gherkin 2.11.3-java → 2.11.4-java

data/History.md

@@ -1,3 +1,9 @@
+## [2.11.4](https://github.com/cucumber/gherkin/compare/v2.11.3...v2.11.4)
+
+* [Core] Support for file encodings different from UTF-8 in feature files. ([#158](https://github.com/cucumber/gherkin/issues/158) Aslak Hellesøy)
+* [Core] Added Persian/Farsi (Sam Naseri)
+* [JavaScript] Fix lexer instantiation. ([#197](https://github.com/cucumber/gherkin/pull/197) Julien Biezemans)
+
 ## [2.11.3](https://github.com/cucumber/gherkin/compare/v2.11.2...v2.11.3)
 
 * [.NET] Upgraded IKVM from 0.46.0.1 to 7.1.4532.2 - quite a version bump! (Aslak Hellesøy)

data/README.md

@@ -54,7 +54,7 @@ The jar file is in the central Maven repo.
     <dependency>
         <groupId>info.cukes</groupId>
         <artifactId>gherkin</artifactId>
-        <version>2.11.3</version>
+        <version>2.11.4</version>
     </dependency>
 
 You can get it manually from [Maven Central](http://search.maven.org/#browse%7C-2073395818)

data/gherkin.gemspec

@@ -15,7 +15,7 @@ Gem::Specification.new do |s|
   # When both are building OK, do a `bundle exec rake install` in both cucumber and gherkin projects, revert the changes in the first 2 steps 
   # and release both projects. Do this for both ruby 1.8.7, ruby 1.9.3 and jruby.
   #
-  s.version     = "2.11.3"
+  s.version     = "2.11.4"
   s.authors     = ["Mike Sassak", "Gregory Hnatiuk", "Aslak Hellesøy"]
   s.description = "A fast Gherkin lexer/parser based on the Ragel State Machine Compiler."
   s.summary     = "#{s.name}-#{s.version}"

data/lib/gherkin/i18n.json

@@ -237,6 +237,20 @@
 	  "and": "*|Ja",
 	  "but": "*|Kuid"
 	},
+    "fa": {
+        "name": "Persian",
+        "native": "فارسی",
+        "feature": "وِیژگی",
+        "background": "زمینه",
+        "scenario": "سناریو",
+        "scenario_outline": "الگوی سناریو",
+        "examples": "نمونه ها",
+        "given": "*|با فرض",
+        "when": "*|هنگامی",
+        "then": "*|آنگاه",
+        "and": "*|و",
+        "but": "*|اما"
+    },
 	"fi": {
 	  "name": "Finnish",
 	  "native": "suomi",

data/lib/gherkin/lexer/encoding.rb

@@ -0,0 +1,34 @@
+module Gherkin
+  module Lexer
+    class Encoding
+      native_impl('gherkin')
+
+      COMMENT_OR_EMPTY_LINE_PATTERN = /^\s*#|^\s*$/
+      ENCODING_PATTERN = /^\s*#\s*encoding\s*:\s*([0-9a-zA-Z\-]+)/i #:nodoc:
+
+      def read_file(path)
+        source = File.new(path).read
+        enc = encoding(source)
+        if(enc != 'UTF-8')
+          # Read it again with different encoding
+          source = File.new(path, "r:#{enc}:UTF-8").read
+        end
+        source
+      end
+
+    private
+
+      def encoding(source)
+        encoding = 'UTF-8'
+        source.each_line do |line|
+          break unless COMMENT_OR_EMPTY_LINE_PATTERN =~ line
+          if ENCODING_PATTERN =~ line
+            encoding = $1
+            break
+          end
+        end
+        encoding.upcase
+      end
+    end
+  end
+end

data/lib/gherkin/native/therubyracer.rb

@@ -5,6 +5,7 @@ class Class
     class << self
       def new(*args)
         js = {
+          # Add more mappings here if needed. The mappings are only used by test code.
           'Gherkin::Formatter::JSONFormatter' => 'js/lib/gherkin/formatter/json_formatter.js',
           'Gherkin::Lexer::En' => 'js/lib/gherkin/lexer/en.js'
         }[self.name]

data/ragel/lexer.java.rl.erb

@@ -39,7 +39,7 @@ public class <%= @i18n.underscored_iso_code.capitalize %> implements Lexer {
     }
 
     action store_docstring_content {
-      String con = unindent(startCol, substring(data, contentStart, nextKeywordStart-1).replaceFirst("(\\r?\\n)?([\\t ])*\\Z", "").replaceAll("\\\\\"\\\\\"\\\\\"", "\"\"\""));
+      String con = unindent(startCol, substring(data, contentStart, nextKeywordStart-1).replaceFirst("(\\r?\\n)?([\\t ])*\\Z", "").replace("\\\"\\\"\\\"", "\"\"\""));
       String conType = substring(data, docstringContentTypeStart, docstringContentTypeEnd).trim();
       listener.docString(conType, con, currentLine);
     }
@@ -127,9 +127,9 @@ public class <%= @i18n.underscored_iso_code.capitalize %> implements Lexer {
     action store_cell_content {
       String con = substring(data, contentStart, p).trim();
       currentRow.add(con
-        .replaceAll("\\\\\\|", "|")
-        .replaceAll("\\\\n", "\n")
-        .replaceAll("\\\\\\\\", "\\\\")
+        .replace("\\|", "|")
+        .replace("\\n", "\n")
+        .replace("\\\\", "\\")
       );
     }
 

data/ragel/lexer.js.rl.erb

@@ -215,7 +215,7 @@ if(typeof module !== 'undefined') {
 if (typeof define !== 'undefined') {
   if(define.amd) {
     define('gherkin/lexer/<%= @i18n.underscored_iso_code %>', [], function() {
-      return Lexer
+      return Lexer;
     });
   } else {
     define('gherkin/lexer/<%= @i18n.underscored_iso_code %>', function(require, exports, module) {

data/spec/gherkin/c_lexer_spec.rb

@@ -15,7 +15,7 @@ module Gherkin
       it_should_behave_like "a Gherkin lexer lexing tags"
       it_should_behave_like "a Gherkin lexer lexing doc_strings"
       it_should_behave_like "a Gherkin lexer lexing rows"
-      it_should_behave_like "parsing windows files"
+      it_should_behave_like "encoding"
     end
   end
 end

data/spec/gherkin/fixtures/iso-8859-1.feature

@@ -0,0 +1,6 @@
+# language: no
+# encoding: iSo-8859-1
+Egenskap: ISO-8859-1
+  Scenario: ���
+    N�r this is encoded as Latin-1
+    S� everything should parse

data/spec/gherkin/i18n_spec.rb

@@ -184,6 +184,7 @@ module Gherkin
       | eo        | Esperanto           | Esperanto         |
       | es        | Spanish             | español           |
       | et        | Estonian            | eesti keel        |
+      | fa        | Persian             | فارسی             |
       | fi        | Finnish             | suomi             |
       | fr        | French              | français          |
       | he        | Hebrew              | עברית             |

data/spec/gherkin/native_lexer_spec.rb

@@ -23,7 +23,7 @@ module Gherkin
       it_should_behave_like "a Gherkin lexer lexing tags"
       it_should_behave_like "a Gherkin lexer lexing doc_strings"
       it_should_behave_like "a Gherkin lexer lexing rows"
-      it_should_behave_like "parsing windows files" unless ENV['GHERKIN_JS_NATIVE']
+      it_should_behave_like "encoding" unless ENV['GHERKIN_JS_NATIVE']
     end
   end
 end

data/spec/gherkin/shared/encoding_group.rb

@@ -0,0 +1,36 @@
+#encoding: utf-8
+require 'spec_helper'
+
+module Gherkin
+  module Lexer
+    shared_examples_for "encoding" do
+      describe "with BOM" do
+        it "should work just fine" do
+          scan_file("with_bom.feature")
+          @listener.to_sexp.should == [
+            [:feature, "Feature", "Feature Text", "", 1],
+            [:scenario, "Scenario", "Reading a Scenario", "", 2],
+            [:step, "Given ", "there is a step", 3],
+            [:eof]
+          ]
+        end
+
+        describe "with ISO-8859-1 encoding" do
+          it "should work just fine" do
+            @lexer = Gherkin::Lexer::I18nLexer.new(@listener)
+            scan_file("iso-8859-1.feature")
+            @listener.to_sexp.should == [
+              [:comment, "# language: no", 1], 
+              [:comment, "# encoding: iSo-8859-1", 2],
+              [:feature, "Egenskap", "ISO-8859-1", "", 3],
+              [:scenario, "Scenario", "ÆØÅ", "", 4],
+              [:step, "Når ", "this is encoded as Latin-1", 5],
+              [:step, "Så ", "everything should parse", 6],
+              [:eof]
+            ]
+          end
+        end
+      end
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -12,11 +12,12 @@ require 'gherkin'
 require 'stringio'
 require 'gherkin/sexp_recorder'
 require 'gherkin/output_stream_string_io'
-require 'gherkin/shared/bom_group'
+require 'gherkin/shared/encoding_group'
 require 'gherkin/shared/lexer_group'
 require 'gherkin/shared/tags_group'
 require 'gherkin/shared/doc_string_group'
 require 'gherkin/shared/row_group'
+require 'gherkin/lexer/encoding'
 $:.unshift(File.dirname(__FILE__))
 
 module GherkinSpecHelper
@@ -25,7 +26,8 @@ module GherkinSpecHelper
   end
 
   def fixture(file)
-    File.new(File.dirname(__FILE__) + "/gherkin/fixtures/" + file).read
+    encoding = Gherkin::Lexer::Encoding.new
+    source = encoding.read_file(File.dirname(__FILE__) + "/gherkin/fixtures/" + file)
   end
 
   def rubify_hash(hash)

data/tasks/release.rake

@@ -1,6 +1,6 @@
 namespace :release do
   desc 'Upload all packages and tag git'
-  task :ALL => ['gems:sanity', 'ikvm:check', :mvn_deploy_jar, :mvn_deploy_site, :push_native_gems, :push_npm_package, 'ikvm:push', :release, 'api:doc', :post_release]
+  task :ALL => ['gems:sanity', 'ikvm:check', :mvn_deploy_jar, :push_native_gems, :push_npm_package, 'ikvm:push', :release, 'api:doc', :post_release]
 
   desc 'Push all gems to rubygems.org'
   task :push_native_gems do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: gherkin
 version: !ruby/object:Gem::Version
-  version: 2.11.3
+  version: 2.11.4
   prerelease: 
 platform: java
 authors:
@@ -11,7 +11,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-10-08 00:00:00.000000000 Z
+date: 2012-10-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: json
@@ -109,22 +109,6 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: 0.9.9
-- !ruby/object:Gem::Dependency
-  name: therubyracer
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: 0.10.2
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: 0.10.2
 - !ruby/object:Gem::Dependency
   name: yard
   requirement: !ruby/object:Gem::Requirement
@@ -248,6 +232,7 @@ files:
 - lib/gherkin/i18n.json
 - lib/gherkin/i18n.rb
 - lib/gherkin/json_parser.rb
+- lib/gherkin/lexer/encoding.rb
 - lib/gherkin/lexer/i18n_lexer.rb
 - lib/gherkin/listener/event.rb
 - lib/gherkin/listener/formatter_listener.rb
@@ -284,6 +269,7 @@ files:
 - spec/gherkin/fixtures/i18n_pt3.feature
 - spec/gherkin/fixtures/i18n_pt4.feature
 - spec/gherkin/fixtures/i18n_zh-CN.feature
+- spec/gherkin/fixtures/iso-8859-1.feature
 - spec/gherkin/fixtures/issue_145.feature
 - spec/gherkin/fixtures/scenario_outline_with_tags.feature
 - spec/gherkin/fixtures/scenario_without_steps.feature
@@ -307,8 +293,8 @@ files:
 - spec/gherkin/output_stream_string_io.rb
 - spec/gherkin/parser/parser_spec.rb
 - spec/gherkin/sexp_recorder.rb
-- spec/gherkin/shared/bom_group.rb
 - spec/gherkin/shared/doc_string_group.rb
+- spec/gherkin/shared/encoding_group.rb
 - spec/gherkin/shared/lexer_group.rb
 - spec/gherkin/shared/row_group.rb
 - spec/gherkin/shared/tags_group.rb
@@ -357,7 +343,7 @@ rubyforge_project:
 rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
-summary: gherkin-2.11.3
+summary: gherkin-2.11.4
 test_files:
 - features/escaped_pipes.feature
 - features/feature_parser.feature
@@ -391,6 +377,7 @@ test_files:
 - spec/gherkin/fixtures/i18n_pt3.feature
 - spec/gherkin/fixtures/i18n_pt4.feature
 - spec/gherkin/fixtures/i18n_zh-CN.feature
+- spec/gherkin/fixtures/iso-8859-1.feature
 - spec/gherkin/fixtures/issue_145.feature
 - spec/gherkin/fixtures/scenario_outline_with_tags.feature
 - spec/gherkin/fixtures/scenario_without_steps.feature
@@ -414,8 +401,8 @@ test_files:
 - spec/gherkin/output_stream_string_io.rb
 - spec/gherkin/parser/parser_spec.rb
 - spec/gherkin/sexp_recorder.rb
-- spec/gherkin/shared/bom_group.rb
 - spec/gherkin/shared/doc_string_group.rb
+- spec/gherkin/shared/encoding_group.rb
 - spec/gherkin/shared/lexer_group.rb
 - spec/gherkin/shared/row_group.rb
 - spec/gherkin/shared/tags_group.rb

data/spec/gherkin/shared/bom_group.rb

@@ -1,20 +0,0 @@
-#encoding: utf-8
-require 'spec_helper'
-
-module Gherkin
-  module Lexer
-    shared_examples_for "parsing windows files" do
-      describe "with BOM" do
-        it "should work just fine" do
-          scan_file("with_bom.feature")
-          @listener.to_sexp.should == [
-            [:feature, "Feature", "Feature Text", "", 1],
-            [:scenario, "Scenario", "Reading a Scenario", "", 2],
-            [:step, "Given ", "there is a step", 3],
-            [:eof]
-          ]
-        end
-      end
-    end
-  end
-end