Module: Gem::Text
Overview
A collection of text-wrangling methods
Instance Method Summary
-
#clean_text(text)
Remove any non-printable characters and make the text suitable for printing.
-
#format_text(text, wrap, indent = 0)
Wraps
text
towrap
characters and optionally indents byindent
characters. -
#levenshtein_distance(str1, str2)
This code is based directly on the
Text
gem implementation Returns a value representing the “cost” of transforming str1 into str2. - #truncate_text(text, description, max_length = 100_000)
Instance Method Details
#clean_text(text)
Remove any non-printable characters and make the text suitable for printing.
# File 'lib/rubygems/text.rb', line 12
def clean_text(text) text.gsub(/[\000-\b\v-\f\016-\037\177]/, ".".freeze) end
#format_text(text, wrap, indent = 0)
Wraps text
to wrap
characters and optionally indents by indent
characters
# File 'lib/rubygems/text.rb', line 26
def format_text(text, wrap, indent=0) result = [] work = clean_text(text) while work.length > wrap do if work =~ /^(.{0,#{wrap}})[ \n]/ then result << $1.rstrip work.slice!(0, $&.length) else result << work.slice!(0, wrap) end end result << work if work.length.nonzero? result.join("\n").gsub(/^/, " " * indent) end
#levenshtein_distance(str1, str2)
This code is based directly on the Text
gem implementation Returns a value representing the “cost” of transforming str1 into str2
# File 'lib/rubygems/text.rb', line 55
def levenshtein_distance str1, str2 s = str1 t = str2 n = s.length m = t.length return m if (0 == n) return n if (0 == m) d = (0..m).to_a x = nil str1.each_char.each_with_index do |char1,i| e = i+1 str2.each_char.each_with_index do |char2,j| cost = (char1 == char2) ? 0 : 1 x = min3( d[j+1] + 1, # insertion e + 1, # deletion d[j] + cost # substitution ) d[j] = e e = x end d[m] = x end return x end
#truncate_text(text, description, max_length = 100_000)
# File 'lib/rubygems/text.rb', line 16
def truncate_text(text, description, max_length = 100_000) raise ArgumentError, "max_length must be positive" unless max_length > 0 return text if text.size <= max_length "Truncating #{description} to #{max_length.to_s.reverse.gsub(/...(?=.)/,'\&,').reverse} characters:\n" + text[0, max_length] end