marc2linkeddata 0.2.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 543898af0ce1ceaa309d3998c8cbfa2b12df00f9
-  data.tar.gz: 45fe5fb9d27c32c66b5d385154ea60ccb9368262
+  metadata.gz: 252172f95d3c381127868b0a31e1558b30adac49
+  data.tar.gz: da2c92881b250cafee8d106c49b2f4e86f7a2cbd
 SHA512:
-  metadata.gz: f0458ac1a99307bf1988628298c9eda642fa1015b37dd92abe6fc8ad09d7f4746a962bbdf90ef3948e30c433d686df84d2d628094202097b21e21177b56911b1
-  data.tar.gz: 06a32b1595aee813138e1705663e2d1fdb92e9d57d03692e5f4dd9e7582c363b014e462641f49100ac561e01b0e7ea1acc6a91e70c0a173dde25a2761de408ea
+  metadata.gz: b77b8490be83acc7fd4b09273fd0c152aca6c3d097394a3aa1ddafc9e96a917d496ef4eeb04fe2e52b7cc89db16da6d32e80da184ff3714b201873df03033d9c
+  data.tar.gz: d391003816a3a35f757ee27e8227c793f032834775671795fde4fb19c8e055ffca8fac65b27a197c021c81a048bbe16fcc58e0dabbc6507e9ce5382217808f93

data/README.md

@@ -55,6 +55,12 @@ Optional Dependencies
     - http://marmotta.apache.org
     - http://stardog.com
 
+MARC resources
+
+  - http://www.loc.gov/marc/
+  - http://wiki.code4lib.org/index.php/Working_with_MaRC
+  - http://openmetadata.lib.harvard.edu/bibdata
+
 Install
 
     gem install marc2linkeddata
@@ -81,6 +87,63 @@ Configure
     # data resources, such as OCLC works for authorities.
     marc2LD_config
 
+Console Exploration
+
+    # First set configuration parameters (see details above).
+    # Then enter the pry REPL console, which requires the
+    # gem and loads the configuration.
+    marc2LD_console
+    > loc = Marc2LinkedData::Loc.new 'http://id.loc.gov/authorities/names/n79044798'
+    > loc.id
+    => "n79044798"
+    > #
+    > # retrieve RDF from LOC
+    > loc.rdf
+    => #<RDF::Graph:0x3fe88de67494(default)>
+    > # the RDF is an in-memory graph
+    > loc.rdf.to_ttl
+    => snipped for brevity
+    > #
+    > # Various attributes derived from the RDF
+    > loc.label
+    => "Byrnes, Christopher I., 1949-"
+    > loc.deprecated?
+    => false
+    > loc.person?
+    => true
+    > loc.corporation?
+    => false
+    > loc.conference?
+    => false
+    > loc.geographic?
+    => false
+    > loc.name_title?
+    => false
+    > loc.uniform_title?
+    => false
+    > # Try to retrieve additional linked data resources:
+    > oclc_uri = loc.get_oclc_identity
+    => "http://www.worldcat.org/identities/lccn-n79044798/"
+    > oclc_auth = Marc2LinkedData::OclcIdentity.new oclc_uri
+    > sa_graph = oclc_auth.same_as
+    => #<RDF::Graph:0x3fce1a5ec0f4(default)>
+    > sa_graph.to_ttl
+    => snipped for brevity
+    > oclc_auth.creative_works
+    => [#<RDF::URI:0x3fce1bc0cc6c URI:http://worldcat.org/oclc/747413718>,
+     #<RDF::URI:0x3fce1bc2a668 URI:http://worldcat.org/oclc/004933024>,
+     snipped for brevity
+     #<RDF::URI:0x3fce1be21444 URI:http://worldcat.org/oclc/751661734>]
+    > #
+    > # Don't just read this, try it out!
+    > # There are similar classes for VIAF, ISNI and OCLC entities,
+    > # explore the code base for more details and figure out how
+    > # to use that VIAF IRI to construct a Viaf object, and
+    > # then use it to get more ISNI linked data 8-)
+    > viaf_uri = loc.get_viaf
+    => "http://viaf.org/viaf/108317368/"
+
+
 Scripting
 
     # First configure (see details above).
@@ -196,10 +259,10 @@ Example Output Files
 
 Ruby Library Use
 
-- authority files
+- iterating records in an authority file
 
         require 'marc2linkeddata'
-        marc_filename = 'stf_auth.01.mrc'
+        marc_filename = 'auth.mrc'
         marc_file = File.open(marc_filename,'r')
         until marc_file.eof?
           leader = ParseMarcAuthority::parse_leader(marc_file)

data/bin/marcTypeCount

@@ -0,0 +1,29 @@
+#!/usr/bin/env ruby
+
+require 'marc2linkeddata'
+CONFIG = Marc2LinkedData.configuration
+
+marc_files = []
+ARGV.each do |filename|
+  path = Pathname(filename)
+  marc_files.push(path) if path.exist?
+end
+if marc_files.empty?
+  script_name = File.basename(__FILE__)
+  # script_path = File.dirname(__FILE__)
+  # example_env_file = File.absolute_path(File.join(script_path,'..','.env_example'))
+  puts <<HELP
+#{script_name} marc_authority_file1.mrc [ marc_authority_file2.mrc .. marc_authority_fileN.mrc ]
+
+Output is a count of the record types in the marc file(s).
+
+HELP
+  exit!
+end
+
+marc_files.each do |path|
+  record_types = Marc2LinkedData::Utils.marc_type_count(path.to_s)
+  puts "MARC record types in: #{path}"
+  pp record_types
+end
+

data/lib/includes.rb

@@ -19,6 +19,7 @@ require 'pry'
 require 'pry-doc'
 
 require_relative 'marc2linkeddata/configuration'
+require_relative 'marc2linkeddata/utils'
 
 require_relative 'marc2linkeddata/resource'
 require_relative 'marc2linkeddata/isni'

data/lib/marc2linkeddata/utils.rb

@@ -0,0 +1,109 @@
+#!/usr/bin/env ruby
+
+
+
+module Marc2LinkedData
+
+  class Utils
+
+    def self.stack_trace(e, record=nil)
+      $stderr.write "\n"
+      $stderr.write "ERROR\n"
+      $stderr.write e.message
+      $stderr.write e.backtrace
+      $stderr.write "\n"
+      $stderr.write record.to_s
+      $stderr.write "\n"
+    end
+
+    # Count all the records in the MARC file, by
+    # parsing the record leader, see
+    # http://www.loc.gov/marc/bibliographic/bdleader.html
+    # http://www.loc.gov/marc/authority/adleader.html
+    def self.marc_type_count(marc_filename)
+      # 06 - Type of record
+      # a - Language material
+      # c - Notated music
+      # d - Manuscript notated music
+      # e - Cartographic material
+      # f - Manuscript cartographic material
+      # g - Projected medium
+      # i - Nonmusical sound recording
+      # z - Authority data
+      record_types = {
+          :a_language_material => 0,
+          :c_notated_music => 0,
+          :d_manuscript_notated_music => 0,
+          :e_cartographic_material => 0,
+          :f_manuscript_cartographic_material => 0,
+          :g_projected_medium => 0,
+          :i_nonmusical_sound_recording => 0,
+          :z_authority_data => 0
+      }
+      marc_file = File.open(marc_filename,'r')
+      until marc_file.eof?
+        begin
+          leader = Marc2LinkedData::Utils.parse_leader(marc_file)
+          marc_file.seek(leader[:length], IO::SEEK_CUR)
+          case leader[:type]
+            when 'a'
+              record_types[:a_language_material] += 1
+            when 'c'
+              record_types[:c_notated_music] += 1
+            when 'd'
+              record_types[:d_manuscript_notated_music] += 1
+            when 'e'
+              record_types[:e_cartographic_material] += 1
+            when 'f'
+              record_types[:f_manuscript_cartographic_material] += 1
+            when 'g'
+              record_types[:g_projected_medium] += 1
+            when 'i'
+              record_types[:i_nonmusical_sound_recording] += 1
+            when 'z'
+              record_types[:z_authority_data] += 1
+          end
+        rescue => e
+          Marc2LinkedData::Utils.stack_trace(e, leader)
+          binding.pry if CONFIG.debug
+        end
+      end
+      marc_file.close
+      record_types
+    end
+
+    def self.parse_leader(file_handle, leader_bytes=24)
+      # example:
+      #record.leader
+      #=> "00774cz  a2200253n  4500"
+      # 00-04: '00774' - record length
+      # 05:    'c' - corrected or revised
+      # 06:    'z' - always 'z' for authority records
+      # 09:    'a' - UCS/Unicode
+      # 12-16: '00253' - base address of data, Length of Leader and Directory
+      # 17:    'n' - Complete authority record
+      # leader_status_codes = {
+      #     'a' => 'Increase in encoding level',
+      #     'c' => 'Corrected or revised',
+      #     'd' => 'Deleted',
+      #     'n' => 'New',
+      #     'o' => 'Obsolete',
+      #     's' => 'Deleted; heading split into two or more headings',
+      #     'x' => 'Deleted; heading replaced by another heading'
+      # }
+      leader = file_handle.read(leader_bytes)
+      file_handle.seek(-1 * leader_bytes, IO::SEEK_CUR)
+      {
+          :length => leader[0..4].to_i,
+          :status => leader[5],  # leader_status_codes[ record.leader[5] ]
+          :type => leader[6],    # always 'z' for authority records
+          :encoding => leader[9],  # translate letter code into ruby encoding string
+          :data_address => leader[12..16].to_i,
+          :complete => leader[17].include?('n')
+      }
+    end
+
+  end
+
+end
+

data/marc2linkeddata.gemspec

@@ -4,7 +4,7 @@ $:.unshift lib unless $:.include?(lib)
 
 Gem::Specification.new do |s|
   s.name        = 'marc2linkeddata'
-  s.version     = '0.2.0'
+  s.version     = '0.2.1'
   s.licenses    = ['Apache-2.0']
 
   # mysql and bson_ext only install on MRI (c-ruby)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: marc2linkeddata
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors:
 - Darren Weber
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-02-18 00:00:00.000000000 Z
+date: 2015-02-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -273,6 +273,7 @@ executables:
 - marc2LD_config
 - marc2LD_console
 - marcAuthority2LD
+- marcTypeCount
 - run_test_data.sh
 extensions: []
 extra_rdoc_files: []
@@ -290,6 +291,7 @@ files:
 - bin/marc2LD_config
 - bin/marc2LD_console
 - bin/marcAuthority2LD
+- bin/marcTypeCount
 - bin/run_test_data.sh
 - lib/includes.rb
 - lib/marc2linkeddata.rb
@@ -310,6 +312,7 @@ files:
 - lib/marc2linkeddata/sparql_dbpedia.rb
 - lib/marc2linkeddata/sparql_local_loc.rb
 - lib/marc2linkeddata/sparql_pubmed.rb
+- lib/marc2linkeddata/utils.rb
 - lib/marc2linkeddata/viaf.rb
 - log/.gitignore
 - marc2linkeddata.gemspec