text_rank 1.2.3 → 1.2.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.rubocop.yml +7 -0
- 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 +11 -8
- 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 +10 -18
- 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 +48 -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
- metadata +4 -1
|
@@ -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
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: text_rank
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.2.
|
|
4
|
+
version: 1.2.4
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- David McCullars
|
|
@@ -141,7 +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
|
|
144
145
|
- lib/text_rank/fingerprint.rb
|
|
146
|
+
- lib/text_rank/fingerprint_overlap.rb
|
|
145
147
|
- lib/text_rank/graph_strategy.rb
|
|
146
148
|
- lib/text_rank/graph_strategy/coocurrence.rb
|
|
147
149
|
- lib/text_rank/keyword_extractor.rb
|
|
@@ -154,6 +156,7 @@ files:
|
|
|
154
156
|
- lib/text_rank/token_filter/min_length.rb
|
|
155
157
|
- lib/text_rank/token_filter/part_of_speech.rb
|
|
156
158
|
- lib/text_rank/token_filter/stopwords.rb
|
|
159
|
+
- lib/text_rank/token_filter/stopwords.yml
|
|
157
160
|
- lib/text_rank/tokenizer.rb
|
|
158
161
|
- lib/text_rank/tokenizer/money.rb
|
|
159
162
|
- lib/text_rank/tokenizer/number.rb
|