def update_omegat_dict_by_pseudo_dict(omegat_dict_file,
pseudo_dict_file,
result_file=None):
"根据伪翻译记忆更新记忆库"
if result_file is None:
result_file = filex.get_result_file_name(pseudo_dict_file,
'_update_by_pseudo')
source_dict = Tools.get_dict_from_omegat(omegat_dict_file)
pseudo_dict = Tools.get_dict_from_omegat(pseudo_dict_file)
print('记忆库共%d条记录，伪翻译共%d条记录' % (len(source_dict), len(pseudo_dict)))
result_dict = ActionsBundle.update_dict_add_extra_info(
source_dict, pseudo_dict)
print('处理结果共%s条记录' % len(result_dict))
Tools.save_omegat_dict(result_dict, result_file)
def translate_file(cls,
file_path,
result_file=None,
ignore_reg_list=None,
ignore_file_path=None,
delete_empty_translation=False):
"""
翻译
寻找一个要翻译的单词
翻译，更新字典，保存
继续
:param cls: 类
:param file_path: 文件路径
:param result_file: 结果文件
:param ignore_reg_list: 忽略正则列表，如果匹配则忽略
:param ignore_file_path: 忽略的单词保存于，用于生成 auto中的tmx ，避免每次都要手动设为相同翻译
:param delete_empty_translation: 删除空翻译
:return:
"""
if result_file is None:
result_file = file_path
if not issubclass(cls, MachineTranslator):
print('%s 不是 MachineTranslator 的子类' % cls)
return
en_dict = Tools.get_dict_from_omegat(file_path)
if not en_dict:
print('翻译文件字典为空')
return
keys = sorted(en_dict.keys())
length = len(keys)
for i in range(length):
en = keys[i]
cn = en_dict[en]
if cn is not None:
continue
continue_loop = False
if ignore_reg_list:
for ignore_reg in ignore_reg_list:
if ignore_reg.startswith('^'):
if re.match(ignore_reg, en):
continue_loop = True
else:
# 不以 ^ 开头才搜索
if re.search(ignore_reg, en):
continue_loop = True
if continue_loop:
print('\n跳过 %d/%d 个:【%s】' % (i + 1, length, en))
if ignore_file_path:
MachineTranslation.save_translation(
ignore_file_path, en, en)
break
if continue_loop:
continue
print('\n翻译 %d/%d 个:【%s】' % (i + 1, length, en))
cn = cls.translate(en)
print('翻译结果 %d/%d 个:【%s】' % (i + 1, length, cn))
# 更新字典
en_dict[en] = cn
# 写入文件
MachineTranslation.save_translation(result_file, en, cn)
if delete_empty_translation:
MachineTranslation.delete_empty_or_same_translation(
result_file, True, True)