Spaces:
Runtime error
Runtime error
File size: 22,070 Bytes
b7e0822 b4f0be3 e22f191 b7e0822 e22f191 b7e0822 e22f191 b7e0822 e22f191 e18ab0a b7e0822 e3f903d e18ab0a b7e0822 6c448b9 c376e46 3951159 8d52819 3951159 e38e6e2 76e0452 e38e6e2 76e0452 e38e6e2 3951159 8d52819 6c448b9 c376e46 fc762cb f05862c fc762cb c376e46 fc762cb c376e46 fc762cb c376e46 fc762cb c376e46 fc762cb c376e46 f05862c c376e46 fc762cb 3dd15de fc762cb c376e46 f05862c e38e6e2 f05862c c376e46 fc762cb c376e46 6c448b9 c376e46 fc762cb f05862c fc762cb f05862c fc762cb c376e46 fc762cb c376e46 fc762cb c376e46 fc762cb c376e46 fc762cb c376e46 fc762cb c376e46 f05862c c376e46 fc762cb c376e46 3951159 c376e46 fc762cb 6c448b9 c376e46 76e0452 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 |
"""
Translate this project to other languages (experimental, please open an issue if there is any bug)
Usage:
1. modify LANG
LANG = "English"
2. modify TransPrompt
TransPrompt = f"Replace each json value `#` with translated results in English, e.g., \"原始文本\":\"TranslatedText\". Keep Json format. Do not answer #."
3. Run `python multi_language.py`.
Note: You need to run it multiple times to increase translation coverage because GPT makes mistakes sometimes.
4. Find the translated program in `multi-language\English\*`
P.S.
- The translation mapping will be stored in `docs/translation_xxxx.json`, you can revised mistaken translation there.
- If you would like to share your `docs/translation_xxxx.json`, (so that everyone can use the cached & revised translation mapping), please open a Pull Request
- If there is any translation error in `docs/translation_xxxx.json`, please open a Pull Request
- Welcome any Pull Request, regardless of language
"""
import os
import json
import functools
import re
import pickle
import time
CACHE_FOLDER = "gpt_log"
blacklist = ['multi-language', 'gpt_log', '.git', 'private_upload', 'multi_language.py']
# LANG = "TraditionalChinese"
# TransPrompt = f"Replace each json value `#` with translated results in Traditional Chinese, e.g., \"原始文本\":\"翻譯後文字\". Keep Json format. Do not answer #."
# LANG = "Japanese"
# TransPrompt = f"Replace each json value `#` with translated results in Japanese, e.g., \"原始文本\":\"テキストの翻訳\". Keep Json format. Do not answer #."
LANG = "English"
TransPrompt = f"Replace each json value `#` with translated results in English, e.g., \"原始文本\":\"TranslatedText\". Keep Json format. Do not answer #."
if not os.path.exists(CACHE_FOLDER):
os.makedirs(CACHE_FOLDER)
def lru_file_cache(maxsize=128, ttl=None, filename=None):
"""
Decorator that caches a function's return value after being called with given arguments.
It uses a Least Recently Used (LRU) cache strategy to limit the size of the cache.
maxsize: Maximum size of the cache. Defaults to 128.
ttl: Time-to-Live of the cache. If a value hasn't been accessed for `ttl` seconds, it will be evicted from the cache.
filename: Name of the file to store the cache in. If not supplied, the function name + ".cache" will be used.
"""
cache_path = os.path.join(CACHE_FOLDER, f"{filename}.cache") if filename is not None else None
def decorator_function(func):
cache = {}
_cache_info = {
"hits": 0,
"misses": 0,
"maxsize": maxsize,
"currsize": 0,
"ttl": ttl,
"filename": cache_path,
}
@functools.wraps(func)
def wrapper_function(*args, **kwargs):
key = str((args, frozenset(kwargs)))
if key in cache:
if _cache_info["ttl"] is None or (cache[key][1] + _cache_info["ttl"]) >= time.time():
_cache_info["hits"] += 1
print(f'Warning, reading cache, last read {(time.time()-cache[key][1])//60} minutes ago'); time.sleep(2)
cache[key][1] = time.time()
return cache[key][0]
else:
del cache[key]
result = func(*args, **kwargs)
cache[key] = [result, time.time()]
_cache_info["misses"] += 1
_cache_info["currsize"] += 1
if _cache_info["currsize"] > _cache_info["maxsize"]:
oldest_key = None
for k in cache:
if oldest_key is None:
oldest_key = k
elif cache[k][1] < cache[oldest_key][1]:
oldest_key = k
del cache[oldest_key]
_cache_info["currsize"] -= 1
if cache_path is not None:
with open(cache_path, "wb") as f:
pickle.dump(cache, f)
return result
def cache_info():
return _cache_info
wrapper_function.cache_info = cache_info
if cache_path is not None and os.path.exists(cache_path):
with open(cache_path, "rb") as f:
cache = pickle.load(f)
_cache_info["currsize"] = len(cache)
return wrapper_function
return decorator_function
def contains_chinese(string):
"""
Returns True if the given string contains Chinese characters, False otherwise.
"""
chinese_regex = re.compile(u'[\u4e00-\u9fff]+')
return chinese_regex.search(string) is not None
def split_list(lst, n_each_req):
"""
Split a list into smaller lists, each with a maximum number of elements.
:param lst: the list to split
:param n_each_req: the maximum number of elements in each sub-list
:return: a list of sub-lists
"""
result = []
for i in range(0, len(lst), n_each_req):
result.append(lst[i:i + n_each_req])
return result
def map_to_json(map, language):
dict_ = read_map_from_json(language)
dict_.update(map)
with open(f'docs/translate_{language.lower()}.json', 'w', encoding='utf8') as f:
json.dump(dict_, f, indent=4, ensure_ascii=False)
def read_map_from_json(language):
if os.path.exists(f'docs/translate_{language.lower()}.json'):
with open(f'docs/translate_{language.lower()}.json', 'r', encoding='utf8') as f:
res = json.load(f)
res = {k:v for k, v in res.items() if v is not None and contains_chinese(k)}
return res
return {}
def advanced_split(splitted_string, spliter, include_spliter=False):
splitted_string_tmp = []
for string_ in splitted_string:
if spliter in string_:
splitted = string_.split(spliter)
for i, s in enumerate(splitted):
if include_spliter:
if i != len(splitted)-1:
splitted[i] += spliter
splitted[i] = splitted[i].strip()
for i in reversed(range(len(splitted))):
if not contains_chinese(splitted[i]):
splitted.pop(i)
splitted_string_tmp.extend(splitted)
else:
splitted_string_tmp.append(string_)
splitted_string = splitted_string_tmp
return splitted_string_tmp
cached_translation = {}
cached_translation = read_map_from_json(language=LANG)
def trans(word_to_translate, language, special=False):
if len(word_to_translate) == 0: return {}
from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
from toolbox import get_conf, ChatBotWithCookies
proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY = \
get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY')
llm_kwargs = {
'api_key': API_KEY,
'llm_model': LLM_MODEL,
'top_p':1.0,
'max_length': None,
'temperature':0.4,
}
import random
N_EACH_REQ = random.randint(16, 32)
word_to_translate_split = split_list(word_to_translate, N_EACH_REQ)
inputs_array = [str(s) for s in word_to_translate_split]
inputs_show_user_array = inputs_array
history_array = [[] for _ in inputs_array]
if special: # to English using CamelCase Naming Convention
sys_prompt_array = [f"Translate following names to English with CamelCase naming convention. Keep original format" for _ in inputs_array]
else:
sys_prompt_array = [f"Translate following sentences to {LANG}. E.g., You should translate sentences to the following format ['translation of sentence 1', 'translation of sentence 2']. Do NOT answer with Chinese!" for _ in inputs_array]
chatbot = ChatBotWithCookies(llm_kwargs)
gpt_say_generator = request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
inputs_array,
inputs_show_user_array,
llm_kwargs,
chatbot,
history_array,
sys_prompt_array,
)
while True:
try:
gpt_say = next(gpt_say_generator)
print(gpt_say[1][0][1])
except StopIteration as e:
result = e.value
break
translated_result = {}
for i, r in enumerate(result):
if i%2 == 1:
try:
res_before_trans = eval(result[i-1])
res_after_trans = eval(result[i])
if len(res_before_trans) != len(res_after_trans):
raise RuntimeError
for a,b in zip(res_before_trans, res_after_trans):
translated_result[a] = b
except:
# try:
# res_before_trans = word_to_translate_split[(i-1)//2]
# res_after_trans = [s for s in result[i].split("', '")]
# for a,b in zip(res_before_trans, res_after_trans):
# translated_result[a] = b
# except:
print('GPT answers with unexpected format, some words may not be translated, but you can try again later to increase translation coverage.')
res_before_trans = eval(result[i-1])
for a in res_before_trans:
translated_result[a] = None
return translated_result
def trans_json(word_to_translate, language, special=False):
if len(word_to_translate) == 0: return {}
from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
from toolbox import get_conf, ChatBotWithCookies
proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY = \
get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY')
llm_kwargs = {
'api_key': API_KEY,
'llm_model': LLM_MODEL,
'top_p':1.0,
'max_length': None,
'temperature':0.1,
}
import random
N_EACH_REQ = random.randint(16, 32)
random.shuffle(word_to_translate)
word_to_translate_split = split_list(word_to_translate, N_EACH_REQ)
inputs_array = [{k:"#" for k in s} for s in word_to_translate_split]
inputs_array = [ json.dumps(i, ensure_ascii=False) for i in inputs_array]
inputs_show_user_array = inputs_array
history_array = [[] for _ in inputs_array]
sys_prompt_array = [TransPrompt for _ in inputs_array]
chatbot = ChatBotWithCookies(llm_kwargs)
gpt_say_generator = request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
inputs_array,
inputs_show_user_array,
llm_kwargs,
chatbot,
history_array,
sys_prompt_array,
)
while True:
try:
gpt_say = next(gpt_say_generator)
print(gpt_say[1][0][1])
except StopIteration as e:
result = e.value
break
translated_result = {}
for i, r in enumerate(result):
if i%2 == 1:
try:
translated_result.update(json.loads(result[i]))
except:
print(result[i])
print(result)
return translated_result
def step_1_core_key_translate():
def extract_chinese_characters(file_path):
syntax = []
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
import ast
root = ast.parse(content)
for node in ast.walk(root):
if isinstance(node, ast.Name):
if contains_chinese(node.id): syntax.append(node.id)
if isinstance(node, ast.Import):
for n in node.names:
if contains_chinese(n.name): syntax.append(n.name)
elif isinstance(node, ast.ImportFrom):
for n in node.names:
if contains_chinese(n.name): syntax.append(n.name)
for k in node.module.split('.'):
if contains_chinese(k): syntax.append(k)
return syntax
def extract_chinese_characters_from_directory(directory_path):
chinese_characters = []
for root, dirs, files in os.walk(directory_path):
if any([b in root for b in blacklist]):
continue
for file in files:
if file.endswith('.py'):
file_path = os.path.join(root, file)
chinese_characters.extend(extract_chinese_characters(file_path))
return chinese_characters
directory_path = './'
chinese_core_names = extract_chinese_characters_from_directory(directory_path)
chinese_core_keys = [name for name in chinese_core_names]
chinese_core_keys_norepeat = []
for d in chinese_core_keys:
if d not in chinese_core_keys_norepeat: chinese_core_keys_norepeat.append(d)
need_translate = []
cached_translation = read_map_from_json(language=LANG)
cached_translation_keys = list(cached_translation.keys())
for d in chinese_core_keys_norepeat:
if d not in cached_translation_keys:
need_translate.append(d)
need_translate_mapping = trans(need_translate, language=LANG, special=True)
map_to_json(need_translate_mapping, language=LANG)
cached_translation = read_map_from_json(language=LANG)
cached_translation = dict(sorted(cached_translation.items(), key=lambda x: -len(x[0])))
chinese_core_keys_norepeat_mapping = {}
for k in chinese_core_keys_norepeat:
chinese_core_keys_norepeat_mapping.update({k:cached_translation[k]})
chinese_core_keys_norepeat_mapping = dict(sorted(chinese_core_keys_norepeat_mapping.items(), key=lambda x: -len(x[0])))
# ===============================================
# copy
# ===============================================
def copy_source_code():
from toolbox import get_conf
import shutil
import os
try: shutil.rmtree(f'./multi-language/{LANG}/')
except: pass
os.makedirs(f'./multi-language', exist_ok=True)
backup_dir = f'./multi-language/{LANG}/'
shutil.copytree('./', backup_dir, ignore=lambda x, y: blacklist)
copy_source_code()
# ===============================================
# primary key replace
# ===============================================
directory_path = f'./multi-language/{LANG}/'
for root, dirs, files in os.walk(directory_path):
for file in files:
if file.endswith('.py'):
file_path = os.path.join(root, file)
syntax = []
# read again
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
for k, v in chinese_core_keys_norepeat_mapping.items():
content = content.replace(k, v)
with open(file_path, 'w', encoding='utf-8') as f:
f.write(content)
def step_2_core_key_translate():
# =================================================================================================
# step2
# =================================================================================================
def load_string(strings, string_input):
string_ = string_input.strip().strip(',').strip().strip('.').strip()
if string_.startswith('[Local Message]'):
string_ = string_.replace('[Local Message]', '')
string_ = string_.strip().strip(',').strip().strip('.').strip()
splitted_string = [string_]
# --------------------------------------
splitted_string = advanced_split(splitted_string, spliter=",", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="。", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter=")", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="(", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="(", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter=")", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="<", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter=">", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="[", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="]", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="【", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="】", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="?", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter=":", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter=":", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter=",", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="#", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="\n", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter=";", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="`", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter=" ", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="- ", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="---", include_spliter=False)
# --------------------------------------
for j, s in enumerate(splitted_string): # .com
if '.com' in s: continue
if '\'' in s: continue
if '\"' in s: continue
strings.append([s,0])
def get_strings(node):
strings = []
# recursively traverse the AST
for child in ast.iter_child_nodes(node):
node = child
if isinstance(child, ast.Str):
if contains_chinese(child.s):
load_string(strings=strings, string_input=child.s)
elif isinstance(child, ast.AST):
strings.extend(get_strings(child))
return strings
string_literals = []
directory_path = f'./multi-language/{LANG}/'
for root, dirs, files in os.walk(directory_path):
for file in files:
if file.endswith('.py'):
file_path = os.path.join(root, file)
syntax = []
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
# comments
comments_arr = []
for code_sp in content.splitlines():
comments = re.findall(r'#.*$', code_sp)
for comment in comments:
load_string(strings=comments_arr, string_input=comment)
string_literals.extend(comments_arr)
# strings
import ast
tree = ast.parse(content)
res = get_strings(tree, )
string_literals.extend(res)
[print(s) for s in string_literals]
chinese_literal_names = []
chinese_literal_names_norepeat = []
for string, offset in string_literals:
chinese_literal_names.append(string)
chinese_literal_names_norepeat = []
for d in chinese_literal_names:
if d not in chinese_literal_names_norepeat: chinese_literal_names_norepeat.append(d)
need_translate = []
cached_translation = read_map_from_json(language=LANG)
cached_translation_keys = list(cached_translation.keys())
for d in chinese_literal_names_norepeat:
if d not in cached_translation_keys:
need_translate.append(d)
up = trans_json(need_translate, language=LANG, special=False)
map_to_json(up, language=LANG)
cached_translation = read_map_from_json(language=LANG)
cached_translation = dict(sorted(cached_translation.items(), key=lambda x: -len(x[0])))
# ===============================================
# literal key replace
# ===============================================
directory_path = f'./multi-language/{LANG}/'
for root, dirs, files in os.walk(directory_path):
for file in files:
if file.endswith('.py'):
file_path = os.path.join(root, file)
syntax = []
# read again
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
for k, v in cached_translation.items():
if v is None: continue
if '"' in v:
v = v.replace('"', "`")
if '\'' in v:
v = v.replace('\'', "`")
content = content.replace(k, v)
with open(file_path, 'w', encoding='utf-8') as f:
f.write(content)
if file.strip('.py') in cached_translation:
file_new = cached_translation[file.strip('.py')] + '.py'
file_path_new = os.path.join(root, file_new)
with open(file_path_new, 'w', encoding='utf-8') as f:
f.write(content)
os.remove(file_path)
step_1_core_key_translate()
step_2_core_key_translate()
|