def check_same_en_difference_cn(en_dir,
cn_dir,
print_msg=False,
suffix='',
trans_unicode=True):
"""英文相同时，是否有不一致的翻译"""
all_translation = dict()
diff_translation = dict()
en_file_list = filex.list_file(en_dir, '\.(?!png|gif)')
for en_file in en_file_list:
print('\ncheck ' + en_file)
cn_file = Translator.get_cn_file_name(en_dir, cn_dir, en_file,
suffix)
if not os.path.exists(cn_file):
print('中文文件不存在' + cn_file)
continue
en_dict = Tools.get_dict_from_file(en_file)
cn_dict = Tools.get_dict_from_file(cn_file,
delete_cn_shortcut=True,
trans_unicode=trans_unicode)
for key, en_value in en_dict.items():
if key in cn_dict.keys():
# 有key对应的中英文
cn_value = cn_dict[key]
if cn_value != en_value:
# 中英文不一样才算翻译
if en_value in all_translation.keys():
pre_translation = all_translation[en_value]
if pre_translation != cn_value:
if en_value not in diff_translation.keys():
diff_translation[
en_value] = pre_translation + '\n' + cn_value
else:
pre_diff_translation = diff_translation[
en_value]
if cn_value not in pre_diff_translation.split(
'\n'):
# 之前没有记录过才再记录
diff_translation[
en_value] = pre_diff_translation + '\n' + cn_value
if print_msg:
print(
'\n词典中已经存在%s，但翻译不相同\n%s\n%s' %
(en_value, pre_translation, cn_value))
else:
all_translation[en_value] = cn_value
if print_msg:
print('the size is %d' % len(sorted(all_translation.keys())))
# 读取守毕
for key in diff_translation.keys():
all_translation.pop(key)
return all_translation, diff_translation
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 update_omegat_dict(dict_file, omegat_dict_file, result_dict_file):
"""更新omegat的记忆文件"""
pre_dict = Tools.get_dict_from_file(dict_file)
print('pre size is %d' % len(sorted(pre_dict.keys())))
omegat_dict = Translator.get_omegat_dict(omegat_dict_file)
print('omegat size is %d' % len(sorted(omegat_dict.keys())))
# 更新，以omegat为准
pre_dict.update(omegat_dict)
print('result size is %d' % len(sorted(pre_dict.keys())))
Tools.save_omegat_dict(pre_dict, result_dict_file)
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 get_action_desc_dict(en_file, print_msg=False):
"""
读取操作对应的描述
:param en_file:
:param print_msg:
:return:
"""
en_dict = Tools.get_dict_from_file(en_file)
desc_dict = dict()
# 重复的处理起来麻烦，索性删除了
duplicate_value = list()
# 反转
for key, value in en_dict.items():
if key.endswith('.text'):
desc_key = key[:-len('.text')] + '.description'
if desc_key in en_dict.keys():
desc = en_dict[desc_key]
if value in desc_dict.keys():
pre_desc = desc_dict[value]
if desc == pre_desc:
print('%s重复【%s】' + value, desc)
else:
duplicate_value.append(value)
desc = '%s【或】%s' % (pre_desc, desc)
print('%s有不同的描述【%s】【%s】' % (value, desc, pre_desc))
desc_dict[value] = desc
for value in duplicate_value:
if value in desc_dict.keys():
desc_dict.pop(value)
if print_msg:
print('删除' + value)
if print_msg:
print(desc_dict)
return desc_dict
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 generate_need_translation_file2(en_dir, result_file):
"""生成需要翻译的文件"""
en_file_list = filex.list_file(en_dir)
all_translation = dict()
for en_file in en_file_list:
en_dict = Tools.get_dict_from_file(en_file)
all_translation.update(en_dict)
result = list()
for key, value in all_translation.items():
result.append('%s=%s\n' % (key, value))
filex.write_lines(result_file, result)
def check_same_key_difference_value(dir_path):
"""如果key相同，value是否有不一致
发现确实有不一致，所以必须区分文件"""
file_list = filex.list_file(dir_path)
all_translation = dict()
for file in file_list:
print('\ncheck ' + file)
translation_dict = Tools.get_dict_from_file(
file, delete_value_and_symbol=True, trans_unicode=True)
if all_translation:
# 不为空再处理，为空的第一次直接update
for key, value in translation_dict.items():
if key in all_translation.keys():
if all_translation[key] != value:
print('key相同%s，但value不一致\n%s\n%s' %
(key, all_translation[key], value))
all_translation.update(translation_dict)
def generate_need_translation_file(en_dir, result_dir):
"""生成需要翻译的文件"""
en_file_list = filex.list_file(en_dir)
all_translation = dict()
for en_file in en_file_list:
en_dict = Tools.get_dict_from_file(en_file)
all_translation.update(en_dict)
i = 0
size = 3000
result = list()
for key, value in all_translation.items():
i += 1
result.append('%s=%s\n' % (key, value))
if i % size == size - 1:
index = int(i / size)
result_file = '%s\\%2d.properties' % (result_dir, index)
filex.write_lines(result_file, result)
result.clear()
if result:
index = int(i / size)
result_file = '%s\\%2d.properties' % (result_dir, index)
filex.write_lines(result_file, result)
result.clear()
def add_ellipsis_and_shortcut(en_file, cn_file, result_file=None):
"""
处理快捷键，将_字母替换为(_字母)
:param en_file:
:param cn_file:
:param result_file:
:return:
"""
if result_file is None:
result_file = filex.get_result_file_name(
cn_file, '_add_ellipsis_and_shortcut')
en_dict = Tools.get_dict_from_file(en_file,
delete_value_ellipsis=False,
delete_value_underline=False)
cn_dict = Tools.get_dict_from_file(cn_file,
delete_value_ellipsis=False,
delete_value_underline=False)
count = 0
p_ellipsise = re.compile('……|…$')
p_period = re.compile('\.')
for (k, v) in en_dict.items():
if v.endswith('.'):
# 以.结尾
if k in cn_dict.keys():
cn_value = cn_dict[k]
old_value = cn_value
if v.endswith('...'):
# 省略号结尾
cn_value = re.sub(p_ellipsise, '...', cn_value)
if not cn_value.endswith('...'):
cn_value += '...'
elif v.endswith('.'):
# 句号结尾
cn_value = re.sub(p_period, '。', cn_value)
if not cn_value.endswith('。'):
cn_value += '。'
if cn_value != old_value:
print('修改【%s】为【%s】' % (old_value, cn_value))
cn_dict[k] = cn_value
if '_' in v:
# 有快捷方式
index = v.find('_')
shortcut = v[index + 1:index + 2]
# 包含快捷键
if k in cn_dict.keys():
# 都有
cn_value = cn_dict[k]
count += 1
# 已经是(_字母结)结尾的，重新替换一遍
p = re.compile(r'(.*)(\(_\w\))')
if re.match(p, cn_value) is not None:
replace_result = re.sub(p, r'\1' + '(_%s)' % shortcut,
cn_value)
print('替换%d,key=%s,v=%s,cn=%s,r=%s' %
(count, shortcut, v, cn_value, replace_result))
else:
replace_result = cn_value.replace(
'_', '') + '(_%s)' % shortcut
print('添加%d,key=%s,v=%s,cn=%s,r=%s' %
(count, shortcut, v, cn_value, replace_result))
cn_dict[k] = replace_result
result = Tools.translate_file_by_dict(en_file, cn_dict, '') # 重新翻译
result.insert(
0,
'# from:[AndroidStudio翻译(3)-ActionsBundle中文翻译](http://blog.pingfangx.com/2355.html)\n'
)
filex.write_lines(result_file, 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)
def check_translation_complete(en_dir, cn_dir, out_put=None, suffix=''):
"""翻译是否完整"""
incomplete_dict = dict()
en_file_list = filex.list_file(en_dir, '\.(?!png|gif)')
incomplete_file = []
miss_file = []
complete_count = 0
same_file = []
complete_file = []
for en_file in en_file_list:
# print('\ncheck ' + en_file)
cn_file = Translator.get_cn_file_name(en_dir, cn_dir, en_file,
suffix)
if not os.path.exists(cn_file):
# print('中文文件不存在' + cn_file)
miss_file.append(cn_file)
continue
if filecmp.cmp(en_file, cn_file):
# print('文件相同' + en_file)
same_file.append(en_file)
continue
en_dict = Tools.get_dict_from_file(en_file)
cn_dict = Tools.get_dict_from_file(cn_file, trans_unicode=True)
is_complete = True
translation_count_in_file = 0
for key, en_value in en_dict.items():
if key not in cn_dict.keys():
is_complete = False
incomplete_dict[key] = en_value
# print('没有翻译%s对应的%s' % (key, en_value))
else:
cn_value = cn_dict[key]
if en_value == cn_value:
is_complete = False
incomplete_dict[key] = en_value
# print('%s对应的翻译仍然是%s，未翻译' % (key, en_value))
else:
translation_count_in_file += 1
complete_count += 1
if not is_complete:
print('文件未完全翻译' + en_file)
incomplete_file.append(en_file)
else:
if translation_count_in_file == 0:
# 一句都没翻译
# print('文件一句都没翻译' + en_file)
same_file.append(en_file)
else:
complete_file.append(en_file)
print('文件翻译完整' + en_file)
print('缺少%d个文件' % len(miss_file))
print(miss_file)
print('有%d个文件完全相同' % len(same_file))
print('有%d个文件未翻译完整' % len(incomplete_file))
print(incomplete_file)
print('有%d个文件完整翻译,共%d条翻译' % (len(complete_file), complete_count))
if out_put is not None:
result = list()
for key, value in incomplete_dict.items():
result.append('%s=%s\n\n' % (key, value))
print('incomplete size is %d' %
len(sorted(incomplete_dict.keys())))
filex.write_lines(out_put, result)
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)