From 38238c7bcc73bc3d9810da31a0c7bf11d7064a17 Mon Sep 17 00:00:00 2001
From: Tim McMackin <timothymcmackin@users.noreply.github.com>
Date: Mon, 15 Jan 2024 09:34:49 -0500
Subject: [PATCH] Enable contextual search (#261)

* Enable contextual search

* Test credentials from algolia

* Test credentials from algolia and use them

* Revert "Test credentials from algolia and use them"

This reverts commit 38ddaaf863e0608bca269e28871dbc2ba2bf9dde.

* Revert "Test credentials from algolia"

This reverts commit a77cafb5c3df145a502e6f80350a0f230d93f26a.

* Search information in README
---
 README.md            | 118 +++++++++++++++++++++++++++++++++++++++++++
 docusaurus.config.js |   2 +-
 2 files changed, 119 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 83e84b252..f8c25d343 100644
--- a/README.md
+++ b/README.md
@@ -44,6 +44,124 @@ To run tests locally, run `npm run test -- --filesToCheck=docs/developing.md,doc
 
 Docusaurus automatically checks for broken links and markdown-encoded images when you run `npm run build`.
 
+## Search
+
+Search on the site is powered by Algolia Docsearch.
+The index is in the [Algolia dashboard](https://dashboard.algolia.com/apps/QRIAHGML9Q/dashboard).
+Contextual search is enabled according to the [Docusaurus instructions](https://docusaurus.io/docs/search#using-algolia-docsearch), although the site does not currently use contextual search to separate searches by version, language, or other similar factors.
+
+The search uses [this crawler](https://crawler.algolia.com/admin/crawlers/eaa2c548-8b82-493b-8ab8-0c37e2e5d5cc/configuration/edit) to index the site:
+
+```js
+new Crawler({
+  rateLimit: 8,
+  maxDepth: 10,
+  maxUrls: 5000,
+  startUrls: ["https://docs.tezos.com/"],
+  sitemaps: ["https://docs.tezos.com/sitemap.xml"],
+  renderJavaScript: false,
+  ignoreCanonicalTo: true,
+  ignoreQueryParams: ["source", "utm_*"],
+  discoveryPatterns: ["https://docs.tezos.com/**"],
+  schedule: "every 24 hours",
+  appId: "QRIAHGML9Q",
+  apiKey: "API_KEY_GOES_HERE",
+  actions: [
+    {
+      indexName: "tezosdocs",
+      pathsToMatch: ["https://docs.tezos.com/**"],
+      recordExtractor: ({ $, helpers }) => {
+        // priority order: deepest active sub list header -> navbar active item -> 'Documentation'
+        const lvl0 =
+          $(
+            ".menu__link.menu__link--sublist.menu__link--active, .navbar__item.navbar__link--active",
+          )
+            .last()
+            .text() || "Documentation";
+
+        return helpers.docsearch({
+          recordProps: {
+            lvl0: {
+              selectors: "",
+              defaultValue: lvl0,
+            },
+            lvl1: ["header h1", "article h1"],
+            lvl2: "article h2",
+            lvl3: "article h3",
+            lvl4: "article h4",
+            lvl5: "article h5, article td:first-child",
+            lvl6: "article h6",
+            content: "article p, article li, article td:last-child",
+          },
+          indexHeadings: true,
+          aggregateContent: true,
+          recordVersion: "v3",
+        });
+      },
+    },
+  ],
+  initialIndexSettings: {
+    tezosdocs: {
+      attributesForFaceting: [
+        "type",
+        "lang",
+        "language",
+        "version",
+        "docusaurus_tag",
+      ],
+      attributesToRetrieve: [
+        "hierarchy",
+        "content",
+        "anchor",
+        "url",
+        "url_without_anchor",
+        "type",
+      ],
+      attributesToHighlight: ["hierarchy", "content"],
+      attributesToSnippet: ["content:10"],
+      camelCaseAttributes: ["hierarchy", "content"],
+      searchableAttributes: [
+        "unordered(hierarchy.lvl0)",
+        "unordered(hierarchy.lvl1)",
+        "unordered(hierarchy.lvl2)",
+        "unordered(hierarchy.lvl3)",
+        "unordered(hierarchy.lvl4)",
+        "unordered(hierarchy.lvl5)",
+        "unordered(hierarchy.lvl6)",
+        "content",
+      ],
+      distinct: true,
+      attributeForDistinct: "url",
+      customRanking: [
+        "desc(weight.pageRank)",
+        "desc(weight.level)",
+        "asc(weight.position)",
+      ],
+      ranking: [
+        "words",
+        "filters",
+        "typo",
+        "attribute",
+        "proximity",
+        "exact",
+        "custom",
+      ],
+      highlightPreTag: '<span class="algolia-docsearch-suggestion--highlight">',
+      highlightPostTag: "</span>",
+      minWordSizefor1Typo: 3,
+      minWordSizefor2Typos: 7,
+      allowTyposOnNumericTokens: false,
+      minProximity: 1,
+      ignorePlurals: true,
+      advancedSyntax: true,
+      attributeCriteriaComputedByMinProximity: true,
+      removeWordsIfNoResults: "allOptional",
+      separatorsToIndex: "_",
+    },
+  },
+});
+```
+
 ## License
 
 This project is open for contribution but the source code itself uses a commercial template and is therefore not licensed under any open-source license. Forking this project as a base for your own projects is not permitted under the license of the original template.
diff --git a/docusaurus.config.js b/docusaurus.config.js
index 656a77851..b6195480e 100644
--- a/docusaurus.config.js
+++ b/docusaurus.config.js
@@ -142,7 +142,7 @@ const config = {
         apiKey: process.env.NEXT_PUBLIC_DOCSEARCH_API_KEY || "57d6a376a3528866784a143809cc7427",
         indexName: process.env.NEXT_PUBLIC_DOCSEARCH_INDEX_NAME || "tezosdocs",
         // Optional: see doc section below
-        contextualSearch: false,
+        contextualSearch: true,
         // Optional: Specify domains where the navigation should occur through window.location instead on history.push. Useful when our Algolia config crawls multiple documentation sites and we want to navigate with window.location.href to them.
         // externalUrlRegex: 'external\\.com|domain\\.com',
         // Optional: Replace parts of the item URLs from Algolia. Useful when using the same search index for multiple deployments using a different baseUrl. You can use regexp or string in the `from` param. For example: localhost:3000 vs myCompany.com/docs