uea-stemmer 0.9.11 → 0.10.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/VERSION +1 -1
- data/lib/uea-stemmer.rb +9 -6
- data/uea-stemmer.gemspec +2 -2
- metadata +2 -2
data/VERSION
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
0.
|
|
1
|
+
0.10.0
|
data/lib/uea-stemmer.rb
CHANGED
|
@@ -27,11 +27,12 @@ class UEAStemmer
|
|
|
27
27
|
include StringHelpers
|
|
28
28
|
|
|
29
29
|
attr_accessor :max_acronym_length, :max_word_length
|
|
30
|
-
attr_reader :rules
|
|
30
|
+
attr_reader :rules, :options
|
|
31
31
|
|
|
32
|
-
def initialize(max_word_length = nil, max_acronym_length = nil)
|
|
32
|
+
def initialize(max_word_length = nil, max_acronym_length = nil, options = {})
|
|
33
33
|
@max_word_length = max_word_length || 'deoxyribonucleicacid'.size
|
|
34
34
|
@max_acronym_length = max_acronym_length || 'CAVASSOO'.size
|
|
35
|
+
@options = options.dup
|
|
35
36
|
|
|
36
37
|
@rules = Array.new
|
|
37
38
|
create_rules
|
|
@@ -54,10 +55,12 @@ class UEAStemmer
|
|
|
54
55
|
stemmed_word = remove_suffix(stemmed_word, 1)
|
|
55
56
|
end
|
|
56
57
|
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
|
|
58
|
+
unless options[:skip_contractions]
|
|
59
|
+
stemmed_word.gsub!(/n't/, ' not')
|
|
60
|
+
stemmed_word.gsub!(/'ve/, ' have')
|
|
61
|
+
stemmed_word.gsub!(/'re/, ' are')
|
|
62
|
+
stemmed_word.gsub!(/'m/, ' am')
|
|
63
|
+
end
|
|
61
64
|
|
|
62
65
|
Word.new(stemmed_word, 93)
|
|
63
66
|
else
|
data/uea-stemmer.gemspec
CHANGED
|
@@ -5,11 +5,11 @@
|
|
|
5
5
|
|
|
6
6
|
Gem::Specification.new do |s|
|
|
7
7
|
s.name = %q{uea-stemmer}
|
|
8
|
-
s.version = "0.
|
|
8
|
+
s.version = "0.10.0"
|
|
9
9
|
|
|
10
10
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
|
11
11
|
s.authors = ["Marie-Claire Jenkins", "Dan J. Smith", "Richard Churchill", "Jason Adams"]
|
|
12
|
-
s.date = %q{2009-10-
|
|
12
|
+
s.date = %q{2009-10-13}
|
|
13
13
|
s.description = %q{Port of UEA-Lite Stemmer to Ruby, a conservative stemmer for search and indexing.}
|
|
14
14
|
s.email = %q{jasonmadams@gmail.com}
|
|
15
15
|
s.extra_rdoc_files = [
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: uea-stemmer
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.10.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Marie-Claire Jenkins
|
|
@@ -12,7 +12,7 @@ autorequire:
|
|
|
12
12
|
bindir: bin
|
|
13
13
|
cert_chain: []
|
|
14
14
|
|
|
15
|
-
date: 2009-10-
|
|
15
|
+
date: 2009-10-13 00:00:00 -04:00
|
|
16
16
|
default_executable:
|
|
17
17
|
dependencies: []
|
|
18
18
|
|