def create_pseudo_translation(jar_file, project_dir, result_file=None, translate_type='empty'):
"""
创建伪翻译
java -jar OmegaT.jar <project-dir> --mode=console-createpseudotranslatetmx --pseudotranslatetmx=<filename>
--pseudotranslatetype=[equal|empty]
:param jar_file: OmegaT 的 jar 文件
:param project_dir: 项目目路
:param result_file: 结果文件，tmx 格式
:param translate_type: 翻译类型，可选 equal | empty
:return:
"""
if result_file is None:
result_file = filex.get_result_file_name('pseudo', '', 'tmx')
cmd = 'java -jar %s %s --mode=console-createpseudotranslatetmx --pseudotranslatetmx=%s ' \
'--pseudotranslatetype=%s' % (jar_file, project_dir, result_file, translate_type)
print(cmd)
subprocess.call(cmd, shell=True)
print('已输出文件 %s' % result_file)
auto_file = 'data/auto.tmx'
shutil.copyfile(result_file, auto_file)
print('已复制文件 %s' % auto_file)
translation_file = 'data/translation.tmx'
shutil.copyfile(result_file, translation_file)
print('已复制文件 %s' % translation_file)
def process_keymap_reference_card_translation(en_file,
cn_file,
result_file=None):
"""
将翻译结果转为md文件
:param en_file:
:param cn_file:
:param result_file:
:return:
"""
if result_file is None:
result_file = filex.get_result_file_name(en_file, '_result', 'md')
en_lines = filex.read_lines(en_file)
cn_lines = filex.read_lines(cn_file)
if en_lines is None or cn_lines is None:
return None
# 以[]中一个或多个#开头，接内容
p_title = re.compile(r'^\[(#+)\]\s?(.*)')
result = []
for i in range(len(cn_lines)):
line = cn_lines[i]
line = encodex.unicode_str_to_chinese(line)
line = re.sub(p_title, r'\1 \2', line)
en_line = en_lines[i].replace('\n', '')
if '【' in en_line:
shortcut = en_line.split('【')[1]
line = line.replace('* ', "")
line = '* %-30s%s' % ('【%s】' % shortcut, line)
result.append(line)
filex.write_lines(result_file, result)
def check_and_append_tips_name(file_path,
tips_name_file,
result_file=None):
"""
根据检查tips的文件是否全
该方法用于 IdeTipsAndTricks 没有指定所有的文件，但还是需要翻译文件名的，所以补全
"""
if result_file is None:
result_file = filex.get_result_file_name(tips_name_file, '_append')
file_list = filex.list_file(file_path)
print('共%d个文件' % len(file_list))
lines = filex.read_lines(tips_name_file)
tips_name = []
for line in lines:
if '=' in line:
name = line.split('=')[0]
tips_name.append(name)
# 名字只加一层，exclude里面的不处理
file_name = '%s\\%s.html' % (file_path, name)
if file_name in file_list:
file_list.remove(file_name)
else:
print('文件不存在%s' % file_name)
print('共有%d个tip名' % len(tips_name))
print('还缺%d个文件' % len(file_list))
# 写入结果
lines.append('\n# append\n')
for file_name in file_list:
name = os.path.splitext(os.path.split(file_name)[1])[0]
word = Tips.camel_word_to_words(name)
lines.append('%s=%s\n' % (name, word))
filex.write_lines(result_file, lines)
def get_all_translation(en_dir,
cn_dir,
dict_file=None,
dict_diff_file=None,
suffix=''):
if dict_file is None:
base_name = os.path.split(cn_dir)[1]
dict_file = 'data/%s_dict.txt' % base_name
if dict_diff_file is None:
dict_diff_file = filex.get_result_file_name(dict_file, '_diff')
"""读取并输出所有翻译"""
all_translation, diff_translation = Translator.check_same_en_difference_cn(
en_dir, cn_dir, False, suffix)
result = list()
for key, value in all_translation.items():
result.append('%s=%s\n' % (key, value))
print('size is %d' % len(sorted(all_translation.keys())))
filex.write_lines(dict_file, result)
result = list()
for key, value in diff_translation.items():
result.append('%s=%s\n\n' % (key, value))
print('size is %d' % len(sorted(diff_translation.keys())))
filex.write_lines(dict_diff_file, result)
def process_keymap_reference_card(file_path, result_file=None):
"""
处理快捷键参考文件
来自：https://resources.jetbrains.com/storage/products/intellij-idea/docs/IntelliJIDEA_ReferenceCard.pdf
保存后将其复制出来，然后用“【”划分快捷键，再进行一次处理
:param file_path:
:param result_file:
:return:
"""
if result_file is None:
result_file = filex.get_result_file_name(file_path, '_modified',
'properties')
lines = filex.read_lines(file_path)
if lines is None:
return
result = []
# 以一个或多个#开头，接内容
p_title = re.compile(r'^(#+)\s?(.*)')
for line in lines:
line = line.replace('\n', '')
line = re.sub(p_title, r'[\1] \2', line)
if '【' in line:
split_result = line.split('【')
line = '* %s' % split_result[0]
result.append(line + '\n')
filex.write_lines(result_file, result)
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 convert_to_omegat_dict(en_file, cn_file, output_file=None):
"""
将翻译结果转为omegaT的字典
:param en_file: 英文文件
:param cn_file: 中文文件
:param output_file: 输出文件
:return:
"""
if output_file is None:
output_file = filex.get_result_file_name(cn_file, '_omegat_result',
'xml')
en_dict = Tools.get_dict_from_file(en_file)
cn_dict = Tools.get_dict_from_file(cn_file)
tmx = Et.Element('tmx')
tmx.attrib['version'] = '1.1'
Et.SubElement(tmx, 'header')
body = Et.SubElement(tmx, 'body')
for (k, v) in cn_dict.items():
if k in en_dict.keys():
en_value = en_dict[k]
cn_value = v
# 判断是否有多个句子，"."加一个空格
added = False
if '. ' in en_value:
en_split = en_value.split('. ')
if en_split[1] != '':
# 包含“.”，不是在最后的“...”
# 检查中文
if '。 ' in cn_value:
cn_split = cn_value.split('。 ')
if len(en_split) == len(cn_split):
added = True
# 中英长度相等
for i in range(len(en_split)):
Tools.add_translate_element(
body, en_split[i], cn_split[i])
print('分开添加:' + cn_split[i])
else:
print('')
print(en_value)
print(cn_value)
print('%d,%d' % (len(en_split), len(cn_split)))
else:
print('')
print(en_value)
print(cn_value)
print('英文中有“. ”，中文中不包含“。 ”')
if not added:
if cn_value:
# 只添加不为空的
Tools.add_translate_element(body, en_value, cn_value)
tree = Et.ElementTree(tmx)
tree.write(output_file, encoding='utf-8')
print('输出为' + output_file)
def delete_symbol(delete_type, file, file_type=0, result_file=None):
delete_action = DeleteAction.action_list[delete_type]
if result_file is None:
result_file = filex.get_result_file_name(file, delete_action[2])
if file_type == DeleteAction.FILE_TYPE_OMEGAT:
DeleteAction.delete_symbol_of_omegat(file, result_file,
delete_action[3:])
else:
DeleteAction.delete_symbol_of_file(file, result_file,
delete_action[3:])
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 process_tips_manifest_file(self):
tips = Tips()
project_name_list = os.listdir(self.source_dir)
for project_name in project_name_list:
project_path = self.source_dir + os.sep + project_name
if os.path.isdir(project_path):
tips_file_path = project_path + os.sep + 'IdeTipsAndTricks' + os.sep + 'IdeTipsAndTricks.xml'
tips_en_file = filex.get_result_file_name(tips_file_path, '_en', 'properties')
if os.path.exists(tips_file_path):
print('处理 %s' % tips_file_path)
tips.process_tips_manifest_file(tips_file_path, tips_en_file)
def export_omegat_dictionary_to_file(file_path, result_file=None):
"""导出omegat的词库为文件"""
if result_file is None:
result_file = filex.get_result_file_name(file_path, '', 'txt')
omegat_dict = Translator.get_omegat_dict(file_path)
result = list()
for key, value in omegat_dict.items():
result.append('%s=%s\n' % (key, value))
print('size is %d' % len(sorted(omegat_dict.keys())))
filex.write_lines(result_file, result)
def check_and_append_tips_name(self):
tips = Tips()
project_name_list = os.listdir(self.source_dir)
for project_name in project_name_list:
project_path = self.source_dir + os.sep + project_name
if os.path.isdir(project_path):
tips_file_path = project_path + os.sep + 'IdeTipsAndTricks' + os.sep + 'IdeTipsAndTricks.xml'
tips_en_file = filex.get_result_file_name(tips_file_path, '_en', 'properties')
if os.path.exists(tips_file_path):
print('处理 %s' % tips_file_path)
project_tips_path = project_path + os.sep + 'resources_en' + os.sep + 'tips'
tips.check_and_append_tips_name(project_tips_path, tips_en_file, tips_en_file)
def handle_keymap_file(en_file, cn_file, comment_file, result_file=None):
"""
将一行一行的keymap重新处理
导出为.properties，这样OmegaT处理时会换照配置文件去处理
我们以[#]或[desc]加空格为开头，会被过滤器正确解析
:param en_file:
:param cn_file:
:param comment_file:
:param result_file:
:return:
"""
if result_file is None:
result_file = filex.get_result_file_name(cn_file,
'_add_desc_and_comment',
'properties')
lines = filex.read_lines(cn_file)
if lines is None:
return
desc_dict = KeymapList.get_action_desc_dict(en_file)
comment_dict = KeymapList.get_comment_dict(comment_file)
count = 0
desc_count = 0
result = []
for line in lines:
line = line.replace('\n', '')
if line.startswith('#'):
old_line = line
# 因为有加了#，所以处理下
line = line.lstrip('# ')
# 相差的长度是trip掉的，注意在替换了\n之后
prefix = old_line[0:len(old_line) - len(line)].rstrip()
else:
prefix = '#' * 5
append = ''
count += 1
if line in desc_dict.keys():
desc = desc_dict[line]
desc_count += 1
print('%d/%d,line=%s,desc=%s' %
(count, desc_count, line, desc))
# 有描述，添加
append += '\n\n%s %s' % ('[desc]', desc)
if line in comment_dict.keys():
comment = comment_dict[line]
print('%s的描述为%s' % (line, comment))
append += '\n\n%s' % comment
line = '\n\n[%s] %s%s' % (prefix, line, append)
result.append(line)
filex.write_lines(result_file, result)
def inspect_file(pseudo_file,
translation_file,
inspection_list,
result_file=None,
print_msg=False,
print_change=False):
"""
:param pseudo_file: 伪翻译文件，也可以与翻译文件相同，用于自校检
:param translation_file: 翻译文件
:param inspection_list: 要检测的方法列表，如检测tips时是不需要检测快捷方式的
:param result_file: 结果文件
:param print_msg: 是否输出操作时的消息
:param print_change: 是否输出更改时的消息，如果2个都置为False，可以查看需要处理的内容
:return:
"""
if result_file is None:
result_file = filex.get_result_file_name(translation_file,
'_inspection')
pseudo_dict = Tools.get_dict_from_omegat(pseudo_file)
translation_dict = Tools.get_dict_from_omegat(translation_file)
print(u'pseudo size is %d' % (len(pseudo_dict)))
print(u'translation size is %d' % (len(translation_dict)))
result = dict()
i = 0
for en in pseudo_dict.keys():
cn_key = None
if en in translation_dict.keys():
cn_key = en
else:
abbreviated_en = DeleteAction.delete_all_symbol_of_string(
en, False)
if abbreviated_en in translation_dict.keys():
cn_key = abbreviated_en
if cn_key:
value = translation_dict[cn_key]
if not value:
continue
translation_dict.pop(cn_key)
old = value
for inspection in inspection_list:
value = inspection(en, value, print_msg)
if old != value:
if print_change:
i += 1
print(u'\n%d.\n【%s】根据【%s】被修改为\n【%s】\n' %
(i, old, en, value))
result[en] = value
else:
print(u'不包含key:%s' % en)
print(u'remain translation size %d' % (len(translation_dict)))
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 write_to_excel(result_file, excel_file=None):
"""
写入excel
:param result_file:
:param excel_file:
:return:
"""
if excel_file is None:
excel_file = filex.get_result_file_name(result_file, '', 'xls')
lines = filex.read_lines(result_file, ignore_line_separator=True)
if lines is None:
return
excelx.write_list_to_excel(excel_file, lines, title=Floor.get_excel_title())
def process_dir_translation_result(en_dir, cn_dir, result_dir=None, name_pattern=None):
"""处理文件夹中的所有文件"""
if result_dir is None:
result_dir = cn_dir + '_add'
en_file_list = filex.list_file(en_dir, name_pattern)
length = len(en_file_list)
for i in range(length):
en_file = en_file_list[i]
print('process %d/%d' % (i + 1, length))
cn_file = en_file.replace(en_dir, cn_dir)
cn_file = filex.get_result_file_name(cn_file, '_zh_CN')
result_file = en_file.replace(en_dir, result_dir)
ActionsBundle.add_ellipsis_and_shortcut(en_file, cn_file, result_file)
def __init__(self,
file: str,
output: str = None,
start_line=None,
end_line=None):
self.file = file
self.output = output
if self.output is None:
self.output = filex.get_result_file_name(self.file, '_line')
self.start_line = start_line
"""起始行，用于只处理部分内容"""
self.end_line = end_line
"""结束行，一般最后的致谢等内容不需要处理，需要过滤"""
def process_tips_manifest_file(self, file_path, result_file=None):
"""
处理清单文件，整理tips的名称方便翻译
:param file_path:
:param result_file:
:return:
"""
if result_file is None:
result_file = filex.get_result_file_name(file_path, '_en',
'properties')
ordered_file_list = self.get_tips_order_files(file_path)
result = []
for file in ordered_file_list:
name = file.split('.')[0]
word = self.camel_word_to_words(name)
result.append('%s=%s\n' % (name, word))
filex.write_lines(result_file, result)
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 process_file_for_translation(file, result_file=None):
"""
在翻译前处理文件
删除快捷方式
删除末尾的.或省略号
:param file:
:param result_file:
:return:
"""
if result_file is None:
result_file = filex.get_result_file_name(file, '_modified')
print('删除省略号')
DeleteAction.delete_ellipsis(file, result_file)
# 后面的将接着用result_fiel
print('删除快捷方式')
DeleteAction.delete_underline_shortcut(result_file, result_file)
print('删除&形式的快捷方式')
DeleteAction.delete_and_shortcut(result_file, result_file)
print('再次删除省略号，防止位于快捷方式之前')
DeleteAction.delete_ellipsis(result_file, result_file)
def process_line_break_for_translation(self, file, output=None):
"""处理文件换行"""
if output is None:
output = filex.get_result_file_name(file, '_line')
ans = []
lines = filex.read_lines(file, ignore_line_separator=True)
if not lines:
print(f'文件内容为空：{file}')
exit()
n = len(lines)
i = 0
while i < n:
line = lines[i]
print(f'{i} {line}')
if self.need_inline(i, line, ans):
print(f'{i} 行符合合并规则，尝试连接到上一行 {ans[-1]}')
self.inline(line, ans)
else:
ans.append(line)
i += 1
filex.write_lines(output, ans, add_line_separator=True)
def translate_file_by_reference(self,
en_file,
cn_file,
result_file=None,
untranslated_replace=None):
"""
根据参考翻译文件
:param en_file:英文
:param cn_file: 参考中文
:param result_file: 结果文件
:param untranslated_replace:未翻译时替换
:return:
"""
if result_file is None:
result_file = filex.get_result_file_name(en_file,
'_translation_result')
translation_dict = Tools.get_dict_from_file(cn_file)
result = self.translate_file_by_dict(en_file, translation_dict,
untranslated_replace)
filex.write_lines(result_file, result)
def change_unicode_to_chinese(file_path, output_file=None):
"""
将unicode转为中文
:param file_path:源文件
:param output_file: 输出文件
:return:
"""
if output_file is None:
output_file = filex.get_result_file_name(file_path, '_cn_result')
lines = filex.read_lines(file_path)
if lines is None:
return
result = []
for line in lines:
line = line.replace('\n', '')
if '=' in line:
key_value = line.split('=', 1)
line = '%s=%s' % (key_value[0],
encodex.unicode_str_to_chinese(key_value[1]))
result.append(line + '\n')
filex.write_lines(output_file, result)
def filter(file_path, ignore_reg_list, result_path=None):
"""过滤掉不需要翻译的"""
if result_path is None:
result_path = filex.get_result_file_name(file_path, '_filter')
"""删除空翻译"""
tree = Et.parse(file_path)
tmx = tree.getroot()
body = tmx.find('body')
empty_translation_list = list()
for tu in body.iter('tu'):
en = None
for tuv in tu.iter('tuv'):
if tuv.attrib['lang'] == 'EN-US':
en = tuv.find('seg').text
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【%s】' % en)
empty_translation_list.append(tu)
break
if continue_loop:
continue
print('删除 %d 条空翻译' % len(empty_translation_list))
for empty_translation in empty_translation_list:
body.remove(empty_translation)
tree.write(result_path, encoding='utf-8')
print('保存完成')
def filter_log(self, log_file):
lines = filex.read_lines(log_file)
print(f'日志 {len(lines)} 行')
lines = list(filter(self.filter_line, lines))
print(f'过滤后 {len(lines)} 行')
filex.write_lines(filex.get_result_file_name(log_file, '_result'), lines)
def process_translated_keymap_file(en_file, cn_file, result_file=None):
"""
处理翻译完的文件
:param en_file:
:param cn_file:
:param result_file:
:return:
"""
if result_file is None:
result_file = filex.get_result_file_name(cn_file, '_final')
en_lines = filex.read_lines(en_file)
cn_lines = filex.read_lines(cn_file)
if cn_lines is None:
return
result = []
p_title = re.compile(r'^\[(#+)\]\s?(.*)')
p_title2 = re.compile(r'(\n*)(#+\s)(.*)')
p_desc = re.compile(r'^\[desc\]\s?(.*)')
p_comment = re.compile(r'^#\[(x+)\](.*)')
for i in range(len(cn_lines)):
line = cn_lines[i].replace('\n', '')
if line.startswith('#'):
# 以#开头不翻译，取原文
line = en_lines[i].replace('\n', '')
match = re.match(p_comment, line)
if match is not None:
# 注释
start_number = match.group(1)
if len(start_number) == 1:
# 1颗星标记基本注释
replace_result = ' \n译注：%s' % (match.group(2))
else:
# 2星以上为加重注释
# 向上寻找标题并加重
last_index = -1
while result[last_index] == '' or re.match(p_title2, result[last_index]) is None:
last_index -= 1
last_line = result[last_index]
if '★' not in last_line:
start_replace = '★' * (len(start_number) - 1)
last_line = re.sub(p_title2, r'\1\2*%s\3%s*' % (start_replace, start_replace),
last_line)
print('替换标题【%s】为【%s】' % (result[last_index], last_line))
result[last_index] = last_line
replace_result = ' \n译注：%s' % (match.group(2))
# print('替换【%s】为【%s】' % (line, replace_result))
line = '%s' % replace_result
else:
# 不以#开头
line = encodex.unicode_str_to_chinese(line)
en_line = en_lines[i].replace('\n', '')
match = re.match(p_title, line)
if match is not None:
# 是标题
en_match = re.match(p_title, en_line)
if len(en_match.group(1)) == 5:
replace_result = '\n\n%s（%s）' % (en_match.group(2), match.group(2))
else:
replace_result = '\n\n%s %s（%s）' % (en_match.group(1), en_match.group(2), match.group(2))
# print('\n替换【%s】为【%s】' % (line, replace_result))
line = '%s' % replace_result
else:
desc_cn_match = re.match(p_desc, line)
if desc_cn_match is not None:
# 是描述
desc_en_match = re.match(p_desc, en_line)
replace_result = ' \n%s \n描述：%s' % (desc_en_match.group(1), desc_cn_match.group(1))
# print('\n描述替换【%s】为【%s】' % (line, replace_result))
line = '%s' % replace_result
result.append(line)
filex.write_lines(result_file, result)
def get_cn_file_name(en_dir, cn_dir, en_file, suffix=None):
"""获取英文文件对应的中文文件，可能会变，所以提出来"""
cn_file = en_file.replace(en_dir, cn_dir)
cn_file = filex.get_result_file_name(cn_file, suffix)
return cn_file
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)
