Module: Mongolian

Included in:
String
Defined in:
lib/mongolian.rb,
lib/mongolian/latin.rb,
lib/mongolian/version.rb,
lib/mongolian/stemmify.rb,
lib/mongolian/tokenizer.rb,
lib/mongolian/spellchecker.rb

Defined Under Namespace

Classes: Error

Constant Summary collapse

VERSION = 
"0.1.1"

Class Method Summary collapse

Instance Method Summary collapse

Class Method Details

.double_constant_check(str) ⇒ Object

蒙古语里没有复辅音是指在书面语单音节中没有复辅音 P89



62
63
64
65
66
67
68
69
70
71
72
73
74
75
 
# File 'lib/mongolian/spellchecker.rb', line 62

def self.double_constant_check(str)
  mongolian_str = str
  result = 1
  syllable(mongolian_str).each do |s|
    sv = s.scan(/[ᠠᠡᠢᠣᠤᠥᠦ]/).join
    if s.index(sv) < 2 and s.size - s.index(sv) - sv.size < 2
      next
    else
      result = 0
      break
    end
  end
  return result
end

Instance Method Details

#ae?(str) ⇒ Boolean

_ 用于分写 ᠠ(a)/ᠡ(e) 跟前面的辅音(h/g + a; n, l, m, s, sh, j, y, r , W + a/e)

Returns:

  • (Boolean) 


81
82
83
84
85
86
87
 
# File 'lib/mongolian/spellchecker.rb', line 81

def ae?(str)
  if str =~ /᠎[ᠠᠡ]/
    return true
  else
    false
  end
end

#is_mongolian? ⇒ Boolean

判断一个词或者字符是否包含蒙古文字符，如果包含蒙古文返回 true，否则返回 nil。

Returns:

  • (Boolean) 


5
6
7
 
# File 'lib/mongolian/tokenizer.rb', line 5

def is_mongolian?
  return true if !!(self =~ /\p{Mongolian}/)
end

#mon_l2m ⇒ Object

对拉丁转写蒙古文恢复为蒙古文



102
103
104
105
106
 
# File 'lib/mongolian/latin.rb', line 102

def mon_l2m
  str = self.dup.to_str
  # 将拉丁文转换文对应的蒙古文
  return str
end

#mon_m2l ⇒ Object

转换传统蒙古文为拉丁转写



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
 
# File 'lib/mongolian/latin.rb', line 9

def mon_m2l
  str = self.dup.to_str
  str = str.gsub(/ᠠ/, "a")
  str = str.gsub(/ᠡ/, "e")
  str = str.gsub(/ᠢ/, "i")
  str = str.gsub(/ᠣ/, "o")
  str = str.gsub(/ᠤ/, "u")
  str = str.gsub(/ᠥ/, "ö")
  str = str.gsub(/ᠦ/, "ü")
  str = str.gsub(/ᠧ/, "ë")
  str = str.gsub(/ᠨ/, "n")
  str = str.gsub(/ᠩ/, "ng")
  str = str.gsub(/ᠪ/, "b")
  str = str.gsub(/ᠫ/, "p")
  str = str.gsub(/ᠬ/, "x")
  str = str.gsub(/ᠭ/, "g")
  str = str.gsub(/ᠮ/, "m")
  str = str.gsub(/ᠯ/, "l")
  str = str.gsub(/ᠰ/, "s")
  str = str.gsub(/ᠱ/, "š")
  str = str.gsub(/ᠲ/, "t")
  str = str.gsub(/ᠳ/, "d")
  str = str.gsub(/ᠴ/, "č")
  str = str.gsub(/ᠵ/, "ǰ")
  str = str.gsub(/ᠶ/, "y")
  str = str.gsub(/ᠷ/, "r")
  str = str.gsub(/ᠸ/, "w")
  str = str.gsub(/ᠹ/, "f")
  str = str.gsub(/ᠺ/, "k")
  str = str.gsub(/ᠻ/, "ḳ")
  str = str.gsub(/ᠼ/, "c")
  str = str.gsub(/ᠽ/, "z")
  str = str.gsub(/ᠾ/, "h")
  str = str.gsub(/ᠿ/, "ž")
  str = str.gsub(/ᡀ/, "lh")
  str = str.gsub(/ᡁ/, "ẑ")
  str = str.gsub(/ᡂ/, "ĉ")
  str = str.gsub(/᠀/, "&")
  str = str.gsub(/᠁/, "…")
  str = str.gsub(/᠂/, ",")
  str = str.gsub(/᠃/, ".")
  str = str.gsub(/᠇/, ":")
  str = str.gsub(/᠈/, "#")
  str = str.gsub(/᠊/, "‐")
  str = str.gsub(/᠋/, "") #fvs1
  str = str.gsub(/᠌/, "") #fvs2
  str = str.gsub(/᠍/, "") #fvs3
  str = str.gsub(/᠎/, "_")
  str = str.gsub(/᠐/, "'0")
  str = str.gsub(/᠑/, "'1")
  str = str.gsub(/᠒/, "'2")
  str = str.gsub(/᠓/, "'3")
  str = str.gsub(/᠔/, "'4")
  str = str.gsub(/᠕/, "'5")
  str = str.gsub(/᠖/, "'6")
  str = str.gsub(/᠗/, "'7")
  str = str.gsub(/᠘/, "'8")
  str = str.gsub(/᠙/, "'9")
  str = str.gsub(/ᡛ/, "ń")
  str = str.gsub(/ᢀ/, "ṃ")
  str = str.gsub(/ᢁ/, "ḥ")
  str = str.gsub(/ᢂ/, "â")
  str = str.gsub(/ᢃ/, "ŏ")
  str = str.gsub(/ᢄ/, "ô")
  str = str.gsub(/ᢅ/, "ˑ")
  str = str.gsub(/ᢆ/, "ːˑ")
  str = str.gsub(/ᢇ/, "ā")
  str = str.gsub(/ᢈ/, "ī")
  str = str.gsub(/ᢉ/, "ḵ")
  str = str.gsub(/ᢊ/, "ṉ")
  str = str.gsub(/ᢋ/, "ƈ")
  str = str.gsub(/ᢌ/, "ť")
  str = str.gsub(/ᢍ/, "ţ")
  str = str.gsub(/ᢎ/, "ḏ")
  str = str.gsub(/ᢏ/, "ņ")
  str = str.gsub(/ᢐ/, "ṯ")
  str = str.gsub(/ᢑ/, "ḓ")
  str = str.gsub(/ᢒ/, "p̄")
  str = str.gsub(/ᢓ/, "ṕh")
  str = str.gsub(/ᢔ/, "ş")
  str = str.gsub(/ᢕ/, "ẖ")
  str = str.gsub(/ᢖ/, "ẕ")
  str = str.gsub(/ᢗ/, "ʒ̄")
  str = str.gsub(/ᢦ/, "ŭ")
  str = str.gsub(/ᢧ/, "ÿ")
  str = str.gsub(/ᢩ/, "̲")
  str = str.gsub(/‌/, "^")
  str = str.gsub(/‍/, "*")
  str = str.gsub(/ /, "-")
  return str
end

#mon_stemmify ⇒ Object

对做好分词的蒙古文词进行词干提取。



3
4
5
6
7
8
9
10
11
12
13
 
# File 'lib/mongolian/stemmify.rb', line 3

def mon_stemmify
  w = self.dup.to_str
  return w if w.length < 4
  
  # 在蒙古文空格后，必定是后缀，删除
  if w =~ /᠎/
    w = $`
  end
  
  return w
end

#mon_syllable_classify ⇒ Object

对单词划分音节：每个元音前最多一个辅音前面既可划分音节返回值是音节数组



36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
 
# File 'lib/mongolian/spellchecker.rb', line 36

def mon_syllable_classify
  mongolian_str = self.dup.to_str
  mlist = []
  s = ""
  mongolian_str.each_char do |c|
    if c =~ /[ᠠᠡᠢᠣᠤᠥᠦ]/
      if s[-1] =~ /[ᠠᠡᠢᠣᠤᠥᠦ]/
        s += c
      else
        if s[0..-2].size > 0
          mlist << s[0..-2]
          s = s[-1]
          s += c
        else
          s += c
        end
      end
    else
      s += c
    end
  end
  mlist << s if s.size > 0
  return mlist
end

#mon_tokenize ⇒ Object

对于混合有多个文种的一段文字，删除其中的非蒙古文字符和蒙古文标点符号后，



12
13
14
15
16
17
18
19
20
21
22
23
 
# File 'lib/mongolian/tokenizer.rb', line 12

def mon_tokenize
  w = self.dup.to_str
  # 去除标点符号，用空格替换标点符号
  w = w.gsub(/[!᠄?·᠃᠂⁈⁉᠁—;《》]/, " ")
  new_w = ""
  # 将字符串中所有非蒙古文字符删除
  w.each_char do |c|
    c = "" unless c.is_mongolian?
    new_w = new_w + c
  end
  return new_w.split
end

#mon_vowel_harmony ⇒ Object

测试单词是否符合元音和谐律，并判断词性 参考P87 返回值 0：错误，不符合元音和谐律，外来词、双词根词或者拼写错误返回值 1：正确，且为阳性词返回值 10：阳性词，但有错误，第一音节出现第五元音，却在后面出现了第四元音返回值 2：正确，阴性词返回值 20：阴性词，但有错误，第一音节出现第七元音，却在后面出现了第六元音



10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
 
# File 'lib/mongolian/spellchecker.rb', line 10

def mon_vowel_harmony
  mongolian_str = self.dup.to_str
  #vowel = ["ᠠ", "ᠡ", "ᠢ", "ᠣ", "ᠤ", "ᠥ", "ᠦ"]
  if mongolian_str =~ /[ᠠᠣᠤ]/ and mongolian_str =~ /[ᠡᠥᠦ]/
    return 0
  else
    if mongolian_str =~ /[ᠠᠣᠤ]/
      #如果第一音节阳性元音为第 5 元音，却在后面出现第 4 元音，则错误
      if mongolian_str.mon_syllable_classify[0] =~ /ᠤ/ and mongolian_str[mongolian_str.mon_syllable_classify[0].size..-1] =~ /ᠣ/
        return 10
      else
        return 1
      end
    else
      #如果第一音节阳性元音为第 7 元音，却在后面出现第 6 元音，则错误
      if mongolian_str.mon_syllable_classify[0] =~ /ᠦ/ and mongolian_str[mongolian_str.mon_syllable_classify[0].size..-1] =~ /ᠥ/
        return 20
      else
        return 2
      end
    end
  end
end