postrank-uri_spec.rb in postrank-uri-1.0.6

- old
+ new

@@ -110,12 +110,31 @@
 
       it "should remove awesm/sms parameters" do
         c('igvita.com/?id=a&utm_source=a&awesm=b').should == 'http://igvita.com/?id=a'
         c('igvita.com/?id=a&sms_ss=a').should == 'http://igvita.com/?id=a'
       end
+    end
 
+    context "hashbang" do
+      it "should rewrite twitter links to crawlable versions" do
+        c('http://twitter.com/#!/igrigorik').should == 'http://twitter.com/igrigorik'
+        c('http://twitter.com/#!/a/statuses/1').should == 'http://twitter.com/a/statuses/1'
+        c('http://nontwitter.com/#!/a/statuses/1').should == 'http://nontwitter.com/#!/a/statuses/1'
+      end
     end
+
+    context "embedded links" do
+      it "should extract embedded redirects from Google News" do
+        u = c('http://news.google.com/news/url?sa=t&fd=R&&url=http://www.ctv.ca/CTVNews/Politics/20110111/')
+        u.should == 'http://www.ctv.ca/CTVNews/Politics/20110111/'
+      end
+
+      it "should extract embedded redirects from xfruits.com" do
+        u = c('http://xfruits.com/MrGroar/?url=http%3A%2F%2Faap.lesroyaumes.com%2Fdepeches%2Fdepeche351820908.html')
+        u.should == 'http://aap.lesroyaumes.com/depeches/depeche351820908.html'
+      end
+    end
   end
 
   context "clean" do
     def c(uri)
       PostRank::URI.clean(uri)
@@ -167,9 +186,13 @@
       end
 
       it "should not pickup bad TLDS" do
         e('stuff.zz a.b.c d.zq').should be_empty
       end
+    end
+
+    it "should extract twitter links with hashbangs" do
+      e('test http://twitter.com/#!/igrigorik').should include('http://twitter.com/igrigorik')
     end
 
     it "should handle a URL that comes after text without a space" do
       e("text:http://spn.tw/tfnLT").should include("http://spn.tw/tfnLT")
       e("text;http://spn.tw/tfnLT").should include("http://spn.tw/tfnLT")