Spaces:
Paused
Paused
translate efficient
Browse files- multi_language.py +34 -0
multi_language.py
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
|
3 |
+
def extract_chinese_characters(file_path):
|
4 |
+
with open(file_path, 'r', encoding='utf-8') as f:
|
5 |
+
content = f.read()
|
6 |
+
chinese_characters = []
|
7 |
+
sentence = {'file':file_path, 'begin':-1, 'end':-1, 'word': ""}
|
8 |
+
for index, char in enumerate(content):
|
9 |
+
if 0x4e00 <= ord(char) <= 0x9fff:
|
10 |
+
sentence['word'] += char
|
11 |
+
if sentence['begin'] == -1: sentence['begin'] = index
|
12 |
+
sentence['end'] = index
|
13 |
+
else:
|
14 |
+
if len(sentence['word'])>0:
|
15 |
+
chinese_characters.append(sentence)
|
16 |
+
sentence = {'file':file_path, 'begin':-1, 'end':-1, 'word': ""}
|
17 |
+
return chinese_characters
|
18 |
+
|
19 |
+
def extract_chinese_characters_from_directory(directory_path):
|
20 |
+
chinese_characters = []
|
21 |
+
for root, dirs, files in os.walk(directory_path):
|
22 |
+
for file in files:
|
23 |
+
if file.endswith('.py'):
|
24 |
+
file_path = os.path.join(root, file)
|
25 |
+
chinese_characters.extend(extract_chinese_characters(file_path))
|
26 |
+
return chinese_characters
|
27 |
+
|
28 |
+
directory_path = './'
|
29 |
+
chinese_characters = extract_chinese_characters_from_directory(directory_path)
|
30 |
+
word_to_translate = {}
|
31 |
+
for d in chinese_characters:
|
32 |
+
word_to_translate[d['word']] = "Translation"
|
33 |
+
|
34 |
+
print('All Chinese characters:', chinese_characters)
|