Spaces:
Sleeping
Sleeping
| import re | |
| from datetime import date, datetime | |
| from typing import Any, Iterable, TypeVar | |
| T = TypeVar("T") | |
| def parse_date(value: Any) -> date | None: | |
| if value is None or value == "": | |
| return None | |
| if isinstance(value, datetime): | |
| return value.date() | |
| if isinstance(value, date): | |
| return value | |
| text = str(value).strip() | |
| if not text: | |
| return None | |
| # `%d/%m/%Y %H:%M` is how the TARIC daily publications write every date. | |
| for date_format in ( | |
| "%Y-%m-%d", | |
| "%d-%m-%Y", | |
| "%d/%m/%Y", | |
| "%d/%m/%Y %H:%M", | |
| "%Y/%m/%d", | |
| "%d.%m.%Y", | |
| "%Y%m%d", | |
| ): | |
| try: | |
| return datetime.strptime(text, date_format).date() | |
| except ValueError: | |
| continue | |
| try: | |
| return datetime.fromisoformat(text).date() | |
| except ValueError: | |
| return None | |
| def normalize_ws(value: Any) -> str | None: | |
| if value is None: | |
| return None | |
| text = re.sub(r"\s+", " ", str(value)).strip() | |
| return text or None | |
| def parse_number(value: Any) -> float | None: | |
| if value is None or value == "": | |
| return None | |
| if isinstance(value, (int, float)): | |
| return float(value) | |
| text = str(value).strip().replace(" ", "").replace(" ", "") | |
| if not text: | |
| return None | |
| if "," in text and "." in text: | |
| text = text.replace(".", "") if text.rfind(",") > text.rfind(".") else text | |
| text = text.replace(",", ".") if text.count(".") <= 1 else text.replace(",", "") | |
| else: | |
| text = text.replace(",", ".") | |
| try: | |
| return float(re.sub(r"[^0-9.\-]", "", text)) | |
| except ValueError: | |
| return None | |
| def normalize_country(value: Any) -> str | None: | |
| if value is None: | |
| return None | |
| text = re.sub(r"[^A-Za-z]", "", str(value)).upper() | |
| if len(text) < 2: | |
| return None | |
| return text[:2] | |
| def dedupe(items: Iterable[T]) -> list[T]: | |
| seen: set[T] = set() | |
| result: list[T] = [] | |
| for item in items: | |
| if item not in seen: | |
| seen.add(item) | |
| result.append(item) | |
| return result | |