wlapi 0.0.3

data/lib/wlapi.rb

@@ -0,0 +1,263 @@
+# 2010-, Andrei Beliankou
+# Version: 0.3
+# :title: Ruby based API for Wortschatz Leipzig web services
+
+
+# SAVON is a SOAP client.
+require 'savon'
+
+# REXML is fast enough for our task.
+require 'rexml/document'
+include REXML
+
+# This class represents an interface to the linguistic web services
+# provided by the University of Leipzig.
+#
+# See the project 'Wortschatz Leipzig' for more details.
+module WLAPI
+  
+  class API
+    
+    # At the creation point clients for all services are being instantiated.
+    # You can also set the login and the password (it defaults to 'anonymous').
+    def initialize(login = 'anonymous', pass = 'anonymous')
+      # This hash contains the URLs to the single services.
+      @services = {
+        'Thesaurus' => 'http://wortschatz.uni-leipzig.de/axis/services/Thesaurus',
+        'Baseform' => 'http://wortschatz.uni-leipzig.de/axis/services/Baseform',
+        'Similarity' => 'http://wortschatz.uni-leipzig.de/axis/services/Similarity',
+        'Synonyms' => 'http://wortschatz.uni-leipzig.de/axis/services/Synonyms',
+        'Sachgebiet' => 'http://wortschatz.uni-leipzig.de/axis/services/Sachgebiet',
+        'Frequencies' => 'http://wortschatz.uni-leipzig.de/axis/services/Frequencies',
+        'Kookurrenzschnitt' => 'http://wortschatz.uni-leipzig.de/axis/services/Kookkurrenzschnitt',
+        'ExperimentalSynonyms' => 'http://wortschatz.uni-leipzig.de/axis/services/ExperimentalSynonyms',
+        'RightCollocationFinder' => 'http://wortschatz.uni-leipzig.de/axis/services/RightCollocationFinder',
+        'LeftCollocationFinder' => 'http://wortschatz.uni-leipzig.de/axis/services/LeftCollocationFinder',
+        'Wordforms' => 'http://wortschatz.uni-leipzig.de/axis/services/Wordforms',
+        'CooccurrencesAll' => 'http://wortschatz.uni-leipzig.de/axis/services/CooccurrencesAll',
+        'LeftNeighbours' => 'http://wortschatz.uni-leipzig.de/axis/services/LeftNeighbours',
+        'RightNeighbours' => 'http://wortschatz.uni-leipzig.de/axis/services/RightNeighbours',
+        'Sentences' => 'http://wortschatz.uni-leipzig.de/axis/services/Sentences',
+        'Cooccurrences' => 'http://wortschatz.uni-leipzig.de/axis/services/Cooccurrences'
+        # no MARSService and Kreuzwortrraetsel
+      }
+      
+      # cl short for client.
+      # Dynamically create all the clients and set access credentials.
+      # It can be a very bad idea to instantiate all the clients at once,
+      # we should investigate the typical user behaviour.
+      # If only one service is used in the separate session => rewrite the class!
+      @services.each do |key, val|
+        cl_name = '@cl_' + key
+        eval("#{cl_name} = Savon::Client.new(val)")
+        eval("#{cl_name}.request.basic_auth(login, pass)")
+      end
+      
+      # Savon creates very verbose logs, switching off.
+      Savon::Request.log = false unless $DEBUG
+    end
+    
+    # Main methods to access different services.
+    #
+    # You can define the limit for the result set, it defaults to 10.
+    # If you want to get all the results, you should provide a number,
+    # which would be greater than the result set since we cannot
+    # predict how many answers the server will give us. Just try it.
+    ##############################################################################
+    
+    ## One parameter methods.
+    ##############################################################################
+    
+    # Returns the frequency and frequency class of the input word.
+    # Frequency class is computed in relation to the most frequent word
+    # in the corpus. The higher the class, the rarer the word.
+    def frequencies
+      raise 'Not implemented yet!'
+    end
+    
+    # This method gets the baseform (whatever it is :) not lemma).
+    # Returns the lemmatized (base) form of the input word.
+    def baseform
+      raise 'Not implemented yet!'
+    end
+    
+    # Returns categories for a given input word.
+    # --
+    # Is it a good name? all names are in English, but here...
+    def sachgebiet
+      raise 'Not implemented yet!'
+    end
+    
+    ## Two parameter methods.
+    ##############################################################################
+    
+    # Returns all other word forms of the same lemma for a given word form .
+    # --
+    # malformed soap, investigate!!!
+    # doesn't function
+    def wordforms(word, limit)
+      raise 'Not implemented yet!' # remove later
+      answer = query(word, limit, @cl_Wordforms, @services['Wordforms'])
+      return get_answer(answer)
+    end
+    
+    # As the Synonyms service returns synonyms of the given input word.
+    # However, this first builds a lemma of the input word
+    # and thus returns more synonyms.
+    def thesaurus(word, limit = 10)
+      answer = query(word, limit, @cl_Thesaurus, @services['Thesaurus'])
+      return get_answer(answer)
+    end
+    
+    # This method searches for synonyms.
+    # Returns synonyms of the input word. In other words, this is a thesaurus.
+    def synonyms(word, limit = 10)
+      answer = query(word, limit, @cl_Synonyms, @services['Synonyms'])
+      # Synonym service provide multiple values, so we take only odd. 
+      return get_answer(answer, '[position() mod 2 = 1 ]')
+    end
+    
+    # ok, but results should be filtered
+    # Returns sample sentences containing the input word.
+    def sentences(word, limit)
+      answer = query(word, limit, @cl_Sentences, @services['Sentences'])
+      return get_answer(answer)
+    end
+    
+    # For a given input word, returns statistically significant left neighbours
+    # (words co-occurring immediately to the left of the input word).
+    # --
+    # ok, but results should be filtered
+    def left_neighbours(word, limit)
+      answer = query(word, limit, @cl_LeftNeighbours, @services['LeftNeighbours'])
+      return get_answer(answer)
+    end
+    
+    # For a given input word, returns statistically significant right neighbours
+    # (words co-occurring immediately to the right of the input word).
+    # --
+    # ok, but results should be filtered
+    def right_neighbours(word, limit)
+      answer = query(word, limit, @cl_RightNeighbours, @services['RightNeighbours'])
+      return get_answer(answer)
+    end
+    
+    
+    # Returns automatically computed contextually similar words of the input word.
+    # Such similar words may be antonyms, hyperonyms, synonyms,
+    # cohyponyms or other.
+    # Note that due to the huge amount of data any query to this services
+    # may take a long time.
+    def similarity
+      raise 'Not implemented yet!'
+    end
+    
+    # This service delivers an experimental synonyms request for internal tests.
+    # --
+    # don't know, if we have to include this service...
+    def experimental_synonyms
+      raise 'Not implemented yet!'
+    end
+    
+    ## Three parameter methods.
+    ##############################################################################
+    
+    # Attempts to find linguistic collocations that occur to the right
+    # of the given input word.
+    # The parameter Wortart accepts four values A,V,N,S which stand for adjective,
+    # verb, noun and stopword, respectively.
+    # The parameter restricts the type of words found. 
+    def right_collocation_finder
+      raise 'Not implemented yet!'
+    end
+    
+    # Attempts to find linguistic collocations that occur to the left
+    # of the given input word.
+    # The parameter Wortart accepts four values A,V,N,S which stand for adjective,
+    # verb, noun and stopword, respectively.
+    # The parameter restricts the type of words found.
+    def left_collocation_finder
+      raise 'Not implemented yet!'
+    end
+    
+    # Returns statistically significant co-occurrences of the input word.
+    def cooccurrences
+      raise 'Not implemented yet!'
+    end
+    
+    # Returns statistically significant co-occurrences of the input word.
+    # However, it searches in the unrestricted version of the co-occurrences table
+    # as in the Cooccurrences services,
+    # which means significantly longer wait times.
+    def cooccurrences_all
+      raise 'Not implemented yet!'
+    end
+    
+    # Returns the intersection of the co-occurrences of the two given words.
+    # The result set is ordered according to the sum of the significances
+    # in descending order. Note that due to the join involved,
+    # this make take some time.
+    def kookurrenzschnitt
+      raise 'Not implemented yet!'
+    end
+    
+    private
+    
+    # Main query method, it invokes the soap engine.
+    # This method combines all the data to one SOAP request and gets the answer.
+    # It is not compatible with one and three parameter methods yet.
+    def query(word, limit, cl, namespace)
+      # Calling the action with ! (disables the wsdl query).
+      # wsdl is disabled since calling the server for wsdl can last too long.
+      resp = cl.execute! do |soap|
+        
+        # adding a namespace, wsdl is disabled
+        soap.namespace = namespace
+        
+        body = <<EOF
+<urn:objRequestParameters>
+  <urn:corpus>de</urn:corpus>
+  <urn:parameters>
+    <urn:dataVectors>
+      <dat:dataRow>Wort</dat:dataRow>
+      <dat:dataRow>#{word}</dat:dataRow>
+    </urn:dataVectors>
+    <urn:dataVectors>
+      <dat:dataRow>Limit</dat:dataRow>
+      <dat:dataRow>#{limit}</dat:dataRow>
+    </urn:dataVectors>
+  </urn:parameters>
+</urn:objRequestParameters>
+EOF
+        
+        soap.body = body
+        
+        soap.namespaces['xmlns:soapenv'] = "http://schemas.xmlsoap.org/soap/envelope/"
+        # Every service has a different namespace, but it doesn't matter.
+        soap.namespaces['xmlns:urn'] = "urn:#{namespace.sub(/.+ces\//, '')}"
+        
+        soap.namespaces['xmlns:dat'] = "http://datatypes.webservice.wortschatz.uni_leipzig.de"
+      end
+      
+      doc = Document.new(resp.to_xml)
+      
+      STDERR.puts doc if $DEBUG
+      
+      return doc
+      
+    end
+    
+    # This method extracts valuable data from the XML structure
+    # of the soap respense. It returns an array with extracted xml text nodes
+    # and prints out the same collection in the DEBUG mode.
+    def get_answer(doc, mod='')
+      result = []
+      # The path seems to be weird, but the namespaces change incrementally
+      # in the output, so I don't want to treat it here.
+      # A modifier needed because synonyms service provides duplicate values.
+      XPath.each(doc, "//result/*/*#{mod}") {|el| STDERR.puts el.text} if $DEBUG
+      XPath.each(doc, "//result/*/*#{mod}") {|el| result << el.text}
+      return result
+    end
+  end
+end

data/wlapi.gemspec

@@ -0,0 +1,14 @@
+Gem::Specification.new do |s|
+  s.name = "wlapi"
+  s.summary = "Use different web services by Wortschatz Lepzip Project."
+  s.description = File.read(File.join(File.dirname(__FILE__), 'README'))
+  s.requirements = [ 'Using this gem requires understanding of the linguistic background behind the WL project.' ]
+  s.version = "0.0.3"
+  s.author = "Andrei Beliankou"
+  s.email = "a.belenkow@uni-trier.de"
+  s.homepage = "http://www.uni-trier.de/index.php?id=34451"
+  s.add_dependency('savon')
+  s.platform = Gem::Platform::RUBY
+  s.required_ruby_version = '>=1.8'
+  s.files = Dir['**/**']
+end

metadata

@@ -0,0 +1,127 @@
+--- !ruby/object:Gem::Specification 
+name: wlapi
+version: !ruby/object:Gem::Version 
+  hash: 25
+  prerelease: false
+  segments: 
+  - 0
+  - 0
+  - 3
+  version: 0.0.3
+platform: ruby
+authors: 
+- Andrei Beliankou
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-11-14 00:00:00 +01:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: savon
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id001
+description: |
+  == WLAPI is a simple API for Wortschatz Leipzig project.
+  
+  See RDOC documentation for details.
+  
+  You can find some invokation examples in example/example.rb
+
+email: a.belenkow@uni-trier.de
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- wlapi.gemspec
+- doc/fr_class_index.html
+- doc/classes/WLAPI.html
+- doc/classes/WLAPI/API.src/M000007.html
+- doc/classes/WLAPI/API.src/M000016.html
+- doc/classes/WLAPI/API.src/M000006.html
+- doc/classes/WLAPI/API.src/M000003.html
+- doc/classes/WLAPI/API.src/M000011.html
+- doc/classes/WLAPI/API.src/M000008.html
+- doc/classes/WLAPI/API.src/M000017.html
+- doc/classes/WLAPI/API.src/M000010.html
+- doc/classes/WLAPI/API.src/M000012.html
+- doc/classes/WLAPI/API.src/M000009.html
+- doc/classes/WLAPI/API.src/M000013.html
+- doc/classes/WLAPI/API.src/M000014.html
+- doc/classes/WLAPI/API.src/M000005.html
+- doc/classes/WLAPI/API.src/M000015.html
+- doc/classes/WLAPI/API.src/M000004.html
+- doc/classes/WLAPI/API.src/M000001.html
+- doc/classes/WLAPI/API.src/M000002.html
+- doc/classes/WLAPI/API.html
+- doc/fr_method_index.html
+- doc/rdoc.css
+- doc/index.html
+- doc/fr_file_index.html
+- doc/README.html
+- doc/created.rid
+- doc/rdoc-style.css
+- doc/WLAPI.html
+- doc/INSTALL.html
+- doc/bin/example_rb.html
+- doc/files/example/example_rb.html
+- doc/files/lib/wlapi/wlapi_rb.html
+- doc/LICENSE.html
+- doc/lib/wlapi_rb.html
+- INSTALL
+- LICENSE
+- README
+- example/example.rb~
+- example/example.rb
+- lib/wlapi.rb
+has_rdoc: true
+homepage: http://www.uni-trier.de/index.php?id=34451
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 31
+      segments: 
+      - 1
+      - 8
+      version: "1.8"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: 
+- Using this gem requires understanding of the linguistic background behind the WL project.
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Use different web services by Wortschatz Lepzip Project.
+test_files: []
+