skinny_jeans 0.9.1 → 0.9.2

data/VERSION

@@ -1 +1 @@
-0.9.1
+0.9.2

data/lib/skinny_jeans/string_parser.rb

@@ -40,7 +40,11 @@ module SkinnyJeans
         if _uri.query.present?
           _cgi = CGI.parse(_uri.query)
           if _cgi[param_name]
-            val = URI.decode(_cgi[param_name].join).strip.downcase
+            begin
+              val = URI.decode(_cgi[param_name].join).strip.downcase
+            rescue ArgumentError => e
+              puts "couldn't parse #{_cgi[param_name]}, must not be utf8"
+            end
             return (!val.nil? && val!='' ? val : nil)
           end
         end

data/test/skinny_jeans_string_parser_test.rb

@@ -56,9 +56,12 @@ class SkinnyJeans::StringParserTest < Test::Unit::TestCase
     assert_equal "hp coupns", SkinnyJeans::StringParser.return_param_from_valid_url_or_path("http://www.bing.com/search?q=hp+coupns&go=&form=QBLH&qs=n&sk=&sc=8-6","q")
     assert_equal "dv6 coupon", SkinnyJeans::StringParser.return_param_from_valid_url_or_path("http://www.google.com/url?sa=t&source=web&cd=1&ved=0CCEQFjAA&url=http%3A%2F%2Fdealzon.com%2Fdeals%2Fhp-dv6-laptop&rct=j&q=dv6%20coupon&ei=1Pz7TKb5AoP7lwfEoeSgBQ&usg=AFQjCNGFVL4PvZ59hbxkCFVdmHMayEe3UQ&sig2=Vs7s9a1z2Elm23NVffMJ8A","q")
     assert_equal "dv6 coupon", SkinnyJeans::StringParser.return_param_from_valid_url_or_path("http://www.google.com/url?sa=t&source=web&cd=1&sqi=2&ved=0CCAQFjAA&url=http%3A%2F%2Fdealzon.com%2Fdeals%2Fhp-dv6-laptop&rct=j&q=dv6%20coupon&ei=xyT7TO7kEYGKlwfT9tSPDA&usg=AFQjCNGFVL4PvZ59hbxkCFVdmHMayEe3UQ&sig2=7pnUG3YTE8sHONsIqLl1sg","q")
-    
+
     assert_equal "dv6 coupon", SkinnyJeans::StringParser.return_param_from_valid_url_or_path("http://www.google.com/url?sa=t&source=web&cd=1&sqi=2&ved=0CCAQFjAA&url=http%3A%2F%2Fdealzon.com%2Fdeals%2Fhp-dv6-laptop&rct=j&q=dv6%20coupon%20&ei=xyT7TO7kEYGKlwfT9tSPDA&usg=AFQjCNGFVL4PvZ59hbxkCFVdmHMayEe3UQ&sig2=7pnUG3YTE8sHONsIqLl1sg","q")
-    
+
+    # this search term has chinese characters in it, as of 2011-04-13, we are just returning nil for them
+    assert_equal nil, SkinnyJeans::StringParser.return_param_from_valid_url_or_path("http://www.google.com.hk/search?q=vostro+3400+3450+%C7%F8%B1%F0&client=aff-9991&ie=GB2312&oe=utf8&hl=zh-CN&newwindow=1&channel=searchbutton","q")
+
   end
 
   def test_extract_search_query

data/test/skinny_jeans_test.rb

@@ -10,7 +10,8 @@ class SkinnyJeansTest < Test::Unit::TestCase
     db_path = File.expand_path(File.dirname(__FILE__) + "/more_sample_data/skinny_jeans_deal_show.db")
     FileUtils.rm(db_path) if File.exists?(db_path)
     # broken_access_big.log is 337,925 lines
-    _logfile_path = File.expand_path(File.dirname(__FILE__) + "/more_sample_data/broken_access_big.log")
+    # _logfile_path = File.expand_path(File.dirname(__FILE__) + "/more_sample_data/broken_access_big.log")
+    _logfile_path = File.expand_path(File.dirname(__FILE__) + "/more_sample_data/another_broken_access_april_12.log")
     puts db_path.inspect
     sj=SkinnyJeans::LogParser.execute(_logfile_path, sqlite_skinny_jeans = db_path, path_regexp = /\s\/deals\/(.*)\sHTTP/, date_regexp = /\[(\d.*\d)\]/)
   end

metadata

@@ -1,12 +1,8 @@
 --- !ruby/object:Gem::Specification 
 name: skinny_jeans
 version: !ruby/object:Gem::Version 
-  prerelease: false
-  segments: 
-  - 0
-  - 9
-  - 1
-  version: 0.9.1
+  prerelease: 
+  version: 0.9.2
 platform: ruby
 authors: 
 - Jonathan Otto
@@ -14,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-03-16 00:00:00 -05:00
+date: 2011-04-13 00:00:00 -05:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -25,10 +21,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 1
-        - 3
-        - 3
         version: 1.3.3
   type: :runtime
   version_requirements: *id001
@@ -40,10 +32,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 3
-        - 0
-        - 0
         version: 3.0.0
   type: :runtime
   version_requirements: *id002
@@ -55,10 +43,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 1
-        - 0
-        - 0
         version: 1.0.0
   type: :runtime
   version_requirements: *id003
@@ -70,10 +54,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 1
-        - 0
-        - 1
         version: 1.0.1
   type: :runtime
   version_requirements: *id004
@@ -111,21 +91,17 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      segments: 
-      - 0
       version: "0"
 required_rubygems_version: !ruby/object:Gem::Requirement 
   none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      segments: 
-      - 0
       version: "0"
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 1.6.2
 signing_key: 
 specification_version: 3
 summary: Fast webserver log parser for persisting daily pageviews per path to sqlite