poliqarpr 0.0.8 → 0.1.0

data/changelog.txt

@@ -1,3 +1,8 @@
+0.1.0
+- synchronization on ansync call without handler done via internal mutex
+  instead of call to STATUS
+- client config moved to external class
+
 0.0.8
 - Speed optimization: socket puts changed to write
 
@@ -8,7 +13,7 @@
 
 0.0.6
 - fix: Excerpt#word - the words consituing the matched query
-- new: Excerpt#matched, Excerpt#right_context Excerpt#left_context 
+- new: Excerpt#matched, Excerpt#right_context Excerpt#left_context
   return the matched, right context, left context segments respecively
 
 0.0.5
@@ -19,16 +24,16 @@
 - Documentation now points to gemcutter instead of github
 
 0.0.4
-- ping/pong diagnostics 
+- ping/pong diagnostics
 - server version
-- corpus statistics 
+- corpus statistics
 - implementation of asynchronous protocol (not stable)
 
 
 0.0.3
 - the license of the corpus included
-- client rdoc documentation 
-- support for lemmata retrieval 
+- client rdoc documentation
+- support for lemmata retrieval
 - excerpt now contains segments instead of strings
 - buffer size setter
 - default corpus moved to separate plugin (sudo gem install apohllo-poliqarpr-corpus)
@@ -45,6 +50,6 @@
 - README.txt included in gem
 - specs included in gem
 
-0.0.1 
+0.0.1
 - initiali implementation
 - synchorous querying for terms

data/lib/poliqarpr.rb

@@ -1,5 +1,5 @@
 begin
-  require 'poliqarpr-corpus' 
+  require 'poliqarpr-corpus'
 rescue LoadError
   # Do nothig, since the default corpus is optional
 end

data/lib/poliqarpr/client.rb

@@ -3,61 +3,59 @@ module Poliqarp
   # Author:: Aleksander Pohl (mailto:apohllo@o2.pl)
   # License:: MIT License
   #
-  # This class is the implementation of the Poliqarp server client. 
+  # This class is the implementation of the Poliqarp server client.
   class Client
-    GROUPS = [:left_context, :left_match, :right_match, :right_context]
-
-    # If debug is turned on, the communication between server and client 
+    # If debug is turned on, the communication between server and client
     # is logged to standard output.
     attr_writer :debug
 
-    # The size of the buffer is the maximum number of excerpts which
-    # are returned for single query.
-    attr_writer :buffer_size
+    # The configuration of the client.
+    attr_reader :config
 
-    # Creates new poliqarp server client. 
-    # 
+    # Creates new poliqarp server client.
+    #
     # Parameters:
     # * +session_name+ the name of the client session. Defaults to "RUBY".
     # * +debug+ if set to true, all messages sent and received from server
     #   are printed to standard output. Defaults to false.
     def initialize(session_name="RUBY", debug=false)
       @session_name = session_name
-      @left_context = 5
-      @right_context = 5
       @debug = debug
-      @buffer_size = 500000
       @connector = Connector.new(debug)
+      @config = Config.new(self,500000)
       @answer_queue = Queue.new
+      @waiting_mutext = Mutex.new
       new_session
+      config.left_context_size = 5
+      config.right_context_size = 5
+      config.tags = []
+      config.lemmata = []
     end
 
     # A hint about installation of default corpus gem
     def self.const_missing(const)
-      if const.to_s =~ /DEFAULT_CORPUS/ 
+      if const.to_s =~ /DEFAULT_CORPUS/
         raise "You need to install 'apohllo-poliqarpr-corpus' to use the default corpus"
       end
       super
     end
 
-    # Creates new session for the client with the name given in constructor. 
-    # If the session was already opened, it is closed. 
+    # Creates new session for the client with the name given in constructor.
+    # If the session was already opened, it is closed.
     #
-    # Parameters: 
+    # Parameters:
     # * +port+ - the port on which the poliqarpd server is accepting connections (defaults to 4567)
     def new_session(port=4567)
       close if @session
       @connector.open("localhost",port)
       talk("MAKE-SESSION #{@session_name}")
-      talk("BUFFER-RESIZE #{@buffer_size}")
+      talk("BUFFER-RESIZE #{config.buffer_size}")
       @session = true
-      self.tags = {}
-      self.lemmata = {}
     end
 
     # Closes the opened session.
     def close
-      talk "CLOSE-SESSION" 
+      talk "CLOSE-SESSION"
       @session = false
     end
 
@@ -66,114 +64,36 @@ module Poliqarp
       talk "CLOSE"
     end
 
-    # Sets the size of the left short context. It must be > 0
-    #
-    # The size of the left short context is the number 
-    # of segments displayed in the found excerpts left to the
-    # matched segment(s).
-    def left_context=(value)
-      if correct_context_value?(value) 
-        result = talk("SET left-context-width #{value}")
-        @left_context = value if result =~ /^R OK/
-      else
-        raise "Invalid argument: #{value}. It must be fixnum greater than 0."
-      end
-    end
-
-    # Sets the size of the right short context. It must be > 0
-    #
-    # The size of the right short context is the number 
-    # of segments displayed in the found excerpts right to the
-    # matched segment(s).
-    def right_context=(value)
-      if correct_context_value?(value)
-        result = talk("SET right-context-width #{value}")
-        @right_context = value if result =~ /^R OK/
-      else
-        raise "Invalid argument: #{value}. It must be fixnum greater than 0."
-      end
-    end
-
-    # Sets the tags' flags. There are four groups of segments 
-    # which the flags apply for:
-    # * +left_context+
-    # * +left_match+
-    # * +right_match+
-    # * +right_context+
-    #
-    # If the flag for given group is set to true, all segments 
-    # in the group are annotated with grammatical tags. E.g.:
-    #  c.find("kot")
-    #  ...
-    #  "kot" tags: "subst:sg:nom:m2"
-    #
-    # You can pass :all to turn on flags for all groups
-    def tags=(options={})
-      options = set_all_flags if options == :all
-      @tag_flags = options
-      flags = ""
-      GROUPS.each do |flag|
-        flags << (options[flag] ? "1" : "0")
-        end
-      talk("SET retrieve-tags #{flags}")
-    end
-
-    # Sets the lemmatas' flags. There are four groups of segments 
-    # which the flags apply for:
-    # * +left_context+
-    # * +left_match+
-    # * +right_match+
-    # * +right_context+
-    #
-    # If the flag for given group is set to true, all segments 
-    # in the group are returned with the base form of the lemmata. E.g.:
-    #  c.find("kotu")
-    #  ...
-    #  "kotu" base_form: "kot"
-    #
-    # You can pass :all to turn on flags for all groups
-    def lemmata=(options={})
-      options = set_all_flags if options == :all
-      @lemmata_flags = options
-      flags = ""
-      GROUPS.each do |flag|
-        flags << (options[flag] ? "1" : "0")
-        end
-      talk("SET retrieve-lemmata #{flags}")
-    end
-
     # *Asynchronous* Opens the corpus given as +path+. To open the default
-    # corpus pass +:default+ as the argument. 
-    # 
+    # corpus pass +:default+ as the argument.
+    #
     # If you don't want to wait until the call is finished, you
     # have to provide +handler+ for the asynchronous answer.
     def open_corpus(path, &handler)
       if path == :default
         open_corpus(DEFAULT_CORPUS, &handler)
       else
-        real_handler = handler || lambda{|msg| @answer_queue.push msg }
-        talk("OPEN #{path}", :async, &real_handler)
-        do_wait if handler.nil?
+        talk("OPEN #{path}", :async, &handler)
       end
     end
 
     # Server diagnostics -- the result should be :pong
-    def ping 
+    def ping
       :pong if talk("PING") =~ /PONG/
     end
 
     # Returns server version
-    def version 
+    def version
       talk("VERSION")
     end
 
     # Returns corpus statistics:
-    # * +:segment_tokens+ the number of segments in the corpus 
+    # * +:segment_tokens+ the number of segments in the corpus
     #   (two segments which look exactly the same are counted separately)
     # * +:segment_types+ the number of segment types in the corpus
     #   (two segments which look exactly the same are counted as one type)
     # * +:lemmata+ the number of lemmata (lexemes) types
-    #   (all forms of inflected word, e.g. 'kot', 'kotu', ... 
+    #   (all forms of inflected word, e.g. 'kot', 'kotu', ...
     #   are treated as one "word" -- lemmata)
     # * +:tags+ the number of different grammar tags (each combination
     #   of atomic tags is treated as different "tag")
@@ -181,7 +101,7 @@ module Poliqarp
       stats = {}
       talk("CORPUS-STATS").split.each_with_index do |value, index|
         case index
-        when 1 
+        when 1
           stats[:segment_tokens] = value.to_i
         when 2
           stats[:segment_types] = value.to_i
@@ -205,7 +125,7 @@ module Poliqarp
     #   (each category has a list of its tags, eg. gender: m1 m2 m3 f n,
     #   means that there are 5 genders: masculine(1,2,3), feminine and neuter)
     # * +:classes+ enlists grammatical tags used to describe it
-    #   (each class has a list of tags used to describe it, eg. adj: degree 
+    #   (each class has a list of tags used to describe it, eg. adj: degree
     #   gender case number, means that adjectives are described in terms
     #   of degree, gender, case and number)
     def tagset
@@ -226,14 +146,14 @@ module Poliqarp
     #
     # Options:
     # * +index+ the index of the (only one) result to be returned. The index is relative
-    #   to the beginning of the query result. In normal case you should query the 
+    #   to the beginning of the query result. In normal case you should query the
     #   corpus without specifying the index, to see what results are returned.
-    #   Then you can use the index and the same query to retrieve one result. 
+    #   Then you can use the index and the same query to retrieve one result.
     #   The pair (query, index) is a kind of unique identifier of the excerpt.
     # * +page_size+ the size of the page of results. If the page size is 0, then
     #   all results are returned on one page. It is ignored if the +index+ option
     #   is present. Defaults to 0.
-    # * +page_index+ the index of the page of results (the first page has index 1, not 0). 
+    # * +page_index+ the index of the page of results (the first page has index 1, not 0).
     #   It is ignored if the +index+ option is present. Defaults to 1.
     def find(query,options={})
       if options[:index]
@@ -243,11 +163,11 @@ module Poliqarp
       end
     end
 
-    alias query find 
+    alias query find
 
     # Returns the number of results for given query.
     def count(query)
-      count_results(make_query(query)) 
+      count_results(make_query(query))
     end
 
     # Returns the long context of the excerpt which is identified by
@@ -257,13 +177,13 @@ module Poliqarp
       result = []
       talk "GET-CONTEXT #{index}"
       # 1st part
-      result << read_word 
+      result << read_word
       # 2nd part
-      result << read_word 
+      result << read_word
       # 3rd part
-      result << read_word 
+      result << read_word
       # 4th part
-      result << read_word 
+      result << read_word
       result
     end
 
@@ -286,19 +206,62 @@ module Poliqarp
     end
 
 protected
+    # Set the size of the left context.
+    def left_context=(value)
+      result = talk("SET left-context-width #{value}")
+      unless result =~ /^OK/
+        raise "Failed to set left context to #{value}: #{result}"
+      end
+    end
+
+    # Set the size of the right context.
+    def right_context=(value)
+      result = talk("SET right-context-width #{value}")
+      unless result =~ /^OK/
+        raise "Failed to set right context to #{value}: #{result}"
+      end
+    end
+
+    # Sets the 'retrieve-tags' flags.
+    def retrieve_tags(flags)
+      talk("SET retrieve-tags #{flags}")
+    end
+
+    # Sets the 'retrieve-lemmata' flags.
+    def retrieve_lemmata(flags)
+      talk("SET retrieve-lemmata #{flags}")
+    end
+
+
     # Sends a message directly to the server
     # * +msg+ the message to send
     # * +mode+ if set to :sync, the method block untli the message
     #   is received. If :async the method returns immediately.
     #   Default: :sync
-    # * +handler+ the handler of the assynchronous message. 
+    # * +handler+ the handler of the assynchronous message.
     #   It is ignored when the mode is set to :sync.
     def talk(msg, mode = :sync, &handler)
       puts msg if @debug
-      @connector.send(msg, mode, &handler)
+      if mode == :sync
+        @connector.send_message(msg, mode, &handler)
+      else
+        if handler.nil?
+          real_handler = lambda do |msg|
+            @answer_queue.push msg
+            stop_waiting
+          end
+          start_waiting
+        else
+          real_handler = handler
+        end
+        @connector.send_message(msg, mode, &real_handler)
+        if handler.nil?
+          do_wait
+        end
+      end
     end
 
-    # Make query and retrieve many results. 
+    # Make query and retrieve many results.
     # * +query+ the query to be sent to the server.
     # * +options+ see find
     def find_many(query, options)
@@ -308,7 +271,7 @@ protected
       answer_offset = page_size * (page_index - 1)
       if page_size > 0
         result_count = make_async_query(query,answer_offset)
-        answers_limit = answer_offset + page_size > result_count ?  
+        answers_limit = answer_offset + page_size > result_count ?
           result_count - answer_offset : page_size
       else
         # all answers needed -- the call must be synchronous
@@ -321,12 +284,12 @@ protected
 
       result = QueryResult.new(page_index, page_count,page_size,self,query)
       if answers_limit > 0
-        talk("GET-RESULTS #{answer_offset} #{answer_offset + answers_limit - 1}") 
+        talk("GET-RESULTS #{answer_offset} #{answer_offset + answers_limit - 1}")
         answers_limit.times do |answer_index|
           result << fetch_result(answer_offset + answer_index, query)
         end
       end
-      result 
+      result
     end
 
     # Make query and retrieve only one result
@@ -334,13 +297,13 @@ protected
     # * +index+ the index of the answer to be retrieved
     def find_one(query,index)
       make_async_query(query,index)
-      talk("GET-RESULTS #{index} #{index}") 
-      fetch_result(index,query) 
+      talk("GET-RESULTS #{index} #{index}")
+      fetch_result(index,query)
     end
 
     # Fetches one result of the query
     #
-    # MAKE-QUERY and GET-RESULTS must be sent to the server before 
+    # MAKE-QUERY and GET-RESULTS must be sent to the server before
     # this method is called
     def fetch_result(index, query)
       result = Excerpt.new(index, self, query)
@@ -357,15 +320,15 @@ protected
       segments = []
       size.times do |segment_index|
         segment = Segment.new(read_word)
-        segments << segment 
-        if @lemmata_flags[group] || @tag_flags[group]
+        segments << segment
+        if config.lemmata.include?(group) || config.tags.include?(group)
           lemmata_size = read_number()
-          lemmata_size.times do |lemmata_index| 
+          lemmata_size.times do |lemmata_index|
             lemmata = Lemmata.new()
-            if @lemmata_flags[group]
+            if config.lemmata.include?(group)
               lemmata.base_form = read_word
             end
-            if @tag_flags[group]
+            if config.tags.include?(group)
               lemmata.tags = read_word
             end
             segment.lemmata << lemmata
@@ -377,7 +340,9 @@ protected
 
     # Reads number stored in the message received from the server.
     def read_number
-      @connector.read_message.match(/\d+/)[0].to_i
+      msg = @connector.read_message
+      puts "XXX #{msg}" if @debug
+      msg.match(/\d+/)[0].to_i
     end
 
     # Counts number of results for given answer
@@ -387,25 +352,22 @@ protected
 
     # *Asynchronous* Sends the query to the server
     # * +query+ query to send
-    # * +handler+ if given, the method returns immediately, 
+    # * +handler+ if given, the method returns immediately,
     #   and the answer is sent to the handler. In this case
     #   the result returned by make_query should be IGNORED!
     def make_query(query, &handler)
       if @last_query != query
         @last_query = query
-        if handler.nil?
-          real_handler = lambda { |msg| @answer_queue.push msg }
-        else
-          real_handler = handler
-        end
         begin
           talk("MAKE-QUERY #{query}")
         rescue JobInProgress
           talk("CANCEL") rescue nil
           talk("MAKE-QUERY #{query}")
         end
-        talk("RUN-QUERY #{@buffer_size}", :async, &real_handler) 
-        @last_result = do_wait if handler.nil?
+        result = talk("RUN-QUERY #{config.buffer_size}", :async, &handler)
+        if handler.nil?
+          @last_result = result
+        end
       end
       @last_result
     end
@@ -415,38 +377,55 @@ protected
       @connector.read_message
     end
 
-private 
+    private
+    # Wait for the assynchronous answer, if some synchronous query
+    # was sent without handler.
     def do_wait
       loop {
-        status = talk("STATUS") rescue break
-        puts "STATUS: #{status}" if @debug
-        sleep 0.3
+        break unless should_wait?
+        puts "WAITING" if @debug
+        sleep 0.1
       }
       @answer_queue.shift
     end
 
-    def set_all_flags
-      options = {}
-      GROUPS.each{|g| options[g] = true}
-      options
+    # Stop waiting for the ansynchonous answer.
+    def stop_waiting
+      @waiting_mutext.synchronize {
+        @should_wait = false
+      }
+      puts "WAITING stopped" if @debug
+    end
+
+    # Check if the thread should still wait for the answer.
+    def should_wait?
+      should_wait = nil
+      @waiting_mutext.synchronize {
+        should_wait = @should_wait
+      }
+      should_wait
     end
-    
-    def correct_context_value?(value)
-      value.is_a?(Fixnum) && value > 0
+
+    # Start waiting for the answer.
+    def start_waiting
+      @waiting_mutext.synchronize {
+        @should_wait = true
+      }
+      puts "WAITING started" if @debug
     end
 
-    def make_async_query(query,answer_offset) 
-      # the handler is empty, since we access the result count through 
-      # BUFFER-STATE call
-      make_query(query){|msg| }
-      result_count = 0 
-      begin 
+    def make_async_query(query,answer_offset)
+      start_waiting
+      # we access the result count through BUFFER-STATE call
+      make_query(query){|msg| stop_waiting}
+      result_count = 0
+      begin
         # the result count might be not exact!
         result_count = talk("BUFFER-STATE").split(" ")[2].to_i
-        talk("STATUS") rescue break
+        break unless should_wait?
       end while result_count < answer_offset
       @last_result = "OK #{result_count}"
       result_count
     end
-  end 
+  end
 end

data/lib/poliqarpr/config.rb

@@ -0,0 +1,138 @@
+# vim:encoding=utf-8
+module Poliqarp
+  # Author:: Aleksander Pohl (mailto:apohllo@o2.pl)
+  # License:: MIT License
+  #
+  # This class holds the configuration of the client.
+  class Config
+    GROUPS = [:left_context, :left_match, :right_match, :right_context]
+    # The size of the buffer is the maximum number of excerpts which
+    # are returned for single query.
+    attr_accessor :buffer_size, :left_context_size, :right_context_size, :tags, :lemmata
+
+    def initialize(client,buffer_size)
+      @client = client
+      @buffer_size = buffer_size
+    end
+
+    # Sets the size of the left short context. It must be > 0
+    #
+    # The size of the left short context is the number
+    # of segments displayed in the found excerpts left to the
+    # matched segment(s).
+    def left_context_size=(value)
+      if correct_context_value?(value)
+        @client.send(:left_context=,value)
+        @left_context_size = value
+      else
+        raise "Invalid argument: #{value}. It must be fixnum greater than 0."
+      end
+    end
+
+    # Sets the size of the right short context. It must be > 0
+    #
+    # The size of the right short context is the number
+    # of segments displayed in the found excerpts right to the
+    # matched segment(s).
+    def right_context_size=(value)
+      if correct_context_value?(value)
+        @client.send(:right_context=,value)
+        @right_context_size = value
+      else
+        raise "Invalid argument: #{value}. It must be fixnum greater than 0."
+      end
+    end
+
+    # Sets the tags' flags. There are four groups of segments
+    # which the flags apply for:
+    # * +:left_context+
+    # * +:left_match+
+    # * +:right_match+
+    # * +:right_context+
+    #
+    # If the flag for given group is present, all segments
+    # in the group are annotated with grammatical tags. E.g.:
+    #  c.find("kot")
+    #  ...
+    #  "kot" tags: "subst:sg:nom:m2"
+    #
+    # E.g. config.tags = [:left_context] will retrieve tags
+    # only for the left context.
+    #
+    # You can pass :all to turn on flags for all groups, i.e.
+    # config.tags = :all will retrieve tags for all groups.
+    def tags=(groups)
+      if groups == :all
+        @tags = GROUPS.dup
+      else
+        @tags = groups
+      end
+      @client.send(:retrieve_tags, flags_for(@tags))
+    end
+
+    # Sets the lemmatas' flags. There are four groups of segments
+    # which the flags apply for:
+    # * +left_context+
+    # * +left_match+
+    # * +right_match+
+    # * +right_context+
+    #
+    # If the flag for given group is present, all segments
+    # in the group are returned with the base form of the lemmata. E.g.:
+    #  c.find("kotu")
+    #  ...
+    #  "kotu" base_form: "kot"
+    #
+    # E.g. config.lemmata = [:left_context] will retrieve lemmata
+    # only for the left context.
+    #
+    # You can pass :all to turn on flags for all groups, i.e.
+    # config.lemmata = :all will retrieve lemmata for all groups.
+    def lemmata=(groups)
+      if groups == :all
+        @lemmata = GROUPS.dup
+      else
+        @lemmata = groups
+      end
+      @client.send(:retrieve_lemmata, flags_for(@lemmata))
+    end
+
+    # Allow for accessing individual group tags/lemmata flag,
+    # e.g. config.left_context_tags, config.left_context_lemmata
+    [:tags,:lemmata].each do |type|
+      GROUPS.each do |group|
+        define_method("#{group}_#{type}".to_sym) do
+          @tags.include?(group)
+        end
+      end
+    end
+
+    # Allow for changing individual group tags/lemmata flag,
+    # e.g. config.left_context_tags = true, config.left_context_lemmata = true
+    [:tags,:lemmata].each do |type|
+      GROUPS.each do |group|
+        define_method("#{group}_#{type}=".to_sym) do |value|
+          if value
+            @tags << group unless @tags.include?(group)
+          else
+            @tags.delete(group) if @tags.include?(group)
+          end
+          @client.send("retrieve_#{type}".to_sym, flags_for(@tags))
+        end
+      end
+    end
+
+    protected
+    def correct_context_value?(value)
+      value.is_a?(Fixnum) && value > 0
+    end
+
+    def flags_for(elements)
+      flags = ""
+      GROUPS.each do |flag|
+        flags << (elements.include?(flag) ? "1" : "0")
+      end
+      flags
+    end
+  end
+end

data/lib/poliqarpr/connector.rb

@@ -44,7 +44,7 @@ module Poliqarp
       @debug = debug
     end
 
-    # Opens connection with poliqarp server which runs 
+    # Opens connection with poliqarp server which runs
     # on given +host+ and +port+.
     def open(host,port)
       @socket_mutex.synchronize {
@@ -60,17 +60,16 @@ module Poliqarp
       }
     end
 
-    # Sends message to the poliqarp server. Returns the first synchronous 
+    # Sends message to the poliqarp server. Returns the first synchronous
     # answer of the server.
     # * +message+ the message to send
     # * +mode+ synchronous (+:sync:) or asynchronous (+:async+)
     # * +handler+ the handler of the asynchronous message
-    def send(message, mode, &handler)
+    def send_message(message, mode, &handler)
       puts "send #{mode} #{message}" if @debug
       if ruby19?
         massage = message.encode(UTF8)
       end
-      #@socket.puts(message)
       @socket.write(message+"\n")
       if mode == :async
         @handler = handler
@@ -79,7 +78,7 @@ module Poliqarp
     end
 
     # Retrives one message from the server.
-    # If the message indicates an error, new runtime error 
+    # If the message indicates an error, new runtime error
     # containing the error description is returned.
     def read_message
       message = @message_queue.shift
@@ -94,7 +93,7 @@ module Poliqarp
 
 private
     def main_loop
-      @loop = Thread.new { 
+      @loop = Thread.new {
         loop {
           receive
           # XXX ??? needed
@@ -124,8 +123,8 @@ private
 
     def receive_async(message)
       puts "receive async: #{message}" if @debug
-      Thread.new{ 
-        @handler.call(message) 
+      Thread.new{
+        @handler.call(message)
       }
     end
 

data/lib/poliqarpr/exceptions.rb

@@ -2,7 +2,7 @@ module Poliqarp
   # Author:: Aleksander Pohl (mailto:apohllo@o2.pl)
   # License:: MIT License
 
-  # The JobInProgress exception is raised if there was asynchronous call 
+  # The JobInProgress exception is raised if there was asynchronous call
   # to the server which haven't finished, which is interrupted by another
   # asynchronous call.
   class JobInProgress < Exception; end

data/lib/poliqarpr/excerpt.rb

@@ -2,13 +2,13 @@ module Poliqarp
   # Author:: Aleksander Pohl
   # License:: MIT License
   #
-  # The excerpt class is used to store single result of the query, 
+  # The excerpt class is used to store single result of the query,
   # i.e. the excerpt of the corpus which contains the words which
-  # the corpus was queried for. 
+  # the corpus was queried for.
   #
   # The excerpt is divided into groups, which contain segments,
-  # which the texts in the corpus were divided for. 
-  # The first group is the left context, the second -- the matched 
+  # which the texts in the corpus were divided for.
+  # The first group is the left context, the second -- the matched
   # query, and the last -- the right context.
   class Excerpt
     attr_reader :index, :base_form, :short_context
@@ -40,7 +40,7 @@ module Poliqarp
       @short_context[2]
     end
 
-    # Returns the matched query as string 
+    # Returns the matched query as string
     def word
       #@short_context[0].split(/\s+/)[-1]
       @short_context[1].map{|s| s.to_s}.join("")
@@ -54,7 +54,7 @@ module Poliqarp
       @short_context.join("")
     end
 
-    # Returns the long context of the query. 
+    # Returns the long context of the query.
     def context
       return @context unless @context.nil?
       @context = @client.context(@base_form, @index)
@@ -63,7 +63,7 @@ module Poliqarp
     { :medium => :medium, :style => :styl, :date => :data_wydania,
       :city => :miejsce_wydania, :publisher => :wydawca, :title => :tytu,
       :author => :autor}.each do |method, keyword|
-      define_method method do 
+      define_method method do
         self.metadata[keyword]
       end
       end

data/lib/poliqarpr/query_result.rb

@@ -2,9 +2,9 @@ module Poliqarp
   # Author:: Aleksander Pohl (mailto:apohllo@o2.pl)
   # License:: MIT License
   #
-  # The query result class is used to paginate results of the 
+  # The query result class is used to paginate results of the
   # query. Each query result has information about its context
-  # (the next and previous page). 
+  # (the next and previous page).
   class QueryResult
     include Enumerable
 
@@ -51,16 +51,16 @@ module Poliqarp
     # Returns the previous page of the query result
     def previous_page
       if @page > 1
-        @client.find(@query, :page_size => @page_size, 
-                     :page_index => @page - 1) 
+        @client.find(@query, :page_size => @page_size,
+                     :page_index => @page - 1)
       end
     end
 
     # Return the next page of the query result
     def next_page
       if @page < @page_count
-        @client.find(@query, :page_size => @page_size, 
-                     :page_index => @page + 1) 
+        @client.find(@query, :page_size => @page_size,
+                     :page_index => @page + 1)
       end
     end
 

data/lib/poliqarpr/segment.rb

@@ -1,22 +1,22 @@
-module Poliqarp 
+module Poliqarp
   # Author:: Aleksander Pohl (mailto:apohllo@o2.pl)
   # License:: MIT LICENSE
   #
-  # The segment is the smallest meaningful part of the text.  
-  # It may contain many lemmata, since the segments are sometimes 
-  # not disambiguated. 
+  # The segment is the smallest meaningful part of the text.
+  # It may contain many lemmata, since the segments are sometimes
+  # not disambiguated.
   class Segment
     attr_reader :literal, :lemmata
 
-    # Creates new segment. The specified argument is the literal 
-    # (as found in the text) representation of the segment. 
+    # Creates new segment. The specified argument is the literal
+    # (as found in the text) representation of the segment.
     def initialize(literal)
       @literal = literal
       @lemmata = []
     end
 
     # Returns the segment literal
-    def to_s 
+    def to_s
       @literal
     end
   end

data/lib/poliqarpr/util.rb

@@ -3,7 +3,7 @@ module Poliqarp #:nodoc:
   module Ruby19
     # Returns true if the Ruby version is at least 1.9.0
     def ruby19?
-      RUBY_VERSION.split(".")[0..1].join(".").to_f >= 1.9 
+      RUBY_VERSION.split(".")[0..1].join(".").to_f >= 1.9
     end
   end
 end

data/poliqarpr.gemspec

@@ -1,13 +1,13 @@
 Gem::Specification.new do |s|
   s.name = "poliqarpr"
-  s.version = "0.0.8"
-  s.date = "2011-01-12"
+  s.version = "0.1.0"
+  s.date = "2011-01-17"
   s.summary = "Ruby client for Poliqarp"
   s.email = "apohllo@o2.pl"
   s.homepage = "http://www.github.com/apohllo/poliqarpr"
   s.description = "Ruby client for Poliqarp (NLP corpus server)"
   s.authors = ['Aleksander Pohl']
-  s.files = ["Rakefile", "poliqarpr.gemspec", 
+  s.files = ["Rakefile", "poliqarpr.gemspec",
     "changelog.txt", "README.txt" ] + Dir.glob("lib/**/*")
   s.test_files = Dir.glob("spec/**/*")
   s.rdoc_options = ["--main", "README.txt"]

data/spec/client.rb

@@ -5,17 +5,17 @@ require 'poliqarpr'
 describe Poliqarp::Client do
   describe "(general test)" do
     before(:each) do
-      @client = Poliqarp::Client.new("TEST")
+      @client = Poliqarp::Client.new("TEST1")
     end
-    
-    after(:each) do 
+
+    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
@@ -32,7 +32,7 @@ describe Poliqarp::Client do
 
   describe "(with 'sample' corpus)" do
     before(:all) do
-      @client = Poliqarp::Client.new("TEST")
+      @client = Poliqarp::Client.new("TEST2")
       @client.open_corpus("/home/fox/local/poliqarp/2.sample.30/sample")
     end
 
@@ -40,35 +40,37 @@ describe Poliqarp::Client do
       @client.close
     end
 
-    it "should allow to set the right context size" do 
-      @client.right_context = 5
+    it "should allow to set and get the right context size" do
+      @client.config.right_context_size = 5
+      @client.config.right_context_size.should == 5
     end
 
-    it "should raise error if the size of right context is not number" do 
-      (proc do 
-        @client.right_context = "a"
+    it "should raise error if the size of right context is not number" do
+      (proc do
+        @client.config.right_context_size = "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
+    it "should rais error if the size of right context is less or equal 0" do
+      (proc do
+        @client.config.right_context_size = 0
       end).should raise_error(RuntimeError)
     end
 
-    it "should allow to set the left context size" do 
-      @client.right_context = 5
+    it "should allow to set and get the left context size" do
+      @client.config.left_context_size = 5
+      @client.config.left_context_size.should == 5
     end
 
-    it "should raise error if the size of left context is not number" do 
-      (lambda do 
-        @client.left_context = "a"
+    it "should raise error if the size of left context is not number" do
+      (lambda do
+        @client.config.left_context_size = "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
+    it "should rais error if the size of left context is less or equal 0" do
+      (lambda do
+        @client.config.left_context_size = 0
       end).should raise_error(RuntimeError)
     end
 
@@ -87,7 +89,7 @@ describe Poliqarp::Client do
       tagset[:classes].should_not == nil
     end
 
-    it "should allow to find 'kot'" do 
+    it "should allow to find 'kot'" do
       @client.find("kot").size.should_not == 0
     end
 
@@ -129,7 +131,7 @@ describe Poliqarp::Client do
     end
 
     describe("(with index specified in find)") do
-      before(:each) do 
+      before(:each) do
         @result = @client.find("nachalny",:index => 0)
       end
 
@@ -146,13 +148,12 @@ describe Poliqarp::Client do
       end
     end
 
-    describe("(with lemmata flags set to true)") do 
+    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}
+        @client.config.lemmata = [:left_context, :right_context, :left_match, :right_match]
       end
 
-      it "should allow to find 'kotu'" do 
+      it "should allow to find 'kotu'" do
         @client.find("kotu").size.should_not == 0
       end
 

data/spec/excerpt.rb

@@ -25,7 +25,7 @@ describe Poliqarp::Excerpt do
       @excerpt.index.should_not == nil
     end
 
-    it "should have base form" do 
+    it "should have base form" do
       @excerpt.base_form.should_not == nil
     end
 
@@ -64,10 +64,10 @@ describe Poliqarp::Excerpt do
     end
 
     it "should have index set to 0" do
-      @excerpt.index.should == 0 
+      @excerpt.index.should == 0
     end
 
-    it "should have base form set to 'kot'" do 
+    it "should have base form set to 'kot'" do
       @excerpt.base_form.should == "mu za to astronomiczną"
     end
 
@@ -96,7 +96,7 @@ describe Poliqarp::Excerpt do
     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."
@@ -114,13 +114,13 @@ describe Poliqarp::Excerpt do
   end
 
   describe('first result for "kotu" with lemmatization turned on') do
-    before(:all) do 
-      @client.lemmata = :all 
+    before(:all) do
+      @client.config.lemmata = :all
       @client.open_corpus(:default)
-      @excerpt = @client.find("kotu")[0] 
+      @excerpt = @client.find("kotu")[0]
     end
 
-    it "should have one lemmata for each segment" do  
+    it "should have one lemmata for each segment" do
       @excerpt.short_context.each do |group|
         group.each do |segment|
           segment.lemmata.size.should == 1
@@ -134,7 +134,7 @@ describe Poliqarp::Excerpt do
       end
     end
 
-    it "should contain 'kot' as one of the lemmata" do 
+    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

data/spec/query_result.rb

@@ -12,7 +12,7 @@ describe Poliqarp::QueryResult do
     @client.close
   end
 
-  describe "(for unspecified query)" do 
+  describe "(for unspecified query)" do
     before(:all) do
       @result = @client.find("kita")
     end
@@ -57,11 +57,11 @@ describe Poliqarp::QueryResult do
   end
 
   describe "(for 'kot' in :default corpus)" do
-    before(:all) do 
+    before(:all) do
       @result = @client.find("kot")
     end
 
-    it "should have size == 6" do 
+    it "should have size == 6" do
       @result.size.should == 6
     end
 
@@ -83,11 +83,11 @@ describe Poliqarp::QueryResult do
   end
 
   describe "(for 'kot' with page_size set to 5 in :default corpus)" do
-    before(:all) do 
+    before(:all) do
       @result = @client.find("kot", :page_size => 5)
     end
 
-    it "should have size == 5" do  
+    it "should have size == 5" do
       @result.size.should == 5
     end
 
@@ -109,11 +109,11 @@ describe Poliqarp::QueryResult do
   end
 
   describe "(next for 'kot' with page_size set to 5 in :default corpus)" do
-    before(:all) do 
+    before(:all) do
       @result = @client.find("kot", :page_size => 5).next_page
     end
 
-    it "should have size == 1" do  
+    it "should have size == 1" do
       @result.size.should == 1
     end
 

metadata

@@ -4,9 +4,9 @@ version: !ruby/object:Gem::Version
   prerelease: false
   segments: 
   - 0
+  - 1
   - 0
-  - 8
-  version: 0.0.8
+  version: 0.1.0
 platform: ruby
 authors: 
 - Aleksander Pohl
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-01-12 00:00:00 +01:00
+date: 2011-01-17 00:00:00 +01:00
 default_executable: 
 dependencies: []
 
@@ -32,6 +32,7 @@ files:
 - changelog.txt
 - README.txt
 - lib/poliqarpr.rb
+- lib/poliqarpr/config.rb
 - lib/poliqarpr/exceptions.rb
 - lib/poliqarpr/lemmata.rb
 - lib/poliqarpr/query_result.rb