Build: Add typesense job

qunitjs · May 8, 2023 · 52730b1 · 52730b1
1 parent a0c8775
commit 52730b1
Show file tree

Hide file tree

Showing 2 changed files with 89 additions and 0 deletions.
diff --git a/.github/workflows/typesense.yaml b/.github/workflows/typesense.yaml
@@ -0,0 +1,29 @@
+name: typesense
+on:
+  # Once a week on Wednesday at 11:45 UTC <https://crontab.guru/>
+  schedule:
+    - cron: '45 11 * * 3'
+  # Or after a deployment
+  push:
+    branches:
+      - main
+      - typesense
+  # Or manually
+  workflow_dispatch:
+jobs:
+  typesense:
+    name: Update Typesense
+    if: ${{ github.repository_owner == 'qunitjs' }} # skip on forks
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Docsearch Scraper
+        shell: bash
+        run: |
+          docker run \
+            -e TYPESENSE_API_KEY=${{ secrets.TYPESENSE_ADMIN_KEY }} \
+            -e TYPESENSE_HOST="${{ secrets.TYPESENSE_HOST }}" \
+            -e TYPESENSE_PORT="443" \
+            -e TYPESENSE_PROTOCOL="https" \
+            -e CONFIG="$(cat docsearch.config.json | jq -r tostring)" \
+            typesense/docsearch-scraper:0.6.0.rc2
diff --git a/docsearch.config.json b/docsearch.config.json
@@ -0,0 +1,60 @@
+{
+  "index_name": "amethyst_demo",
+  "start_urls": [
+    { "url": "https://qunitjs.github.io/jekyll-theme-amethyst/api/", "selectors_key": "api", "page_rank": 20 },
+    { "url": "https://qunitjs.github.io/jekyll-theme-amethyst/\\d{4}/", "selectors_key": "blog", "page_rank": 1 },
+    { "url": "https://qunitjs.github.io/jekyll-theme-amethyst/", "page_rank": 10 }
+  ],
+  "stop_content": [
+    "<meta name=\"docsearch:amethyst_pagetype_navigation\""
+  ],
+  "selectors": {
+    "default": {
+      "lvl0": "h1",
+      "lvl1": "h2",
+      "lvl2": "h3",
+      "lvl3": "h4",
+      "lvl4": "h5",
+      "lvl5": "h6",
+      "text": ".content p, .content li"
+    },
+    "api": {
+      "lvl0": {
+        "// selector": "This is like qSA('p.post-meta .category')[0], match the first category only",
+        "selector": "//article//p[contains(@class,'post-meta')]//*[contains(@class,'category')][1]",
+        "type": "xpath",
+        "global": true,
+        "default_value": "Documentation"
+      },
+      "lvl1": "h1",
+      "lvl2": "h2:not(.screen-reader-text)",
+      "lvl3": "h3:not(.screen-reader-text)",
+      "lvl4": "h4:not(.screen-reader-text)",
+      "lvl5": "h5:not(.screen-reader-text)",
+      "text": ".content p, .content li, .content tr, .content pre"
+    },
+    "blog": {
+      "lvl0": {
+        "selector": "",
+        "global": true,
+        "default_value": "Blog"
+      },
+      "lvl1": "h1",
+      "lvl2": "h2",
+      "lvl3": "h3",
+      "lvl4": "h4",
+      "lvl5": "h5",
+      "text": ".content p, .content li"
+    }
+  },
+  "custom_settings": {
+    "token_separators": ["_", "-", "."]
+  },
+  "selectors_exclude": [
+    "aside.sidebar",
+    ".toc-wrapper"
+  ],
+  "min_indexed_level": 1,
+  "scrape_start_urls": false
+}
+