anystyle-parser 0.6.5 → 0.6.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4124e6f53dcd7d11c94dd91f118ad72bbc1d3397
-  data.tar.gz: c7687a359f621cd4071b05b644dc980ad893d040
+  metadata.gz: f1f0652bc06c8a041ac31417116c39b1bdb750f0
+  data.tar.gz: 694b97ca3f9686f6ef06d374f883ff210d8f7f04
 SHA512:
-  metadata.gz: 782106a15036dd28d7120f22228d79fc44c22cacec68b3faab1f4040ef57abe1bda63dd6d20d8e6bc710a24e7d82764a9ebf314bf2c9794f5eaa3f3e90758817
-  data.tar.gz: 2ad81353224b8e811508ad415fae29c137c38585288bad1dbe3e3fe1c9dadba6ad0653a5deb68d57f52eef211dd29af32751c4b3b826380e2db69de38703b4f9
+  metadata.gz: 733772f8b7418e6652cfe8eb28702eb7c20e4fda0ceec8ea6c02e093e548b21fd3d1c6d7e98f58dd32a053946b77c9f1a60ee8e1be74bd8621265836ade4882a
+  data.tar.gz: bf608a4165adfe1351c9396e5722217e2a2c79ea0e9ee83e22f731bc04a9df8e9063828805905b7e47b46c72074f4e11d431a89bc1a555fd2c65682c77fe25af

data/lib/anystyle/parser/normalizer.rb

@@ -85,7 +85,7 @@ module Anystyle
           hash[:editor] = hash.delete(:author)
           hash = normalize_editor(hash)
         else
-          hash[:'more-authors'] = true if !!authors.sub!(/\bet\.?\s*al.*$/i, '')
+          hash[:'more-authors'] = true if strip_et_al(authors)
           authors.gsub!(/^[^[:alnum:]]+|[^[:alnum:]]+$/, '')
           hash[:author] = normalize_names(authors)
         end
@@ -110,12 +110,13 @@ module Anystyle
           end
         end
 
-        hash[:'more-editors'] = true if !!editors.sub!(/\bet\.?\s*al.*$/i, '')
+        hash[:'more-editors'] = true if strip_et_al(editors)
 
         editors.gsub!(/^\W+|\W+$/, '')
         editors.gsub!(/^in:?\s+/i, '')
         editors.gsub!(/[^[:alpha:]]*[Ee]d(s|itors?|ited)?\b[^[:alpha:]]*/, '')
         editors.gsub!(/[^[:alpha:]]*([Hh]rsg|Herausgeber)\b[^[:alpha:]]*/, '')
+        editors.gsub!(/\b[Hh]erausgeben von\b/, '')
         editors.gsub!(/\bby\b/i, '')
 
         is_trans = !!editors.gsub!(/[^[:alpha:]]*trans(lated)?[^[:alpha:]]*/i, '')
@@ -126,6 +127,10 @@ module Anystyle
         hash
       end
 
+      def strip_et_al(names)
+        !!names.sub!(/(\bet\s+al\b|\bu\.\s*a\.|(\band|\&)\s+others).*$/, '')
+      end
+
       def normalize_translator(hash)
         translators = hash[:translator]
 

data/lib/anystyle/parser/parser.rb

@@ -10,7 +10,7 @@ module Anystyle
         :pattern => File.expand_path('../support/anystyle.pat', __FILE__),
         :compact => true,
         :threads => 4,
-        :separator => /\s+/,
+        :separator => /\s+|\b(\d+:)/,
         :tagged_separator => /\s+|(<\/?[^>]+>)/,
         :strip => /[^[:alnum:]]/,
         :format => :hash,
@@ -107,7 +107,7 @@ module Anystyle
             tokens
           end
         else
-          lines(string).map { |s| s.split(options[:separator]) }
+          lines(string).map { |s| s.split(options[:separator]).reject(&:empty?) }
         end
       end
 

data/lib/anystyle/parser/version.rb

@@ -1,5 +1,5 @@
 module Anystyle
   module Parser
-    VERSION = '0.6.5'.freeze
+    VERSION = '0.6.6'.freeze
   end
 end

data/spec/anystyle/parser/normalizer_spec.rb

@@ -74,6 +74,15 @@ module Anystyle
           n.normalize_editor(:editor => 'ed. by Edward Wood').should == { :editor => 'Wood, Edward' }
           n.normalize_editor(:editor => 'ed by Edward Wood').should == { :editor => 'Wood, Edward' }
         end
+
+        it "strips et al" do
+          n.normalize_editor(:editor => 'Edward Wood et al')[:editor].should == 'Wood, Edward'
+          n.normalize_editor(:editor => 'Edward Wood et al.')[:editor].should == 'Wood, Edward'
+          n.normalize_editor(:editor => 'Edward Wood u.a.')[:editor].should == 'Wood, Edward'
+          n.normalize_editor(:editor => 'Edward Wood u. a.')[:editor].should == 'Wood, Edward'
+          n.normalize_editor(:editor => 'Edward Wood and others')[:editor].should == 'Wood, Edward'
+          n.normalize_editor(:editor => 'Edward Wood & others')[:editor].should == 'Wood, Edward'
+        end
       end
 
       describe 'editors extraction' do

data/spec/anystyle/parser/parser_spec.rb

@@ -14,6 +14,10 @@ module Anystyle::Parser
         subject.tokenize('hello, world!').should == [%w{ hello, world! }]
       end
 
+      it "tokenizes volume/page-range exception" do
+        subject.tokenize('hello:world! http://abc.com 3:45 3:1-2 23:1').should == [%w{ hello:world! http://abc.com 3: 45 3: 1-2 23: 1 }]
+      end
+
       it "takes two lines and returns an array of token sequences" do
         subject.tokenize("hello, world!\ngoodbye!").should == [%w{ hello, world! }, %w{ goodbye! }]
       end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: anystyle-parser
 version: !ruby/object:Gem::Version
-  version: 0.6.5
+  version: 0.6.6
 platform: ruby
 authors:
 - Sylvester Keil
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-05-14 00:00:00.000000000 Z
+date: 2014-05-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bibtex-ruby