399 lines
462 KiB
HTML
399 lines
462 KiB
HTML
|
<!DOCTYPE html>
|
|||
|
|
<html lang="zh"><head><title>正则表达式</title><meta charset="utf-8"/><link rel="preconnect" href="https://fonts.googleapis.com"/><link rel="preconnect" href="https://fonts.gstatic.com"/><link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=IBM Plex Mono&family=Noto Serif Simplified Chinese:wght@400;700&family=Source Sans Pro:ital,wght@0,400;0,600;1,400;1,600&display=swap"/><meta name="viewport" content="width=device-width, initial-scale=1.0"/><meta property="og:title" content="正则表达式"/><meta property="og:description" content="正则表达式基础入门."/><meta property="og:image" content="https://wiki.7wate.com/static/og-image.png"/><meta property="og:width" content="1200"/><meta property="og:height" content="675"/><link rel="icon" href="../../../static/icon.png"/><meta name="description" content="正则表达式基础入门."/><meta name="generator" content="Quartz"/><link href="../../../index.css" rel="stylesheet" type="text/css" spa-preserve/><link href="https://cdnjs.cloudflare.com/ajax/libs/KaTeX/0.16.9/katex.min.css" rel="stylesheet" type="text/css" spa-preserve/><script src="../../../prescript.js" type="application/javascript" spa-preserve></script><script type="application/javascript" spa-preserve>const fetchData = fetch("../../../static/contentIndex.json").then(data => data.json())</script></head><body data-slug="Technology/GettingStarted/文本处理/正则表达式"><div id="quartz-root" class="page"><div id="quartz-body"><div class="left sidebar"><h2 class="page-title"><a href="../../..">🪴 X·Eden</a></h2><div class="spacer mobile-only"></div><div class="search"><button class="search-button" id="search-button"><p>搜索</p><svg role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 19.9 19.7"><title>Search</title><g class="search-path" fill="none"><path stroke-linecap="square" d="M18.5 18.3l-5.4-5.4"></path><circle cx="8" cy="8" r="7"></circle></g></svg></button><div id="search-container"><div id="search-space"><input autocomplete="off" id="search-bar" name="search" type="text" aria-label="搜索些什么" placeholder="搜索些什么"/><div id="search-layout" data-preview="true"></div></div></div></div><button class="darkmode" id="darkmode"><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" id="dayIcon" x="0px" y="0px" viewBox="0 0 35 35" style="enable-background:new 0 0 35 35" xml:space="preserve" aria-label="暗色模式"><title>暗色模式</title><path d="M6,17.5C6,16.672,5.328,16,4.5,16h-3C0.672,16,0,16.672,0,17.5 S0.672,19,1.5,19h3C5.328,19,6,18.328,6,17.5z M7.5,26c-0.414,0-0.789,0.168-1.061,0.439l-2,2C4.168,28.711,4,29.086,4,29.5 C4,30.328,4.671,31,5.5,31c0.414,0,0.789-0.168,1.06-0.44l2-2C8.832,28.289,9,27.914,9,27.5C9,26.672,8.329,26,7.5,26z M17.5,6 C18.329,6,19,5.328,19,4.5v-3C19,0.672,18.329,0,17.5,0S16,0.672,16,1.5v3C16,5.328,16.671,6,17.5,6z M27.5,9 c0.414,0,0.789-0.168,1.06-0.439l2-2C30.832,6.289,31,5.914,31,5.5C31,4.672,30.329,4,29.5,4c-0.414,0-0.789,0.168-1.061,0.44 l-2,2C26.168,6.711,26,7.086,26,7.5C26,8.328,26.671,9,27.5,9z M6.439,8.561C6.711,8.832,7.086,9,7.5,9C8.328,9,9,8.328,9,7.5 c0-0.414-0.168-0.789-0.439-1.061l-2-2C6.289,4.168,5.914,4,5.5,4C4.672,4,4,4.672,4,5.5c0,0.414,0.168,0.789,0.439,1.06 L6.439,8.561z M33.5,16h-3c-0.828,0-1.5,0.672-1.5,1.5s0.672,1.5,1.5,1.5h3c0.828,0,1.5-0.672,1.5-1.5S34.328,16,33.5,16z M28.561,26.439C28.289,26.168,27.914,26,27.5,26c-0.828,0-1.5,0.672-1.5,1.5c0,0.414,0.168,0.789,0.439,1.06l2,2 C28.711,30.832,29.086,31,29.5,31c0.828,0,1.5-0.672,1.5-1.5c0-0.414-0.168-0.789-0.439-1.061L28.561,26.439z M17.5,29 c-0.829,0-1.5,0.672-1.5,1.5v3c0,0.828,0.671,1.5,1.5,1.5s1.5-0.672,1.5-1.5v-3C19,29.672,18.329,29,17.5,29z M17.5,7 C11.71,7,7,11.71,7,17.5S11.71,28,17.5,28S28,23.29,28,17.5S23.29,7,17.5,7z M17.5,25c-4.136,0-7.5-3.364-7.5-7.5 c0-4.136,3.364-7.5,7.5-7.5c4.136,0,7.5,3.364,7.5,7.5C25,21.636,21.636,25,17.5,25z"></path></svg><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" id="nightIcon"
|
|||
|
|
<p>正则表达式（Regular Expression，Regex）是用于匹配字符串中字符组合的模式。它由一系列字符和特殊符号组成，可以高效地执行查找、替换、检查数据格式等多种文本处理任务。正则表达式的概念最初由数学家斯蒂芬·克莱尼在 20 世纪 50 年代提出，最早用于理论计算机科学和形式语言理论中。</p>
|
|||
|
|
<p>几乎所有现代编程语言都支持正则表达式，包括 Python、JavaScript、Java、C#等。此外，许多文本编辑器和开发环境（如 VSCode、Sublime Text）以及命令行工具（如 grep）也广泛应用正则表达式进行文本搜索和编辑。</p>
|
|||
|
|
<h2 id="基本概念">基本概念<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#基本概念" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h2>
|
|||
|
|
<ul>
|
|||
|
|
<li><strong>字面字符</strong>：指在表达式中表示它们自身字面意义的字符，例如 <code>a</code>、<code>1</code>、<code>B</code>。</li>
|
|||
|
|
<li><strong>特殊字符</strong>：在正则表达式中用来表示控制或通配符作用的字符，如 <code>*</code>（匹配前一个字符 0 次或多次）。</li>
|
|||
|
|
</ul>
|
|||
|
|
<h3 id="元字符">元字符<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#元字符" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h3>
|
|||
|
|
<p>元字符是构成正则表达式逻辑的基础，具有特殊的匹配含义：</p>
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
<div class="table-container"><table><thead><tr><th>元字符</th><th>描述</th></tr></thead><tbody><tr><td><code>.</code></td><td>句号匹配任意单个字符除了换行符。</td></tr><tr><td><code>[ ]</code></td><td>字符种类。匹配方括号内的任意字符。</td></tr><tr><td><code>[^ ]</code></td><td>否定的字符种类。匹配除了方括号里的任意字符</td></tr><tr><td><code>*</code></td><td>匹配 >=0 个重复的在 * 号之前的字符。</td></tr><tr><td><code>+</code></td><td>匹配 >=1 个重复的 + 号前的字符。</td></tr><tr><td><code>?</code></td><td>标记 ? 之前的字符为可选。</td></tr><tr><td><code>{n,m}</code></td><td>匹配 num 个大括号之前的字符或字符集 (n <span>⇐</span> num <span>⇐</span> m)。</td></tr><tr><td><code>(xyz)</code></td><td>字符集，匹配与 xyz 完全相等的字符串。</td></tr><tr><td>`</td><td>`</td></tr><tr><td><code>\</code></td><td>转义字符，用于匹配一些保留的字符 `[ ] ( ) { } . * + ? ^ $ \</td></tr><tr><td><code>^</code></td><td>从开始行开始匹配。</td></tr><tr><td><code>$</code></td><td>从末端开始匹配。</td></tr></tbody></table></div>
|
|||
|
|
<h3 id="字符类">字符类<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#字符类" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h3>
|
|||
|
|
<p>字符类允许匹配指定集合中的字符，常见的标准字符类和自定义字符类如下：</p>
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
<div class="table-container"><table><thead><tr><th>简写</th><th>描述</th></tr></thead><tbody><tr><td><code>.</code></td><td>除换行符外的所有字符</td></tr><tr><td><code>\w</code></td><td>匹配所有字母数字，等同于 <code>[a-zA-Z0-9_]</code></td></tr><tr><td><code>\W</code></td><td>匹配所有非字母数字，即符号，等同于： <code>[^\w]</code></td></tr><tr><td><code>\d</code></td><td>匹配数字： <code>[0-9]</code></td></tr><tr><td><code>\D</code></td><td>匹配非数字： <code>[^\d]</code></td></tr><tr><td><code>\s</code></td><td>匹配所有空格字符，等同于： <code>[\t\n\f\r\p{Z}]</code></td></tr><tr><td><code>\S</code></td><td>匹配所有非空格字符： <code>[^\s]</code></td></tr><tr><td><code>\f</code></td><td>匹配一个换页符</td></tr><tr><td><code>\n</code></td><td>匹配一个换行符</td></tr><tr><td><code>\r</code></td><td>匹配一个回车符</td></tr><tr><td><code>\t</code></td><td>匹配一个制表符</td></tr><tr><td><code>\v</code></td><td>匹配一个垂直制表符</td></tr><tr><td><code>\p</code></td><td>匹配 CR/LF（等同于 <code>\r\n</code>），用来匹配 DOS 行终止符</td></tr></tbody></table></div>
|
|||
|
|
<p><strong>自定义字符类</strong></p>
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
<div class="table-container"><table><thead><tr><th>示例</th><th>描述</th></tr></thead><tbody><tr><td><code>[a-z]</code></td><td>匹配任何小写字母</td></tr><tr><td><code>[A-Z]</code></td><td>匹配任何大写字母</td></tr><tr><td><code>[0-9]</code></td><td>匹配任何数字</td></tr><tr><td><code>[aeiou]</code></td><td>匹配所有小写元音字母</td></tr><tr><td><code>[^0-9]</code></td><td>匹配任何不是数字的字符（方括号内的 <code>^</code> 表示非）</td></tr></tbody></table></div>
|
|||
|
|
<h3 id="位置匹配">位置匹配<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#位置匹配" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h3>
|
|||
|
|
<p>位置匹配用于确定字符匹配的具体位置，如行首或行尾等：</p>
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
<div class="table-container"><table><thead><tr><th>锚点字符</th><th>描述</th></tr></thead><tbody><tr><td><code>^</code></td><td>不仅表示行的开始，也可在多行模式中匹配每一行的开始</td></tr><tr><td><code>$</code></td><td>表示行的结束或字符串的结束，同样在多行模式中可匹配每一行的结束</td></tr></tbody></table></div>
|
|||
|
|
<h2 id="量词和分组">量词和分组<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#量词和分组" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h2>
|
|||
|
|
<p>量词和分组是正则表达式中非常强大的功能，它们让我们可以定义复杂的模式，进行精确的文本匹配和操作。这部分内容也可以用表格形式进行更清晰的展示。</p>
|
|||
|
|
<h3 id="量词">量词<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#量词" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h3>
|
|||
|
|
<p>量词用于指定一个元素出现的次数，是正则表达式中控制匹配频度的关键工具。</p>
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
<div class="table-container"><table><thead><tr><th>量词</th><th>描述</th></tr></thead><tbody><tr><td><code>*</code></td><td>匹配前一个元素 0 次或多次。</td></tr><tr><td><code>+</code></td><td>匹配前一个元素 1 次或多次。</td></tr><tr><td><code>?</code></td><td>匹配前一个元素 0 次或 1 次。</td></tr><tr><td><code>{n}</code></td><td>匹配前一个元素恰好 n 次。</td></tr><tr><td><code>{n,}</code></td><td>匹配前一个元素至少 n 次。</td></tr><tr><td><code>{n,m}</code></td><td>匹配前一个元素至少 n 次，但不超过 m 次。</td></tr></tbody></table></div>
|
|||
|
|
<h4 id="贪婪与非贪婪量词">贪婪与非贪婪量词<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#贪婪与非贪婪量词" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h4>
|
|||
|
|
<p>量词默认为贪婪模式，尽可能多地匹配字符。通过添加 <code>?</code> 后缀，量词变为非贪婪模式，尽可能少地匹配字符。</p>
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
<div class="table-container"><table><thead><tr><th>类型</th><th>示例</th><th>描述</th></tr></thead><tbody><tr><td>贪婪匹配</td><td><code>a.*b</code></td><td>在 <code>axxxbxxxb</code> 中匹配从第一个 <code>a</code> 到最后一个 <code>b</code> 的整段文本。</td></tr><tr><td>非贪婪匹配</td><td><code>a.*?b</code></td><td>在 <code>axxxbxxxb</code> 中匹配最短的，以 <code>a</code> 开始，以 <code>b</code> 结束的文本。</td></tr></tbody></table></div>
|
|||
|
|
<h3 id="分组和引用">分组和引用<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#分组和引用" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h3>
|
|||
|
|
<p>分组允许将正则表达式中的部分模式括起来，作为一个整体进行操作，这对于提取信息、构建复杂模式或进行条件匹配非常有用。</p>
|
|||
|
|
<h4 id="捕获分组与非捕获分组">捕获分组与非捕获分组<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#捕获分组与非捕获分组" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h4>
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
<div class="table-container"><table><thead><tr><th>类型</th><th>示例</th><th>描述</th></tr></thead><tbody><tr><td>捕获分组</td><td><code>(abc)</code></td><td>匹配 <code>abc</code>，并捕获匹配的文本，以供后续引用。</td></tr><tr><td>非捕获分组</td><td><code>(?:abc)</code></td><td>匹配 <code>abc</code>，但不捕获匹配的文本，仅用于匹配操作。</td></tr></tbody></table></div>
|
|||
|
|
<h4 id="后向引用">后向引用<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#后向引用" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h4>
|
|||
|
|
<p>后向引用让我们能够引用正则表达式中先前定义的捕获组，这对于匹配重复的文本或验证两部分内容相同非常有用。</p>
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
<div class="table-container"><table><thead><tr><th>示例</th><th>描述</th></tr></thead><tbody><tr><td><code>(\b\w+)\s+\1</code></td><td>匹配一个由单词、空格和相同单词构成的模式，如 <code>word word</code>。</td></tr></tbody></table></div>
|
|||
|
|
<h2 id="高级匹配">高级匹配<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#高级匹配" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h2>
|
|||
|
|
<h3 id="断言">断言<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#断言" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h3>
|
|||
|
|
<p>断言是正则表达式中的一个高级特性，允许进行条件匹配，即只有在满足特定条件的情况下才进行匹配。</p>
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
<div class="table-container"><table><thead><tr><th>符号</th><th>描述</th></tr></thead><tbody><tr><td><code>?=</code></td><td>正先行断言 - 存在</td></tr><tr><td><code>?!</code></td><td>负先行断言 - 排除</td></tr><tr><td><code>?<=</code></td><td>正后发断言 - 存在</td></tr><tr><td><code>?<!</code></td><td>负后发断言 - 排除</td></tr></tbody></table></div>
|
|||
|
|
<p><strong>前向肯定断言</strong> (<code>?=</code>)</p>
|
|||
|
|
<ul>
|
|||
|
|
<li>前向肯定断言允许你指定一个子模式必须出现在某个匹配之后，但不会成为匹配结果的一部分。例如，<code>a(?=b)</code> 会匹配前面有 <code>a</code> 且后面紧跟 <code>b</code> 的位置，但不会返回 <code>b</code>。</li>
|
|||
|
|
</ul>
|
|||
|
|
<p><strong>前向否定断言</strong> (<code>?!</code>)</p>
|
|||
|
|
<ul>
|
|||
|
|
<li>前向否定断言用来指定一个子模式必须不出现在某个匹配之后。例如，<code>a(?!b)</code> 会匹配所有后面不跟 <code>b</code> 的 <code>a</code>。</li>
|
|||
|
|
</ul>
|
|||
|
|
<p><strong>后向断言</strong></p>
|
|||
|
|
<ul>
|
|||
|
|
<li>在支持的语言中（如 JavaScript），后向断言允许你指定一个子模式必须出现在某个匹配之前。如 <code>(?<=b)a</code> 表示 <code>a</code> 前面必须有 <code>b</code>。</li>
|
|||
|
|
</ul>
|
|||
|
|
<h3 id="标志模式修饰符">标志/模式修饰符<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#标志模式修饰符" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h3>
|
|||
|
|
<p>标志或模式修饰符用于改变正则表达式的匹配行为。</p>
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
<div class="table-container"><table><thead><tr><th>标志</th><th>描述</th></tr></thead><tbody><tr><td><code>i</code></td><td>忽略大小写。</td></tr><tr><td><code>g</code></td><td>全局搜索。</td></tr><tr><td><code>m</code></td><td>多行修饰符：锚点元字符 <code>^</code> <code>$</code> 工作范围在每行的起始。</td></tr></tbody></table></div>
|
|||
|
|
<p><strong>大小写不敏感</strong> (<code>i</code>)</p>
|
|||
|
|
<ul>
|
|||
|
|
<li>使用此标志后，匹配时将不区分大小写。例如，正则表达式 <code>/abc/i</code> 将匹配 <code>Abc</code>、<code>aBc</code>、<code>abc</code> 等。</li>
|
|||
|
|
</ul>
|
|||
|
|
<p><strong>多行模式</strong> (<code>m</code>)</p>
|
|||
|
|
<ul>
|
|||
|
|
<li>在多行模式下，<code>^</code> 和 <code>$</code> 不仅匹配输入字符串的开始和结束位置，也匹配行的开始和结束。</li>
|
|||
|
|
</ul>
|
|||
|
|
<p><strong>点号包含换行</strong> (<code>s</code>)</p>
|
|||
|
|
<ul>
|
|||
|
|
<li>通常，<code>.</code> 不匹配换行符。使用此标志后，<code>.</code> 也将匹配换行符。</li>
|
|||
|
|
</ul>
|
|||
|
|
<h2 id="参考实例">参考实例<a role="anchor" aria-hidden="true" tabindex="-1" data-no-popover="true" href="#参考实例" class="internal"><svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></a></h2>
|
|||
|
|
<ul>
|
|||
|
|
<li><a href="https://regex101.com/" class="external">regex101（正则表达式测试工具）<svg aria-hidden="true" class="external-icon" viewBox="0 0 512 512"><path d="M320 0H288V64h32 82.7L201.4 265.4 178.7 288 224 333.3l22.6-22.6L448 109.3V192v32h64V192 32 0H480 320zM32 32H0V64 480v32H32 456h32V480 352 320H424v32 96H64V96h96 32V32H160 32z"></path></svg></a></li>
|
|||
|
|
<li><a href="https://regexr.com/" class="external">REGEXP（正则表达式测试工具）<svg aria-hidden="true" class="external-icon" viewBox="0 0 512 512"><path d="M320 0H288V64h32 82.7L201.4 265.4 178.7 288 224 333.3l22.6-22.6L448 109.3V192v32h64V192 32 0H480 320zM32 32H0V64 480v32H32 456h32V480 352 320H424v32 96H64V96h96 32V32H160 32z"></path></svg></a></li>
|
|||
|
|
<li><a href="https://jex.im/regulex" class="external">Regulex（正则表达式可视化工具）<svg aria-hidden="true" class="external-icon" viewBox="0 0 512 512"><path d="M320 0H288V64h32 82.7L201.4 265.4 178.7 288 224 333.3l22.6-22.6L448 109.3V192v32h64V192 32 0H480 320zM32 32H0V64 480v32H32 456h32V480 352 320H424v32 96H64V96h96 32V32H160 32z"></path></svg></a></li>
|
|||
|
|
<li><a href="https://github.com/any86/any-rule" class="external">any-rule（正则表达式大全）<svg aria-hidden="true" class="external-icon" viewBox="0 0 512 512"><path d="M320 0H288V64h32 82.7L201.4 265.4 178.7 288 224 333.3l22.6-22.6L448 109.3V192v32h64V192 32 0H480 320zM32 32H0V64 480v32H32 456h32V480 352 320H424v32 96H64V96h96 32V32H160 32z"></path></svg></a></li>
|
|||
|
|
<li><a href="https://github.com/ziishaned/learn-regex" class="external">learn-regex<svg aria-hidden="true" class="external-icon" viewBox="0 0 512 512"><path d="M320 0H288V64h32 82.7L201.4 265.4 178.7 288 224 333.3l22.6-22.6L448 109.3V192v32h64V192 32 0H480 320zM32 32H0V64 480v32H32 456h32V480 352 320H424v32 96H64V96h96 32V32H160 32z"></path></svg></a></li>
|
|||
|
|
</ul></article><hr/><div class="page-footer"></div></div><div class="right sidebar"><div class="graph"><h3>关系图谱</h3><div class="graph-outer"><div id="graph-container" data-cfg="{"drag":true,"zoom":true,"depth":1,"scale":1.1,"repelForce":0.5,"centerForce":0.3,"linkDistance":30,"fontSize":0.6,"opacityScale":1,"showTags":true,"removeTags":[],"focusOnHover":false}"></div><button id="global-graph-icon" aria-label="Global Graph"><svg version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px" viewBox="0 0 55 55" fill="currentColor" xml:space="preserve"><path d="M49,0c-3.309,0-6,2.691-6,6c0,1.035,0.263,2.009,0.726,2.86l-9.829,9.829C32.542,17.634,30.846,17,29,17
|
|||
|
|
s-3.542,0.634-4.898,1.688l-7.669-7.669C16.785,10.424,17,9.74,17,9c0-2.206-1.794-4-4-4S9,6.794,9,9s1.794,4,4,4
|
|||
|
|
c0.74,0,1.424-0.215,2.019-0.567l7.669,7.669C21.634,21.458,21,23.154,21,25s0.634,3.542,1.688,4.897L10.024,42.562
|
|||
|
|
C8.958,41.595,7.549,41,6,41c-3.309,0-6,2.691-6,6s2.691,6,6,6s6-2.691,6-6c0-1.035-0.263-2.009-0.726-2.86l12.829-12.829
|
|||
|
|
c1.106,0.86,2.44,1.436,3.898,1.619v10.16c-2.833,0.478-5,2.942-5,5.91c0,3.309,2.691,6,6,6s6-2.691,6-6c0-2.967-2.167-5.431-5-5.91
|
|||
|
|
v-10.16c1.458-0.183,2.792-0.759,3.898-1.619l7.669,7.669C41.215,39.576,41,40.26,41,41c0,2.206,1.794,4,4,4s4-1.794,4-4
|
|||
|
|
s-1.794-4-4-4c-0.74,0-1.424,0.215-2.019,0.567l-7.669-7.669C36.366,28.542,37,26.846,37,25s-0.634-3.542-1.688-4.897l9.665-9.665
|
|||
|
|
C46.042,11.405,47.451,12,49,12c3.309,0,6-2.691,6-6S52.309,0,49,0z M11,9c0-1.103,0.897-2,2-2s2,0.897,2,2s-0.897,2-2,2
|
|||
|
|
S11,10.103,11,9z M6,51c-2.206,0-4-1.794-4-4s1.794-4,4-4s4,1.794,4,4S8.206,51,6,51z M33,49c0,2.206-1.794,4-4,4s-4-1.794-4-4
|
|||
|
|
s1.794-4,4-4S33,46.794,33,49z M29,31c-3.309,0-6-2.691-6-6s2.691-6,6-6s6,2.691,6,6S32.309,31,29,31z M47,41c0,1.103-0.897,2-2,2
|
|||
|
|
s-2-0.897-2-2s0.897-2,2-2S47,39.897,47,41z M49,10c-2.206,0-4-1.794-4-4s1.794-4,4-4s4,1.794,4,4S51.206,10,49,10z"></path></svg></button></div><div id="global-graph-outer"><div id="global-graph-container" data-cfg="{"drag":true,"zoom":true,"depth":-1,"scale":0.9,"repelForce":0.5,"centerForce":0.3,"linkDistance":30,"fontSize":0.6,"opacityScale":1,"showTags":true,"removeTags":[],"focusOnHover":true}"></div></div></div><div class="toc desktop-only"><button type="button" id="toc" class aria-controls="toc-content" aria-expanded="true"><h3>目录</h3><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="fold"><polyline points="6 9 12 15 18 9"></polyline></svg></button><div id="toc-content" class><ul class="overflow"><li class="depth-0"><a href="#概述" data-for="概述">概述</a></li><li class="depth-0"><a href="#基本概念" data-for="基本概念">基本概念</a></li><li class="depth-1"><a href="#元字符" data-for="元字符">元字符</a></li><li class="depth-1"><a href="#字符类" data-for="字符类">字符类</a></li><li class="depth-1"><a href="#位置匹配" data-for="位置匹配">位置匹配</a></li><li class="depth-0"><a href="#量词和分组" data-for="量词和分组">量词和分组</a></li><li class="depth-1"><a href="#量词" data-for="量词">量词</a></li><li class="depth-1"><a href="#分组和引用" data-for="分组和引用">分组和引用</a></li><li class="depth-0"><a href="#高级匹配" data-for="高级匹配">高级匹配</a></li><li class="depth-1"><a href="#断言" data-for="断言">断言</a></li><li class="depth-1"><a href="#标志模式修饰符" data-for="标志模式修饰符">标志/模式修饰符</a></li><li class="depth-0"><a href="#参考实例" data-for="参考实例">参考实例</a></li></ul></div></div><div class="explorer mobile-only"><button type="button" id="explorer" data-behavior="collapse" data-collapsed="collapsed" data-savestate="true" data-tree="[{"path":"Personal","collapsed":true},{"path":"Personal/Blog","collapsed":true},{"path":"Personal/Blog/2018","collapsed":true},{"path":"Personal/Blog/2020","collapsed":true},{"path":"Personal/Blog/2021","collapsed":true},{"path":"Personal/Blog/2022","collapsed":true},{"path":"Personal/Blog/2023","collapsed":true},{"path":"Personal/Blog/2024","collapsed":true},{"path":"Personal/Book","collapsed":true},{"path":"Personal/Book/个人成长","collapsed":true},{"path":"Personal/Book/医学健康","collapsed":true},{"path":"Personal/Book/历史","collapsed":true},{"path":"Personal/Book/哲学宗教","collapsed":true},{"path":"Personal/Book/心理","collapsed":true},{"path":"Personal/Book/政治军事","collapsed":true},{"path":"Personal/Book/教育学习","collapsed":true},{"path":"Personal/Book/文学","collapsed":true},{"path":"Personal/Book/生活百科","collapsed":true},{"path":"Personal/Book/社会文化","collapsed":true},{"path":"Personal/Book/科学技术","collapsed":true},{"path":"Personal/Book/经济理财","collapsed":true},{"path":"Personal/Book/艺术","collapsed":true},{"path":"Personal/Book/计算机","collapsed":true},{"path":"Personal/Journal","col
|
|||
|
|
</script><script type="module">
|
|||
|
|
let mermaidImport = undefined
|
|||
|
|
document.addEventListener('nav', async () => {
|
|||
|
|
if (document.querySelector("code.mermaid")) {
|
|||
|
|
mermaidImport ||= await import('https://cdnjs.cloudflare.com/ajax/libs/mermaid/10.7.0/mermaid.esm.min.mjs')
|
|||
|
|
const mermaid = mermaidImport.default
|
|||
|
|
const darkMode = document.documentElement.getAttribute('saved-theme') === 'dark'
|
|||
|
|
mermaid.initialize({
|
|||
|
|
startOnLoad: false,
|
|||
|
|
securityLevel: 'loose',
|
|||
|
|
theme: darkMode ? 'dark' : 'default'
|
|||
|
|
})
|
|||
|
|
|
|||
|
|
await mermaid.run({
|
|||
|
|
querySelector: '.mermaid'
|
|||
|
|
})
|
|||
|
|
}
|
|||
|
|
});
|
|||
|
|
</script><script src="https://cdnjs.cloudflare.com/ajax/libs/KaTeX/0.16.9/contrib/copy-tex.min.js" type="application/javascript"></script><script src="../../../postscript.js" type="module"></script></html>
|