Class: MList::Util::HtmlTextExtraction

Inherits:
Object
  • Object
show all
Defined in:
lib/mlist/util/email_helpers.rb

Constant Summary collapse

NBSP =

We need a way to maintain non-breaking spaces. Hpricot will replace them with ??.chr. We can easily teach it to convert it to a space, but then we lose the information in the Text node that we need to keep the space around, since that is what they would see in a view of the HTML.

'!!!NBSP!!!'

Instance Method Summary collapse

Constructor Details

#initialize(html) ⇒ HtmlTextExtraction

Returns a new instance of HtmlTextExtraction.



12
13
14
 
# File 'lib/mlist/util/email_helpers.rb', line 12

def initialize(html)
  @doc = Hpricot(html.gsub(' ', NBSP))
end

Instance Method Details

#execute ⇒ Object 



16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
 
# File 'lib/mlist/util/email_helpers.rb', line 16

def execute
  @text, @anchors = '', []
  @doc.each_child do |node|
    extract_text_from_node(node) if Hpricot::Elem::Trav === node
  end
  @text.strip!
  unless @anchors.empty?
    refs = []
    @anchors.each_with_index do |href, i|
      refs << "[#{i+1}] #{href}"
    end
    @text << "\n\n--\n#{refs.join("\n")}"
  end
  @text.gsub(NBSP, ' ')
end

#extract_text_from_children(elem) ⇒ Object 



71
72
73
74
75
76
77
78
79
80
 
# File 'lib/mlist/util/email_helpers.rb', line 71

def extract_text_from_children(elem)
  elem.each_child do |node|
    case node
    when Hpricot::Text::Trav
      extract_text_from_text_node(node)
    when Hpricot::Elem::Trav
      extract_text_from_node(node)
    end
  end
end

#extract_text_from_node(node) ⇒ Object 



32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
 
# File 'lib/mlist/util/email_helpers.rb', line 32

def extract_text_from_node(node)
  case node.name
  when 'head'
  when 'h1', 'h2', 'h3', 'h4', 'h5', 'h6'
    @text << node.inner_text
    @text << "\n\n"
  when 'br'
    @text << "\n"
  when 'ol'
    node.children_of_type('li').each_with_index do |li, i|
      @text << " #{i+1}. #{li.inner_text}"
      @text << "\n\n"
    end
  when 'ul'
    node.children_of_type('li').each do |li|
      @text << " * #{li.inner_text.strip}"
      @text << "\n\n"
    end
  when 'strong'
    @text << "*#{node.inner_text}*"
  when 'em'
    @text << "_#{node.inner_text}_"
  when 'dl'
    node.traverse_element('dt', 'dd') do |dt_dd|
      extract_text_from_node(dt_dd)
    end
  when 'a'
    @anchors << node['href']
    extract_text_from_text_node(node)
    @text << "[#{@anchors.size}]"
  when 'p', 'dt', 'dd'
    extract_text_from_children(node)
    @text.rstrip!
    @text << "\n\n"
  else
    extract_text_from_children(node)
  end
end

#extract_text_from_text_node(node) ⇒ Object 



82
83
84
85
 
# File 'lib/mlist/util/email_helpers.rb', line 82

def extract_text_from_text_node(node)
  text = @text.end_with?("\n") ? node.inner_text.lstrip : node.inner_text
  @text << text.gsub(/\s{2,}/, ' ').sub(/\n/, '')
end