Add CSV Schema lexer (#1039)

This commit adds a lexer for CSV Schema.

lib/rouge/demos/csvs

@@ -0,0 +1,8 @@
+version 1.1
+@totalColumns 5
+@separator ','
+Transaction_Date: xDate
+Transaction_ID: notEmpty
+Originator_Name: notEmpty
+Originator_Address: any("yes","no")
+Originator_Country: notEmpty

lib/rouge/lexers/csvs.rb

@@ -0,0 +1,44 @@
+# -*- coding: utf-8 -*- #
+# frozen_string_literal: true
+
+module Rouge
+  module Lexers
+    class CSVS < RegexLexer
+      tag 'csvs'
+      title "csvs"
+      desc 'The CSV Schema Language (digital-preservation.github.io)'
+      filenames '*.csvs'
+
+      state :root do
+        rule %r/\s+/m, Text
+
+        rule %r(//[\S\t ]*), Comment::Single
+        rule %r(/\*[^*]*\*/)m, Comment::Multiline
+
+        rule %r/(version)( )(\d+\.\d+)/ do
+          groups Keyword, Text::Whitespace, Num::Float
+        end
+
+        rule %r/T?\d{2}:\d{2}:\d{2}(\.\d{5})?(Z|(?:[-+]\d{2}:\d{2}))?/, Literal::Date
+        rule %r/\d{4}-\d{2}-\d{2}/, Literal::Date
+        rule %r/\d{2}\/\d{2}\/\d{4}/, Literal::Date
+
+        rule %r((\d+[.]?\d*|\d*[.]\d+)(e[+-]?[0-9]+)?)i, Num::Float
+        rule %r/\d+/, Num::Integer
+
+        rule %r/@\w+/, Keyword::Pseudo
+
+        rule %r/[-.\w]+:/, Name::Variable
+        rule %r/^"[^"]+"/, Name::Variable
+        rule %r/\$([-.\w]+|("[^"]+"))\/?/, Name::Variable
+
+        rule %r/[A-Z]+/i, Keyword
+
+        rule %r/"[^"]*"/, Str::Double
+        rule %r/'[^\r\n\f']'/, Str::Char
+
+        rule %r/[,()*]/, Punctuation
+      end
+    end
+  end
+end

spec/lexers/csvs_spec.rb

@@ -0,0 +1,14 @@
+# -*- coding: utf-8 -*- #
+# frozen_string_literal: true
+
+describe Rouge::Lexers::CSVS do
+  let(:subject) { Rouge::Lexers::CSVS.new }
+
+  describe 'guessing' do
+    include Support::Guessing
+
+    it 'guesses by filename' do
+      assert_guess :filename => 'foo.csvs'
+    end
+  end
+end

spec/visual/samples/csvs

@@ -0,0 +1,32 @@
+version 1.2
+@totalColumns 3
+name: notEmpty
+age: range(0, 120)
+gender: is("m") or is("f") or is("t") or is("n")
+
+@separator TAB
+@quoted
+@totalColumns 21
+@permitEmpty
+@ignoreColumnNameCase
+
+//This Comment is a Single Line Comment it terminates at this line break
+a_column:
+
+/*This Comment is a Multi Line Comment:
+it can go on for as many lines as you like, until you type*/
+a_column:
+
+a_column: is("some string") and $b_column/starts("some string") //here two tests are combined on a single line, the second test here looks to the second column 
+b_column:                                                       //to check it's value starts with "some string"
+
+a_column: is("some string")    //the contents of a_column must be the string "some string"
+a_column: is($a_column)  //the contents of a_column must be the value held in a_column, treated as a string
+
+a_column: range(*, 10)
+
+a_column: xDateTime(2014-10-04T00:00:01Z,2015-12-03T23:59:59) //the value of a_column must be a valid xDateTime and between the two xDateTimes shown (inclusive)
+a_column: xDateTime(2014-10-04T00:00:01+02:00,2015-12-03T23:59:59+02:00) //the value of a_column must be a valid xDateTime and between the two xDateTimes shown (inclusive)
+a_column: xDateTime(2014-10-04,2015-12-03) //the value of a_column must be a valid xDate and between the two xDates shown (inclusive)
+a_column: xTime(00:00:01+02:00,2015-12-03T23:59:59+02:00) //the value of a_column must be a valid xTime and between the two xTimes shown (inclusive)
+a_column: ukDate(04/10/2014,03/12/2015) //the value of a_column must be a valid ukDate and between the two ukDates shown (inclusive)