feat: add typesense/docsearch-scraper (#11424)

.github/workflows/docsearch.yml

@@ -0,0 +1,24 @@
+name: Index docs to Typesense
+
+on:
+  push:
+    branches:
+      - master
+
+jobs:
+  index_docs:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Index docs to Typesense
+        run: |
+          docker run \
+            -e TYPESENSE_API_KEY=${{ vars.TYPESENSE_API_KEY }} \
+            -e TYPESENSE_HOST="${{ vars.TYPESENSE_HOST }}" \
+            -e TYPESENSE_PORT="443" \
+            -e TYPESENSE_PROTOCOL="https" \
+            -e CONFIG="$(cat docs/docsearch-scraper-config.json | jq -r tostring)" \
+            typesense/docsearch-scraper

docs/docsearch-scraper-config.json

@@ -0,0 +1,49 @@
+{
+  "index_name": "typeorm-docs",
+  "start_urls": [
+    "https://typeorm.io/"
+  ],
+  "sitemap_urls": [
+    "https://typeorm.io/sitemap.xml"
+  ],
+  "allowed_domains":["typeorm.io"],
+  "sitemap_alternate_links": true,
+  "stop_urls": [],
+  "selectors": {
+    "lvl0": {
+      "selector": "(//ul[contains(@class,'menu__list')]//a[contains(@class, 'menu__link menu__link--sublist menu__link--active')]/text() | //nav[contains(@class, 'navbar')]//a[contains(@class, 'navbar__link--active')]/text())[last()]",
+      "type": "xpath",
+      "global": true,
+      "default_value": "Documentation"
+    },
+    "lvl1": "article h1, header h1",
+    "lvl2": "article h2",
+    "lvl3": "article h3",
+    "lvl4": "article h4",
+    "lvl5": "article h5, article td:first-child",
+    "lvl6": "article h6",
+    "text": "article p, article li, article td:last-child"
+  },
+  "strip_chars": " .,;:#",
+  "custom_settings": {
+    "separatorsToIndex": "_",
+    "attributesForFaceting": [
+      "language",
+      "version",
+      "type",
+      "docusaurus_tag"
+    ],
+    "attributesToRetrieve": [
+      "hierarchy",
+      "content",
+      "anchor",
+      "url",
+      "url_without_anchor",
+      "type"
+    ]
+  },
+  "conversation_id": [
+    "833762294"
+  ],
+  "nb_hits": 0
+}