A simple Ruby script to parse text from the Quran into text without diacritics

parse-ayat.rb

#!/usr/bin/env ruby

# 1. Copy the raw text from https://www.corequran.com/
# 2. Run "ruby parse.rb"
# 3. Paste the copied text
# 4. Press "Ctrl + D" to see the output

def parse(str)
  str
    .split("\n")
    .map { |aya| remove_verse_number(aya) }
    .map { |aya| remove_diacritics(aya) }
end

def remove_verse_number(str)
  str.gsub(/﴿.*?﴾/, '').strip
end

def remove_diacritics(str)
  diacritics = 'ِ', 'ُ', 'ٓ', 'ٰ', 'ْ', 'ٌ', 'ٍ', 'ً', 'ّ', 'َ', ' ۛ', ' ۖ', ' ۗ'
  str.gsub Regexp.union(diacritics), ''
end

puts parse(STDIN.read)