File size: 1,886 Bytes
ad16788 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
from pathlib import Path
from typing import Iterable
from typing import List
from typing import Union
import warnings
from typeguard import check_argument_types
from espnet2.text.abs_tokenizer import AbsTokenizer
class WordTokenizer(AbsTokenizer):
def __init__(
self,
delimiter: str = None,
non_linguistic_symbols: Union[Path, str, Iterable[str]] = None,
remove_non_linguistic_symbols: bool = False,
):
assert check_argument_types()
self.delimiter = delimiter
if not remove_non_linguistic_symbols and non_linguistic_symbols is not None:
warnings.warn(
"non_linguistic_symbols is only used "
"when remove_non_linguistic_symbols = True"
)
if non_linguistic_symbols is None:
self.non_linguistic_symbols = set()
elif isinstance(non_linguistic_symbols, (Path, str)):
non_linguistic_symbols = Path(non_linguistic_symbols)
with non_linguistic_symbols.open("r", encoding="utf-8") as f:
self.non_linguistic_symbols = set(line.rstrip() for line in f)
else:
self.non_linguistic_symbols = set(non_linguistic_symbols)
self.remove_non_linguistic_symbols = remove_non_linguistic_symbols
def __repr__(self):
return f'{self.__class__.__name__}(delimiter="{self.delimiter}")'
def text2tokens(self, line: str) -> List[str]:
tokens = []
for t in line.split(self.delimiter):
if self.remove_non_linguistic_symbols and t in self.non_linguistic_symbols:
continue
tokens.append(t)
return tokens
def tokens2text(self, tokens: Iterable[str]) -> str:
if self.delimiter is None:
delimiter = " "
else:
delimiter = self.delimiter
return delimiter.join(tokens)
|