marc 0.5.1 → 0.6.0

data/README.md

@@ -1,3 +1,5 @@
+[![Build Status](https://secure.travis-ci.org/ruby-marc/ruby-marc.png)](http://travis-ci.org/ruby-marc/ruby-marc)
+
 marc is a ruby library for reading and writing MAchine Readable Cataloging
 (MARC). More information about MARC can be found at <http://www.loc.gov/marc>.
 

data/lib/marc/controlfield.rb

@@ -9,21 +9,16 @@ module MARC
   class ControlField
     
     # Initially, control tags are the numbers 1 through 9 or the string '000'
-    @@control_tags = Set.new( (1..9).to_a)
-    @@control_tags << '000'
+    @@control_tags = Set.new(%w{000 001 002 003 004 005 006 007 008 009})
  
     def self.control_tags
       return @@control_tags
     end
- 
-    # A tag is a control tag if it is a member of the @@control_tags set
-    # as either a string (e.g., 'FMT') or in its .to_i representation
-    # (e.g., '008'.to_i == 3 is in @@control_tags by default)
-  
+
+    # A tag is a control tag if tag.to_s is a member of the @@control_tags set.
     def self.control_tag?(tag)
-      return (@@control_tags.include?(tag.to_i) or @@control_tags.include?(tag))
+      return @@control_tags.include? tag.to_s
     end
-    
 
     # the tag value (007, 008, etc)
     attr_accessor :tag

data/lib/marc/reader.rb

@@ -177,22 +177,26 @@ module MARC
     #     print record
     #   end
     def each
-      # while there is data left in the file
-      while rec_length_s = @handle.read(5)
-        # make sure the record length looks like an integer
-        rec_length_i = rec_length_s.to_i
-        if rec_length_i == 0
-          raise MARC::Exception.new("invalid record length: #{rec_length_s}")
-        end
+      unless block_given?
+        return self.enum_for(:each)
+      else
+        # while there is data left in the file
+        while rec_length_s = @handle.read(5)
+          # make sure the record length looks like an integer
+          rec_length_i = rec_length_s.to_i
+          if rec_length_i == 0
+            raise MARC::Exception.new("invalid record length: #{rec_length_s}")
+          end
 
-        # get the raw MARC21 for a record back from the file
-        # using the record length
-        raw = rec_length_s + @handle.read(rec_length_i-5)
+          # get the raw MARC21 for a record back from the file
+          # using the record length
+          raw = rec_length_s + @handle.read(rec_length_i-5)
 
-        # create a record from the data and return it
-        #record = MARC::Record.new_from_marc(raw)
-        record = MARC::Reader.decode(raw, @encoding_options)
-        yield record
+          # create a record from the data and return it
+          #record = MARC::Record.new_from_marc(raw)
+          record = MARC::Reader.decode(raw, @encoding_options)
+          yield record
+        end
       end
     end
 

data/lib/marc/version.rb

@@ -1,3 +1,3 @@
 module MARC
-  VERSION = "0.5.1"
+  VERSION = "0.6.0"
 end

data/lib/marc/xml_parsers.rb

@@ -105,8 +105,12 @@ module MARC
     
     # Loop through the MARC records in the XML document
     def each(&block)    
-      @block = block
-      @parser.parse(@handle)
+      unless block_given?
+        return self.enum_for(:each)
+      else
+        @block = block
+        @parser.parse(@handle)
+      end
     end
         
 
@@ -165,13 +169,17 @@ module MARC
     
     # Loop through the MARC records in the XML document
     def each
-      while @parser.has_next?
-        event = @parser.pull
-        # if it's the start of a record element 
-        if event.start_element? and strip_ns(event[0]) == 'record'
-          yield build_record
-        end
-      end    
+      unless block_given?
+        return self.enum_for(:each)
+      else
+        while @parser.has_next?
+          event = @parser.pull
+          # if it's the start of a record element 
+          if event.start_element? and strip_ns(event[0]) == 'record'
+            yield build_record
+          end
+        end    
+      end
     end
     
     private
@@ -310,11 +318,15 @@ module MARC
     end
 
     def each
-      while (@parser.read) do
-       if @parser.local_name == 'record' && @parser.namespace_uri == @ns
-         yield build_record
-       end
-      end # while
+      unless block_given?
+        return self.enum_for(:each)
+      else
+        while (@parser.read) do
+         if @parser.local_name == 'record' && @parser.namespace_uri == @ns
+           yield build_record
+         end
+        end # while
+      end
     end # each
 
     def build_record
@@ -370,9 +382,13 @@ end
       end
 
       # Loop through the MARC records in the XML document
-      def each(&block)    
-        @block = block
-        parser_dispatch
+      def each(&block)  
+        unless block_given?
+          return self.enum_for(:each)
+        else
+          @block = block
+          parser_dispatch
+        end
       end
 
       def parser_dispatch

data/test/hebrew880s.marc

@@ -0,0 +1 @@
+01998cam a2200469 a 4500001000800000005001700008008004100025020001800066020001500084024001800099024001200117035001200129035001700141035002100158040003200179042000800211049000900219050002100228066000700249100002900256245010000285246008400385260015000469300002100619504006400640541010900704600004100813600004700854650002500901650002300926650002900949650002500978752002201003880003701025880013001062880017301192910002601365936002701391938003801418991006001456994001201516408398520120302131100.0110313s2011    is       b    001 0 heb c  a9789651321337  a96513213348 a00032002131958 a3221319  a4083985  aocn710973037  a(OCoLC)710973037  aWEINBcWEINBdHLSdIXAdCUY  apcc  aJHEE 4aDS149b.R38 2011  c(21 6880-01aRatsabi, Shalom.106880-02aAnarkhizm be-"Tsiyon" :bben Marṭin Buber le-Aharon Daṿid Gordon /cShalom Ratsabi.1 iTitle on t.p. verso:aAnarchy in "Zion" :bbetween Martin Buber and A.D. Gordon  6880-03a[Tel Aviv] :bʻAm ʻoved :bha-Makhon le-ḥeḳer ha-Tsiyonut ve-Yiśra'el ʻa. sh. Ḥayim Ṿaitsman, Universiṭat Tel Aviv,cc2011.  a339 p. ;c23 cm.  aIncludes bibliographical references (p. 320-330) and index.  3Eisenhower copy:cPurchased with support from the National Endowment for the Humanities;dFY2012.5MdBJ.10aBuber, Martin,d1878-1965xReligion.10aGordon, Aaron David,d1856-1922xReligion. 0aZionism and Judaism. 0aReligious Zionism. 0aZionismxHistoriography. 0aZionismxPhilosophy.  aIsraeldTel Aviv.1 6100-01/(2/raרצבי, שלום.106245-02/(2/raאנרכיזם ב״ציון״ :bבין מרטין בובר לאהרן דוד גורדון /cשלום רצבי.  6260-03/(2/ra[תל אביב] :bעם עובד :bהמכון לחקר הציונות וישראל עʺש חיים ויצמן, אוניברסיטת תל אביב,cc2011.  a4083985bHorizon bib#  aPR 747581025 741225747  aA.I. WeinbergbWEINnwb2011369996  aDS149.R38 2011flcbelccc. 1q0i6085034lemainmemsel  aC0bJHE

data/test/tc_datafield.rb

@@ -13,6 +13,14 @@ class TestField < Test::Unit::TestCase
         assert_not_equal(f1, f3)
     end
 
+    def test_alphabetic_tag
+        alph = MARC::DataField.new('ALF')
+        assert_equal 'ALF', alph.tag
+
+        alphnum = MARC::DataField.new('0D9')
+        assert_equal '0D9', alphnum.tag
+    end
+
     def test_indicators
         f1 = MARC::DataField.new('100', '0', '1')
         assert_equal('0', f1.indicator1)

data/test/tc_reader.rb

@@ -72,5 +72,16 @@ class ReaderTest < Test::Unit::TestCase
     records = reader.find_all { |r| r =~ /Foo/ }
     assert_equal(0, records.length)
   end
+  
+  def test_binary_enumerator
+    reader = MARC::Reader.new('test/batch.dat')
+    iter = reader.each
+    r = iter.next
+    assert_instance_of(MARC::Record, r)
+    9.times {iter.next} # total of ten records
+    assert_raises(StopIteration) { iter.next }  
+  end
+
+    
 
 end

data/test/tc_record.rb

@@ -1,5 +1,18 @@
 require 'test/unit'
 require 'marc'
+require 'xmlsimple'
+
+ def xml_cmp a, b
+   eq_all_but_zero = Object.new.instance_eval do
+     def ==(other)
+       Integer(other) == 0 ? false : true
+     end
+     self
+   end
+   a = XmlSimple.xml_in(a.to_s, 'normalisespace' => eq_all_but_zero) 
+   b = XmlSimple.xml_in(b.to_s, 'normalisespace' => eq_all_but_zero) 
+   a == b
+ end
 
 class TestRecord < Test::Unit::TestCase
 
@@ -12,12 +25,7 @@ class TestRecord < Test::Unit::TestCase
       r = get_record()
       doc = r.to_xml
       assert_kind_of REXML::Element, doc
-      if RUBY_VERSION < '1.9.0'
-        assert_equal "<record xmlns='http://www.loc.gov/MARC21/slim'><leader>      Z   22        4500</leader><datafield tag='100' ind1='2' ind2='0'><subfield code='a'>Thomas, Dave</subfield></datafield><datafield tag='245' ind1='0' ind2='4'><subfield code='The Pragmatic Programmer'></subfield></datafield></record>", doc.to_s
-      else
-        # REXML inexplicably sorts the attributes alphabetically in Ruby 1.9
-        assert_equal "<record xmlns='http://www.loc.gov/MARC21/slim'><leader>      Z   22        4500</leader><datafield ind1='2' ind2='0' tag='100'><subfield code='a'>Thomas, Dave</subfield></datafield><datafield ind1='0' ind2='4' tag='245'><subfield code='The Pragmatic Programmer'></subfield></datafield></record>", doc.to_s        
-      end
+      assert xml_cmp("<record xmlns='http://www.loc.gov/MARC21/slim'><leader>      Z   22        4500</leader><datafield tag='100' ind1='2' ind2='0'><subfield code='a'>Thomas, Dave</subfield></datafield><datafield tag='245' ind1='0' ind2='4'><subfield code='The Pragmatic Programmer'></subfield></datafield></record>", doc.to_s)
     end
 
     def test_append_field

data/test/tc_weird_jruby_bytes.rb

@@ -0,0 +1,62 @@
+require 'test/unit'
+
+
+# jruby 1.7.4 (1.9.3p392) 2013-05-16 2390d3b on Java HotSpot(TM) 64-Bit Server VM 1.6.0_51-b11-457-11M4509 [darwin-x86_64]
+class TestField < Test::Unit::TestCase
+
+  def test_confused_bytecount
+
+
+
+
+
+    string_with_ctrl = "hello\x1fhello".force_encoding("UTF-8")
+    # control chars like \x1F ARE legal UTF-8, this is correct:
+    assert string_with_ctrl.valid_encoding?
+
+    # It's even considered ascii_only? -- this is correct, both MRI and jruby
+    assert string_with_ctrl.ascii_only?
+
+
+    # For reasons I can't explain, I can only reproduce the 
+    # problem right now by doing a split, on the control char
+    # (this does represent my actual use case)
+    # Whether the split operand is tagged ASCII or UTF-8 does not matter,
+    # case is identical either way. 
+    elements = string_with_ctrl.split("\x1F".force_encoding("UTF-8"))  
+
+    # For some reason weirdness only happens on the second one in the split
+    # in this case. 
+    second = elements[1]
+
+
+    # For a string composed of all one-byte wide ascii, as this one is...
+    assert_equal "hello", second
+    assert second.ascii_only?
+
+    # string[0] and string.byteslice(0) shoudl be identical. They are
+    # different when the string contains multi-byte chars. 
+    # using #[], we're okay
+    assert_equal "h", second[0]
+
+    # But on jruby, this following actually raises an exception!
+    assert_equal "h", second.byteslice(0)
+    # That one up there actually just raised!!!
+    # Java::JavaLang::ArrayIndexOutOfBoundsException: 12
+    #  org.jruby.util.ByteList.equal(ByteList.java:960)
+
+    # In other cases I saw in my real app, it didn't raise, but
+    # did return the WRONG bytes. Ie, not a 'h' above as expected, or
+    # not:
+
+  
+    assert_equal second[0], second.byteslice(0)
+    # but in jruby we never even get here, we raise. 
+
+    # In MRI, we pass ALL these tests with no exceptions. 
+    # (ruby 1.9.3p448 (2013-06-27 revision 41675) [x86_64-darwin12.4.0])
+  end
+
+
+
+end

data/test/tc_xml.rb

@@ -157,6 +157,25 @@ class XMLTest < Test::Unit::TestCase
 
     File.unlink('test/test.xml')
   end
+  
+  def test_xml_enumerator
+    @parsers.each do | parser |
+      puts "\nRunning test_xml_enumerator with: #{parser}.\n"
+      xml_enumerator_test(parser)
+    end
+  end
+  
+  
+  def xml_enumerator_test(parser)
+    # confusingly, test/batch.xml only has two records, not 10 like batch.dat
+    reader = MARC::XMLReader.new('test/batch.xml', :parser=>parser)
+    iter = reader.each
+    r = iter.next
+    assert_instance_of(MARC::Record, r)
+    iter.next # total of two records
+    assert_raises(StopIteration) { iter.next }  
+  end
+  
 
 end
 

metadata

@@ -1,8 +1,8 @@
 --- !ruby/object:Gem::Specification
 name: marc
 version: !ruby/object:Gem::Version
-  prerelease:
-  version: 0.5.1
+  version: 0.6.0
+  prerelease: 
 platform: ruby
 authors:
 - Kevin Clarke
@@ -13,15 +13,14 @@ authors:
 autorequire: marc
 bindir: bin
 cert_chain: []
-date: 2013-07-11 00:00:00.000000000 Z
+date: 2013-08-19 00:00:00.000000000 Z
 dependencies: []
-description:
+description: 
 email: ehs@pobox.com
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- lib/marc.rb
 - lib/marc/constants.rb
 - lib/marc/controlfield.rb
 - lib/marc/datafield.rb
@@ -35,10 +34,12 @@ files:
 - lib/marc/xml_parsers.rb
 - lib/marc/xmlreader.rb
 - lib/marc/xmlwriter.rb
+- lib/marc.rb
 - test/batch.dat
 - test/batch.xml
 - test/cp866_multirecord.marc
 - test/cp866_unimarc.marc
+- test/hebrew880s.marc
 - test/marc8_accented_chars.marc
 - test/no-leading-zero.xml
 - test/non-numeric.dat
@@ -57,6 +58,7 @@ files:
 - test/tc_reader_char_encodings.rb
 - test/tc_record.rb
 - test/tc_subfield.rb
+- test/tc_weird_jruby_bytes.rb
 - test/tc_writer.rb
 - test/tc_xml.rb
 - test/ts_marc.rb
@@ -69,26 +71,26 @@ files:
 - LICENSE
 homepage: https://github.com/ruby-marc/ruby-marc/
 licenses: []
-post_install_message:
+post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
   requirements:
-  - - '>='
+  - - ! '>='
     - !ruby/object:Gem::Version
       version: 1.8.6
-  none: false
 required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
   requirements:
-  - - '>='
+  - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
-  none: false
 requirements: []
-rubyforge_project:
-rubygems_version: 1.8.24
-signing_key:
+rubyforge_project: 
+rubygems_version: 1.8.23
+signing_key: 
 specification_version: 3
 summary: A ruby library for working with Machine Readable Cataloging
 test_files: