gherkin 1.0.2 → 1.0.3

data/java/test/gherkin/formatter/ArgumentTest.java

@@ -0,0 +1,17 @@
+package gherkin.formatter;
+
+import org.junit.Test;
+
+import java.io.UnsupportedEncodingException;
+
+import static org.junit.Assert.assertEquals;
+
+public class ArgumentTest {
+    @Test
+    public void shouldFormatAscii() throws UnsupportedEncodingException {
+        assertEquals("I have [[[[åtte] cukes i [[[[bøtta]", Argument.format("I have åtte cukes i bøtta", new ArgumentFormat("[[[[", "]"),
+                new Argument(7, "åtte"),
+                new Argument(21, "bøtta")
+                ));
+    }
+}

data/lib/gherkin/csharp_lexer.rb

@@ -0,0 +1,15 @@
+require 'Gherkin.dll'
+
+module Gherkin
+  module CSharpLexer
+    def self.[](i18n_language)
+      i18n_lexer_class_name = i18n_language.gsub(/[\s-]/, '').capitalize
+      puts "In C# lexer: #{i18n_lexer_class_name}"
+      Gherkin::ILexer
+      puts "OK1"
+      l = Gherkin::Lexer.__send__(i18n_lexer_class_name)
+      puts "OK2"
+      l
+    end
+  end
+end

data/lib/gherkin/format/argument.rb

@@ -0,0 +1,35 @@
+module Gherkin
+  module Format
+    class Argument
+      attr_reader :byte_offset, :val
+
+      class << self
+        def new(byte_offset, val)
+          if defined?(JRUBY_VERSION)
+            require 'gherkin.jar'
+            Java::GherkinFormatter::Argument.new(byte_offset, val)
+          else
+            super
+          end
+        end
+      end
+
+      def initialize(byte_offset, val)
+        @byte_offset, @val = byte_offset, val
+      end
+      
+      def self.format(string, argument_format, arguments)
+        s = string.dup
+        offset = past_offset = 0
+        arguments.each do |arg|
+          next if arg.byte_offset.nil? || arg.byte_offset < past_offset
+          replacement = argument_format.format_argument(arg.val)
+          s[arg.byte_offset + offset, arg.val.length] = replacement
+          offset += replacement.unpack("U*").length - arg.val.unpack("U*").length
+          past_offset = arg.byte_offset + arg.val.length
+        end
+        s
+      end
+    end
+  end
+end

data/lib/gherkin/format/monochrome_format.rb

@@ -0,0 +1,9 @@
+module Gherkin
+  module Format
+    class MonochromeFormat
+      def format_argument(arg)
+        arg
+      end
+    end
+  end
+end

data/lib/gherkin/i18n.rb

@@ -18,6 +18,23 @@ module Gherkin
       def languages
         @languages ||= {}
       end
+
+      # Returns all keyword translations and aliases of +keywords+, escaped and joined with <tt>|</tt>.
+      # This method is convenient for editor support and syntax highlighting engines for Gherkin, where
+      # there is typically a code generation tool to generate regular expressions for recognising the
+      # various I18n translations of Gherkin's keywords.
+      #
+      # The +keywords+ arguments can be one of <tt>:feature</tt>, <tt>:background</tt>, <tt>:scenario</tt>, 
+      # <tt>:scenario_outline</tt>, <tt>:examples</tt>, <tt>:step</tt>.
+      def keyword_regexp(*keywords)
+        unique_keywords = all.map do |lang|
+          keywords.map do |keyword|
+            lang.__send__("#{keyword}_keywords".to_sym)
+          end
+        end
+        
+        unique_keywords.flatten.compact.sort.reverse.uniq.join('|').gsub(/\*/, '\*')
+      end
     end
 
     attr_reader :key
@@ -69,12 +86,17 @@ module Gherkin
       %w{given when then and but}.map{|key| keywords(key, true)}.flatten.uniq
     end
 
+    def gwt_keywords
+      %w{given when then}.map{|key| keywords(key, true)}.flatten.uniq
+    end
+
     def keywords(key, space=false)
       raise "No #{key} in #{@keywords.inspect}" if @keywords[key].nil?
       @keywords[key].split('|').map{|kw| space ? keyword_space(kw) : kw}
     end
 
     def adverbs
+      # TODO: looks very similar to #step_keywords. Lose this? Where is it used from?
       %w{given when then and but}.map{|keyword| @keywords[keyword].split('|').map{|w| w.gsub(/[\s<']/, '')}}.flatten
     end
 

data/lib/gherkin/i18n.yml

@@ -1,11 +1,16 @@
 # encoding: UTF-8
-# We use the codes here (prefer 2 letters when possible)
-# http://en.wikipedia.org/wiki/List_of_ISO_639-2_codes
+#
+# We use ISO 639-1 (language) and ISO 3166 alpha-2 (region - if appliccable):
+# http://en.wikipedia.org/wiki/List_of_ISO_639-1_codes
+# http://en.wikipedia.org/wiki/ISO_3166-1
 #
 # If you want several aliases for a keyword, just separate them
 # with a | character. Make sure there are no ambiguities in the
 # keywords.
 #
+# If you do *not* want a trailing space after a keyword, end it with a < character.
+# (See Chinese for examples).
+#
 "en":
   name: English
   native: English
@@ -20,10 +25,6 @@
   and: "*|And"
   but: "*|But"
 
-# Please help us keeping the languages below uptodate. The parsers for a language
-# that is missing a keyword will expect the English word until the missing word(s)
-# are added.
-#
 # Please keep the grammars in alphabetical order by name from here and down.
 
 "ar":
@@ -52,20 +53,20 @@
   then: "*|То"
   and: "*|И"
   but: "*|Но"
-"cat":
+"ca":
   name: Catalan
   native: català
   background: Rerefons|Antecedents
-  feature: Característica
+  feature: Característica|Funcionalitat
   scenario: Escenari
   scenario_outline: Esquema de l'escenari
   examples: Exemples
-  given: "*|Donat|Donada"
+  given: "*|Donat|Donada|Atès|Atesa"
   when: "*|Quan"
-  then: "*|Aleshores"
+  then: "*|Aleshores|Cal"
   and: "*|I"
   but: "*|Però"
-"cy":
+"cy-GB":
   name: Welsh
   native: Cymraeg
   background: Cefndir
@@ -112,7 +113,7 @@
   scenario: Szenario
   scenario_outline: Szenariogrundriss
   examples: Beispiele
-  given: "*|Gegeben sei"
+  given: "*|Angenommen|Gegeben sei"
   when: "*|Wenn"
   then: "*|Dann"
   and: "*|Und"
@@ -143,6 +144,19 @@
   then: "*|DEN"
   and: "*|AN"
   but: "*|BUT"
+"en-Scouse":
+  name: Scouse
+  native: Scouse
+  feature: Feature
+  background: "Dis is what went down"
+  scenario: "The thing of it is"
+  scenario_outline: "Wharrimean is"
+  examples: Examples
+  given: "*|Givun|Youse know when youse got"
+  when: "*|Wun|Youse know like when"
+  then: "*|Dun|Den youse gotta"
+  and: "*|An"
+  but: "*|Buh"
 "en-tx":
   name: Texan
   native: Texan
@@ -294,11 +308,11 @@
   scenario: 시나리오
   scenario_outline: 시나리오 개요
   examples: 예
-  given: "*|조건<"
-  when: "*|만일<"
+  given: "*|조건<|먼저<"
+  when: "*|만일<|만약<"
   then: "*|그러면<"
   and: "*|그리고<"
-  but: "*|하지만<"
+  but: "*|하지만<|단<"
 "lt":
   name: Lithuanian
   native: lietuvių kalba
@@ -390,7 +404,7 @@
   then: "*|Atunci"
   and: "*|Si"
   but: "*|Dar"
-"ro2":
+"ro-RO":
   name: Romanian (diacritical)
   native: română (diacritical)
   background: Condiţii
@@ -416,7 +430,7 @@
   then: "*|То"
   and: "*|И|К тому же"
   but: "*|Но|А"
-"se":
+"sv":
   name: Swedish
   native: Svenska
   feature: Egenskap
@@ -443,8 +457,8 @@
   and: "*|A"
   but: "*|Ale"
 "sr-Latn":
-  name: Serbian_latin
-  native: Srpski_latinica
+  name: Serbian (Latin)
+  native: Srpski (Latinica)
   feature: Funkcionalnost|Mogućnost|Mogucnost|Osobina
   background: Kontekst|Osnova|Pozadina
   scenario: Scenario|Primer
@@ -455,7 +469,7 @@
   then: "*|Onda"
   and: "*|I"
   but: "*|Ali"
-"sr":
+"sr-Cyrl":
   name: Serbian
   native: Српски
   feature: Функционалност|Могућност|Особина

data/lib/gherkin/i18n_lexer.rb

@@ -1,29 +1,73 @@
-require 'gherkin/lexer'
 require 'gherkin/i18n'
 
 module Gherkin
+  I18nLexerNotFound = Class.new(LoadError)
+  LexingError = Class.new(StandardError)
+
   # The main entry point to lexing Gherkin source.
   class I18nLexer
     LANGUAGE_PATTERN = /language\s*:\s*(.*)/ #:nodoc:
 
-    attr_reader :language
+    attr_reader :i18n_language
+
+    class << self
+      def new(parser, force_ruby)
+        if !force_ruby && defined?(JRUBY_VERSION)
+          require 'gherkin.jar'
+          Java::Gherkin::I18nLexer.new(parser)
+        else
+          super
+        end
+      end
+
+      def lexer_class(i18n_lang, force_ruby)
+        begin
+          if force_ruby
+            rb[i18n_lang]
+          else
+            begin
+              c[i18n_lang]
+            rescue NameError, LoadError => e
+              warn("WARNING: #{e.message}. Reverting to Ruby lexer.")
+              rb[i18n_lang]
+            end
+          end
+        rescue LoadError => e
+          raise I18nLexerNotFound, "No lexer was found for #{i18n_lang} (#{e.message}). Supported languages are listed in gherkin/i18n.yml."
+        end
+      end
+
+      def i18n_language(source)
+        line_one = source.split(/\n/)[0]
+        match = LANGUAGE_PATTERN.match(line_one)
+        I18n.get(match ? match[1] : 'en').key
+      end
+
+      def c
+        require 'gherkin/c_lexer'
+        CLexer
+      end
+
+      def csharp
+        require 'gherkin/csharp_lexer'
+        CSharpLexer
+      end
 
-    def initialize(parser)
+      def rb
+        require 'gherkin/rb_lexer'
+        RbLexer
+      end
+    end
+
+    def initialize(parser, force_ruby)
       @parser = parser
+      @force_ruby = force_ruby
     end
 
     def scan(source)
-      @language = lang(source) 
-      delegate = Lexer[@language.key].new(@parser)
+      @i18n_language = self.class.i18n_language(source) 
+      delegate = self.class.lexer_class(@i18n_language, @force_ruby).new(@parser)
       delegate.scan(source)
     end
-
-    private
-
-    def lang(source)
-      line_one = source.split(/\n/)[0]
-      match = LANGUAGE_PATTERN.match(line_one)
-      I18n.get(match ? match[1] : 'en')
-    end
   end
 end

data/lib/gherkin/lexer.rb

@@ -1,24 +1,15 @@
 module Gherkin
   module Lexer
-    I18nLexerNotFound = Class.new(LoadError)
-    LexingError = Class.new(StandardError)
 
     class << self
       def [](i18n_lang)
         begin
-          # Uncomment the line below (during development) to force use of Ruby lexer
-          # return rb[i18n_lang]
-
-          if defined?(JRUBY_VERSION)
-            java[i18n_lang]
-          else
-            begin
-              c[i18n_lang]
-            rescue NameError, LoadError => e
-              warn("WARNING: #{e.message}. Reverting to Ruby lexer.") unless defined?(@warned)
-              @warned = true
-              rb[i18n_lang]
-            end
+          begin
+            c[i18n_lang]
+          rescue NameError, LoadError => e
+            raise("WARNING: #{e.message}. Reverting to Ruby lexer.") unless defined?(@warned)
+            @warned = true
+            rb[i18n_lang]
           end
         rescue LoadError => e
           raise I18nLexerNotFound, "No lexer was found for #{i18n_lang} (#{e.message}). Supported languages are listed in gherkin/i18n.yml."
@@ -30,9 +21,9 @@ module Gherkin
         CLexer
       end
 
-      def java
-        require 'gherkin/java_lexer'
-        JavaLexer
+      def csharp
+        require 'gherkin/csharp_lexer'
+        CSharpLexer
       end
 
       def rb

data/lib/gherkin/parser.rb

@@ -6,13 +6,13 @@ module Gherkin
   end
 
   class Parser
-    def self.new(listener, raise_on_error=false, machine_names='root')
+    def self.new(listener, raise_on_error=false, machine_name='root')
       if defined?(JRUBY_VERSION)
         require 'gherkin.jar'
-        Java::Gherkin::Parser.new(listener, raise_on_error, machine_names)
+        Java::Gherkin::Parser.new(listener, raise_on_error, machine_name)
       else
         require 'gherkin/rb_parser'
-        Gherkin::RbParser.new(listener, raise_on_error, machine_names)
+        Gherkin::RbParser.new(listener, raise_on_error, machine_name)
       end
     end
   end

data/lib/gherkin/parser/meta.txt

@@ -1,4 +1,5 @@
- |         | feature | background | scenario | scenario_outline | examples | step  | table | py_string | comment | tag |
- | meta    | E       | E          | E        | E                | E        | E     | E     | E         | comment | tag |
- | comment | pop()   | pop()      | pop()    | pop()            | pop()    | pop() | pop() | pop()     | pop()   | tag |
- | tag     | pop()   | E          | pop()    | pop()            | pop()    | E     | E     | E         | E       | tag |
+ |         | feature | background | scenario | scenario_outline | examples | step  | row   | py_string | eof | comment | tag |
+ | meta    | E       | E          | E        | E                | E        | E     | E     | E         | eof | comment | tag |
+ | comment | pop()   | pop()      | pop()    | pop()            | pop()    | pop() | pop() | pop()     | eof | pop()   | tag |
+ | tag     | pop()   | E          | pop()    | pop()            | pop()    | E     | E     | E         | E   | E       | tag |
+ | eof     | E       | E          | E        | E                | E        | E     | E     | E         | E   | E       | E   |

data/lib/gherkin/parser/root.txt

@@ -1,9 +1,11 @@
- |                  | feature | background | scenario | scenario_outline | examples | step | table          | py_string | comment    | tag        |
- | root             | feature | E          | E        | E                | E        | E    | E              | E         | push(meta) | push(meta) |
- | feature          | E       | background | scenario | scenario_outline | E        | E    | E              | E         | push(meta) | push(meta) |
- | step             | E       | E          | scenario | scenario_outline | examples | step | step           | step      | push(meta) | push(meta) |
- | background       | E       | E          | scenario | scenario_outline | E        | step | E              | E         | push(meta) | push(meta) |
- | scenario         | E       | E          | scenario | scenario_outline | E        | step | E              | E         | push(meta) | push(meta) |
- | scenario_outline | E       | E          | E        | E                | E        | step | E              | E         | push(meta) | push(meta) |
- | examples         | E       | E          | E        | E                | E        | E    | examples_table | E         | push(meta) | push(meta) |
- | examples_table   | E       | E          | scenario | scenario_outline | examples | E    | E              | E         | push(meta) | push(meta) |
+ |                  | feature | background | scenario | scenario_outline | examples | step         | row            | py_string    | eof | comment    | tag        |
+ | root             | feature | E          | E        | E                | E        | E            | E              | E            | eof | push(meta) | push(meta) |
+ | feature          | E       | background | scenario | scenario_outline | E        | E            | E              | E            | eof | push(meta) | push(meta) |
+ | step             | E       | E          | scenario | scenario_outline | E        | step         | step           | step         | eof | push(meta) | push(meta) |
+ | outline_step     | E       | E          | scenario | scenario_outline | examples | outline_step | outline_step   | outline_step | eof | push(meta) | push(meta) |
+ | background       | E       | E          | scenario | scenario_outline | E        | step         | E              | E            | eof | push(meta) | push(meta) |
+ | scenario         | E       | E          | scenario | scenario_outline | E        | step         | E              | E            | eof | push(meta) | push(meta) |
+ | scenario_outline | E       | E          | E        | E                | E        | outline_step | E              | E            | eof | push(meta) | push(meta) |
+ | examples         | E       | E          | E        | E                | E        | E            | examples_table | E            | eof | push(meta) | push(meta) |
+ | examples_table   | E       | E          | scenario | scenario_outline | examples | E            | examples_table | E            | eof | push(meta) | push(meta) |
+ | eof              | E       | E          | E        | E                | E        | E            | E              | E            | E   | E          | E          |

data/lib/gherkin/parser/steps.txt

@@ -1,3 +1,4 @@
- |       | feature | background | scenario | scenario_outline | examples | step | table | py_string | comment | tag |
- | steps | E       | E          | E        | E                | E        | step | E     | E         | E       | E   |
- | step  | E       | E          | E        | E                | E        | step | steps | steps     | E       | E   |
+ |       | feature | background | scenario | scenario_outline | examples | step | row  | py_string | eof | comment | tag |
+ | steps | E       | E          | E        | E                | E        | step | E    | E         | eof | E       | E   |
+ | step  | E       | E          | E        | E                | E        | step | step | steps     | eof | E       | E   |
+ | eof   | E       | E          | E        | E                | E        | E    | E    | E         | E   | E       | E   |