def create_preposition(html_full_preposition):
data = scrap_preposition(html_full_preposition)
query = "CREATE (:Preposicao {nid:\"%s\", mais_informacoes:\"%s\", divisao_silabica:\"%s\"});"
query = query % (data['lemma'], data['mais_informacoes'],
data['divisao_silabica'])
db_utils.execute_query(query=query)
return query
def create_adverb(html_full_adverb):
data = scrap_adverb(html_full_adverb)
query = "CREATE (:Adverbio {nid:\"%s\", mais_informacoes:\"%s\", divisao_silabica:\"%s\"});"
query = query % (data['lemma'], data['mais_informacoes'],
data['divisao_silabica'])
db_utils.execute_query(query=query)
return query
def create_verb(html_full_verb):
main_verb_token = regex.findall(r"<h1>.+?</h1>", html_full_verb)
main_verb_token = regex.sub(r"<.+?>", "", main_verb_token[0])
main_term = str(main_verb_token).split(" -")[0].strip(" ")
verb_data = scrap_verb(html_full_verb)
data_len = len(verb_data[0])
divisao_silabica = verb_data[2].replace("·", "-")
query = "CREATE (:Verbo {nid:\"" + main_term + "\", divisao_silabica:\"" + divisao_silabica + "\", "
for vvv in range(0, data_len):
if str(vvv) in verb_structure.keys():
data = verb_data[0][vvv]
if vvv == 31:
data = scrapper.ascii_2_portuguese(verb_data[1].replace(
":::", ","))
query += verb_structure[str(vvv)] + ":[\"" + data.replace(
"Pessoal:::", "").replace(":::", "\",\"").replace(
" ", "") + "\"]"
else:
query += verb_structure[str(vvv)] + ":[\"" + data.replace(
"Pessoal:::", "").replace(":::", "\",\"").replace(
" ", "") + "\"], "
query += "});"
db_utils.execute_query(query=query)
return query
def create_number(html_full_number):
data = scrap_number(html_full_number)
query = "CREATE (:Numero {nid:\"%s\", divisao_silabica:\"%s\", masculino_plural:\"%s\", feminino_plural:\"%s\", "
query += "masculino_singular:\"%s\", feminino_singular:\"%s\"});"
query = query % (data['lemma'], data['divisao_silabica'],
data['plur_masc'], data['plur_femi'], data['sing_masc'],
data['sing_femi'])
db_utils.execute_query(query=query)
return query
def create_noun(html_full_noun):
data = scrap_noun(html_full_noun)
main_term = scrapper.ascii_2_portuguese(data[0][0].split(" - ")[0])
gender = scrapper.ascii_2_portuguese(
data[0][0].split(" - ")[1]).split(" ")[-1]
divisao_silabica = scrapper.ascii_2_portuguese(data[1].replace("·", "-"))
plural = data[0][-1].split(" ")[-1]
query = "CREATE (:Substantivo {nid:\"%s\", divisao_silabica:\"%s\", genero:\"%s\", plural:\"%s\"" % (
main_term, divisao_silabica, gender, plural)
query += "});"
db_utils.execute_query(query=query)
return query
def create_adjective(html_full_adjective):
data = scrap_adjective(html_full_adjective)
query = "CREATE (:Adjetivo {nid:\"%s\", divisao_silabica:\"%s\", masculino_plural:\"%s\", feminino_plural:\"%s\", "
if "more_info" in data.keys():
query += "masculino_singular:\"%s\", feminino_singular:\"%s\", mais_informacoes:\"%s\"});"
query = query % (data['lemma'], data['divisao_silabica'],
data['plur_masc'], data['plur_femi'],
data['sing_masc'], data['sing_femi'],
data['more_info'])
else:
query += "masculino_singular:\"%s\", feminino_singular:\"%s\"});"
query = query % (data['lemma'], data['divisao_silabica'],
data['plur_masc'], data['plur_femi'],
data['sing_masc'], data['sing_femi'])
db_utils.execute_query(query=query)
return query
import os
import sys
project_path = os.path.abspath(__file__).split('/')
del project_path[-1]
del project_path[-1]
del project_path[-1]
sys.path.append(os.path.join('/'.join(project_path), 'generators'))
from generators.utils import db_utils
import generators.utils.defs as d
categories = [d.VERBO]
for category in categories:
print category
all_words = set()
result = db_utils.execute_query("MATCH (n:%s) RETURN n.nid" %
category).data()
for node in result:
w = node['n.nid']
all_words.add(w)
count = 0
file_ = open('all_' + category.lower() + '.txt', 'w')
for it in all_words:
if '"' in it:
continue
el = 'u"' + it + '": None, '
count += 1
file_.write(el)
from generators.utils import db_utils
from glob import glob
if __name__ == '__main__':
# file_ = 'simple_dict_outputs/word_queries/file_query1.txt'
for file_ in glob('simple_dict_outputs/word_queries/*'):
print 'file:', file_
queries = open(file_, 'r')
for line in queries.readlines():
word = line.replace('\n', '').split('"')[1]
gram = line.replace('\n', '').split(':')[1].split(' ')[0]
query = """MATCH (n:%s {nid: "%s"}) WITH n SKIP 1 DELETE n;""" % (
gram, word)
# query = """MATCH (n:%s {nid: "%s"}) RETURN n;""" % (gram, word)
result = db_utils.execute_query(query).evaluate()
if result:
print result