fix #1067

- add framework for custom content into
  Lunr indices
- update docs for this feature

assets/js/just-the-docs.js

@@ -87,6 +87,7 @@ function initSearch() {
         this.metadataWhitelist = ['position']
 
         for (var i in docs) {
+          {% include lunr/custom-index.js %}
           this.add({
             id: i,
             title: docs[i].title,

assets/js/zzzz-search-data.json

@@ -51,6 +51,7 @@ permalink: /assets/js/search-data.json
     "title": {{ title | jsonify }},
     "content": {{ content | replace: '</h', ' . </h' | replace: '<hr', ' . <hr' | replace: '</p', ' . </p' | replace: '<ul', ' . <ul' | replace: '</ul', ' . </ul' | replace: '<ol', ' . <ol' | replace: '</ol', ' . </ol' | replace: '</tr', ' . </tr' | replace: '<li', ' | <li' | replace: '</li', ' | </li' | replace: '</td', ' | </td' | replace: '<td', ' | <td' | replace: '</th', ' | </th' | replace: '<th', ' | <th' | strip_html | remove: 'Table of contents' | normalize_whitespace | replace: '. . .', '.' | replace: '. .', '.' | replace: '| |', '|' | append: ' ' | jsonify }},
     "url": "{{ url | relative_url }}",
+    {% include lunr/custom-data.json page=page %}
     "relUrl": "{{ url }}"
   }
         {%- assign i = i | plus: 1 -%}
@@ -62,6 +63,7 @@ permalink: /assets/js/search-data.json
     "title": {{ page.title | jsonify }},
     "content": {{ parts[0] | replace: '</h', ' . </h' | replace: '<hr', ' . <hr' | replace: '</p', ' . </p' | replace: '<ul', ' . <ul' | replace: '</ul', ' . </ul' | replace: '<ol', ' . <ol' | replace: '</ol', ' . </ol' | replace: '</tr', ' . </tr' | replace: '<li', ' | <li' | replace: '</li', ' | </li' | replace: '</td', ' | </td' | replace: '<td', ' | <td' | replace: '</th', ' | </th' | replace: '<th', ' | <th' | strip_html | remove: 'Table of contents' | normalize_whitespace | replace: '. . .', '.' | replace: '. .', '.' | replace: '| |', '|' | append: ' ' | jsonify }},
     "url": "{{ page.url | relative_url }}",
+    {% include lunr/custom-data.json page=page %}
     "relUrl": "{{ page.url }}"
   }
         {%- assign i = i | plus: 1 -%}

docs/search.md

@@ -125,3 +125,42 @@ $ bundle exec just-the-docs rake search:init
 
 This command creates the `assets/js/zzzz-search-data.json` file that Jekyll uses to create your search index.
 Alternatively, you can create the file manually with [this content]({{ site.github.repository_url }}/blob/main/assets/js/zzzz-search-data.json).
+
+## Custom content for search index
+
+The standard text that is indexed is the page (or post) `.content`, `.title`, and sometimes headers which are already in the `.content`. Other text (Front Matter, data files, etc.) is not indexed. When you want additional text to be indexed, you can customize Just the Docs.
+
+{: .warning }
+> Customizing search indices is an advanced feature that requires Javascript and Liquid knowledge.
+
+1. When your site used a previous version of Just the Docs, you must update the file
+   `assets/js/zzzz-search-data.json` using the [above methods](#generate-search-index-when-used-as-a-gem).
+2. Add a new file named `_includes/lunr/custom-data.json` to your site. Insert your custom Liquid
+   code that reads the page object at `include.page` then generates custom Javascript
+   fields that hold the custom text you want to index. You can verify the fields you output at
+   the generated `assets/js/search-data.json`.
+3. Add a new file named `_includes/lunr/custom-index.js` to your site. Insert your custom Javascript
+   code that reads your custom Javascript fields and inserts them into the search index.
+
+#### Example
+
+`_includes/lunr/custom-data.json` custom code reads the page's custom Front Matter `usage` and `examples`
+fields, normalizes the text, and writes the text to custom Javascript `myusage` and `myexamples` fields.
+
+{% raw %}
+```liquid
+{%- capture newline %}
+{% endcapture -%}
+"myusage": {{ include.page.usage | markdownify | replace:newline,' ' | strip_html | normalize_whitespace | strip | jsonify }},
+"myexamples": {{ include.page.examples | markdownify | replace:newline,' ' | strip_html | normalize_whitespace | strip | jsonify }},
+```
+{% endraw %}
+
+`_includes/lunr/custom-index.js` custom code is within a Javascript loop. All custom
+Javascript fields are accessed as fields of `docs[i]` such as `docs[i].myusage`.
+Finally, append your custom fields on to the already existing `docs[i].content`.
+
+```javascript
+const content_to_merge = [docs[i].content, docs[i].myusage, docs[i].myexamples];
+docs[i].content = content_to_merge.join(' ');
+```

lib/tasks/search.rake

@@ -61,6 +61,7 @@ permalink: /assets/js/search-data.json
     "title": {{ title | jsonify }},
     "content": {{ content | replace: \'</h\', \' . </h\' | replace: \'<hr\', \' . <hr\' | replace: \'</p\', \' . </p\' | replace: \'<ul\', \' . <ul\' | replace: \'</ul\', \' . </ul\' | replace: \'<ol\', \' . <ol\' | replace: \'</ol\', \' . </ol\' | replace: \'</tr\', \' . </tr\' | replace: \'<li\', \' | <li\' | replace: \'</li\', \' | </li\' | replace: \'</td\', \' | </td\' | replace: \'<td\', \' | <td\' | replace: \'</th\', \' | </th\' | replace: \'<th\', \' | <th\' | strip_html | remove: \'Table of contents\' | normalize_whitespace | replace: \'. . .\', \'.\' | replace: \'. .\', \'.\' | replace: \'| |\', \'|\' | append: \' \' | jsonify }},
     "url": "{{ url | relative_url }}",
+    {% include lunr/custom-data.json page=page %}
     "relUrl": "{{ url }}"
   }
         {%- assign i = i | plus: 1 -%}
@@ -72,6 +73,7 @@ permalink: /assets/js/search-data.json
     "title": {{ page.title | jsonify }},
     "content": {{ parts[0] | replace: \'</h\', \' . </h\' | replace: \'<hr\', \' . <hr\' | replace: \'</p\', \' . </p\' | replace: \'<ul\', \' . <ul\' | replace: \'</ul\', \' . </ul\' | replace: \'<ol\', \' . <ol\' | replace: \'</ol\', \' . </ol\' | replace: \'</tr\', \' . </tr\' | replace: \'<li\', \' | <li\' | replace: \'</li\', \' | </li\' | replace: \'</td\', \' | </td\' | replace: \'<td\', \' | <td\' | replace: \'</th\', \' | </th\' | replace: \'<th\', \' | <th\' | strip_html | remove: \'Table of contents\' | normalize_whitespace | replace: \'. . .\', \'.\' | replace: \'. .\', \'.\' | replace: \'| |\', \'|\' | append: \' \' | jsonify }},
     "url": "{{ page.url | relative_url }}",
+    {% include lunr/custom-data.json page=page %}
     "relUrl": "{{ page.url }}"
   }
         {%- assign i = i | plus: 1 -%}