poliqarpr 0.0.5 → 0.0.8

data/README.txt

@@ -60,7 +60,7 @@ step of installation process).
 
 Require the gem:
 
-  require 'poliaqarpr'
+  require 'poliqarpr'
 
 Create the server client and open default corpus
 
@@ -76,6 +76,8 @@ Remember to close the client on exit
   
   client.close
 
+NOTE: If you wish to run the specs, you need the 'default' and '2.sample.30'
+corpuses.
 
 == LICENSE:
  

data/changelog.txt

@@ -1,3 +1,16 @@
+0.0.8
+- Speed optimization: socket puts changed to write
+
+0.0.7
+- QueryResult#to_a method added
+- Lexeme#tags method added
+- fix: README invalid require
+
+0.0.6
+- fix: Excerpt#word - the words consituing the matched query
+- new: Excerpt#matched, Excerpt#right_context Excerpt#left_context 
+  return the matched, right context, left context segments respecively
+
 0.0.5
 - Bugfix: making parallel query might lead to silent thread death
 - Support for Ruby 1.9 encoding

data/lib/poliqarpr/client.rb

@@ -366,7 +366,7 @@ protected
               lemmata.base_form = read_word
             end
             if @tag_flags[group]
-              read_word
+              lemmata.tags = read_word
             end
             segment.lemmata << lemmata
           end

data/lib/poliqarpr/connector.rb

@@ -70,7 +70,8 @@ module Poliqarp
       if ruby19?
         massage = message.encode(UTF8)
       end
-      @socket.puts(message)
+      #@socket.puts(message)
+      @socket.write(message+"\n")
       if mode == :async
         @handler = handler
       end

data/lib/poliqarpr/excerpt.rb

@@ -25,11 +25,25 @@ module Poliqarp
       @short_context << value
     end
 
+    # Returns the matched segments
+    def matched
+      @short_context[1]
+    end
+
+    # Returns the segments of the left short context of the match
+    def left_context
+      @short_context[0]
+    end
+
+    # Returns the segments of the right short context of the match
+    def right_context
+      @short_context[2]
+    end
 
     # Returns the matched query as string 
     def word
       #@short_context[0].split(/\s+/)[-1]
-      @short_context[1].to_s
+      @short_context[1].map{|s| s.to_s}.join("")
     end
 
     alias inflected_form word

data/lib/poliqarpr/lemmata.rb

@@ -4,7 +4,7 @@ module Poliqarp
   #
   # The lemmata contains the base form of the segment
   class Lemmata
-    attr_accessor :base_form
+    attr_accessor :base_form, :tags
     def initialize()
     end
   end

data/lib/poliqarpr/query_result.rb

@@ -69,5 +69,10 @@ module Poliqarp
       @excerpts.size
     end
 
+    # Converts current query result page into an array.
+    def to_a
+      @excerpts.dup
+    end
+
   end
 end

data/poliqarpr.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
   s.name = "poliqarpr"
-  s.version = "0.0.5"
-  s.date = "2009-12-10"
+  s.version = "0.0.8"
+  s.date = "2011-01-12"
   s.summary = "Ruby client for Poliqarp"
   s.email = "apohllo@o2.pl"
   s.homepage = "http://www.github.com/apohllo/poliqarpr"
@@ -9,7 +9,7 @@ Gem::Specification.new do |s|
   s.authors = ['Aleksander Pohl']
   s.files = ["Rakefile", "poliqarpr.gemspec", 
     "changelog.txt", "README.txt" ] + Dir.glob("lib/**/*")
-  s.test_files = Dir.glob("test/**/*")
+  s.test_files = Dir.glob("spec/**/*")
   s.rdoc_options = ["--main", "README.txt"]
   s.has_rdoc = true
   s.extra_rdoc_files = ["README.txt"]

data/spec/client.rb

@@ -0,0 +1,171 @@
+#vim:encoding=utf-8
+$:.unshift("lib")
+require 'poliqarpr'
+
+describe Poliqarp::Client do
+  describe "(general test)" do
+    before(:each) do
+      @client = Poliqarp::Client.new("TEST")
+    end
+    
+    after(:each) do 
+      @client.close
+    end
+  
+    it "should allow to open corpus" do
+      @client.open_corpus("/home/fox/local/poliqarp/2.sample.30/sample")
+    end
+  
+    it "should allow to open :default corpus" do
+      @client.open_corpus(:default)
+    end
+
+    it "should respond to :ping" do
+      @client.ping.should == :pong
+    end
+
+    it "should return server version" do
+      @client.version.should_not == nil
+    end
+
+  end
+
+  describe "(with 'sample' corpus)" do
+    before(:all) do
+      @client = Poliqarp::Client.new("TEST")
+      @client.open_corpus("/home/fox/local/poliqarp/2.sample.30/sample")
+    end
+
+    after(:all) do
+      @client.close
+    end
+
+    it "should allow to set the right context size" do 
+      @client.right_context = 5
+    end
+
+    it "should raise error if the size of right context is not number" do 
+      (proc do 
+        @client.right_context = "a"
+      end).should raise_error(RuntimeError)
+    end
+
+    it "should rais error if the size of right context is less or equal 0" do 
+      (proc do 
+        @client.right_context = 0
+      end).should raise_error(RuntimeError)
+    end
+
+    it "should allow to set the left context size" do 
+      @client.right_context = 5
+    end
+
+    it "should raise error if the size of left context is not number" do 
+      (lambda do 
+        @client.left_context = "a"
+      end).should raise_error(RuntimeError)
+    end
+
+    it "should rais error if the size of left context is less or equal 0" do 
+      (lambda do 
+        @client.left_context = 0
+      end).should raise_error(RuntimeError)
+    end
+
+    it "should return corpus statistics" do
+      stats = @client.stats
+      stats.size.should == 4
+      [:segment_tokens, :segment_types, :lemmata, :tags].each do |type|
+        stats[type].should_not == nil
+        stats[type].should > 0
+      end
+    end
+
+    it "should return the corpus tagset" do
+      tagset = @client.tagset
+      tagset[:categories].should_not == nil
+      tagset[:classes].should_not == nil
+    end
+
+    it "should allow to find 'kot'" do 
+      @client.find("kot").size.should_not == 0
+    end
+
+    it "should contain 'kot' in query result for [base=kot]" do
+      @client.find("[base=kot]")[0].to_s.should match(/\bkot\b/)
+    end
+
+    it "should allow to find 'Afrodyta [] od" do
+      @client.find("Afrodyta [] od").size.should_not == 0
+    end
+
+    it "should contain 'Afrodyta .* od' for 'Afrodyta [] od' query " do
+      @client.find("Afrodyta [] od")[0].to_s.should match(/Afrodyta .* od/)
+    end
+
+    it "should return collection for find without index specified" do
+      @client.find("kot").should respond_to(:[])
+    end
+
+    it "should allow to query for term occurences" do
+      @client.count("kot").should_not == nil
+    end
+
+    it "should return 188 occurences of 'kot'" do
+      @client.count("kot").should == 188
+    end
+
+    it "should allow to find first occurence of 'kot'" do
+      @client.find("kot",:index => 0).should_not == nil
+    end
+
+    it "should return different results for different queries" do
+      @client.find("kot").should_not ==
+        @client.find("kita")
+    end
+
+    it "should return same results for same queries" do
+      @client.find("kita").should == @client.find("kita")
+    end
+
+    describe("(with index specified in find)") do
+      before(:each) do 
+        @result = @client.find("nachalny",:index => 0)
+      end
+
+      it "should not return collection for find" do
+        @result.should_not respond_to(:[])
+      end
+
+      it "should not be nil" do
+        @result.should_not == nil
+      end
+
+      it "should fetch the same excerpt as in find without index " do
+        @result.to_s.should == @client.find("nachalny")[0].to_s
+      end
+    end
+
+    describe("(with lemmata flags set to true)") do 
+      before(:all) do
+        @client.lemmata = {:left_context => true, :right_context => true,
+          :left_match => true, :right_match => true}
+      end
+
+      it "should allow to find 'kotu'" do 
+        @client.find("kotu").size.should_not == 0
+      end
+
+      it "should contain 'kotu' in query result for 'kotu'" do
+        @client.find("kotu")[0].to_s.should match(/\bkotu\b/)
+      end
+
+      it "should contain 'kot' in lemmatized query result for 'kotu'" do
+        @client.find("kotu")[0].short_context.flatten.
+          map{|e| e.lemmata[0].base_form}.join(" ").should match(/\bkot\b/)
+      end
+
+    end
+  end
+
+end

data/spec/excerpt.rb

@@ -0,0 +1,142 @@
+#vim:encoding=utf-8
+$:.unshift("lib")
+require 'poliqarpr'
+
+describe Poliqarp::Excerpt do
+  before(:all) do
+    @client = Poliqarp::Client.new("TEST")
+  end
+
+  after(:all) do
+    @client.close
+  end
+
+  describe "(unspecified excerpt)" do
+    before(:all) do
+      @client.open_corpus(:default)
+      @excerpt = @client.find("kot").first
+    end
+
+    after(:all) do
+      @client.close_corpus
+    end
+
+    it "should have index" do
+      @excerpt.index.should_not == nil
+    end
+
+    it "should have base form" do 
+      @excerpt.base_form.should_not == nil
+    end
+
+    it "should contain 3 groups in short context" do
+      @excerpt.short_context.size.should == 3
+    end
+
+    it "should allow to add segment group" do
+      @excerpt << [Poliqarp::Segment.new("abc")]
+    end
+
+
+    it "should contain non empty segments in short context" do
+      @excerpt.short_context.flatten.each do |segment|
+        segment.literal.should_not == nil
+      end
+    end
+
+    it "should contain the exact form which it was created for" do
+      @excerpt.inflected_form.should_not == nil
+    end
+
+    it "should contain the long context of the word" do
+      @excerpt.context.should_not == nil
+    end
+  end
+
+  describe "(first exceprt for 'mu za to astronomiczną' in 'sample' corpus)" do
+    before(:all) do
+      @client.open_corpus("/home/fox/local/poliqarp/2.sample.30/sample")
+      @excerpt = @client.find("mu za to astronomiczną").first
+    end
+
+    after(:all) do
+      @client.close_corpus
+    end
+
+    it "should have index set to 0" do
+      @excerpt.index.should == 0 
+    end
+
+    it "should have base form set to 'kot'" do 
+      @excerpt.base_form.should == "mu za to astronomiczną"
+    end
+
+    it "should have 'kot' as inflected form  " do
+      @excerpt.inflected_form.should_not == nil
+    end
+
+    it "should contain the long context of the word" do
+      @excerpt.context.to_s.size.should >  10
+    end
+
+    it "should have one 'medium' set to 'książka'" do
+      @excerpt.medium.size.should == 1
+      @excerpt.medium[0].should == "książka"
+    end
+
+    it "should have 2 'styles' set to 'naukowo-dydaktyczny' and 'naukowo-humanistyczny'" do
+      @excerpt.style.size.should == 1
+      @excerpt.style.include?("naukowo-dydaktyczny")
+    end
+
+    it "should have 'date' set to nil" do
+      @excerpt.date.should == nil
+    end
+
+    it "should have 'city' set to nil" do
+      @excerpt.city.should == nil
+    end
+    
+    it "should have one 'publisher' set to 'Wydawnictwo Naukowe Akademii Pedagogicznej'" do
+      @excerpt.publisher.size.should == 1
+      @excerpt.publisher[0].should == "Wydawnictwo W.A.B."
+    end
+
+    it "should have one 'title' set to 'Wczesne nauczanie języków obcych. Integracja języka obcego z przedmiotami artystycznymi w młodszych klasach szkoły podstawowej'" do
+      @excerpt.title.size.should == 1
+      @excerpt.title[0].should == "Modlitwa o deszcz"
+    end
+
+    it "should have one 'author' set to 'Małgorzata Pamuła'" do
+      @excerpt.author.size.should == 1
+      @excerpt.author[0].should == "Wojciech Jagielski"
+    end
+  end
+
+  describe('first result for "kotu" with lemmatization turned on') do
+    before(:all) do 
+      @client.lemmata = :all 
+      @client.open_corpus(:default)
+      @excerpt = @client.find("kotu")[0] 
+    end
+
+    it "should have one lemmata for each segment" do  
+      @excerpt.short_context.each do |group|
+        group.each do |segment|
+          segment.lemmata.size.should == 1
+        end
+      end
+    end
+
+    it "should have non-nil lemmata for each segment" do
+      @excerpt.short_context.flatten.each do |segment|
+        segment.lemmata[0].should_not == nil
+      end
+    end
+
+    it "should contain 'kot' as one of the lemmata" do 
+      @excerpt.short_context.flatten.
+        any?{|s| s.lemmata[0].base_form == "kot"}.should == true
+    end
+  end
+end

data/spec/query_result.rb

@@ -0,0 +1,136 @@
+#vim:encoding=utf-8
+$:.unshift("lib")
+require 'poliqarpr'
+
+describe Poliqarp::QueryResult do
+  before(:all) do
+    @client = Poliqarp::Client.new("TEST")
+    @client.open_corpus(:default)
+  end
+
+  after(:all) do
+    @client.close
+  end
+
+  describe "(for unspecified query)" do 
+    before(:all) do
+      @result = @client.find("kita")
+    end
+
+    it "should not be nil" do
+      @result.should_not == nil
+    end
+
+    it "should containt its size" do
+      @result.size.should_not == nil
+    end
+
+    it "should be iterable" do
+      @result.each do |excerpt|
+        excerpt.should_not == nil
+      end
+    end
+
+    it "should allow to add excerpt" do
+      @result << Poliqarp::Excerpt.new(0,@client, "abc")
+    end
+
+    it "should contain current page" do
+      @result.page.should_not == nil
+    end
+
+    it "should contain the page count" do
+      @result.page_count.should_not == nil
+    end
+
+    it "should allow to call previous page" do
+      @result.previous_page
+    end
+
+    it "should allow to call next page" do
+      @result.next_page
+    end
+
+    it "should be the same if the query is the same" do
+      @result.should == @client.find("kita")
+    end
+  end
+
+  describe "(for 'kot' in :default corpus)" do
+    before(:all) do 
+      @result = @client.find("kot")
+    end
+
+    it "should have size == 6" do 
+      @result.size.should == 6
+    end
+
+    it "should have page set to 1" do
+      @result.page.should == 1
+    end
+
+    it "should contain only one page" do
+      @result.page_count.should == 1
+    end
+
+    it "should not have previous page" do
+      @result.previous_page.should == nil
+    end
+
+    it "should not have next page" do
+      @result.next_page.should == nil
+    end
+  end
+
+  describe "(for 'kot' with page_size set to 5 in :default corpus)" do
+    before(:all) do 
+      @result = @client.find("kot", :page_size => 5)
+    end
+
+    it "should have size == 5" do  
+      @result.size.should == 5
+    end
+
+    it "should have page set to 1" do
+      @result.page.should == 1
+    end
+
+    it "should contain 2 pages" do
+      @result.page_count.should == 2
+    end
+
+    it "should not have previous page" do
+      @result.previous_page.should == nil
+    end
+
+    it "should have next page" do
+      @result.next_page.should_not == nil
+    end
+  end
+
+  describe "(next for 'kot' with page_size set to 5 in :default corpus)" do
+    before(:all) do 
+      @result = @client.find("kot", :page_size => 5).next_page
+    end
+
+    it "should have size == 1" do  
+      @result.size.should == 1
+    end
+
+    it "should have page set to 2" do
+      @result.page.should == 2
+    end
+
+    it "should contain 2 pages" do
+      @result.page_count.should == 2
+    end
+
+    it "should have previous page" do
+      @result.previous_page.should_not == nil
+    end
+
+    it "should not have next page" do
+      @result.next_page.should == nil
+    end
+  end
+end

metadata

@@ -1,7 +1,12 @@
 --- !ruby/object:Gem::Specification 
 name: poliqarpr
 version: !ruby/object:Gem::Version 
-  version: 0.0.5
+  prerelease: false
+  segments: 
+  - 0
+  - 0
+  - 8
+  version: 0.0.8
 platform: ruby
 authors: 
 - Aleksander Pohl
@@ -9,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-12-10 00:00:00 +01:00
+date: 2011-01-12 00:00:00 +01:00
 default_executable: 
 dependencies: []
 
@@ -35,6 +40,9 @@ files:
 - lib/poliqarpr/client.rb
 - lib/poliqarpr/util.rb
 - lib/poliqarpr/connector.rb
+- spec/query_result.rb
+- spec/excerpt.rb
+- spec/client.rb
 has_rdoc: true
 homepage: http://www.github.com/apohllo/poliqarpr
 licenses: []
@@ -46,23 +54,29 @@ rdoc_options:
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.5
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
 summary: Ruby client for Poliqarp
-test_files: []
-
+test_files: 
+- spec/query_result.rb
+- spec/excerpt.rb
+- spec/client.rb