File size: 4,355 Bytes
107eeac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
import regex as re

try:
    from config import config

    LANGUAGE_IDENTIFICATION_LIBRARY = (
        config.webui_config.language_identification_library
    )
except:
    LANGUAGE_IDENTIFICATION_LIBRARY = "langid"

module = LANGUAGE_IDENTIFICATION_LIBRARY.lower()

langid_languages = [
    "af",
    "am",
    "an",
    "ar",
    "as",
    "az",
    "be",
    "bg",
    "bn",
    "br",
    "bs",
    "ca",
    "cs",
    "cy",
    "da",
    "de",
    "dz",
    "el",
    "en",
    "eo",
    "es",
    "et",
    "eu",
    "fa",
    "fi",
    "fo",
    "fr",
    "ga",
    "gl",
    "gu",
    "he",
    "hi",
    "hr",
    "ht",
    "hu",
    "hy",
    "id",
    "is",
    "it",
    "ja",
    "jv",
    "ka",
    "kk",
    "km",
    "kn",
    "ko",
    "ku",
    "ky",
    "la",
    "lb",
    "lo",
    "lt",
    "lv",
    "mg",
    "mk",
    "ml",
    "mn",
    "mr",
    "ms",
    "mt",
    "nb",
    "ne",
    "nl",
    "nn",
    "no",
    "oc",
    "or",
    "pa",
    "pl",
    "ps",
    "pt",
    "qu",
    "ro",
    "ru",
    "rw",
    "se",
    "si",
    "sk",
    "sl",
    "sq",
    "sr",
    "sv",
    "sw",
    "ta",
    "te",
    "th",
    "tl",
    "tr",
    "ug",
    "uk",
    "ur",
    "vi",
    "vo",
    "wa",
    "xh",
    "zh",
    "zu",
]


def classify_language(text: str, target_languages: list = None) -> str:
    if module == "fastlid" or module == "fasttext":
        from fastlid import fastlid, supported_langs

        classifier = fastlid
        if target_languages != None:
            target_languages = [
                lang for lang in target_languages if lang in supported_langs
            ]
            fastlid.set_languages = target_languages
    elif module == "langid":
        import langid

        classifier = langid.classify
        if target_languages != None:
            target_languages = [
                lang for lang in target_languages if lang in langid_languages
            ]
            langid.set_languages(target_languages)
    else:
        raise ValueError(f"Wrong module {module}")

    lang = classifier(text)[0]

    return lang


def classify_zh_ja(text: str) -> str:
    for idx, char in enumerate(text):
        unicode_val = ord(char)

        # 检测日语字符
        if 0x3040 <= unicode_val <= 0x309F or 0x30A0 <= unicode_val <= 0x30FF:
            return "ja"

        # 检测汉字字符
        if 0x4E00 <= unicode_val <= 0x9FFF:
            # 检查周围的字符
            next_char = text[idx + 1] if idx + 1 < len(text) else None

            if next_char and (
                0x3040 <= ord(next_char) <= 0x309F or 0x30A0 <= ord(next_char) <= 0x30FF
            ):
                return "ja"

    return "zh"


def split_alpha_nonalpha(text, mode=1):
    if mode == 1:
        pattern = r"(?<=[\u4e00-\u9fff\u3040-\u30FF\d\s])(?=[\p{Latin}])|(?<=[\p{Latin}\s])(?=[\u4e00-\u9fff\u3040-\u30FF\d])"
    elif mode == 2:
        pattern = r"(?<=[\u4e00-\u9fff\u3040-\u30FF\s])(?=[\p{Latin}\d])|(?<=[\p{Latin}\d\s])(?=[\u4e00-\u9fff\u3040-\u30FF])"
    else:
        raise ValueError("Invalid mode. Supported modes are 1 and 2.")

    return re.split(pattern, text)


if __name__ == "__main__":
    text = "这是一个测试文本"
    print(classify_language(text))
    print(classify_zh_ja(text))  # "zh"

    text = "これはテストテキストです"
    print(classify_language(text))
    print(classify_zh_ja(text))  # "ja"

    text = "vits和Bert-VITS2是tts模型。花费3days.花费3天。Take 3 days"

    print(split_alpha_nonalpha(text, mode=1))
    # output: ['vits', '和', 'Bert-VITS', '2是', 'tts', '模型。花费3', 'days.花费3天。Take 3 days']

    print(split_alpha_nonalpha(text, mode=2))
    # output: ['vits', '和', 'Bert-VITS2', '是', 'tts', '模型。花费', '3days.花费', '3', '天。Take 3 days']

    text = "vits 和 Bert-VITS2 是 tts 模型。花费3days.花费3天。Take 3 days"
    print(split_alpha_nonalpha(text, mode=1))
    # output: ['vits ', '和 ', 'Bert-VITS', '2 ', '是 ', 'tts ', '模型。花费3', 'days.花费3天。Take ', '3 ', 'days']

    text = "vits 和 Bert-VITS2 是 tts 模型。花费3days.花费3天。Take 3 days"
    print(split_alpha_nonalpha(text, mode=2))
    # output: ['vits ', '和 ', 'Bert-VITS2 ', '是 ', 'tts ', '模型。花费', '3days.花费', '3', '天。Take ', '3 ', 'days']