annotate search.py @ 2:4291c9d1ff07 draft

Uploaded 20180124

#!/usr/bin/env python

# https://github.com/ross/requests-futures
# http://docs.python-requests.org/en/master/user/quickstart/#more-complicated-post-requests

import os, uuid
import optparse
import requests
from requests_futures.sessions import FuturesSession

#### UV0 ####
# proxy to uv0
#service_url = "http://deputy.bx.psu.edu/";
# url to query page
#query_url = service_url+"query.php";
# url to echo page: just return 'it works!'
#echo_url = service_url+"echo.php";
#############

#### NN14 ####
service_url = "http://nn14.galaxyproject.org:8080/";
query_url = service_url+"tree/0/query";
##############

'''
# synchronous
def echo( options, args ):
    # create a session
    session = requests.Session()
    # make a sync get request
    resp = session.get(echo_url)
    # check for response status code
    resp_code = resp.status_code;
    if resp_code == requests.codes.ok:
        # get output file path
        output_file_path = options.output;
        # write response on the output file
        with open(output_file_path, 'w') as out:
            #out.write(resp.data);
            out.write(resp.content);
        return 0;
    else:
        return resp_code;
'''

# asynchronous
def async_request( options, args, payload ):
    # add additional parameters to the payload
    #payload["tree_id"] = str(options.treeid);
    payload["search_mode"] = str(options.search);
    payload["exact_algorithm"] = int(options.exact);
    payload["search_threshold"] = float(options.sthreshold);
    # set the content type to application/json
    headers = {'Content-type': 'application/json'};
    # create a session
    session = FuturesSession();
    # make an async post request with requests-futures
    future_req = session.post(query_url, headers=headers, json=payload);
    # wait for the request to complete, if it has not already
    resp = future_req.result();
    # check for response status code
    resp_code = resp.status_code;
    # get output file path
    output_file_path = options.output;
    # write response on the output file
    with open(output_file_path, 'w') as out:
        #out.write(resp.data);
        out.write(str(resp.content));
    if resp_code == requests.codes.ok:
        return 0;
    else:
        return resp_code;

def srase_query( options, args ):
    multiple_data = {};
    comma_sep_file_paths = options.files;
    #print("files: "+str(comma_sep_file_paths)+" - "+str(type(comma_sep_file_paths)));
    # check if options.files contains at least one file path
    if comma_sep_file_paths is not None:
        # split file paths
        file_paths = comma_sep_file_paths.split(",");
        # split file names
        comma_sep_file_names = str(options.names);
        #print("names: "+str(comma_sep_file_names));
        file_names = comma_sep_file_names.split(",");
        # populate a dictionary with the files containing the sequences to query
        sequences = [];
        for idx, file_path in enumerate(file_paths):
            #file_name = file_names[idx];
            with open(file_path, 'r') as content_file:
                content = content_file.read()
                sequences.append(content.strip());
                #multiple_data[file_name] = content;
                #print(file_name+": "+content+"\n");
        if len(sequences) > 0:
            multiple_data['sequences'] = sequences;
            return async_request( options, args,  multiple_data );
            #return echo( options, args );
        else:
            return -1;
    else:
        # try with the sequence in --sequence
        text_content = options.sequences;
        #print("sequences: "+text_content);
        # check if options.sequences contains a list of sequences (one for each row)
        if text_content is not None:
            text_content = str(text_content);
            if text_content.strip():
                # populate a dictionary with the files containing the sequences to query
                multiple_data['sequences'] = text_content.strip().split("__cn__");
                return async_request( options, args, multiple_data );
                #return echo( options, args );
            else:
                return -1;
    return -1;

def __main__():
    # Parse the command line options
    usage = "Usage: search.py --files comma_sep_file_paths --names comma_seq_file_names --sequences sequences_text --search search_mode --exact exact_alg --sthreshold threshold --output output_file_path";
    parser = optparse.OptionParser(usage = usage);
    parser.add_option("-f", "--files", type="string",
                    action="store", dest="files", help="comma separated files path");
    parser.add_option("-n", "--names", type="string",
                    action="store", dest="names", help="comma separated names associated to the files specified in --files");
    parser.add_option("-s", "--sequences", type="string",
                    action="store", dest="sequences", help="contains a list of sequences (one for each row)");
    parser.add_option("-a", "--fasta", type="string",
                    action="store", dest="fasta", help="contains the content of a fasta file");
    parser.add_option("-x", "--search", type="string", default=0,
                    action="store", dest="search", help="search mode");
    parser.add_option("-e", "--exact", type="int", default=0,
                    action="store", dest="exact", help="exact algorithm (required if search is 1 only)");
    parser.add_option("-t", "--sthreshold", type="float",
                    action="store", dest="sthreshold", help="threshold applied to the search algrithm");
    parser.add_option("-o", "--output", type="string",
                    action="store", dest="output", help="output file path");
    (options, args) = parser.parse_args();
    return srase_query( options, args );

if __name__ == "__main__": __main__()