marc 0.5.0 → 0.5.1

data/lib/marc/reader.rb

@@ -215,6 +215,10 @@ module MARC
         # declared on the string passed in. 
         params[:external_encoding] = marc.encoding
       end
+      # And now that we've recorded the current encoding, we force
+      # to binary encoding, because we're going to be doing byte arithmetic,
+      # and want to avoid byte-vs-char confusion. 
+      marc.force_encoding("binary") if marc.respond_to?(:force_encoding)
       
       record = Record.new()
       record.leader = marc[0..LEADER_LENGTH-1]

data/lib/marc/version.rb

@@ -1,3 +1,3 @@
 module MARC
-  VERSION = "0.5.0"
+  VERSION = "0.5.1"
 end

data/lib/marc/xml_parsers.rb

@@ -112,7 +112,7 @@ module MARC
 
     def method_missing(methName, *args)
       sax_methods = [:xmldecl, :start_document, :end_document, :start_element,
-        :end_element, :comment, :warning, :error, :cdata_block]
+        :end_element, :comment, :warning, :error, :cdata_block, :processing_instruction]
       unless sax_methods.index(methName)
         raise NoMethodError.new("undefined method '#{methName} for #{self}", 'no_meth')
       end
@@ -293,7 +293,11 @@ module MARC
     end
   end
   
-  module LibXMLReader
+  
+  
+  
+  unless defined? JRUBY_VERSION
+    module LibXMLReader
 
     def self.extended(receiver)
       require 'xml'
@@ -344,6 +348,7 @@ module MARC
       return r
     end
   end
+end
 
   # The JrubySTAXReader uses native java calls to parse the incoming stream
   # of marc-xml. It includes most of the work from GenericPullParser
@@ -352,9 +357,7 @@ module MARC
     module JRubySTAXReader
       include GenericPullParser
       def self.extended(receiver)
-        include Java
-        java.lang.Class.forName("javax.xml.stream.XMLInputFactory")
-        include javax.xml.stream       
+        require 'java' # may only be neccesary in jruby 1.6
         receiver.init
       end
 
@@ -373,13 +376,13 @@ module MARC
       end
 
       def parser_dispatch
-        while event = @parser.next and event != XMLStreamConstants.END_DOCUMENT do
+        while event = @parser.next and event != javax.xml.stream.XMLStreamConstants.END_DOCUMENT do
           case event
-            when XMLStreamConstants.START_ELEMENT
+            when javax.xml.stream.XMLStreamConstants.START_ELEMENT
               start_element_namespace(@parser.getLocalName, [], nil,  @parser.getNamespaceURI, nil)
-            when XMLStreamConstants.END_ELEMENT
+            when javax.xml.stream.XMLStreamConstants.END_ELEMENT
               end_element_namespace(@parser.getLocalName, @parser.getPrefix, @parser.getNamespaceURI)
-            when XMLStreamConstants.CHARACTERS
+            when javax.xml.stream.XMLStreamConstants.CHARACTERS
               characters(@parser.getText)
           end
         end

data/lib/marc/xmlreader.rb

@@ -69,6 +69,7 @@ module MARC
         raise ArgumentError, "jstax only available under jruby" unless defined? JRUBY_VERSION
         extend JRubySTAXReader
       when 'libxml' then extend LibXMLReader
+        raise ArgumentError, "libxml not available under jruby" if defined? JRUBY_VERSION
       end
     end
 
@@ -95,14 +96,9 @@ module MARC
     # Returns the value of the best available parser
     def self.best_available
       parser = nil
-      jruby = [USE_JSTAX, USE_NOKOGIRI, USE_JREXML]
+      jruby = [USE_NOKOGIRI, USE_JSTAX, USE_JREXML]
       ruby = [USE_NOKOGIRI, USE_LIBXML]
       if defined? JRUBY_VERSION
-        begin
-          java.lang.Class.forName("javax.xml.stream.XMLInputFactory")
-          parser = USE_JSTAX
-        rescue java.lang.ClassNotFoundException
-        end
         unless parser
           begin
             require 'nokogiri'
@@ -110,6 +106,14 @@ module MARC
           rescue LoadError
           end
         end
+        unless parser
+          begin
+            # try to find the class, so we throw an error if not found
+            java.lang.Class.forName("javax.xml.stream.XMLInputFactory") 
+            parser = USE_JSTAX
+          rescue java.lang.ClassNotFoundException
+          end
+        end
         unless parser
           begin
             require 'jrexml'
@@ -123,13 +127,15 @@ module MARC
           parser = USE_NOKOGIRI        
         rescue LoadError          
         end
-        unless parser
-          begin
-            require 'xml'
-            parser = USE_LIBXML
-          rescue LoadError
-          end
-        end        
+        unless defined? JRUBY_VERSION
+          unless parser
+            begin
+              require 'xml'
+              parser = USE_LIBXML
+            rescue LoadError
+            end
+          end        
+        end
       end
       parser = USE_REXML unless parser
       parser

data/test/tc_parsers.rb

@@ -164,15 +164,6 @@ end
   def choose_best_available_parser
     parser_name = nil
     parser = nil
-    if defined? JRUBY_VERSION
-      require 'java'
-      begin
-        java.lang.Class.forName("javax.xml.stream.XMLInputFactory")
-        parser_name = "jstax"
-        parser = Java::ComSunOrgApacheXercesInternalImpl::XMLStreamReaderImpl
-      rescue java.lang.ClassNotFoundException
-      end
-    end
     unless parser    
       begin
         require 'nokogiri'
@@ -181,6 +172,17 @@ end
       rescue LoadError
       end
     end
+    unless parser
+      if defined? JRUBY_VERSION
+        require 'java'
+        begin
+          java.lang.Class.forName("javax.xml.stream.XMLInputFactory")
+          parser_name = "jstax"
+          parser = Java::ComSunOrgApacheXercesInternalImpl::XMLStreamReaderImpl
+        rescue java.lang.ClassNotFoundException
+        end
+      end
+    end
     unless parser
       if !defined? JRUBY_VERSION
         begin

data/test/tc_xml.rb

@@ -10,10 +10,12 @@ class XMLTest < Test::Unit::TestCase
       @parsers << :nokogiri
     rescue LoadError
     end
-    begin
-      require 'xml'
-      @parsers << :libxml
-    rescue LoadError
+    unless defined? JRUBY_VERSION
+      begin
+        require 'xml'
+        @parsers << :libxml
+      rescue LoadError
+      end
     end
     if defined? JRUBY_VERSION
       begin

metadata

@@ -1,15 +1,10 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: marc
-version: !ruby/object:Gem::Version 
-  hash: 11
-  prerelease: 
-  segments: 
-  - 0
-  - 5
-  - 0
-  version: 0.5.0
+version: !ruby/object:Gem::Version
+  prerelease:
+  version: 0.5.1
 platform: ruby
-authors: 
+authors:
 - Kevin Clarke
 - Bill Dueber
 - William Groppe
@@ -18,104 +13,83 @@ authors:
 autorequire: marc
 bindir: bin
 cert_chain: []
-
-date: 2012-05-07 00:00:00 Z
+date: 2013-07-11 00:00:00.000000000 Z
 dependencies: []
-
-description: 
+description:
 email: ehs@pobox.com
 executables: []
-
 extensions: []
-
 extra_rdoc_files: []
-
-files: 
-- lib/marc/xml_parsers.rb
+files:
+- lib/marc.rb
+- lib/marc/constants.rb
 - lib/marc/controlfield.rb
-- lib/marc/reader.rb
-- lib/marc/dublincore.rb
-- lib/marc/xmlwriter.rb
 - lib/marc/datafield.rb
-- lib/marc/record.rb
+- lib/marc/dublincore.rb
 - lib/marc/exception.rb
+- lib/marc/reader.rb
+- lib/marc/record.rb
+- lib/marc/subfield.rb
+- lib/marc/version.rb
 - lib/marc/writer.rb
+- lib/marc/xml_parsers.rb
 - lib/marc/xmlreader.rb
-- lib/marc/version.rb
-- lib/marc/constants.rb
-- lib/marc/subfield.rb
-- lib/marc.rb
-- test/one.dat
-- test/one.xml
+- lib/marc/xmlwriter.rb
+- test/batch.dat
 - test/batch.xml
 - test/cp866_multirecord.marc
-- test/random_tag_order.dat
+- test/cp866_unimarc.marc
+- test/marc8_accented_chars.marc
 - test/no-leading-zero.xml
-- test/tc_record.rb
-- test/tc_parsers.rb
-- test/tc_hash.rb
-- test/tc_subfield.rb
 - test/non-numeric.dat
-- test/test_cp866.txt
-- test/batch.dat
-- test/jruby_bad_transcode.rb
+- test/non-numeric.xml
+- test/one.dat
+- test/one.xml
+- test/random_tag_order.dat
+- test/random_tag_order2.dat
 - test/tc_controlfield.rb
-- test/tc_bare_ruby_strings.rb
-- test/tc_marchash.rb
-- test/marc8_accented_chars.marc
-- test/cp866_unimarc.marc
 - test/tc_datafield.rb
-- test/tc_reader_char_encodings.rb
-- test/utf8_with_bad_bytes.marc
-- test/utf8.marc
-- test/bare_cp866.txt
 - test/tc_dublincore.rb
-- test/utf8_multirecord.marc
+- test/tc_hash.rb
+- test/tc_marchash.rb
+- test/tc_parsers.rb
+- test/tc_reader.rb
+- test/tc_reader_char_encodings.rb
+- test/tc_record.rb
+- test/tc_subfield.rb
 - test/tc_writer.rb
 - test/tc_xml.rb
-- test/non-numeric.xml
-- test/random_tag_order2.dat
 - test/ts_marc.rb
-- test/tc_reader.rb
-- test/jruby_just_string.rb
+- test/utf8.marc
+- test/utf8_multirecord.marc
+- test/utf8_with_bad_bytes.marc
 - Rakefile
 - README.md
 - Changes
 - LICENSE
 homepage: https://github.com/ruby-marc/ruby-marc/
 licenses: []
-
-post_install_message: 
+post_install_message:
 rdoc_options: []
-
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 59
-      segments: 
-      - 1
-      - 8
-      - 6
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
       version: 1.8.6
-required_rubygems_version: !ruby/object:Gem::Requirement 
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
-      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+  none: false
 requirements: []
-
-rubyforge_project: 
-rubygems_version: 1.8.23
-signing_key: 
+rubyforge_project:
+rubygems_version: 1.8.24
+signing_key:
 specification_version: 3
 summary: A ruby library for working with Machine Readable Cataloging
-test_files: 
+test_files:
 - test/ts_marc.rb

data/test/bare_cp866.txt

@@ -1 +0,0 @@
-����㭠�. ������ ��� ����⬠��

data/test/jruby_bad_transcode.rb

@@ -1,52 +0,0 @@
-# encoding: utf-8
-
-# 1.9.3p0 :005 > 0x8D.chr.force_encoding("cp866").encode("UTF-8")
-utf8 = "Н".force_encoding("UTF-8")
-
-puts "There's a cyrillic letter that looks kinda like a capital H. Here's what it looks like in unicode: Н"
-
-puts "In unicode, that's byte array: " + utf8.bytes.to_a.inspect
-
-puts "We're gonna use String#encode to convert it to an IBM866 encoding, also known as cp866, an encoding sometimes used in Russia."
-
- 
-puts "  `utf8.encode(\"IBM866\")`"
-
-cp866 = utf8.encode("IBM866") 
-puts cp866.bytes.to_a.inspect
-
-exit
-
-puts
-puts "In cp866, the actual bytes are: #{cp866_phrase.bytes.to_a.inspect}"
-puts
-
-puts "We're going to write the cp866 string to disk, using binary:binary to try and make sure we get the bytes to disk without transcoding."
-
-write = File.open("test_cp866.txt", "w", :internal_encoding => "binary", :external_encoding => "binary")
-write.puts cp866_phrase
-write.close
-puts
-
-puts "Now we're going to read it in with a File object with external_encoding set to IBM866, but no internal_encoding set."
-
-puts
-puts "Make sure we have no default internal_encoding: " + Encoding.default_internal.nil?.inspect
-
-read = File.open("test_cp866.txt", :external_encoding => "cp866")
-puts
-puts "Our ruby file object should have external_encoding of IBM866: " + read.external_encoding.inspect
-puts "  and internal_encoding nil: " + read.internal_encoding.inspect
-
-puts
-
-read_in_string = read.read
-read.close
-
-puts "The encoding of the string we read in should be IBM866: " + (read_in_string.encoding.name == "IBM866").inspect 
-
-puts
-puts "And the bytes should be the very same bytes we wrote out (which are valid cp866) " + (read_in_string.bytes.to_a[0,3] == [140, 165, 166]).inspect + " (#{read_in_string.bytes.to_a})"
-
-puts "The above is TRUE in MRI 1.9.3, but FALSE in jruby "
-

data/test/jruby_just_string.rb

@@ -1,39 +0,0 @@
-# encoding: binary
-
-# jruby 1.6.7 (ruby-1.9.2-p312) (2012-02-22 3e82bc8) (Java HotSpot(TM) 64-Bit Server VM 1.6.0_20) [linux-amd64-java]
-
-# There is a letter in cyrillic that looks kind of like a capital
-# H.  In the cp866 encoding (http://en.wikipedia.org/wiki/Code_page_866)
-# it's represented by "\x8D" which is decimal 141. 
-#
-# In ruby 1.9, it _ought_ to be possible to have those bytes
-# in a string, and tell ruby it's cp866. 
-
-cp866 = "\x8D".force_encoding("IBM866")
-
-# in MRI 1.9.3, if we inspect that, we get "\x8D", just like we expect.
-# and if we look at #bytes.to_a, we get [141], just like we expect. 
-puts cp866.inspect
-puts cp866.bytes.to_a.inspect
-# However, in jruby if we #inspect instead of getting "\x8D", 
-# we get "\u008D" -- this is wrong, it's NOT that unicode codepoint.
-# In jruby, bytes.to_a.inspect is still [141], it hasn't changed
-# the bytes, but it's confused about what's going on. 
-
-# We see this encoding confusion demonstrated if we try
-# a String#encode. 
-#
-# MRI 1.9.3 is perfectly capable of transcoding this to UTF-8
-
-utf8 = cp866.encode("UTF-8")
-puts utf8.inspect # =>  in MRI displays cyrillic in terminal no prob
-puts utf8.bytes.to_a.inspect # => in MRI [208, 157], proper bytes for utf8
-
-# In jruby, puts utf8.inspect displays "\u008D", and
-# utf8.bytes.to_a.inspect is [194, 141]. I don't know where the
-# 191 came from, but it has NOT succesfully transcoded to utf8. 
-
-# In other cases, the #encode will actually raise an illegal byte
-# exception if the original bytes were not legal for UTF8 (or UTF16?) --
-# but the original bytes were not meant to be considered unicode at all.
-

data/test/tc_bare_ruby_strings.rb

@@ -1,43 +0,0 @@
-require 'test/unit'
-
-class TestBareRubyStrings < Test::Unit::TestCase
-
- # The file bare_cp866.txt has in it a phrase encoded in cp866,
- # that if it were translated to utf8 would be:
- # "Междунар. новости мира пластмасс\n"
- #
- # The first few bytes of that in utf8 are:
- # "\xD0\x9C\xD0\xB5"
- # 
- # In cp866 as it is on disk, it's first few bytes are "\x8C\xA5"
-
- def test_read_cp866_with_external_encoding
-   return
-   file = File.open("test/bare_cp866.txt", "r:cp866")
-   string = file.read
-
-   assert_equal "IBM866", string.encoding.name
-
-   cp866_binary = string.dup.force_encoding("binary")
-   assert cp866_binary.start_with?( "\x8C\xA5".force_encoding("binary")  )
-   
-   transcoded = string.encode("UTF-8")
-   assert_equal "UTF-8", transcoded.encoding.name
-
-   utf8_binary = transcoded.dup.force_encoding("binary")
-
-   assert utf8_binary.start_with?( "\xD0\x9C\xD0\xB5".force_encoding("binary"))
- end
-
- def test_read_cp866_binary_all_the_way
-   # tell ruby to treat it as binary binary binary
-   file = File.open("test/bare_cp866.txt", :external_encoding => "binary", :internal_encoding => "binary")
-
-   string = file.read
-
-   # we should get the same bytes that were on disk, right?
-   assert string.start_with?( "\x8C\xA5".force_encoding("binary"))
- end
-
-
-end 

data/test/test_cp866.txt

@@ -1 +0,0 @@
-���