minimal_stemmer 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/lib/minimal_stemmer.rb +20 -0
- data/lib/minimal_stemmer/core_ext/string.rb +7 -0
- data/spec/core_ext/string_spec.rb +11 -0
- data/spec/minimal_stemmer_spec.rb +83 -0
- data/spec/spec_helper.rb +13 -0
- metadata +93 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 05ce713c36de06617c3507310ee3ffd09e1a790d
|
4
|
+
data.tar.gz: 52db46c24a2c4f3903245593b140acbee77c7298
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: bfc7b9bf4fbe4ae2bc8d67c2e2df80cf89327e0751186959f956440328c65e004ef7a1b8264d704dd1d77e7078fd417480a4eb27044c16482596c4752d5ad963
|
7
|
+
data.tar.gz: 2b93575a0f2524b327ea387aae0c9052493705489579fdf134473065f680df8f303cc8b7c1530e6fa83d7be8d09fcee3040fd2e112876d0437df0f19aabd55fa
|
@@ -0,0 +1,20 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
# Simple implementation of the "S-Stemmer" (aka English minimal stemmer).
|
4
|
+
class MinimalStemmer
|
5
|
+
class << self
|
6
|
+
# Stem a word.
|
7
|
+
#
|
8
|
+
# @param [String] word the word to stem
|
9
|
+
# @return [String] the stemmed word
|
10
|
+
def stem(word)
|
11
|
+
if %w(aies eies aes ees oes ss us).any? { |s| word.end_with?(s) }
|
12
|
+
return word
|
13
|
+
end
|
14
|
+
|
15
|
+
word.sub(/ies\z/, 'y')
|
16
|
+
.sub(/es\z/, 'e')
|
17
|
+
.sub(/s\z/, '')
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,83 @@
|
|
1
|
+
require_relative './spec_helper'
|
2
|
+
|
3
|
+
describe MinimalStemmer do
|
4
|
+
describe '.stem' do
|
5
|
+
context 'word ending in "ies"' do
|
6
|
+
it 'stems to a "y"' do
|
7
|
+
expect(MinimalStemmer.stem('tries')).to eq('try')
|
8
|
+
end
|
9
|
+
|
10
|
+
context 'ending in "eies"' do
|
11
|
+
it 'does not stem' do
|
12
|
+
expect(MinimalStemmer.stem('neies')).to eq('neies')
|
13
|
+
end
|
14
|
+
end
|
15
|
+
|
16
|
+
context 'ending in "aies"' do
|
17
|
+
it 'does not stem' do
|
18
|
+
expect(MinimalStemmer.stem('braies')).to eq('braies')
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
context 'word ending in "es"' do
|
24
|
+
it 'stems to a "e"' do
|
25
|
+
expect(MinimalStemmer.stem('cliques')).to eq('clique')
|
26
|
+
end
|
27
|
+
|
28
|
+
context 'ending in "aes"' do
|
29
|
+
it 'does not stem' do
|
30
|
+
expect(MinimalStemmer.stem('sundaes')).to eq('sundaes')
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
context 'ending in "ees"' do
|
35
|
+
it 'does not stem' do
|
36
|
+
expect(MinimalStemmer.stem('trustees')).to eq('trustees')
|
37
|
+
end
|
38
|
+
end
|
39
|
+
|
40
|
+
context 'ending in "oes"' do
|
41
|
+
it 'does not stem' do
|
42
|
+
expect(MinimalStemmer.stem('potatoes')).to eq('potatoes')
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
46
|
+
|
47
|
+
context 'word ending in s' do
|
48
|
+
it 'strips the s' do
|
49
|
+
expect(MinimalStemmer.stem('words')).to eq('word')
|
50
|
+
end
|
51
|
+
|
52
|
+
context 'ending in "us"' do
|
53
|
+
it 'does not stem' do
|
54
|
+
expect(MinimalStemmer.stem('focus')).to eq('focus')
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
context 'ending in "ss"' do
|
59
|
+
it 'does not stem' do
|
60
|
+
expect(MinimalStemmer.stem('success')).to eq('success')
|
61
|
+
end
|
62
|
+
end
|
63
|
+
end
|
64
|
+
|
65
|
+
context 'ignored suffixes' do
|
66
|
+
it 'does not stem "ing"' do
|
67
|
+
expect(MinimalStemmer.stem('running')).to eq('running')
|
68
|
+
end
|
69
|
+
|
70
|
+
it 'does not stem "ly"' do
|
71
|
+
expect(MinimalStemmer.stem('surprisingly')).to eq('surprisingly')
|
72
|
+
end
|
73
|
+
|
74
|
+
it 'does not stem "er"' do
|
75
|
+
expect(MinimalStemmer.stem('runner')).to eq('runner')
|
76
|
+
end
|
77
|
+
|
78
|
+
it 'does not stem "ed"' do
|
79
|
+
expect(MinimalStemmer.stem('planned')).to eq('planned')
|
80
|
+
end
|
81
|
+
end
|
82
|
+
end
|
83
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
require 'bundler/setup'
|
3
|
+
require 'rspec/core'
|
4
|
+
|
5
|
+
$LOAD_PATH.push File.expand_path('../lib', File.dirname(__FILE__))
|
6
|
+
|
7
|
+
require 'minimal_stemmer'
|
8
|
+
|
9
|
+
RSpec.configure do |config|
|
10
|
+
config.expect_with :rspec do |c|
|
11
|
+
c.syntax = :expect
|
12
|
+
end
|
13
|
+
end
|
metadata
ADDED
@@ -0,0 +1,93 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: minimal_stemmer
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Paul Dlug
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-07-23 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: rake
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rspec
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '3'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '3'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: yard
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0.8'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0.8'
|
55
|
+
description: Implements the "S-Stemmer" from "How Effective Is Suffixing?"
|
56
|
+
email: paul.dlug@gmail.com
|
57
|
+
executables: []
|
58
|
+
extensions: []
|
59
|
+
extra_rdoc_files: []
|
60
|
+
files:
|
61
|
+
- lib/minimal_stemmer.rb
|
62
|
+
- lib/minimal_stemmer/core_ext/string.rb
|
63
|
+
- spec/core_ext/string_spec.rb
|
64
|
+
- spec/minimal_stemmer_spec.rb
|
65
|
+
- spec/spec_helper.rb
|
66
|
+
homepage: https://github.com/pdlug/minimal_stemmer
|
67
|
+
licenses:
|
68
|
+
- MIT
|
69
|
+
metadata: {}
|
70
|
+
post_install_message:
|
71
|
+
rdoc_options: []
|
72
|
+
require_paths:
|
73
|
+
- lib
|
74
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
75
|
+
requirements:
|
76
|
+
- - ">="
|
77
|
+
- !ruby/object:Gem::Version
|
78
|
+
version: 1.9.3
|
79
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
80
|
+
requirements:
|
81
|
+
- - ">="
|
82
|
+
- !ruby/object:Gem::Version
|
83
|
+
version: '0'
|
84
|
+
requirements: []
|
85
|
+
rubyforge_project:
|
86
|
+
rubygems_version: 2.4.6
|
87
|
+
signing_key:
|
88
|
+
specification_version: 4
|
89
|
+
summary: Implementation of an English minimal stemmer
|
90
|
+
test_files:
|
91
|
+
- spec/core_ext/string_spec.rb
|
92
|
+
- spec/minimal_stemmer_spec.rb
|
93
|
+
- spec/spec_helper.rb
|