ark_tweet_nlp 0.2.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 854e565fc320e10f108899d9fd46ee4e574224e0
-  data.tar.gz: b0ed001019d18998339e89360b72a74fc66d82c3
+  metadata.gz: f1b3260363eb025c2536fa1e6285a19a722fe2b5
+  data.tar.gz: c3829a1dece24316594a9559cde223dc99ce81d5
 SHA512:
-  metadata.gz: b081388bbaa6a4dc4b4146816225cc1e55d99a84ad1b4a149702a031fb02db6532a8c1075dcc7a7a6efda47285110e0fbe139dd6fbda817d809788e3675420b4
-  data.tar.gz: 10ac78c85e9c80e428d6211e72a90fa5651dfa6b665e979334566d2ca217cfb48e2afaaa0e60bfe4efc15722341fcde5211c503859b42a444622b0ba8eada3bf
+  metadata.gz: 70b20f9826d29940bd7e05a6ab056a1e9d6328c2fbfcffec9181d1e6f18a125e90e8a882d8c93d75c9c96551845181e270ecbb5be72af7fad71ed17241084457
+  data.tar.gz: ab88602b2c048593b668c2967d0356a61b9501551261ecb25d6c96a1fe673c4f5f61d739b2335306c0d1f6fb3bd377e1648ece8e5356e74cf211272067dd62fb

data/lib/ark_tweet_nlp/parser.rb

@@ -59,8 +59,7 @@ module ArkTweetNlp
 
     def Parser.run_tagger text
       #FIXME: regex destroyes urls...
-      text.gsub /[^\w\s\d#]/, ''
-      `echo "#{text}" | #{TAGGER_PATH}`
+      `echo "#{text.gsub(/[^\w\s\d#]/, '')}" | #{TAGGER_PATH}`
     end
 
     def Parser.convert_line line

data/lib/ark_tweet_nlp/version.rb

@@ -1,3 +1,3 @@
 module ArkTweetNlp
-  VERSION = "0.2.0"
+  VERSION = "0.2.1"
 end

data/spec/parser_spec.rb

@@ -15,14 +15,32 @@ describe ArkTweetNlp::Parser do
     it "suports urls" do
       expect(ArkTweetNlp::Parser.find_tags("I think I haven't had a segmentation fault in years http://t.co/COjaaFj6Ib")).to eq(       [{"I"=>:O,
          "think"=>:V,
-         "haven't"=>:V,
+         "havent"=>:V,
          "had"=>:V,
          "a"=>:D,
          "segmentation"=>:N,
          "fault"=>:N,
          "in"=>:P,
          "years"=>:N,
-         "http://t.co/COjaaFj6Ib"=>:U}])
+         "httptcoCOjaaFj6Ib"=>:"$"}])
+    end
+    it "removes ponctuation from the tweets" do
+      expect(ArkTweetNlp::Parser.find_tags("Delayed... And waiting on a tire from Louisville. \"You can't be serious #Disappointed #pissed #letdown http://t.co/BFqsPZmr8m")).to eq([{"Delayed"=>:A,
+         "And"=>:&,
+         "waiting"=>:V,
+         "on"=>:P,
+         "a"=>:D,
+         "tire"=>:N,
+         "from"=>:P,
+         "Louisville"=>:^,
+         "You"=>:O,
+         "cant"=>:V,
+         "be"=>:V,
+         "serious"=>:A,
+         "#Disappointed"=>:"#",
+         "#pissed"=>:"#",
+         "#letdown"=>:"#",
+         "httptcoBFqsPZmr8m"=>:"#"}])
     end
     it "tags multiple tweets per line" do
       expect(ArkTweetNlp::Parser.find_tags("faceboooooooook is awesome\nfaceboooooooook is awesome")).to eq([{'faceboooooooook' => :^,'is' => :V,'awesome' => :A},{'faceboooooooook' => :^,'is' => :V,'awesome' => :A} ])

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ark_tweet_nlp
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors:
 - Bernardo