Last active
May 16, 2025 12:41
-
-
Save devig/1fb23e57f69fa91480d0843b770f30c3 to your computer and use it in GitHub Desktop.
Фильтрация фраз по списку минус-слов
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import re | |
import sys | |
from pathlib import Path | |
def load_words(words_file): | |
words_set = set() | |
with open(words_file, encoding='utf-8') as f: | |
for line in f: | |
word = line.strip() | |
# Удаляем начальные -, ", ! | |
word = re.sub(r'^[-"!]+', '', word) | |
if word: | |
words_set.add(word.lower()) | |
return words_set | |
def tokenize(text): | |
# Разделение по символам-разделителям | |
return re.split(r'[@#\-,\";\s]+', text) | |
def process_phrases(words_lowercase_set, phrases_file): | |
original_name = Path(phrases_file).name | |
dirty_file = f'dirty_{original_name}' | |
clean_file = f'clean_{original_name}' | |
dirty_count = 0 | |
clean_count = 0 | |
matched_words = set() | |
with open(phrases_file, encoding='utf-8') as pf, \ | |
open(dirty_file, 'w', encoding='utf-8') as df, \ | |
open(clean_file, 'w', encoding='utf-8') as cf: | |
for line in pf: | |
line_stripped = line.strip() | |
tokens = tokenize(line_stripped) | |
tokens_lower = [t.lower() for t in tokens if t] | |
# Ищем пересечение | |
matched = set(tokens_lower) & words_lowercase_set | |
if matched: | |
matched_words.update(matched) | |
df.write(line) | |
dirty_count += 1 | |
else: | |
cf.write(line) | |
clean_count += 1 | |
# Вывод отчета | |
print(f"\n🧼 Найденные слова: {', '.join(sorted(matched_words)) or '—'}") | |
print(f"📝 Строк записано в dirty файл: {dirty_count}") | |
print(f"✅ Строк записано в clean файл: {clean_count}") | |
print(f"\nРезультат сохранён в {dirty_file} и {clean_file}") | |
if __name__ == '__main__': | |
if len(sys.argv) != 3: | |
print('Использование: python filter.py слова.txt фразы.txt') | |
sys.exit(1) | |
words_file = sys.argv[1] | |
phrases_file = sys.argv[2] | |
words = load_words(words_file) | |
process_phrases(words, phrases_file) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
python3 filter.py minus-kondei.txt kondei.txt
python filter.py minus-kondei.txt kondei.txt