text_rank 1.1.6 → 1.2.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.codeclimate.yml +1 -6
- data/.rubocop.yml +60 -1075
- data/.ruby-version +1 -1
- data/.travis.yml +13 -5
- data/{LICENSE.txt → LICENSE} +0 -0
- data/README.md +2 -1
- data/bin/console +3 -3
- data/lib/page_rank.rb +2 -0
- data/lib/page_rank/base.rb +9 -8
- data/lib/page_rank/dense.rb +2 -1
- data/lib/page_rank/sparse.rb +6 -7
- data/lib/text_rank.rb +15 -7
- data/lib/text_rank/char_filter.rb +1 -1
- data/lib/text_rank/char_filter/ascii_folding.rb +5 -1
- data/lib/text_rank/char_filter/strip_possessive.rb +2 -2
- data/lib/text_rank/char_filter/undo_contractions.rb +1 -137
- data/lib/text_rank/char_filter/undo_contractions.yml +135 -0
- data/lib/text_rank/fingerprint.rb +91 -0
- data/lib/text_rank/fingerprint_overlap.rb +55 -0
- data/lib/text_rank/graph_strategy/coocurrence.rb +15 -6
- data/lib/text_rank/keyword_extractor.rb +19 -21
- data/lib/text_rank/rank_filter/collapse_adjacent.rb +53 -25
- data/lib/text_rank/rank_filter/normalize_probability.rb +2 -1
- data/lib/text_rank/rank_filter/normalize_unit_vector.rb +2 -1
- data/lib/text_rank/token_filter/part_of_speech.rb +0 -1
- data/lib/text_rank/token_filter/stopwords.rb +1 -321
- data/lib/text_rank/token_filter/stopwords.yml +317 -0
- data/lib/text_rank/tokenizer.rb +1 -1
- data/lib/text_rank/tokenizer/money.rb +11 -6
- data/lib/text_rank/tokenizer/number.rb +4 -3
- data/lib/text_rank/tokenizer/punctuation.rb +4 -1
- data/lib/text_rank/tokenizer/url.rb +3 -0
- data/lib/text_rank/tokenizer/whitespace.rb +4 -1
- data/lib/text_rank/tokenizer/word.rb +5 -2
- data/lib/text_rank/version.rb +3 -1
- data/text_rank.gemspec +9 -10
- metadata +38 -34
@@ -1,14 +1,17 @@
|
|
1
1
|
module TextRank
|
2
2
|
module Tokenizer
|
3
|
+
|
3
4
|
##
|
4
5
|
# A tokenizer regex that preserves a non-space, non-punctuation "word". It does
|
5
6
|
# allow hyphens and numerals, but the first character must be an A-Z character.
|
6
7
|
##
|
7
|
-
|
8
|
+
# rubocop:disable Naming/ConstantName
|
9
|
+
Word = /
|
8
10
|
(
|
9
11
|
[a-z][a-z0-9-]*
|
10
12
|
)
|
11
|
-
|
13
|
+
/xi
|
14
|
+
# rubocop:enable Naming/ConstantName
|
12
15
|
|
13
16
|
end
|
14
17
|
end
|
data/lib/text_rank/version.rb
CHANGED
data/text_rank.gemspec
CHANGED
@@ -1,4 +1,3 @@
|
|
1
|
-
# coding: utf-8
|
2
1
|
lib = File.expand_path('../lib', __FILE__)
|
3
2
|
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
3
|
require 'text_rank/version'
|
@@ -9,8 +8,8 @@ Gem::Specification.new do |spec|
|
|
9
8
|
spec.authors = ['David McCullars']
|
10
9
|
spec.email = ['david.mccullars@gmail.com']
|
11
10
|
|
12
|
-
spec.summary =
|
13
|
-
spec.description =
|
11
|
+
spec.summary = 'Implementation of TextRank solution to ranked keyword extraction'
|
12
|
+
spec.description = 'Implementation of TextRank solution to ranked keyword extraction. See https://web.eecs.umich.edu/~mihalcea/papers/mihalcea.emnlp04.pdf'
|
14
13
|
spec.homepage = 'https://github.com/david-mccullars/text_rank'
|
15
14
|
spec.license = 'MIT'
|
16
15
|
|
@@ -19,12 +18,12 @@ Gem::Specification.new do |spec|
|
|
19
18
|
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
20
19
|
spec.require_paths = ['lib']
|
21
20
|
|
22
|
-
spec.add_development_dependency 'bundler'
|
23
|
-
spec.add_development_dependency 'rake'
|
24
|
-
spec.add_development_dependency 'rspec'
|
25
|
-
spec.add_development_dependency '
|
26
|
-
spec.add_development_dependency '
|
21
|
+
spec.add_development_dependency 'bundler'
|
22
|
+
spec.add_development_dependency 'rake'
|
23
|
+
spec.add_development_dependency 'rspec'
|
24
|
+
spec.add_development_dependency 'rubocop'
|
25
|
+
spec.add_development_dependency 'simplecov', '~> 0.17.0' # 0.18 not supported by code climate
|
27
26
|
|
28
|
-
spec.add_development_dependency 'engtagger'
|
29
|
-
spec.add_development_dependency 'nokogiri'
|
27
|
+
spec.add_development_dependency 'engtagger' # Optional runtime dependency but needed for specs
|
28
|
+
spec.add_development_dependency 'nokogiri' # Optional runtime dependency but needed for specs
|
30
29
|
end
|
metadata
CHANGED
@@ -1,113 +1,113 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: text_rank
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.2.4
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- David McCullars
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2020-06-10 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- - "
|
17
|
+
- - ">="
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: '
|
19
|
+
version: '0'
|
20
20
|
type: :development
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
|
-
- - "
|
24
|
+
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: '
|
26
|
+
version: '0'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: rake
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- - "
|
31
|
+
- - ">="
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: '
|
33
|
+
version: '0'
|
34
34
|
type: :development
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
|
-
- - "
|
38
|
+
- - ">="
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version: '
|
40
|
+
version: '0'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
42
|
name: rspec
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- - "
|
45
|
+
- - ">="
|
46
46
|
- !ruby/object:Gem::Version
|
47
|
-
version: '
|
47
|
+
version: '0'
|
48
48
|
type: :development
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
|
-
- - "
|
52
|
+
- - ">="
|
53
53
|
- !ruby/object:Gem::Version
|
54
|
-
version: '
|
54
|
+
version: '0'
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
|
-
name:
|
56
|
+
name: rubocop
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
|
-
- - "
|
59
|
+
- - ">="
|
60
60
|
- !ruby/object:Gem::Version
|
61
|
-
version: '0
|
61
|
+
version: '0'
|
62
62
|
type: :development
|
63
63
|
prerelease: false
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
|
-
- - "
|
66
|
+
- - ">="
|
67
67
|
- !ruby/object:Gem::Version
|
68
|
-
version: '0
|
68
|
+
version: '0'
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
|
-
name:
|
70
|
+
name: simplecov
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
|
-
- - "
|
73
|
+
- - "~>"
|
74
74
|
- !ruby/object:Gem::Version
|
75
|
-
version:
|
75
|
+
version: 0.17.0
|
76
76
|
type: :development
|
77
77
|
prerelease: false
|
78
78
|
version_requirements: !ruby/object:Gem::Requirement
|
79
79
|
requirements:
|
80
|
-
- - "
|
80
|
+
- - "~>"
|
81
81
|
- !ruby/object:Gem::Version
|
82
|
-
version:
|
82
|
+
version: 0.17.0
|
83
83
|
- !ruby/object:Gem::Dependency
|
84
84
|
name: engtagger
|
85
85
|
requirement: !ruby/object:Gem::Requirement
|
86
86
|
requirements:
|
87
|
-
- - "
|
87
|
+
- - ">="
|
88
88
|
- !ruby/object:Gem::Version
|
89
|
-
version: 0
|
89
|
+
version: '0'
|
90
90
|
type: :development
|
91
91
|
prerelease: false
|
92
92
|
version_requirements: !ruby/object:Gem::Requirement
|
93
93
|
requirements:
|
94
|
-
- - "
|
94
|
+
- - ">="
|
95
95
|
- !ruby/object:Gem::Version
|
96
|
-
version: 0
|
96
|
+
version: '0'
|
97
97
|
- !ruby/object:Gem::Dependency
|
98
98
|
name: nokogiri
|
99
99
|
requirement: !ruby/object:Gem::Requirement
|
100
100
|
requirements:
|
101
|
-
- - "
|
101
|
+
- - ">="
|
102
102
|
- !ruby/object:Gem::Version
|
103
|
-
version: '
|
103
|
+
version: '0'
|
104
104
|
type: :development
|
105
105
|
prerelease: false
|
106
106
|
version_requirements: !ruby/object:Gem::Requirement
|
107
107
|
requirements:
|
108
|
-
- - "
|
108
|
+
- - ">="
|
109
109
|
- !ruby/object:Gem::Version
|
110
|
-
version: '
|
110
|
+
version: '0'
|
111
111
|
description: Implementation of TextRank solution to ranked keyword extraction. See
|
112
112
|
https://web.eecs.umich.edu/~mihalcea/papers/mihalcea.emnlp04.pdf
|
113
113
|
email:
|
@@ -124,7 +124,7 @@ files:
|
|
124
124
|
- ".travis.yml"
|
125
125
|
- CODE_OF_CONDUCT.md
|
126
126
|
- Gemfile
|
127
|
-
- LICENSE
|
127
|
+
- LICENSE
|
128
128
|
- README.md
|
129
129
|
- Rakefile
|
130
130
|
- bin/console
|
@@ -141,6 +141,9 @@ files:
|
|
141
141
|
- lib/text_rank/char_filter/strip_html.rb
|
142
142
|
- lib/text_rank/char_filter/strip_possessive.rb
|
143
143
|
- lib/text_rank/char_filter/undo_contractions.rb
|
144
|
+
- lib/text_rank/char_filter/undo_contractions.yml
|
145
|
+
- lib/text_rank/fingerprint.rb
|
146
|
+
- lib/text_rank/fingerprint_overlap.rb
|
144
147
|
- lib/text_rank/graph_strategy.rb
|
145
148
|
- lib/text_rank/graph_strategy/coocurrence.rb
|
146
149
|
- lib/text_rank/keyword_extractor.rb
|
@@ -153,6 +156,7 @@ files:
|
|
153
156
|
- lib/text_rank/token_filter/min_length.rb
|
154
157
|
- lib/text_rank/token_filter/part_of_speech.rb
|
155
158
|
- lib/text_rank/token_filter/stopwords.rb
|
159
|
+
- lib/text_rank/token_filter/stopwords.yml
|
156
160
|
- lib/text_rank/tokenizer.rb
|
157
161
|
- lib/text_rank/tokenizer/money.rb
|
158
162
|
- lib/text_rank/tokenizer/number.rb
|
@@ -182,7 +186,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
182
186
|
version: '0'
|
183
187
|
requirements: []
|
184
188
|
rubyforge_project:
|
185
|
-
rubygems_version: 2.
|
189
|
+
rubygems_version: 2.7.6
|
186
190
|
signing_key:
|
187
191
|
specification_version: 4
|
188
192
|
summary: Implementation of TextRank solution to ranked keyword extraction
|