Ejemplo n.º 1
0
def scan( out_fd ):
    os.chdir( TEMP_DIRNAME )
    temp_files = os.listdir( CURR_DIR )
    s_files = [ s for s in temp_files if S_PREFIX in s ]
    hash_match = 0
    for s in s_files:        
        s_hash = proccess_input( f( s ) )
        hash_match += scan_trough_qs( s_hash, out_fd ) 
        
    print ( "Found {} entries".format( hash_match ) )
Ejemplo n.º 2
0
def make_parts( in_fd, prefix = 'unkn_' ):
    n = out_file_id = 0
    line = in_fd.readline()
    #print( os.getcwd() )
    os.chdir( TEMP_DIRNAME )
    out_fd = f ( '{}{}'.format( prefix, out_file_id ), mode = 'w' )
    while line:
        if n != 0 and ( n % SHARD_SIZE ) == 0:
            out_fd.close()
            out_file_id += 1
            out_fd = f ( '{}{}'.format( prefix, out_file_id ), mode = 'w' )

        out_fd.write( line )
        n += 1    
        line = in_fd.readline()

    out_fd.close()
    os.chdir( '..' )
    result = out_file_id if out_file_id > 0 else 1
    return result
Ejemplo n.º 3
0
def scan_trough_qs( s_hash, out_fd):
    temp_files = os.listdir( CURR_DIR )
    q_files = [ s for s in temp_files if Q_PREFIX in s ]
    hash_match = 0
    for q in q_files:        
        q_hash = proccess_input( f( q ) )
        #print( '{}{}'.format ( s_hash, q_hash ) )
        m, merged = compare_hashes( s_hash, q_hash )
        hash_match += m

    out.writelines( merged )  
    return hash_match
Ejemplo n.º 4
0
def runtime():
    with f( fname ) as fd:
        line = fd.readline()
        while line:            
            tokens = line.strip('\n').split('\t') #ugly thing
            req_id = tokens[1]
            req_type = tokens[2]
            req = curr_reqs.get( req_id )
            if req == None:
                req = Request()
            curr_reqs[req_id] = req
            req.proccess( tokens )
            line = fd.readline()
Ejemplo n.º 5
0
#    print( input_file.readlines() )
    for line in input_file.readlines():        
        num_id = line[:9]
        data = line[10:].strip( '\n' )
        result.setdefault( num_id, [] ).append( data )
        
    return result

if __name__ == '__main__':
    if len( argv ) < 3:
        print ( '{0} usage syntax {0} <input a file name> <input b file name>'.format( 'simple.py' ) )
        quit()
    fname_a = argv[1]
    fname_b = argv[2]
    fname_res = 'result.csv'
    input_a = f( fname_a, buffering = 1 )
    input_b = f( fname_b, buffering = 1 )
    out = f( fname_res, mode = 'w' ) 
    dict_a = {}
    dict_b = {}
    merged = []
    
    dict_a = proccess_input( input_a )
    dict_b = proccess_input( input_b )
    """
    print( 'dict_a')
    print( dict_a )
    print( 'dict_b')
    print( dict_b )
    """
    for k, a_v in dict_a.items():