arxivsync 0.0.3 → 0.0.4

data/README.md

@@ -1,4 +1,4 @@
-# arxivsync-0.0.3
+# arxivsync-0.0.4
 
 Ruby OAI interface for harvesting the arXiv. Can be used to store and update an XML mirror of paper metadata, and parse the XML into Ruby objects to allow conversion into a friendlier format.
 

data/lib/arxivsync/downloader.rb

@@ -2,6 +2,12 @@ module ArxivSync
   class Downloader
     def initialize(initial_params={})
       @initial_params = initial_params
+
+      if @initial_params[:from] == Date.today
+        puts "Last responseDate was today. arXiv lacks date granularity beyond the day level; please wait before continuing harvest."
+        return false
+      end
+
       unless @initial_params[:resumptionToken]
         @initial_params[:metadataPrefix] ||= 'arXiv'
       end

data/lib/arxivsync/parser.rb

@@ -1,10 +1,14 @@
 module ArxivSync
+  # Layout reference: http://www.xmlns.me/?op=visualize&id=643
   Author = Struct.new(
-    :keyname, :forenames
+    :keyname, :forenames, :suffix, :affiliation
   )
 
   Paper = Struct.new(
-    :id, :created, :updated, :title, :abstract, :authors,
+    :id, :created, :updated, :authors, :title,
+    :msc_class, :report_no, :journal_ref, :comments,
+    :abstract, :categories, :doi, :proxy, :license,
+
     :primary_category, :crosslists
   )
 
@@ -38,15 +42,34 @@ module ArxivSync
         @model.updated = Date.parse(str)
       when :title
         @model.title = clean(str)
+      when :"msc-class"
+        @model.msc_class = str
+      when :"report-no"
+        @model.report_no = str
+      when :"journal-ref"
+        @model.journal_ref = str
+      when :comments
+        @model.comments = clean(str)
       when :abstract
         @model.abstract = clean(str)
       when :categories
+        @model.categories = str.split
         @model.primary_category = str.split[0]
         @model.crosslists = str.split.drop(1)
+      when :doi
+        @model.doi = str
+      when :proxy
+        @model.proxy = str
+      when :license
+        @model.license = str
       when :keyname
         @author.keyname = str
       when :forenames
         @author.forenames = str
+      when :suffix
+        @author.suffix = str
+      when :affiliation
+        @author.affiliation = str
       end
     end
 

data/lib/arxivsync/version.rb

@@ -1,3 +1,3 @@
 module ArxivSync
-  VERSION = "0.0.3"
+  VERSION = "0.0.4"
 end

data/lib/arxivsync/xmlarchive.rb

@@ -41,12 +41,8 @@ module ArxivSync
 
         if last_token.empty? # Previous sync completed successfully
           responseDate = Date.parse(last_response.css('responseDate').text)
-          if responseDate == Date.today
-            puts "Last responseDate was today. arXiv lacks date granularity beyond the day level; please wait before continuing harvest."
-            return false
-          end
           puts "Downloading from last responseDate: #{responseDate}"
-          oai_params[:from] ||= responseDate
+          oai_params[:from] = responseDate
         else # Previous sync aborted prematurely, resume
           puts "Resuming download using previous resumptionToken: #{last_token}"
           oai_params = { resumptionToken: last_token }

data/test/parser.rb

@@ -6,7 +6,7 @@ TEST_ROOT = File.dirname(__FILE__)
 class TestParser < Minitest::Test
   def test_parser
     archive = ArxivSync::XMLArchive.new(File.join(TEST_ROOT, 'fixtures'))
-    tested_a_paper = false
+    tested = 0
     archive.read_metadata do |papers|
       assert_equal papers.count, 1000
       papers.each do |paper|
@@ -14,16 +14,24 @@ class TestParser < Minitest::Test
           assert_equal paper.created, Date.parse("2013-02-04")
           assert_equal paper.updated, nil
           assert_equal paper.title, "Correlation effects in the electronic structure of the Ni-based superconducting KNi2S2"
+          assert_equal paper.license, "http://creativecommons.org/licenses/by/3.0/"
           assert_equal paper.primary_category, "cond-mat.supr-con"
           assert_equal paper.crosslists, []
           assert_includes paper.abstract, "using Gutzwiller approximation method."
           assert_equal paper.authors.map(&:keyname), ["Lu", "Wang", "Xie", "Zhang"]
           assert_equal paper.authors.map(&:forenames), ["Feng", "Wei-Hua", "Xinjian", "Fu-Chun"]
-          tested_a_paper = true
+          tested += 1
+        end
+
+        if paper.id == "1302.0758"
+          assert_equal paper.authors[0].affiliation, "Baylor University, Waco, TX, USA"
+          assert_equal paper.comments, "8 pages, 4 figures; presented by BFLW at ICHEP 2012"
+          assert_equal paper.report_no, "BU-HEPP-12-05"
+          tested += 1
         end
       end
     end
 
-    assert tested_a_paper
+    assert_equal tested, 2
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: arxivsync
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.0.4
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-06-11 00:00:00.000000000 Z
+date: 2013-06-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler