myasorubka 0.1.1 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: dd23e096eea3cce744fc37c905b46f6b8c051d65
-  data.tar.gz: 059064ded607b2b4c21cbefd7a06411e4c123625
+  metadata.gz: 8e16d63b366b3abc035827745c49a22cdf28159a
+  data.tar.gz: b551b32694f999c898d3c898210a9ea5439e22c9
 SHA512:
-  metadata.gz: 0fa734d01b8a3082b4cd62ef0025bd73395bce010828ebf923b4b8f597f278d5ea1b9df9642782e9db3115d62e8279a364bb3feba851e6b7f7a77d0c95c6d3c4
-  data.tar.gz: b6cbb0c92d8a08db9ddd2ef89c147ff9b167bed9b167ca4afa50f12d0717d853f297874c4e28eeae96e7482ca365dc911d7871beb84170cb58a61ee27fb0945d
+  metadata.gz: 343b769967295d8fd6f1860fcd9f2c1b37e9d8f05b1aee00a54c460a242fe79190c9c993691dfbd236540b71473e2e17b013730cd0db37ca25b66cbff71f2926
+  data.tar.gz: 913cdc0cd36ef38e6ffdc4740678f6872107d0cb49d79710a73f7955a6656f7453c28b1f48a488be35a523b59764779c1e461eba94d32a0574fe6eb4ad25d17a

data/.travis.yml

@@ -1,7 +1,7 @@
-branches:
-  only:
-    - master
+sudo: false
+language: ruby
+bundler_args: --without development
 rvm:
-  - 2.0.0
+  - ruby
+  - rbx
   - jruby-19mode
-  - rbx-19mode

data/Gemfile

@@ -1,3 +1,10 @@
+# encoding: utf-8
+
 source 'https://rubygems.org'
 
 gemspec
+
+group :test do
+  gem 'minitest', '~> 5.0'
+  gem 'rake'
+end

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2011-2013 Dmitry Ustalov
+Copyright (c) 2011-2015 Dmitry Ustalov
 
 MIT License
 

data/README.md

@@ -5,7 +5,17 @@ Myasorubka is a morphological data processor that supports
 [AOT](http://aot.ru) and [MULTEXT-East](http://nl.ijs.si/ME/)
 notations.
 
+[![Gem Version][badge_fury_badge]][badge_fury_link] [![Build Status][travis_ci_badge]][travis_ci_link] [![Dependency Status][gemnasium_badge]][gemnasium_link]
+
+[badge_fury_badge]: https://badge.fury.io/rb/myasorubka.svg
+[badge_fury_link]: https://badge.fury.io/rb/myasorubka
+[travis_ci_badge]: https://travis-ci.org/dustalov/myasorubka.svg
+[travis_ci_link]: https://travis-ci.org/dustalov/myasorubka
+[gemnasium_badge]: https://gemnasium.com/dustalov/myasorubka.svg
+[gemnasium_link]: https://gemnasium.com/dustalov/myasorubka
+
 ## MULTEXT-East morphosyntactic descriptors
+
 It is possible to process the MULTEXT-East morphosyntactic descriptors
 (MSDs) in a convenient way.
 
@@ -51,7 +61,8 @@ Also, the `Myasorubka::MSD` class allows to write MSDs.
 ```
 
 ## AOT dictionaries
-Myasorubka provides a simple parsers for lexicon in the [AOT](http://aot.ru)
+
+Myasorubka provides simple parsers for lexicon in the [AOT](http://aot.ru)
 format, both for gramtab and dictionary files.
 
 ```ruby
@@ -104,11 +115,8 @@ You can learn more about AOT lexicon from the
 4. Push to the branch (`git push origin my-new-feature`);
 5. Create new Pull Request.
 
-## Build Status [<img src="https://secure.travis-ci.org/ustalov/myasorubka.png"/>](http://travis-ci.org/ustalov/myasorubka)
-
-## Dependency Status [<img src="https://gemnasium.com/ustalov/myasorubka.png"/>](https://gemnasium.com/ustalov/myasorubka)
-
 ## Copyright
-Copyright (c) 2011-2013 [Dmitry Ustalov]. See LICENSE for details.
 
-[Dmitry Ustalov]: http://eveel.ru
+Copyright (c) 2011-2015 [Dmitry Ustalov]. See LICENSE for details.
+
+[Dmitry Ustalov]: https://ustalov.name/

data/Rakefile

@@ -1,5 +1,6 @@
 # encoding: utf-8
 
+require 'rubygems/package_task'
 require 'bundler/gem_tasks'
 
 require 'rake/testtask'

data/lib/myasorubka.rb

@@ -1,4 +1,5 @@
 # encoding: utf-8
 
 require 'myasorubka/version'
+require 'myasorubka/unicode'
 require 'myasorubka/msd'

data/lib/myasorubka/aot/tags.rb

@@ -133,7 +133,7 @@ class Myasorubka::AOT::Tags
   #
   def self.russian(pos_line, grammemes_line)
     grammemes = grammemes_line.split(',').map do |grammeme|
-      UnicodeUtils.downcase(grammeme)
+      Myasorubka::Unicode.downcase(grammeme)
     end
 
     msd = Myasorubka::MSD.new(Myasorubka::MSD::Russian)
@@ -148,7 +148,7 @@ class Myasorubka::AOT::Tags
       pos_line = 'АББР'
     end
 
-    case UnicodeUtils.upcase(pos_line)
+    case Myasorubka::Unicode.upcase(pos_line)
     when 'С' then begin
       msd[:pos] = :noun
       msd[:type] = if (grammemes & [ 'имя', 'фам', 'отч', 'жарг', 'арх', 'проф', 'опч' ]).empty?

data/lib/myasorubka/msd.rb

@@ -153,26 +153,23 @@ class Myasorubka::MSD
       raise InvalidDescriptor, "category is nil"
     end
 
+    attributes = category[:attrs]
     msd = [category[:code]]
 
-    attrs = category[:attrs]
-    grammemes.each do |attr_name, value|
+    grammemes.each do |attribute, value|
       next unless value
 
-      attr_index = attrs.index { |name, *values| name == attr_name }
-      unless attr_index
-        raise InvalidDescriptor, 'no such attribute "%s" of category "%s"' %
-          [attr_name, pos]
+      unless index = attributes.index { |name, _| name == attribute }
+        raise InvalidDescriptor, 'no such attribute "%s" of category "%s"' % [attribute, pos]
       end
 
-      attr_name, values = attrs[attr_index]
+      _, values = attributes[index]
 
-      unless attr_value = values[value]
-        raise InvalidDescriptor, 'no such attribute "%s" ' \
-          'for attribute "%s" of category "%s"' % [value, attr_name, pos]
+      unless attribute_value = values[value]
+        raise InvalidDescriptor, 'no such value "%s" for attribute "%s" of category "%s"' % [value, attribute, pos]
       end
 
-      msd[attr_index + 1] = attr_value
+      msd[index + 1] = attribute_value
     end
 
     msd.map { |e| e || EMPTY_DESCRIPTOR }.join
@@ -188,6 +185,31 @@ class Myasorubka::MSD
     false
   end
 
+  # Drop every attribute that does not appear in the category.
+  #
+  # @return [MSD] self.
+  #
+  def prune!
+    unless category = language::CATEGORIES[pos]
+      self.pos = nil
+      grammemes.clear
+      return self
+    end
+
+    attributes = category[:attrs]
+
+    grammemes.reject! do |attribute, value|
+      if index = attributes.index { |name, _| name == attribute }
+        _, values = attributes[index]
+        !values[value]
+      else
+        true
+      end
+    end
+
+    self
+  end
+
   protected
   # @private
   def parse! msd_line

data/lib/myasorubka/msd/english.rb

@@ -5,9 +5,6 @@
 #
 # http://nl.ijs.si/ME/V4/msd/html/msd-en.html
 #
-# This specification was translated into the Ruby language
-# by [Dmitry Ustalov](http://eveel.ru).
-#
 module Myasorubka::MSD::English
   # English Noun.
   #

data/lib/myasorubka/msd/russian.rb

@@ -11,9 +11,6 @@
 #
 # http://nl.ijs.si/ME/V4/msd/html/msd-ru.html
 #
-# This specification was translated into the Ruby language
-# by [Dmitry Ustalov](http://eveel.ru).
-#
 module Myasorubka::MSD::Russian
   # Russian Noun.
   #

data/lib/myasorubka/mystem.rb

@@ -0,0 +1,135 @@
+# https://tech.yandex.ru/mystem/
+module Myasorubka::Mystem extend self
+  require 'myasorubka/mystem/binary'
+
+  # https://tech.yandex.ru/mystem/doc/grammemes-values-docpage/
+  GRAMMEMES = {
+    'A'       => :adjective,
+    'ADV'     => :adverb,
+    'ADVPRO'  => :adv_pronoun,
+    'ANUM'    => :adj_numeral,
+    'APRO'    => :adj_pronoun,
+    'COM'     => :composite,
+    'CONJ'    => :conjunction,
+    'INTJ'    => :interjunction,
+    'NUM'     => :numeral,
+    'PART'    => :particle,
+    'PR'      => :preposition,
+    'S'       => :substantive,
+    'SPRO'    => :subst_pronoun,
+    'V'       => :verb,
+    'наст'    => :present,
+    'praes'   => :present,
+    'непрош'  => :notpast,
+    'inpraes' => :notpast,
+    'прош'    => :past,
+    'praet'   => :past,
+    'им'      => :nominative,
+    'nom'     => :nominative,
+    'род'     => :genitive,
+    'gen'     => :genitive,
+    'дат'     => :dative,
+    'dat'     => :dative,
+    'вин'     => :accusative,
+    'acc'     => :accusative,
+    'твор'    => :instrumental,
+    'ins'     => :instrumental,
+    'пр'      => :ablative,
+    'abl'     => :ablative,
+    'парт'    => :partitive,
+    'part'    => :partitive,
+    'местн'   => :locative,
+    'loc'     => :locative,
+    'зват'    => :vocative,
+    'voc'     => :vocative,
+    'ед'      => :singular,
+    'sg'      => :singular,
+    'мн'      => :plural,
+    'pl'      => :plural,
+    'деепр'   => :gerund,
+    'ger'     => :gerund,
+    'инф'     => :infinitive,
+    'inf'     => :infinitive,
+    'прич'    => :participle,
+    'partcp'  => :participle,
+    'изъяв'   => :indicative,
+    'indic'   => :indicative,
+    'пов'     => :imperative,
+    'imper'   => :imperative,
+    'кр'      => :short,
+    'brev'    => :short,
+    'полн'    => :full,
+    'plen'    => :full,
+    'притяж'  => :possessive,
+    'poss'    => :possessive,
+    'прев'    => :superlative,
+    'supr'    => :superlative,
+    'срав'    => :comparative,
+    'comp'    => :comparative,
+    '1-л'     => :person1,
+    '1p'      => :person1,
+    '2-л'     => :person2,
+    '2p'      => :person2,
+    '3-л'     => :person3,
+    '3p'      => :person3,
+    'муж'     => :masculine,
+    'm'       => :masculine,
+    'жен'     => :feminine,
+    'f'       => :feminine,
+    'сред'    => :neuter,
+    'n'       => :neuter,
+    'несов'   => :imperfect,
+    'ipf'     => :imperfect,
+    'сов'     => :perfect,
+    'pf'      => :perfect,
+    'действ'  => :active,
+    'act'     => :active,
+    'страд'   => :passive,
+    'pass'    => :passive,
+    'од'      => :animated,
+    'anim'    => :animated,
+    'неод'    => :inanimated,
+    'inan'    => :inanimated,
+    'пе'      => :transitive,
+    'tran'    => :transitive,
+    'нп'      => :intransitive,
+    'intr'    => :intransitive,
+    'вводн'   => :parenth,
+    'parenth' => :parenth,
+    'гео'     => :geo,
+    'geo'     => :geo,
+    'затр'    => :awkward,
+    'awkw'    => :awkward,
+    'имя'     => :first_name,
+    'persn'   => :first_name,
+    'искаж'   => :distort,
+    'dist'    => :distort,
+    'мж'      => :mas_fem,
+    'mf'      => :mas_fem,
+    'обсц'    => :obscene,
+    'obsc'    => :obscene,
+    'отч'     => :patronymic,
+    'patrn'   => :patronymic,
+    'прдк'    => :praedic,
+    'praed'   => :praedic,
+    'разг'    => :informal,
+    'inform'  => :informal,
+    'редк'    => :rare,
+    'rare'    => :rare,
+    'сокр'    => :abbreviation,
+    'abbr'    => :abbreviation,
+    'устар'   => :obsolete,
+    'obsol'   => :obsolete,
+    'фам'     => :surname,
+    'famn'    => :surname
+  }.freeze
+
+  # Convert an array with mystem character-based grammemes into an MSD.
+  #
+  def to_msd(grammemes)
+    grammemes = grammemes.map { |g| GRAMMEMES[g] }
+    grammemes.compact!
+    grammemes.map! { |g| Myasorubka::Mystem::Binary::GRAMMEMES.key(g) }
+    Myasorubka::Mystem::Binary.to_msd(grammemes)
+  end
+end

data/lib/myasorubka/mystem/binary.rb

@@ -0,0 +1,187 @@
+# A wrapper around mystem's internal binary format.
+#
+module Myasorubka::Mystem::Binary extend self
+  # https://github.com/yandex/tomita-parser/blob/master/src/library/lemmer/dictlib/yx_gram_enum.h
+  GRAMMEMES = {
+    127 => :postposition,
+    128 => :adjective,
+    129 => :adverb,
+    130 => :composite,
+    131 => :conjunction,
+    132 => :interjunction,
+    133 => :numeral,
+    134 => :particle,
+    135 => :preposition,
+    136 => :substantive,
+    137 => :verb,
+    138 => :adj_numeral,
+    139 => :adj_pronoun,
+    140 => :adv_pronoun,
+    141 => :subst_pronoun,
+    142 => :article,
+    143 => :part_of_idiom,
+    144 => :reserved,
+    145 => :abbreviation,
+    146 => :irregular_stem,
+    147 => :informal,
+    148 => :distort,
+    149 => :contracted,
+    150 => :obscene,
+    151 => :rare,
+    152 => :awkward,
+    153 => :obsolete,
+    154 => :subst_adjective,
+    155 => :first_name,
+    156 => :surname,
+    157 => :patronymic,
+    158 => :geo,
+    159 => :proper,
+    160 => :present,
+    161 => :notpast,
+    162 => :past,
+    163 => :future,
+    164 => :past2,
+    165 => :nominative,
+    166 => :genitive,
+    167 => :dative,
+    168 => :accusative,
+    169 => :instrumental,
+    170 => :ablative,
+    171 => :partitive,
+    172 => :locative,
+    173 => :vocative,
+    174 => :singular,
+    175 => :plural,
+    176 => :gerund,
+    177 => :infinitive,
+    178 => :participle,
+    179 => :indicative,
+    180 => :imperative,
+    181 => :conditional,
+    182 => :subjunctive,
+    183 => :short,
+    184 => :full,
+    185 => :superlative,
+    186 => :comparative,
+    187 => :possessive,
+    188 => :person1,
+    189 => :person2,
+    190 => :person3,
+    191 => :feminine,
+    192 => :masculine,
+    193 => :neuter,
+    194 => :mas_fem,
+    195 => :perfect,
+    196 => :imperfect,
+    197 => :passive,
+    198 => :active,
+    199 => :reflexive,
+    200 => :impersonal,
+    201 => :animated,
+    202 => :inanimated,
+    203 => :praedic,
+    204 => :parenth,
+    205 => :transitive,
+    206 => :intransitive,
+    207 => :definite,
+    208 => :indefinite,
+    209 => :sim_conj,
+    210 => :sub_conj,
+    211 => :pronoun_conj,
+    212 => :correlate_conj,
+    213 => :aux_verb
+  }.freeze
+
+  # Convert an array with mystem grammeme codes into a MSD.
+  #
+  def to_msd(grammemes)
+    msd = Myasorubka::MSD.new(Myasorubka::MSD::Russian)
+
+    grammemes.sort.each do |code|
+      case GRAMMEMES[code]
+      # Nomenus
+      when :postposition then msd[:pos] = :adposition
+      when :adjective then msd[:pos] = :adjective; msd[:type] = :qualificative; msd[:degree] = :positive
+      when :adverb then msd[:pos] = :adverb
+      when :conjunction then msd[:pos] = :conjunction
+      when :interjunction then msd[:pos] = :interjection
+      when :numeral then msd[:pos] = :numeral; msd[:type] = :cardinal
+      when :particle then msd[:pos] = :particle
+      when :preposition then msd[:pos] = :adposition; msd[:type] = :preposition
+      when :substantive then msd[:pos] = :noun; msd[:type] = :common
+      when :verb then msd[:pos] = :verb; msd[:type] = :main
+      when :adj_numeral then msd[:pos] = :numeral; msd[:type] = :ordinal
+      when :adj_pronoun then msd[:pos] = :pronoun; msd[:syntactic_type] = :adjectival
+      when :adv_pronoun then msd[:pos] = :pronoun; msd[:syntactic_type] = :adverbial
+      when :subst_pronoun then msd[:pos] = :pronoun; msd[:syntactic_type] = :nominal
+      when :abbreviation then msd[:pos] = :abbreviation
+      when :first_name then msd[:type] = :proper
+      when :surname then msd[:type] = :proper
+      when :patronymic then msd[:type] = :proper
+      when :geo then msd[:type] = :proper
+      when :proper then msd[:type] = :proper
+      # Tempus
+      when :present then msd[:tense] = :present
+      # TODO: how to handle :notpast tense?
+      when :past then msd[:tense] = :past
+      when :future then msd[:tense] = :future
+      when :past2 then msd[:tense] = :past
+      # Casus
+      when :nominative then msd[:case] = :nominative
+      when :genitive then msd[:case] = :genitive
+      when :dative then msd[:case] = :dative
+      when :accusative then msd[:case] = :accusative
+      when :instrumental then msd[:case] = :instrumental
+      when :ablative then msd[:case] = :genitive
+      when :partitive then msd[:case] = :genitive; msd[:case2] = :partitive
+      when :locative then msd[:case] = :genitive; msd[:case2] = :locative
+      when :vocative then msd[:case] = :vocative
+      # Numerus
+      when :singular then msd[:number] = :singular
+      when :plural then msd[:number] = :plural
+      # Modus
+      when :gerund then msd[:vform] = :gerund
+      when :infinitive then msd[:vform] = :infinitive
+      when :participle then msd[:vform] = :participle
+      when :indicative then msd[:vform] = :indicative
+      when :imperative then msd[:vform] = :imperative
+      when :conditional then msd[:vform] = :conditional
+      # Gradus
+      when :short then msd[:definiteness] = :short_art
+      when :full then msd[:definiteness] = :full_art
+      when :superlative then msd[:degree] = :superlative
+      when :comparative then msd[:degree] = :comparative
+      when :possessive then msd[:type] = :possessive
+      # Personae
+      when :person1 then msd[:person] = :first
+      when :person2 then msd[:person] = :second
+      when :person3 then msd[:person] = :third
+      # Gender
+      when :feminine then msd[:gender] = :feminine
+      when :masculine then msd[:gender] = :masculine
+      when :neuter then msd[:gender] = :neuter
+      when :mas_fem then msd[:gender] = :common
+      # Perfectum-Imperfectum
+      when :perfect then msd[:aspect] = :perfective
+      when :imperfect then msd[:aspect] = :progressive
+      # Voice
+      when :passive then msd[:voice] = :passive
+      when :active then msd[:voice] = :active
+      when :reflexive then msd[:type] = :reflexive
+      # Animated
+      when :animated then msd[:animate] = :yes
+      when :inanimated then msd[:animate] = :no
+      # Transitivity
+      when :definite then msd[:definiteness] = :full_art
+      when :indefinite then msd[:definiteness] = :short_art
+      # Definiteness
+      when :sim_conj then msd[:type] = :coordinating
+      when :sub_conj then msd[:type] = :subordinating
+      when :aux_verb then msd[:type] = :auxiliary
+      else
+      end
+    end
+
+    msd.prune!
+  end
+end

data/lib/myasorubka/treebank.rb

@@ -0,0 +1,123 @@
+# encoding: utf-8
+
+# The Penn Treebank Project annotates naturally-occuring text for
+# linguistic structure. Most notably, we produce skeletal parses
+# showing rough syntactic and semantic information — a bank of
+# linguistic trees.
+#
+# Treebanks are often created on top of a corpus that has already been
+# annotated with part-of-speech tags. In turn, treebanks are sometimes
+# enhanced with semantic or other linguistic information.
+#
+module Myasorubka::Treebank
+  extend self
+
+  # Convert the given tag from English Penn Treebank format to the English
+  # representation in the MULTEXT-East format.
+  #
+  def english(tag)
+    msd = Myasorubka::MSD.new(Myasorubka::MSD::English)
+
+    case tag
+    when 'CC' then
+      msd[:pos] = :conjunction
+      msd[:type] = :coordinating
+    when 'CD' then
+      msd[:pos] = :numeral
+      msd[:type] = :cardinal
+    when 'DT' then
+      msd[:pos] = :determiner
+    when 'IN' then
+      msd[:pos] = :conjunction
+      msd[:type] = :subordinating
+    when 'JJ' then
+      msd[:pos] = :adjective
+    when 'JJR' then
+      msd[:pos] = :adjective
+      msd[:degree] = :comparative
+    when 'JJS' then
+      msd[:pos] = :adjective
+      msd[:degree] = :superlative
+    when 'MD' then
+      msd[:pos] = :verb
+      msd[:type] = :modal
+    when 'NN' then
+      msd[:pos] = :noun
+      msd[:type] = :common
+      msd[:number] = :singular
+    when 'NNS'
+      msd[:pos] = :noun
+      msd[:type] = :common
+      msd[:number] = :plural
+    when 'NP'
+      msd[:pos] = :noun
+      msd[:type] = :proper
+      msd[:number] = :singular
+    when 'NPS'
+      msd[:pos] = :noun
+      msd[:type] = :proper
+      msd[:number] = :plural
+    when 'PDT' then
+      msd[:pos] = :determiner
+    when 'PP' then
+      msd[:pos] = :pronoun
+      msd[:type] = :personal
+    when 'PP$' then
+      msd[:pos] = :pronoun
+      msd[:type] = :possessive
+    when 'RB' then
+      msd[:pos] = :adverb
+    when 'RBR' then
+      msd[:pos] = :adverb
+      msd[:degree] = :comparative
+    when 'RBS' then
+      msd[:pos] = :adverb
+      msd[:degree] = :superlative
+    when 'TO' then
+      msd[:pos] = :determiner
+    when 'UH' then
+      msd[:pos] = :interjection
+    when 'VB' then
+      msd[:pos] = :verb
+      msd[:type] = :base
+    when 'VBD' then
+      msd[:pos] = :verb
+      msd[:type] = :base
+      msd[:tense] = :past
+    when 'VBG' then
+      msd[:pos] = :verb
+      msd[:type] = :base
+      msd[:vform] = :participle
+      msd[:tense] = :present
+    when 'VBN' then
+      msd[:pos] = :verb
+      msd[:type] = :base
+      msd[:vform] = :participle
+      msd[:tense] = :past
+    when 'VBP' then
+      msd[:pos] = :verb
+      msd[:type] = :base
+      msd[:tense] = :present
+      msd[:number] = :singular
+    when 'VBZ' then
+      msd[:pos] = :verb
+      msd[:type] = :base
+      msd[:tense] = :present
+      msd[:person] = :third
+      msd[:number] = :singular
+    when 'WDT' then
+      msd[:pos] = :determiner
+    when 'WP' then
+      msd[:pos] = :pronoun
+    when 'WP$' then
+      msd[:pos] = :pronoun
+      msd[:type] = :possessive
+    when 'WRB' then
+      msd[:pos] = :adverb
+    else
+      msd[:pos] = :residual
+    end
+
+    msd
+  end
+end

data/lib/myasorubka/unicode.rb

@@ -0,0 +1,46 @@
+# This module provides downcase and upcase methods designed for Russian.
+# The original code is written by Andrew Kozlov for the Petrovich library.
+#
+# https://github.com/petrovich/petrovich-ruby/blob/df705075542979ab85e1f2bf9a2024b1c0813e1a/lib/petrovich/unicode.rb
+#
+module Myasorubka::Unicode extend self
+  # Russian capital letters.
+  #
+  RU_UPPERCASE = [
+    "\u0410", "\u0411", "\u0412", "\u0413", "\u0414", "\u0415", "\u0416", "\u0417",
+    "\u0418", "\u0419", "\u041A", "\u041B", "\u041C", "\u041D", "\u041E", "\u041F",
+    "\u0420", "\u0421", "\u0422", "\u0423", "\u0424", "\u0425", "\u0426", "\u0427",
+    "\u0428", "\u0429", "\u042A", "\u042B", "\u042C", "\u042D", "\u042E", "\u042F",
+    "\u0401" # Ё
+  ].join
+
+  # Russian small letters.
+  #
+  RU_LOWERCASE = [
+    "\u0430", "\u0431", "\u0432", "\u0433", "\u0434", "\u0435", "\u0436", "\u0437",
+    "\u0438", "\u0439", "\u043A", "\u043B", "\u043C", "\u043D", "\u043E", "\u043F",
+    "\u0440", "\u0441", "\u0442", "\u0443", "\u0444", "\u0445", "\u0446", "\u0447",
+    "\u0448", "\u0449", "\u044A", "\u044B", "\u044C", "\u044D", "\u044E", "\u044F",
+    "\u0451" # Ё
+  ].join
+
+  # Returns a copy of the given string having replaced
+  # capital Russian letters with small ones.
+  #
+  # @param string [String] a string.
+  # @return [String] a new string.
+  #
+  def downcase(string)
+    string.tr(RU_UPPERCASE, RU_LOWERCASE).tap(&:downcase!)
+  end
+
+  # Returns a copy of the given string having replaced
+  # small Russian letters with capital ones.
+  #
+  # @param string [String] a string.
+  # @return [String] a new string.
+  #
+  def upcase(string)
+    string.tr(RU_LOWERCASE, RU_UPPERCASE).tap(&:upcase!)
+  end
+end

data/lib/myasorubka/version.rb

@@ -5,5 +5,5 @@
 module Myasorubka
   # Version of Myasorubka.
   #
-  VERSION = '0.1.1'
+  VERSION = '0.2.0'
 end

data/myasorubka.gemspec

@@ -12,17 +12,11 @@ Gem::Specification.new do |spec|
   spec.description   = 'Myasorubka is a morphological data processor.'
   spec.summary       = 'Myasorubka is a morphological data proceesor ' \
                        'that supports AOT and MULTEXT-East notations.'
-  spec.homepage      = 'https://github.com/ustalov/myasorubka'
+  spec.homepage      = 'https://github.com/dustalov/myasorubka'
   spec.license       = 'MIT'
 
   spec.files         = `git ls-files`.split($/)
   spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ['lib']
-
-  spec.add_development_dependency 'bundler', '~> 1.3'
-  spec.add_development_dependency 'minitest', '>= 2.11'
-  spec.add_development_dependency 'rake'
-
-  spec.add_dependency 'unicode_utils', '~> 1.4'
 end

data/spec/msd_spec.rb

@@ -83,6 +83,19 @@ module Myasorubka
         ('Vmp' =~ re).must_equal 0
         ('Nc-pl' =~ re).must_be_nil
       end
+
+      it 'can be pruned and became valid when the category is wrong' do
+        subject[:pos] = :zalupa
+        subject.prune!
+        subject.must_be :valid?
+      end
+
+      it 'can be pruned and became valid when an attribute is wrong' do
+        subject[:pos] = :verb
+        subject[:animate] = :yes
+        subject.prune!
+        subject.must_be :valid?
+      end
     end
 
     describe 'Generator' do

data/spec/spec_helper.rb

@@ -4,11 +4,9 @@ require 'rubygems'
 
 $:.unshift File.expand_path('../../lib', __FILE__)
 
-if RUBY_VERSION == '1.8'
-  gem 'minitest'
-end
-
+gem 'minitest'
 require 'minitest/autorun'
+require 'minitest/hell'
 
 require 'myasorubka'
 require 'myasorubka/aot'

metadata

@@ -1,71 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: myasorubka
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.2.0
 platform: ruby
 authors:
 - Dmitry Ustalov
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-05-07 00:00:00.000000000 Z
-dependencies:
-- !ruby/object:Gem::Dependency
-  name: bundler
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: '1.3'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: '1.3'
-- !ruby/object:Gem::Dependency
-  name: minitest
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: '2.11'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: '2.11'
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: unicode_utils
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: '1.4'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: '1.4'
+date: 2015-10-17 00:00:00.000000000 Z
+dependencies: []
 description: Myasorubka is a morphological data processor.
 email:
 - dmitry@eveel.ru
@@ -73,13 +17,12 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
-- .travis.yml
+- ".gitignore"
+- ".travis.yml"
 - Gemfile
 - LICENSE.txt
 - README.md
 - Rakefile
-- aot-russian
 - lib/myasorubka.rb
 - lib/myasorubka/aot.rb
 - lib/myasorubka/aot/dictionary.rb
@@ -88,13 +31,17 @@ files:
 - lib/myasorubka/msd.rb
 - lib/myasorubka/msd/english.rb
 - lib/myasorubka/msd/russian.rb
+- lib/myasorubka/mystem.rb
+- lib/myasorubka/mystem/binary.rb
+- lib/myasorubka/treebank.rb
+- lib/myasorubka/unicode.rb
 - lib/myasorubka/version.rb
 - myasorubka.gemspec
 - spec/data/russian.tsv
 - spec/msd/russian_spec.rb
 - spec/msd_spec.rb
 - spec/spec_helper.rb
-homepage: https://github.com/ustalov/myasorubka
+homepage: https://github.com/dustalov/myasorubka
 licenses:
 - MIT
 metadata: {}
@@ -104,17 +51,17 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.0.3
+rubygems_version: 2.4.8
 signing_key: 
 specification_version: 4
 summary: Myasorubka is a morphological data proceesor that supports AOT and MULTEXT-East

data/aot-russian

@@ -1,7 +0,0 @@
-#!/bin/sh
-rake clean aot \
-  mrd=morphs.mrd \
-  tab=rgramtab.tab \
-  encoding=CP1251 \
-  language=russian \
-  --trace