sexmachine 0.0.4 → 0.0.5

data/Gemfile.lock

@@ -1,11 +1,13 @@
 PATH
   remote: .
   specs:
-    sexmachine (0.0.4)
+    sexmachine (0.0.5)
+      unicode_utils (>= 1.3.0)
 
 GEM
   remote: http://rubygems.org/
   specs:
+    unicode_utils (1.3.0)
 
 PLATFORMS
   ruby

data/README.rdoc

@@ -24,7 +24,13 @@ Additionally, you can give preference to specific countries:
   >> d.get_gender("Jamie", :great_britain)
    => :mostly_male
 
-If you have an alterative data file, you can pass that in as an optional argument to the Detector.
+If you have an alterative data file, you can pass that in as an optional filename argument to the Detector.  Additionally, you can create a detector that is not case sensitive (default *is* to be case sensitive):
+
+  >> d = SexMachine::Detector.new(:case_sensitive => false)
+  >> d.get_gender "sally"
+   => :female
+  >> d.get_gender "Sally"
+   => :female
 
 Try to avoid creating many Detectors, as each creation means reading in the data file.
 

data/lib/sexmachine/detector.rb

@@ -1,3 +1,5 @@
+require "unicode_utils/downcase"
+
 module SexMachine
 
   class Detector
@@ -7,9 +9,13 @@ module SexMachine
                   :greece, :russia, :belarus, :moldova, :ukraine, :armenia, :azerbaijan, :georgia, :the_stans, :turkey, :arabia, :israel, :china,
                   :india, :japan, :korea, :vietnam, :other_countries ]
 
-    def initialize(fname=nil)
-      fname ||= File.expand_path('../data/nam_dict.txt', __FILE__)
-      parse fname
+    def initialize(opts = {})
+      opts = {
+        :filename => File.expand_path('../data/nam_dict.txt', __FILE__),
+        :case_sensitive => true
+      }.merge(opts)
+      @case_sensitive = opts[:case_sensitive]
+      parse opts[:filename]
     end
     
     def parse(fname)
@@ -22,6 +28,8 @@ module SexMachine
     end
     
     def get_gender(name, country = nil)
+      name = UnicodeUtils.downcase(name) unless @case_sensitive
+
       if not @names.has_key?(name)
         :andy
       elsif country.nil?
@@ -44,13 +52,14 @@ module SexMachine
       
       parts = line.split(" ").select { |p| p.strip != "" }
       country_values = line.slice(30, line.length)
+      name = @case_sensitive ? parts[1] : UnicodeUtils.downcase(parts[1])
 
       case parts[0]
-        when "M" then set(parts[1], :male, country_values)
-        when "1M", "?M" then set(parts[1], :mostly_male, country_values)
-        when "F" then set(parts[1], :female, country_values)
-        when "1F", "?F" then set(parts[1], :mostly_female, country_values)
-        when "?" then set(parts[1], :andy, country_values)
+        when "M" then set(name, :male, country_values)
+        when "1M", "?M" then set(name, :mostly_male, country_values)
+        when "F" then set(name, :female, country_values)
+        when "1F", "?F" then set(name, :mostly_female, country_values)
+        when "?" then set(name, :andy, country_values)
         else raise "Not sure what to do with a sex of #{parts[0]}"
       end
     end

data/lib/sexmachine/version.rb

@@ -1,3 +1,3 @@
 module SexMachine
-  VERSION = "0.0.4"
+  VERSION = "0.0.5"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: sexmachine
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.5
   prerelease: 
 platform: ruby
 authors:
@@ -9,8 +9,19 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-07-25 00:00:00.000000000Z
-dependencies: []
+date: 2012-07-26 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: unicode_utils
+  requirement: &70220187561160 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.3.0
+  type: :runtime
+  prerelease: false
+  version_requirements: *70220187561160
 description: Get gender from first name.
 email: brian.muller@livingsocial.com
 executables: []