Module: Gem::Text

Overview

A collection of text-wrangling methods

Instance Method Summary collapse

Instance Method Details

#clean_text(text) ⇒ Object

Remove any non-printable characters and make the text suitable for printing.


11
12
13
# File 'lib/rubygems/text.rb', line 11

def clean_text(text)
  text.gsub(/[\000-\b\v-\f\016-\037\177]/, ".".freeze)
end

#format_text(text, wrap, indent = 0) ⇒ Object

Wraps text to wrap characters and optionally indents by indent characters


25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
# File 'lib/rubygems/text.rb', line 25

def format_text(text, wrap, indent=0)
  result = []
  work = clean_text(text)

  while work.length > wrap do
    if work =~ /^(.{0,#{wrap}})[ \n]/
      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) ⇒ Object

Returns a value representing the “cost” of transforming str1 into str2 Vendored version of DidYouMean::Levenshtein.distance from the ruby/did_you_mean gem @ 1.4.0 git.io/JJgZI


55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
# File 'lib/rubygems/text.rb', line 55

def levenshtein_distance(str1, str2)
  n = str1.length
  m = str2.length
  return m if n.zero?
  return n if m.zero?

  d = (0..m).to_a
  x = nil

  # to avoid duplicating an enumerable object, create it outside of the loop
  str2_codepoints = str2.codepoints

  str1.each_codepoint.with_index(1) do |char1, i|
    j = 0
    while j < m
      cost = (char1 == str2_codepoints[j]) ? 0 : 1
      x = min3(
        d[j + 1] + 1, # insertion
        i + 1,      # deletion
        d[j] + cost # substitution
      )
      d[j] = i
      i = x

      j += 1
    end
    d[m] = x
  end

  x
end

#min3(a, b, c) ⇒ Object

:nodoc:


42
43
44
45
46
47
48
49
50
# File 'lib/rubygems/text.rb', line 42

def min3(a, b, c) # :nodoc:
  if a < b && a < c
    a
  elsif b < c
    b
  else
    c
  end
end

#truncate_text(text, description, max_length = 100_000) ⇒ Object

Raises:

  • (ArgumentError)

15
16
17
18
19
# File 'lib/rubygems/text.rb', line 15

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