Class: SpreadsheetBuilder::HtmlParser

Inherits:
Object
  • Object
show all
Defined in:
lib/spreadsheet_builder/html_parser.rb

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(html, *css_paths) ⇒ HtmlParser

Returns a new instance of HtmlParser.



17
18
19
20
21
22
 
# File 'lib/spreadsheet_builder/html_parser.rb', line 17

def initialize(html, *css_paths)
  # TODO merge inline style tags into CssParser
  @css_load_paths = css_paths
  @html = html
  @doc  = Nokogiri::HTML(@html) 
end

Instance Attribute Details

#doc ⇒ Object (readonly)

Returns the value of attribute doc.



16
17
18
 
# File 'lib/spreadsheet_builder/html_parser.rb', line 16

def doc
  @doc
end

Class Method Details

.from_erb(file) ⇒ Object 



8
9
10
11
12
13
14
 
# File 'lib/spreadsheet_builder/html_parser.rb', line 8

def self.from_erb(file)
  html     = File.read(file)
  template = ERB.new(html)
  html     = template.result

  new(html)
end

.from_slim(file, options = {}, context = self, &block) ⇒ Object 



3
4
5
6
 
# File 'lib/spreadsheet_builder/html_parser.rb', line 3

def self.from_slim(file, options = {}, context = self, &block)
  html = Slim::Template.new(file, options).render(context, &block)
  new(html)
end

Instance Method Details

#build(force_level = :none) ⇒ Object 



24
25
26
 
# File 'lib/spreadsheet_builder/html_parser.rb', line 24

def build(force_level = :none)
  SpreadsheetBuilder.from_data(to_data(force_level))
end

#css ⇒ Object 



28
29
30
31
32
33
34
35
36
37
38
39
 
# File 'lib/spreadsheet_builder/html_parser.rb', line 28

def css
  return @css  if @css

  @doc.css('link[rel=stylesheet]').map { |l| 
    href = l["href"].sub(/^\/+/, '')
    # This will have to be updated later with a host
    @css_load_paths << "#{href}" 
  }
  #@css = SpreadsheetBuilder::CssParser.new(@css_load_paths)
  # Figure out the best way to load this
  @css = SpreadsheetBuilder::CssParser.new([])
end

#to_data(force_level = :none) ⇒ Object

TODO clean this up



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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
 
# File 'lib/spreadsheet_builder/html_parser.rb', line 42

def to_data(force_level = :none)
  cells       = [] 
  merges      = []
  col_widths  = {}
  row_heights = {}

  css.reset(force_level)

  tb  = doc.css('table').first 

  # ignoring specified formats for anything other than table tr td/th
  tb_format = css.format_from_node(tb) 

  row = 0
  doc.css('tr').each do |tr|
    tr_format = tb_format.merge(@css.format_from_node(tr))

    increment = true
    tr.css('td, th').each_with_index do |td, col|
       
      # TODO Do we really need rowheight and colwidth now that there
      # is css parsing?
      rowheight = td.attributes["rowheight"]
      colwidth  = td.attributes["colwidth"]
      rowspan   = td.attributes["rowspan"]
      colspan   = td.attributes["colspan"]

      rowheight &&= rowheight.value.to_i
      colwidth  &&= colwidth.value.to_i
      rowspan   &&= rowspan.value.to_i
      colspan   &&= colspan.value.to_i

      add_td_to_cells(row, col, td, tr_format, cells)
      if colspan
        (1..colspan-1).each {|t| 
          add_td_to_cells(row, col+t, td, tr_format, cells)
        }
      end
      if rowspan
        (1..rowspan-2).each {|t| 
          add_td_to_cells(row+t, col, td, tr_format, cells)
        }
        increment = false
      end
      if colspan || rowspan
        merges << [
          row, col, row + (rowspan || 2)-2, col + (colspan || 1)-1
        ]
      end
    end

    row += 1 if increment
  end

  puts cells.inspect
  { cells: cells, merges: { 0 => merges } }
end