Module: ActionMailer::Text::HtmlToPlainText

Defined in:
lib/actionmailer-text/html_to_plain_text.rb

Class Method Summary collapse

Instance Method Summary collapse

Class Method Details

.convert_to_text(html, line_length = 65, _from_charset = 'UTF-8') ⇒ Object

Returns the text in UTF-8 format with all HTML tags removed

TODO: add support for DL, OL



20
21
22
23
24
25
26
27
28
29
30
31
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
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
99
100
101
102
103
104
 
# File 'lib/actionmailer-text/html_to_plain_text.rb', line 20

def self.convert_to_text(html, line_length = 65, _from_charset = 'UTF-8')
  txt = html

  # decode HTML entities
  he = HTMLEntities.new
  txt = he.decode(txt)

  # Ignore things that come outside the body
  txt.gsub!(/.*?(<body.+?\/body>).*?/im, '\1')

  # replace image by their alt attribute
  txt.gsub!(/<img.+?alt=\"([^\"]*)\"[^>]*\/>/i, '\1')
  txt.gsub!(/<img.+?alt='([^\']*)\'[^>]*\/>/i, '\1')

  # links
  txt.gsub!(/<a.+?href=\"([^\"]*)\"[^>]*>(.+?)<\/a>/mi) do |_s|
    Regexp.last_match[2].strip + ' ( ' + Regexp.last_match[1].strip + ' )'
  end

  txt.gsub!(/<a.+?href='([^\']*)\'[^>]*>(.+?)<\/a>/mi) do |_s|
    Regexp.last_match[2].strip + ' ( ' + Regexp.last_match[1].strip + ' )'
  end

  # handle headings (H1-H6)
  txt.gsub!(/(<\/h[1-6]>)/i, "\n\\1") # move closing tags to new lines
  txt.gsub!(/[\s]*<h([1-6]+)[^>]*>[\s]*(.*)[\s]*<\/h[1-6]+>/i) do |_s|
    hlevel = Regexp.last_match[1].to_i

    htext = Regexp.last_match[2]
    htext.gsub!(/<br[\s]*\/?>/i, "\n") # handle <br>s
    htext.gsub!(/<\/?[^>]*>/i, '') # strip tags

    # determine maximum line length
    hlength = 0
    htext.each_line do |l|
      llength = l.strip.length
      hlength = llength if llength > hlength
    end
    hlength = line_length if line_length && hlength > line_length

    case hlevel
    when 1   # H1, asterisks above and below
      htext = ('*' * hlength) + "\n" + htext + "\n" + ('*' * hlength)
    when 2   # H1, dashes above and below
      htext = ('-' * hlength) + "\n" + htext + "\n" + ('-' * hlength)
    else     # H3-H6, dashes below
      htext = htext + "\n" + ('-' * hlength)
    end

    "\n\n" + htext + "\n\n"
  end

  # wrap spans
  txt.gsub!(/(<\/span>)[\s]+(<span)/mi, '\1 \2')

  # lists -- TODO: should handle ordered lists
  txt.gsub!(/[\s]*(<li[^>]*>)[\s]*/i, '* ')
  # list not followed by a newline
  txt.gsub!(/<\/li>[\s]*(?![\n])/i, "\n")

  # paragraphs and line breaks
  txt.gsub!(/<\/p>/i, "\n\n")
  txt.gsub!(/<br[\/ ]*>/i, "\n")

  # strip remaining tags
  txt.gsub!(/<\/?[^>]*>/, '')

  txt = custom_word_wrap(txt, line_length) if line_length

  # remove linefeeds (\r\n and \r -> \n)
  txt.gsub!(/\r\n?/, "\n")

  # strip extra spaces
  txt.gsub!(/\302\240+/, ' ') # non-breaking spaces -> spaces
  txt.gsub!(/\n[ \t]+/, "\n") # space at start of lines
  txt.gsub!(/[ \t]+\n/, "\n") # space at end of lines

  # no more than two consecutive newlines
  txt.gsub!(/[\n]{3,}/, "\n\n")

  # no more than two consecutive spaces
  txt.gsub!(/ {2,}/, ' ')

  txt.strip
end

.custom_word_wrap(txt, line_length) ⇒ Object

Taken from Rails’ word_wrap helper (api.rubyonrails.org/classes/ActionView/Helpers/TextHelper.html#method-i-word_wrap)



107
108
109
110
111
 
# File 'lib/actionmailer-text/html_to_plain_text.rb', line 107

def self.custom_word_wrap(txt, line_length)
  txt.split("\n").collect do |line|
    line.length > line_length ? line.gsub(/(.{1,#{line_length}})(\s+|$)/, "\\1\n").strip : line
  end * "\n"
end

Instance Method Details

#convert_to_text(html, line_length = 65, from_charset = 'UTF-8') ⇒ Object 



13
14
15
 
# File 'lib/actionmailer-text/html_to_plain_text.rb', line 13

def convert_to_text(html, line_length = 65, from_charset = 'UTF-8')
  HtmlToPlainText.convert_to_text(html, line_length, from_charset)
end