38 lines
875 B
Python
38 lines
875 B
Python
|
#!/usr/bin/python3
|
||
|
|
# -*- coding: utf-8 -*-
|
||
|
|
|
||
|
|
import json
|
||
|
|
import requests
|
||
|
|
import sys
|
||
|
|
|
||
|
|
BUFFER_SIZE = 500
|
||
|
|
|
||
|
|
def lemmatize_sentences(language_code, sentences):
|
||
|
|
data = {
|
||
|
|
'operation': 'lemmatizeAll',
|
||
|
|
'languageCode':language_code,
|
||
|
|
'sentences':sentences
|
||
|
|
}
|
||
|
|
|
||
|
|
address = 'http://localhost:8800'
|
||
|
|
|
||
|
|
response = requests.post(address, data = json.dumps(data))
|
||
|
|
response.encoding = 'utf-8'
|
||
|
|
|
||
|
|
response_json = json.loads(response.text)
|
||
|
|
return '\n'.join(response_json['lemmatizedSentences'])
|
||
|
|
|
||
|
|
|
||
|
|
language_code = sys.argv[1]
|
||
|
|
sentences_buffer = []
|
||
|
|
for line in sys.stdin:
|
||
|
|
sentences_buffer.append(line.rstrip())
|
||
|
|
if len(sentences_buffer) == BUFFER_SIZE:
|
||
|
|
print(lemmatize_sentences(language_code,sentences_buffer))
|
||
|
|
sentences_buffer = []
|
||
|
|
|
||
|
|
if len(sentences_buffer) > 0:
|
||
|
|
print(lemmatize_sentences(language_code,sentences_buffer))
|
||
|
|
|
||
|
|
|