75-123 rule

app/pipeline/mapping.py

@@ -106,6 +106,9 @@ def _build_rules(mapping_data: list[dict[str, str | int]]) -> tuple[MappingRule,
             candidates = ["ИННФЛИП", "ИННФЛ", "ИННЮЛ", "ИНН", *candidates]
         if column == "Тип участника":
             candidates = ["Тип", "ТипУчастника", *candidates]
+        if column == "Отчество":
+            # В некоторых выгрузках встречается опечатка тега "Очт".
+            candidates = ["Отч", "Очт", *candidates]
         if path:
             for path_tag in _extract_path_candidate_keys(path):
                 if path_tag not in candidates:
@@ -334,6 +337,7 @@ def build_fixed_row(
             )
     _apply_structured_group_rules(row)
     _apply_conditional_rules_1_74(row)
+    _apply_conditional_rules_75_123(row)
     for column in FIXED_REPORT_COLUMNS:
         row.setdefault(column, "")
     return row
@@ -531,3 +535,19 @@ def _apply_conditional_rules_1_74(row: dict[str, str]) -> None:
     # 62. Статус перевода заполняется только для видов 2/5/8.
     if transfer_type not in {"2", "5", "8"}:
         _set_row_value(row, 62, "")
+
+
+def _apply_conditional_rules_75_123(row: dict[str, str]) -> None:
+    codes = _operation_and_extra_codes(row)
+
+    # 96. Код территории заполняется только для признака 5016 (дубль 36).
+    if "5016" not in codes:
+        _set_row_value(row, 96, "")
+
+    # 103. Если операция без участия сотрудника и данных нет -> подставляем заглушку.
+    if _row_value(row, 104) == "0" and not _row_value(row, 103):
+        _set_row_value(row, 103, "Информация отсутствует")
+
+    # 105. Аналогично для наименования иностранного банка.
+    if _row_value(row, 104) == "0" and not _row_value(row, 105):
+        _set_row_value(row, 105, "Информация отсутствует")

app/pipeline/report.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import shutil
 from dataclasses import dataclass
+from datetime import date, datetime
 from pathlib import Path
 from tempfile import NamedTemporaryFile
 from typing import Iterable
@@ -135,13 +136,19 @@ class StreamingReportWriter:
             operation_fields=row.operation_fields,
             participant_fields=row.participant_fields,
         )
-        values: list[object] = []
         for index, column_name in enumerate(self.columns):
             raw_value = data.get(column_name, "")
-            values.append(raw_value)
+            default_format = self._column_formats[index]
-        for index, value in enumerate(values):
+            value, cell_format = self._normalize_cell_value(
-            cell_format = self._column_formats[index]
+                column_name=column_name,
-            if cell_format is not None:
+                raw_value=raw_value,
+                default_format=default_format,
+            )
+            if isinstance(value, datetime) and cell_format is self._date_format:
+                self.sheet.write_datetime(
+                    self._next_data_row, index, value, cell_format
+                )
+            elif cell_format is not None:
                 self.sheet.write(self._next_data_row, index, value, cell_format)
             else:
                 self.sheet.write(self._next_data_row, index, value)
@@ -186,6 +193,40 @@ class StreamingReportWriter:
             return self._sum_format
         return None
 
+    def _normalize_cell_value(
+        self,
+        *,
+        column_name: str,
+        raw_value: object,
+        default_format,
+    ) -> tuple[object, object | None]:
+        if default_format is self._date_format:
+            parsed_date = self._parse_date_value(raw_value)
+            if parsed_date is not None:
+                return parsed_date, self._date_format
+            if raw_value in (None, ""):
+                return "", None
+            return raw_value, None
+        return raw_value, default_format
+
+    def _parse_date_value(self, value: object) -> datetime | None:
+        if isinstance(value, datetime):
+            return value
+        if isinstance(value, date):
+            return datetime.combine(value, datetime.min.time())
+        if not isinstance(value, str):
+            return None
+        normalized = value.strip()
+        if not normalized:
+            return None
+        date_part = normalized.split()[0]
+        for fmt in ("%Y-%m-%d", "%d/%m/%Y", "%d.%m.%Y", "%Y/%m/%d"):
+            try:
+                return datetime.strptime(date_part, fmt)
+            except ValueError:
+                continue
+        return None
+
     def _cleanup_temp_file(self) -> None:
         try:
             self._temp_report_path.unlink(missing_ok=True)

tests/unit/test_mapping.py

@@ -377,3 +377,62 @@ def test_operator_type_conditions_clear_irrelevant_bank_fields() -> None:
     assert row["БИК банка получателя"] == ""
     assert row["Номер счета банка плательщика"] == ""
     assert row["Номер счета банка получателя"] == ""
+
+
+def test_col96_territory_code_cleared_when_operation_is_not_5016() -> None:
+    row = build_fixed_row(
+        file_name="f.xml",
+        record_id="R1",
+        operation_index=1,
+        operation_fields={
+            "КодОперации": "5007",
+            "КодТерИнГос": "840",
+        },
+        participant_fields={},
+    )
+    assert row["Код территории"] == ""
+
+
+def test_col103_and_105_fill_info_absent_when_no_employee_and_empty() -> None:
+    row = build_fixed_row(
+        file_name="f.xml",
+        record_id="R1",
+        operation_index=1,
+        operation_fields={
+            "ПризнакСотрудник": "0",
+        },
+        participant_fields={},
+    )
+    assert row["Сведения о держателе платежной карты"] == "Информация отсутствует"
+    assert row["Наименование иностранного банка"] == "Информация отсутствует"
+
+
+def test_col103_and_105_keep_original_values_when_present() -> None:
+    row = build_fixed_row(
+        file_name="f.xml",
+        record_id="R1",
+        operation_index=1,
+        operation_fields={
+            "ПризнакСотрудник": "0",
+            "СведДержательКарты": "Иванов И.И.",
+            "НаимИнБанк": "FOREIGN BANK",
+        },
+        participant_fields={},
+    )
+    assert row["Сведения о держателе платежной карты"] == "Иванов И.И."
+    assert row["Наименование иностранного банка"] == "FOREIGN BANK"
+
+
+def test_patronymic_supports_typo_tag_ocht() -> None:
+    row = build_fixed_row(
+        file_name="f.xml",
+        record_id="R1",
+        operation_index=1,
+        operation_fields={},
+        participant_fields={
+            "УчастникФЛИП.СведФЛИП.ФИОФЛИП.Фам": "Азимов",
+            "УчастникФЛИП.СведФЛИП.ФИОФЛИП.Имя": "Ислом",
+            "УчастникФЛИП.СведФЛИП.ФИОФЛИП.Очт": "Каримович",
+        },
+    )
+    assert row["Отчество"] == "Каримович"

tests/unit/test_report.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+from datetime import datetime
 from pathlib import Path
 
 from openpyxl import load_workbook
@@ -15,7 +16,7 @@ def test_write_report_streaming_preserves_header_and_formats(tmp_path: Path) ->
             file_name="SKO115FZ_01_123456789_20260616_X00001.xml",
             record_id="RID-1",
             operation_index=1,
-            operation_fields={"СуммаОпер": "100.50", "ДатаОпер": "2026-06-16"},
+            operation_fields={"СумОперации": "100.50", "ДатаСообщения": "2026-06-16"},
             participant_fields={},
         )
     ]
@@ -33,26 +34,11 @@ def test_write_report_streaming_preserves_header_and_formats(tmp_path: Path) ->
     ]
     assert "SKO115FZ_01_123456789_20260616_X00001.xml" in row_values
 
-    date_col_idx = next(
+    date_col_idx = FIXED_REPORT_COLUMNS.index("Дата сообщения") + 1
-        (
+    assert isinstance(sheet.cell(row=3, column=date_col_idx).value, datetime)
-            index
-            for index, column in enumerate(FIXED_REPORT_COLUMNS, start=1)
-            if "Дата" in column
-        ),
-        None,
-    )
-    if date_col_idx is not None:
     assert sheet.cell(row=3, column=date_col_idx).number_format == "DD.MM.YYYY"
 
-    sum_col_idx = next(
+    sum_col_idx = FIXED_REPORT_COLUMNS.index("Сумма в валюте проведения") + 1
-        (
-            index
-            for index, column in enumerate(FIXED_REPORT_COLUMNS, start=1)
-            if "Сумм" in column or "Сумма" in column
-        ),
-        None,
-    )
-    if sum_col_idx is not None:
     assert sheet.cell(row=3, column=sum_col_idx).number_format == "#,##0.00"
 
 
@@ -77,6 +63,53 @@ def test_write_report_contains_top_group_header_row(tmp_path: Path) -> None:
     assert merged_ranges == expected_ranges
 
 
+def test_write_report_converts_date_string_to_excel_date(tmp_path: Path) -> None:
+    destination = tmp_path / "report.xlsx"
+    rows = [
+        ReportRow(
+            file_name="f.xml",
+            record_id="RID",
+            operation_index=1,
+            operation_fields={"ДатаСообщения": "23/08/2005"},
+            participant_fields={},
+        )
+    ]
+
+    write_report(rows, destination)
+
+    workbook = load_workbook(destination)
+    sheet = workbook["Отчет"]
+    date_col_idx = FIXED_REPORT_COLUMNS.index("Дата сообщения") + 1
+    cell = sheet.cell(row=3, column=date_col_idx)
+    assert isinstance(cell.value, datetime)
+    assert cell.value.date() == datetime(2005, 8, 23).date()
+    assert cell.number_format == "DD.MM.YYYY"
+
+
+def test_write_report_keeps_invalid_date_as_text_without_date_format(
+    tmp_path: Path,
+) -> None:
+    destination = tmp_path / "report.xlsx"
+    rows = [
+        ReportRow(
+            file_name="f.xml",
+            record_id="RID",
+            operation_index=1,
+            operation_fields={"ДатаСообщения": "не дата"},
+            participant_fields={},
+        )
+    ]
+
+    write_report(rows, destination)
+
+    workbook = load_workbook(destination)
+    sheet = workbook["Отчет"]
+    date_col_idx = FIXED_REPORT_COLUMNS.index("Дата сообщения") + 1
+    cell = sheet.cell(row=3, column=date_col_idx)
+    assert cell.value == "не дата"
+    assert cell.number_format != "DD.MM.YYYY"
+
+
 def _column_letter(index: int) -> str:
     value = index
     result = ""