Add/csv import options (#420)

* 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
2026-05-08 15:42:06 +02:00
parent 6c5c49f588
commit 81e9dd224e
62 changed files with 4468 additions and 124 deletions
@@ -0,0 +1,107 @@
+import { describe, it, expect } from 'vitest'
+import { classifyCustomer, classifySupplier } from '../classify'
+
+describe('classifyCustomer', () => {
+  it('classifies 12-digit personnummer as individual', () => {
+    expect(classifyCustomer({
+      org_number: '198001011234',
+      vat_number: null,
+    })).toBe('individual')
+  })
+
+  it('classifies 10-digit Swedish org as swedish_business', () => {
+    expect(classifyCustomer({
+      org_number: '5560217780',
+      vat_number: null,
+    })).toBe('swedish_business')
+  })
+
+  it('classifies non-SE EU VAT prefix as eu_business', () => {
+    expect(classifyCustomer({
+      org_number: null,
+      vat_number: 'DE123456789',
+    })).toBe('eu_business')
+  })
+
+  it('classifies non-EU VAT prefix as non_eu_business', () => {
+    expect(classifyCustomer({
+      org_number: null,
+      vat_number: 'NO12345678',
+    })).toBe('non_eu_business')
+  })
+
+  it('keeps SE VAT prefix as swedish_business', () => {
+    expect(classifyCustomer({
+      org_number: '5560217780',
+      vat_number: 'SE556021778001',
+    })).toBe('swedish_business')
+  })
+
+  it('classifies 10-digit personnummer-month-pattern as individual', () => {
+    // Third digit is 0 (month 01), classic personnummer pattern
+    expect(classifyCustomer({
+      org_number: '8001011234',
+      vat_number: null,
+    })).toBe('individual')
+  })
+
+  it('falls back to swedish_business when no signals', () => {
+    expect(classifyCustomer({
+      org_number: null,
+      vat_number: null,
+    })).toBe('swedish_business')
+  })
+
+  it('uses country code when VAT missing', () => {
+    expect(classifyCustomer({
+      org_number: null,
+      vat_number: null,
+      country: 'DE',
+    })).toBe('eu_business')
+  })
+
+  it('detects Norway as non-EU', () => {
+    expect(classifyCustomer({
+      org_number: null,
+      vat_number: null,
+      country: 'Norge',
+    })).toBe('non_eu_business')
+  })
+})
+
+describe('classifySupplier', () => {
+  it('never returns individual', () => {
+    expect(classifySupplier({
+      org_number: '198001011234',
+      vat_number: null,
+    })).toBe('swedish_business')
+  })
+
+  it('classifies non-SE EU VAT prefix as eu_business', () => {
+    expect(classifySupplier({
+      org_number: null,
+      vat_number: 'FR12345678901',
+    })).toBe('eu_business')
+  })
+
+  it('classifies post-Brexit GB VAT as non_eu_business', () => {
+    expect(classifySupplier({
+      org_number: null,
+      vat_number: 'GB123456789',
+    })).toBe('non_eu_business')
+  })
+
+  it('classifies XI (Northern Ireland) VAT as eu_business', () => {
+    expect(classifySupplier({
+      org_number: null,
+      vat_number: 'XI123456789',
+    })).toBe('eu_business')
+  })
+
+  it('falls back to swedish_business by default', () => {
+    expect(classifySupplier({
+      org_number: null,
+      vat_number: null,
+    })).toBe('swedish_business')
+  })
+})
@@ -0,0 +1,79 @@
+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('MalmÃ¶')).toBe('Malmö')
+    expect(decodeStringContent('Ã¥re')).toBe('Åre'.toLowerCase())
+    expect(decodeStringContent('LinkÃ¶ping')).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('MalmÃ¶')
+    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('MalmÃ¶')).toBe(true) // ö
+    expect(hasEncodingIssues('Ã¥re')).toBe(true) // å
+    expect(hasEncodingIssues('Ã¤lg')).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')
+  })
+})
@@ -0,0 +1,77 @@
+import { describe, it, expect } from 'vitest'
+import * as XLSX from 'xlsx'
+import { readWorkbookFromBuffer } from '../workbook-reader'
+
+function bufFromBytes(bytes: number[]): ArrayBuffer {
+  return new Uint8Array(bytes).buffer
+}
+
+function rowsOf(workbook: XLSX.WorkBook): string[][] {
+  const sheet = workbook.Sheets[workbook.SheetNames[0]]
+  return XLSX.utils.sheet_to_json(sheet, { header: 1, defval: '', raw: false }) as string[][]
+}
+
+describe('readWorkbookFromBuffer', () => {
+  it('decodes UTF-8 CSV with Swedish characters correctly', () => {
+    const csv = new TextEncoder().encode('Namn,Ort\nAcme,GÖTEBORG\nBeta,KÄRRA\n').buffer
+    const wb = readWorkbookFromBuffer(csv, 'lev.csv')
+    expect(rowsOf(wb)).toEqual([
+      ['Namn', 'Ort'],
+      ['Acme', 'GÖTEBORG'],
+      ['Beta', 'KÄRRA'],
+    ])
+  })
+
+  it('decodes UTF-8 CSV with BOM', () => {
+    const bom = [0xef, 0xbb, 0xbf]
+    const body = Array.from(new TextEncoder().encode('Namn,Ort\nAcme,GÖTEBORG\n'))
+    const wb = readWorkbookFromBuffer(bufFromBytes([...bom, ...body]), 'lev.csv')
+    expect(rowsOf(wb)).toEqual([
+      ['Namn', 'Ort'],
+      ['Acme', 'GÖTEBORG'],
+    ])
+  })
+
+  it('decodes Windows-1252 CSV with Swedish characters', () => {
+    // "Namn,Ort\nAcme,GÖTEBORG\nBeta,KÄRRA\n" in Windows-1252:
+    // Ö = 0xD6, Ä = 0xC4
+    const bytes = [
+      0x4e, 0x61, 0x6d, 0x6e, 0x2c, 0x4f, 0x72, 0x74, 0x0a,
+      0x41, 0x63, 0x6d, 0x65, 0x2c, 0x47, 0xd6, 0x54, 0x45, 0x42, 0x4f, 0x52, 0x47, 0x0a,
+      0x42, 0x65, 0x74, 0x61, 0x2c, 0x4b, 0xc4, 0x52, 0x52, 0x41, 0x0a,
+    ]
+    const wb = readWorkbookFromBuffer(bufFromBytes(bytes), 'lev.csv')
+    expect(rowsOf(wb)).toEqual([
+      ['Namn', 'Ort'],
+      ['Acme', 'GÖTEBORG'],
+      ['Beta', 'KÄRRA'],
+    ])
+  })
+
+  it('reads xlsx files via the binary path', () => {
+    const ws = XLSX.utils.aoa_to_sheet([
+      ['Namn', 'Ort'],
+      ['Acme', 'GÖTEBORG'],
+    ])
+    const wb = XLSX.utils.book_new()
+    XLSX.utils.book_append_sheet(wb, ws, 'Sheet1')
+    const buffer = XLSX.write(wb, { type: 'array', bookType: 'xlsx' }) as ArrayBuffer
+
+    const result = readWorkbookFromBuffer(buffer, 'data.xlsx')
+    expect(rowsOf(result)).toEqual([
+      ['Namn', 'Ort'],
+      ['Acme', 'GÖTEBORG'],
+    ])
+  })
+
+  it('treats non-csv extensions as binary spreadsheets', () => {
+    // .xls and .ods both go through the binary path; xlsx handles encoding internally
+    const ws = XLSX.utils.aoa_to_sheet([['A'], ['Ö']])
+    const wb = XLSX.utils.book_new()
+    XLSX.utils.book_append_sheet(wb, ws, 'Sheet1')
+    const buffer = XLSX.write(wb, { type: 'array', bookType: 'xlsx' }) as ArrayBuffer
+
+    const result = readWorkbookFromBuffer(buffer, 'data.xls')
+    expect(rowsOf(result)).toEqual([['A'], ['Ö']])
+  })
+})