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_homonymous_multi_rooted():
multi_root_words = get_dicts_from_csv_file(
'src_dict/Многокорневые слова.csv')
multi_root_names = []
for multi_root_word in multi_root_words:
for root_index_key in list(multi_root_word):
if multi_root_word[root_index_key]:
multi_root_names.append(
get_socket_word_form(multi_root_word[root_index_key]).name)
socket_group_list = list(read_src_socket_bs('src_dict/БГ 10.04.21.txt'))
homonymous_multi_rooted = []
for socket_group in socket_group_list:
for sub_group in socket_group.sub_groups:
title_word_form = sub_group.title_word_form
for word_form in sub_group.socket_word_forms:
if (not word_form.invisible and not word_form.root_index):
if word_form.name in multi_root_names:
print(word_form)
if str(word_form) == str(title_word_form):
homonymous_multi_rooted.append(str(word_form))
else:
homonymous_multi_rooted.append(' < '.join([
str(word_form),
str(title_word_form),
]))
homonymous_multi_rooted = sorted(
homonymous_multi_rooted,
key=lambda x: x.replace('*', '').strip().lower())
save_list_to_file(homonymous_multi_rooted,
'out/Слова, омонимичные многокорневым словам.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_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 find_all_multi_rooted_words_from_bs():
"""
15. Найти в док-те БС 06.04.21.txt все слова (ЗС групп и одиночки)
из док-та Многокорневые слова.xlsx
и создать список строк с такими словами - док-т Многокорневые слова БС.txt .
Учитывая п.п. 1 и 2 Правил соотношения БГ и БС,
сравнить каждую строку док-та Многокорневые слова БС.txt
с каждой ячейкой со словом в док-те Многокорневые слова.xlsx .
"""
multi_root_words = get_dicts_from_csv_file(
'out/Многокорневые слова.csv')
word_forms_bases = list(read_src_bs('src_dict/БС 06.04.21.txt'))
multi_root_bg_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]
)
multi_root_bg_forms.append(
' '.join(filter(
None,
[
socket_form.name,
socket_form.idf,
' '.join(socket_form.info),
socket_form.note.replace('* ', ''),
])))
multi_root_bs_forms = []
for group_word_form in word_forms_bases:
title_form = group_word_form.title_word_form
src_title_form = ' '.join(filter(
None,
[
title_form.name,
title_form.idf,
' '.join(title_form.info),
(title_form.note.replace('.* ', '')
if '<' not in title_form.note else None),
]))
if src_title_form in multi_root_bg_forms:
print(title_form)
multi_root_bs_forms.append(str(title_form))
multi_root_bs_forms = sorted(
multi_root_bs_forms,
key=lambda x: x.replace('*', '').lower().strip()
)
save_list_to_file(multi_root_bs_forms, 'out/Многокорневые слова БС.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 get_multirooted_homonyms():
homonyms = list(get_string_list_from_file('out/Омонимы БГ.txt'))
homonym_names = []
for homonym in homonyms:
socket_form = get_socket_word_form(homonym)
homonym_names.append(socket_form.name)
homonym_names = sorted(list(set(homonym_names)), key=lambda x: x.lower())
multirooted_homonyms = []
for name in homonym_names:
socket_forms = []
for homonym in homonyms:
socket_form = get_socket_word_form(homonym)
if socket_form.name == name:
socket_forms.append(socket_form)
for form in socket_forms:
multirooted = []
single_root = []
if form.root_index:
multirooted.append(form)
else:
single_root.append(form)
if multirooted and single_root:
for item in multirooted:
multirooted_homonyms.append(str(item))
for item in single_root:
multirooted_homonyms.append(str(item))
multirooted_homonyms = sorted(multirooted_homonyms,
key=lambda x: x.lower())
save_list_to_file(multirooted_homonyms,
'out/Омонимы - многокорневые и немногокорневые.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 find_all_multi_rooted_words_from_bs():
multi_root_words = get_dicts_from_csv_file(
'src_dict/Многокорневые слова.csv')
word_forms_bases = list(read_src_bs('src_dict/БС 03.02.21.txt'))
multi_root_bg_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]
)
multi_root_bg_forms.append(
' '.join(filter(
None,
[
socket_form.name,
socket_form.idf,
' '.join(socket_form.info),
socket_form.note.replace('* ', '')
])))
multi_root_bs_forms = []
for group_word_form in word_forms_bases:
title_form = group_word_form.title_word_form
src_title_form = ' '.join(filter(
None,
[
title_form.name,
title_form.idf,
' '.join(title_form.info),
title_form.note.replace('.* ', '')
]))
if src_title_form in multi_root_bg_forms:
print(title_form)
multi_root_bs_forms.append(str(title_form))
multi_root_bs_forms = sorted(
multi_root_bs_forms,
key=lambda x: x.replace('*', '').lower().strip()
)
save_list_to_file(multi_root_bs_forms, 'out/Многокорневые слова БС.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 compare_replays_in_groups():
homonyms_bs = get_string_list_from_file('src_dict/Омонимы БС.txt')
bs_str_forms = []
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('.*', '').strip()
]))
bs_str_forms.append(string_form)
relevant = []
not_relevant = []
with open('src_dict/Повторы в группах.txt', encoding='utf-8') as f_in:
groups = (x.strip() for x in f_in.read().split('\n\n'))
for group in groups:
for line in group.split('\n')[1:]:
if not line.startswith('!'):
word_form = get_socket_word_form(line)
line_form = ' '.join(
filter(None, [
word_form.name,
word_form.idf,
' '.join(word_form.info),
word_form.note.replace('*', '').strip(),
]))
if line_form in bs_str_forms:
relevant.append(line)
else:
not_relevant.append(line)
save_list_to_file(
sorted(relevant, key=lambda x: x.replace('*', '').strip().lower()),
'out/19.1 Совпадающие.txt')
save_list_to_file(
sorted(not_relevant, key=lambda x: x.replace('*', '').strip().lower()),
'out/19.1 Не совпадающие.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
]
not_found_in_bs = []
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)
not_found_in_bs.append(str(socket_form))
save_list_to_file(not_found_in_bs, 'out/Не найденные в БС.txt')
def parsing_replays_in_groups():
word_forms = []
with open('out/Повторы в группах.txt', encoding='utf-8') as f_in:
groups = (x.strip() for x in f_in.read().split('\n\n'))
for group in groups:
for line in group.split('\n')[1:]:
if not line.startswith('!'):
word_forms.append(get_socket_word_form(line))
clear_lines = [
' '.join(filter(None, [x.name, x.idf, ' '.join(x.info)]))
for x in word_forms
]
repeating_clear_lines = [
x for x in clear_lines if clear_lines.count(x) > 1
]
repeating_lines = []
unique_lines = []
for form in word_forms:
clear_form = ' '.join(
filter(None, [form.name, form.idf, ' '.join(form.info)]))
if clear_form in repeating_clear_lines:
repeating_lines.append(str(form))
else:
unique_lines.append(str(form))
save_list_to_file(
sorted(repeating_lines,
key=lambda x: x.replace('*', '').strip().lower()),
'out/Повторы в группах. Повторяющиеся строки.txt')
save_list_to_file(
sorted(unique_lines, key=lambda x: x.replace('*', '').strip().lower()),
'out/Повторы в группах. Уникальные строки.txt')
def check_unique_strings():
word_forms_bases = read_src_bs('src_dict/БС 20.02.21.txt')
bs_title_forms = [x.title_word_form for x in word_forms_bases]
bs_title_str_forms = [
' '.join(filter(None, [
x.name,
x.idf,
' '.join(x.info),
])) for x in bs_title_forms
]
# Повторяющиеся строки
repeating_lines = get_string_list_from_file(
'src_dict/Повторы в группах. Повторяющиеся строки.txt')
r_lines_resp = []
r_lines_not_resp = []
for line in repeating_lines:
socket_form = get_socket_word_form(line)
str_form = ' '.join(
filter(None, [
socket_form.name,
socket_form.idf,
' '.join(socket_form.info),
]))
if bs_title_str_forms.count(str_form) == 1:
r_lines_resp.append(line)
else:
r_lines_not_resp.append(line)
save_list_to_file(
r_lines_resp,
'out/Повторы в группах. Повторяющиеся строки. П.4 Правил соблюдается.txt'
)
save_list_to_file(
r_lines_not_resp,
'out/Повторы в группах. Повторяющиеся строки. П.4 Правил не соблюдается.txt'
)
# Уникальные строки
unique_lines = get_string_list_from_file(
'src_dict/Повторы в группах. Уникальные строки.txt')
u_lines_resp = []
u_lines_not_resp = []
for line in unique_lines:
socket_form = get_socket_word_form(line)
str_form = ' '.join(
filter(None, [
socket_form.name,
socket_form.idf,
' '.join(socket_form.info),
]))
if bs_title_str_forms.count(str_form) == 1:
u_lines_resp.append(line)
else:
u_lines_not_resp.append(line)
save_list_to_file(
u_lines_resp,
'out/Повторы в группах. Уникальные строки. П.4 Правил соблюдается.txt')
save_list_to_file(
u_lines_not_resp,
'out/Повторы в группах. Уникальные строки. П.4 Правил не соблюдается.txt'
)
def compare_dicts():
ordinary_words_bg_list = list(
get_string_list_from_file('out/Обычные слова БГ.txt'))
ordinary_words_bs_list = list(
get_string_list_from_file('out/Обычные слова БС.txt'))
bg_compare_forms = [
get_socket_word_form(x) for x in ordinary_words_bg_list
]
bg_compare_forms = [
' '.join(filter(None, [
x.name,
x.idf,
' '.join(x.info),
x.note[2:],
])) for x in bg_compare_forms
]
bs_compare_forms = [
get_bs_title_word_form(x) for x in ordinary_words_bs_list
]
bs_compare_forms = [
' '.join(filter(None, [
x.name,
x.idf,
' '.join(x.info),
x.note[3:],
])) for x in bs_compare_forms
]
intersection = list(set(bg_compare_forms) & set(bs_compare_forms))
matching_lines = []
bg_unique = []
bs_unique = []
for bg_string in ordinary_words_bg_list:
bg_form = get_socket_word_form(bg_string)
compare_form = ' '.join(
filter(None, [
bg_form.name,
bg_form.idf,
' '.join(bg_form.info),
bg_form.note[2:],
]))
if compare_form in intersection:
matching_lines.append(bg_string)
else:
bg_unique.append(bg_string)
for bs_string in ordinary_words_bs_list:
bs_form = get_bs_title_word_form(bs_string)
compare_form = ' '.join(
filter(None, [
bs_form.name, bs_form.idf, ' '.join(bs_form.info),
bs_form.note[3:]
]))
if compare_form not in intersection:
matching_lines.append(bs_unique)
save_list_to_file(matching_lines, 'out/Строки совпадают.txt')
save_list_to_file(bg_unique, 'out/Уникальные строки БГ.txt')
save_list_to_file(bs_unique, 'out/Уникальные строки БС.txt')
def ordinary_words_bg():
socket_group_list = list(read_src_socket_bs(
'src_dict/БГ 01.03.21.txt'))
exclusion_list = []
# Многокорневые слова
multi_root_words = get_dicts_from_csv_file(
'src_dict/Многокорневые слова.csv')
multi_root_bg_forms = []
for multi_root_word in multi_root_words:
for root_index_key in list(multi_root_word):
if multi_root_word[root_index_key]:
multi_root_bg_forms.append(multi_root_word[root_index_key])
exclusion_list += multi_root_bg_forms
# Повторы в группах
replays_in_groups = []
with open('src_dict/Повторы в группах.txt', encoding='utf-8') as f_in:
groups = (x.strip() for x in f_in.read().split('\n\n'))
for group in groups:
for line in group.split('\n')[1:]:
if not line.startswith('!'):
replays_in_groups.append(line)
exclusion_list += replays_in_groups
# Омонимы БГ
homonyms_bg = get_string_list_from_file('src_dict/Омонимы БГ.txt')
homonyms_bg_str_form = []
for homonym in homonyms_bg:
socket_form = get_socket_word_form(homonym)
string_form = ' '.join(filter(
None, [
socket_form.invisible,
socket_form.name,
socket_form.root_index,
socket_form.idf,
' '.join(socket_form.info),
socket_form.note,
socket_form.etml_note,
]
))
homonyms_bg_str_form.append(string_form)
exclusion_list += homonyms_bg_str_form
# Слова, омонимичные многокорневым
homonymous_words = get_string_list_from_file(
'src_dict/Слова, омонимичные многокорневым словам.txt')
homonymous_words_str_form = []
for word in homonymous_words:
socket_form = get_socket_word_form(word)
string_form = ' '.join(filter(
None, [
socket_form.invisible,
socket_form.name,
socket_form.root_index,
socket_form.idf,
' '.join(socket_form.info),
socket_form.note,
socket_form.etml_note,
]
))
homonymous_words_str_form.append(string_form)
exclusion_list += homonymous_words_str_form
# Обычные слова БГ
ordinary_words_bg_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:
if str(word_form) not in exclusion_list:
ordinary_words_bg_list.append(word_form)
ordinary_words_bg_list = [str(x) for x in sorted(ordinary_words_bg_list)]
save_list_to_file(ordinary_words_bg_list, 'out/Обычные слова БГ.txt')
def get_diff_lists():
ordinary_words_bs_list = get_string_list_from_file(
'out/Обычные слова БС.txt')
ordinary_words_bs_list = [
get_bs_title_word_form(x) for x in ordinary_words_bs_list
]
ordinary_words_bs_list = [
' '.join(
filter(None, [
x.name,
x.idf,
' '.join(x.info),
x.note.replace('.*', '').strip(),
])) for x in ordinary_words_bs_list
]
ordinary_words_bg_list = get_string_list_from_file(
'out/Обычные слова БГ.txt')
ordinary_words_bg_list = [
get_socket_word_form(x) for x in ordinary_words_bg_list
]
ordinary_words_bg_list = [
' '.join(filter(None, [
x.name,
x.idf,
' '.join(x.info),
x.note[2:],
])) for x in ordinary_words_bg_list
]
matching_src = list(
set(ordinary_words_bs_list)
& set(ordinary_words_bg_list))
unique_src_bs = list(
set(ordinary_words_bs_list) - set(ordinary_words_bg_list))
unique_src_bg = list(
set(ordinary_words_bg_list) - set(ordinary_words_bs_list))
matching_forms = []
unique_bs_forms = []
unique_bg_forms = []
for word in ordinary_words_bs_list:
title_form = get_bs_title_word_form(word)
str_form = ' '.join(
filter(None, [
title_form.name,
title_form.idf,
' '.join(title_form.info),
title_form.note.replace('.*', '').strip(),
]))
if str_form in matching_src:
matching_forms.append(title_form)
elif str_form in unique_src_bs:
unique_bs_forms.append(title_form)
for word in ordinary_words_bg_list:
socket_form = get_socket_word_form(word)
str_form = ' '.join(
filter(None, [
socket_form.name,
socket_form.idf,
' '.join(socket_form.info),
socket_form.note[2:],
]))
if str_form in unique_src_bg:
unique_bg_forms.append(socket_form)
save_list_to_file(matching_forms, 'out/Строки совпадают.txt')
save_list_to_file(unique_bs_forms, 'out/Уникальные строки БС.txt')
save_list_to_file(unique_bg_forms, 'out/Уникальные строки БГ.txt')
def get_homonyms_bg():
socket_group_list = list(read_src_socket_bs('src_dict/БГ 10.04.21.txt'))
socket_names = []
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 and not word_form.root_index):
socket_names.append(
word_form.name.replace('*', '').strip())
socket_names = [x for x, y in Counter(socket_names).items() if y > 1]
socket_names = sorted(list(set(socket_names)))
all_homonyms = []
for socket_group in socket_group_list:
group_names = [
x.name.replace('*', '').strip()
for x in socket_group.socket_word_forms if not x.invisible
]
for sub_group in socket_group.sub_groups:
title_word_form = sub_group.title_word_form
for word_form in sub_group.socket_word_forms:
if (not word_form.invisible and not word_form.root_index):
raw_name = word_form.name.replace('*', '').strip()
if (group_names.count(raw_name) == 1
and raw_name in socket_names):
if str(word_form) == str(title_word_form):
all_homonyms.append(str(word_form))
else:
all_homonyms.append(' < '.join([
str(word_form),
str(title_word_form),
]))
replays_homonyms = [get_socket_word_form(x).name for x in all_homonyms]
replays_homonyms = [
x for x in replays_homonyms if replays_homonyms.count(x) > 1
]
homonyms = []
homonymous_repetitions = []
for homonym in all_homonyms:
if get_socket_word_form(homonym).name in replays_homonyms:
homonyms.append(homonym)
else:
homonymous_repetitions.append(homonym)
homonyms = sorted(homonyms,
key=lambda x: x.replace('*', '').strip().lower())
homonymous_repetitions = sorted(
homonymous_repetitions,
key=lambda x: x.replace('*', '').strip().lower())
save_list_to_file(homonyms, 'out/Омонимы БГ.txt')
save_list_to_file(homonymous_repetitions,
'out/Слова, омонимичные повторам в группе.txt')
def get_homonyms_bs():
homonyms_bs = get_string_list_from_file('src_dict/Омонимы БС.txt')
replays_in_groups_spec_note = [] # (".* <")
replays_in_groups = [] # (".*")
with open('src_dict/Повторы в группах.txt', encoding='utf-8') as f_in:
groups = (x.strip() for x in f_in.read().split('\n\n'))
for group in groups:
for line in group.split('\n')[1:]:
if line.startswith('!'):
title_word_sub_group = line
title_name_sub_group = get_socket_word_form(
title_word_sub_group.replace('!', '').strip()).name
else:
word_form = get_socket_word_form(line)
replays_in_groups_spec_note.append(' '.join(
filter(None, [
word_form.name,
word_form.idf,
' '.join(word_form.info),
title_name_sub_group,
])))
replays_in_groups.append(' '.join(
filter(None, [
word_form.name,
word_form.idf,
' '.join(word_form.info),
word_form.note.replace('*', '').strip(),
])))
homonyms_spec_note_relevant = []
homonyms_spec_note_not_relevant = []
homonyms_relevant = []
homonyms_not_relevant = []
for homonym in homonyms_bs:
title_form = get_bs_title_word_form(homonym)
# имеющие специальное примечание (".* <")
if title_form.note.startswith('.* <'):
string_form = ' '.join(
filter(None, [
title_form.name, title_form.idf, ' '.join(title_form.info),
title_form.note.replace('.* <', '').strip()
]))
if string_form in replays_in_groups_spec_note:
homonyms_spec_note_relevant.append(homonym)
else:
homonyms_spec_note_not_relevant.append(homonym)
# НЕ имеющие специальное примечание (".* <")
else:
string_form = ' '.join(
filter(None, [
title_form.name, title_form.idf, ' '.join(title_form.info),
title_form.note.replace('.*', '').strip()
]))
if string_form in replays_in_groups:
homonyms_relevant.append(homonym)
else:
homonyms_not_relevant.append(homonym)
save_list_to_file(homonyms_spec_note_relevant,
'out/О-мы БС спец. прим. совпадают с Повторами.txt')
save_list_to_file(homonyms_spec_note_not_relevant,
'out/О-мы БС спец. прим. не совпадают с Повторами.txt')
save_list_to_file(homonyms_relevant,
'out/О-мы БС совпадают с Повторами.txt')
save_list_to_file(homonyms_not_relevant,
'out/О-мы БС не совпадают с Повторами.txt')
