anystyle-parser 0.0.9 → 0.0.10

data/HISTORY.md

@@ -1,3 +1,7 @@
+0.0.10 / 2012-03-01
+===================
+* Added new output format: tags (to generate training data)
+
 0.0.9 / 2011-09-08
 ==================
 * Added year-range / page-range feature distinction

data/README.md

@@ -41,19 +41,19 @@ Usage
 
 You can access the main Anystyle-Parser instance at `Anystyle.parser`;
 the `#parse` method is also available via `Anystyle.parse`. For more complex
-requirements (e.g., if you need multiple Parser simultaneously) you can create
-your own instances from the `Anystyle::Parser::Parser` class.
+requirements (e.g., if you need multiple Parser instances simultaneously) you
+can create your own instances from the `Anystyle::Parser::Parser` class.
 
 The two fundamental methods you need to know about in order to use
 Anystyle-Parser are `#parse` and `#train` that both accept two arguments.
 
     Parser#parse(input, format = :hash)
-    Parser#train(input, truncate = false)
+    Parser#train(input = options[:training_data], truncate = true)
 
 `#parse` parses the passed-in input (either a filename, your reference strings,
 or an array of your reference strings) and returns the parsed data in the
 format specified as the second argument (supported formats include: *:hash*,
-*:bibtex*, and *:citeproc*).
+*:bibtex*, *:citeproc*, and *:tags*).
 
 `#train` allows you to easily train the Parser's CRF model. The first argument
 is either a filename or your data as a string; the format of training data

data/lib/anystyle/parser/parser.rb

@@ -3,7 +3,7 @@ module Anystyle
 
 		class Parser
 
-			@formats = [:bibtex, :hash, :citeproc].freeze
+			@formats = [:bibtex, :hash, :citeproc, :tags].freeze
 			
 			@defaults = {
 				:model => File.expand_path('../support/anystyle.mod', __FILE__),
@@ -233,7 +233,13 @@ module Anystyle
 			def format_citeproc(labels)
 				format_bibtex(labels).to_citeproc
 			end
-						
+			
+			def format_tags(labels)
+				labels.map do |line|
+					line.map { |label, token| "<#{label}>#{token}</#{label}>" }.join(' ')
+				end
+			end
+			
 		end
 
 	end

data/lib/anystyle/parser/version.rb

@@ -1,5 +1,5 @@
 module Anystyle
   module Parser
-    VERSION = '0.0.9'.freeze
+    VERSION = '0.0.10'.freeze
   end
 end

data/spec/anystyle/parser/parser_spec.rb

@@ -70,6 +70,35 @@ module Anystyle::Parser
 			it 'returns an array of labelled segments' do
 				subject.label(citation)[0].map(&:first).should == [:author, :title, :location, :publisher, :date, :pages]
 			end
+			
+			describe 'when passed more than one line' do
+				it 'returns two arrays' do
+					subject.label("foo\nbar").should have(2).elements
+				end
+			end
+
+			describe 'when passed invalid input' do
+				it 'returns an empty array for an empty string' do
+					subject.label('').should == []
+				end
+				
+				it 'returns an empty array for an empty line' do
+					subject.label("\n").should == []
+					subject.label("\n ").should == [[],[]]
+					subject.label(" \n ").should == [[],[]]
+					subject.label(" \n").should == [[]]
+				end
+
+				it 'does not fail for unrecognizable input' do
+					lambda { subject.label("@misc{70213094902020,\n") }.should_not raise_error
+					lambda { subject.label("doi = {DOI:10.1503/jpn.100140}\n}\n") }.should_not raise_error
+					
+					pending
+					lambda { subject.label("\n doi ") }.should_not raise_error
+				end
+			end
+
+			
 		end
 
 		describe "#parse" do
@@ -78,6 +107,12 @@ module Anystyle::Parser
 			it 'returns a hash of label/segment pairs by default' do
 				subject.parse(citation)[0].should == { :author => 'Perec, Georges', :title => 'A Void', :location => 'London', :publisher => 'The Harvill Press', :year => 1995, :pages => '108', :type => :book }
 			end
+			
+			describe 'using output format "tags"' do
+				it 'returns a tagged string' do
+					subject.parse(citation, :tags)[0].should == '<author>Perec, Georges.</author> <title>A Void.</title> <location>London:</location> <publisher>The Harvill Press,</publisher> <date>1995.</date> <pages>p.108.</pages>'
+				end
+			end
 		end
 
 		

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: anystyle-parser
 version: !ruby/object:Gem::Version
-  version: 0.0.9
+  version: 0.0.10
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-09-08 00:00:00.000000000Z
+date: 2012-03-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bibtex-ruby
-  requirement: &2157133020 !ruby/object:Gem::Requirement
+  requirement: &70338916773120 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,10 +21,10 @@ dependencies:
         version: '1.3'
   type: :runtime
   prerelease: false
-  version_requirements: *2157133020
+  version_requirements: *70338916773120
 - !ruby/object:Gem::Dependency
   name: wapiti
-  requirement: &2157132440 !ruby/object:Gem::Requirement
+  requirement: &70338916772120 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,10 +32,10 @@ dependencies:
         version: '0.0'
   type: :runtime
   prerelease: false
-  version_requirements: *2157132440
+  version_requirements: *70338916772120
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &2157131620 !ruby/object:Gem::Requirement
+  requirement: &70338916770100 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -43,10 +43,10 @@ dependencies:
         version: '0.9'
   type: :development
   prerelease: false
-  version_requirements: *2157131620
+  version_requirements: *70338916770100
 - !ruby/object:Gem::Dependency
   name: racc
-  requirement: &2157131060 !ruby/object:Gem::Requirement
+  requirement: &70338916769520 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -54,10 +54,10 @@ dependencies:
         version: '1.4'
   type: :development
   prerelease: false
-  version_requirements: *2157131060
+  version_requirements: *70338916769520
 - !ruby/object:Gem::Dependency
   name: cucumber
-  requirement: &2157130540 !ruby/object:Gem::Requirement
+  requirement: &70338916768880 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -65,10 +65,10 @@ dependencies:
         version: '1.0'
   type: :development
   prerelease: false
-  version_requirements: *2157130540
+  version_requirements: *70338916768880
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &2157129900 !ruby/object:Gem::Requirement
+  requirement: &70338916768220 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -76,10 +76,10 @@ dependencies:
         version: '2.6'
   type: :development
   prerelease: false
-  version_requirements: *2157129900
+  version_requirements: *70338916768220
 - !ruby/object:Gem::Dependency
   name: ZenTest
-  requirement: &2157129240 !ruby/object:Gem::Requirement
+  requirement: &70338916767680 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -87,7 +87,7 @@ dependencies:
         version: '4.6'
   type: :development
   prerelease: false
-  version_requirements: *2157129240
+  version_requirements: *70338916767680
 description: A sophisticated parser for academic references based on conditional random
   fields.
 email:
@@ -146,12 +146,18 @@ required_ruby_version: !ruby/object:Gem::Requirement
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
+      segments:
+      - 0
+      hash: -640366899922045737
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
+      segments:
+      - 0
+      hash: -640366899922045737
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.10