def process_google_translation_to_omegat_dict(en_file, cn_file, result_file=None):
if result_file is None:
result_file = filex.get_result_file_name(en_file, '', 'tmx')
en_dict = filex.get_dict_from_file(en_file)
cn_dict = filex.get_dict_from_file(cn_file)
print('英文词典%d条' % (len(en_dict)))
print('中文词典%d条' % (len(cn_dict)))
result = dict()
for cn_key, cn_value in cn_dict.items():
cn_key = cn_key.strip()
cn_value=cn_value.strip()
if cn_key in en_dict.keys():
en_value = en_dict[cn_key]
result[en_value] = cn_value
print('结果%d条' % (len(result)))
Tools.save_omegat_dict(result, result_file)
def export_to_omegat(file_path, result_file=None):
"""导出为OmegaT的记忆文件"""
if result_file is None:
result_file = filex.get_result_file_name(file_path, '', '.tmx.xml')
translation_dict = filex.get_dict_from_file(file_path)
output_dict = dict()
for key, value in translation_dict.items():
if value:
if '【】' in value:
output_dict[key] = value.split('【】')[0]
else:
output_dict[key] = value
Tools.save_omegat_dict(output_dict, result_file)
def get_dict_from_file(file_path,
separator='=',
delete_value_ellipsis=True,
delete_value_underline=True,
delete_value_and_symbol=False,
delete_cn_shortcut=False,
trans_unicode=False):
"""
从文件中读取字典，
:param file_path:文件路径
:param separator:分隔符
:return: 如果有错返回None
:param delete_value_ellipsis:删除省略号
:param delete_value_underline: 删除快捷方式
:param delete_value_and_symbol: 是否删降&符号
:param delete_cn_shortcut: 是否删除中文翻译中的快捷方式
:param trans_unicode: 将unicode转为中文
"""
result = filex.get_dict_from_file(file_path, separator)
if result is None:
return None
if delete_value_ellipsis or delete_value_underline or trans_unicode:
# (空白?点一次或多次)
p_ellipsis = r'(\s?\.+)$'
# 空白?，左括号，&?，字母，右括号
p_shortcut = r'\s?\(&?\w\)$'
# &后跟一字母
p_add_symbol = r'&(\w)'
for key, value in result.items():
if delete_value_ellipsis:
value = re.sub(p_ellipsis, '', value)
if delete_value_underline:
value = value.replace('_', '')
if delete_value_and_symbol:
value = re.sub(p_add_symbol, r'\1', value)
if delete_cn_shortcut:
value = re.sub(p_shortcut, '', value)
if trans_unicode:
value = encodex.unicode_str_to_chinese(value)
result[key] = value
return result
def compare_translation(en_dir,
compare_dir_list,
omegat_dict_file=None,
dict_file=None,
dict_diff_file=None,
by_index=False,
trans_unicode=True):
if dict_file is None:
dict_file = 'data/dict.txt'
if dict_diff_file is None:
dict_diff_file = filex.get_result_file_name(dict_file, '_diff')
separator = '[xx|]'
dict_list = list()
for i in compare_dir_list:
if i == r'C:\Users\Admin\Desktop\AndroidStudio汉化\汉化包\整理':
t_dict = dict()
for i_file in filex.list_file(i, '.properties'):
t_dict.update(filex.get_dict_from_file(i_file))
dict_list.append(t_dict)
continue
i_all_translation, i_diff_translation = Translator.check_same_en_difference_cn(
en_dir, i, False, '', trans_unicode=trans_unicode)
dict_list.append(i_all_translation)
if omegat_dict_file is not None:
dict_list.insert(0, Translator.get_omegat_dict(omegat_dict_file))
for i in range(len(dict_list)):
print('%d中共包含翻译%d条' % (i + 1, len(sorted(dict_list[i].keys()))))
all_translation = dict()
diff_translation = dict()
print_i = True
if by_index:
# 按倒序更新，得到结果
for i in range(len(dict_list) - 1, -1, -1):
all_translation.update(dict_list[i])
print('更新%d后，size是%d' %
(i + 1, len(sorted(all_translation.keys()))))
else:
for i in range(len(dict_list)):
i_dict = dict_list[i]
index = 0
length = len(sorted(i_dict.keys()))
for key, i_value in i_dict.items():
index += 1
if print_i:
print('\n检查%d/%d,%s' % (index, length, key))
print('词典%d中是%s' % (i, i_value))
has_diff = False
for j in range(i + 1, len(dict_list)):
j_dict = dict_list[j]
if key in j_dict:
j_value = j_dict[key]
if i_value == j_value:
if print_i:
print('词典%d中相同' % j)
else:
has_diff = True
if key in diff_translation.keys():
pre_translation = diff_translation[key]
if j_value not in pre_translation.split(
separator):
diff_translation[
key] = pre_translation + separator + j_value.replace(
'\n', '')
else:
diff_translation[key] = (i_value +
separator +
j_value).replace(
'\n', '')
if print_i:
print('词典%d中是%s' % (j, j_value))
# 处理后移除
j_dict.pop(key)
else:
if print_i:
print('词典%d中缺少' % j)
if not has_diff:
if print_i:
print('统一翻译')
if i_value:
# 只添加不为空的
all_translation[key] = i_value
print('%d中处理%d条，其中%d条翻译相同,%d条不同' %
(i, len(sorted(
i_dict.keys())), len(sorted(all_translation.keys())),
len(sorted(diff_translation.keys()))))
print('size is %d' % len(sorted(all_translation.keys())))
if all_translation:
if dict_file.endswith('.tmx') or dict_file.endswith('.tmx.xml'):
Tools.save_omegat_dict(all_translation, dict_file)
else:
result = list()
for key, value in all_translation.items():
result.append('%s=%s\n' % (key, value))
filex.write_lines(dict_file, result)
print('diff size is %d' % len(sorted(diff_translation.keys())))
if diff_translation:
result = list()
for key, value in diff_translation.items():
result.append('%s=%s\n' % (key, value))
filex.write_lines(dict_diff_file, result)