Module: Cleaners::ReplaceHTMLMarkup

Defined in:
lib/data_cleansing/cleaners.rb

Overview

Unescape HTML Markup ( case-insensitive )

Constant Summary collapse

HTML_MARKUP = 
Regexp.compile(/&(amp|quot|gt|lt|apos|nbsp);/in)

Class Method Summary collapse

Class Method Details

.call(string) ⇒ Object 



61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
 
# File 'lib/data_cleansing/cleaners.rb', line 61

def self.call(string)
  return string unless string.is_a?(String)

  string.gsub!(HTML_MARKUP) do |match|
    case match.downcase
    when '&' then
      '&'
    when '"' then
      '"'
    when '>' then
      '>'
    when '<' then
      '<'
    when '&apos;' then
      "'"
    when '&nbsp;' then
      ' '
    else
      "&#{match};"
    end
  end || string
end