marc 1.0.0 → 1.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 91f847e4c58a60a123919914206e8b41935d1268
-  data.tar.gz: b9485bfa59528e3703cc5bc4b45ec10df6dea502
+  metadata.gz: 6944f89278a06152fa5710a34fa3c959d9300bc5
+  data.tar.gz: 87e131c8dbe524d724062741de10da219d30b83b
 SHA512:
-  metadata.gz: 7434cec1dd28cd9bdbf0390958d5f663f187720597c8bc5a0a45d04d6a84409bada2c6974e94b48effdc2e33fbb48fe54b3b86fb050a7e2bfa17da49bada3831
-  data.tar.gz: 83d5be3ce3eaa6da114101fe4dcbe15320b394184aeafa9aa20b8f7254c25d01f42f62d7153546909310adcb44d7f809c95f467c66f123435705b587957901b2
+  metadata.gz: 6bae7428d9c5c6c791a8c03687fb48d5ab5d0e3eec2005d8e9637bd6a9202c164b4e0882c6134526a7c64819dca6e7fc5dac17f9797c9891cbd743a1c231a7fc
+  data.tar.gz: b1420e8c1b7e991f878be77a1331a06bb83206b3a74f70057b8de8a3b579bb4900c0bb111bed7c5a88187241ac8b7dbcc07af4e085a3e07e9e0d0cee3ce7a0a4

data/Changes

@@ -1,15 +1,25 @@
+v1.0.2 July 2017
+ - Now (correctly) throw an error if datafield string is the empty string
+   (thanks to @bibliotechy)
+
+v1.0.1 February 2016
+- Non-user-facing change in implementation of FieldMap strictly for performance
+
+v1.0.0 January 2015
+- Mostly changes that deal with encoding, plus the plunge to a 1.0 release
+
 v0.5.0 April 2012
-- Extensive rewrite of MARC::Reader (ISO 2709 binary reader) to provide a 
-  fairly complete and consistent handing of char encoding issues in ruby 1.9. 
+- Extensive rewrite of MARC::Reader (ISO 2709 binary reader) to provide a
+  fairly complete and consistent handing of char encoding issues in ruby 1.9.
   - This code is well covered by automated tests, but ends up complex, there
-    may be bugs, please report them. 
-  - May not work properly under jruby with non-unicode source encodings. 
-  - Still can't handle Marc8 encoding. 
+    may be bugs, please report them.
+  - May not work properly under jruby with non-unicode source encodings.
+  - Still can't handle Marc8 encoding.
   - May not have entirely backwards compatible behavior with regard to char
-    encodings under ruby 1.9.x as previous 0.4.x versions. Test your code. 
+    encodings under ruby 1.9.x as previous 0.4.x versions. Test your code.
     In particular, previous versions may have automatically _transcoded_
     non-unicode encodings to UTF-8 for you. This version will not do
-    so unless you ask it to with correct arguments. 
+    so unless you ask it to with correct arguments.
 
 v0.4.4 Sat Mar 03 14:55:00 EDT 2012
 - Fixed performance regression: strict reader will parse about 5x faster now
@@ -26,8 +36,8 @@ v0.2.1 Mon Aug 18 14:14:16 EDT 2008
   Ross Singer)
 
 v0.2.0 Wed Jun 11 12:42:20 EDT 2008
-- added newline to output generated by REXML::Formatters::Default to make 
-  it a bit more friendly. REXML::Formatters::Pretty and Transitive just 
+- added newline to output generated by REXML::Formatters::Default to make
+  it a bit more friendly. REXML::Formatters::Pretty and Transitive just
   don't do what I want (whitespace in weird places).
 
 v0.1.9 Thu Jun  5 12:00:01 EDT 2008
@@ -36,7 +46,7 @@ v0.1.9 Thu Jun  5 12:00:01 EDT 2008
 
 v0.1.8 Tue Nov 13 22:51:03 EST 2007
 - added examples directory
-- fixed problem with leading whitespace and the leader in xml reader 
+- fixed problem with leading whitespace and the leader in xml reader
   (thanks Morgan Cundiff)
 
 v0.1.7 Mon Nov 12 09:33:57 EST 2007
@@ -58,7 +68,7 @@ v0.1.4 Tue Jan  2 15:45:53 EST 2007
 - fixed bug in MARC::XMLWriter that was outputting all control field tags as 00z
   (thanks Ross Singer)
 - added :include_namespace option to MARC::XMLWriter::encode to include the
-  marcxml namespace, which allows MARC::Record::to_xml to emit the namespace 
+  marcxml namespace, which allows MARC::Record::to_xml to emit the namespace
   for a single record.
 
 v0.1.3  Tue Jan  2 12:56:36 EST 2007
@@ -67,11 +77,11 @@ v0.1.3  Tue Jan  2 12:56:36 EST 2007
   as the hash keys.
 
 v0.1.2  Thu Dec 21 18:46:01 EST 2007
-- fixed MARC::Record::to_xml so that it actually is tested and works (thanks 
+- fixed MARC::Record::to_xml so that it actually is tested and works (thanks
   Ross Singer)
 
 v0.1.1
-- added ability to pass File like objects to the constructor for 
+- added ability to pass File like objects to the constructor for
   MARC::XMLReader like MARC::Reader (thanks Jake Glenn)
 
 v0.1.0  Wed Dec  6 15:40:40 EST 2006
@@ -93,11 +103,11 @@ v0.0.9  Tue Mar 28 10:02:16 CST 2006
 - added :stylesheet argument to XLMWriter.new
 
 v0.0.8  Mon Jan 16 22:31:00 EST 2006
-- removed control tests out of tc_field.rb into tc_control.rb 
+- removed control tests out of tc_field.rb into tc_control.rb
 - fixed some formatting
 - changed control/field to controlfield/datafield
 - added == check for controlfield
-- removed namespace declarations on record elements in favor of default 
+- removed namespace declarations on record elements in favor of default
   namespace on collection element
 - added spaces around subfield code and delimeter in to_s
 - fixed up relevant tests that were expecting old formatting
@@ -106,8 +116,8 @@ v0.0.8  Mon Jan 16 22:31:00 EST 2006
 
 v0.0.7  Mon Jan  2 21:39:28 CST 2006
 - MARC::XMLWriter added
-- removed encode/decode methods in MARC::MARC21 into MARC::Writer and 
-  MARC::Reader respectively. This required pushing MARC21 specific constants 
+- removed encode/decode methods in MARC::MARC21 into MARC::Writer and
+  MARC::Reader respectively. This required pushing MARC21 specific constants
   out into MARC::Constants which is required as necessary.
 - moved encode from MARC::MARXML into MARC::XMLWriter and added constants
   to MARC::Constants

data/README.md

@@ -69,8 +69,6 @@ Developers, release new version of gem to rubygems with `rake release`
 (bundler-supplied task). Note that one nice thing this will do is automatically
 tag the version in git, very important for later figuring out what's going on.
 
-Please send bugs, requests and comments to Code4Lib Mailing list (https://listserv.nd.edu/cgi-bin/wa?A0=CODE4LIB). 
-
 ## Authors
 
 Kevin Clarke <ksclarke@gmail.com>

data/lib/marc/datafield.rb

@@ -50,7 +50,7 @@ module MARC
     def initialize(tag, i1=' ', i2=' ', *subfields)
       # if the tag is less than 3 characters long and 
       # the string is all numeric then we pad with zeros
-      if tag.length < 3 and /^[0-9]*$/ =~ tag
+      if tag.length < 3 and /^[0-9]+$/ =~ tag
         @tag = "%03d" % tag
       else
         @tag = tag 

data/lib/marc/record.rb

@@ -1,16 +1,17 @@
-module MARC  
-    
+module MARC
+
   # The FieldMap is an Array of DataFields and Controlfields.
-  # It also contains a Hash representation 
+  # It also contains a Hash representation
   # of the fields for faster lookups (under certain conditions)
   class FieldMap < Array
     attr_reader :tags
     attr_accessor :clean
+
     def initialize
-      @tags = {}
+      @tags  = {}
       @clean = true
     end
-    
+
     # Rebuild the HashWithChecksumAttribute with the current
     # values of the fields Array
     def reindex
@@ -21,28 +22,42 @@ module MARC
       end
       @clean = true
     end
-    
+
     # Returns an array of all of the tags that appear in the record (not in the order they appear, however).
     def tag_list
       reindex unless @clean
       @tags.keys
     end
-    
+
     # Returns an array of fields, in the order they appear, according to their tag.
     # The tags argument can be a string (e.g. '245'), an array (['100','700','800'])
     # or a range (('600'..'699')).
+
     def each_by_tag(tags)
       reindex unless @clean
-      indices = @tags.values_at(*(@tags.keys & [*tags])).flatten.sort
+      indices = []
+      # Get all the indices associated with the tags
+      Array(tags).each do |t|
+        indices.concat @tags[t] if @tags[t]
+      end
+
+      # Remove any nils
+      indices.compact!
       return [] if indices.empty?
-      self.values_at(*indices).each do |tag|
-        yield tag
+
+     # Sort it, so we get the fields back in the order they appear in the record
+      indices.sort!
+
+      indices.each do |tag|
+        yield self[tag]
       end
     end
 
-    # Freeze for immutability, first reindexing if needed. 
+
+
+    # Freeze for immutability, first reindexing if needed.
     # A frozen FieldMap is safe for concurrent access, and also
-    # can more easily avoid accidental reindexing on even read-only use. 
+    # can more easily avoid accidental reindexing on even read-only use.
     def freeze
       self.reindex unless @clean
       super
@@ -50,18 +65,18 @@ module MARC
   end
 
   # A class that represents an individual MARC record. Every record
-  # is made up of a collection of MARC::DataField objects. 
+  # is made up of a collection of MARC::DataField objects.
   #
   # MARC::Record mixes in Enumerable to enable access to constituent
   # DataFields. For example, to return a list of all subject DataFields:
   #
-  #   record.find_all {|field| field.tag =~ /^6../}  
-  # 
+  #   record.find_all {|field| field.tag =~ /^6../}
+  #
   # The accessor 'fields' is also an Array of MARC::DataField objects which
   # the client can modify if neccesary.
   #
   #   record.fields.delete(field)
-  # 
+  #
   # Other accessor attribute: 'leader' for record leader as String
   #
   # == High-performance lookup by tag
@@ -82,13 +97,13 @@ module MARC
   #
   # MARC::Record is not generally safe for sharing between threads.
   # Even if you think you are just acccessing it read-only,
-  # you may accidentally trigger a reindex of the by-tag cache (see above). 
+  # you may accidentally trigger a reindex of the by-tag cache (see above).
   #
   # However, after you are done constructing a Record, you can mark
   # the `fields` array as immutable. This makes a Record safe for sharing
   # between threads for read-only use, and also helps you avoid accidentally
   # triggering a reindex, as accidental reindexes can harm by-tag
-  # lookup performance. 
+  # lookup performance.
   #
   #     record.fields.freeze
   class Record
@@ -101,9 +116,9 @@ module MARC
     attr_accessor :leader
 
     def initialize
-      @fields = FieldMap.new
+      @fields         = FieldMap.new
       # leader is 24 bytes
-      @leader = ' ' * 24
+      @leader         = ' ' * 24
       # leader defaults:
       # http://www.loc.gov/marc/bibliographic/ecbdldrd.html
       @leader[10..11] = '22'
@@ -119,9 +134,9 @@ module MARC
     end
 
     # alias to append
-    
+
     def <<(field)
-      append(field)      
+      append(field)
     end
 
     # each() is here to support iterating and searching since MARC::Record
@@ -141,20 +156,20 @@ module MARC
         yield field
       end
     end
-    
-    # A more convenient way to iterate over each field with a given tag.  
+
+    # A more convenient way to iterate over each field with a given tag.
     # The filter argument can be a string, array or range.
     def each_by_tag(filter)
-      @fields.each_by_tag(filter) {|tag| yield tag }
+      @fields.each_by_tag(filter) { |tag| yield tag }
     end
 
     # You can lookup fields using this shorthand:
     #   title = record['245']
 
     def [](tag)
-      return self.find {|f| f.tag == tag}
+      return self.find { |f| f.tag == tag }
     end
-    
+
     # Provides a backwards compatible means to access the FieldMap.
     # No argument returns the FieldMap array in entirety.  Providing
     # a string, array or range of tags will return an array of fields
@@ -163,9 +178,9 @@ module MARC
       unless filter
         # Since we're returning the FieldMap object, which the caller
         # may mutate, we precautionarily mark dirty -- unless it's frozen
-        # immutable. 
+        # immutable.
         @fields.clean = false unless @fields.frozen?
-        return @fields 
+        return @fields
       end
       @fields.reindex unless @fields.clean
       flds = []
@@ -180,18 +195,18 @@ module MARC
       end
       flds
     end
-    
+
     # Returns an array of all of the tags that appear in the record (not necessarily in the order they appear).
     def tags
       return @fields.tag_list
     end
 
-    # Factory method for creating a MARC::Record from MARC21 in 
+    # Factory method for creating a MARC::Record from MARC21 in
     # transmission format.
     #
     #   record = MARC::Record.new_from_marc(marc21)
     #
-    # in cases where you might be working with somewhat flawed 
+    # in cases where you might be working with somewhat flawed
     # MARC data you may want to use the :forgiving parameter which
     # will bypass using field byte offsets and simply look for the
     # end of field byte to figure out the end of fields.
@@ -203,12 +218,12 @@ module MARC
     end
 
 
-    # Returns a record in MARC21 transmission format (ANSI Z39.2). 
+    # Returns a record in MARC21 transmission format (ANSI Z39.2).
     # Really this is just a wrapper around MARC::MARC21::encode
     #
     #   marc = record.to_marc()
 
-    def to_marc 
+    def to_marc
       return MARC::Writer.encode(self)
     end
 
@@ -235,51 +250,51 @@ module MARC
     # Return a marc-hash version of the record
     def to_marchash
       return {
-        'type' => 'marc-hash',
-        'version' => [MARCHASH_MAJOR_VERSION, MARCHASH_MINOR_VERSION],
-        'leader' => self.leader,
-        'fields' => self.map {|f| f.to_marchash}
+          'type'    => 'marc-hash',
+          'version' => [MARCHASH_MAJOR_VERSION, MARCHASH_MINOR_VERSION],
+          'leader'  => self.leader,
+          'fields'  => self.map { |f| f.to_marchash }
       }
-    end #to_hash
+    end
+
+    #to_hash
 
     # Factory method for creating a new MARC::Record from
     # a marchash object
     #
     # record = MARC::Record->new_from_marchash(mh)
-    
+
     def self.new_from_marchash(mh)
-      r = self.new()
+      r        = self.new()
       r.leader = mh['leader']
       mh['fields'].each do |f|
-        if (f.length == 2) 
+        if (f.length == 2)
           r << MARC::ControlField.new(f[0], f[1])
-        elsif 
-          r << MARC::DataField.new(f[0], f[1], f[2], *f[3])
+        elsif r << MARC::DataField.new(f[0], f[1], f[2], *f[3])
         end
       end
       return r
     end
-    
 
-    
+
     # Returns a (roundtrippable) hash representation for MARC-in-JSON
     def to_hash
-      record_hash = {'leader'=>@leader, 'fields'=>[]}
+      record_hash = {'leader' => @leader, 'fields' => []}
       @fields.each do |field|
         record_hash['fields'] << field.to_hash
       end
       record_hash
-    end    
+    end
 
     def self.new_from_hash(h)
-      r = self.new
+      r        = self.new
       r.leader = h['leader']
       if h['fields']
         h['fields'].each do |position|
           position.each_pair do |tag, field|
             if field.is_a?(Hash)
               f = MARC::DataField.new(tag, field['ind1'], field['ind2'])
-              field['subfields'].each do | pos |
+              field['subfields'].each do |pos|
                 pos.each_pair do |code, value|
                   f.append MARC::Subfield.new(code, value)
                 end
@@ -290,9 +305,10 @@ module MARC
             end
           end
         end
-      end  
-      return r            
+      end
+      return r
     end
+
     # Returns a string version of the record, suitable for printing
 
     def to_s
@@ -315,7 +331,7 @@ module MARC
     #   if record =~ /Gravity's Rainbow/ then print "Slothrop" end
 
     def =~(regex)
-      return self.to_s =~ regex 
+      return self.to_s =~ regex
     end
 
   end

data/lib/marc/version.rb

@@ -1,3 +1,3 @@
 module MARC
-  VERSION = "1.0.0"
+  VERSION = "1.0.2"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: marc
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.2
 platform: ruby
 authors:
 - Kevin Clarke
@@ -13,54 +13,60 @@ authors:
 autorequire: marc
 bindir: bin
 cert_chain: []
-date: 2015-01-28 00:00:00.000000000 Z
+date: 2017-08-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
+  name: scrub_rb
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.0.1
-    - - <
+    - - "<"
       - !ruby/object:Gem::Version
         version: '2'
-  name: scrub_rb
-  prerelease: false
   type: :runtime
+  prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.0.1
-    - - <
+    - - "<"
       - !ruby/object:Gem::Version
         version: '2'
 - !ruby/object:Gem::Dependency
+  name: unf
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  name: unf
-  prerelease: false
   type: :runtime
+  prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description:
+description: 
 email: ehs@pobox.com
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- Changes
+- LICENSE
+- README.md
+- Rakefile
 - lib/marc.rb
 - lib/marc/constants.rb
 - lib/marc/controlfield.rb
 - lib/marc/datafield.rb
 - lib/marc/dublincore.rb
 - lib/marc/exception.rb
+- lib/marc/marc8/map_to_unicode.rb
+- lib/marc/marc8/to_unicode.rb
 - lib/marc/reader.rb
 - lib/marc/record.rb
 - lib/marc/subfield.rb
@@ -69,14 +75,16 @@ files:
 - lib/marc/xml_parsers.rb
 - lib/marc/xmlreader.rb
 - lib/marc/xmlwriter.rb
-- lib/marc/marc8/map_to_unicode.rb
-- lib/marc/marc8/to_unicode.rb
 - test/bad_eacc_encoding.marc8.marc
 - test/batch.dat
 - test/batch.xml
 - test/cp866_multirecord.marc
 - test/cp866_unimarc.marc
 - test/escaped_character_reference.marc8.marc
+- test/marc8/data/test_marc8.txt
+- test/marc8/data/test_utf8.txt
+- test/marc8/tc_marc8_mapping.rb
+- test/marc8/tc_to_unicode.rb
 - test/marc8_accented_chars.marc
 - test/marc_with_bad_utf8.utf8.marc
 - test/no-leading-zero.xml
@@ -102,38 +110,29 @@ files:
 - test/utf8.marc
 - test/utf8_multirecord.marc
 - test/utf8_with_bad_bytes.marc
-- test/marc8/tc_marc8_mapping.rb
-- test/marc8/tc_to_unicode.rb
-- test/marc8/data/test_marc8.txt
-- test/marc8/data/test_utf8.txt
-- Rakefile
-- README.md
-- Changes
-- LICENSE
 homepage: https://github.com/ruby-marc/ruby-marc/
 licenses:
 - MIT
 metadata: {}
-post_install_message:
+post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: 1.8.6
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project:
-rubygems_version: 2.1.9
-signing_key:
+rubyforge_project: 
+rubygems_version: 2.6.8
+signing_key: 
 specification_version: 4
 summary: A ruby library for working with Machine Readable Cataloging
 test_files:
 - test/ts_marc.rb
-has_rdoc: true