summaryrefslogtreecommitdiff
path: root/lib/feed2imap/textconverters.rb
blob: 418083ff32a5c66af8da415a0ba55151c4fdb938 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
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
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
=begin
Feed2Imap - RSS/Atom Aggregator uploading to an IMAP Server
Copyright (c) 2005 Lucas Nussbaum <lucas@lucas-nussbaum.net>

This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.

This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
=end

require 'uri' # for URI::regexp
require 'feed2imap/html2text-parser'

# This class provides various converters
class String
  # is this text HTML ? search for tags
  def html?
    return (self =~ /<p>/) || (self =~ /<br>/) || (self =~ /<br\s*(\/)?\s*>/)
  end

  # returns true if the text contains escaped HTML (with HTML entities)
  def escaped_html?
    return (self =~ /&lt;img src=/) || (self =~ /&lt;a href=/) || (self =~ /&lt;br(\/| \/|)&gt;/)
  end

  # un-escape HTML in the text
  def unescape_html
    {
      '<' => '&lt;',
      '>' => '&gt;',
      "'" => '&apos;',
      '"' => '&quot;',
      '&' => '&amp;',
      "\047" => '&#39;'
    }.each do |k, v|
      gsub!(v, k)
    end
    self
  end

  # convert text to HTML
  def text2html
    text = self.clone
    return text if text.html?
    if text.escaped_html?
      return text.unescape_html
    end
    # paragraphs
    text.gsub!(/\A\s*(.*)\Z/m, '<p>\1</p>')
    text.gsub!(/\s*\n(\s*\n)+\s*/, "</p>\n<p>")
    # uris
    text.gsub!(/(#{URI::regexp(['http','ftp','https'])})/,
        '<a href="\1">\1</a>')
    text
  end

  # Convert an HTML text to plain text
  def html2text
    if false
      text = self.clone
      # let's remove all CR
      text.gsub!(/\n/, '')
      # convert <p> and <br>
      text.gsub!(/\s*<\/p>\s*/, '')
      text.gsub!(/\s*<p(\s[^>]*)?>\s*/, "\n\n")
      text.gsub!(/\s*<br(\s*)\/?(\s*)>\s*/, "\n")
      # remove other tags
      text.gsub!(/<[^>]*>/, '')
      # remove leading and trailing whilespace
      text.gsub!(/\A\s*/m, '')
      text.gsub!(/\s*\Z/m, '')
      text
    else
      text = self.clone
      # parse HTML
      p = HTML2TextParser::new(true)
      p.feed(text)
      p.close
      text = p.savedata
      # remove leading and trailing whilespace
      text.gsub!(/\A\s*/m, '')
      text.gsub!(/\s*\Z/m, '')
      # remove whitespace around \n
      text.gsub!(/ *\n/m, "\n")
      text.gsub!(/\n */m, "\n")
      # and duplicates \n
      text.gsub!(/\n\n+/m, "\n\n")
      text
    end
  end

  # Remove white space around the text
  def rmWhiteSpace!
    return self.gsub!(/\A\s*/m, '').gsub!(/\s*\Z/m,'')
  end

  # Convert a text in inputenc to a text in ISO-8859-1
  def toISO_8859_1(inputenc)
    if inputenc.downcase == 'utf-8'
      begin
        return self.unpack('U*').pack('C*')
      rescue
        return self
      end
    else
      return self
    end
  end

  # Convert a text in inputenc to a text in UTF8
  # must take care of wrong input locales
  def toUTF8(inputenc)
    if inputenc.downcase != 'utf-8'
      # it is said it is not UTF-8. Ensure it is REALLY not UTF-8
      begin
        if self.unpack('U*').pack('U*') == self
          return self
        end
      rescue
        # do nothing
      end
      begin
        return self.unpack('C*').pack('U*')
      rescue
        return self #failsafe solution. but a dirty one :-)
      end
    else
      return self
    end
  end

  def needMIME
    utf8 = false
    self.unpack('U*').each do |c|
      if c > 127
        utf8 = true
        break
      end
    end
    utf8
  end
end