nikolaandClaude Opus 5
b0026c5a79
A data directory holds one folder per account. Statements dropped into those folders are parsed into a rebuildable SQLite index, categorised by ordered glob rules in rules.toml, and browsed or hand-tagged in a Bubble Tea TUI. Movements between the user's own accounts are marked as transfers by the same rules and excluded from spending totals. Manual tags and transfer marks are stored separately from the rule-derived ones and always win, so editing rules.toml and re-running retag never destroys hand edits. Parsers are pluggable. Three are ported from the Python extractors they replace -- nlb and traderepublic read PDFs via pdftotext -layout, revolut reads the CSV export -- alongside a configurable-column CSV parser and a cmd parser that shells out to an external script. Both ports fix two latent bugs in the originals: the sign character class rejected the typographic minus U+2212 that some PDF fonts emit, and NLB's hardcoded continuation indent broke when pdftotext compressed runs of spaces, so the threshold is now measured from the description column. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
117 lines
3.9 KiB
Go
117 lines
3.9 KiB
Go
package parser
|
|
|
|
import "testing"
|
|
|
|
// A page as pdftotext -layout renders it: a header, transaction lines ending
|
|
// in amount and balance, and indented continuation lines carrying wrapped
|
|
// descriptions and the counterparty IBAN.
|
|
// The description column sits at 15, which is what the script's
|
|
// CONTINUATION_INDENT tells us about the real layout.
|
|
const nlbPage = ` NLB d.d.
|
|
IZPISEK 001/2026
|
|
|
|
DATUM OPIS ZNESEK STANJE
|
|
|
|
02.01.26 PLACILO S KARTICO -45,20 1.234,56
|
|
LIDL SOFIA 4412 SI56 1234 5678 9012 345
|
|
05.01.26 PRILIV PLACE +2.500,00 3.734,56
|
|
ACME DOO
|
|
10.01.26 PRENOS NA VARCEVALNI -500,00 3.234,56
|
|
15.01.26 NEGATIVNO STANJE -3.300,00 65,44-
|
|
|
|
Stran 1
|
|
`
|
|
|
|
func TestParseNLBText(t *testing.T) {
|
|
txns, err := parseNLBText(nlbPage, 2)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if len(txns) != 4 {
|
|
t.Fatalf("got %d transactions, want 4: %+v", len(txns), txns)
|
|
}
|
|
|
|
first := txns[0]
|
|
if first.Date != "2026-01-02" {
|
|
t.Errorf("date = %q, want 2026-01-02", first.Date)
|
|
}
|
|
// The continuation line is appended to the description.
|
|
if first.Description != "PLACILO S KARTICO LIDL SOFIA 4412" {
|
|
t.Errorf("description = %q", first.Description)
|
|
}
|
|
// ...and the IBAN in its second column becomes the counterparty.
|
|
if first.Counterparty != "SI56 1234 5678 9012 345" {
|
|
t.Errorf("counterparty = %q", first.Counterparty)
|
|
}
|
|
if first.AmountMinor != -4520 {
|
|
t.Errorf("amount = %d, want -4520", first.AmountMinor)
|
|
}
|
|
if first.BalanceMinor == nil || *first.BalanceMinor != 123456 {
|
|
t.Errorf("balance = %v, want 123456", first.BalanceMinor)
|
|
}
|
|
|
|
if txns[1].AmountMinor != 250000 {
|
|
t.Errorf("credit amount = %d, want 250000", txns[1].AmountMinor)
|
|
}
|
|
if txns[1].Description != "PRILIV PLACE ACME DOO" {
|
|
t.Errorf("description = %q", txns[1].Description)
|
|
}
|
|
|
|
// A transaction with no continuation line keeps an empty counterparty.
|
|
if txns[2].Counterparty != "" {
|
|
t.Errorf("counterparty = %q, want empty", txns[2].Counterparty)
|
|
}
|
|
|
|
// A trailing minus marks a negative balance.
|
|
if txns[3].BalanceMinor == nil || *txns[3].BalanceMinor != -6544 {
|
|
t.Errorf("balance = %v, want -6544", txns[3].BalanceMinor)
|
|
}
|
|
}
|
|
|
|
// A wrapped line at the top of a page must not attach to the last transaction
|
|
// of the previous page.
|
|
func TestParseNLBPageBoundary(t *testing.T) {
|
|
text := "02.01.26 FIRST -10,00 100,00\n" +
|
|
"\f" +
|
|
" STRAY CONTINUATION AT TOP OF PAGE\n" +
|
|
"03.01.26 SECOND -20,00 80,00\n" +
|
|
" REAL CONTINUATION\n"
|
|
|
|
txns, err := parseNLBText(text, 2)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if len(txns) != 2 {
|
|
t.Fatalf("got %d transactions, want 2", len(txns))
|
|
}
|
|
if txns[0].Description != "FIRST" {
|
|
t.Errorf("first description = %q, want FIRST (page furniture must not leak in)", txns[0].Description)
|
|
}
|
|
if txns[1].Description != "SECOND REAL CONTINUATION" {
|
|
t.Errorf("second description = %q", txns[1].Description)
|
|
}
|
|
}
|
|
|
|
// Shallowly indented lines are footers, not wrapped descriptions.
|
|
func TestParseNLBIgnoresShallowIndent(t *testing.T) {
|
|
text := "02.01.26 FIRST -10,00 100,00\n" +
|
|
" Stran 1 od 2\n"
|
|
|
|
txns, err := parseNLBText(text, 2)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if len(txns) != 1 || txns[0].Description != "FIRST" {
|
|
t.Errorf("got %+v, want a single FIRST transaction", txns)
|
|
}
|
|
}
|
|
|
|
// A date-led line without an amount and balance is a real problem, not
|
|
// something to silently drop.
|
|
func TestParseNLBRejectsMalformedLine(t *testing.T) {
|
|
text := "02.01.26 NO AMOUNT OR BALANCE HERE\n"
|
|
if _, err := parseNLBText(text, 2); err == nil {
|
|
t.Error("expected an error for a transaction line with no amount")
|
|
}
|
|
}
|