def corpus_xml2csv(self, num=1, persistent=True):
env = Environment()
file_xml = env.filename_corpus_xml(num)
df_xml = pd.DataFrame()
df_gram = self.grammemes()
dgram = df_gram.to_dict().get('name')
try:
tree = ET.ElementTree(file=file_xml)
except:
env.debug(1, ['Failed to load XML:', file_xml])
else:
t_start = timer()
env.debug(1, ['CORPUS', 'XML to CSV:', file_xml])
for elem in tree.iter('token'):
#print(elem.tag, elem.attrib)
serie = pd.Series(data=[])
badd = False
s_text = elem.attrib.get('text')
serie[len(serie)] = s_text.lower()
for elem2 in elem.iter('g'):
#print(elem2.tag, elem2.attrib)
sgram = elem2.attrib.get('v')
sgram = sgram.upper()
if (df_gram[df_gram['name'].isin([sgram]) == True].size
) > 0:
serie[len(serie)] = sgram
serie[len(serie)] = int(df_gram.index[
df_gram['name'] == sgram].tolist()[0])
#serie[len(serie)] = list(dgram.keys())[list(dgram.values()).index(sgram)]
badd = True
break
#print(s)
if badd:
df_xml = df_xml.append(serie, ignore_index=True)
if not df_xml.empty:
df_xml = df_xml.drop_duplicates()
df_xml = df_xml.reset_index(drop=True)
df_xml.index.name = 'idcorpus'
df_xml.columns = ['word', 'gram', 'idgram']
df_xml = df_xml.astype({"idgram": int})
if persistent:
file_csv = env.filename_corpus_csv(num)
env.debug(1, ['Write corpus file to CSV:', file_csv])
df_xml.to_csv(file_csv, encoding='utf-8')
t_end = timer()
env.debug(1, [
'CORPUS', 'CSV written:', file_csv,
'takes %s sec.' % env.job_time(t_start, t_end)
])
return df_xml
def corpus_xml2txt(self, num=1, persistent=True):
result = True
env = Environment()
file_xml = env.filename_corpus_xml(num)
try:
tree = ET.ElementTree(file=file_xml)
except:
env.debug(1, ['Failed to load XML:', file_xml])
result = False
else:
file_txt = env.filename_corpus_txt(num)
file = open(file_txt, mode='w')
for elem in tree.iter('source'):
# print(elem.text, elem.tag, elem.attrib)
file.write(elem.text)
file.write(' ')
file.close()
env.debug(1, ['Write corpus file to TXT:', file_txt])
return result
