Drop counterparty, the generic parsers and .money/
counterparty was a structured field only nlb could fill honestly. revolut and traderepublic invented one by running an IBAN-shaped regex over the description they had just built, and the two spellings disagreed -- SI56 1234 5678 9012 345 against SI56123456789012345 -- so a literal rule pattern that worked on one account silently matched nothing on another. It is gone from the model, the index, the rule keys, ls --wide and the rules screen. nlb now appends its IBAN column to the end of the description, where the other two already keep theirs, so match = "*SI56*" works everywhere. That changes those descriptions and with them their fingerprints, so a statement overlapping an already-imported period will re-add rather than dedupe those rows until the index is rebuilt. An index built by an older binary drops the column when it is opened. The index itself moves from .money/index.db up to index.db beside rules.toml. Nothing looks in the old location, so an existing one has to be moved by hand -- otherwise the tool quietly starts a fresh index and the manual tags in the old file, the only thing statements cannot reproduce, stay behind in it. The csv and cmd parsers are gone along with the [csv] and [cmd] config they carried. cmd shelled out to the Python extractors, which were ported to Go and deleted, so it bridged to nothing; csv was a generic column-mapped fallback that no account used, and between them they were the largest configuration surface in the tool. A bank is now described in Go, where it can be tested. The importer tests register their own three-column parser rather than borrow a bank's, so they stay about the directory walk, dedupe and per-file error reporting. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
+19
-12
@@ -18,8 +18,8 @@ func init() {
|
||||
// nlbParser reads an NLB izpisek PDF.
|
||||
//
|
||||
// A transaction starts on a line beginning with a dd.mm.yy date and ends with
|
||||
// the signed amount and the running balance. Long descriptions and the
|
||||
// counterparty account wrap onto indented continuation lines below.
|
||||
// the signed amount and the running balance. Long descriptions and the other
|
||||
// side's account number wrap onto indented continuation lines below.
|
||||
type nlbParser struct {
|
||||
digits int
|
||||
}
|
||||
@@ -37,7 +37,9 @@ var (
|
||||
`(?P<balance>[-\x{2212}]?[\d.,]+[-\x{2212}]?)\s*$`)
|
||||
// Columns inside a line are separated by four or more spaces.
|
||||
nlbFieldSplit = regexp.MustCompile(`\s{4,}`)
|
||||
// A Slovenian IBAN, which is the counterparty account when present.
|
||||
// A Slovenian IBAN, which NLB prints in a column of its own. It is split
|
||||
// out only so that its wrapped fragments can be rejoined; the result goes
|
||||
// onto the end of the description, where every other parser keeps it.
|
||||
nlbAccount = regexp.MustCompile(`^SI\d{2}(?:\s?\d{4}){3}\s?\d{3}$`)
|
||||
)
|
||||
|
||||
@@ -63,9 +65,12 @@ func (p *nlbParser) Parse(path string, acc *config.Account) ([]RawTxn, error) {
|
||||
// be tested against captured pdftotext output.
|
||||
func parseNLBText(text string, digits int) ([]RawTxn, error) {
|
||||
var (
|
||||
txns []RawTxn
|
||||
accts []string // counterparty per transaction, built up alongside
|
||||
descAt int // description column of the last transaction line
|
||||
txns []RawTxn
|
||||
// The account column per transaction, built up alongside because it
|
||||
// wraps in fragments of its own and has to be rejoined before it can
|
||||
// be appended to the description.
|
||||
trailing []string
|
||||
descAt int // description column of the last transaction line
|
||||
)
|
||||
|
||||
for _, page := range pages(text) {
|
||||
@@ -84,7 +89,7 @@ func parseNLBText(text string, digits int) ([]RawTxn, error) {
|
||||
return nil, fmt.Errorf("line %d: %w", i+1, err)
|
||||
}
|
||||
txns = append(txns, txn)
|
||||
accts = append(accts, account)
|
||||
trailing = append(trailing, account)
|
||||
descAt = col
|
||||
continue
|
||||
}
|
||||
@@ -104,20 +109,22 @@ func parseNLBText(text string, digits int) ([]RawTxn, error) {
|
||||
last := len(txns) - 1
|
||||
txns[last].Description += " " + parts[0]
|
||||
if len(parts) > 1 {
|
||||
accts[last] = strings.TrimSpace(accts[last] + " " + parts[1])
|
||||
trailing[last] = strings.TrimSpace(trailing[last] + " " + parts[1])
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The account column goes last rather than in the position it occupied on
|
||||
// the page, so that an IBAN wrapped over several lines stays contiguous
|
||||
// and a glob can match it.
|
||||
for i := range txns {
|
||||
txns[i].Counterparty = accts[i]
|
||||
txns[i].Description = strings.Join(strings.Fields(txns[i].Description), " ")
|
||||
txns[i].Description = strings.Join(strings.Fields(txns[i].Description+" "+trailing[i]), " ")
|
||||
}
|
||||
return txns, nil
|
||||
}
|
||||
|
||||
// parseNLBLine parses one transaction line, returning the transaction, the
|
||||
// counterparty account found among its columns, and the column at which the
|
||||
// account number found among its columns, and the column at which the
|
||||
// description starts, which is where its wrapped lines will sit.
|
||||
func parseNLBLine(line string, digits int) (RawTxn, string, int, error) {
|
||||
trimmed := strings.TrimRight(line, " \t\r")
|
||||
@@ -154,7 +161,7 @@ func parseNLBLine(line string, digits int) (RawTxn, string, int, error) {
|
||||
return RawTxn{}, "", 0, fmt.Errorf("balance %q: %w", balance, err)
|
||||
}
|
||||
|
||||
// The middle holds the description and, sometimes, the counterparty IBAN.
|
||||
// The middle holds the description and, sometimes, the IBAN.
|
||||
var (
|
||||
account string
|
||||
desc []string
|
||||
|
||||
Reference in New Issue
Block a user