Mattsson
81e9dd224e
* feat(import): add customer and supplier parsing functionality - Implemented customer file parsing in `lib/import/customers/parser.ts` with support for Excel and CSV formats. - Created types for detected customer columns and parsed customer rows in `lib/import/customers/types.ts`. - Added tests for customer classification logic in `lib/import/shared/__tests__/classify.test.ts`. - Developed classification functions for customers and suppliers in `lib/import/shared/classify.ts`. - Introduced shared column utility functions in `lib/import/shared/column-utils.ts`. - Implemented supplier file parsing in `lib/import/suppliers/parser.ts` with validation for various fields. - Created types for detected supplier columns and parsed supplier rows in `lib/import/suppliers/types.ts`. - Added tests for supplier column detection and parsing in `lib/import/suppliers/__tests__/column-detector.test.ts` and `lib/import/suppliers/__tests__/parser.test.ts`. * fix(labels): update 'Svenskt företag' to 'Svenskt företag eller organisation' for clarity * feat(import): refactor encoding handling for Swedish files and add tests for character preservation * feat(recapt): implement clearRecaptIdentity function and integrate into logout flow * feat(bookkeeping): implement copy functionality and next voucher sequence retrieval * feat(import): enhance customer and supplier import functionality with normalization and event handling
80 lines
2.9 KiB
TypeScript
80 lines
2.9 KiB
TypeScript
import { describe, it, expect } from 'vitest'
|
|
import {
|
|
decodeFileContent,
|
|
decodeStringContent,
|
|
hasEncodingIssues,
|
|
} from '../encoding'
|
|
|
|
describe('decodeStringContent', () => {
|
|
it('recovers UTF-8-as-Latin-1 mojibake for lowercase Swedish chars', () => {
|
|
expect(decodeStringContent('Malmö')).toBe('Malmö')
|
|
expect(decodeStringContent('Ã¥re')).toBe('Åre'.toLowerCase())
|
|
expect(decodeStringContent('Linköping')).toBe('Linköping')
|
|
})
|
|
|
|
it('recovers UTF-8-as-Latin-1 mojibake for uppercase Swedish chars', () => {
|
|
// The middle char is U+0096 (control), invisible in most renderings → "GÃTEBORG"
|
|
expect(decodeStringContent('GÃ\u0096TEBORG')).toBe('GÖTEBORG')
|
|
expect(decodeStringContent('HISINGS KÃ\u0084RRA')).toBe('HISINGS KÄRRA')
|
|
expect(decodeStringContent('Ã\u0085NGE')).toBe('ÅNGE')
|
|
})
|
|
|
|
it('is a no-op on already-correct Swedish strings', () => {
|
|
expect(decodeStringContent('GÖTEBORG')).toBe('GÖTEBORG')
|
|
expect(decodeStringContent('Malmö')).toBe('Malmö')
|
|
expect(decodeStringContent('STOCKHOLM')).toBe('STOCKHOLM')
|
|
expect(decodeStringContent('')).toBe('')
|
|
})
|
|
|
|
it('is idempotent (running twice equals running once)', () => {
|
|
const once = decodeStringContent('Malmö')
|
|
const twice = decodeStringContent(once)
|
|
expect(twice).toBe(once)
|
|
expect(twice).toBe('Malmö')
|
|
})
|
|
|
|
it('preserves non-Swedish strings unchanged', () => {
|
|
expect(decodeStringContent('Café')).toBe('Café')
|
|
expect(decodeStringContent('München')).toBe('München')
|
|
expect(decodeStringContent('123 Main St')).toBe('123 Main St')
|
|
})
|
|
})
|
|
|
|
describe('hasEncodingIssues', () => {
|
|
it('detects U+FFFD replacement characters', () => {
|
|
expect(hasEncodingIssues('Foo\uFFFDbar')).toBe(true)
|
|
})
|
|
|
|
it('detects all six Swedish mojibake patterns', () => {
|
|
expect(hasEncodingIssues('Malmö')).toBe(true) // ö
|
|
expect(hasEncodingIssues('Ã¥re')).toBe(true) // å
|
|
expect(hasEncodingIssues('älg')).toBe(true) // ä
|
|
expect(hasEncodingIssues('GÃ\u0096TEBORG')).toBe(true) // Ö
|
|
expect(hasEncodingIssues('Ã\u0085NGE')).toBe(true) // Å
|
|
expect(hasEncodingIssues('Ã\u0084RRA')).toBe(true) // Ä
|
|
})
|
|
|
|
it('returns false for clean strings', () => {
|
|
expect(hasEncodingIssues('Stockholm')).toBe(false)
|
|
expect(hasEncodingIssues('Malmö')).toBe(false)
|
|
expect(hasEncodingIssues('Café')).toBe(false)
|
|
})
|
|
})
|
|
|
|
describe('decodeFileContent', () => {
|
|
function buf(bytes: number[]): ArrayBuffer {
|
|
return new Uint8Array(bytes).buffer
|
|
}
|
|
|
|
it('decodes UTF-8 bytes correctly', () => {
|
|
const utf8 = new TextEncoder().encode('GÖTEBORG').buffer
|
|
expect(decodeFileContent(utf8)).toBe('GÖTEBORG')
|
|
})
|
|
|
|
it('falls back to Windows-1252 when UTF-8 decode is invalid', () => {
|
|
// 0xD6 = Ö in Windows-1252; lone 0xD6 is not valid UTF-8 start byte
|
|
const cp1252 = buf([0x47, 0xd6, 0x54, 0x45, 0x42, 0x4f, 0x52, 0x47])
|
|
expect(decodeFileContent(cp1252)).toBe('GÖTEBORG')
|
|
})
|
|
})
|