Spaces:
Running
Running
File size: 3,813 Bytes
67c46fd |
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 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
from pathlib import Path
from typing import Iterable
from typing import List
from typing import Union
import warnings
import re
from funasr_detach.tokenizer.abs_tokenizer import BaseTokenizer
from funasr_detach.register import tables
@tables.register("tokenizer_classes", "CharTokenizer")
class CharTokenizer(BaseTokenizer):
def __init__(
self,
non_linguistic_symbols: Union[Path, str, Iterable[str]] = None,
space_symbol: str = "<space>",
remove_non_linguistic_symbols: bool = False,
split_with_space: bool = False,
seg_dict: str = None,
**kwargs,
):
super().__init__(**kwargs)
self.space_symbol = space_symbol
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)
try:
with non_linguistic_symbols.open("r", encoding="utf-8") as f:
self.non_linguistic_symbols = set(line.rstrip() for line in f)
except FileNotFoundError:
warnings.warn(f"{non_linguistic_symbols} doesn't exist.")
self.non_linguistic_symbols = set()
else:
self.non_linguistic_symbols = set(non_linguistic_symbols)
self.remove_non_linguistic_symbols = remove_non_linguistic_symbols
self.split_with_space = split_with_space
self.seg_dict = None
if seg_dict is not None:
self.seg_dict = load_seg_dict(seg_dict)
def __repr__(self):
return (
f"{self.__class__.__name__}("
f'space_symbol="{self.space_symbol}"'
f'non_linguistic_symbols="{self.non_linguistic_symbols}"'
f")"
)
def text2tokens(self, line: Union[str, list]) -> List[str]:
# if self.split_with_space:
if self.seg_dict is not None:
tokens = line.strip().split(" ")
tokens = seg_tokenize(tokens, self.seg_dict)
else:
tokens = []
while len(line) != 0:
for w in self.non_linguistic_symbols:
if line.startswith(w):
if not self.remove_non_linguistic_symbols:
tokens.append(line[: len(w)])
line = line[len(w) :]
break
else:
t = line[0]
if t == " ":
# t = "<space>"
line = line[1:]
continue
tokens.append(t)
line = line[1:]
return tokens
def tokens2text(self, tokens: Iterable[str]) -> str:
tokens = [t if t != self.space_symbol else " " for t in tokens]
return "".join(tokens)
def load_seg_dict(seg_dict_file):
seg_dict = {}
assert isinstance(seg_dict_file, str)
with open(seg_dict_file, "r", encoding="utf8") as f:
lines = f.readlines()
for line in lines:
s = line.strip().split()
key = s[0]
value = s[1:]
seg_dict[key] = " ".join(value)
return seg_dict
def seg_tokenize(txt, seg_dict):
pattern = re.compile(r"^[\u4E00-\u9FA50-9]+$")
out_txt = ""
for word in txt:
word = word.lower()
if word in seg_dict:
out_txt += seg_dict[word] + " "
else:
if pattern.match(word):
for char in word:
if char in seg_dict:
out_txt += seg_dict[char] + " "
else:
out_txt += "<unk>" + " "
else:
out_txt += "<unk>" + " "
return out_txt.strip().split()
|