html-minifier-next 5.0.1 → 5.0.3

package/README.md

@@ -402,39 +402,39 @@ How does HTML Minifier Next compare to other minifiers? (All minification with t
 <!-- Auto-generated benchmarks, don’t edit -->
 | Site | Original Size (KB) | [HTML Minifier Next](https://github.com/j9t/html-minifier-next) ([config](https://github.com/j9t/html-minifier-next/blob/main/benchmarks/html-minifier.json))<br>[![npm last update](https://img.shields.io/npm/last-update/html-minifier-next)](https://socket.dev/npm/package/html-minifier-next) | [htmlnano](https://github.com/posthtml/htmlnano)<br>[![npm last update](https://img.shields.io/npm/last-update/htmlnano)](https://socket.dev/npm/package/htmlnano) | [@swc/html](https://github.com/swc-project/swc)<br>[![npm last update](https://img.shields.io/npm/last-update/@swc/html)](https://socket.dev/npm/package/@swc/html) | [minify-html](https://github.com/wilsonzlin/minify-html)<br>[![npm last update](https://img.shields.io/npm/last-update/@minify-html/node)](https://socket.dev/npm/package/@minify-html/node) | [minimize](https://github.com/Swaagie/minimize)<br>[![npm last update](https://img.shields.io/npm/last-update/minimize)](https://socket.dev/npm/package/minimize) | [html­com­pressor.­com](https://htmlcompressor.com/) |
 | --- | --- | --- | --- | --- | --- | --- | --- |
-| [A List Apart](https://alistapart.com/) | 64 | **53** | 55 | 56 | 55 | 59 | 57 |
-| [Apple](https://www.apple.com/) | 233 | **174** | 206 | 209 | 210 | 212 | 212 |
-| [BBC](https://www.bbc.co.uk/) | 625 | **569** | 587 | 587 | 588 | 620 | n/a |
-| [CERN](https://home.cern/) | 151 | **82** | 90 | 90 | 91 | 92 | 95 |
-| [CSS-Tricks](https://css-tricks.com/) | 156 | **115** | 122 | 137 | 138 | 142 | 139 |
-| [ECMAScript](https://tc39.es/ecma262/) | 7261 | **6411** | 6583 | 6465 | 6589 | 6637 | n/a |
-| [EDRi](https://edri.org/) | 80 | **59** | 69 | 69 | 71 | 74 | 72 |
-| [EFF](https://www.eff.org/) | 54 | **44** | 48 | 47 | 48 | 49 | 49 |
+| [A List Apart](https://alistapart.com/) | 63 | **53** | 55 | 56 | 55 | 58 | 56 |
+| [Apple](https://www.apple.com/) | 236 | **198** | 209 | 212 | 213 | 215 | 215 |
+| [BBC](https://www.bbc.co.uk/) | 651 | **605** | 611 | 612 | 613 | 646 | n/a |
+| [CERN](https://home.cern/) | 150 | **80** | 90 | 90 | 90 | 92 | 95 |
+| [CSS-Tricks](https://css-tricks.com/) | 155 | 127 | **121** | 136 | 137 | 141 | 138 |
+| [ECMAScript](https://tc39.es/ecma262/) | 7261 | **6447** | 6583 | 6465 | 6589 | 6637 | n/a |
+| [EDRi](https://edri.org/) | 80 | **68** | 69 | 69 | 71 | 74 | 72 |
+| [EFF](https://www.eff.org/) | 54 | **45** | 49 | 47 | 48 | 49 | 49 |
 | [European Alternatives](https://european-alternatives.eu/) | 48 | **30** | 32 | 32 | 32 | 32 | 32 |
-| [FAZ](https://www.faz.net/aktuell/) | 1488 | 1361 | **1337** | 1416 | 1427 | 1436 | n/a |
+| [FAZ](https://www.faz.net/aktuell/) | 1519 | 1389 | **1364** | 1446 | 1457 | 1467 | n/a |
 | [French Tech](https://lafrenchtech.gouv.fr/) | 153 | **122** | 126 | 126 | 126 | 132 | 127 |
-| [Frontend Dogma](https://frontenddogma.com/) | 227 | **219** | 241 | 226 | 227 | 246 | 227 |
-| [Google](https://www.google.com/) | 18 | **16** | 17 | 17 | 17 | 18 | 18 |
-| [Ground News](https://ground.news/) | 2093 | **1829** | 1928 | 1954 | 1957 | 2080 | n/a |
+| [Frontend Dogma](https://frontenddogma.com/) | 227 | **219** | 240 | 225 | 227 | 246 | 226 |
+| [Google](https://www.google.com/) | 18 | **16** | **16** | **16** | 17 | 18 | 18 |
+| [Ground News](https://ground.news/) | 1465 | **1328** | 1350 | 1372 | 1377 | 1453 | n/a |
 | [HTML Living Standard](https://html.spec.whatwg.org/multipage/) | 149 | 148 | 153 | **147** | 149 | 155 | 149 |
-| [Igalia](https://www.igalia.com/) | 49 | **33** | 36 | 35 | 36 | 37 | 36 |
-| [Leanpub](https://leanpub.com/) | 241 | **210** | 225 | 225 | 225 | 236 | 238 |
-| [Mastodon](https://mastodon.social/explore) | 38 | **28** | 32 | 35 | 35 | 36 | 36 |
-| [MDN](https://developer.mozilla.org/en-US/) | 109 | **62** | 64 | 65 | 65 | 68 | 68 |
-| [Middle East Eye](https://www.middleeasteye.net/) | 219 | **194** | 199 | 198 | 198 | 199 | 200 |
-| [Mistral AI](https://mistral.ai/) | 343 | **301** | 307 | 310 | 311 | 340 | n/a |
+| [Igalia](https://www.igalia.com/) | 49 | **34** | 36 | 36 | 36 | 37 | 37 |
+| [Leanpub](https://leanpub.com/) | 241 | **224** | 226 | 226 | 227 | 236 | 238 |
+| [Mastodon](https://mastodon.social/explore) | 38 | 35 | **32** | 35 | 36 | 37 | 37 |
+| [MDN](https://developer.mozilla.org/en-US/) | 109 | **63** | 64 | 65 | 65 | 68 | 68 |
+| [Middle East Eye](https://www.middleeasteye.net/) | 220 | **194** | 200 | 198 | 198 | 199 | 200 |
+| [Mistral AI](https://mistral.ai/) | 343 | **307** | **307** | 310 | 311 | 340 | n/a |
 | [Mozilla](https://www.mozilla.org/) | 47 | **32** | 35 | 35 | 35 | 36 | 36 |
-| [Nielsen Norman Group](https://www.nngroup.com/) | 97 | 72 | **59** | 78 | 80 | 81 | 80 |
-| [SitePoint](https://www.sitepoint.com/) | 494 | **352** | 431 | 468 | 473 | 491 | n/a |
+| [Nielsen Norman Group](https://www.nngroup.com/) | 97 | 73 | **59** | 78 | 80 | 81 | 81 |
+| [SitePoint](https://www.sitepoint.com/) | 494 | 456 | **431** | 468 | 473 | 491 | n/a |
 | [Startup-Verband](https://startupverband.de/) | 43 | **30** | 31 | **30** | 31 | 31 | 31 |
-| [TetraLogical](https://tetralogical.com/) | 59 | **23** | 49 | 51 | 53 | 53 | 53 |
+| [TetraLogical](https://tetralogical.com/) | 59 | 52 | **49** | 51 | 53 | 53 | 53 |
 | [TPGi](https://www.tpgi.com/) | 173 | **157** | 159 | 163 | 164 | 170 | 170 |
-| [United Nations](https://www.un.org/en/) | 151 | **113** | 121 | 125 | 125 | 130 | 123 |
-| [Vivaldi](https://vivaldi.com/) | 93 | **74** | n/a | 79 | 81 | 84 | 82 |
+| [United Nations](https://www.un.org/en/) | 151 | **113** | 121 | 125 | 124 | 130 | 123 |
+| [Vivaldi](https://vivaldi.com/) | 93 | **76** | n/a | 79 | 81 | 84 | 82 |
 | [W3C](https://www.w3.org/) | 50 | **36** | 39 | 38 | 38 | 41 | 39 |
-| **Average processing time** |  | 73 ms (30/30) | 153 ms (29/30) | 51 ms (30/30) | **14 ms (30/30)** | 289 ms (30/30) | 1214 ms (24/30) |
+| **Average processing time** |  | 83 ms (30/30) | 165 ms (29/30) | 47 ms (30/30) | **13 ms (30/30)** | 283 ms (30/30) | 1254 ms (24/30) |
 
-(Last updated: Feb 2, 2026)
+(Last updated: Feb 4, 2026)
 <!-- End auto-generated -->
 
 Notes: Minimize does not minify CSS and JS. [HTML Minifier Terser](https://github.com/terser/html-minifier-terser) is currently not included due to issues around whitespace collapsing and removal of code using modern CSS features, issues which appeared to distort the data.

package/cli.js

@@ -41,6 +41,8 @@ const camelCase = (str) => paramCase(str).replace(/-([a-z])/g, (_, c) => c.toUpp
 
 // Lazy-load HMN to reduce CLI cold-start overhead
 import { getPreset, getPresetNames } from './src/presets.js';
+import { parseRegExp } from './src/lib/utils.js';
+import { optionDefinitions } from './src/lib/option-definitions.js';
 
 const require = createRequire(import.meta.url);
 const pkg = require('./package.json');
@@ -49,7 +51,6 @@ const DEFAULT_FILE_EXTENSIONS = ['html', 'htm', 'xhtml', 'shtml'];
 
 const program = new Command();
 program.name(pkg.name);
-program.version(pkg.version);
 
 function fatal(message) {
   console.error(message);
@@ -82,11 +83,6 @@ process.stdout.on('error', (err) => {
  *
  *    --customAttrSurround "[\"//matchString//\"]"
  */
-function parseRegExp(value) {
-  if (value) {
-    return new RegExp(value.replace(/^\/(.*)\/$/, '$1'));
-  }
-}
 
 function parseJSON(value) {
   if (value) {
@@ -125,68 +121,28 @@ const parseValidInt = (optionName) => (value) => {
   return num;
 };
 
-const mainOptions = {
-  caseSensitive: 'Treat attributes in case-sensitive manner (useful for custom HTML elements)',
-  collapseAttributeWhitespace: 'Trim and collapse whitespace characters within attribute values',
-  collapseBooleanAttributes: 'Omit attribute values from boolean attributes',
-  collapseInlineTagWhitespace: 'Collapse whitespace more aggressively between inline elements—use with `--collapse-whitespace`',
-  collapseWhitespace: 'Collapse whitespace that contributes to text nodes in a document tree',
-  conservativeCollapse: 'Always collapse to one space (never remove it entirely)—use with `--collapse-whitespace`',
-  continueOnMinifyError: 'Abort on minification errors',
-  continueOnParseError: 'Handle parse errors instead of aborting',
-  customAttrAssign: ['Array of regexes that allow to support custom attribute assign expressions (e.g., `<div flex?="{{mode != cover}}"></div>`)', parseJSONRegExpArray],
-  customAttrCollapse: ['Regex that specifies custom attribute to strip newlines from (e.g., /ng-class/)', parseRegExp],
-  customAttrSurround: ['Array of regexes that allow to support custom attribute surround expressions (e.g., `<input {{#if value}}checked="checked"{{/if}}>`)', parseJSONRegExpArray],
-  customEventAttributes: ['Array of regexes that allow to support custom event attributes for minifyJS (e.g., `ng-click`)', parseJSONRegExpArray],
-  customFragmentQuantifierLimit: ['Set maximum quantifier limit for custom fragments to prevent ReDoS attacks (default: 200)', parseValidInt('customFragmentQuantifierLimit')],
-  decodeEntities: 'Use direct Unicode characters whenever possible',
-  ignoreCustomComments: ['Array of regexes that allow to ignore matching comments', parseJSONRegExpArray],
-  ignoreCustomFragments: ['Array of regexes that allow to ignore certain fragments, when matched (e.g., `<?php … ?>`, `{{ … }}`)', parseJSONRegExpArray],
-  includeAutoGeneratedTags: 'Insert elements generated by HTML parser',
-  inlineCustomElements: ['Array of names of custom elements which are inline, for whitespace handling', parseJSONArray],
-  keepClosingSlash: 'Keep the trailing slash on void elements',
-  maxInputLength: ['Maximum input length to prevent ReDoS attacks', parseValidInt('maxInputLength')],
-  maxLineLength: ['Specify a maximum line length; compressed output will be split by newlines at valid HTML split-points', parseValidInt('maxLineLength')],
-  mergeScripts: 'Merge consecutive inline `script` elements into one',
-  minifyCSS: ['Minify CSS in `style` elements and attributes (uses Lightning CSS)', parseJSON],
-  minifyJS: ['Minify JavaScript in `script` elements and event attributes (uses Terser or SWC; pass `{"engine": "swc"}` for SWC)', parseJSON],
-  minifySVG: ['Minify SVG elements and attributes (numeric precision, default attributes, colors)', parseJSON],
-  minifyURLs: ['Minify URLs in various attributes', parseJSON],
-  noNewlinesBeforeTagClose: 'Never add a newline before a tag that closes an element',
-  partialMarkup: 'Treat input as a partial HTML fragment, preserving stray end tags and unclosed tags',
-  preserveLineBreaks: 'Always collapse to one line break (never remove it entirely) when whitespace between tags includes a line break—use with `--collapse-whitespace`',
-  preventAttributesEscaping: 'Prevents the escaping of the values of attributes',
-  processConditionalComments: 'Process contents of conditional comments through minifier',
-  processScripts: ['Array of strings corresponding to types of `script` elements to process through minifier (e.g., `text/ng-template`, `text/x-handlebars-template`, etc.)', parseJSONArray],
-  quoteCharacter: ['Type of quote to use for attribute values (“\'” or “"”)', parseString],
-  removeAttributeQuotes: 'Remove quotes around attributes when possible',
-  removeComments: 'Strip HTML comments',
-  removeEmptyAttributes: 'Remove all attributes with whitespace-only values',
-  removeEmptyElements: 'Remove all elements with empty contents',
-  removeEmptyElementsExcept: ['Array of elements to preserve when `--remove-empty-elements` is enabled (e.g., `td`, `["td", "<span aria-hidden=\'true\'>"]`)', parseJSONArray],
-  removeOptionalTags: 'Remove unrequired tags',
-  removeRedundantAttributes: 'Remove attributes when value matches default',
-  removeScriptTypeAttributes: 'Remove `type="text/javascript"` from `script` elements; other `type` attribute values are left intact',
-  removeStyleLinkTypeAttributes: 'Remove `type="text/css"` from `style` and `link` elements; other `type` attribute values are left intact',
-  removeTagWhitespace: 'Remove space between attributes whenever possible; note that this will result in invalid HTML',
-  sortAttributes: 'Sort attributes by frequency',
-  sortClassNames: 'Sort style classes by frequency',
-  trimCustomFragments: 'Trim whitespace around custom fragments (`--ignore-custom-fragments`)',
-  useShortDoctype: 'Replaces the doctype with the short HTML doctype'
+// Map option types to CLI parsers
+const typeParsers = {
+  regexp: parseRegExp,
+  regexpArray: parseJSONRegExpArray,
+  json: parseJSON,
+  jsonArray: parseJSONArray,
+  string: parseString,
+  int: (key) => parseValidInt(key)
 };
 
-// Configure command-line flags
-const mainOptionKeys = Object.keys(mainOptions);
+// Configure command-line flags from shared option definitions
+const mainOptionKeys = Object.keys(optionDefinitions);
 mainOptionKeys.forEach(function (key) {
-  const option = mainOptions[key];
-  if (Array.isArray(option)) {
-    key = '--' + paramCase(key);
-    key += option[1] === parseJSON ? ' [value]' : ' <value>';
-    program.option(key, option[0], option[1]);
-  } else if (key === 'continueOnMinifyError') {
-    program.option('--no-' + paramCase(key), option);
+  const { description, type } = optionDefinitions[key];
+  if (type === 'invertedBoolean') {
+    program.option('--no-' + paramCase(key), description);
+  } else if (type === 'boolean') {
+    program.option('--' + paramCase(key), description);
   } else {
-    program.option('--' + paramCase(key), option);
+    const flag = '--' + paramCase(key) + (type === 'json' ? ' [value]' : ' <value>');
+    const parser = type === 'int' ? typeParsers.int(key) : typeParsers[type];
+    program.option(flag, description, parser);
   }
 });
 program.option('-o --output <file>', 'Specify output file (reads from file arguments or STDIN; outputs to STDOUT if not specified)');
@@ -252,10 +208,11 @@ function normalizeConfig(config) {
   // Apply parsers to main options
   mainOptionKeys.forEach(function (key) {
     if (key in normalized) {
-      const option = mainOptions[key];
-      if (Array.isArray(option)) {
+      const { type } = optionDefinitions[key];
+      if (type !== 'boolean' && type !== 'invertedBoolean') {
+        const parser = type === 'int' ? typeParsers.int(key) : typeParsers[type];
         const value = normalized[key];
-        normalized[key] = option[1](typeof value === 'string' ? value : JSON.stringify(value));
+        normalized[key] = parser(typeof value === 'string' ? value : JSON.stringify(value));
       }
     }
   });
@@ -288,6 +245,8 @@ program.option('-p --preset <name>', `Use a preset configuration (${getPresetNam
 program.option('-c --config-file <file>', 'Use config file');
 program.option('--cache-css <size>', 'Set CSS minification cache size (number of entries, default: 500)', parseValidInt('cacheCSS'));
 program.option('--cache-js <size>', 'Set JavaScript minification cache size (number of entries, default: 500)', parseValidInt('cacheJS'));
+program.version(pkg.version, '-V, --version', 'Output the version number');
+program.helpOption('-h, --help', 'Display help for command');
 
 (async () => {
   let content;

package/dist/htmlminifier.cjs

@@ -966,7 +966,7 @@ function uniqueId(value) {
   return id;
 }
 
-// Identity functions
+// Identity and transform functions
 
 function identity(value) {
   return value;
@@ -976,6 +976,10 @@ function identityAsync(value) {
   return Promise.resolve(value);
 }
 
+function lowercase(value) {
+  return value.toLowerCase();
+}
+
 // Replace async helper
 
 /**
@@ -997,6 +1001,20 @@ async function replaceAsync(str, regex, asyncFn) {
   return str.replace(regex, () => data.shift());
 }
 
+// String patterns to RegExp conversion (for JSON config support)
+
+function parseRegExp(value) {
+  if (typeof value === 'string') {
+    if (!value) return undefined; // Empty string = not configured
+    const match = value.match(/^\/(.+)\/([dgimsuvy]*)$/);
+    if (match) {
+      return new RegExp(match[1], match[2]);
+    }
+    return new RegExp(value);
+  }
+  return value;
+}
+
 // Regex patterns (to avoid repeated allocations in hot paths)
 
 const RE_WS_START = /^[ \n\r\t\f]+/;
@@ -2041,6 +2059,22 @@ function getSVGMinifierOptions(userOptions) {
   return null;
 }
 
+// Single source of truth for minifier option names, descriptions, types, and shared defaults
+
+
+const optionDefaults = {
+  continueOnMinifyError: true,
+  ignoreCustomComments: [
+    /^!/,
+    /^\s*#/
+  ],
+  ignoreCustomFragments: [
+    /<%[\s\S]*?%>/,
+    /<\?[\s\S]*?\?>/
+  ],
+  includeAutoGeneratedTags: false
+};
+
 // Imports
 
 
@@ -2072,21 +2106,10 @@ function shouldMinifyInnerHTML(options) {
  */
 const processOptions = (inputOptions, { getLightningCSS, getTerser, getSwc, cssMinifyCache, jsMinifyCache } = {}) => {
   const options = {
-    name: function (name) {
-      return name.toLowerCase();
-    },
+    name: lowercase,
     canCollapseWhitespace,
     canTrimWhitespace,
-    continueOnMinifyError: true,
-    ignoreCustomComments: [
-      /^!/,
-      /^\s*#/
-    ],
-    ignoreCustomFragments: [
-      /<%[\s\S]*?%>/,
-      /<\?[\s\S]*?\?>/
-    ],
-    includeAutoGeneratedTags: false,
+    ...optionDefaults,
     log: identity,
     minifyCSS: identityAsync,
     minifyJS: identity,
@@ -2094,14 +2117,6 @@ const processOptions = (inputOptions, { getLightningCSS, getTerser, getSwc, cssM
     minifySVG: null
   };
 
-  // Helper to convert string patterns to RegExp (for JSON config support)
-  const parseRegExp = (value) => {
-    if (typeof value === 'string') {
-      return new RegExp(value.replace(/^\/(.*)\/$/, '$1'));
-    }
-    return value; // Already a RegExp or another type
-  };
-
   const parseRegExpArray = (arr) => {
     return Array.isArray(arr) ? arr.map(parseRegExp) : arr;
   };
@@ -2456,6 +2471,36 @@ function attributesInclude(attributes, attribute) {
   return false;
 }
 
+/**
+ * Remove duplicate attributes from an attribute list.
+ * Per HTML spec, when an attribute appears multiple times, the first occurrence wins.
+ * Duplicate attributes result in invalid HTML, so we keep only the first.
+ * @param {Array} attrs - Array of attribute objects with `name` property
+ * @param {boolean} caseSensitive - Whether to compare names case-sensitively (for XML/SVG)
+ * @returns {Array} Deduplicated attribute array (modifies in place and returns)
+ */
+function deduplicateAttributes(attrs, caseSensitive) {
+  if (attrs.length < 2) {
+    return attrs;
+  }
+
+  const seen = new Set();
+  let writeIndex = 0;
+
+  for (let i = 0; i < attrs.length; i++) {
+    const attr = attrs[i];
+    const key = caseSensitive ? attr.name : attr.name.toLowerCase();
+
+    if (!seen.has(key)) {
+      seen.add(key);
+      attrs[writeIndex++] = attr;
+    }
+  }
+
+  attrs.length = writeIndex;
+  return attrs;
+}
+
 function isAttributeRedundant(tag, attrName, attrValue, attrs) {
   // Fast-path: Check if this element–attribute combination can possibly be redundant
   // before doing expensive string operations
@@ -3036,6 +3081,16 @@ function canRemovePrecedingTag(optionalEndTag, tag) {
 // Element removal logic
 
 function canRemoveElement(tag, attrs) {
+  // Elements with `id` attribute must never be removed—they serve as:
+  // - Navigation targets (skip links, URL fragments)
+  // - JavaScript selector targets (`getElementById`, `querySelector`)
+  // - CSS targets (`:target` pseudo-class, ID selectors)
+  // - Accessibility landmarks (ARIA references)
+  // - Portal mount points (React portals, etc.)
+  if (hasAttrName('id', attrs)) {
+    return false;
+  }
+
   switch (tag) {
     case 'textarea':
       return false;
@@ -3231,6 +3286,9 @@ const DEFAULT_JS_TYPES = new Set(['', 'text/javascript', 'application/javascript
 const RE_START_TAG = /^<[^/!]/;
 const RE_END_TAG = /^<\//;
 
+// HTML encoding types for annotation-xml (MathML)
+const RE_HTML_ENCODING = /^(text\/html|application\/xhtml\+xml)$/i;
+
 // Script merging
 
 /**
@@ -4174,8 +4232,24 @@ async function minifyHTML(value, options, partialMarkup) {
         options.keepClosingSlash = true;
         options.name = identity;
         options.insideSVG = lowerTag === 'svg';
+        options.insideForeignContent = true;
       }
-      tag = options.name(tag);
+      // `foreignObject` in SVG and `annotation-xml` in MathML contain HTML content
+      // Note: The element itself is in SVG/MathML namespace, only its children are HTML
+      let useParentNameForTag = false;
+      if (options.insideForeignContent && (lowerTag === 'foreignobject' ||
+          (lowerTag === 'annotation-xml' && attrs.some(a => a.name.toLowerCase() === 'encoding' &&
+            RE_HTML_ENCODING.test(a.value))))) {
+        const parentName = options.name;
+        options = Object.create(options);
+        options.caseSensitive = false;
+        options.keepClosingSlash = false;
+        options.parentName = parentName; // Preserve for the element tag itself
+        options.name = options.htmlName || lowercase;
+        options.insideForeignContent = false;
+        useParentNameForTag = true;
+      }
+      tag = (useParentNameForTag ? options.parentName : options.name)(tag);
       currentTag = tag;
       charsPrevTag = tag;
       if (!inlineTextSet.has(tag)) {
@@ -4229,6 +4303,11 @@ async function minifyHTML(value, options, partialMarkup) {
 
       buffer.push(openTag);
 
+      // Remove duplicate attributes (per HTML spec, first occurrence wins)
+      // Duplicate attributes result in invalid HTML
+      // https://html.spec.whatwg.org/multipage/parsing.html#attribute-name-state
+      deduplicateAttributes(attrs, options.caseSensitive);
+
       if (options.sortAttributes) {
         options.sortAttributes(tag, attrs);
       }
@@ -4260,8 +4339,12 @@ async function minifyHTML(value, options, partialMarkup) {
     },
     end: function (tag, attrs, autoGenerated) {
       const lowerTag = tag.toLowerCase();
+      // Restore parent context when exiting SVG/MathML or HTML-in-foreign-content elements
       if (lowerTag === 'svg' || lowerTag === 'math') {
         options = Object.getPrototypeOf(options);
+      } else if ((lowerTag === 'foreignobject' || lowerTag === 'annotation-xml') &&
+                 !options.insideForeignContent && Object.getPrototypeOf(options).insideForeignContent) {
+        options = Object.getPrototypeOf(options);
       }
       tag = options.name(tag);
 
@@ -4303,7 +4386,7 @@ async function minifyHTML(value, options, partialMarkup) {
         optionalEndTagEmitted = true;
       }
 
-      if (options.removeEmptyElements && isElementEmpty && canRemoveElement(tag, attrs)) {
+      if (options.removeEmptyElements && isElementEmpty && !options.insideForeignContent && canRemoveElement(tag, attrs)) {
         let preserve = false;
         if (removeEmptyElementsExcept.length) {
           // Normalize attribute names for comparison with specs

package/dist/htmlminifier.esm.bundle.js

@@ -3579,7 +3579,7 @@ function uniqueId(value) {
   return id;
 }
 
-// Identity functions
+// Identity and transform functions
 
 function identity(value) {
   return value;
@@ -3589,6 +3589,10 @@ function identityAsync(value) {
   return Promise.resolve(value);
 }
 
+function lowercase(value) {
+  return value.toLowerCase();
+}
+
 // Replace async helper
 
 /**
@@ -3610,6 +3614,20 @@ async function replaceAsync(str, regex, asyncFn) {
   return str.replace(regex, () => data.shift());
 }
 
+// String patterns to RegExp conversion (for JSON config support)
+
+function parseRegExp(value) {
+  if (typeof value === 'string') {
+    if (!value) return undefined; // Empty string = not configured
+    const match = value.match(/^\/(.+)\/([dgimsuvy]*)$/);
+    if (match) {
+      return new RegExp(match[1], match[2]);
+    }
+    return new RegExp(value);
+  }
+  return value;
+}
+
 // Regex patterns (to avoid repeated allocations in hot paths)
 
 const RE_WS_START = /^[ \n\r\t\f]+/;
@@ -4654,6 +4672,22 @@ function getSVGMinifierOptions(userOptions) {
   return null;
 }
 
+// Single source of truth for minifier option names, descriptions, types, and shared defaults
+
+
+const optionDefaults = {
+  continueOnMinifyError: true,
+  ignoreCustomComments: [
+    /^!/,
+    /^\s*#/
+  ],
+  ignoreCustomFragments: [
+    /<%[\s\S]*?%>/,
+    /<\?[\s\S]*?\?>/
+  ],
+  includeAutoGeneratedTags: false
+};
+
 // Imports
 
 
@@ -4685,21 +4719,10 @@ function shouldMinifyInnerHTML(options) {
  */
 const processOptions = (inputOptions, { getLightningCSS, getTerser, getSwc, cssMinifyCache, jsMinifyCache } = {}) => {
   const options = {
-    name: function (name) {
-      return name.toLowerCase();
-    },
+    name: lowercase,
     canCollapseWhitespace,
     canTrimWhitespace,
-    continueOnMinifyError: true,
-    ignoreCustomComments: [
-      /^!/,
-      /^\s*#/
-    ],
-    ignoreCustomFragments: [
-      /<%[\s\S]*?%>/,
-      /<\?[\s\S]*?\?>/
-    ],
-    includeAutoGeneratedTags: false,
+    ...optionDefaults,
     log: identity,
     minifyCSS: identityAsync,
     minifyJS: identity,
@@ -4707,14 +4730,6 @@ const processOptions = (inputOptions, { getLightningCSS, getTerser, getSwc, cssM
     minifySVG: null
   };
 
-  // Helper to convert string patterns to RegExp (for JSON config support)
-  const parseRegExp = (value) => {
-    if (typeof value === 'string') {
-      return new RegExp(value.replace(/^\/(.*)\/$/, '$1'));
-    }
-    return value; // Already a RegExp or another type
-  };
-
   const parseRegExpArray = (arr) => {
     return Array.isArray(arr) ? arr.map(parseRegExp) : arr;
   };
@@ -5069,6 +5084,36 @@ function attributesInclude(attributes, attribute) {
   return false;
 }
 
+/**
+ * Remove duplicate attributes from an attribute list.
+ * Per HTML spec, when an attribute appears multiple times, the first occurrence wins.
+ * Duplicate attributes result in invalid HTML, so we keep only the first.
+ * @param {Array} attrs - Array of attribute objects with `name` property
+ * @param {boolean} caseSensitive - Whether to compare names case-sensitively (for XML/SVG)
+ * @returns {Array} Deduplicated attribute array (modifies in place and returns)
+ */
+function deduplicateAttributes(attrs, caseSensitive) {
+  if (attrs.length < 2) {
+    return attrs;
+  }
+
+  const seen = new Set();
+  let writeIndex = 0;
+
+  for (let i = 0; i < attrs.length; i++) {
+    const attr = attrs[i];
+    const key = caseSensitive ? attr.name : attr.name.toLowerCase();
+
+    if (!seen.has(key)) {
+      seen.add(key);
+      attrs[writeIndex++] = attr;
+    }
+  }
+
+  attrs.length = writeIndex;
+  return attrs;
+}
+
 function isAttributeRedundant(tag, attrName, attrValue, attrs) {
   // Fast-path: Check if this element–attribute combination can possibly be redundant
   // before doing expensive string operations
@@ -5649,6 +5694,16 @@ function canRemovePrecedingTag(optionalEndTag, tag) {
 // Element removal logic
 
 function canRemoveElement(tag, attrs) {
+  // Elements with `id` attribute must never be removed—they serve as:
+  // - Navigation targets (skip links, URL fragments)
+  // - JavaScript selector targets (`getElementById`, `querySelector`)
+  // - CSS targets (`:target` pseudo-class, ID selectors)
+  // - Accessibility landmarks (ARIA references)
+  // - Portal mount points (React portals, etc.)
+  if (hasAttrName('id', attrs)) {
+    return false;
+  }
+
   switch (tag) {
     case 'textarea':
       return false;
@@ -5844,6 +5899,9 @@ const DEFAULT_JS_TYPES = new Set(['', 'text/javascript', 'application/javascript
 const RE_START_TAG = /^<[^/!]/;
 const RE_END_TAG = /^<\//;
 
+// HTML encoding types for annotation-xml (MathML)
+const RE_HTML_ENCODING = /^(text\/html|application\/xhtml\+xml)$/i;
+
 // Script merging
 
 /**
@@ -6787,8 +6845,24 @@ async function minifyHTML(value, options, partialMarkup) {
         options.keepClosingSlash = true;
         options.name = identity;
         options.insideSVG = lowerTag === 'svg';
+        options.insideForeignContent = true;
       }
-      tag = options.name(tag);
+      // `foreignObject` in SVG and `annotation-xml` in MathML contain HTML content
+      // Note: The element itself is in SVG/MathML namespace, only its children are HTML
+      let useParentNameForTag = false;
+      if (options.insideForeignContent && (lowerTag === 'foreignobject' ||
+          (lowerTag === 'annotation-xml' && attrs.some(a => a.name.toLowerCase() === 'encoding' &&
+            RE_HTML_ENCODING.test(a.value))))) {
+        const parentName = options.name;
+        options = Object.create(options);
+        options.caseSensitive = false;
+        options.keepClosingSlash = false;
+        options.parentName = parentName; // Preserve for the element tag itself
+        options.name = options.htmlName || lowercase;
+        options.insideForeignContent = false;
+        useParentNameForTag = true;
+      }
+      tag = (useParentNameForTag ? options.parentName : options.name)(tag);
       currentTag = tag;
       charsPrevTag = tag;
       if (!inlineTextSet.has(tag)) {
@@ -6842,6 +6916,11 @@ async function minifyHTML(value, options, partialMarkup) {
 
       buffer.push(openTag);
 
+      // Remove duplicate attributes (per HTML spec, first occurrence wins)
+      // Duplicate attributes result in invalid HTML
+      // https://html.spec.whatwg.org/multipage/parsing.html#attribute-name-state
+      deduplicateAttributes(attrs, options.caseSensitive);
+
       if (options.sortAttributes) {
         options.sortAttributes(tag, attrs);
       }
@@ -6873,8 +6952,12 @@ async function minifyHTML(value, options, partialMarkup) {
     },
     end: function (tag, attrs, autoGenerated) {
       const lowerTag = tag.toLowerCase();
+      // Restore parent context when exiting SVG/MathML or HTML-in-foreign-content elements
       if (lowerTag === 'svg' || lowerTag === 'math') {
         options = Object.getPrototypeOf(options);
+      } else if ((lowerTag === 'foreignobject' || lowerTag === 'annotation-xml') &&
+                 !options.insideForeignContent && Object.getPrototypeOf(options).insideForeignContent) {
+        options = Object.getPrototypeOf(options);
       }
       tag = options.name(tag);
 
@@ -6916,7 +6999,7 @@ async function minifyHTML(value, options, partialMarkup) {
         optionalEndTagEmitted = true;
       }
 
-      if (options.removeEmptyElements && isElementEmpty && canRemoveElement(tag, attrs)) {
+      if (options.removeEmptyElements && isElementEmpty && !options.insideForeignContent && canRemoveElement(tag, attrs)) {
         let preserve = false;
         if (removeEmptyElementsExcept.length) {
           // Normalize attribute names for comparison with specs