Word statistics for text file

stat.sh

#!/bin/bash
# 1. clear file from junk
# 2. split by wordd
# 3. lower case
# 4. sort for uniq
# 5. uniq withcount
# 6. sort by count

cat textfile.txt \
| sed -E 's#([^А-Яа-я ])|\s+# #g' \
| sed 's# #\n#g' \
| awk '{print tolower($0)}' \
| sort \
| uniq -c \
| sort -k1 -n -r