def ordinary_words_bs():
word_forms_bases = read_src_bs('src_dict/БС 02.03.21.txt')
bs_word_forms = [str(x.title_word_form) for x in word_forms_bases]
exclusion_list = []
# Многокорневые слова БС
multi_root_bs_forms = get_string_list_from_file(
'src_dict/Многокорневые слова БС.txt')
exclusion_list += multi_root_bs_forms
# Омонимы БС
homonyms_bs = get_string_list_from_file('src_dict/Омонимы БС.txt')
exclusion_list += homonyms_bs
# Повторы ост. совпадает с БС
remaining_repetitions = get_string_list_from_file(
'src_dict/Повторы ост. совпадает с БС.txt')
remaining_repetitions = [str(get_bs_title_word_form(x))
for x in remaining_repetitions]
exclusion_list += remaining_repetitions
# Обычные слова БС
ordinary_words_bs_list = []
for bs_str_form in bs_word_forms:
if bs_str_form not in exclusion_list:
ordinary_words_bs_list.append(bs_str_form)
# print(bs_str_form)
save_list_to_file(ordinary_words_bs_list, 'out/Обычные слова БС.txt')
def fix_adjusted_participles():
socket_group_28_01 = list(get_string_list_from_file(
'src_dict/БГ 28.01.21 изм.txt', encoding='cp1251'))
socket_group_23_01 = list(get_string_list_from_file(
'src_dict/БГ 23.01.21.txt', encoding='cp1251'))
adjusted_participles_list = []
for count, socket_string in enumerate(socket_group_28_01[:]):
if socket_string.startswith('*'):
for replace_string in socket_group_23_01[:]:
if replace_string.startswith('*'):
if replace_string.split()[0].endswith(
socket_string.split()[1]
):
print(replace_string)
socket_group_28_01[count] = replace_string
adjusted_participles_list.append(replace_string)
save_list_to_file(sorted(adjusted_participles_list,
key=lambda x: x.replace('*', '').lower()),
'out/Адъектированные причастия.txt'
)
save_list_to_file(socket_group_28_01, 'out/БГ 28.01.21.txt',
encoding='cp1251')
def add_g38():
g38_list = get_string_list_from_file('src_dict/Г38. -Ь(СЯ).txt')
g38_add_list = get_string_list_from_file('src_dict/Г38 ещё ДОБАВИТЬ.txt')
out_list = list(g38_list) + list(g38_add_list)
out_list = sorted(out_list, key=lambda x: x.replace('*', '').lower())
save_list_to_file(out_list, 'out/-Ь(СЯ).txt')
def compare_homonyms_spec_note():
homonyms_bg = get_string_list_from_file('src_dict/Омонимы БГ.txt')
homonyms_bg_str_form = []
for homonyms in homonyms_bg:
socket_form = get_socket_word_form(homonyms)
spec_note = socket_form.spec_note.replace('< ', '')
spec_note_socket_form = get_socket_word_form(spec_note)
spec_note = ' '.join(
filter(None, [
spec_note_socket_form.invisible,
spec_note_socket_form.name,
spec_note_socket_form.root_index,
spec_note_socket_form.idf,
' '.join(spec_note_socket_form.info),
spec_note_socket_form.note,
]))
string_form = ' '.join(
filter(None, [
socket_form.name,
socket_form.idf,
' '.join(socket_form.info),
spec_note,
]))
homonyms_bg_str_form.append(string_form)
homonyms_spec_note = get_string_list_from_file(
'src_dict/О-мы БС спец. прим. не совпадают с Повторами.txt')
homonyms_spec_note_relevant = []
homonyms_spec_note_not_relevant = []
for homonym in homonyms_spec_note:
title_form = get_bs_title_word_form(homonym)
print(title_form.name, title_form.note)
string_form = ' '.join(
filter(None, [
title_form.name,
title_form.idf,
' '.join(title_form.info),
title_form.note.replace('.* < ', ''),
]))
if string_form in homonyms_bg_str_form:
homonyms_spec_note_relevant.append(homonym)
else:
homonyms_spec_note_not_relevant.append(homonym)
save_list_to_file(homonyms_spec_note_relevant,
'out/О-мы БС спец. прим. совпадают с О-мами БГ.txt')
save_list_to_file(homonyms_spec_note_not_relevant,
'out/О-мы БС спец. прим. не совпадают с О-мами БГ.txt')
def get_remaining_homonyms():
remaining_homonyms = list(
get_string_list_from_file(
'src_dict/О-мы БС спец. прим. не совпадают с Повторами.txt'))
remaining_homonyms += list(
get_string_list_from_file(
'src_dict/О-мы БС не совпадают с Повторами.txt'))
save_list_to_file(
sorted(remaining_homonyms,
key=lambda x: x.replace('*', '').strip().lower()),
'out/О-мы БС ост.txt')
def check_verbs():
verbs = sorted(
list(
get_string_list_from_file(
'src_dict/Г64. -АТЬ(СЯ), -ЕТЬ(СЯ) II спр. сов. в.txt')) + list(
get_string_list_from_file(
'src_dict/Г65. -ИТЬ(СЯ) II спр. сов. в.txt')))
word_forms_bases = list(read_src_bs('src_dict/БС 27.03.21.txt'))
nouns = []
g64_g65_a = []
g64_g65_b = []
for verb in verbs:
for group in word_forms_bases:
if verb == str(group.title_word_form):
print(verb)
gnb2e = None
for word_form in group.word_forms:
if word_form.idf == '.ГНБ2е':
gnb2e = word_form
break
if gnb2e:
if gnb2e.name.endswith(ENDINGS):
if gnb2e.name.endswith('ся'):
prefix = gnb2e.name[:-5]
else:
prefix = gnb2e.name[:-3]
if prefix[-1] in LETTERS:
g64_g65_b.append(verb)
else:
g64_g65_a.append(verb)
else: # окончание какое-то другое
nouns.append(verb)
else: # если словоформа .ГНБ2е отсутствует
nouns.append(verb)
break
save_list_to_file(verbs, 'out/Г64&Г65.txt')
save_list_to_file(nouns, 'out/ГНБ2е отс. или оконч. другое.txt')
save_list_to_file(g64_g65_a, 'out/Г64&Г65А.txt')
save_list_to_file(g64_g65_b, 'out/Г64&Г65Б.txt')
def get_singles_bases():
src_group_word_form_list = get_string_list_from_file(
'src_dict/Добавить одиночки в БС.txt')
for src_title_word_form in src_group_word_form_list:
title_word_form = TitleWordForm(src_title_word_form, '', [], '')
group_word_form = GroupWordForm(title_word_form, [])
yield group_word_form
def add_groups_to_bs():
"""
2 (продолжение).
Соблюдая алфавитный порядок ЗС в док-те БС 15.01.21.txt,
добавить в док-т БС 15.01.21.txt
одиночки из док-та Добавить одиночки в БС 2.txt .
4. Соблюдая алфавитный порядок ЗС в БС, добавить в БС группы
из док-тов Добавить группы в БС. Сущ-ные изм.txt
и Добавить группы в БС. Сущ-ные 2.txt .
"""
word_forms_bases = list(read_src_bs('src_dict/БС 15.01.21.txt'))
loners = get_string_list_from_file(
'src_dict/Добавить одиночки в БС 2.txt')
loners_list = []
for loner in loners:
title_word_form = TitleWordForm(loner, '', [], '')
group_word_form = GroupWordForm(title_word_form, [])
loners_list.append(group_word_form)
modified_nouns = list(read_src_bs(
'src_dict/Добавить группы в БС. Сущ-ные изм.txt'))
nouns_2 = list(read_src_bs('src_dict/Добавить группы в БС. Сущ-ные 2.txt',
encoding='utf-8'))
word_forms_bases += loners_list
word_forms_bases += modified_nouns
word_forms_bases += nouns_2
save_bs_dicts_to_txt(sorted(word_forms_bases), 'out/БС 15.01.21.txt')
def get_not_included_in_the_lists():
word_forms_bases = read_src_bs('src_dict/БС 20.03.21.txt')
file_stems = {
x.stem: list(get_string_list_from_file(f'{x}'))
for x in Path('src_dict/lst').glob('*')
}
for group in word_forms_bases:
title_form = group.title_word_form
info_list = title_form.info
if info_list:
for idf in info_list:
if idf in IDFS:
out_stem = ', '.join(IDFS[idf])
flag = True
added_title_form = []
for f_stem in IDFS[idf]:
if str(title_form) in file_stems[f_stem]:
flag = False
if (
flag
and str(title_form) not in added_title_form
):
print(title_form)
add_string_to_file(str(title_form),
f'out/lst/{out_stem} ещё.txt')
added_title_form.append(str(title_form))
def remove_from_bg():
"""
9. Для всех слов из док-та "Удалить из БГ.txt" сделать следующее:
9.1. найти такое слово в док-те "БГ 27.01.21.txt" и,
9.2.1. если оно является ЗС ПОДгруппы - вставить его
в отдельно созданный док-т "ЗС подгруппы.txt"
9.2.2. если оно НЕ является ЗС ПОДгруппы - удалить его
из док-та "БГ 27.01.21.txt"
"""
remove_bg_list = get_string_list_from_file('src_dict/Удалить из БГ.txt')
socket_group_word_form_list = list(
read_src_socket_bs('src_dict/БГ 27.01.21.txt'))
title_form_list = []
deleted_list = []
for remove_bg in sorted(remove_bg_list):
for group in socket_group_word_form_list:
for sub_group in group.sub_groups:
title_word_form = sub_group.title_word_form
for word_form in sub_group.socket_word_forms[:]:
if remove_bg == word_form.name:
print(word_form)
if remove_bg == title_word_form.name:
title_form_list.append(str(word_form))
else:
deleted_list.append(str(word_form))
sub_group.socket_word_forms.remove(word_form)
save_list_to_file(sorted(title_form_list, key=str.lower),
'out/ЗС подгруппы.txt')
save_list_to_file(sorted(deleted_list, key=str.lower),
'out/удалённые из БГ.txt')
save_socket_bs_dicts_to_txt(socket_group_word_form_list,
'out/БГ 28.01.21.txt')
def find_extra_lines(in_file, in_dir):
files_path = [x for x in Path(in_dir).glob('*')]
in_dir_lines = [x for x in get_file_lines(files_path)]
in_lines = list(get_string_list_from_file(in_file))
extra_lines = [x for x in in_dir_lines if x not in in_lines]
if extra_lines:
save_list_to_file(extra_lines, f'out/Лишние {Path(in_file).stem}.txt')
def get_capital_letter_bs():
capital_letter_bs = list(
get_string_list_from_file('out/Большая буква. БС.txt'))
word_forms_bases = read_src_bs('src_dict/БС 13.03.21.txt')
title_forms = [str(x.title_word_form) for x in word_forms_bases]
capital_letter_bs_homonyms = []
for capital_word in capital_letter_bs:
capital_word_name = get_bs_title_word_form(capital_word).name
title_form_list = []
for title_form in title_forms:
form_name = get_bs_title_word_form(title_form).name.replace(
'*', '')
if form_name == capital_word_name.lower():
print(title_form)
title_form_list.append(title_form)
if title_form_list:
capital_letter_bs_homonyms.append(capital_word)
capital_letter_bs_homonyms += title_form_list
capital_letter_bs_homonyms.append('')
save_list_to_file(capital_letter_bs_homonyms[:-1],
'out/Большая буква. БС. Омонимы.txt')
def get_capital_letter_bg():
capital_letter_bg = list(
get_string_list_from_file('out/Большая буква. БГ.txt'))
socket_group_list = list(read_src_socket_bs('src_dict/БГ 13.03.21.txt'))
capital_letter_bg_homonyms = []
for capital_word in capital_letter_bg:
capital_word_name = get_socket_word_form(capital_word).name
word_form_list = []
for socket_group in socket_group_list:
for sub_group in socket_group.sub_groups:
for word_form in sub_group.socket_word_forms:
if not word_form.invisible:
form_name = word_form.name.replace('*', '')
if form_name == capital_word_name.lower():
print(word_form)
word_form_list.append(str(word_form))
if word_form_list:
capital_letter_bg_homonyms.append(capital_word)
capital_letter_bg_homonyms += word_form_list
capital_letter_bg_homonyms.append('')
save_list_to_file(capital_letter_bg_homonyms[:-1],
'out/Большая буква. БГ. Омонимы.txt')
def get_two_in_one():
remaining_repetitions = get_string_list_from_file('src_dict/Повторы ост.txt')
word_forms_bases = read_src_bs('src_dict/БС 27.02.21.txt')
bs_word_forms = [x.title_word_form for x in word_forms_bases]
bs_word_names = [
' '.join(filter(None, [
x.name,
x.idf,
' '.join(x.info),
x.note
]))
for x in bs_word_forms
]
relevant = []
not_relevant = []
for repeat in remaining_repetitions:
if repeat in bs_word_names:
relevant.append(repeat)
else:
not_relevant.append(repeat)
save_list_to_file(relevant, 'out/Повторы ост. совпадает с БС.txt')
save_list_to_file(not_relevant, 'out/Повторы ост. не совпадает с БС.txt')
def get_bg_abbreviation_homonyms():
abbreviation_bg = get_string_list_from_file('out/Аббревиатура. БГ.txt')
abbreviation_bg = sorted(list(set(abbreviation_bg)))
socket_group_list = list(read_src_socket_bs('src_dict/БГ 13.03.21.txt'))
bg_abbreviation_homonyms = []
for abbreviation in abbreviation_bg:
abbreviation_name = get_socket_word_form(abbreviation).name
word_form_list = []
for socket_group in socket_group_list:
for sub_group in socket_group.sub_groups:
for word_form in sub_group.socket_word_forms:
if not word_form.invisible:
form_name = word_form.name.replace('*', '')
if form_name == abbreviation_name.lower():
print(form_name)
word_form_list.append(str(word_form))
if word_form_list:
bg_abbreviation_homonyms.append(abbreviation)
bg_abbreviation_homonyms += word_form_list
bg_abbreviation_homonyms.append('')
save_list_to_file(bg_abbreviation_homonyms[:-1],
'out/Аббревиатура. БГ. Омонимы.txt')
def get_bs_abbreviation_homonyms():
abbreviation_bs = get_string_list_from_file('out/Аббревиатура. БС.txt')
word_forms_bases = read_src_bs('src_dict/БС 13.03.21.txt')
title_forms = [str(x.title_word_form) for x in word_forms_bases]
bs_abbreviation_homonyms = []
for abbreviation in abbreviation_bs:
abbreviation_name = get_bs_title_word_form(abbreviation).name
title_form_list = []
for title_form in title_forms:
form_name = get_bs_title_word_form(title_form).name.replace(
'*', '')
if form_name == abbreviation_name.lower():
print(title_form)
title_form_list.append(title_form)
if title_form_list:
bs_abbreviation_homonyms.append(abbreviation)
bs_abbreviation_homonyms += title_form_list
bs_abbreviation_homonyms.append('')
save_list_to_file(bs_abbreviation_homonyms[:-1],
'out/Аббревиатура. БС. Омонимы.txt')
def change_bs_abbreviation():
abbreviation_bs = list(
get_string_list_from_file('src_dict/Аббревиатура. БС.txt'))
capital_letter_bs = list(
get_string_list_from_file('src_dict/Большая буква. БС.txt'))
word_forms_bases = list(read_src_bs('src_dict/БС 15.03.21.txt'))
for group in word_forms_bases:
title_form = group.title_word_form
if (str(title_form) in abbreviation_bs
or str(title_form) in capital_letter_bs):
title_form.name = title_form.name.lower()
for word_form in group.word_forms:
word_form.name = word_form.name.lower()
save_bs_dicts_to_txt(sorted(word_forms_bases), 'out/БС 16.03.21.txt')
def change_bg_abbreviation():
abbreviation_bg = sorted(
list(set(get_string_list_from_file('src_dict/Аббревиатура. БГ.txt'))))
capital_letter_bg = sorted(
list(set(get_string_list_from_file('src_dict/Большая буква. БГ.txt'))))
socket_group_list = list(read_src_socket_bs('src_dict/БГ 15.03.21.txt'))
for socket_group in socket_group_list:
for sub_group in socket_group.sub_groups:
for word_form in sub_group.socket_word_forms:
if not word_form.invisible:
if (str(word_form) in abbreviation_bg
or str(word_form) in capital_letter_bg):
word_form.name = word_form.name.lower()
save_socket_bs_dicts_to_txt(socket_group_list, 'out/БГ 16.03.21.txt')
def compare_homonyms():
homonyms_bg = get_string_list_from_file(
'src_dict/Омонимы БГ без этим. примечаний.txt')
homonyms_bg_str_form = []
for homonyms in homonyms_bg:
socket_form = get_socket_word_form(homonyms)
string_form = ' '.join(filter(
None, [
socket_form.name,
socket_form.idf,
' '.join(socket_form.info),
socket_form.note
]
))
homonyms_bg_str_form.append(string_form)
homonyms_bs = get_string_list_from_file(
'src_dict/О-мы БС не совпадают с Повторами.txt')
homonyms_bs_relevant = []
homonyms_bs_not_relevant = []
for homonym in homonyms_bs:
title_form = get_bs_title_word_form(homonym)
string_form = ' '.join(filter(
None,
[
title_form.name,
title_form.idf,
' '.join(title_form.info),
title_form.note.replace('.* ', '* '),
]
))
if string_form in homonyms_bg_str_form:
homonyms_bs_relevant.append(homonym)
else:
homonyms_bs_not_relevant.append(homonym)
save_list_to_file(homonyms_bs_relevant,
'out/О-мы БС совпадают с О-мами БГ.txt')
save_list_to_file(homonyms_bs_not_relevant,
'out/О-мы БС не совпадают с О-мами БГ.txt')
def change_case():
for file_path in Path('src_dict/lst').glob('*'):
file_stem = file_path.stem
lower_words = []
words = get_string_list_from_file(file_path, encoding='cp1251')
for word in words:
if word:
lower_words.append(word.lower())
out_path = f'out/lst/{file_stem}.txt'
save_list_to_file(lower_words, out_path, encoding='cp1251')
def remove_strings():
relevant_repetitions = get_string_list_from_file(
'src_dict/Повторы ост. совпадает с БС.txt')
multi_root_bs = list(get_string_list_from_file(
'src_dict/Многокорневые слова БС.txt'))
multi_root_bs = [get_bs_title_word_form(x) for x in multi_root_bs]
multi_root_bs = [
' '.join(filter(None, [
x.name,
x.idf,
' '.join(x.info),
x.note,
]))
for x in multi_root_bs
]
save_list_to_file(sorted(list(set(
relevant_repetitions) - set(multi_root_bs))),
'out/Повторы ост. совпадает с БС.txt')
def check_presence():
homonyms = [get_bs_title_word_form(x).name
for x in get_string_list_from_file('src_dict/Омонимы БС.txt')]
word_forms_bases = list(read_src_bs('src_dict/БС 16.03.21 изм.txt'))
bs_names = [
x.title_word_form.name.replace('*', '').strip()
for x in word_forms_bases
]
for file_path in Path('out/lst').glob('*'):
file_stem = file_path.stem
presence = [] # 28а. Если слово имеется в док-те Омонимы БС.txt
nouns = [] # 29а. если слово находится
absent = [] # 29б. если слово НЕ находится
words = get_string_list_from_file(file_path, encoding='cp1251')
for word in words:
print(word)
if word in homonyms:
presence.append(word)
else:
if word in bs_names:
for group in word_forms_bases:
if word == group.title_word_form.name:
print(group.title_word_form)
nouns.append(str(group.title_word_form))
else:
absent.append(word)
if presence:
save_list_to_file(
sorted(presence), f'out/homonyms/{file_stem} омонимы.txt')
if nouns:
save_list_to_file(sorted(nouns), f'out/C/С{file_stem}.txt')
if absent:
save_list_to_file(
sorted(absent), f'out/absent/{file_stem} отсутствует.txt')
def get_remaining_repetitions():
homonyms = []
for line in get_string_list_from_file(
'src_dict/О-мы БС спец. прим. совпадают с Повторами.txt'):
bs_form = get_bs_title_word_form(line)
homonyms.append(' '.join(filter(None, [
bs_form.name,
bs_form.idf,
' '.join(bs_form.info),
])))
for line in get_string_list_from_file(
'src_dict/О-мы БС совпадают с Повторами.txt'):
bs_form = get_bs_title_word_form(line)
homonyms.append(' '.join(filter(None, [
bs_form.name,
bs_form.idf,
' '.join(bs_form.info),
bs_form.note.replace('.*', '').strip()
])))
remaining_repetitions = []
replays_in_groups = get_string_list_from_file(
'out/Повторы в группах (без повторов).txt')
replays_in_groups = [
' '.join(filter(None, [
get_socket_word_form(x).name,
get_socket_word_form(x).idf,
' '.join(get_socket_word_form(x).info),
get_socket_word_form(x).note.replace('*', '').strip(),
]))
for x in replays_in_groups
]
for replay in replays_in_groups:
if replay not in homonyms:
remaining_repetitions.append(replay)
save_list_to_file(remaining_repetitions, 'out/Повторы ост.txt')
def check_g58():
endings = ('греть', 'мять', 'оть', 'ыть', 'пеленать')
g58_list = get_string_list_from_file('src_dict/Г58 ещё.txt')
word_forms = [get_bs_title_word_form(x) for x in g58_list]
out_list = []
for word_form in word_forms[:]:
if not word_form.name.endswith(endings):
print(word_form)
out_list.append(str(word_form))
save_list_to_file(sorted(out_list), 'out/Г58 ещё изм.txt')
def get_not_included_in_the_lists():
word_forms_bases = read_src_bs('src_dict/БС 24.03.21.txt')
short_form = list(get_string_list_from_file(
'src_dict/П12. ЕСТЬ краткая форма.txt'))
comparative = list(get_string_list_from_file(
'src_dict/П22. ЕСТЬ сравнительная степень.txt'))
superlative_degree = list(get_string_list_from_file(
'src_dict/П27. ЕСТЬ превосходная степень.txt'))
for group in word_forms_bases:
title_form = group.title_word_form
info_list = title_form.info
if info_list and title_form.idf.startswith('.П'):
flag_p12 = False
flag_p22 = False
flag_p27 = False
for info_id in info_list:
if info_id.startswith('К'):
flag_p12 = True
elif info_id.startswith('С'):
flag_p22 = True
elif info_id.startswith('П'):
flag_p27 = True
if flag_p12 and str(title_form) not in short_form:
print(title_form)
add_string_to_file(str(title_form), f'out/П12 ЕЩЁ.txt')
if flag_p22 and str(title_form) not in comparative:
print(title_form)
add_string_to_file(str(title_form), f'out/П22 ЕЩЁ.txt')
if flag_p27 and str(title_form) not in superlative_degree:
print(title_form)
add_string_to_file(str(title_form), f'out/П27 ЕЩЁ.txt')
def check_socket_bs():
multi_root_words = get_dicts_from_csv_file('out/Многокорневые слова.csv')
multi_root_bs_forms = get_string_list_from_file(
'out/Многокорневые слова БС.txt')
multi_root_bs_forms = [
get_bs_title_word_form(x).name for x in multi_root_bs_forms
]
for multi_root_word in multi_root_words:
for root_index_key in list(multi_root_word)[1:]:
if multi_root_word[root_index_key]:
socket_form = get_socket_word_form(
multi_root_word[root_index_key])
if socket_form.name not in multi_root_bs_forms:
print(socket_form)
def check_g21():
endings = ('верещать', 'верещаться', 'дышать', 'дышаться', 'кишеть',
'кишеться', 'пищать', 'пищаться', 'слышать', 'слышаться',
'трещать', 'трещаться', 'ршать', 'ршаться', 'жить', 'житься',
'чить', 'читься', 'шить', 'шиться', 'щить', 'щиться')
g21_list = get_string_list_from_file('src_dict/Г21 ещё.txt')
word_forms = [get_bs_title_word_form(x) for x in g21_list]
out_list = []
for word_form in word_forms[:]:
if not word_form.name.endswith(endings):
print(word_form)
out_list.append(str(word_form))
save_list_to_file(sorted(out_list), 'out/Г21 ещё изм.txt')
def check_g6():
endings = ('нуть', 'нуться', 'зиждить', 'зиждиться', 'врать', 'враться',
'жрать', 'жраться', 'рвать', 'рваться', 'реветь', 'реветься',
'ржать', 'ржаться', 'сосать', 'сосаться', 'срать', 'сраться',
'стонать', 'стонаться', 'ткать', 'ткаться', 'шибить',
'шибиться')
g6_list = get_string_list_from_file('src_dict/Г6 ещё.txt')
word_forms = [get_bs_title_word_form(x) for x in g6_list]
out_list = []
for word_form in word_forms[:]:
if not word_form.name.endswith(endings):
print(word_form)
out_list.append(str(word_form))
save_list_to_file(sorted(out_list), 'out/Г6 ещё изм.txt')
def check_g15():
endings = ('бормотать', 'бормотаться', 'лепетать', 'лепетаться', 'плакать',
'плакаться', 'прятать', 'прятаться', 'скакать', 'скакаться',
'топтать', 'топтаться', 'шептать', 'шептаться', 'щебетать',
'щебетаться', 'готать', 'готаться', 'котать', 'котаться',
'потать', 'потаться', 'хотать', 'хотаться', 'хтать', 'хтаться')
g15_list = get_string_list_from_file('src_dict/Г15 ещё.txt')
word_forms = [get_bs_title_word_form(x) for x in g15_list]
out_list = []
for word_form in word_forms[:]:
if not word_form.name.endswith(endings):
print(word_form)
out_list.append(str(word_form))
save_list_to_file(sorted(out_list), 'out/Г15 ещё изм.txt')
def get_not_included_in_the_lists():
word_forms_bases = read_src_bs('src_dict/БС 24.03.21.txt')
file_stems = {
x.stem: list(get_string_list_from_file(f'{x}'))
for x in Path('src_dict/lst').glob('*')
}
for group in word_forms_bases:
title_form = group.title_word_form
info_list = title_form.info
if info_list:
for idf in info_list:
if idf in IDFS:
out_stem = IDFS[idf]
if str(title_form) not in file_stems[out_stem]:
print(title_form)
add_string_to_file(str(title_form),
f'out/lst/{out_stem} ещё.txt')
