sumyapi.py

from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

from sumy.parsers.html import HtmlParser
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lex_rank import LexRankSummarizer
from sumy.summarizers.lsa import LsaSummarizer
from sumy.summarizers.luhn import LuhnSummarizer
from sumy.summarizers.random import RandomSummarizer
from sumy.summarizers.text_rank import TextRankSummarizer

from sumy.nlp.stemmers import Stemmer
from sumy.utils import get_stop_words
import sys
import locale


# arguments of sumyapi.py call
# 1: chosen summarizer [lex_rank|lsa|luhn|random|text_rank], default lsa
# 2: language, default [german]
# 3: target summary length in sentences, default [3]
# 4: text to summarize

if __name__ == "__main__":

    LANGUAGE = str(sys.argv[2])
    decode = sys.argv[4].decode(locale.getpreferredencoding())# decode whatever java probably(!) encoded as
    encode = decode.encode("utf-8", "ignore")# make python compliant

    parser = PlaintextParser.from_string(encode, Tokenizer(LANGUAGE))
    stemmer = Stemmer(LANGUAGE)

    if str(sys.argv[1]) == 'lex_rank':
        summarizer = LexRankSummarizer(stemmer)
    elif str(sys.argv[1]) == 'lsa':
        summarizer = LsaSummarizer(stemmer)
    elif str(sys.argv[1]) == 'luhn':
        summarizer = LuhnSummarizer(stemmer)
    elif str(sys.argv[1]) == 'random':
        summarizer = RandomSummarizer(stemmer)
    elif str(sys.argv[1]) == 'text_rank':
        summarizer = TextRankSummarizer(stemmer)
    else:
        summarizer = LsaSummarizer(stemmer)

    summarizer.stop_words = get_stop_words(LANGUAGE)

    for sentence in summarizer(parser.document, int(sys.argv[3])):
        print(sentence)# note python prints in utf - 8, make sure java reads stream as such