stopwords-filter 0.6.0 → 0.7.0
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/CHANGELOG +4 -0
- data/README.md +1 -0
- data/VERSION +1 -1
- data/lib/stopwords/snowball/locales/zh.csv +1 -0
- data/lib/stopwords/snowball/wordsieve.rb +9 -9
- metadata +3 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 558571708b592d1e62ad33001d020e5ff5b92175
|
4
|
+
data.tar.gz: 3a503dfd7e0a56ee8563899f23b49df827538675
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 40fb7adfbc7debddc054e1555b21b243e121dda522749cf166520a4c06f2b8fa23776cef9b3dc69701f0f8bb29464c2d319816e7a57d6e69ac669c64b7ebc02c
|
7
|
+
data.tar.gz: 11153eebc434e912e271b2f57436ad1927e80aa381b7352356847965bb82e08b9ac5dd846d1a283ef47da3722774bcb39c8dafa2470d562dcea93f0735066ecb
|
data/CHANGELOG
CHANGED
data/README.md
CHANGED
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.
|
1
|
+
0.7.0
|
@@ -0,0 +1 @@
|
|
1
|
+
的,地,得,和,跟,与,及,向,并,等,更,已,含,做,我,你,他,她,们,某,该,各,每,这,那,哪,什,么,谁,年,月,日,时,分,秒,几,多,来,在,就,又,很,呢,吧,吗,了,嘛,哇,儿,哼,啊,嗯,是,着,都,不,说,也,看,把,还,个,有,小,到,一,为,中,于,对,会,之,第,此,或,共,按,请
|
@@ -1,19 +1,19 @@
|
|
1
1
|
module Stopwords
|
2
2
|
module Snowball
|
3
|
-
class
|
4
|
-
def initialize
|
5
|
-
@filters = Dir[File.dirname(__FILE__)
|
6
|
-
lang = File.basename(file, '.csv')
|
7
|
-
filters[lang] = Stopwords::Snowball::Filter.new lang, custom_list
|
3
|
+
class WordSieve
|
4
|
+
def initialize(custom_list = [])
|
5
|
+
@filters = Dir["#{File.dirname(__FILE__)}/locales/*.csv"].each_with_object({}) do |file, filters|
|
6
|
+
lang = File.basename(file, '.csv')
|
7
|
+
filters[lang.to_sym] = Stopwords::Snowball::Filter.new lang, custom_list
|
8
8
|
end
|
9
9
|
end
|
10
10
|
|
11
|
-
def stopword?
|
12
|
-
args[:lang] ? @filters[args[:lang]].stopword?(args[:word]
|
11
|
+
def stopword?(args = {})
|
12
|
+
args[:lang] ? @filters[args[:lang]].stopword?(args[:word]) : false
|
13
13
|
end
|
14
14
|
|
15
|
-
def filter
|
16
|
-
args[:lang] ? @filters[args[:lang]].filter(args[:words]
|
15
|
+
def filter(args = {})
|
16
|
+
args[:lang] ? @filters[args[:lang]].filter(args[:words]) : args[:words]
|
17
17
|
end
|
18
18
|
end
|
19
19
|
end
|
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
|
+
version: 0.7.0
|
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: 2021-
|
11
|
+
date: 2021-12-19 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
|
@@ -59,6 +59,7 @@ files:
|
|
59
59
|
- lib/stopwords/snowball/locales/th.csv
|
60
60
|
- lib/stopwords/snowball/locales/tr.csv
|
61
61
|
- lib/stopwords/snowball/locales/vi.csv
|
62
|
+
- lib/stopwords/snowball/locales/zh.csv
|
62
63
|
- lib/stopwords/snowball/wordsieve.rb
|
63
64
|
- spec/lib/filter_spec.rb
|
64
65
|
- spec/lib/snowball_filter_spec.rb
|