split text into sentences

# from nltk import tokenize
import ast
import json
import os
import pyperclip
from binaryornot.check import is_binary


def read_txt_file_basic(file_loc):
    check_file_type = is_binary(file_loc)
    if not check_file_type:
        file_list = []
        try:
            fh = open(file_loc, 'r', encoding='utf-8')
            lines = fh.readlines()
            for line in range(len(lines)):
                file_list.append(lines[line].strip())
            return file_list
        except IOError as e:
            print("unable to read file ({})".format(e))


script_name = os.path.splitext(os.path.basename(__file__))[0]
config_read = read_txt_file_basic(os.getcwd() + os.sep + script_name + '_config.txt')

abbreviations_string = str(config_read[0].split('=', 1)[1].strip()).replace("'", '"')
terminators_string = str(config_read[1].split('=', 1)[1].strip())
wrappers_string = str(config_read[2].split('=', 1)[1].strip())

abbreviations_input = json.loads('{' + abbreviations_string + '}')
abbreviations_low = dict((str(j).lower(), str(k).lower()) for i, (j, k) in enumerate(abbreviations_input.items()))
abbreviations_cap = dict((str(j).capitalize(), str(k).capitalize()) for i, (j, k) in enumerate(abbreviations_input.items()))
abbreviations_up = dict((str(j).upper(), str(k).upper()) for i, (j, k) in enumerate(abbreviations_input.items()))
abbreviations = {**abbreviations_low, **abbreviations_cap, **abbreviations_up}

terminators = ast.literal_eval('[' + terminators_string + ']')
wrappers = ast.literal_eval('[' + wrappers_string + ']')


def find_sentences(paragraph):
    end = True
    sentences = []
    while end > -1:
        end = find_sentence_end(paragraph)
        if end > -1:
            sentences.append(paragraph[end:].strip())
            paragraph = paragraph[:end]
    sentences.append(paragraph)
    sentences.reverse()
    return sentences


def find_sentence_end(paragraph):
    [possible_endings, contraction_locations] = [[], []]
    contractions = abbreviations.keys()
    sentence_terminators = terminators + [terminator + wrapper for wrapper in wrappers for terminator in terminators]
    for sentence_terminator in sentence_terminators:
        t_indices = list(find_all(paragraph, sentence_terminator))
        possible_endings.extend(([] if not len(t_indices) else [[i, len(sentence_terminator)] for i in t_indices]))
    for contraction in contractions:
        c_indices = list(find_all(paragraph, contraction))
        contraction_locations.extend(([] if not len(c_indices) else [i + len(contraction) for i in c_indices]))
    possible_endings = [pe for pe in possible_endings if pe[0] + pe[1] not in contraction_locations]
    if len(paragraph) in [pe[0] + pe[1] for pe in possible_endings]:
        max_end_start = max([pe[0] for pe in possible_endings])
        possible_endings = [pe for pe in possible_endings if pe[0] != max_end_start]
    possible_endings = [pe[0] + pe[1] for pe in possible_endings if
                        sum(pe) > len(paragraph) or (sum(pe) < len(paragraph) and paragraph[sum(pe)] == ' ')]
    end = (-1 if not len(possible_endings) else max(possible_endings))
    return end


def find_all(a_str, sub):
    start = 0
    while True:
        start = a_str.find(sub, start)
        if start == -1:
            return
        yield start
        start += len(sub)


if __name__ == '__main__':
    tmp_sentences = find_sentences(pyperclip.paste())
    result = ''
    for sentence in tmp_sentences:
        result += sentence + '\r\n'
    pyperclip.copy(result)
    # too big compile solution
    # result = ''
    # clipboard = pyperclip.paste()
    # tmp_sentences = tokenize.sent_tokenize(clipboard)
    # for sentence in tmp_sentences:
    #     result += sentence + '\r\n'
    # pyperclip.copy(result)


# sentences_config.txt file structure (create in same folder as compiled file without # of course):
# abbreviations  = 'dr.': 'doctor', 'mr.': 'mister', 'bro.': 'brother', 'bro': 'brother', 'mrs.': 'mistress', 'ms.': 'miss', 'jr.': 'junior', 'sr.': 'senior', 'i.e.': 'for example', 'e.g.': 'for example', 'vs.': 'versus'
# terminators = '.', '!', '?'
# wrappers = '"', "'", ')', ']', '}'