opener-property-tagger 2.1.0 → 2.1.1

checksums.yaml

@@ -1,15 +1,7 @@
 ---
-!binary "U0hBMQ==":
-  metadata.gz: !binary |-
-    ZGQzMjM4MjQxZjMyNDkwOGFiNGQ4Njg3MDZiOWE1N2JmZmIxZTY1NQ==
-  data.tar.gz: !binary |-
-    ZTdmYmMwMGViYTc3MDcyOTRjOTQzM2M4MjMyZTU1NDJjMjUxNWNlNg==
+SHA1:
+  metadata.gz: 01266e13df09e19768ca16aba60a5dde22334d38
+  data.tar.gz: 73fa035f1949b9a45efdd28cbe2fa51edf41a418
 SHA512:
-  metadata.gz: !binary |-
-    ODFmOWVlNzNmM2NiNzM4OWNjNmIyZTNhMGEyYWFmMzVhMTBlYzliMzZkNmU2
-    NGVmYmNjNTZhYjZjMDFjNWYzMDhjODE5MWRiMzI1MTg2MTIxODE5ZTBkMWE1
-    N2Y2OWExNWZlOTQzNjEyYmRiZTgzMjUyMjI4Y2U4NTAzODAzNDc=
-  data.tar.gz: !binary |-
-    Y2M2ZWQyMWYyZDhhYjJjOTYwMmQyYWI1ODljNTgxNzU2YTU1YjhkYzQyMmFi
-    MTEzYjg2MzM1Zjk1MzUwMDM5NGRiMmZiMTU3ZWM0MWUwNDNjNzQwYTk4Mjc2
-    MTg1NzhmY2UyMzI3Yjg5ZGVkNmFlZTg0YmRlZTgyODI2MTQyNjA=
+  metadata.gz: c0317a20e5d4aca38d4cdfde47a9911143b024bdab221c00714f81079231093cdf627866744a18a73ab38f278fc8bea451195ba9f7ac928ac19763a5e63c1c38
+  data.tar.gz: c83585d02d72f38cc6f3ebf2386ad6c399772b1e4e094595b1a7b3d3ab3f6918ea53894f4b5dfa6f932053d11b1398ef8e2503e412808e21a367e299cacbd7d3

data/README.md

@@ -11,7 +11,7 @@ the input KAF file, from the lang attribute of the KAF element  (make sure your
 
 This software is part of a larger collection of natural language processing
 tools known as "the OpeNER project". You can find more information about the
-project at (the OpeNER portal)[http://opener-project.github.io]. There you can
+project at the [OpeNER portal](http://opener-project.github.io). There you can
 also find references to terms like KAF (an XML standard to represent linguistic
 annotations in texts), component, cores, scenario's and pipelines.
 
@@ -112,10 +112,8 @@ Description of dependencies
 ---------------------------
 
 This component runs best if you run it in an environment suited for OpeNER
-components. You can find an installation guide and helper tools in the (OpeNER
-installer)[https://github.com/opener-project/opener-installer] and (an
-installation guide on the Opener
-Website)[http://opener-project.github.io/getting-started/how-to/local-installation.html]
+components. You can find an installation guide and helper tools in the [OpeNER installer](https://github.com/opener-project/opener-installer) and an
+[installation guide on the Opener Website](http://opener-project.github.io/getting-started/how-to/local-installation.html)
 
 At least you need the following system setup:
 
@@ -135,11 +133,11 @@ Domain Adaption and Language Extension
 
 The lexicons in the resource path must be stored in a file and follow this format:
 
-````shell
-surf	verb	facilities
-surfer	noun	facilities
-surfing	verb	facilities
-```
+    shell
+    surf	verb	facilities
+    surfer	noun	facilities
+    surfing	verb	facilities
+
 
 So, one aspect per line, with 3 fields separated by a tabulator, the first one is the word or span of words (in this case use whitespaces), then the part
 of speech (which actually it is not use, you can  include a dummy label) and finally the aspect class associated with the word.
@@ -153,21 +151,20 @@ can find the core technolies (python) in the ```/core``` directory.
 Where to go from here
 ---------------------
 
-* Check (the project websitere)[http://opener-project.github.io]
-* (Checkout the webservice)[http://opener.olery.com/property-tagger]
+* [Check the project websitere](http://opener-project.github.io)
+* [Checkout the webservice](http://opener.olery.com/property-tagger)
 
 Report problem/Get help
 -----------------------
 
-If you encounter problems, please email support@opener-project.eu or leave an
-issue in the (issue tracker)[https://github.com/opener-project/property-tagger/issues].
-
+If you encounter problems, please email <support@opener-project.eu> or leave an
+issue in the [issue tracker](https://github.com/opener-project/property-tagger/issues).
 
 Contributing
 ------------
 
-1. Fork it ( http://github.com/opener-project/property-tagger/fork )
-2. Create your feature branch (`git checkout -b my-new-feature`)
+1. Fork it <http://github.com/opener-project/property-tagger/fork>
+2. 2. Create your feature branch (`git checkout -b my-new-feature`)
 3. Commit your changes (`git commit -am 'Add some feature'`)
 4. Push to the branch (`git push origin my-new-feature`)
 5. Create new Pull Request

data/bin/property-tagger-daemon

@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+
+require 'opener/daemons'
+
+exec_path = File.expand_path('../../exec/property-tagger.rb', __FILE__)
+
+Opener::Daemons::Controller.new(
+  :name      => 'property-tagger',
+  :exec_path => exec_path
+)

data/core/hotel_property_tagger_nl_en.py

@@ -10,7 +10,7 @@ this_folder = os.path.dirname(os.path.realpath(__file__))
 
 # This updates the load path to ensure that the local site-packages directory
 # can be used to load packages (e.g. a locally installed copy of lxml).
-sys.path.append(os.path.join(this_folder, 'site-packages/pre_build'))
+sys.path.append(os.path.join(this_folder, 'site-packages/pre_install'))
 
 from VUKafParserPy import KafParser
 from lxml import etree
@@ -48,8 +48,9 @@ def loadAspects(my_lang,this_file=None):
     fic = codecs.open(aspects_filename,'r','utf-8')
     for line in fic:
       fields = line.strip().split('\t')
-      lemma,pos,aspect = fields
-      my_aspects[lemma] = aspect
+      if len(fields) == 3:
+        lemma,pos,aspect = fields
+        my_aspects[lemma] = aspect
     fic.close()
   return aspects_filename, my_aspects
 ########################################

data/exec/property-tagger.rb

@@ -0,0 +1,9 @@
+#!/usr/bin/env ruby
+
+require 'opener/daemons'
+require_relative '../lib/opener/property_tagger'
+
+options = Opener::Daemons::OptParser.parse!(ARGV)
+daemon  = Opener::Daemons::Daemon.new(Opener::PropertyTagger, options)
+
+daemon.start

data/lib/opener/property_tagger/version.rb

@@ -1,5 +1,5 @@
 module Opener
   class PropertyTagger
-    VERSION = '2.1.0'
+    VERSION = '2.1.1'
   end # PropertyTagger
 end # Opener

data/opener-property-tagger.gemspec

@@ -20,18 +20,20 @@ Gem::Specification.new do |gem|
     'config.ru',
     '*.gemspec',
     '*_requirements.txt',
-    'README.md'
+    'README.md',
+    'exec/**/*'
   ]).select { |file| File.file?(file) }
 
   gem.executables = Dir.glob('bin/*').map { |file| File.basename(file) }
 
-  gem.add_dependency 'opener-build-tools', ['>= 0.2.7']
+  gem.add_dependency 'opener-build-tools', ['>= 1.0.1']
   gem.add_dependency 'rake'
   gem.add_dependency 'sinatra'
   gem.add_dependency 'httpclient'
   gem.add_dependency 'puma'
+  gem.add_dependency 'opener-daemons'
   gem.add_dependency 'opener-webservice'
-  gem.add_dependency 'opener-core'
+  gem.add_dependency 'opener-core', ['>= 0.1.2']
 
   gem.add_development_dependency 'rspec'
   gem.add_development_dependency 'cucumber'

metadata

@@ -1,175 +1,184 @@
 --- !ruby/object:Gem::Specification
 name: opener-property-tagger
 version: !ruby/object:Gem::Version
-  version: 2.1.0
+  version: 2.1.1
 platform: ruby
 authors:
 - development@olery.com
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-05-21 00:00:00.000000000 Z
+date: 2014-05-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: opener-build-tools
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.7
+        version: 1.0.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.7
+        version: 1.0.1
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: sinatra
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: httpclient
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: puma
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: opener-webservice
+  name: opener-daemons
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: opener-core
+  name: opener-webservice
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: opener-core
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.1.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.1.2
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: cucumber
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 description: Property tagger for hotels in Dutch and English.
 email: 
 executables:
 - property-tagger
+- property-tagger-daemon
 - property-tagger-server
 extensions:
 - ext/hack/Rakefile
 extra_rdoc_files: []
 files:
-- core/site-packages/pre_build/VUKafParserPy/__init__.py
-- core/site-packages/pre_build/VUKafParserPy/KafDataObjectsMod.py
-- core/site-packages/pre_build/VUKafParserPy/KafParserMod.py
-- core/site-packages/pre_build/VUKafParserPy-1.0-py2.7.egg-info/dependency_links.txt
-- core/site-packages/pre_build/VUKafParserPy-1.0-py2.7.egg-info/installed-files.txt
-- core/site-packages/pre_build/VUKafParserPy-1.0-py2.7.egg-info/PKG-INFO
-- core/site-packages/pre_build/VUKafParserPy-1.0-py2.7.egg-info/SOURCES.txt
-- core/site-packages/pre_build/VUKafParserPy-1.0-py2.7.egg-info/top_level.txt
+- README.md
+- bin/property-tagger
+- bin/property-tagger-daemon
+- bin/property-tagger-server
+- config.ru
 - core/extract_aspects.py
 - core/hotel_property_tagger_nl_en.py
+- exec/property-tagger.rb
 - ext/hack/Rakefile
 - ext/hack/support.rb
+- lib/opener/property_tagger.rb
 - lib/opener/property_tagger/cli.rb
 - lib/opener/property_tagger/public/markdown.css
 - lib/opener/property_tagger/server.rb
 - lib/opener/property_tagger/version.rb
 - lib/opener/property_tagger/views/index.erb
 - lib/opener/property_tagger/views/result.erb
-- lib/opener/property_tagger.rb
-- config.ru
 - opener-property-tagger.gemspec
 - pre_install_requirements.txt
-- README.md
-- bin/property-tagger
-- bin/property-tagger-server
 homepage: http://opener-project.github.com/
 licenses: []
 metadata: {}
@@ -179,18 +188,19 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: 1.9.2
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.1.11
+rubygems_version: 2.2.2
 signing_key: 
 specification_version: 4
 summary: Property tagger for hotels in Dutch and English.
 test_files: []
+has_rdoc: 

data/core/site-packages/pre_build/VUKafParserPy/KafDataObjectsMod.py

@@ -1,165 +0,0 @@
-class KafTermSentiment:
-  def __init__(self):
-    self.resource=None
-    self.polarity=None
-    self.strength=None
-    self.subjectivity=None
-    
-  def simpleInit(self,r,p,st,su,sm=None):
-    self.resource=r
-    self.polarity=p
-    self.strength=st
-    self.subjectivity=su
-    self.sentiment_modifier = sm
-    
-  def getPolarity(self):
-    return self.polarity
-  
-  def getSentimentModifier(self):
-    return self.sentiment_modifier
-    
-    
-class KafToken:
-  def __init__(self,wid, value, sent=None, para=None):
-    self.token_id = wid
-    self.value = value
-    self.sent = sent
-    self.para = para
-  
-
-class KafOpinionExpression:
-  def __init__(self,polarity,strength,targets):
-    self.polarity = polarity
-    self.strength = strength
-    self.targets = targets
-    
-  def __str__(self):
-    return 'Op_exp==> pol:'+self.polarity+' Str:'+self.strength+' ids:'+'-'.join(self.targets)
-    
-class KafOpinion:
-  def __init__(self,id,holders, targets, opi_exp):
-    self.id = id
-    self.holders = holders
-    self.targets = targets
-    self.opi_exp = opi_exp
-    
-  def __str__(self):
-    c='Opinion id'+self.id+'\n'
-    c+='  Holders: '+'-'.join(self.holders)+'\n'
-    c+='  Targets: '+'-'.join(self.targets)+'\n'
-    c+=str(self.opi_exp)
-    return c
-    
-    
-
-class KafSingleProperty:
-  def __init__(self,id,type,targets):
-    self.id = id
-    self.type = type
-    self.targets = targets
-    
-    
-  def get_id(self):
-    return self.id
-    
-  def get_type(self):
-    return self.type
-  
-  def get_span(self):
-    return self.targets
-  
-  def __str__(self):
-    return 'Id: '+self.id+' Type: '+self.type+' ids:'+' '.join(self.targets)
-
-
-class KafSingleEntity:
-  def __init__(self,id,type,targets):
-    self.id = id
-    self.type = type
-    self.targets = targets
-    
-  def get_id(self):
-    return self.id
-    
-  def get_type(self):
-    return self.type
-  
-  def get_span(self):
-    return self.targets
-  
-  def __str__(self):
-    return 'Id: '+self.id+' Type: '+self.type+' ids:'+' '.join(self.targets)
-
-class KafTerm:
-  def __init__(self):
-    self.tid = None
-    self.lemma = None
-    self.pos = None
-    self.morphofeat = None
-    self.sentiment = None
-    self.list_span_id = []
-    
-  def get_morphofeat(self):
-    return self.morphofeat
-    
-  def set_list_span_id(self, L):
-    self.list_span_id = L
-    
-  def get_list_span(self):
-    return self.list_span_id
-    
-  def get_polarity(self):
-    if self.sentiment != None:
-      return self.sentiment.getPolarity()
-    else:
-      return None
-      
-  def get_sentiment_modifier(self):
-    if self.sentiment != None:
-      return self.sentiment.getSentimentModifier()
-    else:
-      return None
-    
-    
-  def setSentiment(self,my_sent):
-    self.sentiment = my_sent
-    
-  def getSentiment(self):
-    return self.sentiment
-    
-  def getLemma(self): 
-      return self.lemma
-    
-  def setLemma(self,lemma):
-      self.lemma = lemma
-    
-  def getPos(self):
-      return self.pos
-    
-  def setPos(self,pos):
-      self.pos = pos
-      
-  def getId(self):
-      return self.tid
-      
-  def setId(self,id):
-      self.tid = id
-
-  def getShortPos(self):
-    if self.pos==None:
-      return None
-    auxpos=self.pos.lower()[0]
-    if auxpos == 'g': auxpos='a'
-    elif auxpos == 'a': auxpos='r'
-    return auxpos
-    
-  def __str__(self):
-    if self.tid and self.lemma and self.pos:
-        return self.tid+'\n\t'+self.lemma.encode('utf-8')+'\n\t'+self.pos
-    else:
-        return 'None'
-      
-    
-    
-    
-    

data/core/site-packages/pre_build/VUKafParserPy/KafParserMod.py

@@ -1,439 +0,0 @@
-########################################################################
-# 14 Jan 2013: added function add_attrs_to_layer
-########################################################################
-
-###################
-# List of changes #
-###################
-# 14 Jan 2013: added function add_attrs_to_layer
-# 27 Feb 2013: added code for comply with DTD
-# 18 Jun 2013: getSingleProperties adapted to the structure KAF/features/properties/property/references/span/target
-# 18 Jun 2013: funcion add_property created for adding the properties to the KAF
-
-
-from lxml import etree
-from KafDataObjectsMod import *
-import time
-
-class KafParser:
-  def __init__(self,filename=None):
-	self.tree=None
-	self.__pathForToken={}
-	self.__term_ids_for_token_id = None
-    
-	if filename:
-		#self.tree = etree.parse(filename,etree.XMLParser(remove_blank_text=True))
-		self.tree = etree.parse(filename,etree.XMLParser(remove_blank_text=True, strip_cdata=False))
-		## Do the text tokenization
-		self.__textTokenization()
-	else:
-		root = etree.Element('KAF')
-		root.set('version','v1.opener')
-		root.set('{http://www.w3.org/XML/1998/namespace}lang','en')
-		self.tree = etree.ElementTree(element=root)
-		
-  def __textTokenization(self):
-	for wf in self.tree.findall('text/wf'):
-	  wid = wf.get('wid')
-	  self.__pathForToken[wid] = self.tree.getpath(wf)
-	 
-  
-  def getToken(self,tid):
-      if tid in self.__pathForToken:
-          path = self.__pathForToken[tid]
-          return self.tree.xpath(self.__pathForToken[tid])[0]
-      return None
-
-  
-  def getLanguage(self):
-	  lang = self.tree.getroot().get('{http://www.w3.org/XML/1998/namespace}lang','nl')
-	  return lang
-	  
-  ## Return a list of (sentence_id, TOKENS) where tokens is a list of (token_id,token)
-  ## [(s_id1, T1), (sent_id2, T2)....]
-  ## T1 --> [(tokenid, token), (tokenid2,token2)....]
-  def get_tokens_in_sentences(self):
-      sents = []
-      current = []
-      previous_sent = None
-      for element in self.tree.findall('text/wf'):
-          w_id = element.get('wid')
-          s_id = element.get('sent')
-          word = element.text
-          
-          if previous_sent is not None and s_id != previous_sent:
-              sents.append((previous_sent,current))
-              current = []
-          current.append((w_id,word))
-          previous_sent = s_id
-      ####
-      sents.append((s_id,current)) 
-      return sents
-  
-  def get_term_ids_for_token_id(self,tok_id):
-      if self.__term_ids_for_token_id is None:
-          self.__term_ids_for_token_id = {}
-          for element in self.tree.findall('terms/term'):
-              term_id = element.get('tid')
-              for target in element.findall('span/target'):
-                  token_id = target.get('id')
-                  if token_id not in self.__term_ids_for_token_id:
-                      self.__term_ids_for_token_id[token_id] = [term_id]
-                  else:
-                      self.__term_ids_for_token_id[token_id].append(term_id)
-      return self.__term_ids_for_token_id.get(tok_id,[])
-  
-          
-      
-  def getTokens(self):
-	for element in self.tree.findall('text/wf'):
-	  w_id = element.get('wid')
-	  s_id = element.get('sent','0')
-	  word = element.text
-	  yield (word, s_id, w_id)
-	
-    
-    
-  def getTerms(self):
-	 if self.tree:
-	   for element in self.tree.findall('terms/term'):
-		   kafTermObj = KafTerm()
-		   kafTermObj.setId(element.get('tid'))
-		   kafTermObj.setLemma(element.get('lemma'))
-		   kafTermObj.setPos(element.get('pos'))
-		   kafTermObj.morphofeat = element.get('morphofeat')
-		   		   
-		   ## Parsing sentiment
-		   sentiment = element.find('sentiment')
-		   if sentiment is not None:
-			 resource = sentiment.get('resource','')
-			 polarity = sentiment.get('polarity',None)
-			 strength = sentiment.get('strength','')
-			 subjectivity = sentiment.get('subjectivity','')
-			 sentiment_modifier = sentiment.get('sentiment_modifier')
-			 
-			 my_sent = KafTermSentiment()
-			 my_sent.simpleInit(resource,polarity,strength,subjectivity,sentiment_modifier)
-			 kafTermObj.setSentiment(my_sent)
-		  
-		   ## Parsing the span
-		   span = element.find('span')
-		   if span is not None:
-			list_ids = [target.get('id') for target in span.findall('target')]
-			kafTermObj.set_list_span_id(list_ids)
-		
-			 
-		   yield kafTermObj
-	 else:
-	   return
-	  
-	  
-  def getSentimentTriples(self):
-	data = []
-	if self.tree:
-	  for term_element in self.tree.findall('terms/term'):
-		lemma = term_element.get('lemma')
-		polarity = None
-		sentiment_modifier = None
-		
-		sentiment_element = term_element.find('sentiment')
-		if sentiment_element is not None:
-			polarity = sentiment_element.get('polarity',None)
-			sentiment_modifier = sentiment_element.get('sentiment_modifier')
-		data.append( (lemma,polarity,sentiment_modifier))
-	return data
-	  
-   
-	  
-  def addPolarityToTerm(self,termid,my_sentiment_attribs,polarity_pos=None):
-	if self.tree:
-	  for element in self.tree.find('terms'):
-		if element.get('tid','')==termid:
-		  
-		  #In case there is no pos info, we use the polarityPos
-		  if not element.get('pos') and polarity_pos is not None:
-			element.set('pos',polarity_pos)
-		  sentEle = etree.Element('sentiment',attrib=my_sentiment_attribs)
-		  element.append(sentEle)  
-	  
-  def saveToFile(self,filename,myencoding='UTF-8'):
-	if self.tree:
-	  self.tree.write(filename,encoding=myencoding,pretty_print=True,xml_declaration=True)
-	  
-  
-  def addLinguisticProcessor(self,name,version, layer, time_stamp=True):
-	aux = self.tree.findall('kafHeader')
-	if len(aux)!=0:
-	  kaf_header = aux[0]
-	else:
-	  kaf_header = etree.Element('kafHeader')
-	  self.tree.getroot().insert(0,kaf_header)
-
-        aux2= kaf_header.findall('linguisticProcessors')
-        if len(aux2) == 0:
-          new_lp = etree.Element('linguisticProcessors')
-          new_lp.set('layer',layer)
-          kaf_header.append(new_lp)
-          
-	## Check if there is already element for the layer
-	my_lp_ele = None
-	
-	for element in kaf_header.findall('linguisticProcessors'):
-	  if element.get('layer','')==layer:
-		my_lp_ele = element
-		break
-	  
-	if time_stamp:  
-	  my_time = time.strftime('%Y-%m-%dT%H:%M:%S%Z')
-	else:
-	  my_time = '*'
-	  
-	my_lp = etree.Element('lp')
-	my_lp.set('timestamp',my_time)
-	my_lp.set('version',version)
-	my_lp.set('name',name)
-
-	if my_lp_ele is not None: #Already an element for linguisticProcessor with the layer
-	  my_lp_ele.append(my_lp)
-	else:
-	  # Create a new element for the LP layer
-	  my_lp_ele = etree.Element('linguisticProcessors')
-	  my_lp_ele.set('layer',layer)
-	  my_lp_ele.append(my_lp)
-	  #my_lp_ele.tail=my_lp_ele.text='\n'
-	  ## Should be inserted after the last linguisticProcessor element (stored in variable element)
-	  idx = kaf_header.index(element)
-	  kaf_header.insert(idx+1,my_lp_ele)
-		
-	  
-  def addLayer(self,type,element,first_char_id=None):
-	if first_char_id is None:
-		first_char_id = type[0]
-		
-	## Check if there is already layer for the type
-	layer_element = self.tree.find(type)
-	
-	if layer_element is None:
-	  layer_element = etree.Element(type)
-	  self.tree.getroot().append(layer_element)
-	  ## The id is going to be the first one
-	  new_id = first_char_id+'1'
-	else:
-	  ## We need to know how many elements there are in the layer
-	  current_n = len(layer_element.getchildren())
-	  new_id = first_char_id+''+str(current_n+1)
-	  
-	  
-	## In this point layer_element points to the correct element, existing or created
-	
-	element.set(first_char_id+'id',new_id)
-	layer_element.append(element)
-	return new_id
-	
-  def addElementToLayer(self,layer, element,first_char_id=None):
-	return self.addLayer(layer,element,first_char_id)
-
-  def add_attrs_to_layer(self,layer,attrs):
-	layer_element = self.tree.find(layer)
-	if layer_element is not None:
-	  for att, val in attrs.items():
-		layer_element.set(att,val)
-		
-
-  def addAttributeToElement(self,path,str_id, id, attribute, value,sub_path=None):
-	  for element in self.tree.findall(path):
-		if id is not None and element.get(str_id,None) == id:
-		  if sub_path is not None:
-			elements = element.findall(sub_path)
-			if len(elements)!=0: element = elements[0]
-		  element.set(attribute,value)
-		  return
-
-  
-  ## This works with the original definition of the property layer
-  ## KAF -> properties -> property* -> span* -> target*
-  def getSingleProperties_old(self):
-	  for element in self.tree.findall('properties/property'):
-		  my_id = element.get('pid')
-		  my_type = element.get('type')
-		  ref = element.find('references')
-		  if ref is not None:
-			element = ref
-		  for span_element in element.findall('span'):
-			  target_ids = [target_element.get('id') for target_element in span_element.findall('target')]
-			  my_prop = KafSingleProperty(my_id,my_type,target_ids)
-			  yield my_prop
-			   
-  ## 18-June-2013
-  def getSingleProperties(self):
-	  for property in self.tree.findall('features/properties/property'):
-		  my_id = property.get('pid')
-		  if my_id is None:
-			  my_id = property.get('fpid')
-		  my_type = property.get('lemma')
-		  for span_element in property.findall('references/span'):
-			  target_ids = [target_element.get('id') for target_element in span_element.findall('target')]
-			  my_prop = KafSingleProperty(my_id,my_type,target_ids)
-			  yield my_prop
-
-  # This function adds a new property of the type given with the list of ids given
-  # my_type -> 'sleeping comfort'	list_ids = ['id1','id2']
-  # It creates the features/properties layers in case 
-  # Agglomerates all the properties for the same TYPE under the same property element
-  # It calculates automatically the number for the identifier depending on the number
-  # of properties existing
-  def add_property(self,my_type,list_ids,comment=None):
-      
-      #Looking for feature layer or creating it
-      feature_layer = self.tree.find('features')
-      if feature_layer is None:
-          feature_layer = etree.Element('features')
-          self.tree.getroot().append(feature_layer)
-          
-      #Looking for properties layer
-      properties_layer = feature_layer.find('properties')
-      if properties_layer is None:
-          properties_layer = etree.Element('properties')
-          feature_layer.append(properties_layer)
-          
-      num_props = 0
-      property_layer = None
-      for property in properties_layer.findall('property'):
-          num_props += 1
-          prop_type = property.get('lemma')
-          if prop_type == my_type:
-              property_layer = property
-              break
-          
-      if property_layer is None:  # There is no any property for that type, let's create one
-          property_layer = etree.Element('property')
-          property_layer.set('pid','p'+str(num_props+1))
-          property_layer.set('lemma',my_type)    
-          properties_layer.append(property_layer)
-          
-          
-      references = property_layer.find('references')
-      if references is None:
-          references = etree.Element('references')
-          property_layer.append(references)
-      ## Create the new span
-      if comment is not None:
-        references.append(etree.Comment(comment))
-      span = etree.Element('span')
-      references.append(span)
-      for my_id in list_ids:
-           span.append(etree.Element('target',attrib={'id':my_id}))
-       
-   
-			  
-  
-  def getSingleEntities(self):
-	  for element in self.tree.findall('entities/entity'):
-		  my_id = element.get('eid')
-		  my_type = element.get('type')
-		  my_path_to_span = None
-		  ref = element.find('references')
-		  if ref is not None:
-                      my_path_to_span = 'references/span'
-                  else:
-                      my_path_to_span = 'span'
-
-		  for span_element in element.findall(my_path_to_span):
-			  target_ids = [target_element.get('id') for target_element in span_element.findall('target')]
-			  my_prop = KafSingleEntity(my_id,my_type,target_ids)
-			  yield my_prop
-
-
-  def getOpinions(self):
-	for element in self.tree.findall('opinions/opinion'):
-	  my_id = element.get('oid')
-	  
-	  tar_ids_hol = []
-	  tar_ids_tar = []
-	  polarity = strenght = ''
-	  tar_ids_exp = []
-	  
-	  #Holder
-	  opi_hol_eles = element.findall('opinion_holder')
-	  if len(opi_hol_eles)!=0:
-		  opi_hol_ele = opi_hol_eles[0]
-		  tar_ids_hol = [t_ele.get('id') for t_ele in opi_hol_ele.findall('span/target')]
-	  
-	  #Target
-	  opi_tar_eles = element.findall('opinion_target')
-	  if len(opi_tar_eles) != 0:
-		opi_tar_ele = opi_tar_eles[0]
-		tar_ids_tar = [t_ele.get('id') for t_ele in opi_tar_ele.findall('span/target')]
-		
-	  ## Opinion expression
-	  opi_exp_eles = element.findall('opinion_expression')
-	  if len(opi_exp_eles) != 0:
-		  opi_exp_ele = opi_exp_eles[0]
-		  polarity = opi_exp_ele.get('polarity','')
-		  strength = opi_exp_ele.get('strength','')
-		  tar_ids_exp = [t_ele.get('id') for t_ele in opi_exp_ele.findall('span/target')]
-
-	  yield KafOpinion(my_id,tar_ids_hol, tar_ids_tar, KafOpinionExpression(polarity, strength,tar_ids_exp))
-
-
-  
-  def remove_opinion_layer(self):
-      opinion_layer = self.tree.find('opinions')
-      if opinion_layer is not None:
-          self.tree.getroot().remove(opinion_layer)
-  
-  ## This function add an opinion to the opinion layer, creating it if does not exist
-  ## The id is calculated automatically according to the number of elements and ensring there is no repetition
-  def add_opinion(self,hol_ids,tar_ids,polarity,strength,exp_ids):
-      
-      #Looking for opinion layer or creating it
-      opinion_layer = self.tree.find('opinions')
-      if opinion_layer is None:
-          opinion_layer = etree.Element('opinions')
-          self.tree.getroot().append(opinion_layer)
-          
-      ## Generating unique id
-      list_of_oids = [opi.get('oid') for opi in opinion_layer]
-      
-      n = 1
-      while True:
-          my_id = 'o'+str(n)
-          if my_id not in list_of_oids:
-              break
-          n += 1
-      #####
-          
-      op_ele = etree.Element('opinion')
-      opinion_layer.append(op_ele)
-      op_ele.set('oid',my_id)
-
-      ## Holder
-      op_hol = etree.Element('opinion_holder')
-      op_ele.append(op_hol)
-      span_op_hol = etree.Element('span')
-      op_hol.append(span_op_hol)
-      for my_id in hol_ids:
-        span_op_hol.append(etree.Element('target',attrib={'id':my_id}))
-
-      ## TARGET
-      op_tar = etree.Element('opinion_target')
-      op_ele.append(op_tar)
-      span_op_tar = etree.Element('span')
-      op_tar.append(span_op_tar)
-      for my_id in tar_ids:
-        span_op_tar.append(etree.Element('target',attrib={'id':my_id}))
-
-      ## Expression
-    
-      op_exp = etree.Element('opinion_expression',attrib={'polarity':polarity,
-                                                       'strength':str(strength)})
-      op_ele.append(op_exp)
-      span_exp = etree.Element('span')
-      op_exp.append(span_exp)
-      for my_id in exp_ids:
-        span_exp.append(etree.Element('target',attrib={'id':my_id}))
-
-
-
-	
-	

data/core/site-packages/pre_build/VUKafParserPy/__init__.py

@@ -1,7 +0,0 @@
-## version = 0.2
-## Added timestamp to function addLinguisitcProcessor
-## 24-april-2013 --> getSingleEntieies and getSingleProperties reads both entities/props in format
-## entities -> entity -> span -> target and entities -> entity -> references -> span
-####
-
-from KafParserMod import KafParser

data/core/site-packages/pre_build/VUKafParserPy-1.0-py2.7.egg-info/PKG-INFO

@@ -1,10 +0,0 @@
-Metadata-Version: 1.0
-Name: VUKafParserPy
-Version: 1.0
-Summary: Library in python to parse kaf files
-Home-page: UNKNOWN
-Author: Ruben Izquierdo
-Author-email: r.izquierdobevia@vu.nl
-License: UNKNOWN
-Description: UNKNOWN
-Platform: UNKNOWN

data/core/site-packages/pre_build/VUKafParserPy-1.0-py2.7.egg-info/SOURCES.txt

@@ -1,7 +0,0 @@
-VUKafParserPy/KafDataObjectsMod.py
-VUKafParserPy/KafParserMod.py
-VUKafParserPy/__init__.py
-VUKafParserPy.egg-info/PKG-INFO
-VUKafParserPy.egg-info/SOURCES.txt
-VUKafParserPy.egg-info/dependency_links.txt
-VUKafParserPy.egg-info/top_level.txt

data/core/site-packages/pre_build/VUKafParserPy-1.0-py2.7.egg-info/dependency_links.txt

@@ -1 +0,0 @@
-

data/core/site-packages/pre_build/VUKafParserPy-1.0-py2.7.egg-info/installed-files.txt

@@ -1,11 +0,0 @@
-../VUKafParserPy/__init__.py
-../VUKafParserPy/KafDataObjectsMod.py
-../VUKafParserPy/KafParserMod.py
-../VUKafParserPy/__init__.pyc
-../VUKafParserPy/KafDataObjectsMod.pyc
-../VUKafParserPy/KafParserMod.pyc
-./
-dependency_links.txt
-PKG-INFO
-SOURCES.txt
-top_level.txt

data/core/site-packages/pre_build/VUKafParserPy-1.0-py2.7.egg-info/top_level.txt

@@ -1 +0,0 @@
-VUKafParserPy