 两种状态，8 个二进制位组成一个字节（byte），可以表示 256 种不同的状态（2^8 = 256）。如果用一个状态对应一个字符，那么一个字节就能表示 256 个不同的字符，范围从 < code > 0x00</ code > 到 < code > 0xFF</ code > 。</ p >
2222< p > 20 世纪 60 年代，美国制定了 < a target ="_blank " rel ="noopener " href ="https://en.wikipedia.org/wiki/ASCII "> ASCII</ a > 编码标准，将英文字符与二进制数据一一对应。ASCII 编码定义了 128 个字符，包括英文字母、数字、标点符号等。例如，字母 A 对应的二进制值是 < code > 0x41</ code > 。注意：ASCII 只使用了字节中的低 7 位，最高位固定为 0。</ p >
@@ -94,22 +94,55 @@ <h3 id="UTF-8"><a href="#UTF-8" class="headerlink" title="UTF-8"></a>UTF-8</h3><
9494</ li >
9595</ ol >
9696< p > 举例说明：</ p >
97+ < ol >
98+ < li > 字符 < strong > A</ strong > < br > 它的 Unicode 码点是 < strong > U+0041</ strong > ，只需 1 个字节即可存储。根据 UTF-8 单字节编码规则，首位为 0，后面 7 位表示字符编码，因此内存布局为 < strong > 0100 0001</ strong > 。首位 0 表示单字节（往后读取 1 个字节长度），后面 < strong > 0100 0001</ strong > （对应十六进制 < strong > 0x41</ strong > ）就是字符 ‘A’ 在 Unicode 中的码点。</ li >
99+ </ ol >
97100< ul >
98- < li > ASCII 字符 ‘A’( U+0041)：单字节 < code > 0x41 </ code > → < code > 0100 0001 </ code > ； </ li >
99- < li > 汉字 “严”(U+4E25)：三字节 < code > 0xE4B8A5 </ code > → < code > 1110 0100, 1011 1000, 1010 0101 </ code > ； </ li >
100- < li > emoji “🍑”(U+1F351)：四字节 < code > 0xF09F8D91 </ code > → < code > 1111 0000, 1001 1111, 1000 1101, 1001 0001 </ code > ； </ li >
101+ < li > Unicode 码点： < strong > U+0041</ strong > (十六进制) </ li >
102+ < li > UTF-8 编码： < strong > 0x41 </ strong > (1 字节) == < strong > 0100 0001 </ strong > (二进制) </ li >
103+ < li > 解析过程：首位为 < strong > 0 </ strong > ，表示这是单字节编码；后 7 位 < strong > 100 0001 </ strong > 直接存储 Unicode 码点，转换为十六进制即为 < strong > 0x41 </ strong > ，与 Unicode 码点一致。 </ li >
101104</ ul >
102- < h3 id =" UTF-16 " > < a href =" #UTF-16 " class =" headerlink " title =" UTF-16 " > </ a > UTF-16 </ h3 > < p > UTF-16 是另一种常见的 Unicode 编码方案，它采用了一种巧妙的变长编码设计：对于基本多文种平面（BMP）的字符使用 2 字节存储，而对于辅助平面的字符则使用 4 字节存储。这种设计既保证了编码效率，又解决了字符表示的问题。让我们详细了解一下它的工作原理： </ p >
103- < p > < strong > 基本多文种平面（BMP）字符的编码规则： </ strong > </ p >
104- < p > 对于 BMP 范围内的字符（码点范围：0x0000 到 0xFFFF），UTF-16 采用直接存储的方式，将 Unicode 码点转换为 2 字节的二进制数据。例如： </ p >
105+ < ol start =" 2 " >
106+ < li > 汉字 < strong > 严 </ strong > </ li >
107+ </ ol >
105108< ul >
106- < li > ASCII 字符 ‘A’(U+0041)：存储为 < code > 0x0041</ code > </ li >
107- < li > 汉字 “严”(U+4E25)：存储为 < code > 0x4E25</ code > </ li >
109+ < li > Unicode 码点：< strong > U+4E25</ strong > (十六进制)</ li >
110+ < li > UTF-8 编码：< strong > 0xE4B8A5</ strong > (十六进制) == < strong > 1110 0100, 1011 1000, 1010 0101</ strong > (二进制)</ li >
111+ < li > 解析过程：< ul >
112+ < li > 首字节以 < strong > 1110</ strong > 开头（连续 3 个 1），表示这是 3 字节编码</ li >
113+ < li > 后续每个字节均以 < strong > 10</ strong > 开头</ li >
114+ < li > 提取有效位：去除首字节的 < strong > 1110</ strong > 和后续字节的 < strong > 10</ strong > 前缀</ li >
115+ < li > 有效位组合：< strong > 0100, 11 1000, 10 0101</ strong > => < strong > 0100 1110 0010 0101</ strong > </ li >
116+ < li > 转换为十六进制：< strong > 0x4E25</ strong > ，与 Unicode 码点一致</ li >
108117</ ul >
118+ </ li >
119+ </ ul >
120+ < ol start ="3 ">
121+ < li > 表情符号 < strong > 🍑</ strong > </ li >
122+ </ ol >
123+ < ul >
124+ < li > Unicode 码点：< strong > U+1F351</ strong > (十六进制)</ li >
125+ < li > UTF-8 编码：< strong > 0xF09F8D91</ strong > (4 字节) == < strong > 1111 0000, 1001 1111, 1000 1101, 1001 0001</ strong > (二进制)</ li >
126+ < li > 解析过程：< ul >
127+ < li > 首字节以 < strong > 1111</ strong > 开头（连续 4 个 1），表示这是 4 字节编码</ li >
128+ < li > 后续每个字节均以 < strong > 10</ strong > 开头</ li >
129+ < li > 提取有效位：去除首字节的 < strong > 1111</ strong > 和后续字节的 < strong > 10</ strong > 前缀</ li >
130+ < li > 有效位组合：< strong > 000, 01 1111, 00 1101, 01 0001</ strong > => < strong > 0001 1111 0011 0101 0001</ strong > </ li >
131+ < li > 转换为十六进制：< strong > 0x1F351</ strong > ，与 Unicode 码点一致。</ li >
132+ </ ul >
133+ </ li >
134+ </ ul >
135+ < h3 id ="UTF-16 "> < a href ="#UTF-16 " class ="headerlink " title ="UTF-16 "> </ a > UTF-16</ h3 > < p > UTF-16 是另一种常见的 Unicode 编码方案，它采用了一种巧妙的变长编码设计：对于基本多文种平面（BMP）的字符使用 2 字节存储，而对于辅助平面的字符则使用 4 字节存储。这种设计既保证了编码效率，又解决了字符表示的问题。让我们详细了解一下它的工作原理：</ p >
136+ < p > < strong > 基本多文种平面（BMP）字符的编码规则：</ strong > </ p >
137+ < p > 对于 BMP 范围内的字符（码点范围：0x0000 到 0xFFFF），UTF-16 采用直接存储的方式，将 Unicode 码点转换为 2 字节的二进制数据。</ p >
138+ < p > 举例说明：</ p >
139+ < ol >
140+ < li > 字符 < strong > A</ strong > < br > 它的 Unicode 码点是 < strong > U+0041</ strong > ，直接将 < strong > 0x41</ strong > 保存到内存中。</ li >
141+ </ ol >
109142< p > < strong > 辅助平面字符的编码规则：</ strong > </ p >
110143< p > 对于辅助平面的字符（码点范围：0x10000 到 0x10FFFF），UTF-16 采用了一种称为代理对（Surrogate Pair）的编码机制。这种机制的设计非常巧妙：</ p >
111144< ol >
112- < li > < p > 首先，UTF-16 在 BMP 中预留了一个特殊的区域（U+D800 到 U+DFFF），这个区域被称为代理区 ，专门用于代理对编码。</ p >
145+ < li > < p > 首先，UTF-16 在 BMP 中预留了一个特殊的区域（U+D800 到 U+DFFF），这个区域不存储任何字符，它被称为代理区 ，专门用于代理对编码。</ p >
113146</ li >
114147< li > < p > 代理对编码的具体步骤：</ p >
115148< ul >
@@ -121,13 +154,46 @@ <h3 id="UTF-16"><a href="#UTF-16" class="headerlink" title="UTF-16"></a>UTF-16</
121154</ ul >
122155</ li >
123156</ ol >
124- < p > 以 < code > 🍑 </ code > (U+1F351) 为例 ：</ p >
157+ < p > 举例说明 ：</ p >
125158< ol >
126- < li > 0x1F351 - 0x10000 = 0xF351(0b1111 0011 0101 0001)；</ li >
127- < li > 高 10 位：0x3C(0b00 0011 1100) + 0xD800 = 0xD83C；</ li >
128- < li > 低 10 位：0x351(0b0011 0101 0001) + 0xDC00 = 0xDF51；</ li >
129- < li > 最终编码：0xD83CDF51；</ li >
159+ < li > 表情符号 < strong > 🍑</ strong > </ li >
130160</ ol >
161+ < ul >
162+ < li > Unicode 码点：< strong > U+1F351</ strong > </ li >
163+ < li > 步骤一：计算偏移量< ul >
164+ < li > < strong > 0x1F351</ strong > - < strong > 0x10000</ strong > = < strong > 0xF351</ strong > （二进制：< code > 0b1111 0011 0101 0001</ code > ）</ li >
165+ </ ul >
166+ </ li >
167+ < li > 步骤二：分割为低 10 位和高 10 位< ul >
168+ < li > 低 10 位：< code > 0b11 0101 0001</ code > = < strong > 0x351</ strong > </ li >
169+ < li > 高 10 位：< code > 0b00 0011 1100</ code > = < strong > 0x3C</ strong > </ li >
170+ </ ul >
171+ </ li >
172+ < li > 步骤三：计算代理对< ul >
173+ < li > 低代理 = < strong > 0x351</ strong > + < strong > 0xDC00</ strong > = < strong > 0xDF51</ strong > </ li >
174+ < li > 高代理 = < strong > 0x3C</ strong > + < strong > 0xD800</ strong > = < strong > 0xD83C</ strong > </ li >
175+ </ ul >
176+ </ li >
177+ < li > 最终 UTF-16 编码：< strong > 0xD83CDF51</ strong > （4 字节）</ li >
178+ </ ul >
179+ < p > UTF-16 如何判断一个字符是 BMP 字符还是辅助平面字符呢？解析器采用”前瞻判断”的方式：</ p >
180+ < ol >
181+ < li > 读取前 2 字节（高代理部分），检查其值是否在代理区范围内（< strong > 0xD800</ strong > ~ < strong > 0xDFFF</ strong > ）</ li >
182+ < li > 如果在代理区内，则：< ul >
183+ < li > 继续读取后 2 字节（低代理部分）</ li >
184+ < li > 将高代理和低代理组合，按照代理对规则解码为辅助平面字符</ li >
185+ </ ul >
186+ </ li >
187+ < li > 如果不在代理区内，则：< ul >
188+ < li > 直接将该 2 字节值作为 BMP 字符的码点</ li >
189+ </ ul >
190+ </ li >
191+ </ ol >
192+ < p > 举例：</ p >
193+ < ul >
194+ < li > 遇到 < strong > 0xD83C</ strong > ：在代理区范围内（< strong > 0xD800</ strong > ~ < strong > 0xDBFF</ strong > 为高代理区），继续读取 < strong > 0xDF51</ strong > ，组合解码得到 < strong > U+1F351</ strong > （🍑）</ li >
195+ < li > 遇到 < strong > 0x0041</ strong > ：不在代理区范围内，直接解析为 < strong > U+0041</ strong > （A）</ li >
196+ </ ul >
131197< blockquote >
132198< p > 注：UTF-16 编码需要考虑字节序问题，这里使用 Big endian 表示。关于字节序的详细说明，请参考后文的 < a href ="#%E5%AD%97%E8%8A%82%E5%BA%8F "> 字节序</ a > 小节。</ p >
133199</ blockquote >
0 commit comments