greeb 0.0.1 → 0.0.2

data/Gemfile.lock

@@ -0,0 +1,24 @@
+PATH
+  remote: .
+  specs:
+    greeb (0.0.2)
+      rspec (~> 2.4.0)
+
+GEM
+  remote: http://rubygems.org/
+  specs:
+    diff-lcs (1.1.2)
+    rspec (2.4.0)
+      rspec-core (~> 2.4.0)
+      rspec-expectations (~> 2.4.0)
+      rspec-mocks (~> 2.4.0)
+    rspec-core (2.4.0)
+    rspec-expectations (2.4.0)
+      diff-lcs (~> 1.1.2)
+    rspec-mocks (2.4.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  greeb!

data/Rakefile

@@ -2,3 +2,11 @@
 
 require 'bundler'
 Bundler::GemHelper.install_tasks
+
+require 'rspec/core/rake_task'
+desc 'Run all examples'
+RSpec::Core::RakeTask.new(:spec) do |t|
+  t.rspec_opts = %w[--color]
+end
+
+task :default => :spec

data/greeb.gemspec

@@ -1,7 +1,7 @@
 # encoding: utf-8
 
 $:.push File.expand_path('../lib', __FILE__)
-require 'greeb/version'
+require 'greeb'
 
 Gem::Specification.new do |s|
   s.name        = 'greeb'
@@ -11,11 +11,13 @@ Gem::Specification.new do |s|
   s.email       = [ 'dmitry@eveel.ru' ]
   s.homepage    = 'https://github.com/eveel/greeb'
   s.summary     = 'Greeb is a Graphematical Analyzer.'
-  s.description = 'Greeb is a Graphematical Analyzer, ' \
+  s.description = 'Greeb is awesome Graphematical Analyzer, ' \
                   'written in Ruby.'
 
   s.rubyforge_project = 'greeb'
 
+  s.add_dependency 'rspec', '~> 2.4.0'
+
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
   s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }

data/lib/enumerable.rb

@@ -1,7 +1,9 @@
 # encoding: utf-8
 
+# Enumerable module additions.
+#
 module Enumerable
-  def collect_with_index(i = -1)
+  def collect_with_index(i = -1) # :nodoc:
     collect { |e| yield(e, i += 1) }
   end
   alias map_with_index collect_with_index

data/lib/greeb.rb

@@ -1,144 +1,11 @@
 # encoding: utf-8
 
-require 'meta_array'
-require 'enumerable'
-
+# Greeb is awesome Graphematical Analyzer.
+#
 module Greeb
-  RU_LEX = /^[А-Яа-я]+$/u
-  EN_LEX = /^[A-Za-z]+$/u
-  EOL = /^\n+$/u
-  SEP = /^[*=_\/\\ ]$/u
-  PUN = /^(\.|\!|\?)$/u
-  SPUN = /^(\,|\[|\]|\(|\)|\-|:|;)$/u
-  DIG = /^[0-9]+$/u
-  DIL = /^[А-Яа-яA-Za-z0-9]+$/u
-  EMPTY = ''
-
-  class Parser
-    attr_accessor :origin
-    private :origin=
-
-    attr_writer :tree
-    private :tree=
-
-    def initialize(origin)
-      self.origin = origin
-    end
-
-    def tree
-      @tree ||= parse(origin)
-    end
-
-    private
-      def parse(origin) # :nodoc:
-        tree = MetaArray.new
-
-        # paragraph
-        p_id = 0
-
-        # sentence
-        s_id = 0
-
-        # subsentence
-        ss_id = 0
-
-        token = ''
+  # Version of the Greeb.
+  #
+  VERSION = "0.0.2"
 
-        origin.each_char do |c|
-          puts "[#{token.inspect}] ← #{c.inspect}"
-          case c
-            when EOL then begin
-              case token
-                when EMPTY then token << c
-                when EOL then begin
-                  token = ''
-                  p_id += 1
-                  s_id = 0
-                  ss_id = 0
-                end
-              else
-                tree[p_id][s_id][ss_id] << token
-                token = c
-              end
-            end
-            when SEP then begin
-              case token
-                when EMPTY
-              else
-                tree[p_id][s_id][ss_id] << token
-                while tree[p_id][s_id][ss_id].last == c
-                  tree[p_id][s_id][ss_id].pop
-                end
-                tree[p_id][s_id][ss_id] << c
-                token = ''
-              end
-            end
-            when PUN then begin
-              case token
-                when EMPTY
-              else
-                tree[p_id][s_id][ss_id] << token
-                tree[p_id][s_id][ss_id] << c
-                token = ''
-                s_id += 1
-                ss_id = 0
-              end
-            end
-            when SPUN then begin
-              case token
-                when EMPTY
-              else
-                tree[p_id][s_id][ss_id] << token
-                tree[p_id][s_id][ss_id] << c
-                token = ''
-                ss_id += 1
-              end
-            end
-            when RU_LEX then begin
-              case token
-                when EOL then begin
-                  tree[p_id][s_id][ss_id] << ' '
-                  token = c
-                end
-              else
-                token << c
-              end
-            end
-            when EN_LEX then begin
-              case token
-                when EOL then begin
-                  tree[p_id][s_id][ss_id] << ' '
-                  token = c
-                end
-              else
-                token << c
-              end
-            end
-            when DIG then begin
-              case token
-                when EOL then begin
-                  tree[p_id][s_id][ss_id] << ' '
-                  token = c
-                end
-              else
-                token << c
-              end
-            end
-            when DIL then begin
-              case token
-                when EOL then begin
-                  tree[p_id][s_id][ss_id] << token
-                  token = c
-                end
-              else
-                token << c
-              end
-            end
-          end
-        end
-        tree[p_id][s_id][ss_id] << token
-        tree.delete(nil)
-        tree.to_a
-      end
-  end
+  require 'greeb/parser'
 end

data/lib/greeb/parser.rb

@@ -0,0 +1,176 @@
+# encoding: utf-8
+
+require 'meta_array'
+require 'enumerable'
+
+# Graphematical Parser of the Greeb.
+# Use it with love.
+#
+class Greeb::Parser
+  # Russian lexeme (i.e.: "хуй").
+  #
+  RUSSIAN_LEXEME = /^[А-Яа-яЁё]+$/u
+
+  # English lexeme (i.e.: "foo").
+  #
+  ENGLISH_LEXEME = /^[A-Za-z]+$/u
+
+  # End of Line sequence (i.e.: "\n").
+  #
+  END_OF_LINE = /^\n+$/u
+
+  # In-subsentence seprator (i.e.: "*" or "\").
+  #
+  SEPARATOR = /^[*=_\/\\ ]$/u
+
+  # Punctuation character (i.e.: "." or "!").
+  #
+  PUNCTUATION = /^(\.|\!|\?)$/u
+
+  # In-sentence punctuation character (i.e.: "," or "-").
+  #
+  SENTENCE_PUNCTUATION = /^(\,|\[|\]|\(|\)|\-|:|;)$/u
+
+  # Digit (i.e.: "1337").
+  #
+  DIGIT = /^[0-9]+$/u
+
+  # Digit-Letter complex (i.e.: "0xDEADBEEF").
+  #
+  DIGIT_LETTER = /^[А-Яа-яA-Za-z0-9Ёё]+$/u
+
+  # Empty string (i.e.: "").
+  #
+  EMPTY = ''
+
+  attr_accessor :text
+  private :text=
+
+  # Create a new instance of Greeb::Parser.
+  #
+  # ==== Parameters
+  # text<String>:: Source text.
+  #
+  def initialize(text)
+    self.text = text
+  end
+
+  # Perform the text parsing.
+  #
+  # ==== Returns
+  # Array:: Tree of Graphematical Analysis of text.
+  #
+  def parse
+    return @tree if @tree
+
+    # parse tree
+    tree = MetaArray.new
+
+    # paragraph, sentence, subsentence
+    p_id, s_id, ss_id = 0, 0, 0
+
+    # current token
+    token = ''
+
+    # run FSM
+    text.each_char do |c|
+      case c
+        when END_OF_LINE then begin
+          case token
+            when EMPTY then token << c
+            when END_OF_LINE then begin
+              token = ''
+              p_id += 1
+              s_id = 0
+              ss_id = 0
+            end
+          else
+            tree[p_id][s_id][ss_id] << token
+            token = c
+          end
+        end
+        when SEPARATOR then begin
+          case token
+            when EMPTY
+          else
+            tree[p_id][s_id][ss_id] << token
+            while tree[p_id][s_id][ss_id].last == c
+              tree[p_id][s_id][ss_id].pop
+            end
+            tree[p_id][s_id][ss_id] << c
+            token = ''
+          end
+        end
+        when PUNCTUATION then begin
+          case token
+            when EMPTY
+          else
+            tree[p_id][s_id][ss_id] << token
+            tree[p_id][s_id][ss_id] << c
+            token = ''
+            s_id += 1
+            ss_id = 0
+          end
+        end
+        when SENTENCE_PUNCTUATION then begin
+          case token
+            when EMPTY
+          else
+            tree[p_id][s_id][ss_id] << token
+            tree[p_id][s_id][ss_id] << c
+            token = ''
+            ss_id += 1
+          end
+        end
+        when RUSSIAN_LEXEME then begin
+          case token
+            when END_OF_LINE then begin
+              tree[p_id][s_id][ss_id] << ' '
+              token = c
+            end
+          else
+            token << c
+          end
+        end
+        when ENGLISH_LEXEME then begin
+          case token
+            when END_OF_LINE then begin
+              tree[p_id][s_id][ss_id] << ' '
+              token = c
+            end
+          else
+            token << c
+          end
+        end
+        when DIGIT then begin
+          case token
+            when END_OF_LINE then begin
+              tree[p_id][s_id][ss_id] << ' '
+              token = c
+            end
+          else
+            token << c
+          end
+        end
+        when DIGIT_LETTER then begin
+          case token
+            when END_OF_LINE then begin
+              tree[p_id][s_id][ss_id] << token
+              token = c
+            end
+          else
+            token << c
+          end
+        end
+      end
+    end
+
+    unless token.empty?
+      tree[p_id][s_id][ss_id] << token
+    end
+
+    tree.delete(nil)
+
+    @tree = tree.to_a
+  end
+end

data/lib/meta_array.rb

@@ -1,5 +1,8 @@
 # encoding: utf-8
 
+# MetaArray is an Array, which creates subarrays
+# on non-existent elements.
+#
 class MetaArray < Array
   def [] id
     super(id) or begin

data/spec/parser_spec.rb

@@ -0,0 +1,63 @@
+# encoding: utf-8
+
+require File.expand_path('../spec_helper.rb', __FILE__)
+
+describe Greeb::Parser do
+  it 'should parse very simple strings' do
+    'буба сука дебил'.should be_parsed_as([
+      [
+        [ [ 'буба', ' ', 'сука', ' ', 'дебил' ] ]
+      ]
+    ])
+  end
+
+  it 'should parse one sentence with subsentences' do
+    'буба, сука, дебил'.should be_parsed_as([
+      [
+        [
+          [ 'буба', ',' ],
+          [ 'сука', ',' ],
+          [ 'дебил' ]
+        ]
+      ]
+    ])
+  end
+
+  it 'should parse two simple paragraphs' do
+    "буба сука дебил\n\nточно!".should be_parsed_as([
+      [
+        [ [ 'буба', ' ', 'сука', ' ', 'дебил' ] ]
+      ],
+      [
+        [ [ 'точно', '!' ] ]
+      ]
+    ])
+  end
+
+  it 'should parse two sentences in paragraph' do
+    "буба молодец? буба умница.".should be_parsed_as([
+      [
+        [ [ 'буба', ' ', 'молодец', '?' ] ],
+        [ [ 'буба', ' ', 'умница', '.' ] ]
+      ]
+    ])
+  end
+
+  it 'should parse sentences with floating point values' do
+    'буба не считает Пи равной 3.14'.should be_parsed_as([
+      [
+        [ [ 'буба', ' ', 'не', ' ', 'считает', ' ',
+            'Пи', ' ', 'равной', ' ', '3.14' ] ]
+      ]
+    ])
+  end
+
+  it 'should parse sentences with floating "dot" values' do
+    'буба не считает Пи равной 3,14'.should be_parsed_as([
+      [
+        [ [ 'буба', ' ', 'не', ' ', 'считает', ' ',
+            'Пи', ' ', 'равной', ' ', '3,14' ] ]
+      ]
+    ])
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,14 @@
+# encoding: utf-8
+
+require File.expand_path('../../lib/greeb', __FILE__)
+
+RSpec.configure do |c|
+  c.mock_with :rspec
+end
+
+RSpec::Matchers.define :be_parsed_as do |expected|
+  match do |actual|
+    tree = Greeb::Parser.new(actual).parse
+    tree == expected
+  end
+end

metadata

@@ -1,18 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: greeb
 version: !ruby/object:Gem::Version
-  version: 0.0.1
-  prerelease: !!null 
+  version: 0.0.2
+  prerelease: 
 platform: ruby
 authors:
 - Dmitry A. Ustalov
-autorequire: !!null 
+autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-02-06 00:00:00.000000000 +05:00
-default_executable: !!null 
-dependencies: []
-description: Greeb is a Graphematical Analyzer, written in Ruby.
+date: 2011-02-20 00:00:00.000000000 +05:00
+default_executable: 
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: &81165430 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 2.4.0
+  type: :runtime
+  prerelease: false
+  version_requirements: *81165430
+description: Greeb is awesome Graphematical Analyzer, written in Ruby.
 email:
 - dmitry@eveel.ru
 executables: []
@@ -21,18 +32,21 @@ extra_rdoc_files: []
 files:
 - .gitignore
 - Gemfile
+- Gemfile.lock
 - README
 - Rakefile
 - greeb-test.rb
 - greeb.gemspec
 - lib/enumerable.rb
 - lib/greeb.rb
-- lib/greeb/version.rb
+- lib/greeb/parser.rb
 - lib/meta_array.rb
+- spec/parser_spec.rb
+- spec/spec_helper.rb
 has_rdoc: true
 homepage: https://github.com/eveel/greeb
 licenses: []
-post_install_message: !!null 
+post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -50,8 +64,10 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: greeb
-rubygems_version: 1.5.0
-signing_key: !!null 
+rubygems_version: 1.5.2
+signing_key: 
 specification_version: 3
 summary: Greeb is a Graphematical Analyzer.
-test_files: []
+test_files:
+- spec/parser_spec.rb
+- spec/spec_helper.rb

data/lib/greeb/version.rb

@@ -1,5 +0,0 @@
-# encoding: utf-8
-
-module Greeb
-  VERSION = "0.0.1"
-end