unsupervised-language-detection 0.0.3 → 0.0.4
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.
|
@@ -7,8 +7,6 @@ class String
|
|
|
7
7
|
self.normalize_tweet.scan(/.{#{n}}/)
|
|
8
8
|
end
|
|
9
9
|
|
|
10
|
-
private
|
|
11
|
-
|
|
12
10
|
# TODO: Try not normalizing out all non-ASCII characters! Should significantly reduce false positive rate.
|
|
13
11
|
def normalize_tweet
|
|
14
12
|
self.remove_tweeters.remove_links.remove_hashtags.downcase.gsub(/\s/, " ").gsub(/[^a-z0-9\s]/, "")
|
metadata
CHANGED
|
@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
|
|
|
5
5
|
segments:
|
|
6
6
|
- 0
|
|
7
7
|
- 0
|
|
8
|
-
-
|
|
9
|
-
version: 0.0.
|
|
8
|
+
- 4
|
|
9
|
+
version: 0.0.4
|
|
10
10
|
platform: ruby
|
|
11
11
|
authors:
|
|
12
12
|
- Edwin Chen
|
|
@@ -14,7 +14,7 @@ autorequire:
|
|
|
14
14
|
bindir: bin
|
|
15
15
|
cert_chain: []
|
|
16
16
|
|
|
17
|
-
date: 2011-07-
|
|
17
|
+
date: 2011-07-23 00:00:00 -07:00
|
|
18
18
|
default_executable:
|
|
19
19
|
dependencies: []
|
|
20
20
|
|