def test_split(self):
text_split = 'aa/bb\\cc_dd-ee ff'
text_list = CUtils.split(text_split, ['\\', '/', '-', '_', ' '])
assert len(text_list) == 6
assert text_list.count('ff') == 1
assert text_list
print(text_list)
def process(self) -> str:
"""
在这里处理将__file_info__中记录的对象所对应的文件或目录信息, 根据tags_parser_rule的定义, 进行标签识别
:return:
"""
# 调用父类方法
super().process()
if not isinstance(self._tags_parser_rule, list):
return CResult.merge_result(self.Failure,
'标签解析规则必须是一个数组, 您的配置有误, 请检查!')
error_list = []
for tags_parser in self._tags_parser_rule:
catalog = CUtils.any_2_str(
CUtils.dict_value_by_name(tags_parser, self.Name_Catalog, ''))
tag_field_name = CUtils.any_2_str(
CUtils.dict_value_by_name(tags_parser, self.Name_Tag, ''))
keyword_field_list = CUtils.dict_value_by_name(
tags_parser, self.Name_Keyword, None)
data_sample = CUtils.any_2_str(
CUtils.dict_value_by_name(tags_parser, self.Name_Data_Sample,
''))
separator = CUtils.dict_value_by_name(tags_parser,
self.Name_Separator, None)
enable = CUtils.dict_value_by_name(tags_parser, self.Name_Enable,
True)
fuzzy_matching = CUtils.dict_value_by_name(
tags_parser, self.Name_Fuzzy_Matching, False)
if not enable:
continue
if CUtils.equal_ignore_case(tag_field_name, ''):
continue
if CUtils.equal_ignore_case(catalog, ''):
continue
if keyword_field_list is None:
continue
if len(keyword_field_list) == 0:
continue
if CUtils.equal_ignore_case(data_sample,
self.Tag_DataSample_MainName):
# 如果是主名, 则将对象名称和别名, 都以文件路径的格式, 补充在主名之后, 合并进行分类识别
tag_data_sample_str = CFile.join_file(
CFile.join_file(
CUtils.any_2_str(self.file_info.file_main_name),
self.object_name), self.__file_alias_name)
elif CUtils.equal_ignore_case(data_sample,
self.Tag_DataSample_RelationPath):
tag_data_sample_str = CUtils.any_2_str(
self.file_info.file_path_with_rel_path)
else:
# 如果是主名, 则将对象名称和别名, 都以文件路径的格式, 补充在相对路径的文件主名之后, 合并进行分类识别
tag_data_sample_str = CFile.join_file(
CFile.join_file(
CUtils.any_2_str(
self.file_info.file_main_name_with_rel_path),
self.object_name), self.__file_alias_name)
try:
tag_data_sample_list = CUtils.split(tag_data_sample_str,
separator)
self.process_tag(catalog, tag_field_name, keyword_field_list,
tag_data_sample_list, fuzzy_matching)
except Exception as error:
error_list.append(
'对象[{0}]在处理标签库[{1}]分类[{2}]有误, 详细错误信息为: {3}'.format(
self.object_name, catalog, tag_data_sample_str,
error.__str__()))
if len(error_list) == 0:
return CResult.merge_result(
self.Success, '文件或目录[{0}]对象业务分类解析成功完成!'.format(
self.file_info.file_main_name_with_rel_path))
else:
error_message = '文件或目录[{0}]的业务分类解析处理完毕, 但解析过程中出现了错误, 具体如下: \n'.format(
self.file_info.file_main_name_with_rel_path)
for error_str in error_list:
error_message = CUtils.str_append(error_message, error_str)
return CResult.merge_result(self.Success, error_message)
:param data_sample_list:
:param keyword_value:
:param fuzzy_matching:
:return:
"""
keyword_text = CUtils.any_2_str(keyword_value).lower()
if fuzzy_matching:
for data_sample in data_sample_list:
data_sample_text = CUtils.any_2_str(data_sample).lower()
if data_sample_text.find(keyword_text) > -1:
return True
else:
if CUtils.list_count(data_sample_list, keyword_value) > 0:
return True
return False
if __name__ == '__main__':
"""
Job对象的简洁测试模式
创建时, 以sch_center_mission表的scmid, scmParams的内容初始化即可, 调用其execute方法, 即是一次并行调度要运行的主要过程
"""
# tags_parser_text = r'县界'
tags_parser_text = r'县界_昆明市-2019-2018 2017'
# 标签分隔符
tags_parser_split_list: list = ['\\', '_', '/', '-', ' ']
text_part_list = CUtils.split(tags_parser_text, tags_parser_split_list)
for item in text_part_list:
print(item)
