semantic_extraction 0.1.0
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/.document +5 -0
- data/.gitignore +21 -0
- data/LICENSE +20 -0
- data/README.rdoc +37 -0
- data/Rakefile +55 -0
- data/VERSION +1 -0
- data/lib/semantic_extraction/extractors/alchemy.rb +41 -0
- data/lib/semantic_extraction/extractors/yahoo.rb +19 -0
- data/lib/semantic_extraction.rb +73 -0
- data/semantic_extraction.gemspec +65 -0
- data/test/helper.rb +10 -0
- data/test/test_semantic_extraction.rb +7 -0
- metadata +122 -0
data/.document
ADDED
data/.gitignore
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 Chris Vannoy
|
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/README.rdoc
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
= semantic_extraction
|
2
|
+
|
3
|
+
Extract meaningful information from unstructured text with Ruby.
|
4
|
+
|
5
|
+
Using a variety of APIs (Yahoo Term Extractor and Alchemy are currently supported), semantic_extraction can automatically return a collection of keywords for an arbitrary block of text. If you use Alchemy, it can also return named entities.
|
6
|
+
|
7
|
+
== The APIs in use
|
8
|
+
|
9
|
+
* [Yahoo Term Extractor](http://developer.yahoo.com/search/content/V1/termExtraction.html)
|
10
|
+
|
11
|
+
* [Alchemy API](http://www.alchemyapi.com/api/)
|
12
|
+
|
13
|
+
== Upcoming To-Dos
|
14
|
+
|
15
|
+
* Add support for [OpenCalais](http://www.opencalais.com/documentation/opencalais-documentation)
|
16
|
+
|
17
|
+
* Flesh out the rest of the Alchemy API
|
18
|
+
|
19
|
+
* Make it possible to dynamically pick with API to use (so its possible to use multiple APIs in the same app)
|
20
|
+
|
21
|
+
* Make it less fugly.
|
22
|
+
|
23
|
+
* Tests, tests and more tests.
|
24
|
+
|
25
|
+
== Note on Patches/Pull Requests
|
26
|
+
|
27
|
+
* Fork the project.
|
28
|
+
* Make your feature addition or bug fix.
|
29
|
+
* Add tests for it. This is important so I don't break it in a
|
30
|
+
future version unintentionally.
|
31
|
+
* Commit, do not mess with rakefile, version, or history.
|
32
|
+
(if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
|
33
|
+
* Send me a pull request. Bonus points for topic branches.
|
34
|
+
|
35
|
+
== Copyright
|
36
|
+
|
37
|
+
Copyright (c) 2010 Chris Vannoy. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,55 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "semantic_extraction"
|
8
|
+
gem.summary = %Q{Extract meaningful information from unstructured text with Ruby}
|
9
|
+
gem.description = %Q{Using a variety of APIs (Yahoo term Extractor and Alchemy are currently supported), semantic_extraction can automatically return a collection of keywords for an arbitrary block of text. If using Alchemy, it can also return named entities.}
|
10
|
+
gem.email = "chris@chrisvannoy.com"
|
11
|
+
gem.homepage = "http://github.com/dummied/semantic_extraction"
|
12
|
+
gem.authors = ["Chris Vannoy"]
|
13
|
+
gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
|
14
|
+
gem.add_dependency "ruby_tubesday"
|
15
|
+
gem.add_dependency "nokogiri"
|
16
|
+
gem.add_dependency "extlib"
|
17
|
+
end
|
18
|
+
Jeweler::GemcutterTasks.new
|
19
|
+
rescue LoadError
|
20
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
21
|
+
end
|
22
|
+
|
23
|
+
require 'rake/testtask'
|
24
|
+
Rake::TestTask.new(:test) do |test|
|
25
|
+
test.libs << 'lib' << 'test'
|
26
|
+
test.pattern = 'test/**/test_*.rb'
|
27
|
+
test.verbose = true
|
28
|
+
end
|
29
|
+
|
30
|
+
begin
|
31
|
+
require 'rcov/rcovtask'
|
32
|
+
Rcov::RcovTask.new do |test|
|
33
|
+
test.libs << 'test'
|
34
|
+
test.pattern = 'test/**/test_*.rb'
|
35
|
+
test.verbose = true
|
36
|
+
end
|
37
|
+
rescue LoadError
|
38
|
+
task :rcov do
|
39
|
+
abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
task :test => :check_dependencies
|
44
|
+
|
45
|
+
task :default => :test
|
46
|
+
|
47
|
+
require 'rake/rdoctask'
|
48
|
+
Rake::RDocTask.new do |rdoc|
|
49
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
50
|
+
|
51
|
+
rdoc.rdoc_dir = 'rdoc'
|
52
|
+
rdoc.title = "semantic_extraction #{version}"
|
53
|
+
rdoc.rdoc_files.include('README*')
|
54
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
55
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.1.0
|
@@ -0,0 +1,41 @@
|
|
1
|
+
module SemanticExtraction
|
2
|
+
class Alchemy
|
3
|
+
STARTER = "http://access.alchemyapi.com/calls/"
|
4
|
+
|
5
|
+
def self.find_keywords(text)
|
6
|
+
prefix = (SemanticExtraction.is_url?(text) ? "url" : "text")
|
7
|
+
endpoint = (prefix == "url" ? "URL" : "Text") + "GetKeywords"
|
8
|
+
url = STARTER + prefix + "/" + endpoint
|
9
|
+
raw = SemanticExtraction.post(url, text, prefix, SemanticExtraction::ALCHEMY_API_KEY)
|
10
|
+
h = Nokogiri::XML(raw)
|
11
|
+
if (h/"keywords keyword")
|
12
|
+
keywords = []
|
13
|
+
(h/"keywords keyword").each do |p|
|
14
|
+
keywords << p.text
|
15
|
+
end
|
16
|
+
end
|
17
|
+
return keywords
|
18
|
+
end
|
19
|
+
|
20
|
+
def self.find_entities(text)
|
21
|
+
prefix = (SemanticExtraction.is_url?(text) ? "url" : "text")
|
22
|
+
endpoint = (prefix == "url" ? "URL" : "Text") + "GetRankedNamedEntities"
|
23
|
+
url = STARTER + prefix + "/" + endpoint
|
24
|
+
raw = SemanticExtraction.post(url, text, prefix, SemanticExtraction::ALCHEMY_API_KEY)
|
25
|
+
h = Nokogiri::XML(raw)
|
26
|
+
if (h/"entities entity")
|
27
|
+
entities = []
|
28
|
+
(h/"entities entity").each do |p|
|
29
|
+
hashie = Hash.from_xml(p.to_s)["entity"]
|
30
|
+
typer = hashie.delete("type")
|
31
|
+
if typer
|
32
|
+
hashie["entity_type"] = typer
|
33
|
+
end
|
34
|
+
entities << OpenStruct.new(hashie)
|
35
|
+
end
|
36
|
+
end
|
37
|
+
return entities
|
38
|
+
end
|
39
|
+
|
40
|
+
end
|
41
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
module SemanticExtraction
|
2
|
+
class Yahoo
|
3
|
+
STARTER = "http://api.search.yahoo.com/ContentAnalysisService/V1/termExtraction"
|
4
|
+
|
5
|
+
def self.find_keywords(text)
|
6
|
+
prefix = 'context'
|
7
|
+
raw = SemanticExtraction.post(STARTER, text, prefix, SemanticExtraction::YAHOO_API_KEY, :appid)
|
8
|
+
h = Nokogiri::XML(raw)
|
9
|
+
if (h/"Result")
|
10
|
+
keywords = []
|
11
|
+
(h/"Result").each do |p|
|
12
|
+
keywords << p.text
|
13
|
+
end
|
14
|
+
end
|
15
|
+
return keywords
|
16
|
+
end
|
17
|
+
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,73 @@
|
|
1
|
+
require 'ruby_tubesday'
|
2
|
+
require 'nokogiri'
|
3
|
+
require 'extlib'
|
4
|
+
require 'ostruct'
|
5
|
+
|
6
|
+
module SemanticExtraction
|
7
|
+
|
8
|
+
# We'll automatically require any extractors in the ./semantic_extraction/extractors directory.
|
9
|
+
# And, yes, I know there has to be a better way to handle this. Let me know before I get fed up and Google furiously.
|
10
|
+
Dir.entries("./semantic_extraction/extractors").each_with_index do |p, index|
|
11
|
+
unless [0,1].include? index
|
12
|
+
require "./semantic_extraction/extractors/" + p.sub(".rb", "")
|
13
|
+
end
|
14
|
+
end
|
15
|
+
|
16
|
+
# Thrown when you're lacking an api key for the particular api you're using.
|
17
|
+
class MissingApiKey < StandardError; end
|
18
|
+
|
19
|
+
# Thrown when the api you're using doesn't support the method you're attempting.
|
20
|
+
# This will become more important when we start mapping out all of the other features in the Alchemy API
|
21
|
+
class NotSupportedExtraction < StandardError; end
|
22
|
+
|
23
|
+
# By default, we assume you want to use Alchemy.
|
24
|
+
# To override, just set SemanticExtraction::PREFERRED_EXTRACTOR somewhere.
|
25
|
+
def self.preferred_extractor
|
26
|
+
defined?(PREFERRED_EXTRACTOR) ? PREFERRED_EXTRACTOR : "alchemy"
|
27
|
+
end
|
28
|
+
|
29
|
+
HTTP = RubyTubesday.new
|
30
|
+
|
31
|
+
# Will return an array of keywords gleaned from the text you pass in.
|
32
|
+
# Both Yahoo and Alchemy will handle a block of text, but Alchemy can also handle a plain URL.
|
33
|
+
def self.find_keywords(text)
|
34
|
+
klass = SemanticExtraction.const_get(self.preferred_extractor.capitalize)
|
35
|
+
if klass.respond_to?(:find_keywords) && defined?(self.preferred_extractor.upcase + "_API_KEY")
|
36
|
+
return klass.find_keywords(text)
|
37
|
+
elsif !klass.respond_to?(:find_keywords)
|
38
|
+
raise NotSupportedExtraction
|
39
|
+
else
|
40
|
+
raise MissingApiKey
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
# Will return an array of OpenStruct representing the named entities from the text.
|
45
|
+
# At the moment, Alchemy is the only one to support this.
|
46
|
+
# Down the road, we'll add in OpenCalais and others.
|
47
|
+
def self.find_entities(text)
|
48
|
+
klass = SemanticExtraction.const_get(self.preferred_extractor.capitalize)
|
49
|
+
if klass.respond_to?(:find_entities) && defined?(self.preferred_extractor.upcase + "_API_Key")
|
50
|
+
return klass.find_entities(text)
|
51
|
+
elsif !klass.respond_to?(:find_entities)
|
52
|
+
raise NotSupportedExtraction
|
53
|
+
else
|
54
|
+
raise MissingApiKey
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
# Posts the url to the API.
|
59
|
+
def self.post(url, target, calling_param, api_key, api_param="apikey".to_sym)
|
60
|
+
HTTP.post(url, :params => {calling_param => target, api_param => api_key} )
|
61
|
+
end
|
62
|
+
|
63
|
+
# Checks to see if a string is a URL.
|
64
|
+
# This is really dumb at the moment, and will likely be refactored in future releases.
|
65
|
+
def self.is_url?(link)
|
66
|
+
if link[0..3] == "http"
|
67
|
+
return true
|
68
|
+
else
|
69
|
+
return false
|
70
|
+
end
|
71
|
+
end
|
72
|
+
|
73
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
# Generated by jeweler
|
2
|
+
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
+
# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
|
4
|
+
# -*- encoding: utf-8 -*-
|
5
|
+
|
6
|
+
Gem::Specification.new do |s|
|
7
|
+
s.name = %q{semantic_extraction}
|
8
|
+
s.version = "0.1.0"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = ["Chris Vannoy"]
|
12
|
+
s.date = %q{2010-03-10}
|
13
|
+
s.description = %q{Using a variety of APIs (Yahoo term Extractor and Alchemy are currently supported), semantic_extraction can automatically return a collection of keywords for an arbitrary block of text. If using Alchemy, it can also return named entities.}
|
14
|
+
s.email = %q{chris@chrisvannoy.com}
|
15
|
+
s.extra_rdoc_files = [
|
16
|
+
"LICENSE",
|
17
|
+
"README.rdoc"
|
18
|
+
]
|
19
|
+
s.files = [
|
20
|
+
".document",
|
21
|
+
".gitignore",
|
22
|
+
"LICENSE",
|
23
|
+
"README.rdoc",
|
24
|
+
"Rakefile",
|
25
|
+
"VERSION",
|
26
|
+
"lib/semantic_extraction.rb",
|
27
|
+
"lib/semantic_extraction/extractors/alchemy.rb",
|
28
|
+
"lib/semantic_extraction/extractors/yahoo.rb",
|
29
|
+
"semantic_extraction.gemspec",
|
30
|
+
"test/helper.rb",
|
31
|
+
"test/test_semantic_extraction.rb"
|
32
|
+
]
|
33
|
+
s.homepage = %q{http://github.com/dummied/semantic_extraction}
|
34
|
+
s.rdoc_options = ["--charset=UTF-8"]
|
35
|
+
s.require_paths = ["lib"]
|
36
|
+
s.rubygems_version = %q{1.3.6}
|
37
|
+
s.summary = %q{Extract meaningful information from unstructured text with Ruby}
|
38
|
+
s.test_files = [
|
39
|
+
"test/helper.rb",
|
40
|
+
"test/test_semantic_extraction.rb"
|
41
|
+
]
|
42
|
+
|
43
|
+
if s.respond_to? :specification_version then
|
44
|
+
current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
|
45
|
+
s.specification_version = 3
|
46
|
+
|
47
|
+
if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
|
48
|
+
s.add_development_dependency(%q<thoughtbot-shoulda>, [">= 0"])
|
49
|
+
s.add_runtime_dependency(%q<ruby_tubesday>, [">= 0"])
|
50
|
+
s.add_runtime_dependency(%q<nokogiri>, [">= 0"])
|
51
|
+
s.add_runtime_dependency(%q<extlib>, [">= 0"])
|
52
|
+
else
|
53
|
+
s.add_dependency(%q<thoughtbot-shoulda>, [">= 0"])
|
54
|
+
s.add_dependency(%q<ruby_tubesday>, [">= 0"])
|
55
|
+
s.add_dependency(%q<nokogiri>, [">= 0"])
|
56
|
+
s.add_dependency(%q<extlib>, [">= 0"])
|
57
|
+
end
|
58
|
+
else
|
59
|
+
s.add_dependency(%q<thoughtbot-shoulda>, [">= 0"])
|
60
|
+
s.add_dependency(%q<ruby_tubesday>, [">= 0"])
|
61
|
+
s.add_dependency(%q<nokogiri>, [">= 0"])
|
62
|
+
s.add_dependency(%q<extlib>, [">= 0"])
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
data/test/helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,122 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: semantic_extraction
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease: false
|
5
|
+
segments:
|
6
|
+
- 0
|
7
|
+
- 1
|
8
|
+
- 0
|
9
|
+
version: 0.1.0
|
10
|
+
platform: ruby
|
11
|
+
authors:
|
12
|
+
- Chris Vannoy
|
13
|
+
autorequire:
|
14
|
+
bindir: bin
|
15
|
+
cert_chain: []
|
16
|
+
|
17
|
+
date: 2010-03-10 00:00:00 -05:00
|
18
|
+
default_executable:
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
name: thoughtbot-shoulda
|
22
|
+
prerelease: false
|
23
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
24
|
+
requirements:
|
25
|
+
- - ">="
|
26
|
+
- !ruby/object:Gem::Version
|
27
|
+
segments:
|
28
|
+
- 0
|
29
|
+
version: "0"
|
30
|
+
type: :development
|
31
|
+
version_requirements: *id001
|
32
|
+
- !ruby/object:Gem::Dependency
|
33
|
+
name: ruby_tubesday
|
34
|
+
prerelease: false
|
35
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
36
|
+
requirements:
|
37
|
+
- - ">="
|
38
|
+
- !ruby/object:Gem::Version
|
39
|
+
segments:
|
40
|
+
- 0
|
41
|
+
version: "0"
|
42
|
+
type: :runtime
|
43
|
+
version_requirements: *id002
|
44
|
+
- !ruby/object:Gem::Dependency
|
45
|
+
name: nokogiri
|
46
|
+
prerelease: false
|
47
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
48
|
+
requirements:
|
49
|
+
- - ">="
|
50
|
+
- !ruby/object:Gem::Version
|
51
|
+
segments:
|
52
|
+
- 0
|
53
|
+
version: "0"
|
54
|
+
type: :runtime
|
55
|
+
version_requirements: *id003
|
56
|
+
- !ruby/object:Gem::Dependency
|
57
|
+
name: extlib
|
58
|
+
prerelease: false
|
59
|
+
requirement: &id004 !ruby/object:Gem::Requirement
|
60
|
+
requirements:
|
61
|
+
- - ">="
|
62
|
+
- !ruby/object:Gem::Version
|
63
|
+
segments:
|
64
|
+
- 0
|
65
|
+
version: "0"
|
66
|
+
type: :runtime
|
67
|
+
version_requirements: *id004
|
68
|
+
description: Using a variety of APIs (Yahoo term Extractor and Alchemy are currently supported), semantic_extraction can automatically return a collection of keywords for an arbitrary block of text. If using Alchemy, it can also return named entities.
|
69
|
+
email: chris@chrisvannoy.com
|
70
|
+
executables: []
|
71
|
+
|
72
|
+
extensions: []
|
73
|
+
|
74
|
+
extra_rdoc_files:
|
75
|
+
- LICENSE
|
76
|
+
- README.rdoc
|
77
|
+
files:
|
78
|
+
- .document
|
79
|
+
- .gitignore
|
80
|
+
- LICENSE
|
81
|
+
- README.rdoc
|
82
|
+
- Rakefile
|
83
|
+
- VERSION
|
84
|
+
- lib/semantic_extraction.rb
|
85
|
+
- lib/semantic_extraction/extractors/alchemy.rb
|
86
|
+
- lib/semantic_extraction/extractors/yahoo.rb
|
87
|
+
- semantic_extraction.gemspec
|
88
|
+
- test/helper.rb
|
89
|
+
- test/test_semantic_extraction.rb
|
90
|
+
has_rdoc: true
|
91
|
+
homepage: http://github.com/dummied/semantic_extraction
|
92
|
+
licenses: []
|
93
|
+
|
94
|
+
post_install_message:
|
95
|
+
rdoc_options:
|
96
|
+
- --charset=UTF-8
|
97
|
+
require_paths:
|
98
|
+
- lib
|
99
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - ">="
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
segments:
|
104
|
+
- 0
|
105
|
+
version: "0"
|
106
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ">="
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
segments:
|
111
|
+
- 0
|
112
|
+
version: "0"
|
113
|
+
requirements: []
|
114
|
+
|
115
|
+
rubyforge_project:
|
116
|
+
rubygems_version: 1.3.6
|
117
|
+
signing_key:
|
118
|
+
specification_version: 3
|
119
|
+
summary: Extract meaningful information from unstructured text with Ruby
|
120
|
+
test_files:
|
121
|
+
- test/helper.rb
|
122
|
+
- test/test_semantic_extraction.rb
|