File size: 3,157 Bytes
2ae68b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import re


def japanese_cleaners(text):
    from text.japanese import japanese_to_romaji_with_accent
    text = japanese_to_romaji_with_accent(text)
    if re.match('[A-Za-z]', text[-1]):
        text += '.'
    return text


def japanese_cleaners2(text):
    return japanese_cleaners(text).replace('ts', 'ʦ').replace('...', '…')


def korean_cleaners(text):
    '''Pipeline for Korean text'''
    from text.korean import latin_to_hangul, number_to_hangul, divide_hangul
    text = latin_to_hangul(text)
    text = number_to_hangul(text)
    text = divide_hangul(text)
    if re.match('[\u3131-\u3163]', text[-1]):
        text += '.'
    return text


def chinese_cleaners(text):
    '''Pipeline for Chinese text'''
    from text.mandarin import number_to_chinese, chinese_to_bopomofo, latin_to_bopomofo
    text = number_to_chinese(text)
    text = chinese_to_bopomofo(text)
    text = latin_to_bopomofo(text)
    if re.match('[ˉˊˇˋ˙]', text[-1]):
        text += '。'
    return text


def zh_ja_mixture_cleaners(text):
    from text.mandarin import chinese_to_romaji
    from text.japanese import japanese_to_romaji_with_accent
    chinese_texts = re.findall(r'\[ZH\].*?\[ZH\]', text)
    japanese_texts = re.findall(r'\[JA\].*?\[JA\]', text)
    for chinese_text in chinese_texts:
        cleaned_text = chinese_to_romaji(chinese_text[4:-4])
        text = text.replace(chinese_text, cleaned_text+' ', 1)
    for japanese_text in japanese_texts:
        cleaned_text = japanese_to_romaji_with_accent(
            japanese_text[4:-4]).replace('ts', 'ʦ').replace('u', 'ɯ').replace('...', '…')
        text = text.replace(japanese_text, cleaned_text+' ', 1)
    text = text[:-1]
    if re.match('[A-Za-zɯɹəɥ→↓↑]', text[-1]):
        text += '.'
    return text


def sanskrit_cleaners(text):
    text = text.replace('॥', '।').replace('ॐ', 'ओम्')
    if text[-1] != '।':
        text += ' ।'
    return text


def cjks_cleaners(text):
    from text.mandarin import chinese_to_lazy_ipa
    from text.japanese import japanese_to_ipa
    from text.korean import korean_to_lazy_ipa
    from text.sanskrit import devanagari_to_ipa
    chinese_texts = re.findall(r'\[ZH\].*?\[ZH\]', text)
    japanese_texts = re.findall(r'\[JA\].*?\[JA\]', text)
    korean_texts = re.findall(r'\[KO\].*?\[KO\]', text)
    sanskrit_texts = re.findall(r'\[SA\].*?\[SA\]', text)
    for chinese_text in chinese_texts:
        cleaned_text = chinese_to_lazy_ipa(chinese_text[4:-4])
        text = text.replace(chinese_text, cleaned_text+' ', 1)
    for japanese_text in japanese_texts:
        cleaned_text = japanese_to_ipa(japanese_text[4:-4])
        text = text.replace(japanese_text, cleaned_text+' ', 1)
    for korean_text in korean_texts:
        cleaned_text = korean_to_lazy_ipa(korean_text[4:-4])
        text = text.replace(korean_text, cleaned_text+' ', 1)
    for sanskrit_text in sanskrit_texts:
        cleaned_text = devanagari_to_ipa(sanskrit_text[4:-4])
        text = text.replace(sanskrit_text, cleaned_text+' ', 1)
    text = text[:-1]
    if re.match(r'[^\.,!\?\-…~]', text[-1]):
        text += '.'
    return text