bibtex-ruby 2.3.4 → 3.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5b09dca8a81cca150971cdfabcc448c4ffdd2ee7
-  data.tar.gz: 68f2f2564edf0a61eb80944f25f684a7d9fab0e8
+  metadata.gz: 032d4eb545f4e0360cb12438d83c1177dd17af9a
+  data.tar.gz: 2e855f8b6f4b23b67e0330cb4ffae8eea2476c08
 SHA512:
-  metadata.gz: 589c95707591059f965b4bfe7167211a707da6b5f125d349b9b2457657f4f3ac16d70b6039b7022a8d32161d2cc33f6a0409cd2c7ea3c7013041b5c7a890caef
-  data.tar.gz: 1406695031be8949fd6495328d99586e5b4e8d781f2d9fe6a93d3b8cf186d9f36ee0a64bfd00eaf789f7acb668070b82a07d32c12d24827e34ddd23d2cd44e05
+  metadata.gz: 42bcd110dda57b116de19d63ad9e5ca336c0035bde9bad0818f7b0e06c3199e470b86288eb7b4d8bfaf2d1a01d0a7ce8c24d0a8c3728dcf510df2b776f86f2f0
+  data.tar.gz: 7e4f01e424befdd4acec3685cbd3c87c3a1a6697574c93becadcece0433712be4a7dea645d5dc7593cbfa5cceef919161d50ee97d351f9a5392b3d79b4993294

data/Gemfile

@@ -4,6 +4,7 @@ gemspec
 # RDF Export
 gem 'rdf', '~>0.3'
 
+
 group :debug do
 	gem 'debugger', :require => false, :platforms => [:mri_19, :mri_20]
 	gem 'ruby-debug', :require => false, :platforms => [:mri_18]
@@ -18,8 +19,8 @@ end
 
 group :extra do
 	gem 'rb-fsevent', :require => false if RUBY_PLATFORM =~ /darwin/i
-	gem 'guard-minitest'
-	gem 'guard-cucumber'
+	gem 'guard-minitest', :platforms => [:ruby_20]
+	gem 'guard-cucumber', :platforms => [:ruby_20]
 	gem 'redcarpet', :platforms => [:rbx, :mri_20, :mri_19]
 end
 
@@ -33,4 +34,5 @@ group :development do
   gem 'rake'
   gem 'racc'
   gem 'yard'	
+  gem 'iconv', :platforms => [:ruby_20]
 end

data/History.txt

@@ -1,3 +1,9 @@
+3.0.0 / 2013-11-11
+==================
+
+* Added transliteration support to default key generator (@cruessler)
+* Improve parsing of non-ascii keys (@cruessler)
+
 2.3.4 / 2013-08-22
 ==================
 

data/Manifest

@@ -19,6 +19,8 @@ features/issues/crossref.feature
 features/issues/latex_filter.feature
 features/issues/multiline_strings.feature
 features/issues/name_parsing.feature
+features/issues/non_ascii_default_keys.feature
+features/issues/non_ascii_keys.feature
 features/issues/number_keys.feature
 features/issues/parse_months.feature
 features/issues/slash_keys.feature

data/README.md

@@ -97,7 +97,9 @@ Save a bibliography to a file:
 
 Compatibility
 -------------
-The BibTeX-Ruby gem has been developed and tested on Ruby 1.8 and 1.9; it has
+The BibTeX-Ruby gem has been developed and tested on Ruby 2.0 and 1.9; up to
+version 2.x BibTeX-Ruby also supports Ruby 1.8, but starting with version 3.0.0
+support 1.8 is not a priority anymore. It has
 been confirmed to work with JRuby, Rubinius, and REE, however, there have
 been repeated [issues](https://github.com/inukshuk/bibtex-ruby/issues)
 (performance mostly) with MacRuby caused by MacRuby's current StringScanner

data/features/issues/non_ascii_default_keys.feature

@@ -0,0 +1,20 @@
+Feature: Parse BibTeX files and convert LaTeX to Unicode
+	As a hacker who works with bibliographies
+	I want to be able to have autogenerated keys respect non-ASCII characters
+	by transliterating them
+
+  @default_keys
+	Scenario: A single entry with an author whose name contains non-ASCII characters
+		When I create an entry with these elements:
+			| type | author           | title | location | year |
+			| book | Christian Müller | Title | Berlin   | 2013 |
+		Then my bibliography should contain an entry with a key like "mu.?ller2013a"
+
+  @default_keys
+	Scenario: Multiple entries with an author whose name contains non-ASCII characters
+		When I create entries with these elements:
+			| type | author           | title        | location | year |
+			| book | Christian Müller | First Title  | Berlin   | 2013 |
+			| book | Christian Müller | Second Title | Berlin   | 2013 |
+		Then my bibliography should contain an entry with a key like "mu.?ller2013a"
+		And my bibliography should contain an entry with a key like "mu.?ller2013b"

data/features/issues/non_ascii_keys.feature

@@ -0,0 +1,17 @@
+Feature: Keys containing non-ASCII characters
+	As a hacker who works with bibliographies
+	I want to parse BibTeX entries with keys containing non-ASCII characters
+	Because they can occur in many languages other than English
+	
+	Scenario: An entry whose key contains a German umlaut
+		When I parse the following file:
+		"""
+		@article{müller.2011,
+		  author    = {Christian Müller},
+		  title     = {Important article},
+		  journal   = {Not so important journal},
+		  volume    = {5},
+		  year      = {2011}
+		}
+		"""
+		Then my bibliography should contain an article with id "müller.2011"

data/features/step_definitions/bibtex_steps.rb

@@ -30,6 +30,26 @@ When /^I convert all entries using the filter "([^"]*)"$/ do |filter|
   @bibliography.convert(filter)
 end
 
+When /^I create an entry with these elements:$/ do |table|
+  @bibliography = BibTeX::Bibliography.new
+  entry = BibTeX::Entry.new
+  table.hashes.first.each_pair do |field, value|
+    entry[field.to_sym] = value
+  end
+  @bibliography << entry.parse_names
+end
+
+When /^I create entries with these elements:$/ do |table|
+  @bibliography = BibTeX::Bibliography.new
+  table.hashes.each do |entries|
+    entry = BibTeX::Entry.new
+    entries.each_pair do |field, value|
+      entry[field.to_sym] = value
+    end
+    @bibliography << entry.parse_names
+  end
+end
+
 
 Then /^my bibliography should contain the following objects:$/ do |table|
   @bibliography.each_with_index do |object, index|
@@ -59,6 +79,10 @@ Then /^my bibliography should contain an entry with (?:key|id) "([^"]*)"$/ do |k
   refute_nil @bibliography[key.to_s]
 end
 
+Then /^my bibliography should contain an entry with an? (?:key|id) like "([^"]*)"$/ do |key|
+  pattern = Regexp.compile key
+  refute_nil @bibliography.detect { |e| e.key.to_s =~ pattern }
+end
 Then /^my bibliography should contain an entry with (?:key|id) "([^"]*)" and a?n? (\w+) value of "([^"]*)"$/ do |key,field,value|
   refute_nil @bibliography[key.to_s]
   assert_equal value, @bibliography[key.to_s][field.downcase.to_sym].to_s
@@ -92,4 +116,4 @@ end
 
 Then /^the entry with key "([^"]*)" should have a field "([^"]*)" with the value "([^"]*)"$/ do |key, field, value|
   assert_equal value, @bibliography[key][field.downcase.to_sym].to_s
-end
+end

data/lib/bibtex/compatibility.rb

@@ -16,3 +16,23 @@ if RUBY_VERSION < '1.9'
   
   BibTeX::NameParser.patterns[:upper] = /[[:upper:]ÄÖÜ][^\t\r\n\s\{\}\d\\,]*/o
 end
+
+module BibTeX
+  begin
+    require 'iconv'
+
+    @iconv = Iconv.new('ascii//translit//ignore', 'utf-8')
+
+    def self.transliterate(str)
+      @iconv.iconv(str)
+    end
+  rescue LoadError
+
+    @iconv_replacements = Hash[*%w(ä ae ö oe ü ue Ä Ae Ö Oe Ü Ue ß ss)]
+
+    # Returns +str+ transliterated containing only ASCII characters.
+    def self.transliterate(str)
+      str.gsub(/[äöüÄÖÜß]/, @iconv_replacements)
+    end
+  end
+end

data/lib/bibtex/entry.rb

@@ -720,10 +720,18 @@ module BibTeX
     end
 
     def issued
-      m = MONTHS.find_index(fields[:month].to_s.intern) unless !has_field?(:month)
-      m = m + 1 unless m.nil?
+      return unless has_field?(:year)
+      
+      parts = [fields[:year].to_s]
 
-      Hash['date-parts', [[fields[:year],m].compact.map(&:to_i)]]
+      return { 'literal' => parts[0] } unless parts[0] =~ /^\d+$/
+
+      if has_field?(:month)
+        parts.push MONTHS.find_index(fields[:month].to_s.intern)
+        parts[1] = parts[1] + 1 unless parts[1].nil?
+      end
+
+      { 'date-parts' => [parts.compact.map(&:to_i)] }
     end
 
     alias citeproc_date issued
@@ -859,13 +867,12 @@ module BibTeX
     def default_key
       k = names[0]
       k = k.respond_to?(:family) ? k.family : k.to_s
-      k = k[/[A-Za-z]+/] || 'unknown'
+      k = BibTeX.transliterate(k)
+      k = k[/[A-Za-z-]+/] || 'unknown'
       k << (has_field?(:year) ? year : '-')
       k << 'a'
       k.downcase!
       k
     end
-
-
   end
 end

data/lib/bibtex/lexer.rb

@@ -46,8 +46,8 @@ module BibTeX
       :braces       => /\{|\}/o,
       :eq           => /\s*=\s*/o,
       :comma        => /\s*,\s*/o,
-      :number       => /\d+/o,
-      :name         => /[[:alpha:]\d\/:_!$\?\.%&\*-]+/io,
+      :number       => /[[:digit:]]+/o,
+      :name         => /[[:alpha:][:digit:]\/:_!$\?\.%&\*-]+/io,
       :quote        => /\s*"/o,
       :unquote      => /[\{\}"]/o,
       :sharp        => /\s*#\s*/o,
@@ -59,8 +59,8 @@ module BibTeX
       :string       => /string/io,
       :comment      => /comment\b/io,
       :preamble     => /preamble\b/io,
-      :key          => /\s*[[:alpha:]\d \/:_!$\?\.%+&\*-]+,/io,
-      :optional_key => /\s*[[:alpha:]\d \/:_!$\?\.%+&\*-]*,/io
+      :key          => /\s*[[:alpha:][:digit:] \/:_!$\?\.%+&\*-]+,/io,
+      :optional_key => /\s*[[:alpha:][:digit:] \/:_!$\?\.%+&\*-]*,/io
     }.freeze
     
     MODE = Hash.new(:meta).merge({

data/lib/bibtex/version.rb

@@ -18,9 +18,9 @@
 
 module BibTeX
   module Version    
-    MAJOR = 2
-    MINOR = 3
-    PATCH = 4
+    MAJOR = 3
+    MINOR = 0
+    PATCH = 0
     BUILD = nil
 
     STRING = [MAJOR, MINOR, PATCH, BUILD].compact.join('.').freeze

data/test/bibtex/test_entry.rb

@@ -269,6 +269,11 @@ module BibTeX
         assert_equal 'Melville', e['author'][0]['family']
       end
 
+      it 'support literal dates in citeproc export' do
+        @entry.year = 'Test'
+        assert_equal({ 'literal' => 'Test' }, @entry.issued)
+      end
+
       describe 'given a filter object or a filter name' do
         before do
           @filter = Object.new

data/test/bibtex/test_lexer.rb

@@ -1,3 +1,5 @@
+# coding: utf-8
+
 require 'helper.rb'
 
 module BibTeX
@@ -21,6 +23,10 @@ module BibTeX
       Lexer.new.analyse("@misc{foo, }").symbols.must_be :==, [:AT, :NAME, :LBRACE, :KEY, :RBRACE, false]
     end
 
+    it 'matches KEY tokens with non-ascii characters' do
+      Lexer.new.analyse("@misc{löwe, }").symbols.must_be :==, [:AT, :NAME, :LBRACE, :KEY, :RBRACE, false]
+    end
+
     it 'matches KEY tokens after whitespace' do
       Lexer.new.analyse("@misc{  foo, }").symbols.must_be :==, [:AT, :NAME, :LBRACE, :KEY, :RBRACE, false]
     end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bibtex-ruby
 version: !ruby/object:Gem::Version
-  version: 2.3.4
+  version: 3.0.0
 platform: ruby
 authors:
 - Sylvester Keil
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-08-22 00:00:00.000000000 Z
+date: 2013-11-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: latex-decode
@@ -71,6 +71,8 @@ files:
 - features/issues/latex_filter.feature
 - features/issues/multiline_strings.feature
 - features/issues/name_parsing.feature
+- features/issues/non_ascii_default_keys.feature
+- features/issues/non_ascii_keys.feature
 - features/issues/number_keys.feature
 - features/issues/parse_months.feature
 - features/issues/slash_keys.feature