docs: add algolia crawler config (closes #2592)

pull/2663/head
Divyansh Singh 1 year ago
parent ad7ab9cb8e
commit 5a340bf1e5

@ -78,13 +78,17 @@ export default defineConfig({
/**
* @type {Pick<import('minisearch').Options, 'extractField' | 'tokenize' | 'processTerm'>}
*/
options: { /* ... */ },
options: {
/* ... */
},
/**
* @type {import('minisearch').SearchOptions}
* @default
* { fuzzy: 0.2, prefix: true, boost: { title: 4, text: 2, titles: 1 } }
*/
searchOptions: { /* ... */ }
searchOptions: {
/* ... */
}
}
}
}
@ -181,6 +185,114 @@ export default defineConfig({
[These options](https://github.com/vuejs/vitepress/blob/main/types/docsearch.d.ts) can be overridden. Refer official Algolia docs to learn more about them.
### Crawler Config
Here is an example config based on what this site uses:
```ts
new Crawler({
appId: '...',
apiKey: '...',
rateLimit: 8,
startUrls: ['https://vitepress.dev/'],
renderJavaScript: false,
sitemaps: [],
exclusionPatterns: [],
ignoreCanonicalTo: false,
discoveryPatterns: ['https://vitepress.dev/**'],
schedule: 'at 05:10 on Saturday',
actions: [
{
indexName: 'vitepress',
pathsToMatch: ['https://vitepress.dev/**'],
recordExtractor: ({ $, helpers }) => {
return helpers.docsearch({
recordProps: {
lvl1: '.content h1',
content: '.content p, .content li',
lvl0: {
selectors: '',
defaultValue: 'Documentation'
},
lvl2: '.content h2',
lvl3: '.content h3',
lvl4: '.content h4',
lvl5: '.content h5'
},
indexHeadings: true
})
}
}
],
initialIndexSettings: {
vitepress: {
attributesForFaceting: ['type', 'lang'],
attributesToRetrieve: ['hierarchy', 'content', 'anchor', 'url'],
attributesToHighlight: ['hierarchy', 'hierarchy_camel', 'content'],
attributesToSnippet: ['content:10'],
camelCaseAttributes: ['hierarchy', 'hierarchy_radio', 'content'],
searchableAttributes: [
'unordered(hierarchy_radio_camel.lvl0)',
'unordered(hierarchy_radio.lvl0)',
'unordered(hierarchy_radio_camel.lvl1)',
'unordered(hierarchy_radio.lvl1)',
'unordered(hierarchy_radio_camel.lvl2)',
'unordered(hierarchy_radio.lvl2)',
'unordered(hierarchy_radio_camel.lvl3)',
'unordered(hierarchy_radio.lvl3)',
'unordered(hierarchy_radio_camel.lvl4)',
'unordered(hierarchy_radio.lvl4)',
'unordered(hierarchy_radio_camel.lvl5)',
'unordered(hierarchy_radio.lvl5)',
'unordered(hierarchy_radio_camel.lvl6)',
'unordered(hierarchy_radio.lvl6)',
'unordered(hierarchy_camel.lvl0)',
'unordered(hierarchy.lvl0)',
'unordered(hierarchy_camel.lvl1)',
'unordered(hierarchy.lvl1)',
'unordered(hierarchy_camel.lvl2)',
'unordered(hierarchy.lvl2)',
'unordered(hierarchy_camel.lvl3)',
'unordered(hierarchy.lvl3)',
'unordered(hierarchy_camel.lvl4)',
'unordered(hierarchy.lvl4)',
'unordered(hierarchy_camel.lvl5)',
'unordered(hierarchy.lvl5)',
'unordered(hierarchy_camel.lvl6)',
'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'
}
}
})
```
<style>
img[src="/search.png"] {
width: 100%;

Loading…
Cancel
Save