-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
29 changed files
with
3,315 additions
and
1,859 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -58,4 +58,5 @@ profile-* | |
| dist | ||
| scripts/ | ||
|
|
||
| ecosystem.config.cjs | ||
| ecosystem.config.js | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -7,20 +7,20 @@ | |
| "email": "[email protected]" | ||
| }, | ||
| "dependencies": { | ||
| "@jxa/global-type": "^1.3.5", | ||
| "@jxa/run": "^1.3.5", | ||
| "@jxa/global-type": "1.3.5", | ||
| "@jxa/run": "1.3.5", | ||
| "alfy": "0.11.1", | ||
| "convert-layout": "^0.11.1", | ||
| "convert-layout": "0.11.1", | ||
| "default-browser": "2.0.1", | ||
| "minisearch": "4.0.3", | ||
| "patch-package": "^6.4.7", | ||
| "ts-node": "^10.9.1" | ||
| "patch-package": "6.4.7", | ||
| "ts-node": "10.9.1" | ||
| }, | ||
| "devDependencies": { | ||
| "@types/chrome": "^0.0.193", | ||
| "@types/convert-layout": "^0.5.1", | ||
| "ts-node-dev": "^2.0.0", | ||
| "typescript": "^4.9.4" | ||
| "@types/chrome": "0.0.248", | ||
| "@types/convert-layout": "0.5.2", | ||
| "ts-node-dev": "2.0.0", | ||
| "typescript": "5.2.2" | ||
| }, | ||
| "engines": { | ||
| "node": ">=14.16" | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,50 @@ | ||
| import * as fs from 'node:fs'; | ||
| import * as cheerio from 'cheerio'; | ||
| import * as path from 'node:path'; | ||
| import { fileURLToPath } from 'url'; | ||
|
|
||
| // @ts-ignore | ||
| const __dirname = path.dirname(fileURLToPath(import.meta.url)); | ||
|
|
||
| const main = async () => { | ||
| const html = await fs.promises.readFile( | ||
| path.join(__dirname, 'wk.html'), | ||
| 'utf-8', | ||
| ); | ||
|
|
||
| const finnish = html | ||
| .split('<hr />') | ||
| .find((section) => section.includes('id="Finnish"')); | ||
|
|
||
| if (!finnish) throw new Error('No Finnish section found'); | ||
| const $$ = cheerio.load(finnish); | ||
|
|
||
| const $html = $$.root(); | ||
| $html.find('#toc').remove(); | ||
| $html.find('.mw-editsection').remove(); | ||
| $html.find('*').each((_x, el) => { | ||
| const $el = $$(el); | ||
| if ($el.attr('lang') !== 'fi') { | ||
| $el.removeAttr('lang'); | ||
| } | ||
| if ($el.hasClass('term-list-header')) { | ||
| $el.removeClass('term-list-header').addClass('title'); | ||
| } | ||
| if ($el.is('style')) { | ||
| $el.remove(); | ||
| } | ||
| }); | ||
| $html.find('table *').each((_x, el) => { | ||
| $$(el).removeAttr('class').removeAttr('lang'); | ||
| }); | ||
|
|
||
| let maybeTranslation = $html | ||
| .find('.Latn.headword[lang="fi"]') | ||
| .closest('p') | ||
| .next('ol, ul') | ||
| .text(); | ||
|
|
||
| console.log(maybeTranslation); | ||
| }; | ||
|
|
||
| void main(); |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.