def getAlbumList(self):
"""
get post 都有效
:return:
"""
http = Http()
params = {"sitefrom": "cloudalbum_android", "sortType": 0}
res = http.getUrl("http://photo.163.com/papi/user/替换你的用户名/product/list", self.headers, params)
res = res.decode('gbk')
print("========获取到相册列表=========")
parseXml = ParseXml()
return parseXml.parseList(res)
def __init__(self, filename):
self.filename_xml = filename + '.xml'
print self.filename_xml
self.xml = ParseXml(self.filename_xml)
self.parameters = Parameters()
self.dic_t_xml = self.xml.getDicTerms()
self.dic_nts = self.xml.getDicNTStructure()
self.dic_an = {}
#self.dic_sv = {}
#self.dic_vo = {}
self.mountANRelations = True
def getAlbumDetail(self, albumId):
"""
get post 都有效
:return:
"""
http = Http()
params = {"sitefrom": "cloudalbum_android"}
# try:
res = http.getUrl("http://photo.163.com/papi/user/替换你的用户名/albumid/" + albumId, self.headers, params)
res = res.decode('gbk')
# except:
# print("albumId:"+albumId)
print("\n")
print("1、获取到相册：" + albumId + "=========")
parseXml = ParseXml()
return parseXml.parseAlbum(res)
def __buildStatisticalCorpus__(self):
try:
root, dirs, files = os.walk(self.corpus_folder).next()[:3]
except:
print 'ERROR: It was not possible to open the ../Data/Corpus/Raw/ folder'
sys.exit()
accents = Accents()
for corpus_file in files:
if re.match('.*xml$', corpus_file):
corpus_filename = corpus_file.split('.')[0]
xmlfile = ParseXml(root+''+corpus_file)
dic_terms = xmlfile.getDicTerms()
dic_nouns = xmlfile.getNouns()
dic_verbs = xmlfile.getVerbs()
id_sentence = 1
id_word = 1
id_t = 's'+str(id_sentence)+'_'+str(id_word)
string_full = ''
string_nouns = ''
while dic_terms.has_key(id_t):
while dic_terms.has_key(id_t):
if not re.match('^(pu|num|conj|art|prp|spec)', dic_terms[id_t]['pos']) and (re.search('[$]', dic_terms[id_t]['lemma']) is None) and (len(dic_terms[id_t]['lemma']) >= self.parameters.getMinWordSize()):
lemma = accents.buildCodes(dic_terms[id_t]['lemma'])
if dic_nouns.has_key(id_t):
string_nouns += lemma+'__N '
string_full += lemma+'__N '
elif dic_verbs.has_key(id_t):
string_nouns += lemma+'__V '
string_full += lemma+'__V '
else:
string_full += lemma+'__O '
string_nouns = string_nouns.replace('-', '_')
string_full = string_full.replace('-', '_')
id_word += 1
id_t = 's'+str(id_sentence)+'_'+str(id_word)
id_word = 1
id_sentence += 1
id_t = 's'+str(id_sentence)+'_'+str(id_word)
self.__writeCorpusFile__(corpus_filename, string_full, string_nouns)
def __init__(self, filename):
self.filename_xml = filename+'.xml'
print self.filename_xml
self.xml = ParseXml(self.filename_xml)
self.parameters = Parameters()
self.dic_t_xml = self.xml.getDicTerms()
self.dic_nts = self.xml.getDicNTStructure()
self.dic_an = {}
#self.dic_sv = {}
#self.dic_vo = {}
self.mountANRelations = True
class SyntacticContexts:
def __init__(self, filename):
self.filename_xml = filename + '.xml'
print self.filename_xml
self.xml = ParseXml(self.filename_xml)
self.parameters = Parameters()
self.dic_t_xml = self.xml.getDicTerms()
self.dic_nts = self.xml.getDicNTStructure()
self.dic_an = {}
#self.dic_sv = {}
#self.dic_vo = {}
self.mountANRelations = True
#self.mountSVRelations = True
#self.mountVORelations = True
def __extractRelations__(self, type_relation):
if type_relation == 'AN':
for id_t in self.dic_t_xml:
if re.match("^(n|prop)$", self.dic_t_xml[id_t]['pos']) and len(
self.dic_t_xml[id_t]
['lemma']) >= self.parameters.getMinWordSize():
id_sentence = id_t.split("_")[0]
id_word = id_t.split("_")[1]
id_1 = id_sentence + '_' + str((int(id_word) + 1))
id_2 = id_sentence + '_' + str((int(id_word) + 2))
id_3 = id_sentence + '_' + str((int(id_word) + 3))
if self.dic_t_xml.has_key(id_3) and len(
self.dic_t_xml[id_3]
['lemma']) >= self.parameters.getMinWordSize():
ids = self.dic_t_xml[id_t][
'pos'] + ':' + self.dic_t_xml[id_1][
'pos'] + ':' + self.dic_t_xml[id_2][
'pos'] + ':' + self.dic_t_xml[id_3]['pos']
if re.match(
'^(n|prop):prp:(art|num|pron-indef|pron-poss|pu):(n|prop)$',
ids) is not None:
self.__addElementDicAN__(
'prep_' + self.dic_t_xml[id_3]['lemma'] + '#' +
self.dic_t_xml[id_t]['lemma']) # 'prep_#'
self.__addElementDicAN__(
'prep_' + self.dic_t_xml[id_t]['lemma'] + '#' +
self.dic_t_xml[id_3]['lemma']) # 'prep_#'
if re.match('^(n|prop):adj:adj:adj$', ids) is not None:
self.__addElementDicAN__(
'adj_' + self.dic_t_xml[id_3]['lemma'] + '#' +
self.dic_t_xml[id_t]['lemma']) # 'adj_#'
if self.dic_t_xml.has_key(id_2) and len(
self.dic_t_xml[id_2]
['lemma']) >= self.parameters.getMinWordSize():
ids = self.dic_t_xml[id_t][
'pos'] + ':' + self.dic_t_xml[id_1][
'pos'] + ':' + self.dic_t_xml[id_2]['pos']
if re.match('^(n|prop):prp:(n|prop)$',
ids) is not None:
self.__addElementDicAN__(
'prep_' + self.dic_t_xml[id_2]['lemma'] + '#' +
self.dic_t_xml[id_t]['lemma']) # 'prep_#'
self.__addElementDicAN__(
'prep_' + self.dic_t_xml[id_t]['lemma'] + '#' +
self.dic_t_xml[id_2]['lemma']) # 'prep_#'
if re.match('^(n|prop):adj:adj$', ids) is not None:
self.__addElementDicAN__(
'adj_' + self.dic_t_xml[id_2]['lemma'] + '#' +
self.dic_t_xml[id_t]['lemma']) # 'adj_#'
if self.dic_t_xml.has_key(id_1) and len(
self.dic_t_xml[id_1]
['lemma']) >= self.parameters.getMinWordSize():
ids = self.dic_t_xml[id_t][
'pos'] + ':' + self.dic_t_xml[id_1]['pos']
if re.match('^(n|prop):adj$', ids) is not None:
self.__addElementDicAN__(
'adj_' + self.dic_t_xml[id_1]['lemma'] + '#' +
self.dic_t_xml[id_t]['lemma']) # 'adj_#'
if re.match('^(n|prop):(n|prop)$', ids) is not None:
self.__addElementDicAN__(
'nn_' + self.dic_t_xml[id_1]['lemma'] + '#' +
self.dic_t_xml[id_t]['lemma']) # 'nn_#'
self.__addElementDicAN__(
'nn_' + self.dic_t_xml[id_t]['lemma'] + '#' +
self.dic_t_xml[id_1]['lemma']) # 'nn_#'
id_1 = id_sentence + '_' + str((int(id_word) - 1))
id_2 = id_sentence + '_' + str((int(id_word) - 2))
id_3 = id_sentence + '_' + str((int(id_word) - 3))
if self.dic_t_xml.has_key(id_3) and len(
self.dic_t_xml[id_3]
['lemma']) >= self.parameters.getMinWordSize():
ids = self.dic_t_xml[id_3][
'pos'] + ':' + self.dic_t_xml[id_2][
'pos'] + ':' + self.dic_t_xml[id_1][
'pos'] + ':' + self.dic_t_xml[id_t]['pos']
if re.match('^adj:adj:adj:(n|prop)$', ids) is not None:
self.__addElementDicAN__(
'adj_' + self.dic_t_xml[id_3]['lemma'] + '#' +
self.dic_t_xml[id_t]['lemma']) # 'adj_#'
if self.dic_t_xml.has_key(id_2) and len(
self.dic_t_xml[id_2]
['lemma']) >= self.parameters.getMinWordSize():
ids = self.dic_t_xml[id_2][
'pos'] + ':' + self.dic_t_xml[id_1][
'pos'] + ':' + self.dic_t_xml[id_t]['pos']
if re.match('^adj:adj:(n|prop)$', ids) is not None:
self.__addElementDicAN__(
'adj_' + self.dic_t_xml[id_2]['lemma'] + '#' +
self.dic_t_xml[id_t]['lemma']) # 'adj_#'
if self.dic_t_xml.has_key(id_1) and len(
self.dic_t_xml[id_1]
['lemma']) >= self.parameters.getMinWordSize():
ids = self.dic_t_xml[id_1][
'pos'] + ':' + self.dic_t_xml[id_t]['pos']
if re.match('^adj:(n|prop)$', ids) is not None:
self.__addElementDicAN__(
'adj_' + self.dic_t_xml[id_1]['lemma'] + '#' +
self.dic_t_xml[id_t]['lemma']) # 'adj_#'
def __addElementDicAN__(self, relation):
#relation = relation.lower()
if self.dic_an.has_key(relation):
self.dic_an[relation] += 1
else:
self.dic_an[relation] = 1
""" Extract relations for nouns when they are subjects of a verb as noun phrases (NP).
def __extractSVRelations__(self):
for id_t in self.dic_t_cg:
if re.match("^(@SUBJ>|@N<PRED)$", self.dic_t_cg[id_t]['synt']) and re.match("^(n|prop)$", self.dic_t_xml[id_t]['pos']) and len(self.dic_t_xml[id_t]['lemma']) >= self.parameters.getMinWordSize():
id_sentence = id_t.split("_")[0]
id_word = id_t.split("_")[1]
next_word = int(id_word) + 1
id_next_word = id_sentence+'_'+str(next_word)
while self.dic_t_cg.has_key(id_next_word):
if 'v-' in self.dic_t_xml[id_next_word]['pos']:
if self.dic_t_xml[id_t]['headof'] != '':
self.__addElementDicSV__('subj_'+self.dic_t_cg[id_next_word]['lemma']+'#'+self.dic_t_cg[id_t]['lemma'])
nounphrase = self.__cleanStructureToNP__(self.dic_nts[self.dic_t_xml[id_t]['headof']]['structure'])
self.__addElementDicSV__('subj_'+self.dic_t_cg[id_next_word]['lemma']+'#'+nounphrase)
else:
self.__addElementDicSV__('subj_'+self.dic_t_cg[id_next_word]['lemma']+'#'+self.dic_t_cg[id_t]['lemma'])
break
next_word += 1
id_next_word = id_sentence+'_'+str(next_word)
if self.dic_t_cg[id_t]['synt'] == '@<SUBJ' and re.match("^(n|prop)$", self.dic_t_xml[id_t]['pos']) and len(self.dic_t_xml[id_t]['lemma']) >= self.parameters.getMinWordSize():
id_sentence = id_t.split("_")[0]
id_word = id_t.split("_")[1]
previous_word = int(id_word) - 1
id_previous_word = id_sentence+'_'+str(previous_word)
while self.dic_t_cg.has_key(id_previous_word):
if 'v-' in self.dic_t_xml[id_previous_word]['pos']:
if self.dic_t_xml[id_t]['headof'] != '':
self.__addElementDicSV__('subj_'+self.dic_t_cg[id_previous_word]['lemma']+'#'+self.dic_t_cg[id_t]['lemma'])
nounphrase = self.__cleanStructureToNP__(self.dic_nts[self.dic_t_xml[id_t]['headof']]['structure'])
self.__addElementDicSV__('subj_'+self.dic_t_cg[id_previous_word]['lemma']+'#'+nounphrase)
else:
self.__addElementDicSV__('subj_'+self.dic_t_cg[id_previous_word]['lemma']+'#'+self.dic_t_cg[id_t]['lemma'])
break
previous_word -= 1
id_previous_word = id_sentence+'_'+str(previous_word)
def __addElementDicSV__(self, relation):
#relation = relation.lower()
if self.dic_sv.has_key(relation):
self.dic_sv[relation] += 1
else:
self.dic_sv[relation] = 1
"""
""" Extract relations for nouns when they are the object of a verb as noun phrases (NP).
def __extractVORelations__(self):
for id_t in self.dic_t_cg:
if re.match("^(@<ACC|@PRED>)$", self.dic_t_cg[id_t]['synt'])and re.match("^(n|prop)$", self.dic_t_xml[id_t]['pos']) and len(self.dic_t_xml[id_t]['lemma']) >= self.parameters.getMinWordSize():
id_sentence = id_t.split("_")[0]
id_word = id_t.split("_")[1]
previous_word = int(id_word) - 1
id_previous_word = id_sentence+'_'+str(previous_word)
while self.dic_t_cg.has_key(id_previous_word):
if 'v-' in self.dic_t_xml[id_previous_word]['pos']:
if self.dic_t_xml[id_t]['headof'] != '':
self.__addElementDicVO__('obj_'+self.dic_t_cg[id_previous_word]['lemma']+'#'+self.dic_t_cg[id_t]['lemma'])
nounphrase = self.__cleanStructureToNP__(self.dic_nts[self.dic_t_xml[id_t]['headof']]['structure'])
self.__addElementDicVO__('obj_'+self.dic_t_cg[id_previous_word]['lemma']+'#'+nounphrase)
else:
self.__addElementDicVO__('obj_'+self.dic_t_cg[id_previous_word]['lemma']+'#'+self.dic_t_cg[id_t]['lemma'])
break
previous_word -= 1
id_previous_word = id_sentence+'_'+str(previous_word)
def __addElementDicVO__(self, relation):
#relation = relation.lower()
if self.dic_vo.has_key(relation):
self.dic_vo[relation] += 1
else:
self.dic_vo[relation] = 1
def __cleanStructureToNP__(self, noun_phrase):
np = list(noun_phrase)
for id_t in noun_phrase:
if re.match('^(adj|n|prop)', self.dic_t_xml[id_t]['pos']):
break
else:
np.remove(id_t)
for id_t in reversed(noun_phrase):
if re.match('^(n|prop|adj)', self.dic_t_xml[id_t]['pos']):
break
else:
np.remove(id_t)
phrase = '';
for id_t in np:
phrase += self.dic_t_xml[id_t]['lemma']+' '
phrase = phrase.replace(' --', ',').rstrip()
phrase = phrase.replace('-', '_')
phrase = phrase.replace(' ', '_')
phrase = phrase.replace(',,', ',')
return phrase
"""
""" Get and Print methods
"""
def getDicAN(self):
if self.mountANRelations:
self.__extractRelations__('AN')
self.mountANRelations = False
return self.dic_an
def printDicAN(self):
if self.mountANRelations:
self.__extractRelations__('AN')
self.mountANRelations = False
for id_an in self.dic_an:
print id_an + ' = ' + str(self.dic_an[id_an])
def writeDicAN(self, filename):
misc = Miscelaneous()
output_an = misc.openFile(filename + '.txt', 'w')
if self.mountANRelations:
self.__extractRelations__('AN')
self.mountANRelations = False
for id_an in self.dic_an:
output_an.write(id_an + '#' + str(self.dic_an[id_an]) + '\n')
output_an.close()
"""
class SyntacticContexts:
def __init__(self, filename):
self.filename_xml = filename+'.xml'
print self.filename_xml
self.xml = ParseXml(self.filename_xml)
self.parameters = Parameters()
self.dic_t_xml = self.xml.getDicTerms()
self.dic_nts = self.xml.getDicNTStructure()
self.dic_an = {}
#self.dic_sv = {}
#self.dic_vo = {}
self.mountANRelations = True
#self.mountSVRelations = True
#self.mountVORelations = True
def __extractRelations__(self, type_relation):
if type_relation == 'AN':
for id_t in self.dic_t_xml:
if re.match("^(n|prop)$", self.dic_t_xml[id_t]['pos']) and len(self.dic_t_xml[id_t]['lemma']) >= self.parameters.getMinWordSize():
id_sentence = id_t.split("_")[0]
id_word = id_t.split("_")[1]
id_1 = id_sentence+'_'+str((int(id_word) + 1))
id_2 = id_sentence+'_'+str((int(id_word) + 2))
id_3 = id_sentence+'_'+str((int(id_word) + 3))
if self.dic_t_xml.has_key(id_3) and len(self.dic_t_xml[id_3]['lemma']) >= self.parameters.getMinWordSize():
ids = self.dic_t_xml[id_t]['pos']+':'+self.dic_t_xml[id_1]['pos']+':'+self.dic_t_xml[id_2]['pos']+':'+self.dic_t_xml[id_3]['pos']
if re.match('^(n|prop):prp:(art|num|pron-indef|pron-poss|pu):(n|prop)$', ids) is not None:
self.__addElementDicAN__('prep_'+self.dic_t_xml[id_3]['lemma']+'#'+self.dic_t_xml[id_t]['lemma']) # 'prep_#'
self.__addElementDicAN__('prep_'+self.dic_t_xml[id_t]['lemma']+'#'+self.dic_t_xml[id_3]['lemma']) # 'prep_#'
if re.match('^(n|prop):adj:adj:adj$', ids) is not None:
self.__addElementDicAN__('adj_'+self.dic_t_xml[id_3]['lemma']+'#'+self.dic_t_xml[id_t]['lemma']) # 'adj_#'
if self.dic_t_xml.has_key(id_2) and len(self.dic_t_xml[id_2]['lemma']) >= self.parameters.getMinWordSize():
ids = self.dic_t_xml[id_t]['pos']+':'+self.dic_t_xml[id_1]['pos']+':'+self.dic_t_xml[id_2]['pos']
if re.match('^(n|prop):prp:(n|prop)$', ids) is not None:
self.__addElementDicAN__('prep_'+self.dic_t_xml[id_2]['lemma']+'#'+self.dic_t_xml[id_t]['lemma']) # 'prep_#'
self.__addElementDicAN__('prep_'+self.dic_t_xml[id_t]['lemma']+'#'+self.dic_t_xml[id_2]['lemma']) # 'prep_#'
if re.match('^(n|prop):adj:adj$', ids) is not None:
self.__addElementDicAN__('adj_'+self.dic_t_xml[id_2]['lemma']+'#'+self.dic_t_xml[id_t]['lemma']) # 'adj_#'
if self.dic_t_xml.has_key(id_1) and len(self.dic_t_xml[id_1]['lemma']) >= self.parameters.getMinWordSize():
ids = self.dic_t_xml[id_t]['pos']+':'+self.dic_t_xml[id_1]['pos']
if re.match('^(n|prop):adj$', ids) is not None:
self.__addElementDicAN__('adj_'+self.dic_t_xml[id_1]['lemma']+'#'+self.dic_t_xml[id_t]['lemma']) # 'adj_#'
if re.match('^(n|prop):(n|prop)$', ids) is not None:
self.__addElementDicAN__('nn_'+self.dic_t_xml[id_1]['lemma']+'#'+self.dic_t_xml[id_t]['lemma']) # 'nn_#'
self.__addElementDicAN__('nn_'+self.dic_t_xml[id_t]['lemma']+'#'+self.dic_t_xml[id_1]['lemma']) # 'nn_#'
id_1 = id_sentence+'_'+str((int(id_word) - 1))
id_2 = id_sentence+'_'+str((int(id_word) - 2))
id_3 = id_sentence+'_'+str((int(id_word) - 3))
if self.dic_t_xml.has_key(id_3) and len(self.dic_t_xml[id_3]['lemma']) >= self.parameters.getMinWordSize():
ids = self.dic_t_xml[id_3]['pos']+':'+self.dic_t_xml[id_2]['pos']+':'+self.dic_t_xml[id_1]['pos']+':'+self.dic_t_xml[id_t]['pos']
if re.match('^adj:adj:adj:(n|prop)$', ids) is not None:
self.__addElementDicAN__('adj_'+self.dic_t_xml[id_3]['lemma']+'#'+self.dic_t_xml[id_t]['lemma']) # 'adj_#'
if self.dic_t_xml.has_key(id_2) and len(self.dic_t_xml[id_2]['lemma']) >= self.parameters.getMinWordSize():
ids = self.dic_t_xml[id_2]['pos']+':'+self.dic_t_xml[id_1]['pos']+':'+self.dic_t_xml[id_t]['pos']
if re.match('^adj:adj:(n|prop)$', ids) is not None:
self.__addElementDicAN__('adj_'+self.dic_t_xml[id_2]['lemma']+'#'+self.dic_t_xml[id_t]['lemma']) # 'adj_#'
if self.dic_t_xml.has_key(id_1) and len(self.dic_t_xml[id_1]['lemma']) >= self.parameters.getMinWordSize():
ids = self.dic_t_xml[id_1]['pos']+':'+self.dic_t_xml[id_t]['pos']
if re.match('^adj:(n|prop)$', ids) is not None:
self.__addElementDicAN__('adj_'+self.dic_t_xml[id_1]['lemma']+'#'+self.dic_t_xml[id_t]['lemma']) # 'adj_#'
def __addElementDicAN__(self, relation):
#relation = relation.lower()
if self.dic_an.has_key(relation):
self.dic_an[relation] += 1
else:
self.dic_an[relation] = 1
""" Extract relations for nouns when they are subjects of a verb as noun phrases (NP).
def __extractSVRelations__(self):
for id_t in self.dic_t_cg:
if re.match("^(@SUBJ>|@N<PRED)$", self.dic_t_cg[id_t]['synt']) and re.match("^(n|prop)$", self.dic_t_xml[id_t]['pos']) and len(self.dic_t_xml[id_t]['lemma']) >= self.parameters.getMinWordSize():
id_sentence = id_t.split("_")[0]
id_word = id_t.split("_")[1]
next_word = int(id_word) + 1
id_next_word = id_sentence+'_'+str(next_word)
while self.dic_t_cg.has_key(id_next_word):
if 'v-' in self.dic_t_xml[id_next_word]['pos']:
if self.dic_t_xml[id_t]['headof'] != '':
self.__addElementDicSV__('subj_'+self.dic_t_cg[id_next_word]['lemma']+'#'+self.dic_t_cg[id_t]['lemma'])
nounphrase = self.__cleanStructureToNP__(self.dic_nts[self.dic_t_xml[id_t]['headof']]['structure'])
self.__addElementDicSV__('subj_'+self.dic_t_cg[id_next_word]['lemma']+'#'+nounphrase)
else:
self.__addElementDicSV__('subj_'+self.dic_t_cg[id_next_word]['lemma']+'#'+self.dic_t_cg[id_t]['lemma'])
break
next_word += 1
id_next_word = id_sentence+'_'+str(next_word)
if self.dic_t_cg[id_t]['synt'] == '@<SUBJ' and re.match("^(n|prop)$", self.dic_t_xml[id_t]['pos']) and len(self.dic_t_xml[id_t]['lemma']) >= self.parameters.getMinWordSize():
id_sentence = id_t.split("_")[0]
id_word = id_t.split("_")[1]
previous_word = int(id_word) - 1
id_previous_word = id_sentence+'_'+str(previous_word)
while self.dic_t_cg.has_key(id_previous_word):
if 'v-' in self.dic_t_xml[id_previous_word]['pos']:
if self.dic_t_xml[id_t]['headof'] != '':
self.__addElementDicSV__('subj_'+self.dic_t_cg[id_previous_word]['lemma']+'#'+self.dic_t_cg[id_t]['lemma'])
nounphrase = self.__cleanStructureToNP__(self.dic_nts[self.dic_t_xml[id_t]['headof']]['structure'])
self.__addElementDicSV__('subj_'+self.dic_t_cg[id_previous_word]['lemma']+'#'+nounphrase)
else:
self.__addElementDicSV__('subj_'+self.dic_t_cg[id_previous_word]['lemma']+'#'+self.dic_t_cg[id_t]['lemma'])
break
previous_word -= 1
id_previous_word = id_sentence+'_'+str(previous_word)
def __addElementDicSV__(self, relation):
#relation = relation.lower()
if self.dic_sv.has_key(relation):
self.dic_sv[relation] += 1
else:
self.dic_sv[relation] = 1
"""
""" Extract relations for nouns when they are the object of a verb as noun phrases (NP).
def __extractVORelations__(self):
for id_t in self.dic_t_cg:
if re.match("^(@<ACC|@PRED>)$", self.dic_t_cg[id_t]['synt'])and re.match("^(n|prop)$", self.dic_t_xml[id_t]['pos']) and len(self.dic_t_xml[id_t]['lemma']) >= self.parameters.getMinWordSize():
id_sentence = id_t.split("_")[0]
id_word = id_t.split("_")[1]
previous_word = int(id_word) - 1
id_previous_word = id_sentence+'_'+str(previous_word)
while self.dic_t_cg.has_key(id_previous_word):
if 'v-' in self.dic_t_xml[id_previous_word]['pos']:
if self.dic_t_xml[id_t]['headof'] != '':
self.__addElementDicVO__('obj_'+self.dic_t_cg[id_previous_word]['lemma']+'#'+self.dic_t_cg[id_t]['lemma'])
nounphrase = self.__cleanStructureToNP__(self.dic_nts[self.dic_t_xml[id_t]['headof']]['structure'])
self.__addElementDicVO__('obj_'+self.dic_t_cg[id_previous_word]['lemma']+'#'+nounphrase)
else:
self.__addElementDicVO__('obj_'+self.dic_t_cg[id_previous_word]['lemma']+'#'+self.dic_t_cg[id_t]['lemma'])
break
previous_word -= 1
id_previous_word = id_sentence+'_'+str(previous_word)
def __addElementDicVO__(self, relation):
#relation = relation.lower()
if self.dic_vo.has_key(relation):
self.dic_vo[relation] += 1
else:
self.dic_vo[relation] = 1
def __cleanStructureToNP__(self, noun_phrase):
np = list(noun_phrase)
for id_t in noun_phrase:
if re.match('^(adj|n|prop)', self.dic_t_xml[id_t]['pos']):
break
else:
np.remove(id_t)
for id_t in reversed(noun_phrase):
if re.match('^(n|prop|adj)', self.dic_t_xml[id_t]['pos']):
break
else:
np.remove(id_t)
phrase = '';
for id_t in np:
phrase += self.dic_t_xml[id_t]['lemma']+' '
phrase = phrase.replace(' --', ',').rstrip()
phrase = phrase.replace('-', '_')
phrase = phrase.replace(' ', '_')
phrase = phrase.replace(',,', ',')
return phrase
"""
""" Get and Print methods
"""
def getDicAN(self):
if self.mountANRelations:
self.__extractRelations__('AN')
self.mountANRelations = False
return self.dic_an
def printDicAN(self):
if self.mountANRelations:
self.__extractRelations__('AN')
self.mountANRelations = False
for id_an in self.dic_an:
print id_an+' = '+str(self.dic_an[id_an])
def writeDicAN(self, filename):
misc = Miscelaneous()
output_an = misc.openFile(filename+'.txt', 'w')
if self.mountANRelations:
self.__extractRelations__('AN')
self.mountANRelations = False
for id_an in self.dic_an:
output_an.write(id_an+'#'+str(self.dic_an[id_an])+'\n')
output_an.close()
"""