paulocoutinhox
commented
3 months ago I try isolate the expression and it works in that case:
from __future__ import annotations
from enum import Enum
from typing import Any
from typing import Type
import re
class Book(Enum):
def __new__(
cls: Type[Book],
*args: dict[str, Any],
**kwargs: dict[str, Any],
) -> Book:
obj: Book = object.__new__(cls)
obj._value_ = args[0]
return obj
def __init__(
self: Book,
_: int,
title: str,
regular_expression: str,
abbreviations: tuple[str, ...],
) -> None:
"""Set the title and regular_expression properties."""
self._title_ = title
self._regular_expression_ = regular_expression
self._abbreviations_ = abbreviations
@property
def title(self: Book) -> str:
return self._title_
@property
def regular_expression(self: Book) -> str:
return self._regular_expression_
@property
def abbreviations(self: Book) -> tuple[str, ...]:
return self._abbreviations_
LEVITICUS = 3, "Leviticus", r"(Lev(?:iticus)?|Lv|Levítico)", ("Lev", "Lv")
BOOK: str = rf"\b({'|'.join(book.regular_expression for book in Book)})\b\.*"
SCRIPTURE_REFERENCE_REGULAR_EXPRESSION: Pattern[str] = re.compile(
BOOK,
re.IGNORECASE | re.UNICODE,
)
test_strings = [
"Lev", "Lv", "Leviticus", "Levítico"
]
for test in test_strings:
match = SCRIPTURE_REFERENCE_REGULAR_EXPRESSION.search(test)
if match:
print(f"Matched: {test} -> {match.group()}")
else:
print(f"No match: {test}")Output:
Matched: Lev -> Lev
Matched: Lv -> Lv
Matched: Leviticus -> Leviticus
Matched: Levítico -> Levítico
Hi,
I made a new version of books in a fork to support portuguese/spanish.
I tested one by one, but i have a problem with only 5 books:
For example (above) it understand "lev 1" but not "lv 1", the same for others. I tested with
LEVITICUS = 3, "Leviticus", r"(Lev|Lv)", ("Lev", "Lv")but it don't work too.I don't know what im doing wrong. Can you point me what is wrong in regexp for this five cases?
Thanks.