gherkin3 3.0.0.alpha.1

data/lib/gherkin3/token.rb

@@ -0,0 +1,18 @@
+module Gherkin3
+  class Token < Struct.new(:line, :location)
+    attr_accessor :matched_type, :matched_text, :matched_keyword, :matched_indent,
+                  :matched_items, :matched_gherkin_dialect
+
+    def eof?
+      line.nil?
+    end
+
+    def detach
+      # TODO: detach line - is this needed?
+    end
+
+    def token_value
+      eof? ? "EOF" : line.get_line_text(-1)
+    end
+  end
+end

data/lib/gherkin3/token_formatter_builder.rb

@@ -0,0 +1,35 @@
+module Gherkin3
+  class TokenFormatterBuilder
+    def initialize
+      @tokens_text = ""
+    end
+
+    def build(token)
+      @tokens_text << "#{format_token(token)}\n"
+    end
+
+    def start_rule(rule_type)
+    end
+
+    def end_rule(rule_type)
+    end
+
+    def get_result
+      @tokens_text
+    end
+
+    private
+    def format_token(token)
+      return "EOF" if token.eof?
+
+      sprintf "(%s:%s)%s:%s/%s/%s",
+        token.location[:line],
+        token.location[:column],
+        token.matched_type,
+        token.matched_keyword,
+        token.matched_text,
+        Array(token.matched_items).map { |i| "#{i.column}:#{i.text}"}.join(',')
+    end
+
+  end
+end

data/lib/gherkin3/token_matcher.rb

@@ -0,0 +1,163 @@
+require_relative 'dialect'
+require_relative 'errors'
+
+module Gherkin3
+  class TokenMatcher
+    LANGUAGE_PATTERN = /^\s*#\s*language\s*:\s*([a-zA-Z\-_]+)\s*$/
+
+    def initialize(dialect_name = 'en')
+      change_dialect(dialect_name, nil)
+      @active_doc_string_separator = nil
+      @indent_to_remove = 0
+    end
+
+    def match_TagLine(token)
+      return false unless token.line.start_with?('@')
+
+      set_token_matched(token, :TagLine, nil, nil, nil, token.line.tags)
+      true
+    end
+
+    def match_FeatureLine(token)
+      match_title_line(token, :FeatureLine, @dialect.feature_keywords)
+    end
+
+    def match_ScenarioLine(token)
+      match_title_line(token, :ScenarioLine, @dialect.scenario_keywords)
+    end
+
+    def match_ScenarioOutlineLine(token)
+      match_title_line(token, :ScenarioOutlineLine, @dialect.scenario_outline_keywords)
+    end
+
+    def match_BackgroundLine(token)
+      match_title_line(token, :BackgroundLine, @dialect.background_keywords)
+    end
+
+    def match_ExamplesLine(token)
+      match_title_line(token, :ExamplesLine, @dialect.examples_keywords)
+    end
+
+    def match_TableRow(token)
+      return false unless token.line.start_with?('|')
+      # TODO: indent
+      set_token_matched(token, :TableRow, nil, nil, nil, token.line.table_cells)
+      true
+    end
+
+    def match_Empty(token)
+      return false unless token.line.empty?
+      set_token_matched(token, :Empty, nil, nil, 0)
+      true
+    end
+
+    def match_Comment(token)
+      return false unless token.line.start_with?('#')
+      text = token.line.get_line_text(0) #take the entire line, including leading space
+      set_token_matched(token, :Comment, text, nil, 0)
+      true
+    end
+
+    def match_Language(token)
+      return false unless token.line.trimmed_line_text =~ LANGUAGE_PATTERN
+
+      dialect_name = $1
+      set_token_matched(token, :Language, dialect_name)
+
+      change_dialect(dialect_name, token.location)
+
+      true
+    end
+
+    def match_DocStringSeparator(token)
+      if @active_doc_string_separator.nil?
+        # open
+        _match_DocStringSeparator(token, '"""', true) ||
+        _match_DocStringSeparator(token, '```', true)
+      else
+        # close
+        _match_DocStringSeparator(token, @active_doc_string_separator, false)
+      end
+    end
+
+    def _match_DocStringSeparator(token, separator, is_open)
+      return false unless token.line.start_with?(separator)
+
+      content_type = nil
+      if is_open
+        content_type = token.line.get_rest_trimmed(separator.length)
+        @active_doc_string_separator = separator
+        @indent_to_remove = token.line.indent
+      else
+        @active_doc_string_separator = nil
+        @indent_to_remove = 0
+      end
+
+      # TODO: Use the separator as keyword. That's needed for pretty printing.
+      set_token_matched(token, :DocStringSeparator, content_type)
+      true
+    end
+
+    def match_EOF(token)
+      return false unless token.eof?
+      set_token_matched(token, :EOF)
+      true
+    end
+
+    def match_Other(token)
+      text = token.line.get_line_text(@indent_to_remove) # take the entire line, except removing DocString indents
+      set_token_matched(token, :Other, unescape_docstring(text), nil, 0)
+      true
+    end
+
+    def match_StepLine(token)
+      keywords = @dialect.given_keywords +
+                 @dialect.when_keywords +
+                 @dialect.then_keywords +
+                 @dialect.and_keywords +
+                 @dialect.but_keywords
+
+      keyword = keywords.detect { |k| token.line.start_with?(k) }
+
+      return false unless keyword
+
+      title = token.line.get_rest_trimmed(keyword.length)
+      set_token_matched(token, :StepLine, title, keyword)
+      return true
+    end
+
+    private
+
+    def change_dialect(dialect_name, location)
+      dialect = Dialect.for(dialect_name)
+      raise NoSuchLanguageException.new(dialect_name, location) if dialect.nil?
+
+      @dialect_name = dialect_name
+      @dialect = dialect
+    end
+
+    def match_title_line(token, token_type, keywords)
+      keyword = keywords.detect { |k| token.line.start_with_title_keyword?(k) }
+
+      return false unless keyword
+
+      title = token.line.get_rest_trimmed(keyword.length + ':'.length)
+      set_token_matched(token, token_type, title, keyword)
+      true
+    end
+
+    def set_token_matched(token, matched_type, text=nil, keyword=nil, indent=nil, items=[])
+      token.matched_type = matched_type
+      token.matched_text = text && text.chomp
+      token.matched_keyword = keyword
+      token.matched_indent = indent || (token.line && token.line.indent) || 0
+      token.matched_items = items
+      token.location[:column] = token.matched_indent + 1
+      token.matched_gherkin_dialect = @dialect_name
+    end
+
+    def unescape_docstring(text)
+      text.gsub("\\\"\\\"\\\"", "\"\"\"")
+    end
+  end
+end

data/lib/gherkin3/token_scanner.rb

@@ -0,0 +1,33 @@
+require_relative 'token'
+require_relative 'gherkin_line'
+
+module Gherkin3
+  class TokenScanner
+
+    def initialize(source_or_path_or_io)
+      @line_number = 0
+      if String === source_or_path_or_io
+        if File.file?(source_or_path_or_io)
+          @io = File.open(source_or_path_or_io, 'r:BOM|UTF-8')
+        else
+          @io = StringIO.new(source_or_path_or_io)
+        end
+      else
+        @io = source_or_path_or_io
+      end
+    end
+
+    def read
+      location = {line: @line_number += 1}
+      if @io.nil? || line = @io.gets
+        gherkin_line = line ? GherkinLine.new(line, location[:line]) : nil
+        Token.new(gherkin_line, location)
+      else
+        @io.close unless @io.closed? # ARGF closes the last file after final gets
+        @io = nil
+        Token.new(nil, location)
+      end
+    end
+
+  end
+end

data/spec/capture_warnings.rb

@@ -0,0 +1,68 @@
+# With thanks to @myronmarston
+# https://github.com/vcr/vcr/blob/master/spec/capture_warnings.rb
+
+module CaptureWarnings
+  def report_warnings(&block)
+    current_dir = Dir.pwd
+    warnings, errors = capture_error(&block).partition { |line| line.include?('warning') }
+    project_warnings, other_warnings = warnings.uniq.partition { |line| line.include?(current_dir) }
+
+    if errors.any?
+      puts errors.join("\n")
+    end
+
+    if other_warnings.any?
+      puts "#{ other_warnings.count } non-gherkin3 warnings detected, set VIEW_OTHER_WARNINGS=true to see them."
+      print_warnings('other', other_warnings) if ENV['VIEW_OTHER_WARNINGS']
+    end
+
+    if project_warnings.any?
+      puts "#{ project_warnings.count } gherkin3 warnings detected"
+      print_warnings('gherkin3', project_warnings)
+      fail "Please remove all gherkin3 warnings."
+    end
+
+    ensure_system_exit_if_required
+  end
+
+  def capture_error(&block)
+    old_stderr = STDERR.clone
+    pipe_r, pipe_w = IO.pipe
+    pipe_r.sync    = true
+    error         = ""
+    reader = Thread.new do
+      begin
+        loop do
+          error << pipe_r.readpartial(1024)
+        end
+      rescue EOFError
+      end
+    end
+    STDERR.reopen(pipe_w)
+    block.call
+  ensure
+    capture_system_exit
+    STDERR.reopen(old_stderr)
+    pipe_w.close
+    reader.join
+    return error.split("\n")
+  end
+
+  def print_warnings(type, warnings)
+    puts
+    puts "-" * 30 + " #{type} warnings: " + "-" * 30
+    puts
+    puts warnings.join("\n")
+    puts
+    puts "-" * 75
+    puts
+  end
+
+  def ensure_system_exit_if_required
+    raise @system_exit if @system_exit
+  end
+
+  def capture_system_exit
+    @system_exit = $!
+  end
+end

data/spec/coverage.rb

@@ -0,0 +1,10 @@
+require 'simplecov'
+formatters = [ SimpleCov::Formatter::HTMLFormatter ]
+
+if ENV['TRAVIS']
+  require 'coveralls'
+  formatters << Coveralls::SimpleCov::Formatter
+end
+
+SimpleCov.formatter = SimpleCov::Formatter::MultiFormatter[*formatters]
+SimpleCov.start

data/spec/gherkin3/parser_spec.rb

@@ -0,0 +1,26 @@
+require 'gherkin3/parser'
+require 'gherkin3/token_scanner'
+require 'gherkin3/token_matcher'
+require 'gherkin3/ast_builder'
+require 'rspec'
+
+module Gherkin3
+  describe Parser do
+    it "parses a simple feature" do
+      parser = Parser.new
+      scanner = TokenScanner.new("Feature: test")
+      builder = AstBuilder.new
+      ast = parser.parse(scanner, builder, TokenMatcher.new)
+      expect(ast).to eq({
+        type: :Feature,
+        tags: [],
+        location: {line: 1, column: 1},
+        language: "en",
+        keyword: "Feature",
+        name: "test",
+        scenarioDefinitions: [],
+        comments: []
+      })
+    end
+  end
+end

metadata

@@ -0,0 +1,130 @@
+--- !ruby/object:Gem::Specification
+name: gherkin3
+version: !ruby/object:Gem::Version
+  version: 3.0.0.alpha.1
+platform: ruby
+authors:
+- Gáspár Nagy
+- Aslak Hellesøy
+- Steve Tooke
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-07-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.4'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.4'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.3'
+- !ruby/object:Gem::Dependency
+  name: coveralls
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.8'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.8'
+description: Gherkin parser
+email: cukes@googlegroups.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".travis.yml"
+- CONTRIBUTING.md
+- Gemfile
+- LICENSE
+- Makefile
+- README.md
+- Rakefile
+- bin/gherkin-generate-ast
+- bin/gherkin-generate-tokens
+- gherkin-ruby.razor
+- gherkin3.gemspec
+- lib/gherkin3/ast_builder.rb
+- lib/gherkin3/ast_node.rb
+- lib/gherkin3/dialect.rb
+- lib/gherkin3/errors.rb
+- lib/gherkin3/gherkin-languages.json
+- lib/gherkin3/gherkin_line.rb
+- lib/gherkin3/parser.rb
+- lib/gherkin3/token.rb
+- lib/gherkin3/token_formatter_builder.rb
+- lib/gherkin3/token_matcher.rb
+- lib/gherkin3/token_scanner.rb
+- spec/capture_warnings.rb
+- spec/coverage.rb
+- spec/gherkin3/parser_spec.rb
+homepage: https://github.com/cucumber/gherkin3
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options:
+- "--charset=UTF-8"
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 1.9.3
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">"
+    - !ruby/object:Gem::Version
+      version: 1.3.1
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.5
+signing_key: 
+specification_version: 4
+summary: gherkin-3.0.0.alpha.1
+test_files:
+- spec/capture_warnings.rb
+- spec/coverage.rb
+- spec/gherkin3/parser_spec.rb