typesense-scraper workflow job

.github/workflows/publish-docs-index-typesense.yml

@@ -0,0 +1,26 @@
+name: "Publish : Docs search index (Typesense)"
+
+on:
+  # Triggered manually
+  workflow_dispatch:
+    
+jobs:
+  doc-indexer:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v3   # You MUST checkout your repository first!
+
+      - name: Run DocSearch Scraper
+        uses: ./packages/noco-docs
+        with:
+          # The secret containing your Typesense API key. Required.
+          api-key: ${{ secrets.TYPESENSE_API_KEY }}      
+          # The hostname or IP address of your Typesense server. Required.
+          host: ${{ secrets.TYPESENSE_HOST }}      
+          # The port on which your Typesense server is listening. Optional. Default: 8108.
+          port: 443      
+          # The protocol to use when connecting to your Typesense server. Optional. Default: http.
+          protocol: https      
+          # The path to your DocSearch config file. Optional. Default: docsearch.config.json.
+          config: typesense-scrape-config.json

packages/noco-docs/typesense-scrape-config.json

@@ -0,0 +1,50 @@
+{
+    "index_name": "nocodb-oss-docs-index",
+    "start_urls": [
+      "https://docs.nocodb.com/"
+    ],
+    "sitemap_urls": [
+      "https://docs.nocodb.com/sitemap.xml"
+    ],
+    "sitemap_alternate_links": true,
+    "stop_urls": [
+      "/tests"
+    ],
+    "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": "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": 46250
+  }