stemmer4jr 0.0.1
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/LICENSE +20 -0
- data/Manifest.txt +8 -0
- data/README.txt +2 -0
- data/Rakefile +50 -0
- data/lib/libstemmer_java.jar +0 -0
- data/lib/stemmer.rb +70 -0
- data/lib/stemmer4r.jar +0 -0
- data/lib/stemmer_utf8.rb +66 -0
- metadata +55 -0
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2007 Ola Bini <ola.bini@gmail.com>
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/Manifest.txt
ADDED
data/README.txt
ADDED
data/Rakefile
ADDED
@@ -0,0 +1,50 @@
|
|
1
|
+
require 'rake'
|
2
|
+
|
3
|
+
task :default => :package
|
4
|
+
|
5
|
+
def java_classpath_arg # myriad of ways to discover JRuby classpath
|
6
|
+
"-cp " + (ENV['JRUBY_PARENT_CLASSPATH'] || ENV['JRUBY_HOME'] &&
|
7
|
+
(FileList["#{ENV['JRUBY_HOME']}/lib/*.jar"]+['lib/libstemmer_java.jar']).join(File::PATH_SEPARATOR))
|
8
|
+
end
|
9
|
+
|
10
|
+
desc "Compile the native Java code."
|
11
|
+
task :java_compile do
|
12
|
+
mkdir_p "pkg/classes"
|
13
|
+
sh "javac -target 1.4 -source 1.4 -d pkg/classes #{java_classpath_arg} #{FileList['src/java/**/*.java'].join(' ')}"
|
14
|
+
sh "jar cfm lib/stemmer4r.jar java_manifest -C pkg/classes/ ."
|
15
|
+
end
|
16
|
+
file "lib/stemmer4r.jar" => :java_compile
|
17
|
+
|
18
|
+
task :more_clean do
|
19
|
+
rm_f(FileList['lib/*.jar'] - ['lib/libstemmer_java.jar'])
|
20
|
+
end
|
21
|
+
|
22
|
+
task :clean => :more_clean
|
23
|
+
|
24
|
+
task :filelist do
|
25
|
+
puts FileList['pkg/**/*'].inspect
|
26
|
+
end
|
27
|
+
|
28
|
+
begin
|
29
|
+
MANIFEST = FileList["Manifest.txt", "README.txt",
|
30
|
+
"Rakefile", "LICENSE", "lib/**/*.rb", "lib/stemmer4r.jar", "lib/libstemmer_java.jar"]
|
31
|
+
|
32
|
+
file "Manifest.txt" => :manifest
|
33
|
+
task :manifest do
|
34
|
+
File.open("Manifest.txt", "w") {|f| MANIFEST.each {|n| f << "#{n}\n"} }
|
35
|
+
end
|
36
|
+
Rake::Task['manifest'].invoke # Always regen manifest, so Hoe has up-to-date list of files
|
37
|
+
|
38
|
+
require 'hoe'
|
39
|
+
Hoe.new("stemmer4jr", "0.0.1") do |p|
|
40
|
+
p.rubyforge_name = "jruby-extras"
|
41
|
+
p.url = "http://jruby-extras.rubyforge.org/stemmer4jr"
|
42
|
+
p.author = "Ola Bini"
|
43
|
+
p.email = "ola.bini@gmail.com"
|
44
|
+
p.summary = "JRuby version of stemmer4r"
|
45
|
+
p.description = p.paragraphs_of('README.txt', 0...1).join("\n\n")
|
46
|
+
p.extra_deps.reject!{|d| d.first == "hoe"}
|
47
|
+
end
|
48
|
+
rescue LoadError
|
49
|
+
puts "You really need Hoe installed to be able to package this gem"
|
50
|
+
end
|
Binary file
|
data/lib/stemmer.rb
ADDED
@@ -0,0 +1,70 @@
|
|
1
|
+
#
|
2
|
+
# == Stemmable module
|
3
|
+
#
|
4
|
+
# This module is automatically added to the String and Array classes when you:
|
5
|
+
#
|
6
|
+
# require 'stemmer'
|
7
|
+
#
|
8
|
+
# It adds a +stem+ method to String and Array.
|
9
|
+
#
|
10
|
+
# str = 'this is a string'
|
11
|
+
#
|
12
|
+
# stemmed_str = str.stem
|
13
|
+
#
|
14
|
+
# array = %w{this is an array}
|
15
|
+
#
|
16
|
+
# stemmed_array = array.stem
|
17
|
+
#
|
18
|
+
# By default, stemming occurs in english. If you want to stem in another language, just give it as a parameter:
|
19
|
+
#
|
20
|
+
# str = 'Chaîne de caractères française'
|
21
|
+
#
|
22
|
+
# stemmed_str = str.stem('fr')
|
23
|
+
#
|
24
|
+
# Or you can change the default configuration:
|
25
|
+
#
|
26
|
+
# Stemmable::stemmer_default_language = 'fr'
|
27
|
+
#
|
28
|
+
# stemmed_str = str.stem
|
29
|
+
#
|
30
|
+
module Stemmable
|
31
|
+
begin
|
32
|
+
require 'rubygems'
|
33
|
+
gem 'stemmer4jr'
|
34
|
+
ensure
|
35
|
+
require 'stemmer4r'
|
36
|
+
end
|
37
|
+
|
38
|
+
@@stemmer_default_language = 'en'
|
39
|
+
@@stemmer = Stemmer.new('en')
|
40
|
+
@@UTF8_MAP = {
|
41
|
+
'fr' => 'iso-8859-1'
|
42
|
+
}
|
43
|
+
|
44
|
+
def Stemmable.stemmer_default_language=(language)
|
45
|
+
@@stemmer_default_language = language
|
46
|
+
@@stemmer = Stemmer.new(language)
|
47
|
+
language
|
48
|
+
end
|
49
|
+
|
50
|
+
def Stemmable.stemmer_default_language
|
51
|
+
return @@stemmer_default_language
|
52
|
+
end
|
53
|
+
|
54
|
+
def stem(language = nil)
|
55
|
+
if (language.nil?)
|
56
|
+
@@stemmer.stem(self)
|
57
|
+
else
|
58
|
+
stemmer = Stemmer.new(language)
|
59
|
+
stemmer.stem(self)
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
63
|
+
|
64
|
+
class String
|
65
|
+
include Stemmable
|
66
|
+
end
|
67
|
+
|
68
|
+
class Array
|
69
|
+
include Stemmable
|
70
|
+
end
|
data/lib/stemmer4r.jar
ADDED
Binary file
|
data/lib/stemmer_utf8.rb
ADDED
@@ -0,0 +1,66 @@
|
|
1
|
+
#
|
2
|
+
# == Stemmable_utf8 module
|
3
|
+
#
|
4
|
+
# This module is automatically added to the String and Array classes when you:
|
5
|
+
#
|
6
|
+
# require 'stemmer_utf8'
|
7
|
+
#
|
8
|
+
# It adds a +stem_utf8+ method to String and Array.
|
9
|
+
#
|
10
|
+
# str_utf8 = 'this is a UTF-8 encoded string'
|
11
|
+
#
|
12
|
+
# stemmed_str_utf8 = str_utf8.stem_utf8
|
13
|
+
#
|
14
|
+
# array_utf8 = %w{this is an array with utf8 caracters}
|
15
|
+
#
|
16
|
+
# stemmed_array_utf8 = array_utf8.stem_utf8
|
17
|
+
#
|
18
|
+
# By default, stemming occurs in english. If you want to stem in another language, just give it as a parameter:
|
19
|
+
#
|
20
|
+
# str_utf8 = 'Cha�ne de caract�res fran�aise en UTF-8'
|
21
|
+
#
|
22
|
+
# stemmed_str_utf8 = str.stem_utf8('fr')
|
23
|
+
#
|
24
|
+
# Or you can change the default configuration:
|
25
|
+
#
|
26
|
+
# Stemmable::stemmer_default_language = 'fr'
|
27
|
+
#
|
28
|
+
# stemmed_str_utf8 = str_utf8.stem_utf8
|
29
|
+
#
|
30
|
+
module Stemmable_utf8
|
31
|
+
include Stemmable
|
32
|
+
|
33
|
+
def stem_utf8(language = nil)
|
34
|
+
require 'iconv'
|
35
|
+
if (language.nil?)
|
36
|
+
language = @@stemmer_default_language
|
37
|
+
stemmer = @@stemmer
|
38
|
+
else
|
39
|
+
stemmer = Stemmer.new(language)
|
40
|
+
end
|
41
|
+
language_encoding = @@UTF8_MAP[language] || 'iso-8859-1'
|
42
|
+
if self.is_a?(String)
|
43
|
+
Iconv.new('utf-8', language_encoding).iconv(stemmer.stem(Iconv.new(language_encoding, 'utf-8').iconv(self)))
|
44
|
+
elsif self.is_a?(Array)
|
45
|
+
temp = []
|
46
|
+
output = []
|
47
|
+
Iconv.open(language_encoding, 'utf-8') do |cd|
|
48
|
+
self.each { |s| temp << cd.iconv(s) + cd.iconv(nil) }
|
49
|
+
end
|
50
|
+
Iconv.open('utf-8', language_encoding) do |cd|
|
51
|
+
stemmer.stem(temp).each { |s| output << cd.iconv(s) + cd.iconv(nil) }
|
52
|
+
end
|
53
|
+
output
|
54
|
+
else
|
55
|
+
raise 'no valid type'
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
59
|
+
|
60
|
+
class String
|
61
|
+
include Stemmable_utf8
|
62
|
+
end
|
63
|
+
|
64
|
+
class Array
|
65
|
+
include Stemmable_utf8
|
66
|
+
end
|
metadata
ADDED
@@ -0,0 +1,55 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
required_ruby_version: !ruby/object:Gem::Version::Requirement
|
3
|
+
requirements:
|
4
|
+
- - '>'
|
5
|
+
- !ruby/object:Gem::Version
|
6
|
+
version: 0.0.0
|
7
|
+
version:
|
8
|
+
email: ola.bini@gmail.com
|
9
|
+
cert_chain:
|
10
|
+
summary: JRuby version of stemmer4r
|
11
|
+
post_install_message:
|
12
|
+
homepage: http://jruby-extras.rubyforge.org/stemmer4jr
|
13
|
+
extra_rdoc_files: []
|
14
|
+
signing_key:
|
15
|
+
name: stemmer4jr
|
16
|
+
rdoc_options: []
|
17
|
+
rubyforge_project: jruby-extras
|
18
|
+
autorequire:
|
19
|
+
executables: []
|
20
|
+
description: Stemmer4Jr
|
21
|
+
default_executable:
|
22
|
+
files:
|
23
|
+
- Manifest.txt
|
24
|
+
- README.txt
|
25
|
+
- Rakefile
|
26
|
+
- LICENSE
|
27
|
+
- lib/stemmer.rb
|
28
|
+
- lib/stemmer_utf8.rb
|
29
|
+
- lib/stemmer4r.jar
|
30
|
+
- lib/libstemmer_java.jar
|
31
|
+
specification_version: 1
|
32
|
+
extensions: []
|
33
|
+
rubygems_version: 0.9.1
|
34
|
+
requirements: []
|
35
|
+
authors:
|
36
|
+
- Ola Bini
|
37
|
+
platform: ruby
|
38
|
+
date: 2007-04-24 22:00:00 +00:00
|
39
|
+
require_paths:
|
40
|
+
- lib
|
41
|
+
version: !ruby/object:Gem::Version
|
42
|
+
version: 0.0.1
|
43
|
+
test_files: []
|
44
|
+
bindir: bin
|
45
|
+
dependencies:
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
version_requirements: !ruby/object:Gem::Version::Requirement
|
48
|
+
requirements:
|
49
|
+
- - '>='
|
50
|
+
- !ruby/object:Gem::Version
|
51
|
+
version: 1.2.0
|
52
|
+
version:
|
53
|
+
version_requirement:
|
54
|
+
name: hoe
|
55
|
+
has_rdoc: true
|