wordfreq.sh

#!/usr/bin/env bash

# List the most frequently used words in a text.

[ $# -ge 1 ] && [ -f "$1" ] && input="$1" || input="-"

# shellcheck disable=SC2002
cat "$input" |
  tr -cs '[:alpha:]' '\n' |     # Split words and drop non-alphabetic characters.
  tr '[:upper:]' '[:lower:]' |  # Put it all to lowercase.
  sed '/../!d' |                # Remove lines with less than two chars.
  sort | uniq -c | sort -k1nr | # Deduplicate and sort by number of occurrences.
  awk '$1 > 1'                  # Keep words with more than one occurrence.