text_cleanup.rb

ALNUM       = /[a-z0-9]/i
PUNCT       = /[^a-z0-9\s]/i
REPEAT      = /(.)\1{2,}/
UPPER       = /[A-Z]/
LOWER       = /[a-z]/
ACRONYM     = /^[A-Z]+('?s|[.,])?$/
ALL_ALPHA   = /^[a-z]+$/i
CONSONANT   = /[bcdfghjklmnpqrstvwxz]/i
VOWEL       = /[aeiouy]/i
CONSONANT_5 = /[bcdfghjklmnpqrstvwxz]{5}/i
VOWEL_4     = /[aeiouy]{4}/i

# More than 20 bytes in length.
w.length > 20

# More punctuation than alpha numerics.
w.length > 2 && (w.scan(ALNUM).length < w.scan(PUNCT).length)

# Ignoring the first and last characters in the string, if there are three or
# more different punctuation characters in the string.
w[1...-1].scan(PUNCT).uniq.length >= 3

# If there are three or more identical characters in a row in the string.
w =~ REPEAT

# Number of uppercase letters greater than lowercase letters, but the word is
# not all uppercase + punctuation.
upper = w.scan(UPPER).length
lower = w.scan(LOWER).length
upper > lower && (w !~ ACRONYM)

# All characters are alphabetic and there are 8 times more vowels than
# consonants, or 8 times more consonants than vowels.
valid       = w.length > 2 && (w =~ ALL_ALPHA) && (w !~ ACRONYM)
vowels      = w.scan(VOWEL).length
consonants  = w.scan(CONSONANT).length
valid && (vowels > consonants * 8 || consonants > vowels * 8)

# Four or more consecutive vowels, or five or more consecutive consonants.
(w =~ VOWEL_4) || (w =~ CONSONANT_5)