comparison query.py @ 8:256d015d69f9 draft

Uploaded 20180131
author fabio
date Wed, 31 Jan 2018 16:05:19 -0500
parents 97dd57f81d77
children 027f2e9d4a25
comparison
equal deleted inserted replaced
7:edc721c9c418 8:256d015d69f9
95 for idx, file_path in enumerate(file_paths): 95 for idx, file_path in enumerate(file_paths):
96 #file_name = file_names[idx]; 96 #file_name = file_names[idx];
97 with open(file_path, 'r') as content_file: 97 with open(file_path, 'r') as content_file:
98 for line in content_file: 98 for line in content_file:
99 if line.strip() != "": 99 if line.strip() != "":
100 line_split = line.strip().split("__tc__"); # split on tab 100 line_split = line.strip().split("\t"); # split on tab
101 if len(line_split) == 2: # 0:id , 1:seq , otherwise skip line 101 if len(line_split) == 2: # 0:id , 1:seq , otherwise skip line
102 seq_id = line_split[0]; 102 seq_id = line_split[0];
103 seq_text = line_split[1]; 103 seq_text = line_split[1];
104 if seq_id in multiple_data: 104 if seq_id in multiple_data:
105 return "Error: the id '"+seq_id+"' is duplicated"; 105 return "Error: the id '"+seq_id+"' is duplicated";