opener-tree-tagger 2.0.1 → 2.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4570c463f56695ff7dee60413f86b60b26eeee0b
-  data.tar.gz: 6123da901f2b037f38d413d998fe3768cdebe497
+  metadata.gz: 0e0592434c89300d52ab34fd394c18e7a3e85709
+  data.tar.gz: 8fe88f3028427e8847b9ec2fddcb180502436266
 SHA512:
-  metadata.gz: 6d7fd2849e8c010e497ede5e6df23d6fc2141f4d9dd2498d277c4365e564e3e53b482c2e0613c460f05d3f4235344afe506a630bcc9801b88af7b97b6ee0ac10
-  data.tar.gz: b5e9826d95ab61bba42f0ada4ec1a5c019c11770c794b2a446f506e4f8c3a08e46583ec4e280169dc4c8cc977dff0e101f5c3907e133d29102057b68dcddf5d6
+  metadata.gz: 8693293f1d7afef28466f4090098d7c8e2051699614bf9f9cf292a673ebc695ba262537e34c581625f7422c758d9f7932ec925ad4b38cd82362969f856c42617
+  data.tar.gz: 5b4a1e287469e6655e1ec00946bc1b13dfd2ff97f18441c67a15d7802fc9cacea209a41b88d0526773f69a1e33f47905504712a344d2a9e128a0ebfdc35362ac

data/README.md

@@ -7,14 +7,15 @@ This module implements a wrapper to process text with the PoS tagger TreeTagger.
 This module takes KAF as input, with the token layer created (for instance by one of our tokenizer modules) and outputs KAF with a new term layer. It is important to note
 that the token layer in the input is not modified in the output, so the program takes care of performing the correct matching between the term and the token layer.
 
-By default this module works for text in English, Dutch and German, but can be easily extended to other languages. The language of the input KAF text has to be specified through
-the attribute xml:lang in the main KAF element.
+The language of the input KAF text has to be specified through the attribute xml:lang in the main KAF element. This module works for text in all the languages covered by the OpeNER project (English, Dutch,German,
+Italian, Spanish and French). It can be easily extended to other languages by downloading the specific TreeTagger
+models for that language and providing a mapping from the tagset used by these models to the tagset defined in KAF. 
 
 ### Confused by some terminology?
 
 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.
 
@@ -34,8 +35,7 @@ typing
 
     pip install lxml
 
-If that doesn't work, please check the (installation guide on the OpeNER
-portal)[http://opener-project.github.io/getting-started/how-to/local-installation.html].
+If that doesn't work, please check the [installation guide on the OpeNER portal](http://opener-project.github.io/getting-started/how-to/local-installation.html).
 
 Please bare in mind that all components in OpeNER take KAF as an input and
 output KAF by default.
@@ -86,10 +86,8 @@ 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:
 
@@ -103,7 +101,7 @@ At least you need the following system setup:
   variable.
 
 If TreeTagger is not installed in your machine
-you can download it from http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/ and follow the installation instructions. To indicate to our scripts where
+you can download it from <http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/> and follow the installation instructions. To indicate to our scripts where
 TreeTagger is located, you have to set an environment variable with the
 location:
 
@@ -130,8 +128,8 @@ can find the core technolies in the core directory of this repository.
 Where to go from here
 ---------------------
 
-* Check (the project websitere)[http://opener-project.github.io]
-* (Checkout the webservice)[http://opener.olery.com/tree-tagger]
+* [Check the project websitere](http://opener-project.github.io)
+* [Checkout the webservice](http://opener.olery.com/tree-tagger)
 
 Report problem/Get help
 -----------------------
@@ -143,7 +141,7 @@ issue in the (issue tracker)[https://github.com/opener-project/tree-tagger/issue
 Contributing
 ------------
 
-1. Fork it ( http://github.com/opener-project/tree-tagger/fork )
+1. Fork it <http://github.com/opener-project/tree-tagger/fork>
 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`)

data/core/tt_from_kaf_to_kaf.py

@@ -18,7 +18,7 @@ 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'))
 
 import operator
 import time
@@ -36,7 +36,7 @@ from token_matcher import token_matcher
 if not os.environ.get('TREE_TAGGER_PATH'):
   print>>sys.stderr,"TREE_TAGGER_PATH environment variable not found. Please set the full path to your tree tagger in the TREE_TAGGER_PATH environent variable."
   sys.exit(-1)
-  
+
 complete_path_to_treetagger = os.environ.get('TREE_TAGGER_PATH')
 
 
@@ -102,7 +102,7 @@ if __name__=='__main__':
     treetagger_cmd = complete_path_to_treetagger+'/cmd/tree-tagger-dutch-utf8'
     mapping_file = this_folder +'/dutch.map.treetagger.kaf.csv'
     model = 'Dutch models'
-    
+
   map_tt_to_kaf = loadMapping(mapping_file)
 
 
@@ -209,7 +209,7 @@ if __name__=='__main__':
         input_kaf.addElementToLayer('terms', ele_term)
   ##End for each sentence
 
-  input_kaf.addLinguisticProcessor('TreeTagger_from_kaf '+model,'1.0', 'term', time_stamp)  
+  input_kaf.addLinguisticProcessor('TreeTagger_from_kaf '+model,'1.0', 'term', time_stamp)
   input_kaf.saveToFile(sys.stdout)
 
 

data/ext/hack/Rakefile

@@ -7,7 +7,7 @@ task :requirements do
 end
 
 task :default => :requirements do
-  # path = File.join(PYTHON_SITE_PACKAGES, 'pre_install')
-  # 
-  # pip_install(PRE_INSTALL_REQUIREMENTS, path)
+  path = File.join(PYTHON_SITE_PACKAGES, 'pre_install')
+
+  pip_install(PRE_INSTALL_REQUIREMENTS, path)
 end

data/lib/opener/tree_tagger/version.rb

@@ -1,5 +1,5 @@
 module Opener
   class TreeTagger
-    VERSION = "2.0.1"
+    VERSION = "2.0.2"
   end
 end

data/opener-tree-tagger.gemspec

@@ -8,6 +8,7 @@ Gem::Specification.new do |gem|
   gem.description = %q{Ruby wrapped KAF based Tree Tagger for 6 languages }
   gem.summary     = gem.description
   gem.homepage    = "http://opener-project.github.com/"
+  gem.extensions  = ['ext/hack/Rakefile']
 
   gem.files = Dir.glob([
     'core/site-packages/pre_build/**/*',

data/pre_install_requirements.txt

@@ -0,0 +1 @@
+https://github.com/opener-project/VU-kaf-parser/archive/master.zip#egg=VUKafParserPy

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: opener-tree-tagger
 version: !ruby/object:Gem::Version
-  version: 2.0.1
+  version: 2.0.2
 platform: ruby
 authors:
 - rubenIzquierdo
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-05-20 00:00:00.000000000 Z
+date: 2014-05-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: opener-daemons
@@ -145,7 +145,8 @@ executables:
 - tree-tagger
 - opener-tree-tagger-daemon
 - opener-tree-tagger-server
-extensions: []
+extensions:
+- ext/hack/Rakefile
 extra_rdoc_files: []
 files:
 - README.md
@@ -158,14 +159,6 @@ files:
 - core/french.map.treetagger.kaf.csv
 - core/german.map.treetagger.kaf.csv
 - core/italian.map.treetagger.kaf.csv
-- 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/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/top_level.txt
-- core/site-packages/pre_build/VUKafParserPy/KafDataObjectsMod.py
-- core/site-packages/pre_build/VUKafParserPy/KafParserMod.py
-- core/site-packages/pre_build/VUKafParserPy/__init__.py
 - core/spanish.map.treetagger.kaf.csv
 - core/token_matcher.py
 - core/tt_from_kaf_to_kaf.py
@@ -180,7 +173,7 @@ files:
 - lib/opener/tree_tagger/views/index.erb
 - lib/opener/tree_tagger/views/result.erb
 - opener-tree-tagger.gemspec
-- pre_build_requirements.txt
+- pre_install_requirements.txt
 homepage: http://opener-project.github.com/
 licenses: []
 metadata: {}

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/KafParserMod.py
-../VUKafParserPy/__init__.py
-../VUKafParserPy/KafDataObjectsMod.py
-../VUKafParserPy/KafParserMod.pyc
-../VUKafParserPy/__init__.pyc
-../VUKafParserPy/KafDataObjectsMod.pyc
-./
-top_level.txt
-SOURCES.txt
-PKG-INFO
-dependency_links.txt

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

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

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/pre_build_requirements.txt

@@ -1 +0,0 @@
-git+ssh://git@github.com/opener-project/VU-kaf-parser.git#egg=VUKafParserPy