rdf-tabular 0.4.0 → 3.1.0

data/spec/metadata_spec.rb

@@ -838,12 +838,6 @@ describe RDF::Tabular::Metadata do
         ":type Schema" => [{}, {type: :Schema}, RDF::Tabular::Schema],
         ":type Column" => [{}, {type: :Column}, RDF::Tabular::Column],
         ":type Dialect" => [{}, {type: :Dialect}, RDF::Tabular::Dialect],
-        "@type TableGroup" => [{}, {"@type" => "TableGroup"}, RDF::Tabular::TableGroup],
-        "@type Table" => [{"@type" => "Table"}, RDF::Tabular::Table],
-        "@type Template" => [{"@type" => "Template"}, RDF::Tabular::Transformation],
-        "@type Schema" => [{"@type" => "Schema"}, RDF::Tabular::Schema],
-        "@type Column" => [{"@type" => "Column"}, RDF::Tabular::Column],
-        "@type Dialect" => [{"@type" => "Dialect"}, RDF::Tabular::Dialect],
         "tables TableGroup" => [{"tables" => []}, RDF::Tabular::TableGroup],
         "dialect Table" => [{"dialect" => {}}, RDF::Tabular::Table],
         "tableSchema Table" => [{"tableSchema" => {}}, RDF::Tabular::Table],
@@ -874,7 +868,7 @@ describe RDF::Tabular::Metadata do
           options ||= {}
           options[:logger] = logger
           options[:context] ||= 'http://www.w3.org/ns/csvw'
-          expect(described_class.new(input, options)).to be_a(klass)
+          expect(described_class.new(input, **options)).to be_a(klass)
           expect(logger.to_s).not_to match(/ERROR|WARN/)
         end
       end
@@ -1136,7 +1130,7 @@ describe RDF::Tabular::Metadata do
           format: {"groupChar" => ";"},
           value: "123;;456.789",
           result: "123;;456.789",
-          errors: [/has repeating/]
+          errors: [/does not match numeric pattern/]
         },
         "decimal with explicit decimalChar" => {
           base: "decimal",
@@ -1184,19 +1178,19 @@ describe RDF::Tabular::Metadata do
         "invalid nonPositiveInteger" => {base: "nonPositiveInteger", value: "1", errors: ["1 is not a valid nonPositiveInteger"]},
         "valid nonNegativeInteger" => {base: "nonNegativeInteger", value: "0"},
         "invalid nonNegativeInteger" => {base: "nonNegativeInteger", value: "-1", errors: ["-1 is not a valid nonNegativeInteger"]},
-        "valid double" => {base: "double", value: "1234.456E789"},
+        "valid double" => {base: "double", value: "1234.456e789"},
         "invalid double" => {base: "double", value: "1z", errors: ["1z is not a valid double"]},
-        "NaN double" => {base: "double", value: "NaN"},
+        "NaN double" => {base: "double", value: "NaN", result: "NaN"},
         "INF double" => {base: "double", value: "INF"},
         "-INF double" => {base: "double", value: "-INF"},
-        "valid number" => {base: "number", value: "1234.456E789"},
+        "valid number" => {base: "number", value: "1234.456e789"},
         "invalid number" => {base: "number", value: "1z", errors: ["1z is not a valid number"]},
-        "NaN number" => {base: "number", value: "NaN"},
+        "NaN number" => {base: "number", value: "NaN", result: "NaN"},
         "INF number" => {base: "number", value: "INF"},
         "-INF number" => {base: "number", value: "-INF"},
-        "valid float" => {base: "float", value: "1234.456E7"},
+        "valid float" => {base: "float", value: "1234.456e7"},
         "invalid float" => {base: "float", value: "1z", errors: ["1z is not a valid float"]},
-        "NaN float" => {base: "float", value: "NaN"},
+        "NaN float" => {base: "float", value: "NaN", result: "NaN"},
         "INF float" => {base: "float", value: "INF"},
         "-INF float" => {base: "float", value: "-INF"},
 
@@ -1327,7 +1321,7 @@ describe RDF::Tabular::Metadata do
         "valid NMTOKEN" => {base: "NMTOKEN", value: "someThing", result: RDF::Literal("someThing", datatype: RDF::XSD.NMTOKEN)},
 
         # Aliases
-        "number is alias for double" => {base: "number", value: "1234.456E789", result: RDF::Literal("1234.456E789", datatype: RDF::XSD.double)},
+        "number is alias for double" => {base: "number", value: "1234.456e789", result: RDF::Literal("1234.456e789", datatype: RDF::XSD.double)},
         "binary is alias for base64Binary" => {base: "binary", value: "Tm93IGlzIHRoZSB0aW1lIGZvciBhbGwgZ29vZCBjb2RlcnMKdG8gbGVhcm4g", result: RDF::Literal("Tm93IGlzIHRoZSB0aW1lIGZvciBhbGwgZ29vZCBjb2RlcnMKdG8gbGVhcm4g", datatype: RDF::XSD.base64Binary)},
         "datetime is alias for dateTime" => {base: "dateTime", value: "15-3-2015 1502",  format: "d-M-yyyy HHmm", result: RDF::Literal("2015-03-15T15:02:00", datatype: RDF::XSD.dateTime)},
         "any is alias for anyAtomicType" => {base: "any", value: "some thing", result: RDF::Literal("some thing", datatype: RDF::XSD.anyAtomicType)},
@@ -1379,7 +1373,7 @@ describe RDF::Tabular::Metadata do
       context "Unsupported datatypes" do
         %w(anyType anySimpleType ENTITIES IDREFS NMTOKENS ENTITY ID IDREF NOTATAION foo).each do |base|
           it "detects #{base} as unsupported" do
-            md = RDF::Tabular::Table.new({
+            RDF::Tabular::Table.new({
              url: "http://example.com/table.csv",
               tableSchema: {
                 columns: [{

data/spec/suite_helper.rb

@@ -23,7 +23,7 @@ module RDF::Util
     #   HTTP Request headers.
     # @return [IO] File stream
     # @yield [IO] File stream
-    def self.open_file(filename_or_url, options = {}, &block)
+    def self.open_file(filename_or_url, **options, &block)
       case
       when filename_or_url.to_s =~ /^file:/
         path = filename_or_url.to_s[5..-1]
@@ -73,7 +73,7 @@ module RDF::Util
           end
         end
       else
-        original_open_file(filename_or_url, options) do |remote_document|
+        original_open_file(filename_or_url, **options) do |remote_document|
           # Add Link header, if necessary
           remote_document.headers[:link] = options[:httpLink] if options[:httpLink]
 

data/spec/suite_spec.rb

@@ -18,18 +18,17 @@ describe RDF::Tabular::Reader do
           m.entries.each do |t|
             next if t.approval =~ /Rejected/
             specify "#{t.id.split("/").last}: #{t.name} - #{t.comment}" do
-              pending "rdf#test158 should be isomorphic" if t.id.include?("rdf#test158")
+              pending "rdf#test283 literal normalization" if t.id.include?("rdf#test283")
               t.logger = RDF::Spec.logger
               t.logger.formatter = lambda {|severity, datetime, progname, msg| "#{severity}: #{msg}\n"}
               t.logger.info t.inspect
               t.logger.info "source:\n#{t.input}"
               begin
                 RDF::Tabular::Reader.open(t.action,
-                  t.reader_options.merge(
-                    base_uri: t.base,
-                    validate: t.validation?,
-                    logger:   t.logger,
-                  )
+                  base_uri: t.base,
+                  validate: t.validation?,
+                  logger:   t.logger,
+                  **t.reader_options
                 ) do |reader|
                   expect(reader).to be_a RDF::Reader
 

data/spec/uax35_spec.rb

@@ -0,0 +1,239 @@
+# encoding: UTF-8
+$:.unshift "."
+require 'spec_helper'
+
+describe RDF::Tabular::UAX35 do
+  subject {"".extend(RDF::Tabular::UAX35)}
+
+  describe "parse_uax35_date" do
+    {
+      # Dates
+      "valid date yyyy-MM-dd" => {value: "2015-03-22", pattern: "yyyy-MM-dd", result: "2015-03-22"},
+      "valid date yyyyMMdd"   => {value: "20150322", pattern: "yyyyMMdd", result: "2015-03-22"},
+      "valid date dd-MM-yyyy" => {value: "22-03-2015", pattern: "dd-MM-yyyy", result: "2015-03-22"},
+      "valid date d-M-yyyy"   => {value: "22-3-2015", pattern: "d-M-yyyy", result: "2015-03-22"},
+      "valid date d-M-yy"     => {value: "22-3-15", pattern: "d-M-yy", result: "2015-03-22"},
+      "valid date d-M-y"      => {value: "22-3-15", pattern: "d-M-y", result: "2015-03-22"},
+      "valid date MM-dd-yyyy" => {value: "03-22-2015", pattern: "MM-dd-yyyy", result: "2015-03-22"},
+      "valid date M-d-yyyy"   => {value: "3-22-2015", pattern: "M-d-yyyy", result: "2015-03-22"},
+      "valid date M-d-yy"     => {value: "3-22-70", pattern: "M-d-yy", result: "1970-03-22"},
+      "valid date M-d-y"      => {value: "3-22-70", pattern: "M-d-y", result: "1970-03-22"},
+      "valid date dd/MM/yyyy" => {value: "22/03/2015", pattern: "dd/MM/yyyy", result: "2015-03-22"},
+      "valid date d/M/yyyy"   => {value: "22/3/2015", pattern: "d/M/yyyy", result: "2015-03-22"},
+      "valid date d/M/yy"     => {value: "22/3/15", pattern: "d/M/yy", result: "2015-03-22"},
+      "valid date d/M/y"      => {value: "22/3/15", pattern: "d/M/y", result: "2015-03-22"},
+      "valid date MM/dd/yyyy" => {value: "03/22/2015", pattern: "MM/dd/yyyy", result: "2015-03-22"},
+      "valid date M/d/yyyy"   => {value: "3/22/2015", pattern: "M/d/yyyy", result: "2015-03-22"},
+      "valid date M/d/yy"     => {value: "3/22/15", pattern: "M/d/yy", result: "2015-03-22"},
+      "valid date M/d/y"      => {value: "3/22/15", pattern: "M/d/y", result: "2015-03-22"},
+      "valid date dd.MM.yyyy" => {value: "22.03.2015", pattern: "dd.MM.yyyy", result: "2015-03-22"},
+      "valid date d.M.yyyy"   => {value: "22.3.2015", pattern: "d.M.yyyy", result: "2015-03-22"},
+      "valid date d.M.yy"     => {value: "22.3.15", pattern: "d.M.yy", result: "2015-03-22"},
+      "valid date d.M.y"      => {value: "22.3.15", pattern: "d.M.y", result: "2015-03-22"},
+      "valid date MM.dd.yyyy" => {value: "03.22.2015", pattern: "MM.dd.yyyy", result: "2015-03-22"},
+      "valid date M.d.yyyy"   => {value: "3.22.2015", pattern: "M.d.yyyy", result: "2015-03-22"},
+      "valid date M.d.yy"     => {value: "3.22.15", pattern: "M.d.yy", result: "2015-03-22"},
+      "valid date M.d.y"      => {value: "3.22.15", pattern: "M.d.y", result: "2015-03-22"},
+
+      # Times
+      "valid time HH:mm:ss.S" => {value: "15:02:37.1", pattern: "HH:mm:ss.S", result: "15:02:37.1"},
+      "valid time HH:mm:ss"   => {value: "15:02:37", pattern: "HH:mm:ss", result: "15:02:37"},
+      "valid time HHmmss"     => {value: "150237", pattern: "HHmmss", result: "15:02:37"},
+      "valid time HH:mm"      => {value: "15:02", pattern: "HH:mm", result: "15:02:00"},
+      "valid time HHmm"       => {value: "1502", pattern: "HHmm", result: "15:02:00"},
+
+      # DateTimes
+      "valid dateTime yyyy-MM-ddTHH:mm:ss"  => {value: "2015-03-15T15:02:37", pattern: "yyyy-MM-ddTHH:mm:ss", result: "2015-03-15T15:02:37"},
+      "valid dateTime yyyy-MM-ddTHH:mm:ss.S"=> {value: "2015-03-15T15:02:37.1", pattern: "yyyy-MM-ddTHH:mm:ss.S", result: "2015-03-15T15:02:37.1"},
+      "valid dateTime yyyy-MM-dd HH:mm:ss"  => {value: "2015-03-15 15:02:37", pattern: "yyyy-MM-dd HH:mm:ss", result: "2015-03-15T15:02:37"},
+      "valid dateTime yyyyMMdd HHmmss"      => {value: "20150315 150237",   pattern: "yyyyMMdd HHmmss",   result: "2015-03-15T15:02:37"},
+      "valid dateTime dd-MM-yyyy HH:mm"     => {value: "15-03-2015 15:02", pattern: "dd-MM-yyyy HH:mm", result: "2015-03-15T15:02:00"},
+      "valid dateTime d-M-yyyy HHmm"        => {value: "15-3-2015 1502",  pattern: "d-M-yyyy HHmm",   result: "2015-03-15T15:02:00"},
+      "valid dateTime yyyy-MM-ddTHH:mm"     => {value: "2015-03-15T15:02",  pattern: "yyyy-MM-ddTHH:mm",   result: "2015-03-15T15:02:00"},
+      "valid dateTimeStamp d-M-yyyy HHmm X" => {value: "15-3-2015 1502 Z",  pattern: "d-M-yyyy HHmm X",   result: "2015-03-15T15:02:00Z"},
+      "valid datetime yyyy-MM-ddTHH:mm:ss"  => {value: "2015-03-15T15:02:37", pattern: "yyyy-MM-ddTHH:mm:ss", result: "2015-03-15T15:02:37"},
+      "valid datetime yyyy-MM-dd HH:mm:ss"  => {value: "2015-03-15 15:02:37", pattern: "yyyy-MM-dd HH:mm:ss", result: "2015-03-15T15:02:37"},
+      "valid datetime yyyyMMdd HHmmss"      => {value: "20150315 150237",   pattern: "yyyyMMdd HHmmss",   result: "2015-03-15T15:02:37"},
+      "valid datetime dd-MM-yyyy HH:mm"     => {value: "15-03-2015 15:02", pattern: "dd-MM-yyyy HH:mm", result: "2015-03-15T15:02:00"},
+      "valid datetime d-M-yyyy HHmm"        => {value: "15-3-2015 1502",  pattern: "d-M-yyyy HHmm",   result: "2015-03-15T15:02:00"},
+      "valid datetime yyyy-MM-ddTHH:mm"     => {value: "2015-03-15T15:02",  pattern: "yyyy-MM-ddTHH:mm",   result: "2015-03-15T15:02:00"},
+
+      # Timezones
+      "valid w/TZ yyyy-MM-ddX"              => {value: "2015-03-22Z", pattern: "yyyy-MM-ddX", result: "2015-03-22Z"},
+      "valid w/TZ HH:mm:ssX"                => {value: "15:02:37-05", pattern: "HH:mm:ssX", result: "15:02:37-05:00"},
+      "valid w/TZ yyyy-MM-dd HH:mm:ss X"    => {value: "2015-03-15 15:02:37 +0800", pattern: "yyyy-MM-dd HH:mm:ss X", result: "2015-03-15T15:02:37+08:00"},
+      "valid w/TZ HHmm XX"                  => {value: "1502 +0800", pattern: "HHmm XX", result: "15:02:00+08:00"},
+      "valid w/TZ yyyy-MM-dd HH:mm:ss XX"   => {value: "2015-03-15 15:02:37 -0800", pattern: "yyyy-MM-dd HH:mm:ss XX", result: "2015-03-15T15:02:37-08:00"},
+      "valid w/TZ HHmm XXX"                 => {value: "1502 +08:00", pattern: "HHmm XXX", result: "15:02:00+08:00"},
+      "valid w/TZ yyyy-MM-ddTHH:mm:ssXXX"   => {value: "2015-03-15T15:02:37-05:00", pattern: "yyyy-MM-ddTHH:mm:ssXXX", result: "2015-03-15T15:02:37-05:00"},
+      "invalid w/TZ HH:mm:ssX"              => {value: "15:02:37-05:00", pattern: "HH:mm:ssX", error: "15:02:37-05:00 does not match pattern HH:mm:ssX"},
+      "invalid w/TZ HH:mm:ssXX"             => {value: "15:02:37-05", pattern: "HH:mm:ssXX", error: "15:02:37-05 does not match pattern HH:mm:ssXX"},
+    }.each do |name, props|
+      context name do
+        let(:base) {props[:base]}
+        let(:pattern) {props[:pattern]}
+        let(:value) {props[:value]}
+        let(:result) {props.fetch(:result, value)}
+        if props[:error]
+          it "finds error" do
+            expect {subject.parse_uax35_date(pattern, value)}.to raise_error(RDF::Tabular::UAX35::ParseError, props[:error])
+          end
+        else
+          it "generates #{props[:result] || props[:value]}" do
+            expect(subject.parse_uax35_date(pattern, value)).to eql result
+          end
+        end
+      end
+    end
+  end
+
+  describe "parse_uax35_number" do
+    {
+      # Numbers
+      "default no constraints" => {valid: %w(4)},
+      "default matching pattern" => {pattern: "000", valid: %w(123)},
+      "default explicit groupChar" => {groupChar: ";", valid: {"123;456.789" => "123456.789"}},
+      "default repeated groupChar" => {groupChar: ";", invalid: %w(123;;456.789)},
+      "default explicit decimalChar" => {decimalChar: ";", valid: {"123456;789" => "123456.789"}},
+      "default percent" => {groupChar: ",", valid: {"123456.789%" => "1234.56789"}},
+      "default per-mille" => {groupChar: ",", valid: {"123456.789‰" => "123.456789"}},
+
+      "0"          => {pattern: "0", valid: %w(1 -1 12), invalid: %w(1.2)},
+      "00"         => {pattern: "00", valid: %w(12 123), invalid: %w(1 1,2)},
+      "#"          => {pattern: "#", valid: %w(1 12 123), invalid: %w(1.2)},
+      "##"         => {pattern: "##", valid: %w(1 12 123), invalid: %w(1.2)},
+      "#0"         => {pattern: "#0", valid: %w(1 12 123), invalid: %w(1.2)},
+      '0.0'        => {pattern: "0.0", valid: %w(1.1 -1.1 12.1), invalid: %w(1.12)},
+      '0.00'       => {pattern: '0.00', valid: %w(1.12 +1.12 12.12), invalid: %w(1.1 1.123)},
+      '0.#'        => {pattern: '0.#', valid: %w(1 1.1 12.1), invalid: %w(1.12)},
+      '-0'         => {pattern: '-0', valid: %w(-1 -10), invalid: %w(1 +1)},
+      '%000'       => {pattern: '%000', valid: {"%123" => "1.23", "%+123" => "+1.23", "%1234" => "12.34"}, invalid: %w(%12 123%)},
+      '‰000'       => {pattern: '‰000', valid: {"‰123" => "0.123", "‰+123" => "+0.123", "‰1234" => "1.234"}, invalid: %w(‰12 123‰)},
+      '000%'       => {pattern: '000%', valid: {"123%" => "1.23", "+123%" => "+1.23", "1234%" => "12.34"}, invalid: %w(12% %123)},
+      '000‰'       => {pattern: '000‰', valid: {"123‰" => "0.123", "+123‰" => "+0.123", "1234‰" => "1.234"}, invalid: %w(12‰ ‰123)},
+      '000.0%'     => {pattern: '000.0%', valid: {"123.4%" => "1.234", "+123.4%" => "+1.234"}, invalid: %w(123.4‰ 123.4 1.234% 12.34% 123.45%)},
+      
+      '###0.#####' => {pattern: '###0.#####', valid: %w(1 1.1 12345.12345), invalid: %w(1,234.1 1.123456)},
+      '###0.0000#' => {pattern: '###0.0000#', valid: %w(1.1234 1.12345 12345.12345), invalid: %w(1,234.1234 1.12)},
+      '00000.0000' => {pattern: '00000.0000', valid: %w(12345.1234), invalid: %w(1.2 1,234.123,4)},
+      
+      '#0.0#E#0'   => {pattern: '#0.0#E#0', valid: %w(1.2e3 12.34e56)},
+      '#0.0#E+#0'  => {pattern: '#0.0#E+#0', valid: %w(1.2e+3 12.34e+56), invalid: %w(1.2e3 12.34e56)},
+      '#0.0#E#0%'  => {pattern: '#0.0#E#0%', valid: {"1.2e3%" => "0.012e3", "12.34e56%" => "0.1234e56"}, invalid: %w(1.2e+3 12.34e+56 1.2e3 12.34e56)},
+      
+      # Grouping
+      '#,##,##0'   => {pattern: '#,##,##0', valid: {"1" => "1", "12" => "12", "123" => "123", "1,234" => "1234", "12,345" => "12345", "1,23,456" => "123456"}, invalid: %w(1,2 12,34)},
+      '#,##,#00'   => {pattern: '#,##,#00', valid: {"12" => "12", "123" => "123", "1,234" => "1234", "12,345" => "12345"}, invalid: %w(1)},
+      '#,##,000'   => {pattern: '#,##,000', valid: {"123" => "123", "1,234" => "1234", "12,345" => "12345"}, invalid: %w(1 12)},
+      '#,#0,000'   => {pattern: '#,#0,000', valid: {"1,234" => "1234", "12,345" => "12345"}, invalid: %w(1 12 123)},
+      '#,00,000'   => {pattern: '#,00,000', valid: {"12,345" => "12345"}, invalid: %w(1 12 123 1,234)},
+      '0,00,000'   => {pattern: '0,00,000'},
+      
+      '0.0##,###'  => {pattern: '0.0##,###'},
+      '0.00#,###'  => {pattern: '0.00#,###'},
+      '0.000,###'  => {pattern: '0.000,###'},
+      '0.000,0##'  => {pattern: '0.000,0##'},
+      '0.000,00#'  => {pattern: '0.000,00#'},
+      '0.000,000'  => {pattern: '0.000,000'},
+      
+      # Jeni's
+      '##0'        => {pattern: '##0', valid: %w(1 12 123 1234), invalid: %w(1,234 123.4)},
+      '#,#00'      => {pattern: '#,#00', valid: {"12" => "12", "123" => "123", "1,234" => "1234", "1,234,567" => "1234567"}, invalid: %w(1 1234 12,34 12,34,567)},
+      '#0.#'       => {pattern: '#0.#', valid: %w(1 1.2 1234.5), invalid: %w(12.34 1,234.5)},
+      '#0.0#,#'    => {pattern: '#0.0#,#', valid: {"12.3" => "12.3", "12.34" => "12.34", "12.34,5" => "12.345"}, invalid: %w(1 12.345 12.34,56,7 12.34,567)},
+    }.each do |name, props|
+      context name do
+        let(:pattern) {props[:pattern]}
+        let(:groupChar) {props.fetch(:groupChar, ',')}
+        let(:decimalChar) {props.fetch(:decimalChar, '.')}
+
+        describe "valid" do
+          case props[:valid]
+          when Hash
+            props[:valid].each do |value, result|
+              it "with #{props[:pattern].inspect} #{value.inspect} => #{result.inspect}" do
+                expect(subject.parse_uax35_number(pattern, value, groupChar, decimalChar)).to eql result
+              end
+            end
+          when Array
+            props[:valid].each do |value|
+              it "with #{props[:pattern].inspect} #{value.inspect} => #{value.inspect}" do
+                expect(subject.parse_uax35_number(pattern, value, groupChar, decimalChar)).to eql value
+              end
+            end
+          end
+        end
+        describe "invalid" do
+          Array(props[:invalid]).each do |value|
+            it "with #{props[:pattern].inspect} #{value.inspect} invalid" do
+              expect {subject.parse_uax35_number(pattern, value, groupChar, decimalChar)}.to raise_error RDF::Tabular::UAX35::ParseError
+            end
+          end
+        end
+
+        it "recognizes bad pattern #{pattern.inspect}" do
+          expect{subject.parse_uax35_number(pattern, "", groupChar, decimalChar)}.to raise_error(ArgumentError)
+        end if props[:exception]
+      end
+    end
+  end
+
+  describe "#build_number_re" do
+    {
+      '0'          => {valid: %w(1 -1 +1 12), invalid: %w(1.2), base: "integer", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,})(?<suffix>)$/},
+      '00'         => {valid: %w(12 123), invalid: %w(1 1,2), base: "integer", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{2,})(?<suffix>)$/},
+      '#'          => {valid: %w(1 12 123), invalid: %w(1.2), base: "integer", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{0,})(?<suffix>)$/},
+      '##'         => {re: /^(?<prefix>[+-]?)(?<numeric_part>\d{0,})(?<suffix>)$/},
+      '#0'         => {re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,})(?<suffix>)$/},
+
+      '0.0'         => {valid: %w(1.1 -1.1 12.1), invalid: %w(1.12), base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}\.\d{1})(?<suffix>)$/},
+      '0.00'        => {valid: %w(1.12 +1.12 12.12), invalid: %w(1.1 1.123), base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}\.\d{2})(?<suffix>)$/},
+      '0.#'         => {valid: %w(1 1.1 12.1), invalid: %w(1.12), base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}(?:\.\d{0,1})?)(?<suffix>)$/},
+      '-0'         => {valid: %w(-1 -10), invalid: %w(1 +1), base: "decimal", re: /^(?<prefix>\-)(?<numeric_part>\d{1,})(?<suffix>)$/},
+      '%000'       => {valid: %w(%123 %+123 %-123 %1234), invalid: %w(%12 123%), base: "decimal", re: /^(?<prefix>%[+-]?)(?<numeric_part>\d{3,})(?<suffix>)$/},
+      '‰000'       => {valid: %w(‰123 ‰+123 ‰-123 ‰1234), invalid: %w(‰12 123‰), base: "decimal", re: /^(?<prefix>‰[+-]?)(?<numeric_part>\d{3,})(?<suffix>)$/},
+      '000%'       => {valid: %w(123% +123% -123% 1234%), invalid: %w(12% %123), base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{3,})(?<suffix>%)$/},
+      '000‰'       => {valid: %w(123‰ +123‰ -123‰ 1234‰), invalid: %w(12‰ ‰123), base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{3,})(?<suffix>‰)$/},
+      '000.0%'     => {base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{3,}\.\d{1})(?<suffix>%)$/},
+
+      '###0.#####' => {valid: %w(1 1.1 12345.12345), invalid: %w(1,234.1 1.123456), base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}(?:\.\d{0,5})?)(?<suffix>)$/},
+      '###0.0000#' => {valid: %w(1.1234 1.12345 12345.12345), invalid: %w(1,234.1234 1.12), base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}\.\d{4,5})(?<suffix>)$/},
+      '00000.0000' => {valid: %w(12345.1234), invalid: %w(1.2 1,234.123,4), base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{5,}\.\d{4})(?<suffix>)$/},
+
+      '#0.0#E#0'   => {base: "double", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}\.\d{1,2}E[+-]?\d{1,2})(?<suffix>)$/},
+      '#0.0#E+#0'   => {base: "double", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}\.\d{1,2}E\+\d{1,2})(?<suffix>)$/},
+      '#0.0#E#0%'  => {base: "double", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}\.\d{1,2}E[+-]?\d{1,2})(?<suffix>%)$/},
+
+      # Grouping
+      '#,##,##0'   => {base: "integer", re: /^(?<prefix>[+-]?)(?<numeric_part>(?:(?:(?:\d{1,2},)?(?:\d{2},)*\d)?\d)?\d{1})(?<suffix>)$/},
+      '#,##,#00'   => {base: "integer", re: /^(?<prefix>[+-]?)(?<numeric_part>(?:(?:\d{1,2},)?(?:\d{2},)*\d)?\d{2})(?<suffix>)$/},
+      '#,##,000'   => {base: "integer", re: /^(?<prefix>[+-]?)(?<numeric_part>(?:\d{1,2},)?(?:\d{2},)*\d{3})(?<suffix>)$/},
+      '#,#0,000'   => {base: "integer", re: /^(?<prefix>[+-]?)(?<numeric_part>(?:(?:\d{1,2},)?(?:\d{2},)*\d)?\d{1},\d{3})(?<suffix>)$/},
+      '#,00,000'   => {base: "integer", re: /^(?<prefix>[+-]?)(?<numeric_part>(?:\d{1,2},)?(?:\d{2},)*\d{2},\d{3})(?<suffix>)$/},
+      '0,00,000'   => {base: "integer", re: /^(?<prefix>[+-]?)(?<numeric_part>(?:(?:\d{1,2},)?(?:\d{2},)*\d)?\d{1},\d{2},\d{3})(?<suffix>)$/},
+
+      '0.0##,###'  => {base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}\.\d{1}(?:\d(?:\d(?:,\d(?:\d(?:\d)?)?)?)?)?)(?<suffix>)$/},
+      '0.00#,###'  => {base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}\.\d{2}(?:\d(?:,\d(?:\d(?:\d)?)?)?)?)(?<suffix>)$/},
+      '0.000,###'  => {base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}\.\d{3}(?:,\d(?:\d(?:\d)?)?)?)(?<suffix>)$/},
+      '0.000,0##'  => {base: "decimal", re:/^(?<prefix>[+-]?)(?<numeric_part>\d{1,}\.\d{3},\d{1}(?:\d(?:\d)?)?)(?<suffix>)$/},
+      '0.000,00#'  => {base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}\.\d{3},\d{2}(?:\d)?)(?<suffix>)$/},
+      '0.000,000'  => {base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}\.\d{3},\d{3})(?<suffix>)$/},
+
+      # Jeni's
+      '##0'        => {valid: %w(1 12 123 1234), invalid: %w(1,234 123.4), base: "integer", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,})(?<suffix>)$/},
+      '#,#00'      => {valid: %w(12 123 1,234 1,234,567), invalid: %w(1 1234 12,34 12,34,567), base: "integer", re: /^(?<prefix>[+-]?)(?<numeric_part>(?:(?:\d{1,3},)?(?:\d{3},)*\d)?\d{2})(?<suffix>)$/},
+      '#0.#'       => {valid: %w(1 1.2 1234.5), invalid: %w(12.34 1,234.5), base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}(?:\.\d{0,1})?)(?<suffix>)$/},
+      '#0.0#,#'    => {valid: %w(12.3 12.34 12.34,5), invalid: %w(1 12.345 12.34,56,7 12.34,567), base: "decimal", re: /^(?<prefix>[+-]?)(?<numeric_part>\d{1,}\.\d{1}(?:\d(?:,\d)?)?)(?<suffix>)$/},
+    }.each do |pattern, props|
+      context pattern do
+        it "generates #{props[:re]} for #{pattern}" do
+          expect(subject.build_number_re(pattern, ",", ".")).to eql props[:re]
+        end if props[:re].is_a?(Regexp)
+
+        it "recognizes bad pattern #{pattern}" do
+          expect{subject.build_number_re(pattern, ",", ".")}.to raise_error(ArgumentError)
+        end if props[:re] == ArgumentError
+      end
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rdf-tabular
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 3.1.0
 platform: ruby
 authors:
 - Gregg Kellogg
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-04-10 00:00:00.000000000 Z
+date: 2019-12-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bcp47
@@ -36,56 +36,56 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
 - !ruby/object:Gem::Dependency
   name: rdf-vocab
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
 - !ruby/object:Gem::Dependency
   name: rdf-xsd
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
 - !ruby/object:Gem::Dependency
   name: json-ld
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
 - !ruby/object:Gem::Dependency
   name: addressable
   requirement: !ruby/object:Gem::Requirement
@@ -106,28 +106,28 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '1.8'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '1.8'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.4'
+        version: '3.7'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.4'
+        version: '3.7'
 - !ruby/object:Gem::Dependency
   name: rspec-its
   requirement: !ruby/object:Gem::Requirement
@@ -148,84 +148,84 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
 - !ruby/object:Gem::Dependency
   name: rdf-spec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
 - !ruby/object:Gem::Dependency
   name: rdf-turtle
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
 - !ruby/object:Gem::Dependency
   name: sparql
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.1'
 - !ruby/object:Gem::Dependency
   name: webmock
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.17'
+        version: '3.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.17'
+        version: '3.0'
 - !ruby/object:Gem::Dependency
   name: yard
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: 0.9.12
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: 0.9.12
 description: RDF::Tabular processes tabular data with metadata creating RDF or JSON
   output.
 email: public-rdf-ruby@w3.org
@@ -250,12 +250,68 @@ files:
 - lib/rdf/tabular.rb
 - lib/rdf/tabular/csvw.rb
 - lib/rdf/tabular/format.rb
-- lib/rdf/tabular/json.rb
 - lib/rdf/tabular/literal.rb
 - lib/rdf/tabular/metadata.rb
 - lib/rdf/tabular/reader.rb
 - lib/rdf/tabular/uax35.rb
 - lib/rdf/tabular/version.rb
+- spec/data/countries-minimal.json
+- spec/data/countries-minimal.ttl
+- spec/data/countries-standard.json
+- spec/data/countries-standard.ttl
+- spec/data/countries.csv
+- spec/data/countries.csv-minimal.json
+- spec/data/countries.csv-minimal.ttl
+- spec/data/countries.csv-standard.json
+- spec/data/countries.csv-standard.ttl
+- spec/data/countries.html
+- spec/data/countries.json
+- spec/data/countries_embed-minimal.json
+- spec/data/countries_embed-minimal.ttl
+- spec/data/countries_embed-standard.json
+- spec/data/countries_embed-standard.ttl
+- spec/data/countries_embed.html
+- spec/data/countries_html-minimal.json
+- spec/data/countries_html-minimal.ttl
+- spec/data/countries_html-standard.json
+- spec/data/countries_html-standard.ttl
+- spec/data/country-codes-and-names-minimal.json
+- spec/data/country-codes-and-names-minimal.ttl
+- spec/data/country-codes-and-names-standard.json
+- spec/data/country-codes-and-names-standard.ttl
+- spec/data/country-codes-and-names.csv
+- spec/data/country_slice.csv
+- spec/data/junior-roles.csv
+- spec/data/junior-roles.json
+- spec/data/roles-minimal.json
+- spec/data/roles-minimal.ttl
+- spec/data/roles-standard.json
+- spec/data/roles-standard.ttl
+- spec/data/roles.json
+- spec/data/senior-roles.csv
+- spec/data/senior-roles.json
+- spec/data/test232-metadata.json
+- spec/data/test232.csv
+- spec/data/tree-ops-atd.json
+- spec/data/tree-ops-ext-minimal.json
+- spec/data/tree-ops-ext-minimal.ttl
+- spec/data/tree-ops-ext-standard.json
+- spec/data/tree-ops-ext-standard.ttl
+- spec/data/tree-ops-ext.csv
+- spec/data/tree-ops-ext.json
+- spec/data/tree-ops-minimal.json
+- spec/data/tree-ops-minimal.ttl
+- spec/data/tree-ops-standard.json
+- spec/data/tree-ops-standard.ttl
+- spec/data/tree-ops-virtual-minimal.json
+- spec/data/tree-ops-virtual-minimal.ttl
+- spec/data/tree-ops-virtual-standard.json
+- spec/data/tree-ops-virtual-standard.ttl
+- spec/data/tree-ops-virtual.json
+- spec/data/tree-ops.csv
+- spec/data/tree-ops.csv-metadata.json
+- spec/data/tree-ops.html
+- spec/data/tree-ops.tsv
 - spec/format_spec.rb
 - spec/matchers.rb
 - spec/metadata_spec.rb
@@ -263,6 +319,7 @@ files:
 - spec/spec_helper.rb
 - spec/suite_helper.rb
 - spec/suite_spec.rb
+- spec/uax35_spec.rb
 homepage: http://github.com/ruby-rdf/rdf-tabular
 licenses:
 - Unlicense
@@ -275,24 +332,80 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.0'
+      version: 2.2.2
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.4.8
+rubygems_version: 3.0.6
 signing_key: 
 specification_version: 4
 summary: Tabular Data RDF Reader and JSON serializer.
 test_files:
-- spec/format_spec.rb
-- spec/matchers.rb
-- spec/metadata_spec.rb
-- spec/reader_spec.rb
 - spec/spec_helper.rb
-- spec/suite_helper.rb
+- spec/metadata_spec.rb
+- spec/matchers.rb
 - spec/suite_spec.rb
-has_rdoc: false
+- spec/suite_helper.rb
+- spec/reader_spec.rb
+- spec/format_spec.rb
+- spec/uax35_spec.rb
+- spec/data/roles.json
+- spec/data/countries.csv-minimal.ttl
+- spec/data/countries_embed-standard.json
+- spec/data/tree-ops-standard.json
+- spec/data/countries.csv
+- spec/data/countries_embed-minimal.json
+- spec/data/countries-standard.json
+- spec/data/countries_html-minimal.json
+- spec/data/countries.csv-minimal.json
+- spec/data/senior-roles.csv
+- spec/data/roles-standard.ttl
+- spec/data/countries_embed-standard.ttl
+- spec/data/senior-roles.json
+- spec/data/countries_html-minimal.ttl
+- spec/data/junior-roles.csv
+- spec/data/countries.csv-standard.ttl
+- spec/data/tree-ops-ext-standard.json
+- spec/data/countries_html-standard.ttl
+- spec/data/tree-ops-minimal.ttl
+- spec/data/junior-roles.json
+- spec/data/roles-minimal.json
+- spec/data/countries_html-standard.json
+- spec/data/country_slice.csv
+- spec/data/countries.csv-standard.json
+- spec/data/tree-ops-virtual-minimal.ttl
+- spec/data/countries.json
+- spec/data/tree-ops.tsv
+- spec/data/tree-ops-virtual.json
+- spec/data/countries-minimal.json
+- spec/data/tree-ops-atd.json
+- spec/data/tree-ops-ext-minimal.ttl
+- spec/data/tree-ops.csv
+- spec/data/tree-ops-standard.ttl
+- spec/data/tree-ops-virtual-standard.ttl
+- spec/data/countries-minimal.ttl
+- spec/data/tree-ops-virtual-standard.json
+- spec/data/countries.html
+- spec/data/tree-ops-ext-standard.ttl
+- spec/data/country-codes-and-names-minimal.json
+- spec/data/tree-ops.html
+- spec/data/test232.csv
+- spec/data/tree-ops-ext.json
+- spec/data/roles-minimal.ttl
+- spec/data/countries_embed.html
+- spec/data/country-codes-and-names-standard.json
+- spec/data/country-codes-and-names-minimal.ttl
+- spec/data/countries_embed-minimal.ttl
+- spec/data/roles-standard.json
+- spec/data/tree-ops-virtual-minimal.json
+- spec/data/tree-ops-minimal.json
+- spec/data/tree-ops.csv-metadata.json
+- spec/data/countries-standard.ttl
+- spec/data/tree-ops-ext-minimal.json
+- spec/data/country-codes-and-names-standard.ttl
+- spec/data/test232-metadata.json
+- spec/data/tree-ops-ext.csv
+- spec/data/country-codes-and-names.csv