Finish 1.0.0

.gitignore

@@ -5,3 +5,4 @@
 /coverage/
 Gemfile.lock
 /.byebug_history
+/spec/w3c-csvw/

.travis.yml

@@ -4,15 +4,15 @@ script: "bundle exec rspec spec"
 env:
   - CI=true
 rvm:
-  - 2.0
-  - 2.1
-  - 2.2.4
-  - 2.3.0
-  - jruby-9.0.4.0
-  - rbx-2
+  - 2.2.6
+  - 2.3.3
+  - 2.4.0
+  - jruby
+  - rbx
 cache: bundler
 sudo: false
 matrix:
   allow_failures:
-    - rvm: rbx-2
+    - rvm: rbx
+    - rvm: jruby
 

Gemfile

@@ -5,6 +5,7 @@ gem 'rdf',      github: "ruby-rdf/rdf",       branch: "develop"
 gem 'rdf-xsd',  github: "ruby-rdf/rdf-xsd",   branch: "develop"
 
 group :development do
+  gem 'linkeddata',         github: "ruby-rdf/linkeddata",          branch: "develop"
   gem 'ebnf',               github: "gkellogg/ebnf",                branch: "develop"
   gem 'json-ld',            github: "ruby-rdf/json-ld",             branch: "develop"
   gem 'rdf-aggregate-repo', github: "ruby-rdf/rdf-aggregate-repo",  branch: "develop"
@@ -14,11 +15,10 @@ group :development do
   gem 'rdf-vocab',          github: "ruby-rdf/rdf-vocab",           branch: "develop"
   gem 'sparql',             github: "ruby-rdf/sparql",              branch: "develop"
   gem 'sparql-client',      github: "ruby-rdf/sparql-client",       branch: "develop"
-  gem 'sxp',                github: "gkellogg/sxp-ruby",            branch: "develop"
+  gem 'sxp',                github: "dryruby/sxp.rb",               branch: "develop"
 end
 
 group :debug do
-  gem "wirble"
   gem "byebug",  platforms: :mri
 end
 

README.md

@@ -248,7 +248,7 @@ Full documentation available on [RubyDoc](http://rubydoc.info/gems/rdf-tabular/f
   * {RDF::Tabular::Reader}
 
 ## Dependencies
-* [Ruby](http://ruby-lang.org/) (>= 2.0)
+* [Ruby](http://ruby-lang.org/) (>= 2.2.2)
 * [RDF.rb](http://rubygems.org/gems/rdf) (>= 2.0)
 * [JSON](https://rubygems.org/gems/json) (>= 1.5)
 

VERSION

@@ -1 +1 @@
-0.4.0
+1.0.0

dependencyci.yml

@@ -0,0 +1,5 @@
+platform:
+  Rubygems:
+    rdf-isomorphic:
+      tests:
+        unmaintained: skip

examples/bpotw.csv

@@ -0,0 +1 @@
+Identifier,Name,Description,Latitude,Longitude,ZONE,URL

examples/bpotw.json

@@ -0,0 +1,53 @@
+{
+  "@context": ["http://www.w3.org/ns/csvw", {"@language": "en"}],
+  "url": "bpotw.csv",
+  "dc:title": "CSV distribution of bus-stops-2015-05-05 dataset",
+  "dcat:keyword": ["bus", "stop", "mobility"],
+  "dc:publisher": {
+    "schema:name": "Transport Agency of MyCity",
+    "schema:url": {"@id": "http://example.org"}
+  },
+  "dc:license": {"@id": "http://opendefinition.org/licenses/cc-by/"},
+  "dc:modified": {"@value": "2015-05-05", "@type": "xsd:date"},
+  "tableSchema": {
+    "columns": [{
+      "name": "stop_id",
+      "titles": ["Identifier"],
+      "dc:description": "An identifier for the bus stop.",
+      "datatype": "string",
+      "required": true
+    }, {
+      "name": "stop_name",
+      "titles": ["Name"],
+      "dc:description": "The name of the bus stop.",
+      "datatype": "string"
+    },  {
+      "name": "stop_desc",
+      "titles": ["Description"],
+      "dc:description": "A description for the bus stop.",
+      "datatype": "string"
+   }, {
+      "name": "stop_lat",
+      "titles": ["Latitude"],
+      "dc:description": "The latitude of the bus stop.",
+      "datatype": "number"
+    }, {
+      "name": "stop_long",
+      "titles": ["Longitude"],
+      "dc:description": "The longitude of the bus stop.",
+      "datatype": "number"
+    }, {
+      "name": "zone_id",
+      "titles": ["ZONE"],
+      "dc:description": "An identifier for the zone where the bus stop is located.",
+      "datatype": "string"
+    },
+    {
+      "name": "stop_url",
+      "titles": ["URL"],
+      "dc:description": "URL that identifies the bus stop.",
+      "datatype": "string"
+    }],
+    "primaryKey": "stop_id"
+  }
+}

examples/niklas.csv

@@ -0,0 +1,2 @@
+role
+"aut,li"

examples/niklas.json

@@ -0,0 +1,11 @@
+{
+  "@context": "http://www.w3.org/ns/csvw",
+  "url": "niklas.csv",
+  "tableSchema": {
+    "columns": [{
+      "name": "role",
+      "separator": ",",
+      "valueUrl": "http://id.loc.gov/vocabulary/relators/{/role*}"
+    }]
+  }
+}

lib/rdf/tabular/format.rb

@@ -24,10 +24,10 @@ module RDF::Tabular
   #
   # @see http://www.w3.org/TR/rdf-testcases/#ntriples
   class Format < RDF::Format
-    content_type     'text/csv',
+    content_type     'text/csv;q=0.4',
                      extensions: [:csv, :tsv],
                      alias: %w{
-                       text/tab-separated-values
+                       text/tab-separated-values;q=0.4
                        application/csvm+json
                      }
     content_encoding 'utf-8'

lib/rdf/tabular/metadata.rb

@@ -2171,33 +2171,13 @@ def value_matching_datatype(value, datatype, expanded_dt, language)
         decimalChar = format["decimalChar"] || '.'
         pattern = format["pattern"]
 
-        if !datatype.parse_uax35_number(pattern, value, groupChar || ",", decimalChar)
+        begin
+          value = datatype.parse_uax35_number(pattern, value, groupChar || ",", decimalChar)
+        rescue UAX35::ParseError
           value_errors << "#{value} does not match numeric pattern #{pattern ? pattern.inspect : 'default'}"
         end
 
-        # pattern facet failed
-        value_errors << "#{value} has repeating #{groupChar.inspect}" if groupChar && value.include?(groupChar*2)
-        value = value.gsub(groupChar || ',', '')
-        value = value.sub(decimalChar, '.')
-
-        # Extract percent or per-mille sign
-        percent = permille = false
-        case value
-        when /%/
-          value = value.sub('%', '')
-          percent = true
-        when /‰/
-          value = value.sub('‰', '')
-          permille = true
-        end
-
         lit = RDF::Literal(value, datatype: expanded_dt)
-        if percent || permille
-          o = lit.object
-          o = o / 100 if percent
-          o = o / 1000 if permille
-          lit = RDF::Literal(o, datatype: expanded_dt)
-        end
 
         if !lit.plain? && datatype.minimum && lit < datatype.minimum
           value_errors << "#{value} < minimum #{datatype.minimum}"
@@ -2238,10 +2218,11 @@ def value_matching_datatype(value, datatype, expanded_dt, language)
           end
         end
       when :date, :time, :dateTime, :dateTimeStamp, :datetime
-        if value = datatype.parse_uax35_date(format, value)
+        begin
+          value = datatype.parse_uax35_date(format, value)
           lit = RDF::Literal(value, datatype: expanded_dt)
-        else
-          value_errors << "#{original_value} does not match format #{format}"
+        rescue UAX35::ParseError
+          value_errors << "#{value} does not match format #{format}"
         end
       when :duration, :dayTimeDuration, :yearMonthDuration
         # SPEC CONFUSION: surely format also includes that for other duration types?