biburi 0.0.1 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a1c33a8d71f4dfb1035bb83a6f4be20820372286
-  data.tar.gz: 85efe72c97ada25dd9fb831b253e8237eee4341f
+  metadata.gz: 5826c0467c0aa9d64cd79d4347eb09811e81b4aa
+  data.tar.gz: 707baa6b8b9bda043ec66f9a05606819e142f52e
 SHA512:
-  metadata.gz: 4fc5f2c69f6a36372d25f94517bd4e926328c830cac8bdcda80f147b47ad454674a872e28413514bedb98fe0e510c8cb296b18749d8f36efde09c67ce6365114
-  data.tar.gz: d6fe457ac2cf2538a2b82e7735183b55819c2162b22eee6e8a2310031c35caba939f13e4ffd13165e4f2bab2850761053374393a0254b5910faee0494b2217f6
+  metadata.gz: 9a0fbed4417f1903c3ed9f0aa38407ec80e952458c293334db4fbfde99562a108971f3bd3f0d1e4ea99def2aef86568346ba2f06ca62088e38e7316ea5a63822
+  data.tar.gz: 322a876c1a113d12aaf4e96f11505d952aa7aa342fa59a11f07d070e6fb023c5ac86c556cbd3b4b68ca6fe63b19c89f14ede7ca5b0d207ac8ae6f53661159a7c

data/CHANGELOG.mediawiki

@@ -1,4 +1,7 @@
 = BibURI Changelog =
 
+* 0.1.0 (October 4, 2013)
+** MAJOR CHANGE: lookup() now returns a single BibTeX::Entry object, instead of an Array. One driver supports lookup_all() to return all entries.
+
 * 0.0.1 (October 2, 2013)
 ** First release, with basic support for DOIs using the CrossRef API.

data/biburi.gemspec

@@ -18,11 +18,11 @@ Gem::Specification.new do |spec|
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ["lib"]
 
-  spec.add_development_dependency "bundler", "~> 1.3"
-  spec.add_development_dependency "rake"
-  spec.add_development_dependency "rspec"
-  spec.add_development_dependency "rspec-core"
-  spec.add_development_dependency "coveralls"
+  spec.add_development_dependency "bundler", "~>1.3.5"
+  spec.add_development_dependency "rake", "~> 10.1"
+  spec.add_development_dependency "rspec", "~> 2.14.1"
+  spec.add_development_dependency "coveralls", "~> 0.7.0"
 
-  spec.add_runtime_dependency 'bibtex-ruby', '~> 2.0'
+  spec.add_runtime_dependency 'bibtex-ruby', '~> 2.3.4'
+  spec.add_runtime_dependency 'nokogiri', '~> 1.6.0'
 end

data/bin/biburi.rb

@@ -0,0 +1,63 @@
+#!/usr/bin/env ruby
+
+#
+# A binary to access BibURI from the command line.
+#
+require 'biburi'
+require 'optparse'
+
+# Command line options
+options = {}
+
+# Reads command line arguments and figures out what to run.
+def main
+    # Process command line options.
+    OptionParser.new do |opts|
+        opts.banner = "Usage: biburi [arguments] [uri]\n\n" +
+            "biburi can read any number of URIs in its arguments.\n" +
+            "If no URI is provided, biburi will read URIs from STDIN\nand return one BibTeX citation per input line."
+
+        opts.separator ""
+
+        # Documentary stuff.
+        opts.on("-h", "--help", "Show this message") do
+            puts opts
+        end
+
+        opts.on("-v", "--[no-]verbose", "Produce verbose output") do |v|
+            options[:verbose] = v
+        end
+
+        opts.separator ""
+    end.parse!
+
+    # Do we have command line argument URIs?
+    if !ARGV.empty? then
+        ARGV.each do |uri|
+            uri_to_bibtex(uri)
+        end
+    else
+        # If not, open STDIN and process that instead. 
+        lines = STDIN.readlines
+        lines.each do |line|
+            line.chomp!
+            uri_to_bibtex(line)
+        end
+    end
+end
+
+# Returns a URI as BibTeX thanks to the magic of BibURI.
+def uri_to_bibtex(uri)
+    entry = BibURI::lookup(uri)
+    if entry.nil? then
+        entry = BibTeX::Entry.new(
+            :title => uri,
+            :identifiers => uri
+        )
+    end
+
+    puts entry.to_s
+end
+
+# Start execution
+main()

data/lib/biburi/driver/coins.rb

@@ -0,0 +1,272 @@
+# A driver to read BibTeX from web pages by reading
+# in COinS on that page. Find out more about COinS
+# at: http://ocoins.info/
+#
+# Author:: Gaurav Vaidya
+# Copyright:: Copyright (c) 2013 Gaurav Vaidya
+# License:: MIT
+
+require 'biburi'
+require 'biburi/driver'
+require 'net/http'
+require 'json'
+require 'bibtex'
+require 'uri'
+require 'nokogiri'
+require 'cgi'
+
+# This driver reads COinS citations in an HTML
+# page and returns them. It defaults to returning
+# a single citation, but can be used to return all
+# citations.
+
+module BibURI::Driver::COinS
+  include BibURI::Driver
+
+  # We support an identifier if we can make them look
+  # canonical.
+  def self.supported?(id)
+    canonical = self.canonical(id)
+    return !(canonical.nil?)
+  end
+
+  # The canonical form of this identifier is the
+  # normalized URI, IF it has a scheme of 'http'
+  # or 'https'.
+  def self.canonical(id)
+    uri = URI.parse(id)
+
+    unless uri.scheme == 'http' || uri.scheme == 'https'
+        return nil
+    end
+
+    return uri.to_s
+
+  rescue URI::InvalidURIError
+    # If there is an error in the URI, it is not an identifier.
+    nil
+  end
+
+  # Returns a list of parsed values with
+  # BibTeX names by looking up the provided id (a URL).
+  # 
+  # This will call self.lookup_all(), and then only
+  # return the first match. For pages like Mendeley, this is
+  # necessary to avoid pulling in 'related to' citations
+  # or to pull in all entries.
+  def self.lookup(id)
+    self.lookup_all(id) do |first_only|
+      return first_only
+    end
+  end
+   
+  # This method returns ALL COinS on this page. For Mendeley,
+  # this will return the pages' COinS as well as all related
+  # papers. Use self.lookup() to find a single one.
+  def self.lookup_all(id)
+    # Calculate the canonical identifier.
+    url = canonical(id)
+    if url.nil? then
+        return nil
+    end
+
+    # Retrieve the HTML.
+    content = Net::HTTP.get(URI(url))
+    doc = Nokogiri::HTML(content)
+    spans = doc.css('span.Z3988')
+
+    # Go through results and format them as BibTeX::Entry.
+    # We support both 
+    results = [] unless block_given?
+        
+    spans.each do |span|
+        coins = span['title']
+
+        bibentry = self.coins_to_bibtex(coins)
+
+        # Set identifiers so we know where this came from.
+        bibentry[:url] = url
+
+        identifiers = bibentry[:identifiers].split("\n")
+        identifiers.push(url)
+        bibentry.add(:identifiers, identifiers.join("\n"))
+
+        # See if we have a DOI.
+        identifiers.each do |identifier|
+            match = identifier.match(/^(?:http:\/\/dx\.doi\.org\/|doi:|info:doi\/)(.*)$/i) 
+            if match then
+                bibentry[:doi] = match[1] 
+            end
+        end
+
+        # Yield values or return array.
+        if block_given? then
+            yield(bibentry)
+        else
+            results.push(bibentry)
+        end 
+    end
+
+    # If we built an array, return it.
+    unless block_given? then
+        return results
+    end
+  end
+
+  # Converts a COinS string to a BibTeX entry.
+  def self.coins_to_bibtex(coins)
+    # Create a BibTeX entry to store these values.
+    bibentry = BibTeX::Entry.new
+
+    # If we have COinS data, we have a lot more data.
+    coins_kv = CGI::parse(coins)
+    metadata = {}
+    coins_kv.each do |key, val|
+        if val.length == 1 then
+            metadata[key] = val[0]
+        else
+            metadata[key] = val
+        end
+    end
+
+    # COinS values are explained at http://ocoins.info/cobg.html
+    # and in http://ocoins.info/cobgbook.html.
+
+    # If we're not Z3988-2004, skip out.
+    ctx_ver = metadata['ctx_ver']
+    if ctx_ver != 'Z39.88-2004' then
+        ctx_ver = "" if ctx_ver.nil?
+        raise "ctx_ver is: '#{ctx_ver}'"
+    end
+
+    # Add ALL the identifiers.
+    bibentry[:identifiers] = ""
+    if metadata.key?('rft_id') then
+        if metadata['rft_id'].kind_of?(Array) then
+            bibentry[:identifiers] = metadata['rft_id'].join("\n")
+        else
+            bibentry[:identifiers] = metadata['rft_id']
+        end
+    end
+
+    # COinS supports some types
+    genre = metadata['rft.genre']
+    if genre == 'article' then
+        bibentry.type = "article"
+    elsif genre == 'book' then
+        bibentry.type = "book"
+    elsif genre == 'bookitem' then
+        bibentry.type = "inbook"
+    elsif genre == 'proceeding' then
+        bibentry.type = "proceedings"
+    elsif genre == 'conference' then
+        bibentry.type = "inproceedings"
+    elsif genre == 'report' then
+        bibentry.type = "techreport"
+    end 
+    
+    # Journal title: title, jtitle
+    journal_title = metadata['rft.title']       # The old-style journal title.
+    journal_title ||= metadata['rft.stitle']    # An abbreviated title.
+    journal_title ||= metadata['rft.jtitle']    # Complete title.
+    bibentry[:journal] = journal_title
+
+    # Book title: btitle
+    if metadata.key?('rft.btitle')
+        if journal_title
+            bibentry[:booktitle] = metadata['rft.btitle']
+        else
+            bibentry[:title] = metadata['rft.btitle']
+        end
+    end
+
+    # Pages: spage, epage
+    pages = metadata['rft.pages']       # If only pages are provided
+
+    # Expand a single dash to a BibTeX-y double-dash.
+    pages.gsub!(/([^\-])\-([^\-])/, '\1--\2') unless pages.nil?
+
+    pages ||= metadata['rft.spage'] + "--" + metadata['rft.epage']
+                                    # If we have start and end pages
+    bibentry[:pages] = pages
+
+    # Authors are all in 'rft.au'
+    authors = []
+    metadata['rft.au'] = [ metadata['rft.au'] ] unless metadata['rft.au'].kind_of?(Array)
+    metadata['rft.au'].each do |author|
+        authors.push(BibTeX::Name.parse(author)) unless author.nil?
+    end
+
+    # However! Sometimes a name is in aufirst/aulast
+    # and also in au; and sometimes it's only in aufirst/aulast.
+    first_author = BibTeX::Name.new
+    first_author.last = metadata['rft.aulast']
+    first_author.suffix = metadata['rft.ausuffix'] if metadata.key?('rft.ausuffix')
+    if metadata.key?('rft.aufirst') then
+        first_author.first = metadata['rft.aufirst']
+    elsif metadata.key?('rft.auinit') then
+        first_author.first = metadata['rft.auinit']
+    elsif 
+        first_author.first = metadata['rft.auinit1']
+        first_author.first += " " + metadata['rftinitm'] if metadata.key?('rftinitm')
+    end
+    if !authors.include?(first_author) then
+        authors.unshift(first_author)
+    end
+
+    bibentry[:author] = BibTeX::Names.new(authors)
+
+    # Dates. 
+    date = metadata['rft.date']
+    bibentry[:date] = date
+
+    # Citeulike dates are easy to parse. 
+    unless date.nil? then
+        if match = date.match(/^(\d{4})$/) then
+            bibentry[:year] = match[1] 
+
+        elsif match = date.match(/^(\d{4})-(\d{1,2})$/) then
+            bibentry[:year] = match[1] 
+            bibentry[:month] = match[2] 
+
+        elsif match = date.match(/^(\d{4})-(\d{1,2})-(\d{1,2})$/) then
+            bibentry[:year] = match[1] 
+            bibentry[:month] = match[2] 
+            bibentry[:day] = match[3] 
+
+        end
+    end
+
+    # Map remaining fields to BibTeX.
+    standard_mappings = {
+        "rft.atitle" =>     "title",
+        "rft.volume" =>     "volume",
+        "rft.issue" =>      "number",
+        "rft.artnum" =>     "article_number",
+        "rft.issn" =>       "issn",
+        "rft.eissn" =>      "eissn",
+        "rft.isbn" =>       "isbn",
+        "rft.coden" =>      "CODEN",
+        "rft.sici" =>       "SICI",
+        "rft.chron" =>      "chronology",
+        "rft.ssn" =>        "season",
+        "rft.quarter" =>    "quarter",
+        "rft.part" =>       "part",
+
+        "rft.place" =>      "address",
+        "rft.pub" =>        "publisher",
+        "rft.edition" =>    "edition",
+        "rft.tpages" =>     "total_pages",
+        "rft.series" =>     "series",
+        "rft.bici" =>       "bici"
+    }
+
+    standard_mappings.keys.each do |field|
+        if metadata.key?(field) then
+            bibentry[standard_mappings[field]] = metadata[field]
+        end
+    end
+
+    return bibentry
+  end
+end

data/lib/biburi/driver/doi.rb

@@ -7,13 +7,11 @@
 
 require 'biburi'
 require 'biburi/driver'
+require 'biburi/driver/coins'
 require 'net/http'
 require 'json'
 require 'bibtex'
  
-# For CGI::parse to make sense of COinS
-require 'cgi'
-
 # This driver provides information in BibTeX on a DOI by
 # querying CrossRef's metadata search API. 
 
@@ -72,103 +70,38 @@ module BibURI::Driver::DOI
     # Go through results and format them as BibTeX::Entry.
     # We support both 
     results = [] unless block_given?
-    as_json.each do |match|
-        # Skip non-identical DOI matches.
-        next unless match['doi'].downcase == canonical_id.downcase
-
-        # Create a BibTeX entry to store these values.
-        bibentry = BibTeX::Entry.new
-
-        # Set identifiers so we know where this came from.
-        bibentry[:url] = canonical_id
-        bibentry[:doi] = canonical_id.match(/^http:\/\/dx\.doi\.org\/(.*)$/)[1]
-
-        # CrossRef itself provides a full citation and year.
-        if match.key?('fullCitation') then
-            bibentry[:title] = match['fullCitation']
-        end
-
-        if match.key?('year') then
-            bibentry[:year] = match['year'] 
-        end
-        
-        # If we have COinS data, we have a lot more data.
-        if match.key?('coins') then
-            coins_kv = CGI::parse(match['coins'])
-            metadata = {}
-            coins_kv.each do |key, val|
-                if val.length == 1 then
-                    metadata[key] = val[0]
-                else
-                    metadata[key] = val
-                end
-            end
-
-            # COinS values are explained at http://ocoins.info/cobg.html
-            # Some values need to be handled separately.
-            
-            # Journal title: title, jtitle
-            journal_title = metadata['rft.title']       # The old-style journal title.
-            journal_title ||= metadata['rft.stitle']    # An abbreviated title.
-            journal_title ||= metadata['rft.jtitle']    # Complete title.
-            bibentry[:journal] = journal_title
-
-            # Pages: spage, epage
-            pages = metadata['rft.pages']       # If only pages are provided
-            pages ||= metadata['rft.spage'] + "-" + metadata['rft.epage']
-                                            # If we have start and end pages
-            bibentry[:pages] = pages
-
-            # Authors are all in 'rft.au'
-            authors = BibTeX::Names.new
-            metadata['rft.au'].each do |author|
-                authors.add(BibTeX::Name.parse(author))
-            end
-            bibentry[:author] = authors
-
-            # COinS supports some types
-            genre = metadata['rft.genre']
-            if genre == 'article' then
-                bibentry.type = "article"
-            elsif genre == 'proceeding' || genre == 'conference' then
-                bibentry.type = "inproceeding"
-            end 
-
-            # Map remaining fields to BibTeX.
-            standard_mappings = {
-                "rft.atitle" =>     "title",
-                "rft.date" =>       "date",
-                "rft.volume" =>     "volume",
-                "rft.issue" =>      "number",
-                "rft.artnum" =>     "article_number",
-                "rft.issn" =>       "issn",
-                "rft.eissn" =>      "eissn",
-                "rft.isbn" =>       "isbn",
-                "rft.coden" =>      "CODEN",
-                "rft.sici" =>       "SICI",
-                "rft.chron" =>      "chronology",
-                "rft.ssn" =>        "season",
-                "rft.quarter" =>    "quarter",
-                "rft.part" =>       "part",
-            }
-            standard_mappings.keys.each do |field|
-                if metadata.key?(field) then
-                    bibentry[standard_mappings[field]] = metadata[field]
-                end
-            end
-        end
-
-        # Yield values or return array.
-        if block_given? then
-            yield(bibentry)
-        else
-            results.push(bibentry)
-        end 
+    match = as_json.first
+
+    # Skip non-identical DOI matches.
+    return nil unless match['doi'].downcase == canonical_id.downcase
+
+    # Create a BibTeX entry to store these values.
+    bibentry = BibTeX::Entry.new
+
+    # Process any COinS content first, if any.
+    if match.key?('coins') then
+        bibentry = BibURI::Driver::COinS::coins_to_bibtex(match['coins'])
+    end
+
+    # Set identifiers so we know where this came from.
+    bibentry[:url] = canonical_id
+
+    identifiers = bibentry[:identifiers].split("\n")
+    identifiers.push(canonical_id)
+    bibentry.add(:identifiers, identifiers.join("\n"))
+
+    bibentry[:doi] = canonical_id.match(/^http:\/\/dx\.doi\.org\/(.*)$/)[1]
+
+    # CrossRef itself provides a full citation and year.
+    if !bibentry.has_field?('title') and match.key?('fullCitation') then
+        bibentry[:title] = match['fullCitation']
     end
 
-    # If we built an array, return it.
-    unless block_given? then
-        return results
+    if !bibentry.has_field?('year') and match.key?('year') then
+        bibentry[:year] = match['year'] 
     end
+    
+    # Yield values or return array.
+    return bibentry
   end
 end

data/lib/biburi/driver.rb

@@ -41,10 +41,12 @@ end
 # Load all the drivers, and add them to BibURI::Driver
 # in order of preference.
 require "biburi/driver/doi"
+require "biburi/driver/coins"
 
 module BibURI::Driver
   @@drivers = [
-    BibURI::Driver::DOI
+    BibURI::Driver::DOI,
+    BibURI::Driver::COinS
   ]
 end
 

data/lib/biburi/version.rb

@@ -1,3 +1,3 @@
 module BibURI
-  VERSION = "0.0.1"
+  VERSION = "0.1.0"
 end

data/lib/biburi.rb

@@ -19,10 +19,8 @@ module BibURI
   def self.lookup(id)
     self.drivers.each do |driver|
       if driver.supported?(id) then
-        results = driver.lookup(id)  
-        if !results.nil? then
-          return results
-        end
+        bibtex = driver.lookup(id)  
+        return bibtex unless bibtex.nil?
       end
     end
 

data/spec/biburi_spec.rb

@@ -1,3 +1,5 @@
+# encoding: utf-8
+
 require_relative 'spec_helper'
 
 describe BibURI do
@@ -17,33 +19,144 @@ describe BibURI do
     end
 
     describe "lookup" do
-        it "should be able to do simple lookups" do
+        it "should be able to do DOI lookups" do
             queries = {
-                "doi:10.1038/171737a0" => [
+                "doi:10.1038/171737a0" =>
                     BibTeX::Entry.new(
-                        :url => "http://dx.doi.org/10.1038/171737a0", 
-                        :doi => "10.1038/171737a0",
-                        :title => "Molecular Structure of Nucleic Acids: A Structure for Deoxyribose Nucleic Acid, year = 1953, journal = Nature, pages = 737-738", 
+                        :type => 'article',
+                        :identifiers => "info:doi/http://dx.doi.org/10.1038/171737a0\nhttp://dx.doi.org/10.1038/171737a0",
+                        :journal => "Nature",
+                        :pages => "737--738",
                         :author => "WATSON, J. D. and CRICK, F. H. C.", 
                         :date => "1953",
+                        :year => "1953",
+                        :title => "Molecular Structure of Nucleic Acids: A Structure for Deoxyribose Nucleic Acid", 
                         :volume => "171", 
-                        :number => "4356"
-                    )
-                ],
-                "http://dx.doi.org/10.1111/j.1096-0031.2010.00329.x" => [
+                        :number => "4356",
+                        :url => "http://dx.doi.org/10.1038/171737a0",
+                        :doi => "10.1038/171737a0",
+                    ),
+                "http://dx.doi.org/10.1111/j.1096-0031.2010.00329.x" =>
                     BibTeX::Entry.new({
-                        "url" => "http://dx.doi.org/10.1111/j.1096-0031.2010.00329.x",
-                        "doi" => "10.1111/j.1096-0031.2010.00329.x",
-                        "title" => "SequenceMatrix: concatenation software for the fast assembly of multi-gene datasets with character set and codon information",
-                        "year" => "2011",
+                        :type => 'article',
+                        "identifiers" => "info:doi/http://dx.doi.org/10.1111/j.1096-0031.2010.00329.x\nhttp://dx.doi.org/10.1111/j.1096-0031.2010.00329.x",
                         "journal" => "Cladistics", 
-                        "pages" => "171-180",
+                        "pages" => "171--180",
                         "author" => "Vaidya, Gaurav and Lohman, David J. and Meier, Rudolf",
                         "date" => "2011",
+                        "year" => "2011",
+                        "title" => "SequenceMatrix: concatenation software for the fast assembly of multi-gene datasets with character set and codon information",
                         "volume" => "27", 
-                        "number" => "2"
+                        "number" => "2",
+                        "url" => "http://dx.doi.org/10.1111/j.1096-0031.2010.00329.x",
+                        "doi" => "10.1111/j.1096-0031.2010.00329.x",
                     })
-                ]
+            }
+
+            queries.keys.each do |query|
+                result = BibURI::lookup(query)
+
+                expect(result.to_s).to eq(queries[query].to_s)
+            end 
+        end
+
+        it "should be able to do COinS lookups" do
+            queries = {
+                "http://www.mendeley.com/research/outline-morphometric-approach-identifying-fossil-spiders-preliminary-examination-florissant-formation/" =>
+                    BibTeX::Entry.new(
+                        :type => 'article',
+                        :identifiers => "info:doi/10.1130/2008.2435(07).\nhttp://www.mendeley.com/research/outline-morphometric-approach-identifying-fossil-spiders-preliminary-examination-florissant-formation/",
+                        :journal => "Society", 
+                        :pages => "105", 
+                        :author => "Kinchloe Roberts, A and Smith, D M and Guralnick, R P and Cushing, P E and Krieger, J",
+                        :date => "2008", 
+                        :year => "2008",
+                        :title => "An outline morphometric approach to identifying fossil spiders: A preliminary examination from the Florissant Formation",
+                        :volume => "435", 
+                        :number => "303", 
+                        :url => "http://www.mendeley.com/research/outline-morphometric-approach-identifying-fossil-spiders-preliminary-examination-florissant-formation/",
+                        :doi => "10.1130/2008.2435(07)." # This is wrong though
+                    ),
+                "http://www.mendeley.com/catalog/big-questions-biodiversity-informatics/" =>
+                    BibTeX::Entry.new(
+                        :type => 'article',
+                        :identifiers => "info:doi/10.1080/14772001003739369\nhttp://www.mendeley.com/catalog/big-questions-biodiversity-informatics/",
+                        :journal => "Systematics and Biodiversity",
+                        :pages => "159--168",
+                        :author => "Peterson, A Townsend and Knapp, Sandra and Guralnick, Robert and Soberón, Jorge and Holder, Mark T",
+                        :date => "2010",
+                        :year => "2010",
+                        :title => "The big questions for biodiversity informatics",
+                        :volume => "8",
+                        :number => "2",
+                        :issn => "14772000",
+                        :url => "http://www.mendeley.com/catalog/big-questions-biodiversity-informatics/",
+                        :doi => "10.1080/14772001003739369"
+                    ),
+                "http://www.mendeley.com/catalog/biodiversity-informatics-automated-approaches-documenting-global-biodiversity-patterns-processes/" => 
+                    BibTeX::Entry.new(
+                        :type => 'article',
+                        :identifiers => "info:pmid/19129210\nhttp://www.mendeley.com/catalog/biodiversity-informatics-automated-approaches-documenting-global-biodiversity-patterns-processes/",
+                        :journal => "Bioinformatics",
+                        :pages => "421--428",
+                        :author => "Guralnick, Robert and Hill, Andrew",
+                        :date => "2009",
+                        :year => "2009",
+                        :title => "Biodiversity informatics: automated approaches for documenting global biodiversity patterns and processes.",
+                        :volume => "25",
+                        :number => "4",
+                        :url => "http://www.mendeley.com/catalog/biodiversity-informatics-automated-approaches-documenting-global-biodiversity-patterns-processes/"
+                    ),
+                "http://www.mendeley.com/research/hs-2-w-estern-o-ffshoots-1500-2001-australia-canada-new-zealand-united-states/" => 
+                    BibTeX::Entry.new(
+                        :type => 'article',
+                        :identifiers => "http://www.mendeley.com/research/hs-2-w-estern-o-ffshoots-1500-2001-australia-canada-new-zealand-united-states/",
+                        :journal => "Work",
+                        :pages => "71--90",
+                        :author => "Offshoots, Western",
+                        :date => "2001",
+                        :year => "2001",
+                        :title => "HS – 2 : W ESTERN O FFSHOOTS : 1500 – 2001 ( Australia , Canada , New Zealand , and the United States )",
+                        :volume => "2001",
+                        :isbn => "9264022619",
+                        :url => "http://www.mendeley.com/research/hs-2-w-estern-o-ffshoots-1500-2001-australia-canada-new-zealand-united-states/"
+                    ),
+                "http://www.citeulike.org/user/bjbraams/article/12683220" => 
+                    BibTeX::Entry.new(
+                        :type => 'article',
+                        :identifiers => "info:doi/10.1016/s0009-2614(02)00988-0\nhttp://www.citeulike.org/user/bjbraams/article/12683220",
+                        :journal => "Chemical Physics Letters",
+                        :pages => "520--524",
+                        :author => "Scemama, Anthony and Chaquin, Patrick and Gazeau, Marie-Claire and Bénilan, Yves",
+                        :date => "2002-8",
+                        :year => "2002",
+                        :month => "8",
+                        :title => "Semi-empirical calculation of electronic absorption wavelengths of polyynes, monocyano- and dicyanopolyynes. Predictions for long chain compounds and carbon allotrope carbyne",
+                        :volume => "361",
+                        :number => "5-6",
+                        :issn => "00092614",
+                        :url => "http://www.citeulike.org/user/bjbraams/article/12683220",
+                        :doi => "10.1016/s0009-2614(02)00988-0"
+                    ),
+                #"http://www.bioone.org/doi/abs/10.1642/0004-8038(2002)119%5B0897:FTSTTA%5D2.0.CO%3B2" => 
+                #    BibTeX::Entry.new(
+                #
+                #    ),
+                "http://www.biodiversitylibrary.org/part/87340#/summary" => 
+                    BibTeX::Entry.new(
+                        :type => 'article',
+                        :identifiers => "info:doi/10.2307/4067078\nurn:ISSN:0004-8038\nhttp://www.biodiversitylibrary.org/part/87340\nhttp://www.biodiversitylibrary.org/part/87340#/summary",
+                        :journal => "The Auk",
+                        :pages => "60--66",
+                        :author => "Allen, J A and Brewster, William and Coues, Elliott and Ridgway, Robert and Sage, John H",
+                        :date => "1890",
+                        :year => "1890",
+                        :title => "Second Supplement to the American Ornithologists' Union Check-List of North American Birds",
+                        :volume => "7",
+                        :issn => "0004-8038",
+                        :url => "http://www.biodiversitylibrary.org/part/87340#/summary",
+                        :doi => "10.2307/4067078"
+                    )
             }
 
             queries.keys.each do |query|

data/spec/doi_spec.rb

@@ -46,31 +46,21 @@ describe BibURI::Driver::DOI do
     describe "lookup" do
         it "should be able to download information on some DOIs" do
             queries = {
-                "doi:10.1038/171737a0" => [
+                "doi:10.1038/171737a0" =>
                     BibTeX::Entry.new(
-                        :url => "http://dx.doi.org/10.1038/171737a0", 
-                        :doi => "10.1038/171737a0",
-                        :title => "Molecular Structure of Nucleic Acids: A Structure for Deoxyribose Nucleic Acid, year = 1953, journal = Nature, pages = 737-738", 
+                        :type => 'article',
+                        :identifiers => "info:doi/http://dx.doi.org/10.1038/171737a0\nhttp://dx.doi.org/10.1038/171737a0",
+                        :journal => "Nature",
+                        :pages => "737--738",
                         :author => "WATSON, J. D. and CRICK, F. H. C.", 
                         :date => "1953",
+                        :year => "1953",
+                        :title => "Molecular Structure of Nucleic Acids: A Structure for Deoxyribose Nucleic Acid", 
                         :volume => "171", 
-                        :number => "4356"
+                        :number => "4356",
+                        :url => "http://dx.doi.org/10.1038/171737a0",
+                        :doi => "10.1038/171737a0"
                     )
-                ],
-                "http://dx.doi.org/10.1111/j.1096-0031.2010.00329.x" => [
-                    BibTeX::Entry.new({
-                        "url" => "http://dx.doi.org/10.1111/j.1096-0031.2010.00329.x",
-                        "doi" => "10.1111/j.1096-0031.2010.00329.x",
-                        "title" => "SequenceMatrix: concatenation software for the fast assembly of multi-gene datasets with character set and codon information",
-                        "year" => "2011",
-                        "journal" => "Cladistics", 
-                        "pages" => "171-180",
-                        "author" => "Vaidya, Gaurav and Lohman, David J. and Meier, Rudolf",
-                        "date" => "2011",
-                        "volume" => "27", 
-                        "number" => "2"
-                    })
-                ]
             }
 
             queries.keys.each do |query|

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: biburi
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.1.0
 platform: ruby
 authors:
 - Gaurav Vaidya
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-10-02 00:00:00.000000000 Z
+date: 2013-10-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -16,88 +16,89 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '1.3'
+        version: 1.3.5
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '1.3'
+        version: 1.3.5
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '10.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '10.1'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 2.14.1
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 2.14.1
 - !ruby/object:Gem::Dependency
-  name: rspec-core
+  name: coveralls
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.7.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.7.0
 - !ruby/object:Gem::Dependency
-  name: coveralls
+  name: bibtex-ruby
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
+        version: 2.3.4
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 2.3.4
 - !ruby/object:Gem::Dependency
-  name: bibtex-ruby
+  name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: 1.6.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: 1.6.0
 description: Find the BibTeX information when your citation has an identifier
 email:
 - gaurav@ggvaidya.com
-executables: []
+executables:
+- biburi.rb
 extensions: []
 extra_rdoc_files: []
 files:
@@ -109,8 +110,10 @@ files:
 - README.md
 - Rakefile
 - biburi.gemspec
+- bin/biburi.rb
 - lib/biburi.rb
 - lib/biburi/driver.rb
+- lib/biburi/driver/coins.rb
 - lib/biburi/driver/doi.rb
 - lib/biburi/version.rb
 - spec/biburi_spec.rb