acts_as_fuzzy_search 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +41 -0
- data/Rakefile +2 -0
- data/acts_as_fuzzy_search.gemspec +22 -0
- data/lib/acts_as_fuzzy_search.rb +8 -0
- data/lib/acts_as_fuzzy_search/fuzzy.rb +90 -0
- data/lib/acts_as_fuzzy_search/version.rb +3 -0
- metadata +77 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Jordan Babe
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,41 @@
|
|
1
|
+
# ActsAsFuzzySearch
|
2
|
+
|
3
|
+
Return Activerecord records that match a search query. Ideally used for small sets of data and simple search terms.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'acts_as_fuzzy_search'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install acts_as_fuzzy_search
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
# app/models/foobar.rb
|
22
|
+
class Foobar < ActiveRecord::Base
|
23
|
+
acts_as_fuzzy_search
|
24
|
+
|
25
|
+
# Or pass it some options:
|
26
|
+
# acts_as_fuzzy_search(:scope => :your_scope_name, :search_algorithm => :white_similarity)
|
27
|
+
end
|
28
|
+
|
29
|
+
# Elsewhere in your code
|
30
|
+
Foobar.find_by_fuzzy_search 'smthing'
|
31
|
+
|
32
|
+
# Or pass it some options
|
33
|
+
Foobar.find_by_fuzzy_search 'smthing', {:date_format => "%B %d %Y", :search_algorithm => :levenshtein_distance})
|
34
|
+
|
35
|
+
## Contributing
|
36
|
+
|
37
|
+
1. Fork it
|
38
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
39
|
+
3. Commit your changes (`git commit -am 'Added some feature'`)
|
40
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
41
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/acts_as_fuzzy_search/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["Jordan Babe"]
|
6
|
+
gem.email = ["jorbabe@gmail.com"]
|
7
|
+
gem.description = %q{ Return Activerecord records that match a search query. Ideally used for small sets of data and simple search terms.}
|
8
|
+
gem.summary = %q{ AR find based on word matching }
|
9
|
+
gem.homepage = "http://github.com/jbabe/acts_as_fuzzy_search"
|
10
|
+
|
11
|
+
gem.files = `git ls-files`.split($\)
|
12
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
13
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
14
|
+
gem.name = "acts_as_fuzzy_search"
|
15
|
+
gem.require_paths = ["lib"]
|
16
|
+
gem.version = ActsAsFuzzySearch::VERSION
|
17
|
+
|
18
|
+
gem.add_dependency "text", "~> 1.0.0"
|
19
|
+
# gem.add_dependency "fuzzy-string-match", "~> 0.9.0" Drop this until we
|
20
|
+
|
21
|
+
gem.add_development_dependency "minitest"
|
22
|
+
end
|
@@ -0,0 +1,90 @@
|
|
1
|
+
module ActsAsFuzzySearch
|
2
|
+
module Fuzzy
|
3
|
+
|
4
|
+
extend ActiveSupport::Concern
|
5
|
+
|
6
|
+
included do
|
7
|
+
end
|
8
|
+
|
9
|
+
module ClassMethods
|
10
|
+
|
11
|
+
DEFAULT_ALGORITHM = :white_similarity
|
12
|
+
MATCH_SCORE = 0.8 # used by jarow-winkler and white-similarity
|
13
|
+
MIN_LEVENSHTEIN_DISTANCE = 3 # number of changes to get the strings to match
|
14
|
+
|
15
|
+
DATE_FORMAT = "%B %d %Y"
|
16
|
+
SCOPE = "all"
|
17
|
+
|
18
|
+
|
19
|
+
|
20
|
+
attr_accessor :config
|
21
|
+
|
22
|
+
def acts_as_fuzzy_search(options = {})
|
23
|
+
@config = { :date_format => DATE_FORMAT,
|
24
|
+
:scope => "all",
|
25
|
+
:search_algorithm => DEFAULT_ALGORITHM,
|
26
|
+
:jarow_score => MATCH_SCORE,
|
27
|
+
:white_similarity_score => MATCH_SCORE,
|
28
|
+
:min_levenshtein_distance => MIN_LEVENSHTEIN_DISTANCE,
|
29
|
+
:debug => false }
|
30
|
+
|
31
|
+
@config.merge!(options)
|
32
|
+
end
|
33
|
+
|
34
|
+
def find_by_fuzzy_search(search_term, options = {})
|
35
|
+
|
36
|
+
@config.merge!(options)
|
37
|
+
|
38
|
+
search_term = search_term.strip.chomp
|
39
|
+
records = []
|
40
|
+
|
41
|
+
send(config[:scope]).each do |record|
|
42
|
+
|
43
|
+
attrs = record.attributes.values
|
44
|
+
|
45
|
+
# convert dates to ones humans will likely search on
|
46
|
+
attrs.collect! {|a| ([Date,Time,DateTime].include? a.class) ? a.strftime(config[:date_format]) : a }
|
47
|
+
|
48
|
+
# 'create' an html page
|
49
|
+
markup = Nokogiri::HTML(attrs.join(" "))
|
50
|
+
|
51
|
+
# strip all the tags and whitespace
|
52
|
+
no_tags = markup.text.gsub(/\s+|\n/, ' ')
|
53
|
+
|
54
|
+
# Match each word in the document against each search term
|
55
|
+
no_tags.split(" ").each do |word|
|
56
|
+
search_term.split(" ").each do |term|
|
57
|
+
records << record if matches?(term, word)
|
58
|
+
end
|
59
|
+
end
|
60
|
+
end
|
61
|
+
return records.uniq
|
62
|
+
end
|
63
|
+
|
64
|
+
private
|
65
|
+
|
66
|
+
def matches?(word1, word2)
|
67
|
+
# mostly for the regex - the other matches are probably smart enough
|
68
|
+
word1 = word1.downcase
|
69
|
+
word2 = word2.downcase
|
70
|
+
|
71
|
+
case config[:search_algorithm]
|
72
|
+
when :jarow_winkler
|
73
|
+
# Drop for now cause we're using 1.8
|
74
|
+
raise "Jarow-Winkler not supported" #return FuzzyStringMatch::JaroWinkler.create(:native).getDistance(word1, word2) >= config[:jarow_score]
|
75
|
+
when :white_similarity
|
76
|
+
return Text::WhiteSimilarity.new.similarity(word1,word2) >= config[:white_similarity_score]
|
77
|
+
when :levenshtein_distance
|
78
|
+
return Text::Levenshtein.distance(word1,word2) <= config[:min_levenshtein_distance]
|
79
|
+
else
|
80
|
+
return word1.match(word2).present? # simple regex match
|
81
|
+
end
|
82
|
+
|
83
|
+
end
|
84
|
+
|
85
|
+
|
86
|
+
end
|
87
|
+
end
|
88
|
+
end
|
89
|
+
|
90
|
+
ActiveRecord::Base.send :include, ActsAsFuzzySearch::Fuzzy
|
metadata
ADDED
@@ -0,0 +1,77 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: acts_as_fuzzy_search
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Jordan Babe
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-04-16 00:00:00.000000000Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: text
|
16
|
+
requirement: &2160283960 !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: 1.0.0
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *2160283960
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: minitest
|
27
|
+
requirement: &2160278160 !ruby/object:Gem::Requirement
|
28
|
+
none: false
|
29
|
+
requirements:
|
30
|
+
- - ! '>='
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '0'
|
33
|
+
type: :development
|
34
|
+
prerelease: false
|
35
|
+
version_requirements: *2160278160
|
36
|
+
description: ! ' Return Activerecord records that match a search query. Ideally used
|
37
|
+
for small sets of data and simple search terms.'
|
38
|
+
email:
|
39
|
+
- jorbabe@gmail.com
|
40
|
+
executables: []
|
41
|
+
extensions: []
|
42
|
+
extra_rdoc_files: []
|
43
|
+
files:
|
44
|
+
- .gitignore
|
45
|
+
- Gemfile
|
46
|
+
- LICENSE
|
47
|
+
- README.md
|
48
|
+
- Rakefile
|
49
|
+
- acts_as_fuzzy_search.gemspec
|
50
|
+
- lib/acts_as_fuzzy_search.rb
|
51
|
+
- lib/acts_as_fuzzy_search/fuzzy.rb
|
52
|
+
- lib/acts_as_fuzzy_search/version.rb
|
53
|
+
homepage: http://github.com/jbabe/acts_as_fuzzy_search
|
54
|
+
licenses: []
|
55
|
+
post_install_message:
|
56
|
+
rdoc_options: []
|
57
|
+
require_paths:
|
58
|
+
- lib
|
59
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
60
|
+
none: false
|
61
|
+
requirements:
|
62
|
+
- - ! '>='
|
63
|
+
- !ruby/object:Gem::Version
|
64
|
+
version: '0'
|
65
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
66
|
+
none: false
|
67
|
+
requirements:
|
68
|
+
- - ! '>='
|
69
|
+
- !ruby/object:Gem::Version
|
70
|
+
version: '0'
|
71
|
+
requirements: []
|
72
|
+
rubyforge_project:
|
73
|
+
rubygems_version: 1.8.8
|
74
|
+
signing_key:
|
75
|
+
specification_version: 3
|
76
|
+
summary: AR find based on word matching
|
77
|
+
test_files: []
|