2016-02-01 07:43:26 -05:00
|
|
|
# frozen_string_literal: true
|
2009-06-09 17:38:59 -04:00
|
|
|
require 'rubygems'
|
|
|
|
|
|
|
|
##
|
|
|
|
# A collection of text-wrangling methods
|
|
|
|
|
|
|
|
module Gem::Text
|
|
|
|
|
2017-08-28 04:31:28 -04:00
|
|
|
##
|
|
|
|
# Remove any non-printable characters and make the text suitable for
|
|
|
|
# printing.
|
|
|
|
def clean_text(text)
|
|
|
|
text.gsub(/[\000-\b\v-\f\016-\037\177]/, ".".freeze)
|
|
|
|
end
|
|
|
|
|
|
|
|
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
|
|
|
|
|
2009-06-09 17:38:59 -04:00
|
|
|
##
|
|
|
|
# Wraps +text+ to +wrap+ characters and optionally indents by +indent+
|
|
|
|
# characters
|
|
|
|
|
|
|
|
def format_text(text, wrap, indent=0)
|
|
|
|
result = []
|
2017-08-28 04:31:28 -04:00
|
|
|
work = clean_text(text)
|
2009-06-09 17:38:59 -04:00
|
|
|
|
|
|
|
while work.length > wrap do
|
|
|
|
if work =~ /^(.{0,#{wrap}})[ \n]/ then
|
2011-05-31 23:45:05 -04:00
|
|
|
result << $1.rstrip
|
2009-06-09 17:38:59 -04:00
|
|
|
work.slice!(0, $&.length)
|
|
|
|
else
|
|
|
|
result << work.slice!(0, wrap)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
result << work if work.length.nonzero?
|
|
|
|
result.join("\n").gsub(/^/, " " * indent)
|
|
|
|
end
|
|
|
|
|
2014-09-13 23:30:02 -04:00
|
|
|
def min3 a, b, c # :nodoc:
|
2014-12-06 19:53:01 -05:00
|
|
|
if a < b && a < c then
|
2014-09-13 23:30:02 -04:00
|
|
|
a
|
2014-12-06 19:53:01 -05:00
|
|
|
elsif b < c then
|
2014-09-13 23:30:02 -04:00
|
|
|
b
|
|
|
|
else
|
|
|
|
c
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2011-01-18 19:08:49 -05:00
|
|
|
# This code is based directly on the Text gem implementation
|
|
|
|
# Returns a value representing the "cost" of transforming str1 into str2
|
|
|
|
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
|
|
|
|
|
2014-09-13 23:30:02 -04:00
|
|
|
str1.each_char.each_with_index do |char1,i|
|
2011-01-18 19:08:49 -05:00
|
|
|
e = i+1
|
|
|
|
|
2014-09-13 23:30:02 -04:00
|
|
|
str2.each_char.each_with_index do |char2,j|
|
|
|
|
cost = (char1 == char2) ? 0 : 1
|
|
|
|
x = min3(
|
2011-01-18 19:08:49 -05:00
|
|
|
d[j+1] + 1, # insertion
|
|
|
|
e + 1, # deletion
|
|
|
|
d[j] + cost # substitution
|
2014-09-13 23:30:02 -04:00
|
|
|
)
|
2011-01-18 19:08:49 -05:00
|
|
|
d[j] = e
|
|
|
|
e = x
|
|
|
|
end
|
|
|
|
|
|
|
|
d[m] = x
|
|
|
|
end
|
|
|
|
|
|
|
|
return x
|
|
|
|
end
|
2009-06-09 17:38:59 -04:00
|
|
|
end
|