Module: Emoninja::Stemmable

Included in:
String
Defined in:
lib/emoninja/porter_stemmer.rb

Overview

There are numerous strategies and algorithms for stemming. A widely-used algorithm for English stemming is the Porter stemming algorithm,

written by Martin Porter in 1980. The Porter stemmer follows a strategy
of suffix stripping, which basically uses a set of rules to strip away suffixes.

For example, a word that ends with ‘-ed’ might be suffix-stripped to remove the ‘-ed’. The Porter stemmer follows a sequence of steps in stripping suffixes.

tartarus.org/~martin/PorterStemmer/ruby.txt rubocop:disable Metrics/ModuleLength

Constant Summary collapse

STEP_2_LIST = 
{
  'ational' => 'ate', 'tional' => 'tion', 'enci' => 'ence', 'anci' => 'ance',
  'izer' => 'ize', 'bli' => 'ble',
  'alli' => 'al', 'entli' => 'ent', 'eli' => 'e', 'ousli' => 'ous',
  'ization' => 'ize', 'ation' => 'ate',
  'ator' => 'ate', 'alism' => 'al', 'iveness' => 'ive', 'fulness' => 'ful',
  'ousness' => 'ous', 'aliti' => 'al',
  'iviti' => 'ive', 'biliti' => 'ble', 'logi' => 'log'
}.freeze
STEP_3_LIST = 
{
  'icate' => 'ic', 'ative' => '', 'alize' => 'al', 'iciti' => 'ic',
  'ical' => 'ic', 'ful' => '', 'ness' => ''
}.freeze
SUFFIX_1_REGEXP = 
/(
ational  |
tional   |
enci     |
anci     |
izer     |
bli      |
alli     |
entli    |
eli      |
ousli    |
ization  |
ation    |
ator     |
alism    |
iveness  |
fulness  |
ousness  |
aliti    |
iviti    |
biliti   |
logi)$/x
SUFFIX_2_REGEXP = 
/(
al       |
ance     |
ence     |
er       |
ic       |
able     |
ible     |
ant      |
ement    |
ment     |
ent      |
ou       |
ism      |
ate      |
iti      |
ous      |
ive      |
ize)$/x
C = 
'[^aeiou]'.freeze
V = 
'[aeiouy]'.freeze
CC = 
"#{C}(?>[^aeiouy]*)".freeze
VV = 
"#{V}(?>[aeiou]*)".freeze
MGR0 =

[cc]vvcc… is m>0

/^(#{CC})?#{VV}#{CC}/o
MEQ1 =
cc]vvcc[vv

is m=1

/^(#{CC})?#{VV}#{CC}(#{VV})?$/o
MGR1 =

[cc]vvccvvcc… is m>1

/^(#{CC})?#{VV}#{CC}#{VV}#{CC}/o
VOWEL_IN_STEM =

vowel in stem

/^(#{CC})?#{V}/o

Instance Method Summary collapse

Instance Method Details

#stem_porter ⇒ Object Also known as: stem

rubocop:disable Metrics/MethodLength rubocop:disable Style/PerlBackrefs



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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
 
# File 'lib/emoninja/porter_stemmer.rb', line 97

def stem_porter
  # make a copy of the given object and convert it to a string.
  w = dup.to_str
  return w if w.length < 3

  # now map initial y to Y so that the patterns never treat it as vowel
  w[0] = 'Y' if w[0] == 'y'

  # Step 1a
  case w
  when /(ss|i)es$/ then w = $` + $1
  when /([^s])s$/  then w = $` + $1
  end

  # Step 1b
  if w =~ /eed$/
    w.chop! if $` =~ MGR0
  elsif w =~ /(ed|ing)$/
    stem = $`
    if stem =~ VOWEL_IN_STEM
      w = stem
      case w
      when /(at|bl|iz)$/             then w << 'e'
      when /([^aeiouylsz])\1$/       then w.chop!
      when /^#{CC}#{V}[^aeiouwxy]$/o then w << 'e'
      end
    end
  end

  if w =~ /y$/
    stem = $`
    w = stem + 'i' if stem =~ VOWEL_IN_STEM
  end

  # Step 2
  if w =~ SUFFIX_1_REGEXP
    stem = $`
    suffix = $1
    # print "stem= " + stem + "\n" + "suffix=" + suffix + "\n"
    w = stem + STEP_2_LIST[suffix] if stem =~ MGR0
  end

  # Step 3
  if w =~ /(icate|ative|alize|iciti|ical|ful|ness)$/
    stem = $`
    suffix = $1
    w = stem + STEP_3_LIST[suffix] if stem =~ MGR0
  end

  # Step 4
  if w =~ SUFFIX_2_REGEXP
    stem = $`
    w = stem if stem =~ MGR1
  elsif w =~ /(s|t)(ion)$/
    stem = $` + $1
    w = stem if stem =~ MGR1
  end

  #  Step 5
  if w =~ /e$/
    stem = $`
    w = stem if (stem =~ MGR1) || (stem =~ MEQ1 && stem !~ /^#{CC}#{V}[^aeiouwxy]$/o)
  end

  w.chop! if w =~ /ll$/ && w =~ MGR1

  # and turn initial Y back to y
  w[0] = 'y' if w[0] == 'Y'

  w
end