anystyle-parser 0.0.1 → 0.0.2

data/README.md

@@ -29,7 +29,7 @@ recommended to install Kyoto Cabinet and the `kyotocabinet-ruby` gem.
 The database file will be created the first time you access the dictionary;
 note that you will need write permissions in the directory where the file
 is to be created. You can change the Dictionary's default path in the
-Dictrionary's options:
+Dictionary's options:
 
     Anystyle::Parser::Dictionary.instance.options[:path]
 
@@ -72,7 +72,17 @@ The following irb sessions illustrates some parser goodness:
     => "Jorge"
     > b[0].author.to_s
     => "Liu, Dong C. and Nocedal, Jorge"
-
+    > puts Anystyle.parse('Auster, Paul. The Art of Hunger. Expanded. New York: Penguin, 1997.', :bibtex).to_s
+    @book{2162008820,
+      author = {Auster, Paul},
+      title = {The Art of Hunger},
+      location = {New York},
+      publisher = {Penguin},
+      edition = {Expanded},
+      year = {1997}
+    }
+    => nil
+    
 ### Unhappy with the results?
 
 Citation references come in many forms, so, inevitably, you will find data
@@ -117,6 +127,8 @@ data again:
     > Anystyle.parse 'John Lafferty, Andrew McCallum, and Fernando Pereira. 2001. Conditional random fields: probabilistic models for segmenting and labeling sequence data. In Proceedings of the International Conference on Machine Learning, pages 282-289. Morgan Kaufmann, San Francisco, CA.'
     => [{:author=>"John Lafferty and Andrew McCallum and Fernando Pereira", :title=>"Conditional random fields: probabilistic models for segmenting and labeling sequence data", :booktitle=>"Proceedings of the International Conference on Machine Learning", :pages=>"282--289", :publisher=>"Morgan Kaufmann", :location=>"San Francisco, CA", :year=>2001, :type=>:inproceedings}]
 
+If you want to make Anystyle-Parser smarter, please consider sending us your
+tagged references (see below). 
 
 Contributing
 ------------
@@ -132,6 +144,10 @@ If you've found a bug or have a question, please open an issue on the
 Or, for extra credit, clone the Anystyle-Parser repository, write a failing
 example, fix the bug and submit a pull request.
 
+If you want to contribute tagged references, please either add them to
+`resources/train.txt` or create a new file in the `resources` directory
+and open a pull request on GitHub.
+
 
 License
 -------

data/Rakefile

@@ -0,0 +1,18 @@
+lib = File.expand_path('../lib/', __FILE__)
+$:.unshift lib unless $:.include?(lib)
+
+require 'rake/clean'
+
+require 'anystyle/parser/version'
+
+task :build => [:clean] do
+  system 'gem build anystyle-parser.gemspec'
+end
+
+task :release => [:build] do
+  system "git tag #{Anystyle::Parser::VERSION}"
+  system "gem push anystyle-parser-#{Anystyle::Parser::VERSION}.gem"
+end
+
+CLEAN.include('*.gem')
+CLEAN.include('*.rbc')

data/lib/anystyle/parser/normalizer.rb

@@ -136,7 +136,7 @@ module Anystyle
 				s, n, ns, cc = StringScanner.new(names), '', [], 0
 				until s.eos?
 					case
-					when s.scan(/,?\s*and\b|&/)
+					when s.scan(/,?\s*(and\b|&)/)
 						ns << n
 						n, cc = '', 0
 					when s.scan(/\s+/)
@@ -144,14 +144,16 @@ module Anystyle
 					when s.scan(/,?\s*(jr|sr|ph\.?d|m\.?d|esq)\.?/i)
 						n << s.matched
 					when s.scan(/,/)
-						if cc > 0 || n =~ /\w\w+\s+\w\w+/
+						if cc > 0 || (n =~ /\S{2,}\s+\S{2,}/ && s.rest !~ /^\s*\w+(\.|,|$)/)
 							ns << n
 							n, cc = '', 0							
 						else
 							n << s.matched
 							cc += 1
 						end
-					when s.scan(/\w+/), s.scan(/./)
+					when s.scan(/\w+/)
+						n << s.matched
+					when  s.scan(/./)
 						n << s.matched
 					end
 				end

data/lib/anystyle/parser/version.rb

@@ -1,5 +1,5 @@
 module Anystyle
   module Parser
-    VERSION = '0.0.1'.freeze
+    VERSION = '0.0.2'.freeze
   end
 end

data/spec/anystyle/parser/normalizer_spec.rb

@@ -29,6 +29,26 @@ module Anystyle
 					Normalizer.instance.tokenize_names('A, B, C').should == ['A, B', ' C']
 				end
 
+				it "tokenizes 'Aa Bb, C.'" do
+					Normalizer.instance.tokenize_names('Aa Bb, C.').should == ['Aa Bb, C.']
+				end
+				
+				it "tokenizes 'Aa Bb, Cc Dd, and E F G'" do
+					Normalizer.instance.tokenize_names('Aa Bb, C D, and E F G').should == ['Aa Bb', ' C D', ' E F G']
+				end
+				
+				[
+					['Poe, Edgar A.', ['Poe, Edgar A.']],
+					['Edgar A. Poe', ['Edgar A. Poe']],
+					['Edgar A. Poe, Herman Melville', ['Edgar A. Poe', ' Herman Melville']],
+					['Poe, Edgar A., Melville, Herman', ['Poe, Edgar A.', ' Melville, Herman']],
+					['Aeschlimann Magnin, E.', ['Aeschlimann Magnin, E.']]
+				].each do |name, tokens|
+					it "tokenizes #{name.inspect}" do
+						Normalizer.instance.tokenize_names(name).should == tokens
+					end
+				end
+				
 			end
 		end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: anystyle-parser
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-09-05 00:00:00.000000000Z
+date: 2011-09-06 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bibtex-ruby
-  requirement: &2152150220 !ruby/object:Gem::Requirement
+  requirement: &2153531180 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,10 +21,10 @@ dependencies:
         version: '1.3'
   type: :runtime
   prerelease: false
-  version_requirements: *2152150220
+  version_requirements: *2153531180
 - !ruby/object:Gem::Dependency
   name: wapiti
-  requirement: &2152110260 !ruby/object:Gem::Requirement
+  requirement: &2153529340 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,10 +32,10 @@ dependencies:
         version: '0.0'
   type: :runtime
   prerelease: false
-  version_requirements: *2152110260
+  version_requirements: *2153529340
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &2152107240 !ruby/object:Gem::Requirement
+  requirement: &2153528780 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -43,10 +43,10 @@ dependencies:
         version: '0.9'
   type: :development
   prerelease: false
-  version_requirements: *2152107240
+  version_requirements: *2153528780
 - !ruby/object:Gem::Dependency
   name: racc
-  requirement: &2152096280 !ruby/object:Gem::Requirement
+  requirement: &2153528020 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -54,10 +54,10 @@ dependencies:
         version: '1.4'
   type: :development
   prerelease: false
-  version_requirements: *2152096280
+  version_requirements: *2153528020
 - !ruby/object:Gem::Dependency
   name: cucumber
-  requirement: &2152093880 !ruby/object:Gem::Requirement
+  requirement: &2153526200 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -65,10 +65,10 @@ dependencies:
         version: '1.0'
   type: :development
   prerelease: false
-  version_requirements: *2152093880
+  version_requirements: *2153526200
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &2152091560 !ruby/object:Gem::Requirement
+  requirement: &2153524800 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -76,10 +76,10 @@ dependencies:
         version: '2.6'
   type: :development
   prerelease: false
-  version_requirements: *2152091560
+  version_requirements: *2153524800
 - !ruby/object:Gem::Dependency
   name: ZenTest
-  requirement: &2152088380 !ruby/object:Gem::Requirement
+  requirement: &2153523460 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -87,7 +87,7 @@ dependencies:
         version: '4.6'
   type: :development
   prerelease: false
-  version_requirements: *2152088380
+  version_requirements: *2153523460
 description: A sophisticated parser for academic references based on conditional random
   fields.
 email:
@@ -105,6 +105,7 @@ files:
 - HISTORY.md
 - LICENSE
 - README.md
+- Rakefile
 - anystyle-parser.gemspec
 - features/step_definitions/parser_steps.rb
 - features/support/env.rb