def patch(self, json_file):
with open(json_file) as json_data:
d = json.load(json_data)
if u'file_name' not in d:
return
file_name = d[u'file_name']
path = d[u'path']
encoding = d[u'encoding']
data = d[u'data']
# type: data
md5 = d[u'md5']
print file_name
print path
print encoding
print data
if not os.path.exists(path):
print 'Error: 找不到源文件！！'
return
file_md5 = get_file_md5(path)
if md5 != file_md5:
print 'Error: 源文件已经被篡改，不能覆盖！！'
return
print '=>验证通过，开始回填数据'
backup = path + '.backup'
# shutil.copy(path, backup) # 备份文件
with open(path) as f:
lines = f.readlines()
unicode_lines = map(lambda s: s.decode(encoding), lines)
print '======'
print unicode_lines
for (k, v) in data.items():
v.sort(reverse=True, key=lambda x: x['start'])
for item in v:
line = unicode_lines[int(k)]
start = item['start']
end = item['end']
trans = item['trans']
# print start, end, '|', origin, '|', trans
new_line = line[:start] + trans + line[end:]
unicode_lines[int(k)] = new_line
print unicode_lines
lines = map(lambda s: s.encode(encoding), unicode_lines)
f = open(path, 'w')
f.writelines(lines)
f.close()
print '<=回填结束'
print ''
def resolve(self):
file_name = unicode(os.path.basename(self.path))
f = open(self.path)
code = chardet.detect(f.read())
f.seek(0, 0)
lines = f.readlines()
f.close()
try:
unicode_lines = map(lambda s: s.decode(code['encoding']), lines)
except UnicodeDecodeError as e:
print('fail to decode file: ', file_name)
print('except: ', e)
return {}
except TypeError as e:
print('fail to decode file: ', file_name)
print('except: ', e)
return {}
data = {}
# dict_map 保存找到的中文串
dict_map = {}
sort_order_data = ['text', 'start', 'end', 'origin', 'trans', 'auto']
for seq in xrange(len(unicode_lines)):
if self.is_comment(unicode_lines[seq]):
continue
# 匹配第一个正则表达式
m = re.finditer(self.pattern, unicode_lines[seq])
m_list = [i.span() for i in m]
if len(m_list) > 0:
data[seq] = []
for item in m_list:
item_data = {
'text': unicode_lines[seq],
'start': item[0],
'end': item[1],
'origin': unicode_lines[seq][item[0]:item[1]],
'trans': self.transform((unicode_lines[seq][item[0]:item[1]]), unicode_lines[seq], item[0],
item[1], unicode_lines, seq),
'auto': ''
}
# 保存中文串
dict_map[unicode_lines[seq][item[0]:item[1]][1:-1]] = unicode_lines[seq][item[0]:item[1]][1:-1]
# 排序字典
data_ordered = OrderedDict(
sorted(item_data.iteritems(), key=lambda (k, v): sort_order_data.index(k)))
data[seq].append(data_ordered)
# 匹配第二个正则表达式
# print 'second'
m = re.finditer(self.pattern_plus, unicode_lines[seq])
m_list = [i.span() for i in m]
if len(m_list) > 0:
if seq not in data:
data[seq] = []
for item in m_list:
start = item[0]
end = item[1]
if not self.is_item_include(start, end, data[seq]):
# print item
# print unicode_lines[seq][item[0]:item[1]]
item_data = {
'text': unicode_lines[seq],
'start': item[0],
'end': item[1],
'origin': unicode_lines[seq][item[0]:item[1]],
'trans': self.transform_simple((unicode_lines[seq][item[0]:item[1]])),
'auto': ''
}
# 保存中文串
dict_map[unicode_lines[seq][item[0]:item[1]]] = unicode_lines[seq][item[0]:item[1]]
# 排序字典
data_ordered = OrderedDict(
sorted(item_data.iteritems(), key=lambda (k, v): sort_order_data.index(k)))
data[seq].append(data_ordered)
ret = {
'path': unicode(self.path),
'file_name': file_name,
'md5': get_file_md5(self.path),
'encoding': code['encoding'],
'data': data,
}
sort_order = ['file_name', 'md5', 'path', 'encoding', 'data']
ret_ordered = OrderedDict(sorted(ret.iteritems(), key=lambda (k, v): sort_order.index(k)))
if not os.path.exists(self.output_path):
os.makedirs(self.output_path)
if len(data) <= 0:
return
f = codecs.open(
os.path.join(self.output_path, file_name + '-' + hashlib.md5(self.path).hexdigest() + '-output.json'), 'w',
encoding="utf-8")
f.write(json.dumps(ret_ordered, encoding='utf-8', ensure_ascii=False, indent=4))
f.close()
return dict_map