ada/CourseWork_IRFM
1
0
Fork 0
mirror of https://github.com/ada-dmitry/CourseWork_IRFM.git synced 2026-09-24 01:10:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove outdated documentation and improve comments in main and crawler modules

Browse Source
This commit is contained in:
Dmitry
2026-04-29 23:23:09 +03:00
parent 045fc41660
commit bf13d4d478
7 changed files with 2 additions and 625 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main.py
+1 -1
View File
@@ -22,7 +22,7 @@ def main():
subject_index = build_subject_index(original_text, top_n=100) # Строим предметный указатель
(output_dir / "uk_rf_original.txt").write_text(original_text, encoding="utf-8") # Вывод исходного текста в файл
(output_dir / "uk_rf_prepared.txt").write_text(prepared_text, encoding="utf-8") # Вывод токенизированного и обработанного текста в файл
(output_dir / "uk_rf_prepared.txt").write_text(prepared_text, encoding="utf-8") # Вывод обработанного текста в файл
write_subject_index_csv(subject_index, output_dir / "uk_rf_subject_index.csv") # Вывод предметного указателя в csv
write_subject_index_json(subject_index, output_dir / "uk_rf_subject_index.json") # Предметные указатель в json