Mercurial > repos > fabio > sbtas_se

comparison query.py @ 10:027f2e9d4a25 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded 20180131
author fabio
date Wed, 31 Jan 2018 17:29:01 -0500
parents 256d015d69f9
children 039e8e1e8b1f
comparison
equal deleted inserted replaced
9:f9ba0b65e1fa 10:027f2e9d4a25
5 5
6 import os, uuid, optparse, requests, json, time 6 import os, uuid, optparse, requests, json, time
7 #from requests_futures.sessions import FuturesSession 7 #from requests_futures.sessions import FuturesSession
8 8
9 #### NN14 #### 9 #### NN14 ####
10 service_url = "http://nn14.galaxyproject.org:8080/"; 10 SERVICE_URL = "http://nn14.galaxyproject.org:8080/";
11 #service_url = "http://127.0.0.1:8082/"; 11 #service_url = "http://127.0.0.1:8082/";
12 query_url = service_url+"tree/0/query"; 12 QUERY_URL = SERVICE_URL+"tree/0/query";
13 status_url = service_url+"status/<task_id>"; 13 STATUS_URL = SERVICE_URL+"status/<task_id>";
14 ############## 14 ##############
15 # query delay in seconds 15 # query delay in seconds
16 query_delay = 30; 16 QUERY_DELAY = 30;
17 ############## 17 ##############
18
19 VALID_CHARS = '.-()[]0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ '
18 20
19 def query_request( options, args, payload ): 21 def query_request( options, args, payload ):
20 # add additional parameters to the payload 22 # add additional parameters to the payload
21 #payload["tree_id"] = str(options.treeid); 23 #payload["tree_id"] = str(options.treeid);
22 payload["search_mode"] = str(options.search); 24 payload["search_mode"] = str(options.search);
26 headers = {'Content-type': 'application/json'}; 28 headers = {'Content-type': 'application/json'};
27 29
28 # create a session 30 # create a session
29 session = requests.Session(); 31 session = requests.Session();
30 # make a synchronous post request to the query route 32 # make a synchronous post request to the query route
31 req = session.post(query_url, headers=headers, json=payload); 33 req = session.post(QUERY_URL, headers=headers, json=payload);
32 resp_code = req.status_code; 34 resp_code = req.status_code;
33 print(str(req.content)+"\n\n"); 35 print(str(req.content)+"\n\n");
34 if resp_code == requests.codes.ok: 36 if resp_code == requests.codes.ok:
35 resp_content = str(req.content); 37 resp_content = str(req.content);
36 # convert out to json 38 # convert out to json
43 task_status = None; 45 task_status = None;
44 while task_processed is False: 46 while task_processed is False:
45 # create a new session 47 # create a new session
46 session = requests.Session(); 48 session = requests.Session();
47 # make a synchronous get request to the status route 49 # make a synchronous get request to the status route
48 status_query_url = status_url.replace("<task_id>", task_id); 50 status_query_url = STATUS_URL.replace("<task_id>", task_id);
49 status_req = session.get(status_query_url); 51 status_req = session.get(status_query_url);
50 status_resp_content = str(status_req.content); 52 status_resp_content = str(status_req.content);
51 print(status_resp_content+"\n\n"); 53 print(status_resp_content+"\n\n");
52 # convert out to json 54 # convert out to json
53 json_status_content = json.loads(status_resp_content); 55 json_status_content = json.loads(status_resp_content);
57 task_processed = True; 59 task_processed = True;
58 break; 60 break;
59 elif json_status_content['state'] in ['FAILURE', 'REVOKED']: 61 elif json_status_content['state'] in ['FAILURE', 'REVOKED']:
60 return "Task status: "+str(json_status_content['state']); 62 return "Task status: "+str(json_status_content['state']);
61 else: 63 else:
62 time.sleep(query_delay); # in seconds 64 time.sleep(QUERY_DELAY); # in seconds
63 65
64 # get output dir (collection) path 66 # get output dir (collection) path
65 output_dir_path = options.outputdir; 67 output_dir_path = options.outputdir;
66 if not os.path.exists(output_dir_path): 68 if not os.path.exists(output_dir_path):
67 os.makedirs(output_dir_path); 69 os.makedirs(output_dir_path);
68 out_file_format = "txt"; 70 out_file_format = "tabular";
69 71
70 for block in json_status_content['results']: 72 for block in json_status_content['results']:
71 seq_id = block['sequence_id']; 73 seq_id = block['sequence_id'];
72 accessions = block['accession_numbers']; 74 accessions = block['accession_numbers'];
73 # put response block in the output collection 75 # put response block in the output collection
98 for line in content_file: 100 for line in content_file:
99 if line.strip() != "": 101 if line.strip() != "":
100 line_split = line.strip().split("\t"); # split on tab 102 line_split = line.strip().split("\t"); # split on tab
101 if len(line_split) == 2: # 0:id , 1:seq , otherwise skip line 103 if len(line_split) == 2: # 0:id , 1:seq , otherwise skip line
102 seq_id = line_split[0]; 104 seq_id = line_split[0];
105 # fix seq_id using valid chars only
106 seq_id = ''.join(e for e in seq_id if e in VALID_CHARS)
103 seq_text = line_split[1]; 107 seq_text = line_split[1];
104 if seq_id in multiple_data: 108 if seq_id in multiple_data:
105 return "Error: the id '"+seq_id+"' is duplicated"; 109 return "Error: the id '"+seq_id+"' is duplicated";
106 multiple_data[seq_id] = seq_text; 110 multiple_data[seq_id] = seq_text;
107 if len(multiple_data) > 0: 111 if len(multiple_data) > 0:
122 for line in text_content: 126 for line in text_content:
123 if line.strip() != "": 127 if line.strip() != "":
124 line_split = line.strip().split("__tc__"); # split on tab 128 line_split = line.strip().split("__tc__"); # split on tab
125 if len(line_split) == 2: # 0:id , 1:seq , otherwise skip line 129 if len(line_split) == 2: # 0:id , 1:seq , otherwise skip line
126 seq_id = line_split[0]; 130 seq_id = line_split[0];
131 # fix seq_id using valid chars only
132 seq_id = ''.join(e for e in seq_id if e in VALID_CHARS)
127 seq_text = line_split[1]; 133 seq_text = line_split[1];
128 if seq_id in multiple_data: 134 if seq_id in multiple_data:
129 return "Error: the id '"+seq_id+"' is duplicated"; 135 return "Error: the id '"+seq_id+"' is duplicated";
130 multiple_data[seq_id] = seq_text; 136 multiple_data[seq_id] = seq_text;
131 if len(multiple_data) > 0: 137 if len(multiple_data) > 0: