max_file_utils

from collections import defaultdict
from operator import itemgetter
from itertools import groupby
from collections import deque
from ast import literal_eval
import os

class my_file_utils:

    def __init__(self, file_a=None, file_b=None):
        ''' create an instance of my_file_utils, with or without pre-set files '''
        self.f1 = file_a
        self.f2 = file_b

    def set_file_a(self, file_a):
        ''' set file_a '''
        self.f1 = file_a

    def set_file_b(self, file_b):
        ''' set file_b '''
        self.f2 = file_b

    @property
    def files_set(self):
        ''' checks if file_a and file_b are set '''
        return (self.f1 and self.f2)

    def load(self, file_in=None, file_out=None):
        '''
        Reads file_in (file_a)
        Parses lines.
        Writes to file_out (file_b)
        '''
        if not file_in and self.f1:
            file_in = self.f1
        elif not file_in and not self.f1:
            raise ValueError('no input file specified, and none pre-set')
        if not file_out and self.f2:
            file_out = self.f2
        elif not file_out and not self.f2:
            raise ValueError('no output file specified, and none pre-set')

        with open(file_in) as fin, open(fileOut, 'w') as fout:
            for line in fin:
                rows = line.split()
                frame, rect = row[2], row[3:7]
                fout.write('{{{}:{}}}\n'.format(frame, rect))

    def compare(self, output_file='my_file_compare_results.txt', first_file=None, second_file=None):
        '''
        Reads two files and compares them
        Keeps all lines in first_file not in second_file
        Does something to them ?
        If no output specified, it is created in CWD with the name:
            my_file_compare_results.txt
        '''
        if not first_file and self.f1:
            first_file = self.f1
        elif not first_file and not self.f1:
            raise ValueError('no first_file specified, and none pre-set')
        if not second_file and self.f2:
            second_file = self.f2
        elif not second_file and not self.f2:
            raise ValueError('no second_file specified, and none pre-set')

        diffs = defaultdict(list)
        with open(first_file) as f1, open(second_file) as f2:
            lines_1 = [l.strip() for l in f1]
            lines_2 = [l.strip() for l in f2]
            diff_lines = [l for l in lines_1 if l not in lines_2]

        for line in diff_ines:
            d = literal_eval(line)
            for k, v in d.items():
                for i in range(0, len(d[k]), 2):
                    diffs[d[k][i]].append(k)

        with open(output_file, 'w') as fout:
            for k, v in diffs.items():
                for _, g in groupby(enumerate(sorted(v)), lambda (i, x): i - x):
                    group = map(itemgetter(1), g)
                    fout.write('{0} {1} {2}\n'.format(k, group[0], group[-1]))

    def final(self, file_in=None, dir_out=None):
        '''
        Reads from file_in (file_a)
        Does something ?
        Writes to file_out (file_b)
        '''
        if not file_in and self.f1:
            file_in = self.f1
        elif not file_in and not self.f1:
            raise ValueError('no input file specified, and none pre-set')
        if not dir_out:
            dir_out = os.getcwd()
        else:
            raise ValueError('no output dir specified')

        with open(file_in) as fin:
            lines = (line.split() for line in fin)
            for k, g in groupby(lines, itemgetter(0)):
                fst = next(g)
                lst = next(iter(deque(g, 1)), fst)

                with open(dir_out + '/final_{}.txt'.format(k), 'w') as fout:
                    fout.write('{} {}'.format(fst[1], lst[2]))