jekyll-tfidf-related-posts 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +2 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +13 -0
- data/jekyll-tfidf-related-posts.gemspec +23 -0
- data/lib/jekyll-tfidf-related-posts.rb +167 -0
- metadata +123 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: be9718e2724638708bdd9f40b2c9a6a8b9eb37a8
|
4
|
+
data.tar.gz: c26b700ff4ec87fbb228a835bd487d33c0754191
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 9d5e168c31cc4c799174bb099006ac00321d130a09ed5445dbad5f56d6fd35c056e7e579f10ae191c523cf11678a03e8b4905268e24c491178a89a23aec25b42
|
7
|
+
data.tar.gz: 9f3d690f6be343d64a15793ec1edc521bbb83f828f4beff3d85d69b976e96691661b2285658d59d7c6694be2c3e652c33af669473aa30a84f305d6877b811631
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2019 Sangsoo Nam
|
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 +1,13 @@
|
|
1
|
+
# jekyll-tdidf-related-posts
|
2
|
+
|
3
|
+
[![DUB](https://img.shields.io/dub/l/vibe-d.svg)]()
|
4
|
+
|
5
|
+
[Jekyll](http://jekyllrb.com) plugin to show related posts based on the content, tags, and categories. The similarity is calculated using TF-IDF(term frequency-inverted document frequency). Since tags and categories are use-defined values, those are considered with higher weights than a content while calculating.
|
6
|
+
|
7
|
+
### Configuration
|
8
|
+
|
9
|
+
By default, there are 4 related posts. You can configure it in the `_config.yml`
|
10
|
+
|
11
|
+
```
|
12
|
+
related_posts_count: 8
|
13
|
+
```
|
@@ -0,0 +1,23 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
|
5
|
+
Gem::Specification.new do |spec|
|
6
|
+
spec.name = "jekyll-tfidf-related-posts"
|
7
|
+
spec.version = "0.1.0"
|
8
|
+
spec.authors = ["Sangsoo Nam"]
|
9
|
+
spec.email = ["sangsoo.ted@gmail.com"]
|
10
|
+
spec.summary = %q{Jekyll plugin to show related posts based on the content, tags, and categories.}
|
11
|
+
spec.description = %q{[Jekyll](http://jekyllrb.com) plugin to show related posts based on the content, tags, and categories. The similarity is calculated using TF-IDF(term frequency-inverted document frequency). Since tags and categories are use-defined values, those are considered with higher weights than a content while calculating.}
|
12
|
+
spec.homepage = "https://github.com/SangsooNam/jekyll-tfidf-related-posts"
|
13
|
+
spec.license = "MIT"
|
14
|
+
|
15
|
+
spec.files = `git ls-files -z`.split("\x0")
|
16
|
+
spec.require_paths = ["lib"]
|
17
|
+
|
18
|
+
spec.add_dependency "jekyll", "~> 3.0"
|
19
|
+
spec.add_dependency "stopwords-filter", "~> 0.4"
|
20
|
+
spec.add_dependency "fast-stemmer", "~> 1.0"
|
21
|
+
spec.add_dependency "pqueue", "~> 2.1"
|
22
|
+
spec.add_dependency "nmatrix", "~> 0.2"
|
23
|
+
end
|
@@ -0,0 +1,167 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'jekyll'
|
3
|
+
require 'fast_stemmer'
|
4
|
+
require 'stopwords'
|
5
|
+
require 'pqueue'
|
6
|
+
require 'nmatrix'
|
7
|
+
|
8
|
+
module SangsooNam
|
9
|
+
module Jekyll
|
10
|
+
class TFIDFRelatedPosts
|
11
|
+
def initialize
|
12
|
+
@docs = Array.new
|
13
|
+
@keywords = Array.new
|
14
|
+
@tags_and_categories = Array.new
|
15
|
+
@stopwords_filter = Stopwords::Snowball::Filter.new('en')
|
16
|
+
end
|
17
|
+
|
18
|
+
def add_post(post)
|
19
|
+
tags = post.data['tags'].map { |e| "@tag:" + e }.map(&:to_sym)
|
20
|
+
categories = post.data['categories'].map { |e| "@category:" + e }.map(&:to_sym)
|
21
|
+
doc = {
|
22
|
+
post: post,
|
23
|
+
content: (stem(post.content) + stem(post.data['title']) + tags + categories)
|
24
|
+
}
|
25
|
+
@docs << doc
|
26
|
+
@keywords += doc[:content]
|
27
|
+
@tags_and_categories += tags + categories
|
28
|
+
end
|
29
|
+
|
30
|
+
def build(site)
|
31
|
+
@keywords.uniq!
|
32
|
+
@tags_and_categories.uniq!
|
33
|
+
@weights = custom_weights(@tags_and_categories)
|
34
|
+
related = build_related_docs_with_score(site.config['related_posts_count'] || 4)
|
35
|
+
|
36
|
+
@docs.each do |doc|
|
37
|
+
doc[:post].instance_variable_set(:@related_posts,related[doc].map { |x| x[:post] })
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
private
|
42
|
+
|
43
|
+
def build_related_docs_with_score(count = 8)
|
44
|
+
dc = document_correleation
|
45
|
+
result = Hash.new
|
46
|
+
count = [count, @docs.size].min
|
47
|
+
|
48
|
+
@docs.each_with_index do |doc, index|
|
49
|
+
queue = PQueue.new(dc.row(index).each_with_index) do |a, b|
|
50
|
+
a[0] > b[0]
|
51
|
+
end
|
52
|
+
|
53
|
+
result[doc] = []
|
54
|
+
count.times do
|
55
|
+
score, id = queue.pop
|
56
|
+
begin
|
57
|
+
result[doc] << {
|
58
|
+
score: score,
|
59
|
+
post: @docs[id][:post]
|
60
|
+
}
|
61
|
+
rescue
|
62
|
+
break
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
return result
|
68
|
+
end
|
69
|
+
|
70
|
+
def document_correleation()
|
71
|
+
scores = tfidf
|
72
|
+
result = scores.dot(scores.transpose)
|
73
|
+
|
74
|
+
result.each_with_indices do |_, u, v|
|
75
|
+
if u != v
|
76
|
+
result[u, v] /= (result[u, u] + result[v, v] - result[u, v])
|
77
|
+
else
|
78
|
+
result[u, v] = 0.0
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
return result
|
83
|
+
end
|
84
|
+
|
85
|
+
def bag_of_words
|
86
|
+
result = NMatrix.new([@docs.size, @keywords.size], 0.0)
|
87
|
+
@max = NMatrix.new([@docs.size], 0.0)
|
88
|
+
|
89
|
+
result.each_with_indices do |_, pi, ki|
|
90
|
+
result[pi, ki] = @docs[pi][:content].count(@keywords[ki])
|
91
|
+
|
92
|
+
if result[pi, ki] > @max[pi]
|
93
|
+
@max[pi] = result[pi, ki]
|
94
|
+
end
|
95
|
+
end
|
96
|
+
|
97
|
+
@bag_of_words = result.dup
|
98
|
+
return result
|
99
|
+
end
|
100
|
+
|
101
|
+
def term_frequency
|
102
|
+
result = bag_of_words
|
103
|
+
|
104
|
+
result.rows.times do |r|
|
105
|
+
result[r, 0..-1] *= @weights
|
106
|
+
result[r, 0..-1] /= @max[r]
|
107
|
+
end
|
108
|
+
|
109
|
+
return result
|
110
|
+
end
|
111
|
+
|
112
|
+
def custom_weights(terms, weight = 8.0)
|
113
|
+
result = NMatrix.new([1, @keywords.size], 1.0)
|
114
|
+
|
115
|
+
terms.each do |term|
|
116
|
+
result[0, @keywords.index(term)] = weight
|
117
|
+
end
|
118
|
+
|
119
|
+
return result
|
120
|
+
end
|
121
|
+
|
122
|
+
def inverse_document_frequency
|
123
|
+
result = NMatrix.new([1, @keywords.size], 0.0)
|
124
|
+
|
125
|
+
@bag_of_words.each_column do |column|
|
126
|
+
occurences = column.reduce do |m, c|
|
127
|
+
m + (c > 0 ? 1.0 : 0.0)
|
128
|
+
end
|
129
|
+
|
130
|
+
result[0, column.offset[1]] = Math.log(column.size / occurences) if occurences > 0
|
131
|
+
end
|
132
|
+
|
133
|
+
return result
|
134
|
+
end
|
135
|
+
|
136
|
+
def tfidf
|
137
|
+
result = term_frequency
|
138
|
+
idf = inverse_document_frequency
|
139
|
+
|
140
|
+
result.rows.times do |r|
|
141
|
+
result[r, 0..-1] *= idf
|
142
|
+
end
|
143
|
+
|
144
|
+
return result
|
145
|
+
end
|
146
|
+
|
147
|
+
def stem(data)
|
148
|
+
data = data.gsub(/{%.+%}/, ' ') # Replace liquid templates
|
149
|
+
tokenized = data.scan(/\w+/).map(&:downcase)
|
150
|
+
filtered = @stopwords_filter.filter(tokenized)
|
151
|
+
stemmed = filtered.map(&:stem).select{|s| s.length > 1}.map(&:to_sym)
|
152
|
+
return stemmed
|
153
|
+
end
|
154
|
+
end
|
155
|
+
end
|
156
|
+
end
|
157
|
+
|
158
|
+
Jekyll::Hooks.register :site, :pre_render do |site|
|
159
|
+
Jekyll.logger.info("Building TFIDF index...")
|
160
|
+
tfidf = SangsooNam::Jekyll::TFIDFRelatedPosts.new
|
161
|
+
site.posts.docs.each do |x|
|
162
|
+
tfidf.add_post(x)
|
163
|
+
end
|
164
|
+
|
165
|
+
Jekyll.logger.info("Replaceing Related Posts...")
|
166
|
+
tfidf.build(site)
|
167
|
+
end
|
metadata
ADDED
@@ -0,0 +1,123 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: jekyll-tfidf-related-posts
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Sangsoo Nam
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2019-01-06 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: jekyll
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '3.0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '3.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: stopwords-filter
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0.4'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0.4'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: fast-stemmer
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: pqueue
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '2.1'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '2.1'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: nmatrix
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0.2'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0.2'
|
83
|
+
description: "[Jekyll](http://jekyllrb.com) plugin to show related posts based on
|
84
|
+
the content, tags, and categories. The similarity is calculated using TF-IDF(term
|
85
|
+
frequency-inverted document frequency). Since tags and categories are use-defined
|
86
|
+
values, those are considered with higher weights than a content while calculating."
|
87
|
+
email:
|
88
|
+
- sangsoo.ted@gmail.com
|
89
|
+
executables: []
|
90
|
+
extensions: []
|
91
|
+
extra_rdoc_files: []
|
92
|
+
files:
|
93
|
+
- ".gitignore"
|
94
|
+
- Gemfile
|
95
|
+
- LICENSE.txt
|
96
|
+
- README.md
|
97
|
+
- jekyll-tfidf-related-posts.gemspec
|
98
|
+
- lib/jekyll-tfidf-related-posts.rb
|
99
|
+
homepage: https://github.com/SangsooNam/jekyll-tfidf-related-posts
|
100
|
+
licenses:
|
101
|
+
- MIT
|
102
|
+
metadata: {}
|
103
|
+
post_install_message:
|
104
|
+
rdoc_options: []
|
105
|
+
require_paths:
|
106
|
+
- lib
|
107
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
108
|
+
requirements:
|
109
|
+
- - ">="
|
110
|
+
- !ruby/object:Gem::Version
|
111
|
+
version: '0'
|
112
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
113
|
+
requirements:
|
114
|
+
- - ">="
|
115
|
+
- !ruby/object:Gem::Version
|
116
|
+
version: '0'
|
117
|
+
requirements: []
|
118
|
+
rubyforge_project:
|
119
|
+
rubygems_version: 2.6.11
|
120
|
+
signing_key:
|
121
|
+
specification_version: 4
|
122
|
+
summary: Jekyll plugin to show related posts based on the content, tags, and categories.
|
123
|
+
test_files: []
|