File: utf8prober.rb

package info (click to toggle)
ruby-rchardet 1.3-3
  • links: PTS, VCS
  • area: main
  • in suites: jessie, jessie-kfreebsd, wheezy
  • size: 664 kB
  • ctags: 246
  • sloc: ruby: 5,839; makefile: 3
file content (87 lines) | stat: -rwxr-xr-x 2,231 bytes parent folder | download
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
######################## BEGIN LICENSE BLOCK ########################
# The Original Code is mozilla.org code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 1998
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
#   Jeff Hodges - port to Ruby
#   Mark Pilgrim - port to Python
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
# 
# This library 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
# Lesser General Public License for more details.
# 
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
# 02110-1301  USA
######################### END LICENSE BLOCK #########################

module CharDet
  ONE_CHAR_PROB = 0.5

  class UTF8Prober < CharSetProber
    def initialize
      super()
      @_mCodingSM = CodingStateMachine.new(UTF8SMModel)
      reset()
    end

    def reset
      super()
      @_mCodingSM.reset()
      @_mNumOfMBChar = 0
    end

    def get_charset_name
      return "utf-8"
    end

    def feed(aBuf)
      aBuf.each_byte do |b|
	c = b.chr
	codingState = @_mCodingSM.next_state(c)
	if codingState == EError
	  @_mState = ENotMe
	  break
	elsif codingState == EItsMe
	  @_mState = EFoundIt
	  break
	elsif codingState == EStart
	  if @_mCodingSM.get_current_charlen() >= 2
	    @_mNumOfMBChar += 1
	  end
	end
      end

      if get_state() == EDetecting
	if get_confidence() > SHORTCUT_THRESHOLD
	  @_mState = EFoundIt
	end
      end

      return get_state()
    end

    def get_confidence
      unlike = 0.99
      if @_mNumOfMBChar < 6
	for i in (0...@_mNumOfMBChar)
	  unlike = unlike * ONE_CHAR_PROB
	end
	return 1.0 - unlike
      else
	return unlike
      end
    end
  end
end