apohllo-poliqarpr 0.0.2 → 0.0.3

data/README.txt

@@ -9,6 +9,8 @@ Poliqarpr is Ruby client for Poliqarp server.
 
 == FEATURES/PROBLEMS:
 
+* built-in pagination of query results
+* support for lemmatization 
 * asynchronous communication is implemented in synchronous manner 
 * only partial implementation of server protocol
 
@@ -38,6 +40,34 @@ Then you can type:
 
 * sudo gem install apohllo-poliqarpr
 
+You can install the optional default corpus (warning: it is distributed under
+different license!):
+
+* sudo gem install apohllo-poliqarpr-corpus
+
+== BASIC USAGE: 
+
+(You need the poliqarpr-corpus to be installed for this to work. See the last
+step of installation process).
+
+Require the gem:
+
+  require 'poliaqarpr'
+
+Create the server client and open default corpus
+
+  client = Poliqarp::Client.new
+  client.open_corpus :default
+
+Query the corpus for given segment
+  
+  result = client.find("kot")
+  result[0].to_s 
+
+Remember to close the client on exit
+  
+  client.close
+
 
 == LICENSE:
  

data/changelog.txt

@@ -1,3 +1,11 @@
+0.0.3
+- the license of the corpus included
+- 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)
+
 0.0.2
 - query result is full blown class
 - source divided into client, excerpt and query resutl

data/lib/poliqarpr/client.rb

@@ -1,6 +1,10 @@
+require 'socket'
 module Poliqarp
+  # Author:: Aleksander Pohl (mailto:apohllo@o2.pl)
+  # License:: MIT License
+  #
+  # This class is the implementation of the Poliqarp server client. 
   class Client
-    DEFAULT_CORPUS = File.join(File.expand_path(File.dirname(__FILE__)),"..", "..", "corpus", "frek")
     ERRORS = {
       1 =>   "Incorrect number of arguments",
       3 =>   "No session opened",
@@ -20,8 +24,22 @@ module Poliqarp
       19 =>   "Invalid session option value",
       20 =>   "Invalid sorting criteria"
     }
+    GROUPS = [:left_context, :left_match, :right_match, :right_context]
+
+    # 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
+
+    # 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
@@ -31,9 +49,22 @@ module Poliqarp
       new_session
     end
 
-    def new_session
+    # A hint about uninstalled default corpus gem
+    def self.const_missing(const)
+      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. 
+    #
+    # Parameters: 
+    # * +port+ - the port on which the poliqarpd server is accepting connections (defaults to 4567)
+    def new_session(port=4567)
       close if @session
-      @socket = TCPSocket.new("localhost",4567)
+      @socket = TCPSocket.new("localhost",port)
       talk "MAKE-SESSION #{@session_name}"
       rcv_sync
       talk("BUFFER-RESIZE #{@buffer_size}")
@@ -43,11 +74,7 @@ module Poliqarp
       self.lemmata = {}
     end
 
-    def talk(msg)
-      puts msg if @debug
-      @socket.puts(msg)
-    end
-
+    # Closes the opened connection to the poliqarpd server.
     def close
       #talk "CLOSE"
       #rcv_sync
@@ -57,43 +84,88 @@ module Poliqarp
       @session = false
     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 value.is_a? Fixnum
+      if correct_context_value?(value) 
         talk "SET left-context-width #{value}" 
         result = rcv_sync 
         @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 value.is_a? Fixnum
+      if correct_context_value?(value)
         talk "SET right-context-width #{value}"     
         result = rcv_sync 
         @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 = ""
-      [:left_context_tags, :leftM_tags, 
-        :rightM_tags, :right_context_tags].each do |flag|
+      GROUPS.each do |flag|
         flags << (options[flag] ? "1" : "0")
         end
       talk "SET retrieve-tags #{flags}"
       rcv_sync
     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 = ""
-      [:left_context_lemmata, :leftM_lemmata, 
-        :rightM_lemmata, :right_context_lemmata].each do |flag|
+      GROUPS.each do |flag|
         flags << (options[flag] ? "1" : "0")
         end
       talk "SET retrieve-lemmata #{flags}"
       rcv_sync
     end
 
-
+    # Opens the corpus given as +path+. To open the default
+    # corpus pass +:default+ as the argument. 
     def open_corpus(path)
       if path == :default
         open_corpus(DEFAULT_CORPUS)
@@ -104,6 +176,19 @@ module Poliqarp
       end
     end
 
+    # Send the query to the opened corpus.
+    #
+    # 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 
+    #   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. 
+    #   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). 
+    #   It is ignored if the +index+ option is present. Defaults to 1.
     def find(query,options={})
       if options[:index]
         find_one(query, options[:index])
@@ -114,10 +199,13 @@ module Poliqarp
 
     alias query find 
 
+    # Returns the number of results for given query.
     def count(query)
       count_results(make_query(query)) 
     end
 
+    # Returns the long context of the excerpt which is identified by
+    # given (query, index) pair.
     def context(query,index)
       make_query(query)
       result = []
@@ -135,6 +223,8 @@ module Poliqarp
       result
     end
 
+    # Returns the metadata of the excerpt which is identified by
+    # given (query, index) pair.
     def metadata(query, index)
       make_query(query)
       result = {}
@@ -152,6 +242,13 @@ module Poliqarp
     end
 
 protected
+    # Sends a message directly to the server
+    # * +msg+ the message to send
+    def talk(msg)
+      puts msg if @debug
+      @socket.puts(msg)
+    end
+
     def find_many(query, options)
       page_size = (options[:page_size] || 0)
       page_index = (options[:page_index] || 1)
@@ -193,29 +290,45 @@ protected
     end
 
     # Fetches one result of the query
-    #
+    ##
     # MAKE-QUERY and GET-RESULTS must be called on server before 
     # this method is called
     def fetch_result(index, query)
       result = Excerpt.new(index, self, query)
-      # left_context
-      result << read_segments
-      # matched query
-      result << read_segments
-      # right context
-      result << read_segments
+      result << read_segments(:left_context)
+      result << read_segments(:left_match)
+      # XXX
+      #result << read_segments(:right_match)
+      result << read_segments(:right_context)
 
       result
     end
 
-    def read_segments
-      answer = rcv_sync
-      size = answer.match(/\d+/)[0].to_i
+    def read_segments(group)
+      size = get_number(rcv_sync)
       segments = []
       size.times do |segment_index|
-        segments << read_word
+        segment = Segment.new(read_word)
+        segments << segment 
+        if @lemmata_flags[group] || @tag_flags[group]
+          lemmata_size = get_number(rcv_sync)
+          lemmata_size.times do |lemmata_index| 
+            lemmata = Lemmata.new()
+            if @lemmata_flags[group]
+              lemmata.base_form = read_word
+            end
+            if @tag_flags[group]
+              read_word
+            end
+            segment.lemmata << lemmata
+          end
+        end
       end
-      segments.join("")
+      segments
+    end
+
+    def get_number(str)
+      str.match(/\d+/)[0].to_i
     end
 
     def count_results(answer)
@@ -268,5 +381,16 @@ protected
       end until line =~ /^M/
       line
     end
+
+private 
+    def set_all_flags
+      options = {}
+      GROUPS.each{|g| options[g] = true}
+      options
+    end
+    
+    def correct_context_value?(value)
+      value.is_a?(Fixnum) && value > 0
+    end
   end 
 end

data/lib/poliqarpr/excerpt.rb

@@ -1,4 +1,15 @@
 module Poliqarp
+  # Author:: Aleksander Pohl
+  # License:: MIT License
+  #
+  # 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 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 
+  # query, and the last -- the right context.
   class Excerpt
     attr_reader :index, :base_form, :short_context
 
@@ -9,11 +20,13 @@ module Poliqarp
       @short_context = []
     end
 
+    # Adds segment group to the excerpt
     def <<(value)
       @short_context << value
     end
 
 
+    # Returns the matched query as string 
     def word
       #@short_context[0].split(/\s+/)[-1]
       @short_context[1].to_s
@@ -21,10 +34,13 @@ module Poliqarp
 
     alias inflected_form word
 
+    # The string representation of the excerpt is the shord
+    # context of the query.
     def to_s
       @short_context.join("")
     end
 
+    # Returns the long context of the query. 
     def context
       return @context unless @context.nil?
       @context = @client.context(@base_form, @index)

data/lib/poliqarpr/lemmata.rb

@@ -0,0 +1,11 @@
+module Poliqarp
+  # Author:: Aleksander Pohl (mailto:apohllo@o2.pl)
+  # License:: MIT License
+  #
+  # The lemmata contains the base form of the segment
+  class Lemmata
+    attr_accessor :base_form
+    def initialize()
+    end
+  end
+end

data/lib/poliqarpr/query_result.rb

@@ -1,4 +1,10 @@
 module Poliqarp
+  # Author:: Aleksander Pohl (mailto:apohllo@o2.pl)
+  # License:: MIT License
+  #
+  # 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). 
   class QueryResult
     include Enumerable
 
@@ -13,10 +19,12 @@ module Poliqarp
       @excerpts = []
     end
 
+    # Adds excerpt to the query result
     def <<(excerpt)
       @excerpts << excerpt
     end
 
+    # Allows to iterate over the results stored in the result
     def each
       @excerpts.each{|e| yield e}
     end
@@ -27,16 +35,20 @@ module Poliqarp
       end
     end
 
+    # Returns excerpt with given index.
     def [](index)
       @excerpts[index]
     end
 
+    # Two excerpts are equal iff their page number, page count,
+    # query and page size are equal.
     def ==(other)
       return false unless other.is_a? QueryResult
       @page == other.page && @page_count == other.page_count &&
         @query == other.query && @page_size == other.page_size
     end
 
+    # Returns the previous page of the query result
     def previous_page
       if @page > 1
         @client.find(@query, :page_size => @page_size, 
@@ -44,6 +56,7 @@ module Poliqarp
       end
     end
 
+    # Return the next page of the query result
     def next_page
       if @page < @page_count
         @client.find(@query, :page_size => @page_size, 
@@ -51,6 +64,7 @@ module Poliqarp
       end
     end
 
+    # Returns the number of excerpts stored in this page (query result)
     def size
       @excerpts.size
     end

data/lib/poliqarpr/segment.rb

@@ -0,0 +1,23 @@
+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. 
+  class Segment
+    attr_reader :literal, :lemmata
+
+    # 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 
+      @literal
+    end
+  end
+end

data/lib/poliqarpr.rb

@@ -2,4 +2,10 @@ path = File.join(File.dirname(__FILE__), 'poliqarpr')
 require File.join(path, 'client')
 require File.join(path, 'query_result')
 require File.join(path, 'excerpt')
-
+require File.join(path, 'segment')
+require File.join(path, 'lemmata')
+begin
+  require 'poliqarpr-corpus' 
+rescue LoadError
+  # Do nothig, since the default corpus is optional
+end

data/poliqarpr.gemspec

@@ -1,9 +1,7 @@
-#require 'rake'
-
 Gem::Specification.new do |s|
   s.name = "poliqarpr"
-  s.version = "0.0.2"
-  s.date = "2008-12-15"
+  s.version = "0.0.3"
+  s.date = "2008-12-20"
   s.summary = "Ruby client for Poliqarp"
   s.email = "apohllo@o2.pl"
   s.homepage = "http://www.apohllo.pl/projekty/poliqarpr"
@@ -14,42 +12,9 @@ Gem::Specification.new do |s|
     "lib/poliqarpr/client.rb", 
     "lib/poliqarpr/query_result.rb", 
     "lib/poliqarpr/excerpt.rb", 
+    "lib/poliqarpr/lemmata.rb", 
+    "lib/poliqarpr/segment.rb", 
     "README.txt",
-    "corpus/frek.cdf",
-    "corpus/frek.poliqarp.base1.image",
-    "corpus/frek.poliqarp.corpus.image",
-    "corpus/frek.poliqarp.meta-value.offset",
-    "corpus/frek.poliqarp.rindex.amb",
-    "corpus/frek.poliqarp.rindex.orth.offset",
-    "corpus/frek.poliqarp.subpos1.offset",
-    "corpus/frek.cfg",
-    "corpus/frek.poliqarp.base1.offset",
-    "corpus/frek.poliqarp.meta.image",
-    "corpus/frek.poliqarp.orth.image",
-    "corpus/frek.poliqarp.rindex.amb.offset",
-    "corpus/frek.poliqarp.subchunk.image",
-    "corpus/frek.poliqarp.subpos2.image",
-    "corpus/frek.cfg~",
-    "corpus/frek.poliqarp.base2.image",
-    "corpus/frek.poliqarp.meta-key.image",
-    "corpus/frek.poliqarp.orth.index.alpha",
-    "corpus/frek.poliqarp.rindex.disamb",
-    "corpus/frek.poliqarp.subchunk.item.ch",
-    "corpus/frek.poliqarp.subpos2.offset",
-    "corpus/frek.meta.cfg",
-    "corpus/frek.poliqarp.base2.offset",
-    "corpus/frek.poliqarp.meta-key.offset",
-    "corpus/frek.poliqarp.orth.index.atergo",
-    "corpus/frek.poliqarp.rindex.disamb.offset",
-    "corpus/frek.poliqarp.subchunk.offset",
-    "corpus/frek.poliqarp.tag.image",
-    "corpus/frek.meta.lisp",
-    "corpus/frek.poliqarp.chunk.image",
-    "corpus/frek.poliqarp.meta-value.image",
-    "corpus/frek.poliqarp.orth.offset",
-    "corpus/frek.poliqarp.rindex.orth",
-    "corpus/frek.poliqarp.subpos1.image",
-    "corpus/frek.poliqarp.tag.offset"
   ]
   s.test_files = [
     "spec/client.rb",

data/spec/client.rb

@@ -29,6 +29,38 @@ describe Poliqarp::Client 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 allow to find 'kot'" do 
       @client.find("kot").size.should_not == 0
     end
@@ -83,6 +115,27 @@ describe Poliqarp::Client 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

@@ -23,8 +23,19 @@ describe Poliqarp::Excerpt do
       @excerpt.base_form.should_not == nil
     end
 
-    it "should allow to add short context" do
-      @excerpt << "abc"
+    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
@@ -92,4 +103,31 @@ describe Poliqarp::Excerpt do
       @excerpt.author[0].should == "Małgorzata Pamuła"
     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

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: apohllo-poliqarpr
 version: !ruby/object:Gem::Version 
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors: 
 - Aleksander Pohl
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2008-12-15 00:00:00 -08:00
+date: 2008-12-20 00:00:00 -08:00
 default_executable: 
 dependencies: []
 
@@ -29,42 +29,9 @@ files:
 - lib/poliqarpr/client.rb
 - lib/poliqarpr/query_result.rb
 - lib/poliqarpr/excerpt.rb
+- lib/poliqarpr/lemmata.rb
+- lib/poliqarpr/segment.rb
 - README.txt
-- corpus/frek.cdf
-- corpus/frek.poliqarp.base1.image
-- corpus/frek.poliqarp.corpus.image
-- corpus/frek.poliqarp.meta-value.offset
-- corpus/frek.poliqarp.rindex.amb
-- corpus/frek.poliqarp.rindex.orth.offset
-- corpus/frek.poliqarp.subpos1.offset
-- corpus/frek.cfg
-- corpus/frek.poliqarp.base1.offset
-- corpus/frek.poliqarp.meta.image
-- corpus/frek.poliqarp.orth.image
-- corpus/frek.poliqarp.rindex.amb.offset
-- corpus/frek.poliqarp.subchunk.image
-- corpus/frek.poliqarp.subpos2.image
-- corpus/frek.cfg~
-- corpus/frek.poliqarp.base2.image
-- corpus/frek.poliqarp.meta-key.image
-- corpus/frek.poliqarp.orth.index.alpha
-- corpus/frek.poliqarp.rindex.disamb
-- corpus/frek.poliqarp.subchunk.item.ch
-- corpus/frek.poliqarp.subpos2.offset
-- corpus/frek.meta.cfg
-- corpus/frek.poliqarp.base2.offset
-- corpus/frek.poliqarp.meta-key.offset
-- corpus/frek.poliqarp.orth.index.atergo
-- corpus/frek.poliqarp.rindex.disamb.offset
-- corpus/frek.poliqarp.subchunk.offset
-- corpus/frek.poliqarp.tag.image
-- corpus/frek.meta.lisp
-- corpus/frek.poliqarp.chunk.image
-- corpus/frek.poliqarp.meta-value.image
-- corpus/frek.poliqarp.orth.offset
-- corpus/frek.poliqarp.rindex.orth
-- corpus/frek.poliqarp.subpos1.image
-- corpus/frek.poliqarp.tag.offset
 has_rdoc: true
 homepage: http://www.apohllo.pl/projekty/poliqarpr
 post_install_message: 

data/corpus/frek.cdf

@@ -1,4 +0,0 @@
-version = 1
-endianness = little-endian
-indices = oda
-index-granularity = 1024

data/corpus/frek.cfg

@@ -1,100 +0,0 @@
-# Config file format for Oasis release
-# Config version 1.0
-
-# The new startup section may contain any command normally accepted by the shell
-
-[ALIASES]
-
-masc = m1|m2|m3
-verb = pact|ppas|winien|praet|bedzie|fin|impt|aglt|ger|imps|inf|pant|pcon
-noun = subst|depr|xxs|ger|ppron12|ppron3
-pron = ppron12|ppron3|siebie
-
-
-[ATTR]
-
-number			= sg pl
-case			= nom gen dat acc inst loc voc
-gender			= m1 m2 m3 f n
-person			= pri sec ter
-degree			= pos comp sup
-aspect			= imperf perf
-negation		= aff neg
-accommodability		= congr rec
-accentability		= akc nakc
-post-prepositionality	= npraep praep
-agglutination		= agl nagl
-vocalicity		= nwok wok
-
-# Parts of speech no longer need forward declarations, this was inconvenient and ugly.
-# Also, any attribute may be optional so a declaration such as:
-# foo = [bar] [froz] fred [wilma]
-# should no longer cause problems and ctags with such attributes now parse correctly regardless
-# of presence or absence of any optional attribute
-
-[POS]
-
-adja	=
-adjp	=
-conj	=
-interp	= 
-pred	=
-xxx	=
-adv	= degree
-imps	= aspect
-inf	= aspect
-pant	= aspect
-pcon	= aspect
-qub	= [vocalicity]
-prep	= case [vocalicity]
-siebie	= case
-subst	= number case gender
-depr	= number case gender
-xxs	= number case gender
-ger	= number case gender aspect negation
-ppron12	= number case gender person [accentability]
-ppron3	= number case gender person [accentability] [post-prepositionality]
-num	= number case gender [accommodability]
-adj	= number case gender degree
-pact	= number case gender aspect negation
-ppas	= number case gender aspect negation
-winien	= number gender aspect
-praet	= number gender aspect [agglutination]
-bedzie	= number person aspect
-fin	= number person aspect
-impt	= number person aspect
-aglt	= number person aspect vocalicity
-ign     =
-
-# Named entities replaced old 'special' attributes, name changed mostly because of
-# unification of 'named-thing' handling code into one named-entity thing
-# Entity aliasing allows for any existing entity to be seen under different name
-#
-# FCQP provides four builtin entities:
-#    entity-current
-#    entity-base
-#    entity-tag
-#    entity-pos
-
-[NAMED-ENTITY]
-
-entity-orth		= orth
-entity-base		= base
-entity-tag		= tag
-entity-pos		= pos
-
-# Old 'aliases' for attribute names
-
-pos			= flex
-number			= numb nmb
-case			= cas
-gender			= gnd gend
-person			= per pers
-degree			= deg degr
-aspect			= asp
-negation		= neg
-accommodability		= acco acom acm
-accentability		= acce acen acn
-post-prepositionality	= ppr ppre
-agglutination		= agg aggl
-vocalicity		= vcl

data/corpus/frek.cfg~

@@ -1,100 +0,0 @@
-# Config file format for Oasis release
-# Config version 1.0
-
-# The new startup section may contain any command normally accepted by the shell
-
-[STARTUP]
-
-/alias masc = m1 m2 m3
-/alias verb = pact ppas winien praet bedzie fin impt aglt ger imps inf pant pcon 
-/alias noun = subst depr xxs ger ppron12 ppron3
-/alias pron = ppron12 ppron3 siebie
-
-
-[ATTR]
-
-number			= sg pl
-case			= nom gen dat acc inst loc voc
-gender			= m1 m2 m3 f n
-person			= pri sec ter
-degree			= pos comp sup
-aspect			= imperf perf
-negation		= aff neg
-accommodability		= congr rec
-accentability		= akc nakc
-post-prepositionality	= npraep praep
-agglutination		= agl nagl
-vocalicity		= nwok wok
-
-# Parts of speech no longer need forward declarations, this was inconvenient and ugly.
-# Also, any attribute may be optional so a declaration such as:
-# foo = [bar] [froz] fred [wilma]
-# should no longer cause problems and ctags with such attributes now parse correctly regardless
-# of presence or absence of any optional attribute
-
-[POS]
-
-adja	=
-adjp	=
-conj	=
-interp	= 
-pred	=
-xxx	=
-adv	= degree
-imps	= aspect
-inf	= aspect
-pant	= aspect
-pcon	= aspect
-qub	= [vocalicity]
-prep	= case [vocalicity]
-siebie	= case
-subst	= number case gender
-depr	= number case gender
-xxs	= number case gender
-ger	= number case gender aspect negation
-ppron12	= number case gender person [accentability]
-ppron3	= number case gender person [accentability] [post-prepositionality]
-num	= number case gender [accommodability]
-adj	= number case gender degree
-pact	= number case gender aspect negation
-ppas	= number case gender aspect negation
-winien	= number gender aspect
-praet	= number gender aspect [agglutination]
-bedzie	= number person aspect
-fin	= number person aspect
-impt	= number person aspect
-aglt	= number person aspect vocalicity
-ign     =
-
-# Named entities replaced old 'special' attributes, name changed mostly because of
-# unification of 'named-thing' handling code into one named-entity thing
-# Entity aliasing allows for any existing entity to be seen under different name
-#
-# FCQP provides four builtin entities:
-#    entity-current
-#    entity-base
-#    entity-tag
-#    entity-pos
-
-[NAMED-ENTITY]
-
-entity-orth		= orth
-entity-base		= base
-entity-tag		= tag
-entity-pos		= pos
-
-# Old 'aliases' for attribute names
-
-pos			= flex
-number			= numb nmb
-case			= cas
-gender			= gnd gend
-person			= per pers
-degree			= deg degr
-aspect			= asp
-negation		= neg
-accommodability		= acco acom acm
-accentability		= acce acen acn
-post-prepositionality	= ppr ppre
-agglutination		= agg aggl
-vocalicity		= vcl

data/corpus/frek.meta.cfg

@@ -1 +0,0 @@
-S sample

data/corpus/frek.meta.lisp

@@ -1,4 +0,0 @@
-(single	"sample"
-        "/cesHeader/fileDesc/(sourceDesc/biblFull/)*sourceDesc/biblStruct/monogr/h.title")
-
-