parseval

##https://github.com/nickpettican/PDB-parser/blob/master/PDBparser.py

import gzip
import os
import re
import sys
from operator import itemgetter
from itertools import groupby
#import chimera
#from chimera import runCommand
#import Midas
#import MatchMaker

def openPDBFile(protein_name):
    f = gzip.open(pathFinder(protein_name), 'rb')
    file = f.read()
    return file
def  PDBFileOnEnt(protein_name):
    return gzip.open(pathFinder(protein_name), 'rb')
num_of_str_with = []
#find strings with this protein name
def findSims(protein_name):
    f = open('95sim', 'r');
    strings = f.read();
    str_array = strings.splitlines()
    for m in range(len(str_array)):
        if (str_array[m].find(protein_name) <> -1):
            num_of_str_with.append(m)  # count from 0th string

def pathFinder(protein_name):
    path = '/home/dima/pdb/' + protein_name[1].lower() + protein_name[2].lower() + '/pdb' + protein_name.lower() + '.ent.gz'
    return path
#save file from tar gz to pdb file
def saveInFile(protein_name):
    f = open('/home/dima/artur/forpdb/' + protein_name + '.pdb', 'w')
    f.write(openPDBFile(protein_name))
#save and return the path to reserved file
def pathFinderPDB(protein_name):
    saveInFile(protein_name)
    return '/home/dima/artur/forpdb/' + protein_name + '.pdb'
#pars of PDB file
def parsPDB(protein_name):
    data = [line.strip() for line in open(pathFinderPDB(protein_name), 'r')]
    return data
#print and find all differents elemenents in line[0]
def lineHeads(protein_name):
    data = [line.strip().split for line in open(pathFinderPDB(protein_name), 'r')]
    print "The file has %s lines \n" % len(data)
    line_head_set = set()
    for line in data:
        if line[0] != "END":
            line_head_set.add(line[0])
    for element in set(line_head_set):
        x = [line[0].count(element) for line in data]
        print "{x} of which are {y} elements\n".format(x=x.count(1), y=element)

def findElement(pdb, busca):
    return sum( 1 for l in pdb if re.search(busca, l))

def findRange(pdb,busca):
    # finds the range/s where the query "busca" is
    range_busca = [i for i, line in enumerate(pdb) if re.search(busca, line)]
    real_ranges = [map(itemgetter(1), value)
                  for i, value in groupby(enumerate(range_busca),
                  lambda (i, x): i-x)]
    if len(real_ranges) == 1:
        return [[real_ranges[0][0], real_ranges[0][-1] + 1]]
    elif len(real_ranges) >= 2:
        return [[real_ranges[i][0], real_ranges[i][-1] + 1]
                for i, line in enumerate(real_ranges)]
def returnThePart(pdb, busca):
    range = findRange(pdb, busca)



protein_name = sys.argv[1]
lineHeads(protein_name)
data = parsPDB(protein_name)
print findRange(data, 'HETATM')