Files
accounted/lib/import/bank-file/__tests__/parser.test.ts
T
Jakob WennbergandClaude Opus 4.6 e8fb84b4fd feat: import system improvements, INK2 fix, and Swedish text corrections (#10)
- SIE parser: Windows-1252 and CP437 encoding detection and decoding
- Bank file parser: add Nordea Business (Företag) CSV format
- Bank file parser: improve format detection for SEB, Länsförsäkringar, generic CSV
- INK2 engine: calculate årets resultat (7222) from income statement for open fiscal years
- Dashboard: parallel Supabase queries, simplified dashboard page
- Fix Swedish characters (å, ä, ö) in BAS data descriptions, validation messages, AI consent disclosures
- Import wizard UI improvements across all steps
- Migration: add 'bas_range' match type to sie_account_mappings constraint
- Extensive new tests for SIE parser encoding and bank file parser

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-11 18:05:37 +01:00

1547 lines
53 KiB
TypeScript

/**
* Comprehensive tests for the bank file parser library.
*
* Covers auto-detection, parsing for all Swedish bank formats (Nordea, SEB,
* Swedbank, Handelsbanken), ISO 20022 camt.053 XML, external ID generation,
* file hashing, stats calculation, date range extraction, and edge cases.
*/
import { detectFileFormat, parseBankFile, generateExternalId, generateFileHash, getFormat, getAllFormats } from '../parser'
import type { ParsedBankTransaction, BankFileFormatId } from '../types'
import { parseGenericCSV } from '../formats/generic-csv'
import { parseCSVLine } from '../formats/nordea'
// ---------------------------------------------------------------------------
// Test data — realistic CSV/XML content for each Swedish bank format
// ---------------------------------------------------------------------------
const NORDEA_CSV = [
'Datum,Transaktion,Kategori,Belopp,Saldo',
'2024-01-15,SPOTIFY AB,,"-99,00","12 345,67"',
'2024-01-14,ICA MAXI LINDHAGEN,,"-432,50","12 444,67"',
'2024-01-13,LÖNEUTBETALNING,,"25 000,00","12 877,17"',
].join('\n')
const NORDEA_CSV_WITH_RESERVED = [
'Datum,Transaktion,Kategori,Belopp,Saldo',
'2024-01-15,SPOTIFY AB,,"-99,00","12 345,67"',
'2024-01-14,Reserverat köp CLAS OHLSON,,"-199,00","12 444,67"',
'2024-01-13,LÖNEUTBETALNING,,"25 000,00","12 643,67"',
].join('\n')
const NORDEA_CSV_SWEDISH_CHARS = [
'Datum,Transaktion,Kategori,Belopp,Saldo',
'2024-03-01,GÖTEBORGS HAMNCAFÉ,,"-85,00","5 000,00"',
'2024-03-02,ÅHLENS CITY,,"-249,00","4 751,00"',
'2024-03-03,ÄRLA GÅRD AB,,"1 200,00","5 951,00"',
].join('\n')
const SEB_CSV = [
'Bokföringsdag;Valutadag;Verifikationsnummer;Text;Belopp;Saldo',
'2024-01-15;2024-01-15;12345;SPOTIFY AB;-99,00;12345,67',
'2024-01-14;2024-01-14;12346;HEMKÖP FRIDHEMSPLAN;-432,50;12444,67',
'2024-01-13;2024-01-13;12347;LÖNEUTBETALNING;25000,00;12877,17',
].join('\n')
const SWEDBANK_CSV = [
'Kontouppgifter',
'Clearingnummer,Kontonummer,Datum,Text,Belopp,Saldo',
'8123,12345678,2024-01-15,SPOTIFY AB,-99.00,12345.67',
'8123,12345678,2024-01-14,ICA MAXI,-432.50,12444.67',
'8123,12345678,2024-01-13,LÖNEUTBETALNING,25000.00,12877.17',
].join('\n')
const SWEDBANK_CSV_NO_METADATA = [
'Clearingnummer,Kontonummer,Datum,Text,Belopp,Saldo',
'8123,12345678,2024-02-01,TELIA SVERIGE,-299.00,10000.00',
'8123,12345678,2024-02-02,SKATTEVERKET INBETALNING,5000.00,15000.00',
].join('\n')
const HANDELSBANKEN_CSV = [
'Reskontradatum;Transaktionsdatum;Text;Belopp;Saldo',
'2024-01-15;2024-01-15;SPOTIFY AB;-99,00;12345,67',
'2024-01-14;2024-01-14;HEMKÖP;-432,50;12444,67',
'2024-01-13;2024-01-13;LÖNEUTBETALNING;25000,00;12877,17',
].join('\n')
const HANDELSBANKEN_CSV_WITH_PREL = [
'Reskontradatum;Transaktionsdatum;Text;Belopp;Saldo',
'2024-01-15;2024-01-15;SPOTIFY AB;-99,00;12345,67',
'2024-01-14;2024-01-14;Prel kortköp CLAS OHLSON;-199,00;12444,67',
'2024-01-13;2024-01-13;LÖNEUTBETALNING;25000,00;12643,67',
].join('\n')
const CAMT053_XML = `<?xml version="1.0" encoding="UTF-8"?>
<Document xmlns="urn:iso:std:iso:20022:tech:xsd:camt.053.001.02">
<BkToCstmrStmt>
<Stmt>
<Acct><Ccy>SEK</Ccy></Acct>
<Ntry>
<BookgDt><Dt>2024-01-15</Dt></BookgDt>
<Amt Ccy="SEK">99.00</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<NtryRef>REF001</NtryRef>
<NtryDtls><TxDtls>
<RmtInf><Ustrd>SPOTIFY AB</Ustrd></RmtInf>
</TxDtls></NtryDtls>
</Ntry>
<Ntry>
<BookgDt><Dt>2024-01-14</Dt></BookgDt>
<Amt Ccy="SEK">25000.00</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<NtryRef>REF002</NtryRef>
<NtryDtls><TxDtls>
<RmtInf><Ustrd>LÖNEUTBETALNING</Ustrd></RmtInf>
</TxDtls></NtryDtls>
</Ntry>
</Stmt>
</BkToCstmrStmt>
</Document>`
const CAMT053_XML_WITH_STRUCTURED_REF = `<?xml version="1.0" encoding="UTF-8"?>
<Document xmlns="urn:iso:std:iso:20022:tech:xsd:camt.053.001.02">
<BkToCstmrStmt>
<Stmt>
<Ntry>
<BookgDt><Dt>2024-02-01</Dt></BookgDt>
<Amt Ccy="SEK">1500.00</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<NtryRef>REF100</NtryRef>
<NtryDtls><TxDtls>
<RmtInf>
<Strd><CdtrRefInf><Ref>OCR123456789</Ref></CdtrRefInf></Strd>
<Ustrd>Betalning faktura 1001</Ustrd>
</RmtInf>
</TxDtls></NtryDtls>
</Ntry>
</Stmt>
</BkToCstmrStmt>
</Document>`
const LANSFORSAKRINGAR_CSV = [
'"Datum";"Bokföringsdag";"Typ";"Text";"Belopp";"Saldo"',
'"2024-01-15";"2024-01-15";"Kortköp";"SPOTIFY AB";"-99,00";"12 345,67"',
'"2024-01-14";"2024-01-14";"Kortköp";"ICA MAXI";"-432,50";"12 444,67"',
'"2024-01-13";"2024-01-13";"Insättning";"LÖNEUTBETALNING";"25 000,00";"12 877,17"',
].join('\n')
const LANSFORSAKRINGAR_CSV_NO_HEADER = [
'"2024-01-15";"2024-01-15";"Kortköp";"SPOTIFY AB";"-99,00";"12 345,67"',
'"2024-01-14";"2024-01-14";"Kortköp";"ICA MAXI";"-432,50";"12 444,67"',
].join('\n')
const ICA_BANKEN_CSV = [
'Kontonamn: Lönekonto',
'Kontonummer: 1234 567 890',
'Saldo: 12 877,17',
'Tillgängligt belopp: 12 877,17',
'Period: 2024-01-01 - 2024-01-31',
'Exporterad: 2024-02-01',
'Datum;Text;Belopp;Saldo',
'2024-01-15;SPOTIFY AB;-99,00;12345,67',
'2024-01-14;ICA MAXI LINDHAGEN;-432,50;12444,67',
'2024-01-13;LÖNEUTBETALNING;25000,00;12877,17',
].join('\n')
const SKANDIA_CSV = [
'Datum;Beskrivning;Belopp;Saldo',
'2024-01-15;SPOTIFY AB;-99,00;12345,67',
'2024-01-14;HEMKÖP FRIDHEMSPLAN;-432,50;12444,67',
'2024-01-13;LÖNEUTBETALNING;25000,00;12877,17',
].join('\n')
const SKANDIA_CSV_WITH_BANKKATEGORI = [
'Datum;Beskrivning;Belopp;Saldo;Bankkategori',
'2024-01-15;SPOTIFY AB;-99,00;12345,67;Underhållning',
'2024-01-14;ICA MAXI;-432,50;12444,67;Livsmedel',
].join('\n')
const LUNAR_CSV = [
'Date,Text,Amount,Balance',
'2024-01-15,SPOTIFY AB,"-99,00","12.345,67"',
'2024-01-14,ICA MAXI LINDHAGEN,"-432,50","12.444,67"',
'2024-01-13,LÖNEUTBETALNING,"25.000,00","12.877,17"',
].join('\n')
const UNKNOWN_CSV = [
'id,name,value,timestamp',
'1,Widget A,100,2024-01-15T10:00:00',
'2,Widget B,200,2024-01-16T11:00:00',
].join('\n')
const EMPTY_FILE = ''
const HEADER_ONLY_NORDEA = 'Datum,Transaktion,Kategori,Belopp,Saldo\n'
const NORDEA_BUSINESS_CSV = [
'Bokföringsdag;Belopp;Avsändare;Mottagare;Namn;Rubrik;Saldo;Valuta',
'2024-01-15;-99,00;;SPOTIFY AB;SPOTIFY AB;Kortköp;12 345,67;SEK',
'2024-01-14;-432,50;;ICA MAXI;ICA MAXI LINDHAGEN;Kortköp;12 444,67;SEK',
'2024-01-13;25 000,00;ARBETSGIVAREN AB;;ARBETSGIVAREN AB;Löneutbetalning;12 877,17;SEK',
].join('\n')
const NORDEA_BUSINESS_CSV_SWEDISH_CHARS = [
'Bokföringsdag;Belopp;Avsändare;Mottagare;Namn;Rubrik;Saldo;Valuta',
'2024-03-01;-85,00;;GÖTEBORGS HAMNCAFÉ;GÖTEBORGS HAMNCAFÉ;Kortköp;5 000,00;SEK',
'2024-03-02;-249,00;;ÅHLENS CITY;ÅHLENS CITY;Kortköp;4 751,00;SEK',
'2024-03-03;1 200,00;ÄRLA GÅRD AB;;ÄRLA GÅRD AB;Betalning;5 951,00;SEK',
].join('\n')
const HEADER_ONLY_NORDEA_BUSINESS = 'Bokföringsdag;Belopp;Avsändare;Mottagare;Namn;Rubrik;Saldo;Valuta\n'
// ---------------------------------------------------------------------------
// Tests
// ---------------------------------------------------------------------------
describe('detectFileFormat', () => {
it('detects Nordea CSV from header keywords', () => {
const format = detectFileFormat(NORDEA_CSV, 'transaktioner.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('nordea')
})
it('detects Nordea Business CSV from semicolon-delimited header with bokföringsdag and rubrik', () => {
const format = detectFileFormat(NORDEA_BUSINESS_CSV, 'PLUSGIROKONTO FTG 212 68 87-5.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('nordea_business')
})
it('does not confuse Nordea Business with SEB (SEB has valutadag)', () => {
const format = detectFileFormat(NORDEA_BUSINESS_CSV, 'export.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('nordea_business')
})
it('detects SEB CSV from semicolon-delimited header with bokföringsdag', () => {
const format = detectFileFormat(SEB_CSV, 'kontoutdrag.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('seb')
})
it('detects Swedbank CSV from clearingnummer header', () => {
const format = detectFileFormat(SWEDBANK_CSV, 'export.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('swedbank')
})
it('detects Swedbank CSV when header is on the first line (no metadata)', () => {
const format = detectFileFormat(SWEDBANK_CSV_NO_METADATA, 'export.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('swedbank')
})
it('detects Handelsbanken CSV from reskontradatum/transaktionsdatum header', () => {
const format = detectFileFormat(HANDELSBANKEN_CSV, 'handelsbanken.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('handelsbanken')
})
it('detects camt.053 XML from namespace and .xml extension', () => {
const format = detectFileFormat(CAMT053_XML, 'statement.xml')
expect(format).not.toBeNull()
expect(format!.id).toBe('camt053')
})
it('detects camt.053 XML when content includes BkToCstmrStmt tag', () => {
const xmlContent = '<?xml version="1.0"?><Document><BkToCstmrStmt></BkToCstmrStmt></Document>'
const format = detectFileFormat(xmlContent, 'data.xml')
expect(format).not.toBeNull()
expect(format!.id).toBe('camt053')
})
it('does not detect camt.053 without .xml extension', () => {
// camt053 detection requires .xml extension
const format = detectFileFormat(CAMT053_XML, 'statement.csv')
// It should not match camt053 since extension is .csv
// But it could match something else if the content resembles a CSV header
// The important check is that it does NOT return camt053
if (format) {
expect(format.id).not.toBe('camt053')
}
})
it('detects Länsförsäkringar CSV from header with "typ" keyword', () => {
const format = detectFileFormat(LANSFORSAKRINGAR_CSV, 'lansforsakringar.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('lansforsakringar')
})
it('detects Länsförsäkringar CSV from two adjacent date fields (no header)', () => {
const format = detectFileFormat(LANSFORSAKRINGAR_CSV_NO_HEADER, 'export.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('lansforsakringar')
})
it('detects ICA Banken CSV from metadata rows before header', () => {
const format = detectFileFormat(ICA_BANKEN_CSV, 'ica.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('ica_banken')
})
it('detects Skandia CSV from "beskrivning" header keyword', () => {
const format = detectFileFormat(SKANDIA_CSV, 'skandia.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('skandia')
})
it('detects Skandia CSV from "bankkategori" header keyword', () => {
const format = detectFileFormat(SKANDIA_CSV_WITH_BANKKATEGORI, 'skandia.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('skandia')
})
it('detects Lunar CSV from English headers (date, text, amount, balance)', () => {
const format = detectFileFormat(LUNAR_CSV, 'lunar.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('lunar')
})
it('returns null for unrecognized CSV content', () => {
const format = detectFileFormat(UNKNOWN_CSV, 'data.csv')
expect(format).toBeNull()
})
it('returns null for empty content', () => {
const format = detectFileFormat(EMPTY_FILE, 'empty.csv')
expect(format).toBeNull()
})
it('generic_csv format never auto-detects', () => {
// Even with simple CSV content, generic should not be picked
const simpleCSV = 'date,description,amount\n2024-01-15,Test,-100'
const format = detectFileFormat(simpleCSV, 'test.csv')
if (format) {
expect(format.id).not.toBe('generic_csv')
}
})
it('is case-insensitive on header detection', () => {
const upperNordea = 'DATUM,TRANSAKTION,KATEGORI,BELOPP,SALDO\n2024-01-15,Test,,"-100,00","5000,00"'
const format = detectFileFormat(upperNordea, 'test.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('nordea')
})
})
describe('parseBankFile — Nordea format', () => {
it('parses comma-delimited CSV with comma decimal separator', () => {
const result = parseBankFile(NORDEA_CSV, 'nordea.csv')
expect(result.format).toBe('nordea')
expect(result.format_name).toBe('Nordea')
expect(result.transactions).toHaveLength(3)
expect(result.issues).toHaveLength(0)
})
it('correctly parses negative amounts with comma decimal and space thousands', () => {
const result = parseBankFile(NORDEA_CSV, 'nordea.csv')
const spotify = result.transactions[0]
expect(spotify.amount).toBe(-99)
expect(spotify.description).toBe('SPOTIFY AB')
expect(spotify.date).toBe('2024-01-15')
expect(spotify.currency).toBe('SEK')
const ica = result.transactions[1]
expect(ica.amount).toBe(-432.5)
})
it('correctly parses positive amounts with space thousands separator', () => {
const result = parseBankFile(NORDEA_CSV, 'nordea.csv')
const salary = result.transactions[2]
expect(salary.amount).toBe(25000)
expect(salary.description).toBe('LÖNEUTBETALNING')
})
it('parses balance field with space thousands separator', () => {
const result = parseBankFile(NORDEA_CSV, 'nordea.csv')
const spotify = result.transactions[0]
expect(spotify.balance).toBe(12345.67)
})
it('filters out "Reserverat" (pending) transactions', () => {
const result = parseBankFile(NORDEA_CSV_WITH_RESERVED, 'nordea.csv')
expect(result.transactions).toHaveLength(2)
expect(result.stats.skipped_rows).toBe(1)
const descriptions = result.transactions.map((t) => t.description)
expect(descriptions).not.toContain(expect.stringContaining('Reserverat'))
})
it('handles Swedish characters (a-ring, a-diaeresis, o-diaeresis)', () => {
const result = parseBankFile(NORDEA_CSV_SWEDISH_CHARS, 'nordea.csv')
expect(result.transactions).toHaveLength(3)
expect(result.transactions[0].description).toBe('GÖTEBORGS HAMNCAFÉ')
expect(result.transactions[1].description).toBe('ÅHLENS CITY')
expect(result.transactions[2].description).toBe('ÄRLA GÅRD AB')
})
it('stores raw_line for each transaction', () => {
const result = parseBankFile(NORDEA_CSV, 'nordea.csv')
result.transactions.forEach((tx) => {
expect(tx.raw_line).toBeDefined()
expect(tx.raw_line!.length).toBeGreaterThan(0)
})
})
it('handles header-only file with no data rows', () => {
const result = parseBankFile(HEADER_ONLY_NORDEA, 'nordea.csv')
expect(result.format).toBe('nordea')
expect(result.transactions).toHaveLength(0)
expect(result.date_from).toBeNull()
expect(result.date_to).toBeNull()
expect(result.stats.parsed_rows).toBe(0)
})
})
describe('parseBankFile — Nordea Business format', () => {
it('parses semicolon-delimited CSV with correct columns', () => {
const result = parseBankFile(NORDEA_BUSINESS_CSV, 'nordea_ftg.csv')
expect(result.format).toBe('nordea_business')
expect(result.format_name).toBe('Nordea Företag')
expect(result.transactions).toHaveLength(3)
expect(result.issues).toHaveLength(0)
})
it('correctly parses negative amounts', () => {
const result = parseBankFile(NORDEA_BUSINESS_CSV, 'nordea_ftg.csv')
const spotify = result.transactions[0]
expect(spotify.amount).toBe(-99)
expect(spotify.date).toBe('2024-01-15')
expect(spotify.currency).toBe('SEK')
})
it('correctly parses positive amounts with space thousands separator', () => {
const result = parseBankFile(NORDEA_BUSINESS_CSV, 'nordea_ftg.csv')
const salary = result.transactions[2]
expect(salary.amount).toBe(25000)
expect(salary.date).toBe('2024-01-13')
})
it('builds description from Namn and Rubrik columns', () => {
const result = parseBankFile(NORDEA_BUSINESS_CSV, 'nordea_ftg.csv')
const spotify = result.transactions[0]
expect(spotify.description).toBe('SPOTIFY AB — Kortköp')
const salary = result.transactions[2]
expect(salary.description).toBe('ARBETSGIVAREN AB — Löneutbetalning')
})
it('extracts counterparty from Mottagare (expense) or Avsändare (income)', () => {
const result = parseBankFile(NORDEA_BUSINESS_CSV, 'nordea_ftg.csv')
// Expense: counterparty from Mottagare
expect(result.transactions[0].counterparty).toBe('SPOTIFY AB')
// Income: counterparty from Avsändare
expect(result.transactions[2].counterparty).toBe('ARBETSGIVAREN AB')
})
it('parses balance field', () => {
const result = parseBankFile(NORDEA_BUSINESS_CSV, 'nordea_ftg.csv')
expect(result.transactions[0].balance).toBe(12345.67)
expect(result.transactions[2].balance).toBe(12877.17)
})
it('handles Swedish characters', () => {
const result = parseBankFile(NORDEA_BUSINESS_CSV_SWEDISH_CHARS, 'nordea_ftg.csv')
expect(result.transactions).toHaveLength(3)
expect(result.transactions[0].description).toContain('GÖTEBORGS HAMNCAFÉ')
expect(result.transactions[1].description).toContain('ÅHLENS CITY')
expect(result.transactions[2].description).toContain('ÄRLA GÅRD AB')
})
it('stores raw_line for each transaction', () => {
const result = parseBankFile(NORDEA_BUSINESS_CSV, 'nordea_ftg.csv')
result.transactions.forEach((tx) => {
expect(tx.raw_line).toBeDefined()
expect(tx.raw_line!.length).toBeGreaterThan(0)
})
})
it('handles header-only file with no data rows', () => {
const result = parseBankFile(HEADER_ONLY_NORDEA_BUSINESS, 'nordea_ftg.csv')
expect(result.format).toBe('nordea_business')
expect(result.transactions).toHaveLength(0)
expect(result.date_from).toBeNull()
expect(result.date_to).toBeNull()
expect(result.stats.parsed_rows).toBe(0)
})
it('calculates correct date range', () => {
const result = parseBankFile(NORDEA_BUSINESS_CSV, 'nordea_ftg.csv')
expect(result.date_from).toBe('2024-01-13')
expect(result.date_to).toBe('2024-01-15')
})
it('calculates correct income and expense stats', () => {
const result = parseBankFile(NORDEA_BUSINESS_CSV, 'nordea_ftg.csv')
expect(result.stats.total_income).toBe(25000)
expect(result.stats.total_expenses).toBe(-531.5)
expect(result.stats.parsed_rows).toBe(3)
expect(result.stats.skipped_rows).toBe(0)
})
})
describe('parseBankFile — SEB format', () => {
it('parses semicolon-delimited CSV with comma decimal separator', () => {
const result = parseBankFile(SEB_CSV, 'seb.csv')
expect(result.format).toBe('seb')
expect(result.format_name).toBe('SEB')
expect(result.transactions).toHaveLength(3)
expect(result.issues).toHaveLength(0)
})
it('correctly extracts columns using dynamic header mapping', () => {
const result = parseBankFile(SEB_CSV, 'seb.csv')
const spotify = result.transactions[0]
expect(spotify.date).toBe('2024-01-15')
expect(spotify.description).toBe('SPOTIFY AB')
expect(spotify.amount).toBe(-99)
expect(spotify.balance).toBe(12345.67)
})
it('parses positive income amounts correctly', () => {
const result = parseBankFile(SEB_CSV, 'seb.csv')
const salary = result.transactions[2]
expect(salary.amount).toBe(25000)
expect(salary.description).toBe('LÖNEUTBETALNING')
})
it('handles alternative SEB header names', () => {
const altSEB = [
'Bokforingsdatum;Valutadag;Verifikationsnummer;Text;Belopp;Saldo',
'2024-01-15;2024-01-15;12345;TEST;-50,00;1000,00',
].join('\n')
const result = parseBankFile(altSEB, 'seb_alt.csv')
expect(result.format).toBe('seb')
expect(result.transactions).toHaveLength(1)
expect(result.transactions[0].amount).toBe(-50)
})
})
describe('parseBankFile — Swedbank format', () => {
it('parses comma-delimited CSV with PERIOD decimal separator', () => {
const result = parseBankFile(SWEDBANK_CSV, 'swedbank.csv')
expect(result.format).toBe('swedbank')
expect(result.format_name).toBe('Swedbank')
expect(result.transactions).toHaveLength(3)
expect(result.issues).toHaveLength(0)
})
it('correctly handles period decimal separator (the Swedish exception)', () => {
const result = parseBankFile(SWEDBANK_CSV, 'swedbank.csv')
const spotify = result.transactions[0]
expect(spotify.amount).toBe(-99)
expect(spotify.balance).toBe(12345.67)
const ica = result.transactions[1]
expect(ica.amount).toBe(-432.5)
})
it('skips metadata line when present (first line is account info)', () => {
const result = parseBankFile(SWEDBANK_CSV, 'swedbank.csv')
// With metadata line, there are 3 data rows after headerLineIdx=1
expect(result.transactions).toHaveLength(3)
// No transaction should have "Kontouppgifter" as description
const descriptions = result.transactions.map((t) => t.description)
expect(descriptions).not.toContain('Kontouppgifter')
})
it('works when header is on the first line (no metadata)', () => {
const result = parseBankFile(SWEDBANK_CSV_NO_METADATA, 'swedbank.csv')
expect(result.format).toBe('swedbank')
expect(result.transactions).toHaveLength(2)
expect(result.transactions[0].amount).toBe(-299)
expect(result.transactions[1].amount).toBe(5000)
})
it('extracts dates correctly', () => {
const result = parseBankFile(SWEDBANK_CSV, 'swedbank.csv')
expect(result.transactions[0].date).toBe('2024-01-15')
expect(result.transactions[2].date).toBe('2024-01-13')
})
})
describe('parseBankFile — Handelsbanken format', () => {
it('parses semicolon-delimited CSV with comma decimal separator', () => {
const result = parseBankFile(HANDELSBANKEN_CSV, 'handelsbanken.csv')
expect(result.format).toBe('handelsbanken')
expect(result.format_name).toBe('Handelsbanken')
expect(result.transactions).toHaveLength(3)
expect(result.issues).toHaveLength(0)
})
it('correctly parses amounts and balances', () => {
const result = parseBankFile(HANDELSBANKEN_CSV, 'handelsbanken.csv')
expect(result.transactions[0].amount).toBe(-99)
expect(result.transactions[0].balance).toBe(12345.67)
expect(result.transactions[2].amount).toBe(25000)
})
it('filters out "Prel" (preliminary) transactions', () => {
const result = parseBankFile(HANDELSBANKEN_CSV_WITH_PREL, 'handelsbanken.csv')
expect(result.transactions).toHaveLength(2)
expect(result.stats.skipped_rows).toBe(1)
const descriptions = result.transactions.map((t) => t.description)
expect(descriptions).not.toContain(expect.stringContaining('Prel'))
})
it('prefers transaktionsdatum over reskontradatum when both are present', () => {
// Handelsbanken has both columns; transaktionsdatum should be used
const result = parseBankFile(HANDELSBANKEN_CSV, 'handelsbanken.csv')
// In our test data both dates are the same, but verify it selects dates properly
expect(result.transactions[0].date).toBe('2024-01-15')
})
it('uses transaktionsdatum as the primary date field', () => {
// Create data where reskontradatum differs from transaktionsdatum
const diffDates = [
'Reskontradatum;Transaktionsdatum;Text;Belopp;Saldo',
'2024-01-16;2024-01-15;PURCHASE;-100,00;5000,00',
].join('\n')
const result = parseBankFile(diffDates, 'shb.csv')
expect(result.transactions[0].date).toBe('2024-01-15')
})
})
describe('parseBankFile — Länsförsäkringar format', () => {
it('parses semicolon-delimited CSV with quoted fields and comma decimal separator', () => {
const result = parseBankFile(LANSFORSAKRINGAR_CSV, 'lf.csv')
expect(result.format).toBe('lansforsakringar')
expect(result.format_name).toBe('Länsförsäkringar')
expect(result.transactions).toHaveLength(3)
expect(result.issues).toHaveLength(0)
})
it('correctly parses amounts with comma decimal and space thousands', () => {
const result = parseBankFile(LANSFORSAKRINGAR_CSV, 'lf.csv')
expect(result.transactions[0].amount).toBe(-99)
expect(result.transactions[0].description).toBe('SPOTIFY AB')
expect(result.transactions[0].date).toBe('2024-01-15')
expect(result.transactions[1].amount).toBe(-432.5)
expect(result.transactions[2].amount).toBe(25000)
})
it('parses balance field', () => {
const result = parseBankFile(LANSFORSAKRINGAR_CSV, 'lf.csv')
expect(result.transactions[0].balance).toBe(12345.67)
})
it('handles files without a header row (data-only)', () => {
const result = parseBankFile(LANSFORSAKRINGAR_CSV_NO_HEADER, 'lf.csv')
expect(result.format).toBe('lansforsakringar')
expect(result.transactions).toHaveLength(2)
expect(result.transactions[0].amount).toBe(-99)
expect(result.transactions[1].amount).toBe(-432.5)
})
it('calculates stats correctly', () => {
const result = parseBankFile(LANSFORSAKRINGAR_CSV, 'lf.csv')
expect(result.stats.total_income).toBe(25000)
expect(result.stats.total_expenses).toBe(-531.5)
expect(result.stats.parsed_rows).toBe(3)
})
it('extracts correct date range', () => {
const result = parseBankFile(LANSFORSAKRINGAR_CSV, 'lf.csv')
expect(result.date_from).toBe('2024-01-13')
expect(result.date_to).toBe('2024-01-15')
})
})
describe('parseBankFile — ICA Banken format', () => {
it('parses semicolon-delimited CSV with metadata rows before header', () => {
const result = parseBankFile(ICA_BANKEN_CSV, 'ica.csv')
expect(result.format).toBe('ica_banken')
expect(result.format_name).toBe('ICA Banken')
expect(result.transactions).toHaveLength(3)
expect(result.issues).toHaveLength(0)
})
it('skips metadata rows and finds the correct header', () => {
const result = parseBankFile(ICA_BANKEN_CSV, 'ica.csv')
// No transaction should contain metadata text
const descriptions = result.transactions.map((t) => t.description)
expect(descriptions).not.toContain(expect.stringContaining('Kontonamn'))
expect(descriptions).not.toContain(expect.stringContaining('Exporterad'))
})
it('correctly parses amounts with comma decimal separator', () => {
const result = parseBankFile(ICA_BANKEN_CSV, 'ica.csv')
expect(result.transactions[0].amount).toBe(-99)
expect(result.transactions[0].description).toBe('SPOTIFY AB')
expect(result.transactions[0].date).toBe('2024-01-15')
expect(result.transactions[1].amount).toBe(-432.5)
expect(result.transactions[2].amount).toBe(25000)
})
it('parses balance field', () => {
const result = parseBankFile(ICA_BANKEN_CSV, 'ica.csv')
expect(result.transactions[0].balance).toBe(12345.67)
})
it('calculates stats correctly', () => {
const result = parseBankFile(ICA_BANKEN_CSV, 'ica.csv')
expect(result.stats.total_income).toBe(25000)
expect(result.stats.total_expenses).toBe(-531.5)
expect(result.stats.parsed_rows).toBe(3)
})
it('extracts correct date range', () => {
const result = parseBankFile(ICA_BANKEN_CSV, 'ica.csv')
expect(result.date_from).toBe('2024-01-13')
expect(result.date_to).toBe('2024-01-15')
})
})
describe('parseBankFile — Skandia format', () => {
it('parses semicolon-delimited CSV with comma decimal separator', () => {
const result = parseBankFile(SKANDIA_CSV, 'skandia.csv')
expect(result.format).toBe('skandia')
expect(result.format_name).toBe('Skandia')
expect(result.transactions).toHaveLength(3)
expect(result.issues).toHaveLength(0)
})
it('correctly parses amounts and descriptions', () => {
const result = parseBankFile(SKANDIA_CSV, 'skandia.csv')
expect(result.transactions[0].amount).toBe(-99)
expect(result.transactions[0].description).toBe('SPOTIFY AB')
expect(result.transactions[0].date).toBe('2024-01-15')
expect(result.transactions[1].amount).toBe(-432.5)
expect(result.transactions[1].description).toBe('HEMKÖP FRIDHEMSPLAN')
expect(result.transactions[2].amount).toBe(25000)
})
it('parses balance field', () => {
const result = parseBankFile(SKANDIA_CSV, 'skandia.csv')
expect(result.transactions[0].balance).toBe(12345.67)
})
it('handles files with bankkategori column', () => {
const result = parseBankFile(SKANDIA_CSV_WITH_BANKKATEGORI, 'skandia.csv')
expect(result.format).toBe('skandia')
expect(result.transactions).toHaveLength(2)
expect(result.transactions[0].amount).toBe(-99)
expect(result.transactions[1].amount).toBe(-432.5)
})
it('calculates stats correctly', () => {
const result = parseBankFile(SKANDIA_CSV, 'skandia.csv')
expect(result.stats.total_income).toBe(25000)
expect(result.stats.total_expenses).toBe(-531.5)
expect(result.stats.parsed_rows).toBe(3)
})
it('extracts correct date range', () => {
const result = parseBankFile(SKANDIA_CSV, 'skandia.csv')
expect(result.date_from).toBe('2024-01-13')
expect(result.date_to).toBe('2024-01-15')
})
})
describe('parseBankFile — Lunar format', () => {
it('parses comma-delimited CSV with English headers', () => {
const result = parseBankFile(LUNAR_CSV, 'lunar.csv')
expect(result.format).toBe('lunar')
expect(result.format_name).toBe('Lunar')
expect(result.transactions).toHaveLength(3)
expect(result.issues).toHaveLength(0)
})
it('correctly parses amounts with comma decimal and period thousand separator', () => {
const result = parseBankFile(LUNAR_CSV, 'lunar.csv')
expect(result.transactions[0].amount).toBe(-99)
expect(result.transactions[0].description).toBe('SPOTIFY AB')
expect(result.transactions[0].date).toBe('2024-01-15')
expect(result.transactions[1].amount).toBe(-432.5)
expect(result.transactions[2].amount).toBe(25000)
})
it('parses balance field with period thousand separator', () => {
const result = parseBankFile(LUNAR_CSV, 'lunar.csv')
expect(result.transactions[0].balance).toBe(12345.67)
expect(result.transactions[2].balance).toBe(12877.17)
})
it('calculates stats correctly', () => {
const result = parseBankFile(LUNAR_CSV, 'lunar.csv')
expect(result.stats.total_income).toBe(25000)
expect(result.stats.total_expenses).toBe(-531.5)
expect(result.stats.parsed_rows).toBe(3)
})
it('extracts correct date range', () => {
const result = parseBankFile(LUNAR_CSV, 'lunar.csv')
expect(result.date_from).toBe('2024-01-13')
expect(result.date_to).toBe('2024-01-15')
})
it('does not confuse Lunar (English) with Nordea (Swedish) headers', () => {
// Nordea has Swedish headers, Lunar has English
const nordeaResult = detectFileFormat(NORDEA_CSV, 'test.csv')
const lunarResult = detectFileFormat(LUNAR_CSV, 'test.csv')
expect(nordeaResult!.id).toBe('nordea')
expect(lunarResult!.id).toBe('lunar')
})
})
describe('parseBankFile — camt.053 XML format', () => {
it('parses XML with credit and debit entries', () => {
const result = parseBankFile(CAMT053_XML, 'statement.xml')
expect(result.format).toBe('camt053')
expect(result.format_name).toBe('ISO 20022 camt.053')
expect(result.transactions).toHaveLength(2)
})
it('applies DBIT indicator as negative amount', () => {
const result = parseBankFile(CAMT053_XML, 'statement.xml')
const debit = result.transactions.find((t) => t.description === 'SPOTIFY AB')
expect(debit).toBeDefined()
expect(debit!.amount).toBe(-99)
})
it('applies CRDT indicator as positive amount', () => {
const result = parseBankFile(CAMT053_XML, 'statement.xml')
const credit = result.transactions.find((t) => t.description === 'LÖNEUTBETALNING')
expect(credit).toBeDefined()
expect(credit!.amount).toBe(25000)
})
it('extracts entry reference into raw_line for external ID generation', () => {
const result = parseBankFile(CAMT053_XML, 'statement.xml')
const debit = result.transactions[0]
expect(debit.raw_line).toBe('REF001')
})
it('extracts OCR reference from structured remittance info', () => {
const result = parseBankFile(CAMT053_XML_WITH_STRUCTURED_REF, 'statement.xml')
expect(result.transactions).toHaveLength(1)
expect(result.transactions[0].reference).toBe('OCR123456789')
})
it('uses unstructured remittance info as description', () => {
const result = parseBankFile(CAMT053_XML, 'statement.xml')
expect(result.transactions[0].description).toBe('SPOTIFY AB')
})
it('extracts currency from Amount element', () => {
const result = parseBankFile(CAMT053_XML, 'statement.xml')
result.transactions.forEach((tx) => {
expect(tx.currency).toBe('SEK')
})
})
it('handles XML with no Ntry elements', () => {
const emptyXml = `<?xml version="1.0"?>
<Document xmlns="urn:iso:std:iso:20022:tech:xsd:camt.053.001.02">
<BkToCstmrStmt><Stmt></Stmt></BkToCstmrStmt></Document>`
const result = parseBankFile(emptyXml, 'empty.xml')
expect(result.format).toBe('camt053')
expect(result.transactions).toHaveLength(0)
expect(result.issues.length).toBeGreaterThan(0)
expect(result.issues[0].message).toContain('No <Ntry> elements')
})
})
describe('parseBankFile — explicit format override', () => {
it('uses the specified format instead of auto-detection', () => {
// Force parsing Nordea content as SEB (will produce issues but should use SEB format)
const result = parseBankFile(
'Datum,Transaktion,Kategori,Belopp,Saldo\n2024-01-15,Test,,"-100,00","5000,00"',
'nordea.csv',
'seb'
)
expect(result.format).toBe('seb')
})
it('returns error for unknown formatId', () => {
const result = parseBankFile(NORDEA_CSV, 'test.csv', 'unknown_format' as BankFileFormatId)
expect(result.format).toBe('unknown_format')
expect(result.format_name).toBe('Unknown')
expect(result.transactions).toHaveLength(0)
expect(result.issues).toHaveLength(1)
expect(result.issues[0].severity).toBe('error')
expect(result.issues[0].message).toContain('Unknown format')
})
it('returns format detection error when no format matches and no override given', () => {
const result = parseBankFile(UNKNOWN_CSV, 'unknown.csv')
expect(result.format).toBe('generic_csv')
expect(result.format_name).toBe('Unknown')
expect(result.transactions).toHaveLength(0)
expect(result.issues).toHaveLength(1)
expect(result.issues[0].message).toContain('Could not auto-detect')
})
it('can force generic_csv format by explicit ID', () => {
const csvContent = '2024-01-15,Some purchase,-50.00\n2024-01-16,Income,1000.00'
const result = parseBankFile(csvContent, 'test.csv', 'generic_csv')
// generic_csv uses a default mapping (date=0, description=1, amount=2)
// But the first line is treated as header (skip_rows=1), so only second row is data
expect(result.format).toBe('generic_csv')
})
})
describe('generateExternalId', () => {
const baseTx: ParsedBankTransaction = {
date: '2024-01-15',
description: 'SPOTIFY AB',
amount: -99,
currency: 'SEK',
balance: 12345.67,
reference: null,
counterparty: null,
raw_line: '2024-01-15,SPOTIFY AB,,"-99,00","12 345,67"',
}
it('generates SHA-256 composite key for CSV formats', () => {
const id = generateExternalId(baseTx, 'nordea', 0)
expect(id).toMatch(/^nordea_[0-9a-f]{16}$/)
})
it('generates different IDs for different row indices (same transaction data)', () => {
const id1 = generateExternalId(baseTx, 'nordea', 0)
const id2 = generateExternalId(baseTx, 'nordea', 1)
expect(id1).not.toBe(id2)
})
it('generates different IDs for different formats (same data, same row index)', () => {
const nordeaId = generateExternalId(baseTx, 'nordea', 0)
const sebId = generateExternalId(baseTx, 'seb', 0)
expect(nordeaId).not.toBe(sebId)
})
it('generates deterministic IDs for the same inputs', () => {
const id1 = generateExternalId(baseTx, 'nordea', 0)
const id2 = generateExternalId(baseTx, 'nordea', 0)
expect(id1).toBe(id2)
})
it('uses entry reference for camt.053 transactions with NtryRef', () => {
const camtTx: ParsedBankTransaction = {
date: '2024-01-15',
description: 'SPOTIFY AB',
amount: -99,
currency: 'SEK',
raw_line: 'REF001', // NtryRef stored in raw_line
}
const id = generateExternalId(camtTx, 'camt053', 0)
expect(id).toBe('camt053_REF001')
})
it('falls back to hash for camt.053 when raw_line starts with camt053_entry_', () => {
const camtTx: ParsedBankTransaction = {
date: '2024-01-15',
description: 'SPOTIFY AB',
amount: -99,
currency: 'SEK',
raw_line: 'camt053_entry_0', // Auto-generated fallback reference
}
const id = generateExternalId(camtTx, 'camt053', 0)
// Should fall through to hash-based ID since raw_line starts with 'camt053_entry_'
expect(id).toMatch(/^camt053_[0-9a-f]{16}$/)
})
it('falls back to hash for camt.053 when raw_line is undefined', () => {
const camtTx: ParsedBankTransaction = {
date: '2024-01-15',
description: 'SPOTIFY AB',
amount: -99,
currency: 'SEK',
}
const id = generateExternalId(camtTx, 'camt053', 0)
expect(id).toMatch(/^camt053_[0-9a-f]{16}$/)
})
it('includes amount in hash so different amounts produce different IDs', () => {
const tx1 = { ...baseTx, amount: -99 }
const tx2 = { ...baseTx, amount: -100 }
const id1 = generateExternalId(tx1, 'nordea', 0)
const id2 = generateExternalId(tx2, 'nordea', 0)
expect(id1).not.toBe(id2)
})
it('includes description in hash so different descriptions produce different IDs', () => {
const tx1 = { ...baseTx, description: 'SPOTIFY AB' }
const tx2 = { ...baseTx, description: 'NETFLIX' }
const id1 = generateExternalId(tx1, 'nordea', 0)
const id2 = generateExternalId(tx2, 'nordea', 0)
expect(id1).not.toBe(id2)
})
})
describe('generateFileHash', () => {
it('returns a SHA-256 hex string', () => {
const hash = generateFileHash(NORDEA_CSV)
expect(hash).toMatch(/^[0-9a-f]{64}$/)
})
it('produces deterministic output for the same input', () => {
const hash1 = generateFileHash(NORDEA_CSV)
const hash2 = generateFileHash(NORDEA_CSV)
expect(hash1).toBe(hash2)
})
it('produces different hashes for different content', () => {
const hash1 = generateFileHash(NORDEA_CSV)
const hash2 = generateFileHash(SEB_CSV)
expect(hash1).not.toBe(hash2)
})
it('produces different hash even for tiny content differences', () => {
const hash1 = generateFileHash('abc')
const hash2 = generateFileHash('abd')
expect(hash1).not.toBe(hash2)
})
it('handles empty string', () => {
const hash = generateFileHash('')
expect(hash).toMatch(/^[0-9a-f]{64}$/)
})
})
describe('stats calculation', () => {
it('calculates total_income as sum of positive amounts (Nordea)', () => {
const result = parseBankFile(NORDEA_CSV, 'nordea.csv')
expect(result.stats.total_income).toBe(25000)
})
it('calculates total_expenses as sum of negative amounts (Nordea)', () => {
const result = parseBankFile(NORDEA_CSV, 'nordea.csv')
// -99 + -432.5 = -531.5
expect(result.stats.total_expenses).toBe(-531.5)
})
it('calculates parsed_rows correctly', () => {
const result = parseBankFile(NORDEA_CSV, 'nordea.csv')
expect(result.stats.parsed_rows).toBe(3)
})
it('calculates total_rows (excluding header)', () => {
const result = parseBankFile(NORDEA_CSV, 'nordea.csv')
// 4 lines total - 1 header = 3 data rows
expect(result.stats.total_rows).toBe(3)
})
it('tracks skipped_rows for reserved/preliminary transactions', () => {
const result = parseBankFile(NORDEA_CSV_WITH_RESERVED, 'nordea.csv')
expect(result.stats.skipped_rows).toBe(1)
expect(result.stats.parsed_rows).toBe(2)
})
it('calculates stats correctly for SEB format', () => {
const result = parseBankFile(SEB_CSV, 'seb.csv')
expect(result.stats.total_income).toBe(25000)
expect(result.stats.total_expenses).toBe(-531.5)
expect(result.stats.parsed_rows).toBe(3)
expect(result.stats.skipped_rows).toBe(0)
})
it('calculates stats correctly for Swedbank format', () => {
const result = parseBankFile(SWEDBANK_CSV, 'swedbank.csv')
expect(result.stats.total_income).toBe(25000)
expect(result.stats.total_expenses).toBe(-531.5)
expect(result.stats.parsed_rows).toBe(3)
})
it('calculates stats correctly for camt.053 XML', () => {
const result = parseBankFile(CAMT053_XML, 'statement.xml')
expect(result.stats.total_income).toBe(25000)
expect(result.stats.total_expenses).toBe(-99)
expect(result.stats.parsed_rows).toBe(2)
expect(result.stats.total_rows).toBe(2)
})
it('uses Math.round(x * 100) / 100 for monetary precision', () => {
// Create a file that would produce floating point imprecision
const precisionCSV = [
'Datum,Transaktion,Kategori,Belopp,Saldo',
'2024-01-01,TX1,,"-0,10","100,00"',
'2024-01-02,TX2,,"-0,20","99,90"',
'2024-01-03,TX3,,"-0,30","99,70"',
].join('\n')
const result = parseBankFile(precisionCSV, 'precision.csv')
// 0.1 + 0.2 + 0.3 = 0.6000000000000001 without rounding
// With Math.round(x * 100) / 100, it should be -0.6
expect(result.stats.total_expenses).toBe(-0.6)
})
})
describe('date range extraction', () => {
it('sets date_from to the earliest date', () => {
const result = parseBankFile(NORDEA_CSV, 'nordea.csv')
expect(result.date_from).toBe('2024-01-13')
})
it('sets date_to to the latest date', () => {
const result = parseBankFile(NORDEA_CSV, 'nordea.csv')
expect(result.date_to).toBe('2024-01-15')
})
it('returns null dates for empty transaction set', () => {
const result = parseBankFile(HEADER_ONLY_NORDEA, 'nordea.csv')
expect(result.date_from).toBeNull()
expect(result.date_to).toBeNull()
})
it('handles single-transaction file (date_from equals date_to)', () => {
const singleRow = [
'Datum,Transaktion,Kategori,Belopp,Saldo',
'2024-06-15,ENSKILD BETALNING,,"-500,00","10 000,00"',
].join('\n')
const result = parseBankFile(singleRow, 'single.csv')
expect(result.date_from).toBe('2024-06-15')
expect(result.date_to).toBe('2024-06-15')
})
it('calculates correct date range for camt.053', () => {
const result = parseBankFile(CAMT053_XML, 'statement.xml')
expect(result.date_from).toBe('2024-01-14')
expect(result.date_to).toBe('2024-01-15')
})
it('sorts dates lexicographically (YYYY-MM-DD is naturally sortable)', () => {
const multiMonth = [
'Datum,Transaktion,Kategori,Belopp,Saldo',
'2024-12-31,DEC TX,,"-10,00","1000,00"',
'2024-01-01,JAN TX,,"-20,00","990,00"',
'2024-06-15,JUN TX,,"-30,00","960,00"',
].join('\n')
const result = parseBankFile(multiMonth, 'multimonth.csv')
expect(result.date_from).toBe('2024-01-01')
expect(result.date_to).toBe('2024-12-31')
})
})
describe('empty file handling', () => {
it('returns error result for completely empty file (no auto-detect match)', () => {
const result = parseBankFile(EMPTY_FILE, 'empty.csv')
expect(result.transactions).toHaveLength(0)
expect(result.issues.length).toBeGreaterThan(0)
expect(result.date_from).toBeNull()
expect(result.date_to).toBeNull()
expect(result.stats.parsed_rows).toBe(0)
})
it('returns zero transactions for file with only whitespace', () => {
const whitespace = ' \n \n '
const result = parseBankFile(whitespace, 'blank.csv')
expect(result.transactions).toHaveLength(0)
})
it('returns zero transactions for Nordea header-only file', () => {
const result = parseBankFile(HEADER_ONLY_NORDEA, 'nordea.csv')
expect(result.format).toBe('nordea')
expect(result.transactions).toHaveLength(0)
expect(result.stats.total_rows).toBe(0)
})
})
describe('getFormat and getAllFormats', () => {
it('getFormat returns the correct format by ID', () => {
const nordea = getFormat('nordea')
expect(nordea).toBeDefined()
expect(nordea!.id).toBe('nordea')
expect(nordea!.name).toBe('Nordea')
const seb = getFormat('seb')
expect(seb).toBeDefined()
expect(seb!.id).toBe('seb')
})
it('getFormat returns undefined for unknown ID', () => {
const unknown = getFormat('nonexistent' as BankFileFormatId)
expect(unknown).toBeUndefined()
})
it('getAllFormats returns all registered formats', () => {
const formats = getAllFormats()
expect(formats.length).toBeGreaterThanOrEqual(10)
const ids = formats.map((f) => f.id)
expect(ids).toContain('nordea')
expect(ids).toContain('seb')
expect(ids).toContain('swedbank')
expect(ids).toContain('handelsbanken')
expect(ids).toContain('lansforsakringar')
expect(ids).toContain('ica_banken')
expect(ids).toContain('skandia')
expect(ids).toContain('lunar')
expect(ids).toContain('camt053')
expect(ids).toContain('generic_csv')
})
it('camt053 is listed before bank-specific CSV formats (detection priority)', () => {
const formats = getAllFormats()
const camtIdx = formats.findIndex((f) => f.id === 'camt053')
const nordeaIdx = formats.findIndex((f) => f.id === 'nordea')
expect(camtIdx).toBeLessThan(nordeaIdx)
})
it('generic_csv is listed last (manual fallback only)', () => {
const formats = getAllFormats()
const genericIdx = formats.findIndex((f) => f.id === 'generic_csv')
expect(genericIdx).toBe(formats.length - 1)
})
})
describe('edge cases and robustness', () => {
it('handles Windows-style line endings (CRLF)', () => {
const crlfContent = 'Datum,Transaktion,Kategori,Belopp,Saldo\r\n2024-01-15,SPOTIFY AB,,"-99,00","12 345,67"\r\n'
const result = parseBankFile(crlfContent, 'nordea.csv')
expect(result.format).toBe('nordea')
expect(result.transactions).toHaveLength(1)
expect(result.transactions[0].amount).toBe(-99)
})
it('handles BOM (Byte Order Mark) prefix', () => {
const bomContent = '\uFEFF' + NORDEA_CSV
const result = parseBankFile(bomContent, 'nordea.csv')
expect(result.format).toBe('nordea')
expect(result.transactions).toHaveLength(3)
})
it('handles rows with invalid dates gracefully', () => {
const invalidDate = [
'Bokföringsdag;Valutadag;Verifikationsnummer;Text;Belopp;Saldo',
'not-a-date;2024-01-15;12345;SPOTIFY AB;-99,00;12345,67',
'2024-01-14;2024-01-14;12346;VALID TX;-50,00;12395,67',
].join('\n')
const result = parseBankFile(invalidDate, 'seb.csv')
expect(result.transactions).toHaveLength(1)
expect(result.transactions[0].description).toBe('VALID TX')
expect(result.issues.length).toBeGreaterThan(0)
expect(result.stats.skipped_rows).toBe(1)
})
it('handles rows with invalid amounts gracefully', () => {
const invalidAmount = [
'Datum,Transaktion,Kategori,Belopp,Saldo',
'2024-01-15,SPOTIFY AB,,"abc","12 345,67"',
'2024-01-14,VALID TX,,"-50,00","12 395,67"',
].join('\n')
const result = parseBankFile(invalidAmount, 'nordea.csv')
expect(result.transactions).toHaveLength(1)
expect(result.transactions[0].description).toBe('VALID TX')
expect(result.stats.skipped_rows).toBe(1)
})
it('handles trailing blank lines', () => {
const trailing = NORDEA_CSV + '\n\n\n'
const result = parseBankFile(trailing, 'nordea.csv')
expect(result.transactions).toHaveLength(3)
})
it('handles Handelsbanken CSV with only reskontradatum (no transaktionsdatum)', () => {
const onlyReskontra = [
'Reskontradatum;Text;Belopp;Saldo',
'2024-01-15;SPOTIFY AB;-99,00;12345,67',
].join('\n')
const format = detectFileFormat(onlyReskontra, 'shb.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('handelsbanken')
})
it('handles large amounts without overflow', () => {
const largeAmounts = [
'Datum,Transaktion,Kategori,Belopp,Saldo',
'2024-01-15,BIG TRANSFER,,"1 500 000,00","2 000 000,00"',
].join('\n')
const result = parseBankFile(largeAmounts, 'nordea.csv')
expect(result.transactions).toHaveLength(1)
expect(result.transactions[0].amount).toBe(1500000)
expect(result.transactions[0].balance).toBe(2000000)
})
it('handles zero amounts', () => {
const zeroAmount = [
'Datum,Transaktion,Kategori,Belopp,Saldo',
'2024-01-15,FEE REVERSAL,,"0,00","5 000,00"',
].join('\n')
const result = parseBankFile(zeroAmount, 'nordea.csv')
expect(result.transactions).toHaveLength(1)
expect(result.transactions[0].amount).toBe(0)
})
})
// --- Fix 5: SEB duplicate condition removal ---
describe('SEB detection — no duplicate conditions', () => {
it('detects SEB with bokföringsdag header', () => {
const content = 'Bokföringsdag;Valutadag;Text;Belopp;Saldo\n2024-01-15;2024-01-15;Test;-100,00;5000,00'
const format = detectFileFormat(content, 'seb.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('seb')
})
it('detects SEB with bokforingsdatum header (no diacritics)', () => {
const content = 'Bokforingsdatum;Valutadag;Text;Belopp;Saldo\n2024-01-15;2024-01-15;Test;-100,00;5000,00'
const format = detectFileFormat(content, 'seb.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('seb')
})
})
// --- Fix 6: Länsförsäkringar false positive prevention ---
describe('Länsförsäkringar detection — false positive prevention', () => {
it('detects valid LF data rows with comma-decimal amounts', () => {
const format = detectFileFormat(LANSFORSAKRINGAR_CSV, 'lf.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('lansforsakringar')
})
it('detects LF header-less data with two dates and comma-decimal amount', () => {
const format = detectFileFormat(LANSFORSAKRINGAR_CSV_NO_HEADER, 'lf.csv')
expect(format).not.toBeNull()
expect(format!.id).toBe('lansforsakringar')
})
it('does not false-positive on generic semicolon CSV with two date columns but non-numeric 5th field', () => {
// This CSV has two date columns + 5 fields but the 5th field is not a number
const falsePositive = [
'"2024-01-15";"2024-01-15";"Typ";"Text";"not-a-number"',
].join('\n')
const format = detectFileFormat(falsePositive, 'generic.csv')
// Should NOT detect as Länsförsäkringar
expect(format?.id).not.toBe('lansforsakringar')
})
})
// --- Fix 7: Generic CSV column bounds checking ---
describe('parseGenericCSV — column bounds checking', () => {
it('skips rows with too few columns and adds warning', () => {
const content = [
'Date,Description,Amount',
'2024-01-15,Test,-100.00',
'2024-01-16,Short', // Only 2 columns, mapping needs column 2 (amount)
].join('\n')
const result = parseGenericCSV(content, {
date: 0,
description: 1,
amount: 2,
delimiter: ',',
decimal_separator: '.',
skip_rows: 1,
date_format: 'YYYY-MM-DD',
})
expect(result.transactions).toHaveLength(1)
expect(result.transactions[0].description).toBe('Test')
expect(result.stats.skipped_rows).toBe(1)
expect(result.issues.some((i) => i.message.includes('columns but mapping requires'))).toBe(true)
})
it('skips rows when mapping index exceeds field count', () => {
const content = [
'A,B',
'val1,val2',
].join('\n')
const result = parseGenericCSV(content, {
date: 0,
description: 1,
amount: 5, // Column 5 does not exist (only 2 columns)
delimiter: ',',
decimal_separator: '.',
skip_rows: 1,
date_format: 'YYYY-MM-DD',
})
expect(result.transactions).toHaveLength(0)
expect(result.stats.skipped_rows).toBe(1)
expect(result.issues).toHaveLength(1)
})
it('parses normally when all columns are within bounds', () => {
const content = [
'Date,Description,Amount',
'2024-01-15,SPOTIFY,-99.00',
'2024-01-16,SALARY,25000.00',
].join('\n')
const result = parseGenericCSV(content, {
date: 0,
description: 1,
amount: 2,
delimiter: ',',
decimal_separator: '.',
skip_rows: 1,
date_format: 'YYYY-MM-DD',
})
expect(result.transactions).toHaveLength(2)
expect(result.stats.skipped_rows).toBe(0)
expect(result.issues).toHaveLength(0)
})
})
// --- Fix 8: parseCSVLine unclosed quote handling ---
describe('parseCSVLine — unclosed quote handling', () => {
it('handles normal quoted fields correctly', () => {
const fields = parseCSVLine('"hello","world"', ',')
expect(fields).toEqual(['hello', 'world'])
})
it('handles escaped quotes (doubled) inside fields', () => {
const fields = parseCSVLine('"he said ""hi""",other', ',')
expect(fields).toEqual(['he said "hi"', 'other'])
})
it('produces a result even with unclosed quotes instead of hanging', () => {
// Unclosed quote: the parser should not hang or crash
const fields = parseCSVLine('"unclosed,field2,field3', ',')
// With unclosed quote, everything after the opening quote is one field
// The important thing is it doesn't crash and returns something
expect(fields.length).toBeGreaterThan(0)
})
it('preserves data with unclosed quote rather than losing it', () => {
const fields = parseCSVLine('normal,"unclosed value', ',')
// Should have at least the first field and whatever was accumulated
expect(fields.length).toBe(2)
expect(fields[0]).toBe('normal')
// The unclosed quoted field should still contain the text
expect(fields[1]).toContain('unclosed value')
})
it('handles semicolon delimiter with quotes', () => {
const fields = parseCSVLine('"2024-01-15";"SPOTIFY AB";"-99,00"', ';')
expect(fields).toEqual(['2024-01-15', 'SPOTIFY AB', '-99,00'])
})
})