reformat-headers.py

#!/usr/bin/env python3
from collections import defaultdict
import re
import os
import textwrap
import argparse
import sys


def SUM(ls):
    count = 0
    for i in ls:
        count += float(i)
    return count


def deExt(string):
    ls = string.split(".")
    ls2 = ls[0:len(ls) - 1]
    outstring = "".join(ls2)
    return outstring


def unique(ls, ls2):
    unqlist = []
    for i in ls:
        if i not in unqlist and i in ls2:
            unqlist.append(i)
    return len(unqlist)



def derep(ls):
    outLS = []
    for i in ls:
        if i not in outLS:
            outLS.append(i)
    return outLS


def cluster(data, maxgap):
    '''Arrange data into groups where successive elements
       differ by no more than *maxgap*

        #->>> cluster([1, 6, 9, 100, 102, 105, 109, 134, 139], maxgap=10)
        [[1, 6, 9], [100, 102, 105, 109], [134, 139]]

        #->>> cluster([1, 6, 9, 99, 100, 102, 105, 134, 139, 141], maxgap=10)
        [[1, 6, 9], [99, 100, 102, 105], [134, 139, 141]]

    '''
    # data = sorted(data)
    data.sort(key=int)
    groups = [[data[0]]]
    for x in data[1:]:
        if abs(x - groups[-1][-1]) <= maxgap:
            groups[-1].append(x)
        else:
            groups.append([x])
    return groups


def lastItem(ls):
    x = ''
    for i in ls:
        x = i
    return x


def RemoveDuplicates(ls):
    empLS = []
    for i in ls:
        if i not in empLS:
            empLS.append(i)
        else:
            pass
    return empLS


def allButTheLast(iterable, delim):
    x = ''
    length = len(iterable.split(delim))
    for i in range(0, length - 1):
        x += iterable.split(delim)[i]
        x += delim
    return x[0:len(x) - 1]


def secondToLastItem(ls):
    x = ''
    for i in ls[0:len(ls) - 1]:
        x = i
    return x


def pull(item, one, two):
    ls = []
    counter = 0
    for i in item:
        if counter == 0:
            if i != one:
                pass
            else:
                counter += 1
                ls.append(i)
        else:
            if i != two:
                ls.append(i)
            else:
                ls.append(i)
                counter = 0
    outstr = "".join(ls)
    return outstr


def stabilityCounter(int):
    if len(str(int)) == 1:
        string = (str(0) + str(0) + str(0) + str(0) + str(int))
        return (string)
    if len(str(int)) == 2:
        string = (str(0) + str(0) + str(0) + str(int))
        return (string)
    if len(str(int)) == 3:
        string = (str(0) + str(0) + str(int))
        return (string)
    if len(str(int)) == 4:
        string = (str(0) + str(int))
        return (string)


def replace(stringOrlist, list, item):
    emptyList = []
    for i in stringOrlist:
        if i not in list:
            emptyList.append(i)
        else:
            emptyList.append(item)
    outString = "".join(emptyList)
    return outString


def remove(stringOrlist, list):
    emptyList = []
    for i in stringOrlist:
        if i not in list:
            emptyList.append(i)
        else:
            pass
    outString = "".join(emptyList)
    return outString


def remove2(stringOrlist, list):
    emptyList = []
    for i in stringOrlist:
        if i not in list:
            emptyList.append(i)
        else:
            pass
    # outString = "".join(emptyList)
    return emptyList


def removeLS(stringOrlist, list):
    emptyList = []
    for i in stringOrlist:
        if i not in list:
            emptyList.append(i)
        else:
            pass
    return emptyList


def fasta(fasta_file):
    seq = ''
    header = ''
    Dict = defaultdict(lambda: defaultdict(lambda: 'EMPTY'))
    for i in fasta_file:
        i = i.rstrip()
        if re.match(r'^>', i):
            if len(seq) > 0:
                Dict[header] = seq
                header = i[1:]
                header = header.split(" # ")[0]
                seq = ''
            else:
                header = i[1:]
                header = header.split(" # ")[0]
                seq = ''
        else:
            seq += i
    Dict[header] = seq
    return Dict


def filter(list, items):
    outLS = []
    for i in list:
        if i not in items:
            outLS.append(i)
    return outLS


def delim(line):
    ls = []
    string = ''
    for i in line:
        if i != " ":
            string += i
        else:
            ls.append(string)
            string = ''
    ls = filter(ls, [""])
    return ls


parser = argparse.ArgumentParser(
    prog="LithoGenie.py",
    formatter_class=argparse.RawDescriptionHelpFormatter,
    description=textwrap.dedent('''
    *******************************************************

    Developed by Arkadiy Garber and Gustavo Ramírez;
    University of Southern California, Earth Sciences
    Please send comments and inquiries to arkadiyg@usc.edu
    *******************************************************
    '''))

parser.add_argument('-i', type=str, help="input fasta")

parser.add_argument('-o', type=str, help="output fasta")

args = parser.parse_args()

out = open(args.o, "w")
file = open(args.i)
for i in file:
    if not re.match(r'>', i):
        out.write(i.rstrip() + "\n")
    else:
        out.write(remove(i.rstrip(), ["|", "/", " ", ",", "&", "$", "!"]) + "\n")
out.close()