fix: parse extended Ourocard country layouts

docs/imports.md

@@ -138,7 +138,7 @@ both occurrence and posting dates. OFX and PDF are unsupported.
 | Profile | Accepted layout |
 | --- | --- |
 | `BANK_CSV_V1` | Bank account CSV, comma-delimited with CSV quoting, at least six header columns; date at column 0 as `DD/MM/YYYY`, description at 2, signed decimal-point amount at 5. Each record must match the header width. |
-| `OUROCARD_FULL_V1` | Card TXT, `DD.MM.YYYY`, 37-character description/location field, two-character country field, debit and credit in Brazilian decimal notation. A separate `PGTO DEBITO CONTA` layout is recognized. |
+| `OUROCARD_FULL_V1` | Card TXT, `DD.MM.YYYY`, with either a 37-character description/location field plus a two-character country field, or a 33-character description/location field plus a seven-character country field; debit and credit use Brazilian decimal notation. A separate `PGTO DEBITO CONTA` layout is recognized. |
 | `OUROCARD_PARTIAL_V1` | Card TXT, `DD/MM`, 43-character description/location field, country, debit and credit; requires an explicit date interval. |
 
 CSV header aliases are case/accent insensitive: date accepts `Data`,

ingestion/parsers.py

@@ -85,7 +85,9 @@ def _txt_items(text, profile, skipped):
     partial = profile == 'OUROCARD_PARTIAL_V1'
     date_size, body_size = (5, 43) if partial else (10, 37)
     date_re = r'\d{2}/\d{2}' if partial else r'\d{2}\.\d{2}\.\d{4}'
-    regular = re.compile(rf'^({date_re})(.{{{body_size}}})([A-Z ]{{2}})\s+(\S+)\s+(\S+)\s*$')
+    regular = [re.compile(rf'^({date_re})(.{{{body_size}}})([A-Z ]{{2}})\s+(\S+)\s+(\S+)\s*$')]
+    if profile == 'OUROCARD_FULL_V1':
+        regular.append(re.compile(rf'^({date_re})(.{{33}})([A-Za-z ]{{7}})\s+(\S+)\s+(\S+)\s*$'))
     payment = re.compile(rf'^({date_re})\s*(PGTO DEBITO CONTA.*?)200211\s+(\S+)\s+(\S+)\s*$')
     section, section_count = '1', 0
     for number, line in enumerate(text.splitlines(), 1):
@@ -100,7 +102,7 @@ def _txt_items(text, profile, skipped):
             skipped['balance'] += 1
         elif match := payment.fullmatch(line):
             yield ParsedItem(locator, section, match[1], match[2].strip(), match[3], match[4], True)
-        elif match := regular.fullmatch(line):
+        elif match := next((candidate for pattern in regular if (candidate := pattern.fullmatch(line))), None):
             if _balance(match[2]):
                 skipped['balance'] += 1
             else:

tests/test_import_parsers.py

@@ -20,6 +20,10 @@ def card_line(day='15.02.2026', body='LOJA INVENTADA', debit='12,34', credit='0,
     return day + body.ljust(43 if partial else 37) + 'BR' + f' {debit} {credit}'
 
 
+def alternate_full_card_line(day='15.02.2026', body='LOJA EXTERIOR', country='ESTADOS', debit='12,34', credit='0,00'):
+    return day + body.ljust(33) + country.ljust(7) + f' {debit} {credit}'
+
+
 def card(text, partial=False, context=None):
     return normalize(parse_document(text.encode(), 'OUROCARD_PARTIAL_V1' if partial else 'OUROCARD_FULL_V1', context))
 
@@ -60,6 +64,14 @@ def test_full_card_sections_installments_credit_and_payment():
     assert rows[3].description == 'unknown text'
 
 
+@pytest.mark.parametrize('country', ['ESTADOS', 'Brasil'])
+def test_full_card_accepts_extended_country_layout(country):
+    row = card(alternate_full_card_line(country=country))[0]
+    assert row.errors == ()
+    assert row.description == 'LOJA EXTERIOR'
+    assert row.amount == '-12.34'
+
+
 def test_card_ambiguity_bad_shapes_and_installments_block():
     assert 'AMBIGUOUS_AMOUNT' in card(card_line(debit='2,00', credit='1,00'))[0].errors
     assert 'INVALID_ROW' in card('15.02.2026 MALFORMED')[0].errors