op_type_span.append(ele_id) opinion_type.append(op_type_span) opinion.append(opinion_type) return opinion if __name__ == '__main__': my_time_stamp = True try: opts, args = getopt.getopt(sys.argv[1:],"",["no-time"]) for opt, arg in opts: if opt == "--no-time": my_time_stamp = False except getopt.GetoptError: pass kafObj = KafParser(sys.stdin) data_str = kafObj.getSentimentTriples() data= convertPolarityToFloats(data_str) my_data_neg = applyNegators(data) my_data_neg_int = applyIntensifiers(my_data_neg) total = computeTotal(my_data_neg_int) opinionObj = createOpinion(kafObj,total) kafObj.addLayer('opinions',opinionObj) kafObj.addLinguisticProcessor('RuleBasedSentimentAnalyzer','1.0','opinion',time_stamp=my_time_stamp) kafObj.saveToFile(sys.stdout)
print>>sys.stderr,'Example usage: cat myUTF8file.kaf.xml |',sys.argv[0] sys.exit(-1) my_time_stamp = True try: opts, args = getopt.getopt(sys.argv[1:],"",["no-time"]) for opt, arg in opts: if opt == "--no-time": my_time_stamp = False except getopt.GetoptError: pass logging.debug('Starting stanford parser for German text') logging.debug('Loading and parsing KAF file ...') my_kaf = KafParser(sys.stdin) lang = my_kaf.getLanguage() if lang != 'de': print>>sys.stdout,'ERROR! Language is',lang,'and must be "de" (German)' sys.exit(-1) logging.debug('Extracting sentences from the KAF') termid_for_token = {} lemma_for_termid = {} for term in my_kaf.getTerms(): lemma_for_termid[term.getId()] = term.getLemma() tokens_id = term.get_list_span() for token_id in tokens_id: termid_for_token[token_id] = term.getId()
print >> sys.stderr, 'Input stream required in KAF format at least with the text layer.' print >> sys.stderr, 'The language encoded in the KAF has to be Dutch, otherwise it will raise an error.' print >> sys.stderr, 'Example usage: cat myUTF8file.kaf.xml |', sys.argv[0] sys.exit(-1) my_time_stamp = True try: opts, args = getopt.getopt(sys.argv[1:], "", ["no-time"]) for opt, arg in opts: if opt == "--no-time": my_time_stamp = False except getopt.GetoptError: pass logging.debug('Loading and parsing KAF file ...') my_kaf = KafParser(sys.stdin) lang = my_kaf.getLanguage() if lang != 'nl': print >> sys.stdout, 'ERROR! Language is ', lang, ' and must be nl (Dutch)' sys.exit(-1) logging.debug('Extracting sentences from the KAF') sentences = [] current_sent = [] term_ids = [] current_sent_tid = [] lemma_for_termid = {} termid_for_token = {}
logging.getLogger().setLevel(logging.ERROR) numNegators = 0 ## READ the data and create structure for terms if not sys.stdin.isatty(): ## READING FROM A PIPE logging.debug('Reading from standard input') fic = sys.stdin else: print >> sys.stderr, 'Input stream required.' print >> sys.stderr, 'Example usage: cat myUTF8file.kaf.xml |', sys.argv[ 0] print >> sys.stderr, sys.argv[0] + ' -h for help' sys.exit(-1) kafParserObj = KafParser(fic) for term in kafParserObj.getTerms(): terms.append(term) logging.debug('Number of terms loaded ' + str(len(terms))) ## Load lexicons lang = kafParserObj.getLanguage() ##lexSent = LexiconSent(lang,'general') lexSent = LexiconSent(lang, arguments.lexicon, arguments.lexicon_path) ##Default lexicons ################ ## For each term, establish its sentiment polarity
opinion_type.append(op_type_span) opinion.append(opinion_type) return opinion if __name__ == '__main__': my_time_stamp = True try: opts, args = getopt.getopt(sys.argv[1:], "", ["no-time"]) for opt, arg in opts: if opt == "--no-time": my_time_stamp = False except getopt.GetoptError: pass kafObj = KafParser(sys.stdin) data_str = kafObj.getSentimentTriples() data = convertPolarityToFloats(data_str) my_data_neg = applyNegators(data) my_data_neg_int = applyIntensifiers(my_data_neg) total = computeTotal(my_data_neg_int) opinionObj = createOpinion(kafObj, total) kafObj.addLayer('opinions', opinionObj) kafObj.addLinguisticProcessor('RuleBasedSentimentAnalyzer', '1.0', 'opinion', time_stamp=my_time_stamp) kafObj.saveToFile(sys.stdout)
numNegators = 0 ## READ the data and create structure for terms if not sys.stdin.isatty(): ## READING FROM A PIPE logging.debug('Reading from standard input') fic = sys.stdin else: print>>sys.stderr,'Input stream required.' print>>sys.stderr,'Example usage: cat myUTF8file.kaf.xml |',sys.argv[0] print>>sys.stderr,sys.argv[0]+' -h for help' sys.exit(-1) kafParserObj = KafParser(fic) for term in kafParserObj.getTerms(): terms.append(term) logging.debug('Number of terms loaded '+str(len(terms))) ## Load lexicons lang = kafParserObj.getLanguage() ##lexSent = LexiconSent(lang,'general') lexSent = LexiconSent(lang,arguments.lexicon,arguments.lexicon_path) ##Default lexicons ################