@docusaurus/core 0.0.0-5811 → 0.0.0-5813

package/lib/server/brokenLinks.js

@@ -13,21 +13,38 @@ const logger_1 = tslib_1.__importDefault(require("@docusaurus/logger"));
 const react_router_config_1 = require("react-router-config");
 const utils_1 = require("@docusaurus/utils");
 const utils_2 = require("./utils");
-function getBrokenLinksForPage({ collectedLinks, pagePath, pageLinks, routes, }) {
-    const allCollectedPaths = new Set(Object.keys(collectedLinks));
+function matchRoutes(routeConfig, pathname) {
+    // @ts-expect-error: React router types RouteConfig with an actual React
+    // component, but we load route components with string paths.
+    // We don't actually access component here, so it's fine.
+    return (0, react_router_config_1.matchRoutes)(routeConfig, pathname);
+}
+function createBrokenLinksHelper({ collectedLinks, routes, }) {
+    const validPathnames = new Set(collectedLinks.keys());
+    // Matching against the route array can be expensive
+    // If the route is already in the valid pathnames,
+    // we can avoid matching against it as an optimization
+    const remainingRoutes = routes.filter((route) => !validPathnames.has(route.path));
+    function isPathnameMatchingAnyRoute(pathname) {
+        if (matchRoutes(remainingRoutes, pathname).length > 0) {
+            // IMPORTANT: this is an optimization here
+            // See https://github.com/facebook/docusaurus/issues/9754
+            // Large Docusaurus sites have many routes!
+            // We try to minimize calls to a possibly expensive matchRoutes function
+            validPathnames.add(pathname);
+            return true;
+        }
+        return false;
+    }
     function isPathBrokenLink(linkPath) {
         const pathnames = [linkPath.pathname, decodeURI(linkPath.pathname)];
-        const matchedRoutes = pathnames
-            // @ts-expect-error: React router types RouteConfig with an actual React
-            // component, but we load route components with string paths.
-            // We don't actually access component here, so it's fine.
-            .map((l) => (0, react_router_config_1.matchRoutes)(routes, l))
-            .flat();
-        // The link path is broken if:
-        // - it doesn't match any route
-        // - it doesn't match any collected path
-        return (matchedRoutes.length === 0 &&
-            !pathnames.some((p) => allCollectedPaths.has(p)));
+        if (pathnames.some((p) => validPathnames.has(p))) {
+            return false;
+        }
+        if (pathnames.some(isPathnameMatchingAnyRoute)) {
+            return false;
+        }
+        return true;
     }
     function isAnchorBrokenLink(linkPath) {
         const { pathname, hash } = linkPath;
@@ -41,38 +58,44 @@ function getBrokenLinksForPage({ collectedLinks, pagePath, pageLinks, routes, })
         if (hash === '') {
             return false;
         }
-        const targetPage = collectedLinks[pathname] || collectedLinks[decodeURI(pathname)];
+        const targetPage = collectedLinks.get(pathname) || collectedLinks.get(decodeURI(pathname));
         // link with anchor to a page that does not exist (or did not collect any
         // link/anchor) is considered as a broken anchor
         if (!targetPage) {
             return true;
         }
-        // it's a broken anchor if the target page exists
-        // but the anchor does not exist on that page
-        const hashes = [hash, decodeURIComponent(hash)];
-        return !targetPage.anchors.some((anchor) => hashes.includes(anchor));
+        // it's a not broken anchor if the anchor exists on the target page
+        if (targetPage.anchors.has(hash) ||
+            targetPage.anchors.has(decodeURIComponent(hash))) {
+            return false;
+        }
+        return true;
     }
-    const brokenLinks = pageLinks.flatMap((link) => {
+    return {
+        collectedLinks,
+        isPathBrokenLink,
+        isAnchorBrokenLink,
+    };
+}
+function getBrokenLinksForPage({ pagePath, helper, }) {
+    const pageData = helper.collectedLinks.get(pagePath);
+    const brokenLinks = [];
+    pageData.links.forEach((link) => {
         const linkPath = (0, utils_1.parseURLPath)(link, pagePath);
-        if (isPathBrokenLink(linkPath)) {
-            return [
-                {
-                    link,
-                    resolvedLink: (0, utils_1.serializeURLPath)(linkPath),
-                    anchor: false,
-                },
-            ];
+        if (helper.isPathBrokenLink(linkPath)) {
+            brokenLinks.push({
+                link,
+                resolvedLink: (0, utils_1.serializeURLPath)(linkPath),
+                anchor: false,
+            });
         }
-        if (isAnchorBrokenLink(linkPath)) {
-            return [
-                {
-                    link,
-                    resolvedLink: (0, utils_1.serializeURLPath)(linkPath),
-                    anchor: true,
-                },
-            ];
+        else if (helper.isAnchorBrokenLink(linkPath)) {
+            brokenLinks.push({
+                link,
+                resolvedLink: (0, utils_1.serializeURLPath)(linkPath),
+                anchor: true,
+            });
         }
-        return [];
     });
     return brokenLinks;
 }
@@ -88,14 +111,16 @@ function filterIntermediateRoutes(routesInput) {
 }
 function getBrokenLinks({ collectedLinks, routes, }) {
     const filteredRoutes = filterIntermediateRoutes(routes);
-    return lodash_1.default.mapValues(collectedLinks, (pageCollectedData, pagePath) => {
+    const helper = createBrokenLinksHelper({
+        collectedLinks,
+        routes: filteredRoutes,
+    });
+    const result = {};
+    collectedLinks.forEach((_unused, pagePath) => {
         try {
-            return getBrokenLinksForPage({
-                collectedLinks,
-                pageLinks: pageCollectedData.links,
-                pageAnchors: pageCollectedData.anchors,
+            result[pagePath] = getBrokenLinksForPage({
                 pagePath,
-                routes: filteredRoutes,
+                helper,
             });
         }
         catch (e) {
@@ -104,6 +129,7 @@ function getBrokenLinks({ collectedLinks, routes, }) {
             });
         }
     });
+    return result;
 }
 function brokenLinkMessage(brokenLink) {
     const showResolvedLink = brokenLink.link !== brokenLink.resolvedLink;
@@ -204,13 +230,18 @@ function reportBrokenLinks({ brokenLinks, onBrokenLinks, onBrokenAnchors, }) {
 // JS users might call "collectLink(undefined)" for example
 // TS users might call "collectAnchor('#hash')" with/without #
 // We clean/normalize the collected data to avoid obscure errors being thrown
+// We also use optimized data structures for a faster algorithm
 function normalizeCollectedLinks(collectedLinks) {
-    return lodash_1.default.mapValues(collectedLinks, (pageCollectedData) => ({
-        links: pageCollectedData.links.filter(lodash_1.default.isString),
-        anchors: pageCollectedData.anchors
-            .filter(lodash_1.default.isString)
-            .map((anchor) => (anchor.startsWith('#') ? anchor.slice(1) : anchor)),
-    }));
+    const result = new Map();
+    Object.entries(collectedLinks).forEach(([pathname, pageCollectedData]) => {
+        result.set(pathname, {
+            links: new Set(pageCollectedData.links.filter(lodash_1.default.isString)),
+            anchors: new Set(pageCollectedData.anchors
+                .filter(lodash_1.default.isString)
+                .map((anchor) => (anchor.startsWith('#') ? anchor.slice(1) : anchor))),
+        });
+    });
+    return result;
 }
 async function handleBrokenLinks({ collectedLinks, onBrokenLinks, onBrokenAnchors, routes, }) {
     if (onBrokenLinks === 'ignore' && onBrokenAnchors === 'ignore') {

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@docusaurus/core",
   "description": "Easy to Maintain Open Source Documentation Websites",
-  "version": "0.0.0-5811",
+  "version": "0.0.0-5813",
   "license": "MIT",
   "publishConfig": {
     "access": "public"
@@ -43,13 +43,13 @@
     "@babel/runtime": "^7.22.6",
     "@babel/runtime-corejs3": "^7.22.6",
     "@babel/traverse": "^7.22.8",
-    "@docusaurus/cssnano-preset": "0.0.0-5811",
-    "@docusaurus/logger": "0.0.0-5811",
-    "@docusaurus/mdx-loader": "0.0.0-5811",
+    "@docusaurus/cssnano-preset": "0.0.0-5813",
+    "@docusaurus/logger": "0.0.0-5813",
+    "@docusaurus/mdx-loader": "0.0.0-5813",
     "@docusaurus/react-loadable": "5.5.2",
-    "@docusaurus/utils": "0.0.0-5811",
-    "@docusaurus/utils-common": "0.0.0-5811",
-    "@docusaurus/utils-validation": "0.0.0-5811",
+    "@docusaurus/utils": "0.0.0-5813",
+    "@docusaurus/utils-common": "0.0.0-5813",
+    "@docusaurus/utils-validation": "0.0.0-5813",
     "@slorber/static-site-generator-webpack-plugin": "^4.0.7",
     "@svgr/webpack": "^6.5.1",
     "autoprefixer": "^10.4.14",
@@ -104,8 +104,8 @@
     "webpackbar": "^5.0.2"
   },
   "devDependencies": {
-    "@docusaurus/module-type-aliases": "0.0.0-5811",
-    "@docusaurus/types": "0.0.0-5811",
+    "@docusaurus/module-type-aliases": "0.0.0-5813",
+    "@docusaurus/types": "0.0.0-5813",
     "@types/detect-port": "^1.3.3",
     "@types/react-dom": "^18.2.7",
     "@types/react-router-config": "^5.0.7",
@@ -124,5 +124,5 @@
   "engines": {
     "node": ">=18.0"
   },
-  "gitHead": "06b637e03ce679fa1713ca0e467a354c55f6db5e"
+  "gitHead": "0f04893f7d821f3e0b741017ee7adcac940cba62"
 }