csvrdf 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 576c7d46ab56d1923d4845164ac2aae4500c92f5
+  data.tar.gz: 894f4603e919bc2d2781a8041129271480cc64e2
+SHA512:
+  metadata.gz: 1cfedbc8923bff07d2e3401ea3a3fa7dd40e1cea0dccfa397ec0b3164678e3cd37909e0d50f95775765056a0a160b0fe1c843e8b8770449bc70c24ce8a54a8f8
+  data.tar.gz: 028f9eb5a89c0b8e7e072b31cafad6df6b10b1ab699a2ec8f36d21481876f0435108a8d2c30a88333e9c8f45cc923330e1fada4668fdd9cef7487669889ee596

data/bin/csvrdf

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+
+require 'json'
+require 'csv'
+require 'csvrdf'
+
+if ARGV.size != 2
+  puts 'Usage:'
+  puts 'ruby parser.rb schema.json file.csv > file.nt'
+  exit 1
+end
+
+translator = CSVRDF::Translator.new(0, JSON.parse(File.open(ARGV[0]).read))
+
+puts translator.run(CSV.new(File.open(ARGV[1])), :ntriples)

data/lib/csvrdf.rb

@@ -0,0 +1,69 @@
+require 'rdf'
+require 'rdf/ntriples'
+
+module CSVRDF
+  include RDF
+
+  class Translator
+    def initialize(iterator, schema)
+      @iterator = iterator
+      @schema   = schema
+      @prefix   = RDF::URI.new(@schema['prefix'])
+      @type     = RDF::URI.new(@schema['type'])
+      @schemata = []
+      @schema['schemata'].each do |column|
+        if column.nil?
+          @schemata << nil
+        else
+          predicate = RDF::URI.new(column[0])
+
+          if column.size == 1
+            column_parser = Proc.new do |subject, object|
+              [subject, predicate, RDF::Literal.new(object)]
+            end
+          end
+
+          if column.size > 1
+            case column[1]
+            when 'integer'
+              column_parser = Proc.new do |subject, object|
+                [subject, predicate, RDF::Literal.new(Integer(object))]
+              end
+            when 'date'
+              column_parser = Proc.new do |subject, object|
+                [
+                 subject,
+                 predicate,
+                 RDF::Literal.new(Date.strptime(object, column[2] || '%Y-%m-%d'))
+                ]
+              end
+            end
+          end
+          
+          @schemata << column_parser
+        end
+      end
+    end
+
+    def run(rows, format)
+      graph = RDF::Graph.new
+
+      rows.each do |row|
+        @iterator = @iterator.next
+
+        resource = @prefix.join(@iterator.to_s)
+        
+        graph << [resource, RDF.type, @type]
+
+        row.each_index do |i|
+          unless @schemata[i].nil? or row[i].nil?
+            graph << @schemata[i].call(resource, row[i].strip)
+          end
+        end
+      end
+
+      graph.dump(format)
+    end
+  end
+
+end

metadata

@@ -0,0 +1,46 @@
+--- !ruby/object:Gem::Specification
+name: csvrdf
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Daniel Hernandez
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-01-10 00:00:00.000000000 Z
+dependencies: []
+description: A simple translator of CSV files into RDF
+email: daniel@degu.cl
+executables:
+- csvrdf
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/csvrdf
+- lib/csvrdf.rb
+homepage: https://gitlab.com/danielhz/csv2rdf-ruby
+licenses:
+- CC0-1.0
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.5.1
+signing_key: 
+specification_version: 4
+summary: CSV to RDF
+test_files: []