semantic_extraction 0.1.1 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +11 -7
- data/Rakefile +2 -1
- data/VERSION +1 -1
- data/lib/semantic_extraction.rb +38 -36
- data/lib/semantic_extraction/extractors/alchemy.rb +37 -20
- data/lib/semantic_extraction/extractors/yahoo.rb +11 -8
- data/lib/semantic_extraction/utility_methods.rb +26 -0
- data/semantic_extraction.gemspec +16 -8
- data/test/api_extractor.rb +17 -0
- data/test/our_extractor.rb +12 -0
- data/test/test_semantic_extraction.rb +25 -2
- metadata +42 -10
data/README.rdoc
CHANGED
@@ -4,22 +4,26 @@ Extract meaningful information from unstructured text with Ruby.
|
|
4
4
|
|
5
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
6
|
|
7
|
+
A brief walkthrough:
|
8
|
+
|
9
|
+
$ require 'rubygems'
|
10
|
+
$ require 'semantic_extraction'
|
11
|
+
$ SemanticExtraction.alchemy_api_key = 'YOUR_API_KEY_HERE'
|
12
|
+
$ SemanticExtraction.find_keywords("http://chrisvannoy.com/2010/03/10/introducing_semantic_extraction/")
|
13
|
+
$ ["Knight News Challenge", "Yahoo Term Extractor", "obscure gem", "soon-to-be twitter employee", "handle serving gems", "API providers", "Alchemy API", "unstructured text", "earliest steps", "Rails 3-compatible version", "structured data", "early stage", "death threats", "github", "final aside", "awesome piece", "default choice", "HTTP communication", "Indianapolis Star", "Feel free"]
|
14
|
+
|
7
15
|
== The APIs in use
|
8
16
|
|
9
|
-
*
|
17
|
+
* {Yahoo Term Extractor}[http://developer.yahoo.com/search/content/V1/termExtraction.html]
|
10
18
|
|
11
|
-
*
|
19
|
+
* {Alchemy API}[http://www.alchemyapi.com/api/]
|
12
20
|
|
13
21
|
== Upcoming To-Dos
|
14
22
|
|
15
|
-
* Add support for [
|
23
|
+
* Add support for {OpenCalais}[http://www.opencalais.com/documentation/opencalais-documentation]
|
16
24
|
|
17
25
|
* Flesh out the rest of the Alchemy API
|
18
26
|
|
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
27
|
* Tests, tests and more tests.
|
24
28
|
|
25
29
|
== Note on Patches/Pull Requests
|
data/Rakefile
CHANGED
@@ -10,7 +10,8 @@ begin
|
|
10
10
|
gem.email = "chris@chrisvannoy.com"
|
11
11
|
gem.homepage = "http://github.com/dummied/semantic_extraction"
|
12
12
|
gem.authors = ["Chris Vannoy"]
|
13
|
-
gem.add_development_dependency "
|
13
|
+
gem.add_development_dependency "shoulda", ">= 0"
|
14
|
+
gem.add_development_dependency "fakeweb"
|
14
15
|
gem.add_dependency "ruby_tubesday"
|
15
16
|
gem.add_dependency "nokogiri"
|
16
17
|
gem.add_dependency "extlib"
|
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.
|
1
|
+
0.2.0
|
data/lib/semantic_extraction.rb
CHANGED
@@ -2,10 +2,35 @@ require 'ruby_tubesday'
|
|
2
2
|
require 'nokogiri'
|
3
3
|
require 'extlib'
|
4
4
|
require 'ostruct'
|
5
|
+
require 'active_support/core_ext/module/attribute_accessors'
|
5
6
|
|
6
7
|
module SemanticExtraction
|
7
8
|
|
9
|
+
|
10
|
+
mattr_accessor :preferred_extractor
|
11
|
+
mattr_accessor :alchemy_api_key
|
12
|
+
mattr_accessor :yahoo_api_key
|
13
|
+
mattr_accessor :valid_extractors
|
14
|
+
mattr_accessor :requires_api_key
|
15
|
+
|
16
|
+
self.valid_extractors = ["yahoo", "alchemy"]
|
17
|
+
self.requires_api_key = ["yahoo", "alchemy"]
|
18
|
+
|
19
|
+
# By default, we assume you want to use Alchemy.
|
20
|
+
# To override, just set SemanticExtraction.preferred_extractor somewhere and define the appropriate api_key.
|
21
|
+
def self.preferred_extractor=(value)
|
22
|
+
if self.valid_extractors.include?(value)
|
23
|
+
@@preferred_extractor = value
|
24
|
+
else
|
25
|
+
raise NotSupportedExtractor
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
self.preferred_extractor = "alchemy" if self.preferred_extractor.blank?
|
30
|
+
|
31
|
+
|
8
32
|
# Screw it. Hard-code time!
|
33
|
+
require 'semantic_extraction/utility_methods'
|
9
34
|
require 'semantic_extraction/extractors/yahoo'
|
10
35
|
require 'semantic_extraction/extractors/alchemy'
|
11
36
|
|
@@ -16,53 +41,30 @@ module SemanticExtraction
|
|
16
41
|
# This will become more important when we start mapping out all of the other features in the Alchemy API
|
17
42
|
class NotSupportedExtraction < StandardError; end
|
18
43
|
|
19
|
-
#
|
20
|
-
|
21
|
-
def self.preferred_extractor
|
22
|
-
defined?(PREFERRED_EXTRACTOR) ? PREFERRED_EXTRACTOR : "alchemy"
|
23
|
-
end
|
44
|
+
# Thrown when you attempt to set the preferred extractor to an extractor we don't yet support.
|
45
|
+
class NotSupportedExtractor < StandardError; end
|
24
46
|
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
def self.find_keywords(text)
|
30
|
-
klass = SemanticExtraction.const_get(self.preferred_extractor.capitalize)
|
31
|
-
if klass.respond_to?(:find_keywords) && defined?(self.preferred_extractor.upcase + "_API_KEY")
|
32
|
-
return klass.find_keywords(text)
|
33
|
-
elsif !klass.respond_to?(:find_keywords)
|
47
|
+
def self.find_generic(typer, args)
|
48
|
+
if self.is_valid?(typer)
|
49
|
+
return @@klass.send(typer.to_sym, args)
|
50
|
+
elsif !@@klass.respond_to?(typer.to_sym)
|
34
51
|
raise NotSupportedExtraction
|
35
52
|
else
|
36
53
|
raise MissingApiKey
|
37
54
|
end
|
38
55
|
end
|
39
56
|
|
40
|
-
|
41
|
-
|
42
|
-
# Down the road, we'll add in OpenCalais and others.
|
43
|
-
def self.find_entities(text)
|
44
|
-
klass = SemanticExtraction.const_get(self.preferred_extractor.capitalize)
|
45
|
-
if klass.respond_to?(:find_entities) && defined?(self.preferred_extractor.upcase + "_API_Key")
|
46
|
-
return klass.find_entities(text)
|
47
|
-
elsif !klass.respond_to?(:find_entities)
|
48
|
-
raise NotSupportedExtraction
|
49
|
-
else
|
50
|
-
raise MissingApiKey
|
51
|
-
end
|
57
|
+
def self.method_missing(method, args)
|
58
|
+
find_generic(method.to_sym, args)
|
52
59
|
end
|
53
60
|
|
54
|
-
# Posts the url to the API.
|
55
|
-
def self.post(url, target, calling_param, api_key, api_param="apikey".to_sym)
|
56
|
-
HTTP.post(url, :params => {calling_param => target, api_param => api_key} )
|
57
|
-
end
|
58
61
|
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
return true
|
62
|
+
def self.is_valid?(method)
|
63
|
+
@@klass = SemanticExtraction.const_get(self.preferred_extractor.gsub(/\/(.?)/) { "::#{$1.upcase}" }.gsub(/(?:^|_)(.)/) { $1.upcase })
|
64
|
+
if self.requires_api_key.include? self.preferred_extractor
|
65
|
+
(@@klass.respond_to?(method) && defined?(self.send((preferred_extractor + "_api_key").to_sym)) && !(self.send((preferred_extractor + "_api_key").to_sym)).empty?) ? true : false
|
64
66
|
else
|
65
|
-
|
67
|
+
@@klass.respond_to?(method)
|
66
68
|
end
|
67
69
|
end
|
68
70
|
|
@@ -1,41 +1,58 @@
|
|
1
1
|
module SemanticExtraction
|
2
|
-
|
2
|
+
module Alchemy
|
3
|
+
include SemanticExtraction::UtilityMethods
|
3
4
|
STARTER = "http://access.alchemyapi.com/calls/"
|
4
5
|
|
5
6
|
def self.find_keywords(text)
|
6
|
-
prefix =
|
7
|
+
prefix = is_url?(text) ? "url" : "text"
|
7
8
|
endpoint = (prefix == "url" ? "URL" : "Text") + "GetKeywords"
|
8
9
|
url = STARTER + prefix + "/" + endpoint
|
9
|
-
raw =
|
10
|
+
raw = post(url, text, prefix)
|
11
|
+
output_keywords(raw)
|
12
|
+
end
|
13
|
+
|
14
|
+
def self.output_keywords(raw)
|
10
15
|
h = Nokogiri::XML(raw)
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
keywords << p.text
|
15
|
-
end
|
16
|
+
keywords = []
|
17
|
+
(h/"keywords keyword").each do |p|
|
18
|
+
keywords << p.text
|
16
19
|
end
|
17
20
|
return keywords
|
18
21
|
end
|
19
22
|
|
20
23
|
def self.find_entities(text)
|
21
|
-
prefix =
|
24
|
+
prefix = is_url?(text) ? "url" : "text"
|
22
25
|
endpoint = (prefix == "url" ? "URL" : "Text") + "GetRankedNamedEntities"
|
23
26
|
url = STARTER + prefix + "/" + endpoint
|
24
|
-
raw =
|
27
|
+
raw = post(url, text, prefix)
|
28
|
+
output_entities(raw)
|
29
|
+
end
|
30
|
+
|
31
|
+
def self.output_entities(raw)
|
25
32
|
h = Nokogiri::XML(raw)
|
26
|
-
|
27
|
-
|
28
|
-
(
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
hashie["entity_type"] = typer
|
33
|
-
end
|
34
|
-
entities << OpenStruct.new(hashie)
|
33
|
+
entities = []
|
34
|
+
(h/"entities entity").each do |p|
|
35
|
+
hashie = Hash.from_xml(p.to_s)["entity"]
|
36
|
+
typer = hashie.delete("type")
|
37
|
+
if typer
|
38
|
+
hashie["entity_type"] = typer
|
35
39
|
end
|
40
|
+
entities << OpenStruct.new(hashie)
|
36
41
|
end
|
37
42
|
return entities
|
38
43
|
end
|
39
|
-
|
44
|
+
|
45
|
+
def self.extract_text(text)
|
46
|
+
prefix = is_url?(text) ? "url" : "html"
|
47
|
+
endpoint = (prefix == "url" ? "URL" : "HTML") + "GetText"
|
48
|
+
url = STARTER + prefix + "/" + endpoint
|
49
|
+
raw = post(url, text, prefix)
|
50
|
+
output_text(raw)
|
51
|
+
end
|
52
|
+
|
53
|
+
def self.output_text(raw)
|
54
|
+
h = Nokogiri::XML(raw)
|
55
|
+
return (h/"text").first.inner_html
|
56
|
+
end
|
40
57
|
end
|
41
58
|
end
|
@@ -1,16 +1,19 @@
|
|
1
1
|
module SemanticExtraction
|
2
|
-
|
2
|
+
module Yahoo
|
3
|
+
include SemanticExtraction::UtilityMethods
|
3
4
|
STARTER = "http://api.search.yahoo.com/ContentAnalysisService/V1/termExtraction"
|
4
|
-
|
5
|
+
|
5
6
|
def self.find_keywords(text)
|
6
7
|
prefix = 'context'
|
7
|
-
raw = SemanticExtraction.post(STARTER, text, prefix,
|
8
|
+
raw = SemanticExtraction.post(STARTER, text, prefix, :appid)
|
9
|
+
self.output_keywords(raw)
|
10
|
+
end
|
11
|
+
|
12
|
+
def self.output_keywords(raw)
|
8
13
|
h = Nokogiri::XML(raw)
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
keywords << p.text
|
13
|
-
end
|
14
|
+
keywords = []
|
15
|
+
(h/"Result").each do |p|
|
16
|
+
keywords << p.text
|
14
17
|
end
|
15
18
|
return keywords
|
16
19
|
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
module SemanticExtraction
|
2
|
+
module UtilityMethods
|
3
|
+
|
4
|
+
def self.included(includer)
|
5
|
+
includer.module_eval do
|
6
|
+
|
7
|
+
# Posts the url to the API.
|
8
|
+
def self.post(url, target, calling_param, api_param="apikey".to_sym)
|
9
|
+
RubyTubesday.new.post(url, :params => {calling_param => target, api_param => (SemanticExtraction.send((SemanticExtraction.preferred_extractor + "_api_key").to_sym))} )
|
10
|
+
end
|
11
|
+
|
12
|
+
# Checks to see if a string is a URL.
|
13
|
+
# This is really dumb at the moment, and will likely be refactored in future releases.
|
14
|
+
def self.is_url?(link)
|
15
|
+
if link[0..3] == "http"
|
16
|
+
return true
|
17
|
+
else
|
18
|
+
return false
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
|
25
|
+
end
|
26
|
+
end
|
data/semantic_extraction.gemspec
CHANGED
@@ -5,11 +5,11 @@
|
|
5
5
|
|
6
6
|
Gem::Specification.new do |s|
|
7
7
|
s.name = %q{semantic_extraction}
|
8
|
-
s.version = "0.
|
8
|
+
s.version = "0.2.0"
|
9
9
|
|
10
10
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
11
|
s.authors = ["Chris Vannoy"]
|
12
|
-
s.date = %q{2010-
|
12
|
+
s.date = %q{2010-07-06}
|
13
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
14
|
s.email = %q{chris@chrisvannoy.com}
|
15
15
|
s.extra_rdoc_files = [
|
@@ -26,17 +26,22 @@ Gem::Specification.new do |s|
|
|
26
26
|
"lib/semantic_extraction.rb",
|
27
27
|
"lib/semantic_extraction/extractors/alchemy.rb",
|
28
28
|
"lib/semantic_extraction/extractors/yahoo.rb",
|
29
|
+
"lib/semantic_extraction/utility_methods.rb",
|
29
30
|
"semantic_extraction.gemspec",
|
31
|
+
"test/api_extractor.rb",
|
30
32
|
"test/helper.rb",
|
33
|
+
"test/our_extractor.rb",
|
31
34
|
"test/test_semantic_extraction.rb"
|
32
35
|
]
|
33
36
|
s.homepage = %q{http://github.com/dummied/semantic_extraction}
|
34
37
|
s.rdoc_options = ["--charset=UTF-8"]
|
35
38
|
s.require_paths = ["lib"]
|
36
|
-
s.rubygems_version = %q{1.3.
|
39
|
+
s.rubygems_version = %q{1.3.7}
|
37
40
|
s.summary = %q{Extract meaningful information from unstructured text with Ruby}
|
38
41
|
s.test_files = [
|
39
|
-
"test/
|
42
|
+
"test/api_extractor.rb",
|
43
|
+
"test/helper.rb",
|
44
|
+
"test/our_extractor.rb",
|
40
45
|
"test/test_semantic_extraction.rb"
|
41
46
|
]
|
42
47
|
|
@@ -44,19 +49,22 @@ Gem::Specification.new do |s|
|
|
44
49
|
current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
|
45
50
|
s.specification_version = 3
|
46
51
|
|
47
|
-
if Gem::Version.new(Gem::
|
48
|
-
s.add_development_dependency(%q<
|
52
|
+
if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
|
53
|
+
s.add_development_dependency(%q<shoulda>, [">= 0"])
|
54
|
+
s.add_development_dependency(%q<fakeweb>, [">= 0"])
|
49
55
|
s.add_runtime_dependency(%q<ruby_tubesday>, [">= 0"])
|
50
56
|
s.add_runtime_dependency(%q<nokogiri>, [">= 0"])
|
51
57
|
s.add_runtime_dependency(%q<extlib>, [">= 0"])
|
52
58
|
else
|
53
|
-
s.add_dependency(%q<
|
59
|
+
s.add_dependency(%q<shoulda>, [">= 0"])
|
60
|
+
s.add_dependency(%q<fakeweb>, [">= 0"])
|
54
61
|
s.add_dependency(%q<ruby_tubesday>, [">= 0"])
|
55
62
|
s.add_dependency(%q<nokogiri>, [">= 0"])
|
56
63
|
s.add_dependency(%q<extlib>, [">= 0"])
|
57
64
|
end
|
58
65
|
else
|
59
|
-
s.add_dependency(%q<
|
66
|
+
s.add_dependency(%q<shoulda>, [">= 0"])
|
67
|
+
s.add_dependency(%q<fakeweb>, [">= 0"])
|
60
68
|
s.add_dependency(%q<ruby_tubesday>, [">= 0"])
|
61
69
|
s.add_dependency(%q<nokogiri>, [">= 0"])
|
62
70
|
s.add_dependency(%q<extlib>, [">= 0"])
|
@@ -0,0 +1,17 @@
|
|
1
|
+
module SemanticExtraction
|
2
|
+
module ApiExtractor
|
3
|
+
include SemanticExtraction::UtilityMethods
|
4
|
+
|
5
|
+
SemanticExtraction.valid_extractors << "api_extractor"
|
6
|
+
SemanticExtraction.requires_api_key << "api_extractor"
|
7
|
+
|
8
|
+
SemanticExtraction.module_eval("mattr_accessor :api_extractor_api_key")
|
9
|
+
|
10
|
+
SemanticExtraction.api_extractor_api_key = "bogus"
|
11
|
+
|
12
|
+
def self.find_keywords(text)
|
13
|
+
return []
|
14
|
+
end
|
15
|
+
|
16
|
+
end
|
17
|
+
end
|
@@ -1,7 +1,30 @@
|
|
1
1
|
require 'helper'
|
2
|
+
require 'our_extractor'
|
3
|
+
require 'api_extractor'
|
2
4
|
|
3
5
|
class TestSemanticExtraction < Test::Unit::TestCase
|
4
|
-
should "
|
5
|
-
|
6
|
+
should "correctly identify a url in is_url?" do
|
7
|
+
assert_equal SemanticExtraction.is_url?("http://www.indystar.com"), true
|
8
|
+
assert_equal SemanticExtraction.is_url?("I am a cheeky monkey"), false
|
6
9
|
end
|
10
|
+
|
11
|
+
should "throw error when trying to set an invalid extractor" do
|
12
|
+
begin
|
13
|
+
SemanticExtraction.preferred_extractor = "bullshit"
|
14
|
+
rescue StandardError => err
|
15
|
+
assert_equal err.class.to_s, "SemanticExtraction::NotSupportedExtractor"
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
should "be able to define new extractors without api keys" do
|
20
|
+
SemanticExtraction.preferred_extractor = "our_extractor"
|
21
|
+
assert_equal true, SemanticExtraction.is_valid?(:find_keywords)
|
22
|
+
end
|
23
|
+
|
24
|
+
should "be able to define new extractors with api keys" do
|
25
|
+
SemanticExtraction.preferred_extractor = "api_extractor"
|
26
|
+
assert_equal true, SemanticExtraction.requires_api_key.include?("api_extractor")
|
27
|
+
assert_equal true, SemanticExtraction.is_valid?(:find_keywords)
|
28
|
+
end
|
29
|
+
|
7
30
|
end
|
metadata
CHANGED
@@ -1,12 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: semantic_extraction
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
+
hash: 23
|
4
5
|
prerelease: false
|
5
6
|
segments:
|
6
7
|
- 0
|
7
|
-
-
|
8
|
-
-
|
9
|
-
version: 0.
|
8
|
+
- 2
|
9
|
+
- 0
|
10
|
+
version: 0.2.0
|
10
11
|
platform: ruby
|
11
12
|
authors:
|
12
13
|
- Chris Vannoy
|
@@ -14,57 +15,79 @@ autorequire:
|
|
14
15
|
bindir: bin
|
15
16
|
cert_chain: []
|
16
17
|
|
17
|
-
date: 2010-
|
18
|
+
date: 2010-07-06 00:00:00 -04:00
|
18
19
|
default_executable:
|
19
20
|
dependencies:
|
20
21
|
- !ruby/object:Gem::Dependency
|
21
|
-
name:
|
22
|
+
name: shoulda
|
22
23
|
prerelease: false
|
23
24
|
requirement: &id001 !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
24
26
|
requirements:
|
25
27
|
- - ">="
|
26
28
|
- !ruby/object:Gem::Version
|
29
|
+
hash: 3
|
27
30
|
segments:
|
28
31
|
- 0
|
29
32
|
version: "0"
|
30
33
|
type: :development
|
31
34
|
version_requirements: *id001
|
32
35
|
- !ruby/object:Gem::Dependency
|
33
|
-
name:
|
36
|
+
name: fakeweb
|
34
37
|
prerelease: false
|
35
38
|
requirement: &id002 !ruby/object:Gem::Requirement
|
39
|
+
none: false
|
36
40
|
requirements:
|
37
41
|
- - ">="
|
38
42
|
- !ruby/object:Gem::Version
|
43
|
+
hash: 3
|
39
44
|
segments:
|
40
45
|
- 0
|
41
46
|
version: "0"
|
42
|
-
type: :
|
47
|
+
type: :development
|
43
48
|
version_requirements: *id002
|
44
49
|
- !ruby/object:Gem::Dependency
|
45
|
-
name:
|
50
|
+
name: ruby_tubesday
|
46
51
|
prerelease: false
|
47
52
|
requirement: &id003 !ruby/object:Gem::Requirement
|
53
|
+
none: false
|
48
54
|
requirements:
|
49
55
|
- - ">="
|
50
56
|
- !ruby/object:Gem::Version
|
57
|
+
hash: 3
|
51
58
|
segments:
|
52
59
|
- 0
|
53
60
|
version: "0"
|
54
61
|
type: :runtime
|
55
62
|
version_requirements: *id003
|
56
63
|
- !ruby/object:Gem::Dependency
|
57
|
-
name:
|
64
|
+
name: nokogiri
|
58
65
|
prerelease: false
|
59
66
|
requirement: &id004 !ruby/object:Gem::Requirement
|
67
|
+
none: false
|
60
68
|
requirements:
|
61
69
|
- - ">="
|
62
70
|
- !ruby/object:Gem::Version
|
71
|
+
hash: 3
|
63
72
|
segments:
|
64
73
|
- 0
|
65
74
|
version: "0"
|
66
75
|
type: :runtime
|
67
76
|
version_requirements: *id004
|
77
|
+
- !ruby/object:Gem::Dependency
|
78
|
+
name: extlib
|
79
|
+
prerelease: false
|
80
|
+
requirement: &id005 !ruby/object:Gem::Requirement
|
81
|
+
none: false
|
82
|
+
requirements:
|
83
|
+
- - ">="
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
hash: 3
|
86
|
+
segments:
|
87
|
+
- 0
|
88
|
+
version: "0"
|
89
|
+
type: :runtime
|
90
|
+
version_requirements: *id005
|
68
91
|
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
92
|
email: chris@chrisvannoy.com
|
70
93
|
executables: []
|
@@ -84,8 +107,11 @@ files:
|
|
84
107
|
- lib/semantic_extraction.rb
|
85
108
|
- lib/semantic_extraction/extractors/alchemy.rb
|
86
109
|
- lib/semantic_extraction/extractors/yahoo.rb
|
110
|
+
- lib/semantic_extraction/utility_methods.rb
|
87
111
|
- semantic_extraction.gemspec
|
112
|
+
- test/api_extractor.rb
|
88
113
|
- test/helper.rb
|
114
|
+
- test/our_extractor.rb
|
89
115
|
- test/test_semantic_extraction.rb
|
90
116
|
has_rdoc: true
|
91
117
|
homepage: http://github.com/dummied/semantic_extraction
|
@@ -97,26 +123,32 @@ rdoc_options:
|
|
97
123
|
require_paths:
|
98
124
|
- lib
|
99
125
|
required_ruby_version: !ruby/object:Gem::Requirement
|
126
|
+
none: false
|
100
127
|
requirements:
|
101
128
|
- - ">="
|
102
129
|
- !ruby/object:Gem::Version
|
130
|
+
hash: 3
|
103
131
|
segments:
|
104
132
|
- 0
|
105
133
|
version: "0"
|
106
134
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
135
|
+
none: false
|
107
136
|
requirements:
|
108
137
|
- - ">="
|
109
138
|
- !ruby/object:Gem::Version
|
139
|
+
hash: 3
|
110
140
|
segments:
|
111
141
|
- 0
|
112
142
|
version: "0"
|
113
143
|
requirements: []
|
114
144
|
|
115
145
|
rubyforge_project:
|
116
|
-
rubygems_version: 1.3.
|
146
|
+
rubygems_version: 1.3.7
|
117
147
|
signing_key:
|
118
148
|
specification_version: 3
|
119
149
|
summary: Extract meaningful information from unstructured text with Ruby
|
120
150
|
test_files:
|
151
|
+
- test/api_extractor.rb
|
121
152
|
- test/helper.rb
|
153
|
+
- test/our_extractor.rb
|
122
154
|
- test/test_semantic_extraction.rb
|