From 0de8d9a7e22f9d7a240ed9ecf69998499cd7d005 Mon Sep 17 00:00:00 2001
From: Kenneth Bingham <kenneth.bingham@netfoundry.io>
Date: Tue, 14 Feb 2023 15:23:46 -0500
Subject: [PATCH] commit algolia crawler config for reference

---
 website/algolia-crawler-config.js | 104 ++++++++++++++++++++++++++++++
 1 file changed, 104 insertions(+)
 create mode 100644 website/algolia-crawler-config.js

diff --git a/website/algolia-crawler-config.js b/website/algolia-crawler-config.js
new file mode 100644
index 00000000..799c3679
--- /dev/null
+++ b/website/algolia-crawler-config.js
@@ -0,0 +1,104 @@
+// this is not part of the Docusaurus site, but a copy of the active config in the Algolia Crawler
+new Crawler({
+  appId: 'CO73R59OLO',
+  apiKey: 'ALGOLIA_CRAWLER_API_KEY',
+  rateLimit: 8,
+  maxDepth: 10,
+  startUrls: ['https://docs.zrok.io/'],
+  sitemaps: ['https://docs.zrok.io/sitemap.xml'],
+  ignoreCanonicalTo: true,
+  discoveryPatterns: ['https://docs.zrok.io/**'],
+  actions: [
+    {
+      indexName: 'zrok',
+      pathsToMatch: ['https://docs.zrok.io/**'],
+      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: {
+    zrok: {
+      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: '_',
+    },
+  },
+});
\ No newline at end of file