nikon/docsearch
1
0
Fork 0
Code Activity Actions

Lint for misspelling

Browse source
This commit is contained in:
Pixelastic 2018-08-24 12:36:11 +02:00
parent dfc12b4b5e
commit 9fa44b531a
12 changed files with 256 additions and 38 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

209
docs/.textlint.terms.json Normal file
View file

@ -0,0 +1,209 @@
[
"3D",
"API",
"Airbnb",
"Ajax",
"Algolia",
"Android",
"BrowserStack",
"Browsersync",
"CSS",
"CodePen",
"CodeSandbox",
"Codecov",
"DocSearch",
"ECMAScript",
"ESLint",
"EditorConfig",
"GIF",
"GitHub",
"GraphQL",
"HTML",
"HTTPS",
"ID",
"InstantSearch",
"IoT",
"I/O",
"JPEG",
"JavaScript",
"JetBrains",
"LinkedIn",
"Lodash",
"MIME",
"MacBook",
"Markdown",
"OK",
"OpenType",
"PDF",
"PNG",
"PaaS",
"SaaS",
"Sass",
"SemVer",
"TypeScript",
"URL",
"UglifyJS",
"WebStorm",
"WordPress",
"YouTube",
"advancedSyntax",
"allowCompressionOfIntegerArray",
"allowTyposOnNumericTokens",
"alternativesAsExact",
"analyticsTags",
"aroundLatLngViaIP",
"aroundLatLng",
"aroundPrecision",
"aroundRadius",
"aroundRadius",
"attributeForDistinct",
"attributesForFaceting",
"attributesToHighlight",
"attributesToRetrieve",
"attributesToSnippet",
"camelCaseAttributes",
"clickAnalytics",
"customRanking",
"decompoundedAttributes",
"disableExactOnAttributes",
"disablePrefixOnAttributes",
"disableTypoToleranceOnAttributes",
"disableTypoToleranceOnWords",
"enableRules",
"exactOnSingleWordQuery",
"e-commerce",
"facetFilters",
"facetingAfterDistinct",
"getRankingInfo",
"highlightPostTag",
"highlightPreTag",
"hitsPerPage",
"iOS",
"ignorePlurals",
"insideBoundingBox",
"insidePolygon",
"jQuery",
"maxFacetHits",
"maxValuesPerFacet",
"minProximity",
"minWordSizefor1Typo",
"minWordSizefor2Typos",
"minimumAroundRadius",
"npm",
"numericAttributesForFiltering",
"numericFilters",
"open source",
"optionalFilters",
"optionalWords",
"pagehitsPerPagepagination",
"paginationLimitedTo",
"percentileComputation",
"queryType",
"removeStopWords",
"removeWordsIfNoResults",
"replaceSynonymsInHighlight",
"responseFields",
"restrictHighlightAndSnippetArrays",
"restrictSearchableAttributes",
"ruleContexts",
"searchableAttributes",
"searchableAttributes",
"separatorsToIndex",
"snippetEllipsisText",
"sortFacetValuesBy",
"sumOrFiltersScores",
"tagFilters",
"typoTolerance",
"unretrievableAttributes",
["3-D", "3D"],
["Aloglia", "Algolia"],
["CLI tool(s?)", "command-line tool$1"],
["HTTP[ /]2(?:\\.0)?", "HTTP/2"],
["I-O", "I/O"],
["JSDocs?", "JSDoc"],
["Mac ?OS", "macOS"],
["Nodejs", "Node.js"],
["OS X", "macOS"],
["React[ .]js", "React"],
["SauceLabs", "Sauce Labs"],
["StackOverflow", "Stack Overflow"],
["an URL", "a URL"],
["auto[- ]complete", "autocomplete"],
["auto[- ]fixing", "autofixing"],
["auto[- ]fix", "autofix"],
["auto[- ]format", "autoformat"],
["a npm", "an npm"],
["backwards compatible", "backward compatible"],
["back[- ]end(\\w*)", "backend$1"],
["bug[- ]fix(es?)", "bugfix$1"],
["build system(s?)", "build tool$1"],
["built ?in", "built-in"],
["check[- ]box(es?)", "checkbox$1"],
["client ?side", "client-side"],
["code-?review(s?)", "code review$1"],
["code-?splitting", "code splitting"],
["code[- ]base(es?)", "codebase$1"],
["command ?line", "command-line"],
["co[- ]locate(d?)", "colocate$1"],
["css-?in-?js", "CSS in JS"],
["datas", "data"],
["ecommerce", "e-commerce"],
["end ?to ?end", "end-to-end"],
["end-?user(s?)", "end user$1"],
["end[- ]point(s?)", "endpoint$1"],
["environemnt(s?)", "environment$1"],
["error ?prone", "error-prone"],
["e commerce", "e-commerce"],
["e[- ]mail(s?)", "email$1"],
["falsey", "falsy"],
["feedbacks", "feedback"],
["file-?type(s?)", "file type$1"],
["file[- ]name(s?)", "filename$1"],
["front[- ]end(\\w*)", "frontend$1"],
["he or she", "they"],
["he/she", "they"],
["higher ?order", "higher-order"],
["host[- ]name(s?)", "hostname$1"],
["hot[- ]key(s?)", "hotkey$1"],
["id(s?)", "ID$1"],
["informations", "information"],
["key[/ ]?value", "key-value"],
["life[- ]cycle", "lifecycle"],
["life[- ]stream(s?)", "lifestream$1"],
["lock[- ]file(s?)", "lockfile$1"],
["mark-up", "markup"],
["meta[- ]data", "metadata"],
["name[- ]space(s?)", "namespace$1"],
["one URLs", "one URL"],
["opensource([\\.,]?)", "open source$1"],
["open-source([\\.,]?)", "open source$1"],
["pacakge(s?)", "package$1"],
["pre[- ]condition(s?)", "precondition$1"],
["pre[- ]defined", "predefined"],
["pre[- ]release(s?)", "prerelease$1"],
["regexp?(s?)", "regular expression$1"],
["repo\\b", "repository"],
["run[- ]time", "runtime"],
["screen[- ]shot(s?)", "screenshot$1"],
["screen[- ]?snap(s?)", "screenshot$1"],
["server ?side", "server-side"],
["slave(s?)", "replica$1"],
["smartphone(s?)", "mobile phone$1"],
["source-?map(s?)", "source map$1"],
["styled ?components", "styled-components"],
["style-?guide(s?)", "style guide$1"],
["style-?sheet(s?)", "style sheet$1"],
["sub[- ]class((?:es|ing)?)", "subclass$1"],
["sub[- ]tree(s?)", "subtree$1"],
["tilda", "tilde"],
["time[- ]stamp(s?)", "timestamp$1"],
["touch[- ]screen(s?)", "touchscreen$1"],
["tree-?shaking", "tree shaking"],
["user-?base", "user base"],
["user[- ]name(s?)", "username$1"],
["walk[- ]through", "walkthrough"],
["web-?page(s?)", "web page$1"],
["white[- ]space", "whitespace"],
["wild[- ]card(s?)", "wildcard$1"],
["wi[- ]?fi", "Wi-Fi"]
]

5
docs/.textlintrc.js
View file

@ -2,6 +2,11 @@
module.exports = {
rules: {
'common-misspellings': true,
'en-capitalization': true,
terminology: {
defaultTerms: false,
terms: `${__dirname}/.textlint.terms.json`,
},
'stop-words': {
exclude: [
'relative to', // We need to talk about links "relative to the root"

8
docs/README.md
View file

@ -32,20 +32,20 @@ to the `gh-pages` branch and push it to GitHub.
## Internals
The documentation generation is not using any existing static websites
generators, but custom javascript scripts.
generators, but custom JavaScript scripts.
The main two entry points are `./scripts/build.js` and `./scripts/serve.js`. The
second one adds a webserver with live-reload on top of the first one.
### HTML
All markdown files situated in `./src` will be transformed into `.html` files in
All Markdown files situated in `./src` will be transformed into `.html` files in
`./dist`. They will be wrapped into the layout defined in their front-matter.
All the headers will be converted to their respective `<hX>` tag, along with
a unique `#id` to allow for easy anchoring.
You can also use plain HTML inside those markdown files if you need more
You can also use plain HTML inside those Markdown files if you need more
advanced styling.
### Layouts
@ -122,7 +122,7 @@ element extracted from the markup of the current page.
### Redirects
The `config.json` file can hold a `redirects` array, with object containing both
a `from` and a `to` key. For each `from`, it will create a plain html page at
a `from` and a `to` key. For each `from`, it will create a plain HTML page at
this location, that will redirect anyone visiting it to the page defined in
`to`.

4
docs/package.json
View file

@ -66,7 +66,9 @@
"tailwindcss": "^0.6.4",
"textlint": "^11.0.0",
"textlint-rule-common-misspellings": "^1.0.1",
"textlint-rule-stop-words": "pixelastic/textlint-rule-stop-words#master"
"textlint-rule-en-capitalization": "^2.0.1",
"textlint-rule-stop-words": "^1.0.4",
"textlint-rule-terminology": "^1.1.29"
},
"peerDependencies": {},
"dependencies": {

20
docs/src/config-file.md
View file

@ -44,7 +44,7 @@ like.
## `start_urls`
This array contains the list of urls that will be used to start crawling your
This array contains the list of URLs that will be used to start crawling your
website. The crawler will recursively follow any links on those pages. It will
not follow links that are on another domain and never follow links defined in `stop_urls`.
@ -85,7 +85,7 @@ have `lang: en` and `version: latest` added to it, allowing you to then filter
based on those values.
The following example shows how you can filter results matching specifics
language and version from the front-end
language and version from the frontend
```js
docsearch({
@ -126,7 +126,7 @@ docsearch({
### Using Page Rank
To give more weight to some pages to boost their ranking in the
results, you can attribute a custom `page_rank` to specific urls. Pages with
results, you can attribute a custom `page_rank` to specific URLs. Pages with
highest `page_rank` will be returned before pages with a lower `page_rank`. Note
that you can pass any numeric value, including negative values.
@ -452,8 +452,8 @@ use it to define which pages to crawl.
### `sitemap_urls` _Optional_
You can pass an array of urls pointing to your sitemap(s) files. If this value
is set, DocSearch will try to read urls from your sitemap(s) instead of
You can pass an array of URLs pointing to your sitemap(s) files. If this value
is set, DocSearch will try to read URLs from your sitemap(s) instead of
following every link of your `starts_urls`.
```json
@ -466,9 +466,9 @@ following every link of your `starts_urls`.
### `sitemap_alternate_links` _Optional_
Sitemaps can contain _alternative links_ for urls. Those are other versions of
the same page, in a different language, or with a different url. By default
DocSearch will ignore those urls.
Sitemaps can contain _alternative links_ for URLs. Those are other versions of
the same page, in a different language, or with a different URL. By default
DocSearch will ignore those URLs.
Set this to `true` if you want those other version to be crawled as well.
@ -504,7 +504,7 @@ encourage you to update your website to enable server-side rendering._
### `js_render` _Optional_
Set this value to true if your website requires client-side rendering. This will
make DocSearch spawn a Selenium proxy to fetch all your webpages.
make DocSearch spawn a Selenium proxy to fetch all your web pages.
```json
{
@ -534,7 +534,7 @@ This option has no impact if `js_render` is set to `false`.
### `use_anchors` _Optional_
Websites using client-side rendering often don't use full urls, but instead take
advantage of the url hash (the part after the `#`).
advantage of the URL hash (the part after the `#`).
If your website is using such urls, you should set `use_anchors` to `true` for
DocSearch to index all your content.

2
docs/src/crawler-overview.md
View file

@ -22,7 +22,7 @@ We run this service entirely free of charge, we're just asking that you keep the
"powered by Algolia" logo next to the search results.
That being said, if you'd like to run DocSearch on your own, [all the code is
open-source][3] and even packaged as a Docker image. Just grab it, and run it
open source][3] and even packaged as a Docker image. Just grab it, and run it
with your own credentials.
[1]: https://scrapy.org/

6
docs/src/faq.md
View file

@ -63,6 +63,7 @@ more complete information in our [privacy policy][6].
The free DocSearch we provide will crawl documentation pages. If you want
to use it on other parts of your website, you'll need to create your own Algolia
account and either:
You need to use the searchableAttributes and attributesForFaceting.
- Run the [DocSearch crawler][7] on your own
- Use one of our other [framework integrations or API clients][8]
@ -72,6 +73,7 @@ account and either:
Yes, but we do not recommend it.
Code samples are a great way for humans to understand how a specific pattern
ap alpha
/ method should be used. It often requires boilerplate code though, repeated
across examples, which will add noise to the results.
@ -81,12 +83,12 @@ content so the method names are actual headers.
### Why do I have duplicate content in my results?
This can happen when you have more than one urls pointing to the same content,
This can happen when you have more than one URL pointing to the same content,
for example with `./docs`, `./docs/` and `./docs/index.html` or even both `http`
and `https` in place.
This can be fixed by `stop_urls` to all the patterns you want to exclude. The
following example will exclude all urls ending with `/` or `index.html` as well
following example will exclude all URLs ending with `/` or `index.html` as well
as those starting with `http://`.
```json

12
docs/src/how-does-it-work.md
View file

@ -5,11 +5,11 @@ title: How does it work?
Getting up and ready with DocSearch is a straightforward process that requires
a three steps: you apply, we configure the crawler for you, and you update your
front-end.
frontend.
<img src="./assets/docsearch-how-it-works.png" alt="How it works" class="mt-2"/>
### 1. You apply
### You apply
The first thing you'll need to do is to apply for DocSearch by filling the
form on this page (make sure to double check that you qualify first). We are
@ -19,19 +19,19 @@ anyone.
We guarantee that we will answer to every request, but we receive a lot
of applications, so please give us a couple of days to get back to you :)
### 2. We create a configuration
### We create a configuration
Once we receive your application, we'll have a look at your website and create
a custom configuration file for it. This file defines which urls we
a custom configuration file for it. This file defines which URLs we
should crawl or ignore, as well as the specific CSS selectors to be used for
selecting headers, subheaders, etc. All configs are publicly available in our
[config repo][1].
[config repository][1].
This step still requires some manual work, but thanks to the 900+ configs we
already created, we're able to automate most of it. Once done, we'll run a first
indexing of your website and have it run automatically every 24h.
### 3. You update your website
### You update your website
We'll then get back to you with the JavaScript snippet you'll need to add to
your website. This will bind your search `input` field to display results from

8
docs/src/run-your-own.md
View file

@ -8,12 +8,12 @@ servers, running every 24 hours. To update your results
more often than that, or to index content sitting behind a
firewall, you might want to run the crawler yourself.
The code of DocSearch is Open-Source, and we packaged it as a Docker
The code of DocSearch is open source, and we packaged it as a Docker
image to make this even easier for you to use.
## Installation
Start by cloning [the repo][1] and then running `./docsearch
Start by cloning [the repository][1] and then running `./docsearch
docker:build` to create the local image.
Even if not recommended, you can run DocSearch directly from you host.
@ -73,7 +73,7 @@ index_name is example [enter to confirm]: <Enter>
=================
```
Copy-paste the content into a file name `example.json`, we'll use it
Copy-paste the content into a filename `example.json`, we'll use it
later to start the crawling. You can find the complete list of
available options in [our documentation][3], or browse the [list of
live configs][4].
@ -123,7 +123,7 @@ docsearch({
You can run `./docsearch` without any argument to see the list of all
available commands.
Note that we use this CLI tool internally at Algolia to run the free
Note that we use this command-line tool internally at Algolia to run the free
hosted version, so you might not need all the listed commands.
[1]: https://github.com/algolia/docsearch-scraper

8
docs/src/styling.md
View file

@ -55,7 +55,7 @@ and you're encouraged to style it to fit your own theming. All we ask is that
you keep the `search by Algolia` logo and link next to your search results.
The logo is automatically added in the dropdown with the default styling. It's
ok to hide it through CSS, as long as you re-add it somewhere else on your page
OK to hide it through CSS, as long as you re-add it somewhere else on your page
close to the search input or search results. It's our way to let more people
know about what do, and how they could also have from fast and relevant search
on their website.
@ -93,9 +93,9 @@ To more heavily style the results, feel free to have a look at the
[SCSS source code][4].
`_variables.scss` contains all the default theming, sizing and breakpoints.
You can generate your own CSS file by cloning the repo and running `yarn run
build:css`. The resulting file will be generated in `./dist/cdn`, and should be
used instead of the default one.
You can generate your own CSS file by cloning the repository and running `yarn
run build:css`. The resulting file will be generated in `./dist/cdn`, and should
be used instead of the default one.
[1]: ./assets/default-colorscheme.png

6
docs/src/what-is-docsearch.md
View file

@ -13,9 +13,9 @@ experience building search interfaces. We wanted to use those skills to help
others. That's why we created a way to automatically extract content from tech
documentation and make it available to everyone with only a few keystrokes.
DocSearch itself is made of a crawler and a front-end library. We run the
DocSearch itself is made of a crawler and a frontend library. We run the
crawler on our end every 24h to extract content from your website and push it to
an Algolia index. You'll then have to add the front-end library to your website
an Algolia index. You'll then have to add the frontend library to your website
to redirect all the search requests to this index.
DocSearch is entirely free and mostly automated. The only thing we'll need from
@ -24,7 +24,7 @@ the JavaScript snippet needed to add DocSearch to your website. We just ask that
you keep the "powered by Algolia" link displayed.
DocSearch is [one of our ways][1] to give back
to the Open-Source community for everything it did for us already.
to the open source community for everything it did for us already.
[1]: https://opencollective.com/algolia

6
docs/src/who-can-apply.md
View file

@ -32,7 +32,7 @@ points.
If in doubt, don't hesitate to [apply][1] and we'll figure it out together.
Even if we cannot accept your request, this does not mean that you cannot enjoy
great search on your website. DocSearch is entirely open-source and you can run
great search on your website. DocSearch is entirely open source and you can run
it yourself, or use any of our other API clients to take advantage of the
features of Algolia.
@ -42,8 +42,8 @@ We're receiving many requests every day, and while we strive to answer them all
as fast as we can, we sometimes give priority to some of them based on the
following criteria:
- 🙂 If your project is Open-Source, we'll handle it before any other
close-source product. We love Open-Source and want to help as much as we can.
- 🙂 If your project is open source, We'll handle it before any other
close-source product. We love open source and want to help as much as we can.
- 🙂 If you're using one of our [official integrations][2], creating your config
will be much faster for us.