bougyman-name_parse 0.0.4 → 0.0.5

data/AUTHORS

@@ -1,5 +1,6 @@
 Following persons have contributed to name_parse.
 (Sorted by number of submitted patches, then alphabetically)
 
-     7 TJ Vanderpoel <bougy.man@gmail.com>
+    10 TJ Vanderpoel <bougy.man@gmail.com>
      2 Jayson Vaughn (thedonvaughn) <jayson.vaughn@gmail.com>
+     2 TJ Vanderpoel <bougyman@zero.(none)>

data/CHANGELOG

@@ -1,3 +1,23 @@
+[736bf3d | Thu May 07 16:54:52 UTC 2009] TJ Vanderpoel <bougyman@zero.(none)>
+
+  * completed refactoring to methodized matchers in #parse
+
+[e58f6e4 | Thu May 07 16:29:25 UTC 2009] TJ Vanderpoel <bougyman@zero.(none)>
+
+  * continued to refacor into a methodized pattern for matching in #parse
+
+[835e508 | Thu May 07 03:29:00 UTC 2009] TJ Vanderpoel <bougy.man@gmail.com>
+
+  * ignore csv files
+
+[fcb13a0 | Thu May 07 03:28:14 UTC 2009] TJ Vanderpoel <bougy.man@gmail.com>
+
+  * added README as description
+
+[016010c | Thu May 07 03:18:51 UTC 2009] TJ Vanderpoel <bougy.man@gmail.com>
+
+  * Version 0.0.4
+
 [5d85b44 | Thu May 07 03:14:31 UTC 2009] TJ Vanderpoel <bougy.man@gmail.com>
 
   * methodized when match target for first_name.  TODO: make the other when matchers follow the same format

data/Rakefile

@@ -27,7 +27,7 @@ GEMSPEC = Gem::Specification.new{|s|
   s.name         = 'name_parse'
   s.author       = "TJ Vanderpoel"
   s.summary      = "Parse name strings into their constituent parts"
-  s.description  = s.summary
+  s.description  = File.read("README")
   s.email        = 'bougy.man@gmail.com'
   s.homepage     = 'http://github.com/bougyman/name_parse'
   s.platform     = Gem::Platform::RUBY

data/lib/name_parse/parser.rb

@@ -1,73 +1,91 @@
 module NameParse
   class Parser
     attr_reader :first, :last, :suffix, :prefix, :middle, :raw, :matched
+    attr_accessor :first_name_re, :last_name_re, :middle_name_re, :prefix_re
 
-    def initialize(name_string = nil)
-      @raw = name_string
-      parse(@raw) if @raw
+    def initialize(name_string = nil, options = {})
+      @options = options
+      @last_name_re = @options[:last_name_re] || /(?:(?:v[ao]n(?:\s+der?)?|de\s+la)\s+)?\w[-.'\w]+/i
+      @middle_name_re = @options[:middle_name_re] || /\w(?:\.|[-.'\w]+)?/
+      @prefix_re = @options[:prefix_re] || /(?:c\/o|dr|mrs?|ms|miss|mister|sgt|cpt|cpl)\.?/i
+      @first_name_re = @options[:first_name_re] || /\w[-.'\w]+/
+      parse(name_string) if name_string
     end
 
-    def prefix_re
-      /(?:c\/o|dr|mrs?|ms|miss|mister|sgt|cpt|cpl)\.?/i
-    end
-
-    def first_name_re
-      /\w[-.'\w]+/
-    end
-    
-    def first_last(match = nil)
-      if match.nil?
-        /^(#{first_name_re})\s+(#{last_name_re})$/
-      else
-        @matched = :first_last
-        @first, @last = match.to_a[1 .. 2]
-      end
-    end
-
-    def last_name_re
-      /(?:(?:v[ao]n(?:\s+der?)?|de\s+la)\s+)?\w[-.'\w]+/i
-    end
-
-    def middle_name_re
-      /\w(?:\.|[-.'\w]+)?/
-    end
-
-    def middle_i
-      return nil if middle.nil?
-      middle[0,1]
-    end
-    
     def parse(name)
+      @raw = name
       case name
       # just "Firstname Lastname"
       when first_last
         first_last($~)
       # Catch names with prefixes, no comma
-      when /^(#{prefix_re})\s+(#{first_name_re})\s+(#{last_name_re})$/
-        @prefix, @first, @last = $1, $2, $3
-        @matched = :pre_first_last
+      when pre_first_last
+        pre_first_last($~)
       # Catch names with prefixes and middle names, no comma
-      when /^(#{prefix_re})\s+(#{first_name_re})\s+(#{middle_name_re})\s+(#{last_name_re})$/
-        @prefix, @first, @middle, @last = $1, $2, $3, $4
-        @matched = :pre_first_mid_last
+      when pre_first_mid_last
+        pre_first_mid_last($~)
       # just "Firstname Middle Lastname"
-      when /^(#{first_name_re})\s+(#{middle_name_re})\s+(#{last_name_re})$/
-        @first, @middle, @last = $1, $2, $3
-        @matched = :first_mid_last
+      when first_mid_last
+        first_mid_last($~)
       # just "Lastname, Firstname (Middle)" middle is optional
-      when /^(#{last_name_re}),(?:\s+)?(#{first_name_re})(?:\s+(#{middle_name_re}))?$/
-        @first, @last, @middle = $2, $1, $3
-        @matched = :last_comma_first_mid
+      when last_comma_first_mid
+        last_comma_first_mid($~)
       # Comma with lots of lastnames, a first name, optional middle name
-      when /^((?:#{last_name_re}(?:\s+)?)+),(?:\s+)(#{first_name_re})(?:\s+(#{middle_name_re}))?$/
-        @first, @last, @middle = $2, $1, $3
-        @matched = :multi_last_comma
+      when multi_last_comma
+        multi_last_comma($~)
       else 
-        raise UnknownFormat, "Could not parse #{@raw_name}"
+        if @options[:raise_on_unknown]
+          raise UnknownFormat, "Could not parse #{@raw}"
+        else
+          @matched = :unknown
+          false
+        end
       end
     end
 
     alias :first_name :first
 
+    def middle_i
+      return nil if middle.nil?
+      middle[0,1]
+    end
+    
+    private
+    def first_last(match = nil)
+      return %r{^(#{first_name_re})\s+(#{last_name_re})$} if match.nil?
+      @first, @last = match[1 .. 2]
+      @matched = :first_last
+    end
+    
+    def pre_first_last(match = nil)
+      return %r{^(#{prefix_re})\s+(#{first_name_re})\s+(#{last_name_re})$} if match.nil?
+      @prefix, @first, @last = match[1 .. 3]
+      @matched = :pre_first_last
+    end
+
+    def pre_first_mid_last(match = nil)
+      return %r{^(#{prefix_re})\s+(#{first_name_re})\s+(#{middle_name_re})\s+(#{last_name_re})$} if match.nil?
+      @prefix, @first, @middle, @last = match[1 .. 4]
+      @matched = :pre_first_mid_last
+    end
+
+    def first_mid_last(match = nil)
+      return %r{^(#{first_name_re})\s+(#{middle_name_re})\s+(#{last_name_re})$} if match.nil?
+      @first, @middle, @last = match[1 .. 3]
+      @matched = :first_mid_last
+    end
+
+    def last_comma_first_mid(match = nil)
+      return %r{^(#{last_name_re}),(?:\s+)?(#{first_name_re})(?:\s+(#{middle_name_re}))?$} if match.nil?
+      @first, @last, @middle = match[2], match[1], match[3]
+      @matched = :last_comma_first_mid
+    end
+
+    def multi_last_comma(match = nil)
+      return %r{^((?:#{last_name_re}(?:\s+)?)+),(?:\s+)(#{first_name_re})(?:\s+(#{middle_name_re}))?$} if match.nil?
+      @first, @last, @middle = match[2], match[1], match[3]
+      @matched = :multi_last_comma
+    end
+
   end
 end

data/lib/name_parse/version.rb

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

data/name_parse.gemspec

@@ -2,12 +2,12 @@
 
 Gem::Specification.new do |s|
   s.name = %q{name_parse}
-  s.version = "0.0.4"
+  s.version = "0.0.5"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["TJ Vanderpoel"]
-  s.date = %q{2009-05-06}
-  s.description = %q{Parse name strings into their constituent parts}
+  s.date = %q{2009-05-07}
+  s.description = %q{========================================================= Name Parse Copyright (c) 2009 The Rubyists (Jayson Vaughn, Tj Vanderpoel, Michael Fellinger, Kevin Berry)  Distributed under the terms of the MIT License. ==========================================================  About ----- A ruby library for turning arbitrary name strings such as "Dr Helen Hunt", "Mr James T. Kirk" into a  standardized object usable as  parsed = NameParse::Parser.new("Dr Helen Hunt") puts "%s %s" % [parsed.first, parsed.last]   Requirements ------------ - ruby (>= 1.8)  Usage -----  Example of using on a list:  bougyman@zero:~/git_checkouts/name_parse$ irb -r lib/name_parse irb(main):001:0> list = ["Jayson Vaughn", "Dr Helen Hunt",  "Mr James T. Kirk"] => ["Jayson Vaughn", "Dr Helen Hunt", "Mr James T. Kirk"] irb(main):002:0> list.map { |n| p = NameParse[n]; [p.first, p.last] } => [["Jayson", "Vaughn"], ["Helen", "Hunt"], ["James", "Kirk"]]   Support ------- Home page at http://github.com/bougyman/name_parse #rubyists on FreeNode}
   s.email = %q{bougy.man@gmail.com}
   s.files = ["AUTHORS", "CHANGELOG", "MANIFEST", "README", "Rakefile", "lib/name_parse.rb", "lib/name_parse/error.rb", "lib/name_parse/parser.rb", "lib/name_parse/version.rb", "name_parse.gemspec", "spec/helper.rb", "spec/name_parse/parser.rb", "tasks/authors.rake", "tasks/bacon.rake", "tasks/changelog.rake", "tasks/copyright.rake", "tasks/gem.rake", "tasks/gem_installer.rake", "tasks/install_dependencies.rake", "tasks/manifest.rake", "tasks/rcov.rake", "tasks/release.rake", "tasks/reversion.rake", "tasks/setup.rake", "tasks/yard.rake"]
   s.has_rdoc = true

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: bougyman-name_parse
 version: !ruby/object:Gem::Version 
-  version: 0.0.4
+  version: 0.0.5
 platform: ruby
 authors: 
 - TJ Vanderpoel
@@ -9,11 +9,11 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-05-06 00:00:00 -07:00
+date: 2009-05-07 00:00:00 -07:00
 default_executable: 
 dependencies: []
 
-description: Parse name strings into their constituent parts
+description: "========================================================= Name Parse Copyright (c) 2009 The Rubyists (Jayson Vaughn, Tj Vanderpoel, Michael Fellinger, Kevin Berry)  Distributed under the terms of the MIT License. ==========================================================  About ----- A ruby library for turning arbitrary name strings such as \"Dr Helen Hunt\", \"Mr James T. Kirk\" into a  standardized object usable as  parsed = NameParse::Parser.new(\"Dr Helen Hunt\") puts \"%s %s\" % [parsed.first, parsed.last]   Requirements ------------ - ruby (>= 1.8)  Usage -----  Example of using on a list:  bougyman@zero:~/git_checkouts/name_parse$ irb -r lib/name_parse irb(main):001:0> list = [\"Jayson Vaughn\", \"Dr Helen Hunt\",  \"Mr James T. Kirk\"] => [\"Jayson Vaughn\", \"Dr Helen Hunt\", \"Mr James T. Kirk\"] irb(main):002:0> list.map { |n| p = NameParse[n]; [p.first, p.last] } => [[\"Jayson\", \"Vaughn\"], [\"Helen\", \"Hunt\"], [\"James\", \"Kirk\"]]   Support ------- Home page at http://github.com/bougyman/name_parse #rubyists on FreeNode"
 email: bougy.man@gmail.com
 executables: []