Hugging Face's logo

Spaces:
botp
/
baicai1145_Genshin_M-Q
Sleeping

App Files Community
baicai1145_Genshin_M-Q
File size: 3,427 Bytes 
a17d0bc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
import ast
import json
from collections import OrderedDict
import os

# locale_path = "./i18n/locale" # The path to the i18n locale directory, you can change it to your own path
# scan_list = ["./",
#              "GPT_SoVITS/",
#              "tools/"
#              ]  # The path to the directory you want to scan, you can change it to your own path
# scan_subfolders = False  # Whether to scan subfolders

locale_path = "./Inference/i18n/locale"
scan_list = ["./Inference/"]  # The path to the directory you want to scan, you can change it to your own path
scan_subfolders = True

special_words_to_keep = {
    "auto": "θ‡ͺεŠ¨εˆ€ζ–­",
    "zh": "δΈ­ζ–‡",
    "en": "θ‹±ζ–‡",
    "ja": "ζ—₯ζ–‡",
    "all_zh": "εͺζœ‰δΈ­ζ–‡",
    "all_ja": "εͺζœ‰ζ—₯ζ–‡",
    "auto_cut": "ζ™Ίθƒ½εˆ‡εˆ†",
    "cut0": "δ»…ε‡­ζ’θ‘Œεˆ‡εˆ†",
    "cut1": "凑四ε₯δΈ€εˆ‡",
    "cut2": "凑50ε­—δΈ€εˆ‡",
    "cut3": "ζŒ‰δΈ­ζ–‡ε₯ε·γ€‚εˆ‡",
    "cut4": "ζŒ‰θ‹±ζ–‡ε₯号.εˆ‡",
    "cut5": "ζŒ‰ζ ‡η‚Ήη¬¦ε·εˆ‡",
    
}


def extract_i18n_strings(node):
    i18n_strings = []

    if (
        isinstance(node, ast.Call)
        and isinstance(node.func, ast.Name)
        and node.func.id == "i18n"
    ):
        for arg in node.args:
            if isinstance(arg, ast.Str):
                i18n_strings.append(arg.s)

    for child_node in ast.iter_child_nodes(node):
        i18n_strings.extend(extract_i18n_strings(child_node))

    return i18n_strings

strings = []

# for each file, parse the code into an AST
# for each AST, extract the i18n strings
def scan_i18n_strings(filename):
    with open(filename, "r", encoding="utf-8") as f:
        code = f.read()
        if "I18nAuto" in code:
            tree = ast.parse(code)
            i18n_strings = extract_i18n_strings(tree)
            print(filename, len(i18n_strings))
            strings.extend(i18n_strings)


# scan the directory for all .py files (recursively)
if scan_subfolders:
    for folder in scan_list:
        for dirpath, dirnames, filenames in os.walk(folder):
            for filename in [f for f in filenames if f.endswith(".py")]:
                scan_i18n_strings(os.path.join(dirpath, filename))
else:
    for folder in scan_list:
        for filename in os.listdir(folder):
            if filename.endswith(".py"):
                scan_i18n_strings(os.path.join(folder, filename))
        
code_keys = set(strings)
"""
n_i18n.py
gui_v1.py 26
app.py 16
infer-web.py 147
scan_i18n.py 0
i18n.py 0
lib/train/process_ckpt.py 1
"""
print()
print("Total unique:", len(code_keys))


standard_file = os.path.join(locale_path, "zh_CN.json")
with open(standard_file, "r", encoding="utf-8") as f:
    standard_data = json.load(f, object_pairs_hook=OrderedDict)
standard_keys = set(standard_data.keys())

# Define the standard file name
unused_keys = standard_keys - code_keys
print("Unused keys:", len(unused_keys))
for unused_key in unused_keys:
    print("\t", unused_key)

missing_keys = code_keys - standard_keys
print("Missing keys:", len(missing_keys))
for missing_key in missing_keys:
    print("\t", missing_key)
    


code_keys_dict = OrderedDict()
for s in strings:
    if s in special_words_to_keep:
        code_keys_dict[s] = special_words_to_keep[s]
    else:    
        code_keys_dict[s] = s

# write back
with open(standard_file, "w", encoding="utf-8") as f:
    json.dump(code_keys_dict, f, ensure_ascii=False, indent=4, sort_keys=True)
    f.write("\n")