twitter-text 1.4.10 → 1.4.11

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    twitter-text (1.4.10)
+    twitter-text (1.4.11)
       activesupport
 
 GEM

data/lib/regex.rb

@@ -97,13 +97,13 @@ module Twitter
       regex_range(0x2F800, 0x2FA1F), regex_range(0x3005), regex_range(0x303B) # Kanji (CJK supplement)
     ].join('').freeze
 
-    HASHTAG_BOUNDARY = /(?:\A|\z|#{REGEXEN[:spaces]}|「|」|。|、|\.|!|\?|！|？|,)/
+    HASHTAG_BOUNDARY = /(?:\A|\z|#{REGEXEN[:spaces]}|[「」。、.,!?！？:;"'])/
 
     # A hashtag must contain latin characters, numbers and underscores, but not all numbers.
     HASHTAG_ALPHA = /[a-z_#{LATIN_ACCENTS}#{NON_LATIN_HASHTAG_CHARS}#{CJ_HASHTAG_CHARACTERS}]/io
     HASHTAG_ALPHANUMERIC = /[a-z0-9_#{LATIN_ACCENTS}#{NON_LATIN_HASHTAG_CHARS}#{CJ_HASHTAG_CHARACTERS}]/io
 
-    HASHTAG = /(#{HASHTAG_BOUNDARY})(#|＃)(#{HASHTAG_ALPHANUMERIC}*#{HASHTAG_ALPHA}#{HASHTAG_ALPHANUMERIC}*)(?=#{HASHTAG_BOUNDARY})/io
+    HASHTAG = /(#{HASHTAG_BOUNDARY})(#|＃)(#{HASHTAG_ALPHANUMERIC}*#{HASHTAG_ALPHA}#{HASHTAG_ALPHANUMERIC}*)/io
 
     REGEXEN[:auto_link_hashtags] = /#{HASHTAG}/io
 

data/spec/extractor_spec.rb

@@ -228,11 +228,11 @@ describe Twitter::Extractor do
         end
 
         it "should not allow the multiplication character" do
-          @extractor.extract_hashtags("#pre#{Twitter::Unicode::U00D7}post").should == []
+          @extractor.extract_hashtags("#pre#{Twitter::Unicode::U00D7}post").should == ["pre"]
         end
 
         it "should not allow the division character" do
-          @extractor.extract_hashtags("#pre#{Twitter::Unicode::U00F7}post").should == []
+          @extractor.extract_hashtags("#pre#{Twitter::Unicode::U00F7}post").should == ["pre"]
         end
       end
 
@@ -241,6 +241,10 @@ describe Twitter::Extractor do
     it "should not extract numeric hashtags" do
       @extractor.extract_hashtags("#1234").should == []
     end
+
+    it "should extract hashtag followed by punctuations" do
+      @extractor.extract_hashtags("#test1: #test2; #test3\"").should == ["test1", "test2" ,"test3"]
+    end
   end
 
   describe "hashtags with indices" do
@@ -283,11 +287,11 @@ describe Twitter::Extractor do
         end
 
         it "should not allow the multiplication character" do
-          not_match_hashtag_in_text("#pre#{[0xd7].pack('U')}post")
+          match_hashtag_in_text("pre", "#pre#{[0xd7].pack('U')}post", 0)
         end
 
         it "should not allow the division character" do
-          not_match_hashtag_in_text("#pre#{[0xf7].pack('U')}post")
+          match_hashtag_in_text("pre", "#pre#{[0xf7].pack('U')}post", 0)
         end
       end
     end
@@ -296,4 +300,4 @@ describe Twitter::Extractor do
       not_match_hashtag_in_text("#1234")
     end
   end
-end
+end

data/twitter-text.gemspec

@@ -1,6 +1,6 @@
 spec = Gem::Specification.new do |s|
   s.name = "twitter-text"
-  s.version = "1.4.10"
+  s.version = "1.4.11"
   s.authors = ["Matt Sanford", "Patrick Ewing", "Ben Cherry", "Britt Selvitelle",
                "Raffi Krikorian", "J.P. Cummins", "Yoshimasa Niwa", "Keita Fujii"]
   s.email = ["matt@twitter.com", "patrick.henry.ewing@gmail.com", "bcherry@gmail.com", "bs@brittspace.com",

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: twitter-text
 version: !ruby/object:Gem::Version 
-  hash: 19
+  hash: 17
   prerelease: 
   segments: 
   - 1
   - 4
-  - 10
-  version: 1.4.10
+  - 11
+  version: 1.4.11
 platform: ruby
 authors: 
 - Matt Sanford
@@ -22,7 +22,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-09-20 00:00:00 -07:00
+date: 2011-09-26 00:00:00 -07:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency