Module: Aitextcleaner::FormattingResidue

Defined in:
lib/aitextcleaner/formatting_residue.rb

Constant Summary collapse

BLOCK_TAG = 
/<\/?(?:address|article|blockquote|br|div|li|p|pre|section)\b[^>]*>/i
HTML_TAG = 
/<[^>]*>/

Class Method Summary collapse

Class Method Details

.clean(text) ⇒ Object

Raises:

  • (TypeError) 


10
11
12
13
14
15
16
17
18
 
# File 'lib/aitextcleaner/formatting_residue.rb', line 10

def clean(text)
  raise TypeError, "text must be a string" unless text.is_a?(String)

  cleaned = text.gsub(BLOCK_TAG, "\n").gsub(HTML_TAG, "")
  cleaned = CGI.unescapeHTML(cleaned)
  cleaned = cleaned.gsub("“", '"').gsub("”", '"').gsub("‘", "'").gsub("’", "'")
    .gsub("–", "-").gsub("—", "-").gsub("…", "...")
  cleaned.gsub(/[ \t]+\n/, "\n").gsub(/\n{3,}/, "\n\n").strip
end