answerific 0.1.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/.travis.yml +3 -0
- data/Gemfile +4 -0
- data/Guardfile +13 -0
- data/README.md +56 -0
- data/Rakefile +14 -0
- data/answerific.gemspec +28 -0
- data/bin/console +14 -0
- data/bin/setup +7 -0
- data/lib/answerific.rb +166 -0
- data/lib/answerific/version.rb +3 -0
- metadata +152 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: a6b5905e26045c85b62eadee1a917f7a6f33edb5
|
4
|
+
data.tar.gz: b1721baa87c03b00cf36e614dc50561dc8473a35
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: b30eed839c2149e237033351b458427bb56274d970db991977a689232a5cecd55e7ece89d78a8f1cd40c5ce72b8bb60622fb9f7cd159b87e45b8ac3f14359927
|
7
|
+
data.tar.gz: 8b347d026f099cbb41b02b626bd524724edc135b7c61f1fd038b7af1efd93a66c302d1d4107e62b79b2009b90dc86b6f3fa70be826185e9d863de8aeae2053e3
|
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/Guardfile
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
clearing :on
|
2
|
+
|
3
|
+
guard 'rspec', cmd: "bundle exec rspec --format=doc --format=Nc" do
|
4
|
+
# watch /lib/ files
|
5
|
+
watch(%r{^lib/(.+).rb$}) do |m|
|
6
|
+
"spec/#{m[1]}_spec.rb"
|
7
|
+
end
|
8
|
+
|
9
|
+
# watch /spec/ files
|
10
|
+
watch(%r{^spec/(.+).rb$}) do |m|
|
11
|
+
"spec/#{m[1]}.rb"
|
12
|
+
end
|
13
|
+
end
|
data/README.md
ADDED
@@ -0,0 +1,56 @@
|
|
1
|
+
# Answerific
|
2
|
+
|
3
|
+
AI Bot that can answer questions posed in natural language.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'answerific'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install answerific
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
bot = Answerific::Bot.new()
|
24
|
+
bot.answer('what is the composition of Pluto?')
|
25
|
+
|
26
|
+
## How it works
|
27
|
+
|
28
|
+
Given an input, answerific will
|
29
|
+
|
30
|
+
1. Preprocess the input
|
31
|
+
2. Detect the type of question
|
32
|
+
3. Parse and rearrange the input given the type of question
|
33
|
+
4. Extract information from the web for that parsed input
|
34
|
+
5. Select and return the best answer
|
35
|
+
|
36
|
+
## Roadmap
|
37
|
+
|
38
|
+
* Add options at initialization
|
39
|
+
* Sentence split on dot: handle abbreviations
|
40
|
+
* Return special message when no result found? Or just nil?
|
41
|
+
* Better support for wh-words (atm, the bot just gets rid of them)
|
42
|
+
* Better support for yes-no questions: answer with definite yes-no instead of statement
|
43
|
+
|
44
|
+
## Development
|
45
|
+
|
46
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `bin/console` for an interactive prompt that will allow you to experiment.
|
47
|
+
|
48
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release` to create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
49
|
+
|
50
|
+
## Contributing
|
51
|
+
|
52
|
+
1. Fork it ( https://github.com/[my-github-username]/answerific/fork )
|
53
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
54
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
55
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
56
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
require 'rspec/core/rake_task'
|
2
|
+
require 'bundler/gem_tasks'
|
3
|
+
|
4
|
+
# Default directory to look in is `/specs`
|
5
|
+
# Run with `rake spec`
|
6
|
+
RSpec::Core::RakeTask.new(:spec) do |task|
|
7
|
+
task.rspec_opts = ['--color', '--format=d', '--format=Nc']
|
8
|
+
end
|
9
|
+
|
10
|
+
task :default => :spec
|
11
|
+
|
12
|
+
task :console do
|
13
|
+
exec "irb -r answerific -I ./lib"
|
14
|
+
end
|
data/answerific.gemspec
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'answerific/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "answerific"
|
8
|
+
spec.version = Answerific::VERSION
|
9
|
+
spec.authors = ["Justin Domingue"]
|
10
|
+
spec.email = ["justin.domingue@hotmail.com"]
|
11
|
+
|
12
|
+
spec.summary = 'Bot that answers natural language questions.'
|
13
|
+
spec.homepage = 'https://github.com/justindomingue/answerific'
|
14
|
+
|
15
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
16
|
+
spec.bindir = "exe"
|
17
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
18
|
+
spec.require_paths = ["lib"]
|
19
|
+
|
20
|
+
spec.add_development_dependency "bundler", "~> 1.9"
|
21
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
22
|
+
spec.add_development_dependency "rspec"
|
23
|
+
spec.add_development_dependency "rspec-nc"
|
24
|
+
spec.add_development_dependency "guard"
|
25
|
+
spec.add_development_dependency "guard-rspec"
|
26
|
+
|
27
|
+
spec.add_runtime_dependency "google-search"
|
28
|
+
end
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "answerific"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/setup
ADDED
data/lib/answerific.rb
ADDED
@@ -0,0 +1,166 @@
|
|
1
|
+
require "answerific/version"
|
2
|
+
require "google-search"
|
3
|
+
|
4
|
+
module Answerific
|
5
|
+
class Bot
|
6
|
+
|
7
|
+
def answer(question)
|
8
|
+
mine(parse(preprocess(question)))
|
9
|
+
end
|
10
|
+
|
11
|
+
# === SELECT RESPONSE ===
|
12
|
+
|
13
|
+
def process_google_results(results, query)
|
14
|
+
candidates = select_responses(results, query)
|
15
|
+
select_best_response(candidates)
|
16
|
+
end
|
17
|
+
|
18
|
+
# Returns a single response from the list of responses
|
19
|
+
# TODO how to select the best? right now, return the first one
|
20
|
+
def select_best_response(responses)
|
21
|
+
responses.sample
|
22
|
+
end
|
23
|
+
|
24
|
+
# Returns the responses from `results` that have a the words in `query`
|
25
|
+
def select_responses(results, query)
|
26
|
+
sentences = results.map { |r| split_at_dot r }.flatten
|
27
|
+
query_words = query.split ' '
|
28
|
+
|
29
|
+
# Select the responses, only keeping the sentence that contain the search query
|
30
|
+
selected = sentences.select do |sentence|
|
31
|
+
query_words.all? { |w| sentence.include? w } # contains all query words
|
32
|
+
end
|
33
|
+
|
34
|
+
return selected
|
35
|
+
end
|
36
|
+
|
37
|
+
# === EXTRACT INFO ===
|
38
|
+
|
39
|
+
def mine(query)
|
40
|
+
results = []
|
41
|
+
|
42
|
+
Google::Search::Web.new(query: query).each do |r|
|
43
|
+
results << clean_google_result(r.content)
|
44
|
+
end
|
45
|
+
|
46
|
+
process_google_results(results, query)
|
47
|
+
end
|
48
|
+
|
49
|
+
# === PARSE AND REARRANGE === (prepare for search engines)
|
50
|
+
|
51
|
+
def parse(question)
|
52
|
+
type = broad_question_type question
|
53
|
+
parsed = ''
|
54
|
+
|
55
|
+
case type
|
56
|
+
when 'wh'
|
57
|
+
parsed = parse_wh_question question
|
58
|
+
when 'yes-no'
|
59
|
+
parsed = parse_yes_no_question question
|
60
|
+
when 'declarative'
|
61
|
+
parsed = parse_declarative_question question
|
62
|
+
end
|
63
|
+
|
64
|
+
return parsed
|
65
|
+
end
|
66
|
+
|
67
|
+
# TODO consider verb permutations
|
68
|
+
# TODO consider wh-word: where is the sun => the sun is [located]
|
69
|
+
# Parses the wh-question `question` by removing the wh-word and moving the main verb at the end
|
70
|
+
# Assumptions:
|
71
|
+
# * wh-word is at the beginning
|
72
|
+
# * main verb follows the wh-word
|
73
|
+
# (TODO not accurate for which/whose but should be ok for the others)
|
74
|
+
# Example:
|
75
|
+
# question: 'where is the Kuiper belt'
|
76
|
+
# returns : 'the Kuiper belt is'
|
77
|
+
def parse_wh_question(question)
|
78
|
+
words = question.split ' '
|
79
|
+
parsed = words[2..-1] << words[1]
|
80
|
+
parsed.join " "
|
81
|
+
end
|
82
|
+
|
83
|
+
# Returns an array of permutations of the main verb in the question without the wh-word
|
84
|
+
# Parses the wh-question `question` by removing the wh-word
|
85
|
+
# Assumptions:
|
86
|
+
# * wh-word is at the beginning
|
87
|
+
# * main verb follows the wh-word
|
88
|
+
# (TODO not accurate for which/whose but should be ok for the others)
|
89
|
+
# Example:
|
90
|
+
# question: 'where is the Kuiper belt'
|
91
|
+
# returns : ['is the Kuiper belt',
|
92
|
+
# 'the is Kuiper belt',
|
93
|
+
# 'the Kuiper is belt',
|
94
|
+
# 'the Kuiper belt is']
|
95
|
+
# def parse_wh_question(question)
|
96
|
+
|
97
|
+
# end
|
98
|
+
|
99
|
+
# Returns `question` without the yes-no verb
|
100
|
+
# Example:
|
101
|
+
# question: 'is pluto closer to the sun than saturn'
|
102
|
+
# returns : 'pluto closer to the sun than saturn'
|
103
|
+
def parse_yes_no_question(question)
|
104
|
+
words = question.split ' '
|
105
|
+
return words[1..-1].join ' '
|
106
|
+
end
|
107
|
+
|
108
|
+
# Returns `question` without the declarative statement
|
109
|
+
# Example:
|
110
|
+
# question: 'tell me what is Pluto'
|
111
|
+
# returns : 'what is Pluto'
|
112
|
+
def parse_declarative_question(question)
|
113
|
+
declarative_expressions = [ 'tell me', 'I want to know' ]
|
114
|
+
return question.gsub(/^#{Regexp.union(*declarative_expressions)}/, '').strip
|
115
|
+
end
|
116
|
+
|
117
|
+
# === DETECT TYPE OF QUESTION ===
|
118
|
+
|
119
|
+
def broad_question_type(question)
|
120
|
+
return 'wh' if is_wh_question question
|
121
|
+
return 'yes-no' if is_yes_no_question question
|
122
|
+
return 'declarative'
|
123
|
+
end
|
124
|
+
|
125
|
+
# Returns true if question starts with a wh-question word
|
126
|
+
def is_wh_question(question)
|
127
|
+
wh_words = %w(who where when why what which how)
|
128
|
+
return /^#{Regexp.union(*wh_words)}/ === question
|
129
|
+
end
|
130
|
+
|
131
|
+
# Returns true if question starts with a yes-no question expression
|
132
|
+
def is_yes_no_question(question)
|
133
|
+
yes_no_words = %w(am are is was were have has do does did can could should may)
|
134
|
+
return /^#{Regexp.union(*yes_no_words)}/ === question
|
135
|
+
end
|
136
|
+
|
137
|
+
# === PREPROCESSING ===
|
138
|
+
|
139
|
+
# Returns cleaned `input`
|
140
|
+
def preprocess(input)
|
141
|
+
clean(input)
|
142
|
+
end
|
143
|
+
|
144
|
+
# Cleans the string `input` by removing non alpha-numeric characters
|
145
|
+
def clean(input)
|
146
|
+
ret = input.downcase
|
147
|
+
ret.gsub(/[^0-9a-z ]/i, '').strip
|
148
|
+
end
|
149
|
+
|
150
|
+
# === OTHER FORMATTING ===
|
151
|
+
|
152
|
+
def clean_google_result(string)
|
153
|
+
string
|
154
|
+
.downcase
|
155
|
+
.gsub(/[^\.]+\.{3,}/, '') # remove incomplete sentences
|
156
|
+
.gsub(/<("[^"]*"|'[^']*'|[^'">])*>/, '') # html tags
|
157
|
+
.gsub(/\w{3} \d{1,2}, \d{4} \.{3} /, '') # dates (27 Jan, 2015)
|
158
|
+
.gsub("\n",'') # new lines
|
159
|
+
end
|
160
|
+
|
161
|
+
def split_at_dot(string)
|
162
|
+
re = /([a-z]{2})[\.\?!] ?/i # regex to match *aa. where a is any letter
|
163
|
+
string.split(re).each_slice(2).map(&:join)
|
164
|
+
end
|
165
|
+
end
|
166
|
+
end
|
metadata
ADDED
@@ -0,0 +1,152 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: answerific
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Justin Domingue
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-04-29 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.9'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.9'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rspec-nc
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: guard
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: guard-rspec
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: google-search
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - ">="
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ">="
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
description:
|
112
|
+
email:
|
113
|
+
- justin.domingue@hotmail.com
|
114
|
+
executables: []
|
115
|
+
extensions: []
|
116
|
+
extra_rdoc_files: []
|
117
|
+
files:
|
118
|
+
- ".gitignore"
|
119
|
+
- ".travis.yml"
|
120
|
+
- Gemfile
|
121
|
+
- Guardfile
|
122
|
+
- README.md
|
123
|
+
- Rakefile
|
124
|
+
- answerific.gemspec
|
125
|
+
- bin/console
|
126
|
+
- bin/setup
|
127
|
+
- lib/answerific.rb
|
128
|
+
- lib/answerific/version.rb
|
129
|
+
homepage: https://github.com/justindomingue/answerific
|
130
|
+
licenses: []
|
131
|
+
metadata: {}
|
132
|
+
post_install_message:
|
133
|
+
rdoc_options: []
|
134
|
+
require_paths:
|
135
|
+
- lib
|
136
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
137
|
+
requirements:
|
138
|
+
- - ">="
|
139
|
+
- !ruby/object:Gem::Version
|
140
|
+
version: '0'
|
141
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - ">="
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: '0'
|
146
|
+
requirements: []
|
147
|
+
rubyforge_project:
|
148
|
+
rubygems_version: 2.4.5
|
149
|
+
signing_key:
|
150
|
+
specification_version: 4
|
151
|
+
summary: Bot that answers natural language questions.
|
152
|
+
test_files: []
|