Module: Sanitizer

Defined in:

lib/sanitizer/version.rb,
lib/sanitizer/sanitizer.rb

Constant Summary

VERSION =

"0.2.1"

@@htmle =

HTMLEntris

HTMLEntities.new

Class Method Summary

• .clean_spaces(text) ⇒ Object
• .clean_spaces!(text) ⇒ Object

  Clean retundant spaces.

• .entities_to_chars(text) ⇒ Object
• .entities_to_chars!(text) ⇒ Object

  Alguns feeds retornam tags "escapadas" dentro do conteúdo (ex: <br/>) Este método deve ser utilizado após o stripping e sanitização, para não deixar que essas tags sejam exibidas como conteúdo.

• .html_decode(text) ⇒ Object

  Convert invalid chars to HTML Entries.

• .html_encode(text) ⇒ Object

  Convert invalid chars to HTML Entries.

• .sanitize(text) ⇒ Object
• .sanitize!(text) ⇒ Object

  Sanitize to clean text.

• .strip_comments(text) ⇒ Object
• .strip_comments!(text) ⇒ Object

  remove comments.

• .strip_disallowed_tags(text) ⇒ Object
• .strip_disallowed_tags!(text) ⇒ Object

  Remove all

  # File 'lib/sanitizer/sanitizer.rb', line 28
  
  def clean_spaces(text)
    clean_spaces! text.dup
  end

  .clean_spaces!(text) ⇒ Object

  Clean retundant spaces

  # File 'lib/sanitizer/sanitizer.rb', line 22
  
  def clean_spaces!(text)
    text.gsub!(/\s+/, " ")
    text.strip!
    text
  end

  .entities_to_chars(text) ⇒ Object

  # File 'lib/sanitizer/sanitizer.rb', line 89
  
  def entities_to_chars(text)
    entities_to_chars! text.dup
  end

  .entities_to_chars!(text) ⇒ Object

  Alguns feeds retornam tags "escapadas" dentro do conteúdo (ex: <br/>) Este método deve ser utilizado após o stripping e sanitização, para não deixar que essas tags sejam exibidas como conteúdo

  # File 'lib/sanitizer/sanitizer.rb', line 83
  
  def entities_to_chars!(text)
    text.gsub!(/\&lt;/uim, "<")
    text.gsub!(/\&gt;/uim, ">")
    text
  end

  .html_decode(text) ⇒ Object

  Convert invalid chars to HTML Entries

  # File 'lib/sanitizer/sanitizer.rb', line 100
  
  def html_decode(text)
    text = text.to_s  
    @@htmle.decode(text)
  end

  .html_encode(text) ⇒ Object

  Convert invalid chars to HTML Entries

  # File 'lib/sanitizer/sanitizer.rb', line 94
  
  def html_encode(text)
    text = text.to_s  
    @@htmle.encode(text, :named)
  end

  .sanitize(text) ⇒ Object

  # File 'lib/sanitizer/sanitizer.rb', line 17
  
  def sanitize(text)
    sanitize! text.dup
  end

  .sanitize!(text) ⇒ Object

  Sanitize to clean text

  # File 'lib/sanitizer/sanitizer.rb', line 10
  
  def sanitize!(text)
    strip_tags!(text)
    clean_spaces!(text)
    text.replace html_encode(text)
    text
  end

  .strip_comments(text) ⇒ Object

  # File 'lib/sanitizer/sanitizer.rb', line 39
  
  def strip_comments(text)
    strip_comments! text.dup
  end

  .strip_comments!(text) ⇒ Object

  remove comments

  # File 'lib/sanitizer/sanitizer.rb', line 33
  
  def strip_comments!(text)
    text.gsub!(/(\<\!\-\-\b*[^\-\-\>]*.*?\-\-\>)/ui, "")
    text.gsub!(/(\&lt;\s?\!--.*\s?--\&gt;)/uim, "")
    text
  end

  .strip_disallowed_tags(text) ⇒ Object

  # File 'lib/sanitizer/sanitizer.rb', line 58
  
  def strip_disallowed_tags(text)
    strip_disallowed_tags! text.dup
  end

  .strip_disallowed_tags!(text) ⇒ Object

  Remove all

  # File 'lib/sanitizer/sanitizer.rb', line 77
  
  def strip_tags(text, *tags)
    strip_tags! text.dup, *tags
  end

  .strip_tags!(text, *tags) ⇒ Object

  Remove all tags from from text

  # File 'lib/sanitizer/sanitizer.rb', line 63
  
  def strip_tags!(text, *tags)
    if tags.empty? # clear all tags by default
      text.gsub!(/<\/?[^>]*>/uim, "")
      text.gsub!(/\&lt;\/?[^\&gt;]*\&gt;/uim, "")
    else # clean only selected tags 
      strip = tags.map do |tag|  
        %Q{(#{tag})}
      end.join('|')
      text.gsub!(/<\/?(#{strip})[^>]*>/uim, "")
      text.gsub!(/\&lt;\/?(#{strip})[^\&gt;]*\&gt;/uim, "")
    end
    text
  end

  Generated on Tue Sep 15 13:17:24 2026 by yard 0.9.45 (ruby-4.0.6).