50 lines
2.0 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""Сборщики ответов ИС для тестов нормализатора (набор json, задачи 3, 4 и 6)."""
from typing import Any
OK = {"code": "", "message": ""}
BAD = {"code": "INVALID_DOCUMENT", "message": "Не удалось определить тип документа."}
HEAD = {
"organization": {"form_name": "ООО «Пример»", "confidence": 100.0},
"inn": {"form_name": "7700000000", "confidence": 100.0},
"units": {"form_name": "тыс. руб.", "confidence": 100.0},
"date": {"form_name": "на 31 декабря 2024 г.", "confidence": 100.0},
}
BALANCE = [
("Наименование показателя", "Код", "На 31 декабря 2024 г."),
("Запасы", "1210", "60"),
("Дебиторы", "1230", "40"),
("Итого II", "1200", "100"),
("НМА", "1110", "50"),
("Итого I", "1100", "50"),
("БАЛАНС", "1600", "150"),
("Капитал", "1310", "150"),
("Итого III", "1300", "150"),
("БАЛАНС", "1700", "150"),
]
INCOME = [
("Наименование показателя", "Код", "За 2024 г."),
("Выручка", "2110", "100"),
("Себестоимость", "2120", "(60)"),
("Валовая прибыль", "2100", "40"),
("Прибыль от продаж", "2200", "40"),
]
def ocr_table(label: str, rows: list[tuple[str, ...]]) -> dict[str, Any]:
return {
"label": {"form_name": label, "confidence": 100.0},
"rows": [
{"row_index": i, "cells": [{"column_index": c, "value": v, "confidence": 100.0} for c, v in enumerate(r)]}
for i, r in enumerate(rows)
],
}
def response(*tables: dict[str, Any], error: dict[str, str] = OK, head: dict[str, Any] = HEAD) -> dict[str, Any]:
return {"file_uid": "x", "error": error, "data_ocr": {**head, "table_structure": list(tables)}}
def merged(*files: tuple[str, Any]) -> dict[str, Any]:
return {"job_id": "j", "files": [{"name": n, "response": r, "parse_error": None} for n, r in files]}