Add PageFind beta V2 (Full Text Search across Site)

.eslintignore

@@ -6,6 +6,8 @@ node_modules
 
 packages/cli/src/lib/live-server/*
 
+packages/cli/test/**/pagefind/**/*.js
+
 # --- packages/core ---
 
 # Ignore JS files that are compiled from TS

.eslintrc.js

@@ -2,6 +2,7 @@
 /* eslint quotes: ["error", "double"] */
 
 module.exports = {
+  "ignorePatterns": ["docs/_site/**", "**/dist/**", "**/node_modules/**"],
   "env": {
     "node": true,
     "es6": true,

.gitignore

@@ -46,6 +46,9 @@ packages/core/template/*/_site
 # Generated site (MarkBind)
 packages/cli/test/functional/*/_site
 
+# Generated pagefind directories for sites and in expected
+packages/cli/test/functional/**/pagefind
+
 # Ignore .page-vue-render.js files in functional test and subdirectories on update
 packages/cli/test/functional/**/*.page-vue-render.js
 
@@ -117,6 +120,9 @@ packages/core/src/lib/markdown-it/patches/**/*.js
 .nx/cache
 .nx/workspace-data
 
+# Pagefind fragments
+*.pf_fragment
+
 # AI Tools directories (symlinks)
 .opencode
 .cline

.stylelintrc.js

@@ -6,5 +6,16 @@ module.exports = {
     // MarkBind generates some blank CSS files when initialising a site,
     // which violates the no-empty-source rule
     "no-empty-source": null
-  }
+  },
+  "overrides": [
+    {
+      // pagefind uses BEM-style class names (e.g., .pagefind-ui__result) as default.
+      // Since we currently style pagefind's default UI classes, we need to ignore the kebab-case rule here. 
+      // This override should be removed once we no longer rely on pagefind's default CSS classes.
+      "files": ["**/pagefindSearchBar/**"],
+      "rules": {
+        "selector-class-pattern": null
+      }
+    }
+  ]
 };

docs/userGuide/makingTheSiteSearchable.md

@@ -37,6 +37,112 @@ You can add a search bar component to your website to allow users to search the
 <include src="syntax/keywords.md" />
 <include src="syntax/indexing.md" />
 
+
+
+
+
+## Using Pagefind (Beta)
+
+
+MarkBind now supports [Pagefind](https://pagefind.app/), a static low-bandwidth search library, as a built-in feature. This provides full-text search capabilities without external services.
+
+<box type="info">
+This is a <strong>beta</strong> feature and will be refined in future updates. To use it, you must have <code>enableSearch: true</code> in your <code>site.json</code> (this is the default).
+</box>
+
+<box type="warning">
+The Pagefind index is currently only generated during a full site build (e.g., <code>markbind build</code>). It will <strong>not</strong> repeatedly update during live reload (<code>markbind serve</code>) when you modify pages. You must restart the server (re-run <code>markbind serve</code>) or rebuild to refresh the search index.
+</box>
+
+To add the Pagefind search bar to your page, simply insert the following element where you want it to appear:
+
+```md
+<search />
+```
+
+The following UI will be rendered, which is provided by Pagefind:
+
+<search />
+
+<br>
+
+### Ignoring Individual Elements from Pagefind Search
+
+You can exclude specific elements from the search index by adding the `data-pagefind-ignore` attribute to them:
+
+```html
+<div>
+    <h1>This content will be in your search index.</h1>
+    <div data-pagefind-ignore>
+        This content and all its children will be excluded from search.
+    </div>
+</div>
+```
+
+For more details, see the [Pagefind documentation on removing individual elements](https://pagefind.app/docs/indexing/#removing-individual-elements-from-the-index).
+
+### Using Pagefind Configuration
+
+You can customize Pagefind's indexing behavior by adding a `pagefind` configuration in your `site.json`. This allows you to control which content is indexed and how search works.
+
+#### Excluding Content from Search Index
+
+You can use the `exclude_selectors` option to exclude specific elements from the search index. This is useful if you are migrating from Algolia and want to reuse your existing CSS class selectors.
+
+In your `site.json`:
+
+```json
+{
+  "pagefind": {
+    "exclude_selectors": [".algolia-no-index", "[class*='algolia-no-index']"]
+  }
+}
+```
+
+This tells Pagefind to exclude any element with the `algolia-no-index` class (or containing it in a space-separated list) from the search index, similar to using `data-pagefind-ignore`.
+
+#### Limiting Which Pages Are Searchable
+
+You can use the `glob` option to limit which pages are indexed by Pagefind. This is useful when you want search results to only show pages from specific sections of your site.
+
+In your `site.json`:
+
+```json
+{
+  "pagefind": {
+    "glob": [
+      "devGuide",
+      "userGuide/*"
+    ]
+  }
+}
+```
+
+MarkBind supports glob patterns and will automatically append `.html` to your patterns if not specified. For example:
+- `"devGuide"` becomes `"devGuide/**/*.html"`
+- `"devGuide/*"` becomes `"devGuide/*.html"`
+- `"**/devGuide/**"` becomes `"**/devGuide/**/*.html"`
+- `"*.html"` remains `"*.html"` (no change needed)
+
+Only pages matching these glob patterns will appear in search results. This can be particularly useful for:
+- Multi-site setups where you want to search only specific sections
+- Including only certain directories from search results
+
+For more details on glob patterns, see the [Pagefind documentation](https://pagefind.app/docs/config-options/#glob).
+
+<panel header="Potential Future Enhancements">
+
+Additional Pagefind configuration options may be supported in future releases:
+
+- **`root_selector`**: Allows specifying a custom root element for indexing (default: `html`). Useful for sites with specific content containers.
+- **`force_language`**: Forces a specific language for indexing (e.g., `"en"`, `"pt"`). Improves search accuracy for multilingual sites.
+
+</panel>
+
+
+
+<br>
+
 ## Using External Search Services
 
 MarkBind sites can use Algolia Doc Search services easily via the Algolia plugin. Unlike the built-in search, Algolia provides full-text search. See the panel below for more info.

packages/cli/test/functional/test.ts

@@ -50,12 +50,14 @@ expectedErrors.forEach((error, index) => {
   logger.info(`${index + 1}: ${error}`);
 });
 
+const GENERATED_DIRECTORIES_TO_IGNORE = ['**/pagefind/**'];
+
 testSites.forEach((siteName) => {
   console.log(`Running ${siteName} tests`);
   try {
     execSync(`node ${CLI_PATH} build ${siteName}`, execOptions);
     const siteIgnoredFiles = plantumlGeneratedFilesForTestSites[siteName];
-    compare(siteName, 'expected', '_site', siteIgnoredFiles);
+    compare(siteName, 'expected', '_site', siteIgnoredFiles, GENERATED_DIRECTORIES_TO_IGNORE);
   } catch (err) {
     if (_.isError(err)) {
       printFailedMessage(err, siteName);
@@ -74,7 +76,8 @@ testConvertSites.forEach((sitePath) => {
     execSync(`node ${CLI_PATH} init ${nonMarkBindSitePath} -c`, execOptions);
     execSync(`node ${CLI_PATH} build ${nonMarkBindSitePath}`, execOptions);
     const siteIgnoredFiles = plantumlGeneratedFilesForConvertSites[siteName];
-    compare(sitePath, 'expected', 'non_markbind_site/_site', siteIgnoredFiles);
+    compare(sitePath, 'expected', 'non_markbind_site/_site', siteIgnoredFiles,
+            GENERATED_DIRECTORIES_TO_IGNORE);
   } catch (err) {
     if (_.isError(err)) {
       printFailedMessage(err, sitePath);
@@ -98,7 +101,7 @@ testTemplateSites.forEach((templateAndSitePath) => {
     execSync(`node ${CLI_PATH} init ${siteCreationTempPath} --template ${flag}`, execOptions);
     execSync(`node ${CLI_PATH} build ${siteCreationTempPath}`, execOptions);
     const siteIgnoredFiles = plantumlGeneratedFilesForTemplateSites[siteName];
-    compare(sitePath, 'expected', 'tmp/_site', siteIgnoredFiles);
+    compare(sitePath, 'expected', 'tmp/_site', siteIgnoredFiles, GENERATED_DIRECTORIES_TO_IGNORE);
   } catch (err) {
     if (_.isError(err)) {
       printFailedMessage(err, sitePath);
@@ -141,7 +144,7 @@ function testEmptyDirectoryBuild() {
     } catch (err) {
       // Verify that test_empty directory remains empty using compare()
       try {
-        compare(siteRootName, 'expected', 'empty_dir', [], true);
+        compare(siteRootName, 'expected', 'empty_dir', [], [], true);
       } catch (compareErr) {
         if (_.isError(compareErr)) {
           printFailedMessage(compareErr, siteRootName);

packages/cli/test/functional/testUtil/compare.ts

@@ -13,6 +13,11 @@ const TEST_BLACKLIST = ignore().add([
   '*.log',
   '*.woff',
   '*.woff2',
+  '*.pf_fragment',
+  '*.pf_index',
+  '*.pf_meta',
+  '*.wasm.pagefind',
+  'wasm.unknown.pagefind',
 ]);
 
 const CRLF_REGEX = /\r\n/g;
@@ -54,10 +59,12 @@ function getDirectoryStructure(dirPath: string) {
  * @param {string} expectedSiteRelativePath - Relative path to expected site output (default: "expected")
  * @param {string} siteRelativePath - Relative path to actual generated site output (default: "_site")
  * @param {string[]} ignoredPaths - Specify any paths to ignore for comparison, but still check for existence.
+ * @param {string[]} ignoredDirectories - Specify any directories to ignore for comparison (e.g. 'pagefind')
  * @param {boolean} compareDirectories - Whether to compare directory structures (default: false)
  */
 function compare(root: string, expectedSiteRelativePath = 'expected', siteRelativePath = '_site',
-                 ignoredPaths: string[] = [], compareDirectories = false) {
+                 ignoredPaths: string[] = [], ignoredDirectories: string[] = [],
+                 compareDirectories = false) {
   const expectedDirectory = path.join(root, expectedSiteRelativePath);
   const actualDirectory = path.join(root, siteRelativePath);
 
@@ -73,8 +80,9 @@ function compare(root: string, expectedSiteRelativePath = 'expected', siteRelati
     }
   }
 
-  let expectedPaths = walkSync(expectedDirectory, { directories: false });
-  let actualPaths = walkSync(actualDirectory, { directories: false });
+  const walkSyncOptions = { directories: false, ignore: ignoredDirectories };
+  let expectedPaths = walkSync(expectedDirectory, walkSyncOptions);
+  let actualPaths = walkSync(actualDirectory, walkSyncOptions);
 
   // Vue render JS files (*.page-vue-render.js) are not committed to version control,
   // so we exclude them from the comparison to avoid false positive diffs.

packages/cli/test/functional/test_site/expected/bugs/index.html

@@ -16,6 +16,7 @@
   <link rel="stylesheet" href="/test_site/markbind/glyphicons/css/bootstrap-glyphicons.min.css">
   <link rel="stylesheet" href="/test_site/markbind/css/codeblock-dark.min.css">
   <link rel="stylesheet" href="/test_site/markbind/css/markbind.min.css">
+  <link rel="stylesheet" href="/test_site/markbind/pagefind/pagefind-ui.css">
   <link rel="stylesheet" href="/test_site/plugins/testMarkbindPlugin/testMarkbindPluginStylesheet.css">
   <link rel="stylesheet" href="/test_site/plugins/web3Form/web-3-form.css">
   <link rel="stylesheet" href="/test_site/plugins/markbind-plugin-anchors/markbind-plugin-anchors.css">
@@ -359,5 +360,6 @@ <h1 id="heading-in-footer-should-not-be-indexed">Heading in footer should not be
     });
 
   </script>
+<script src="/test_site/markbind/pagefind/pagefind-ui.js"></script>
 
 </html>

packages/cli/test/functional/test_site/expected/index.html

@@ -16,6 +16,7 @@
   <link rel="stylesheet" href="/test_site/markbind/glyphicons/css/bootstrap-glyphicons.min.css">
   <link rel="stylesheet" href="/test_site/markbind/css/codeblock-dark.min.css">
   <link rel="stylesheet" href="/test_site/markbind/css/markbind.min.css">
+  <link rel="stylesheet" href="/test_site/markbind/pagefind/pagefind-ui.css">
   <link rel="stylesheet" href="/test_site/plugins/testMarkbindPlugin/testMarkbindPluginStylesheet.css">
   <link rel="stylesheet" href="/test_site/plugins/web3Form/web-3-form.css">
   <link rel="stylesheet" href="/test_site/plugins/markbind-plugin-anchors/markbind-plugin-anchors.css">
@@ -1025,5 +1026,6 @@ <h1 id="heading-in-footer-should-not-be-indexed">Heading in footer should not be
     });
 
   </script>
+<script src="/test_site/markbind/pagefind/pagefind-ui.js"></script>
 
 </html>