stopwords-filter 0.4.0 → 0.4.1
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/Gemfile +1 -1
- data/Gemfile.lock +15 -10
- data/README.md +2 -0
- data/VERSION +1 -1
- data/spec/lib/filter_spec.rb +2 -2
- data/spec/lib/snowball_filter_spec.rb +3 -3
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 26ad2be238de99a15566a44868507c98eca63b9c
|
|
4
|
+
data.tar.gz: 27018c7a631d3652a1f85c4b654a99cf1194db2d
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 8421df77574b543b1c62ed5655c24094f5e8c8927ff8266f0e223082c9f656c5bc26691aa77086cd51eeeb6797510fc5937130bdc667f3141f18a2ec54a084df
|
|
7
|
+
data.tar.gz: 949edc4a8ad7d68f87bbded9b06c55683e4cf46d34c7c44c377e8d88d29ae3f243dd1e176829a3d7d855eda91e5a83159e9f8d1b2408aa4026e55b9e59e64137
|
data/Gemfile
CHANGED
data/Gemfile.lock
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
GEM
|
|
2
2
|
remote: https://rubygems.org/
|
|
3
3
|
specs:
|
|
4
|
-
diff-lcs (1.
|
|
4
|
+
diff-lcs (1.3)
|
|
5
5
|
git (1.3.0)
|
|
6
6
|
jeweler (1.8.4)
|
|
7
7
|
bundler (~> 1.0)
|
|
@@ -10,21 +10,26 @@ GEM
|
|
|
10
10
|
rdoc
|
|
11
11
|
rake (12.0.0)
|
|
12
12
|
rdoc (5.0.0)
|
|
13
|
-
rspec (
|
|
14
|
-
rspec-core (~>
|
|
15
|
-
rspec-expectations (~>
|
|
16
|
-
rspec-mocks (~>
|
|
17
|
-
rspec-core (
|
|
18
|
-
|
|
19
|
-
|
|
20
|
-
|
|
13
|
+
rspec (3.5.0)
|
|
14
|
+
rspec-core (~> 3.5.0)
|
|
15
|
+
rspec-expectations (~> 3.5.0)
|
|
16
|
+
rspec-mocks (~> 3.5.0)
|
|
17
|
+
rspec-core (3.5.4)
|
|
18
|
+
rspec-support (~> 3.5.0)
|
|
19
|
+
rspec-expectations (3.5.0)
|
|
20
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
|
21
|
+
rspec-support (~> 3.5.0)
|
|
22
|
+
rspec-mocks (3.5.0)
|
|
23
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
|
24
|
+
rspec-support (~> 3.5.0)
|
|
25
|
+
rspec-support (3.5.0)
|
|
21
26
|
|
|
22
27
|
PLATFORMS
|
|
23
28
|
ruby
|
|
24
29
|
|
|
25
30
|
DEPENDENCIES
|
|
26
31
|
jeweler (= 1.8.4)
|
|
27
|
-
rspec
|
|
32
|
+
rspec
|
|
28
33
|
|
|
29
34
|
BUNDLED WITH
|
|
30
35
|
1.13.6
|
data/README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
|
1
1
|
Stopwords Filter
|
|
2
2
|
================
|
|
3
3
|
|
|
4
|
+
[](https://travis-ci.org/brenes/stopwords-filter)
|
|
5
|
+
|
|
4
6
|
This project is a very simple and naive implementation of a stopwords filter that remove a list of banned words (stopwords) from a sentence.
|
|
5
7
|
|
|
6
8
|
Quick guide
|
data/VERSION
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
0.4.
|
|
1
|
+
0.4.1
|
data/spec/lib/filter_spec.rb
CHANGED
|
@@ -9,9 +9,9 @@ describe Stopwords::Filter do
|
|
|
9
9
|
|
|
10
10
|
subject { filter }
|
|
11
11
|
|
|
12
|
-
it("should remove the stopwords for the list of words to be filtered") { filter.filter("desde Santurce a Bilbao".split).
|
|
12
|
+
it("should remove the stopwords for the list of words to be filtered") { expect(filter.filter("desde Santurce a Bilbao".split)).to eq ["Santurce", "Bilbao"]}
|
|
13
13
|
|
|
14
14
|
end
|
|
15
15
|
|
|
16
16
|
|
|
17
|
-
end
|
|
17
|
+
end
|
|
@@ -9,9 +9,9 @@ describe Stopwords::Snowball::Filter do
|
|
|
9
9
|
|
|
10
10
|
subject { filter }
|
|
11
11
|
|
|
12
|
-
|
|
12
|
+
it("should have the appropiate stopwords") { expect(subject.stopwords).to eq ["de", "la", "que", "el", "en", "y", "a", "los", "del", "se", "las", "por", "un", "para", "con", "no", "una", "su", "al", "lo", "como", "más", "pero", "sus", "le", "ya", "o", "este", "sí", "porque", "esta", "entre", "cuando", "muy", "sin", "sobre", "también", "me", "hasta", "hay", "donde", "quien", "desde", "todo", "nos", "durante", "todos", "uno", "les", "ni", "contra", "otros", "ese", "eso", "ante", "ellos", "e", "esto", "mí", "antes", "algunos", "qué", "unos", "yo", "otro", "otras", "otra", "él", "tanto", "esa", "estos", "mucho", "quienes", "nada", "muchos", "cual", "poco", "ella", "estar", "estas", "algunas", "algo", "nosotros", "mi", "mis", "tú", "te", "ti", "tu", "tus", "ellas", "nosotras", "vosotros", "vosotras", "os", "mío", "mía", "míos", "mías", "tuyo", "tuya", "tuyos", "tuyas", "suyo", "suya", "suyos", "suyas", "nuestro", "nuestra", "nuestros", "nuestras", "vuestro", "vuestra", "vuestros", "vuestras", "esos", "esas", "estoy", "estás", "está", "estamos", "estáis", "están", "esté", "estés", "estemos", "estéis", "estén", "estaré", "estarás", "estará", "estaremos", "estaréis", "estarán", "estaría", "estarías", "estaríamos", "estaríais", "estarían", "estaba", "estabas", "estábamos", "estabais", "estaban", "estuve", "estuviste", "estuvo", "estuvimos", "estuvisteis", "estuvieron", "estuviera", "estuvieras", "estuviéramos", "estuvierais", "estuvieran", "estuviese", "estuvieses", "estuviésemos", "estuvieseis", "estuviesen", "estando", "estado", "estada", "estados", "estadas", "estad", "he", "has", "ha", "hemos", "habéis", "han", "haya", "hayas", "hayamos", "hayáis", "hayan", "habré", "habrás", "habrá", "habremos", "habréis", "habrán", "habría", "habrías", "habríamos", "habríais", "habrían", "había", "habías", "habíamos", "habíais", "habían", "hube", "hubiste", "hubo", "hubimos", "hubisteis", "hubieron", "hubiera", "hubieras", "hubiéramos", "hubierais", "hubieran", "hubiese", "hubieses", "hubiésemos", "hubieseis", "hubiesen", "habiendo", "habido", "habida", "habidos", "habidas", "soy", "eres", "es", "somos", "sois", "son", "sea", "seas", "seamos", "seáis", "sean", "seré", "serás", "será", "seremos", "seréis", "serán", "sería", "serías", "seríamos", "seríais", "serían", "era", "eras", "éramos", "erais", "eran", "fui", "fuiste", "fue", "fuimos", "fuisteis", "fueron", "fuera", "fueras", "fuéramos", "fuerais", "fueran", "fuese", "fueses", "fuésemos", "fueseis", "fuesen", "siendo", "sido", "tengo", "tienes", "tiene", "tenemos", "tenéis", "tienen", "tenga", "tengas", "tengamos", "tengáis", "tengan", "tendré", "tendrás", "tendrá", "tendremos", "tendréis", "tendrán", "tendría", "tendrías", "tendríamos", "tendríais", "tendrían", "tenía", "tenías", "teníamos", "teníais", "tenían", "tuve", "tuviste", "tuvo", "tuvimos", "tuvisteis", "tuvieron", "tuviera", "tuvieras", "tuviéramos", "tuvierais", "tuvieran", "tuviese", "tuvieses", "tuviésemos", "tuvieseis", "tuviesen", "teniendo", "tenido", "tenida", "tenidos", "tenidas", "tened"]}
|
|
13
13
|
|
|
14
|
-
it("should remove the stopwords for the list of words to be filtered") { filter.filter("desde Santurce a Bilbao".split).
|
|
14
|
+
it("should remove the stopwords for the list of words to be filtered") { expect(filter.filter("desde Santurce a Bilbao".split)).to eq ["Santurce", "Bilbao"]}
|
|
15
15
|
|
|
16
16
|
end
|
|
17
17
|
|
|
@@ -21,7 +21,7 @@ describe Stopwords::Snowball::Filter do
|
|
|
21
21
|
|
|
22
22
|
subject { filter }
|
|
23
23
|
|
|
24
|
-
it("should remove the stopwords for the list of words to be filtered") { filter.filter("desde Santurce a Bilbao".split).
|
|
24
|
+
it("should remove the stopwords for the list of words to be filtered") { expect(filter.filter("desde Santurce a Bilbao".split)).to eq ["Bilbao"]}
|
|
25
25
|
|
|
26
26
|
end
|
|
27
27
|
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: stopwords-filter
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.4.
|
|
4
|
+
version: 0.4.1
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- David J. Brenes
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date:
|
|
11
|
+
date: 2017-02-16 00:00:00.000000000 Z
|
|
12
12
|
dependencies: []
|
|
13
13
|
description: Small library that allows you to create a simple stopwords filter or
|
|
14
14
|
use some based on Snowball stopwords lists
|