File size: 5,148 Bytes
ab26e54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
#!/usr/bin/env python3
import json
from typing import Iterator, List, Union

from tokenizers import AddedToken, Regex, Tokenizer, decoders, normalizers, pre_tokenizers, trainers
from tokenizers.implementations.base_tokenizer import BaseTokenizer
from tokenizers.models import Unigram
from tokenizers.processors import TemplateProcessing


class SentencePieceUnigramTokenizer(BaseTokenizer):
    """
    This class is a copy of `DeDLOC's tokenizer implementation <https://github.com/yandex-research/DeDLOC/blob/main/sahajbert/tokenizer/tokenizer_model.py>`__ .

    Custom SentencePiece Unigram Tokenizer with NMT, NKFC, spaces and lower-casing characters normalization
    Represents the Unigram algorithm, with the pretokenization used by SentencePiece
    """

    def __init__(
        self,
        replacement: str = "▁",
        add_prefix_space: bool = True,
        unk_token: Union[str, AddedToken] = "<unk>",
        eos_token: Union[str, AddedToken] = "</s>",
        pad_token: Union[str, AddedToken] = "<pad>",
    ):
        self.special_tokens = {
            "pad": {"id": 0, "token": pad_token},
            "eos": {"id": 1, "token": eos_token},
            "unk": {"id": 2, "token": unk_token},
        }

        self.special_tokens_list = [None] * len(self.special_tokens)
        for token_dict in self.special_tokens.values():
            self.special_tokens_list[token_dict["id"]] = token_dict["token"]

        tokenizer = Tokenizer(Unigram())

        # the following regexes are taken directly from https://github.com/aub-mind/arabert/blob/f92f06a29804f74878e2d1e39ea57fba8dcb0eac/preprocess.py
        url = " [رابط] "
        email = " [بريد] "
        usr = " [مستخدم] "

        url_regexes = [
            r"(http(s)?:\/\/.)?(www\.)?[-a-zA-Z0-9@:%._\+~#=]{2,256}\.[a-z]{2,6}\b([-a-zA-Z0-9@:%_\+.~#?&//=]*)",
            r"@(https?|ftp)://(-\.)?([^\s/?\.#-]+\.?)+(/[^\s]*)?$@iS",
            r"http[s]?://[a-zA-Z0-9_\-./~\?=%&]+",
            r"www[a-zA-Z0-9_\-?=%&/.~]+",
            r"[a-zA-Z]+\.com",
            r"(?=http)[^\s]+",
            r"(?=www)[^\s]+",
            r"://",
        ]

        email_regexes = [r"[\w-]+@([\w-]+\.)+[\w-]+", r"\S+@\S+"]

        user_mention_regex = r"@[\w\d]+"

        tokenizer.normalizer = normalizers.Sequence(
            [
                normalizers.Nmt(),
                normalizers.NFKC(),
                # remove links, emails, user mentions ans hashtags
                *[normalizers.Replace(Regex(r), url) for r in url_regexes],
                *[normalizers.Replace(Regex(r), email) for r in email_regexes],
                normalizers.Replace(Regex(user_mention_regex), usr),
                # remove html
                normalizers.Replace(Regex("<br />"), " "),
                normalizers.Replace(Regex("</?[^>]+>"), " "),
                # remove extra white space
                normalizers.Replace(Regex(" {2,}"), " "),
                normalizers.Lowercase(),
            ]
        )
        tokenizer.pre_tokenizer = pre_tokenizers.Sequence(
            [
                pre_tokenizers.Metaspace(replacement=replacement, add_prefix_space=add_prefix_space),
                pre_tokenizers.Digits(individual_digits=True),
                pre_tokenizers.Punctuation(),
            ]
        )
        tokenizer.decoder = decoders.Metaspace(replacement=replacement, add_prefix_space=add_prefix_space)

        tokenizer.post_processor = TemplateProcessing(
            single=f"$A {self.special_tokens['eos']['token']}",
            special_tokens=[(self.special_tokens["eos"]["token"], self.special_tokens["eos"]["id"])],
        )

        parameters = {
            "model": "SentencePieceUnigram",
            "replacement": replacement,
            "add_prefix_space": add_prefix_space,
        }

        super().__init__(tokenizer, parameters)

    def train(
        self,
        files: Union[str, List[str]],
        vocab_size: int = 8000,
        show_progress: bool = True,
    ):
        """Train the model using the given files"""

        trainer = trainers.UnigramTrainer(
            vocab_size=vocab_size,
            special_tokens=self.special_tokens_list,
            show_progress=show_progress,
        )

        if isinstance(files, str):
            files = [files]
        self._tokenizer.train(files, trainer=trainer)

        self.add_unk_id()

    def train_from_iterator(
        self,
        iterator: Union[Iterator[str], Iterator[Iterator[str]]],
        vocab_size: int = 8000,
        show_progress: bool = True,
    ):
        """Train the model using the given iterator"""

        trainer = trainers.UnigramTrainer(
            vocab_size=vocab_size,
            special_tokens=self.special_tokens_list,
            show_progress=show_progress,
        )

        self._tokenizer.train_from_iterator(iterator, trainer=trainer)

        self.add_unk_id()

    def add_unk_id(self):
        tokenizer_json = json.loads(self._tokenizer.to_str())

        tokenizer_json["model"]["unk_id"] = self.special_tokens["unk"]["id"]

        self._tokenizer = Tokenizer.from_str(json.dumps(tokenizer_json))