postagger.py

# 
# Panduan Penggunaan pebahasa untuk POS Tagger
# 
from hmmtagger import MainTagger
from tokenization import *

mt = None

def init_tag():
    global mt
    if mt is None:
        mt = MainTagger("resource/Lexicon.trn", "resource/Ngram.trn", 0, 3, 3, 0, 0, False, 0.2, 0, 500.0, 1)
    
def do_tag(str_masukan):
    lines = str_masukan.strip().split("\n")
    result = []
    try:
        init_tag()
        for l in lines:
            if len(l) == 0: continue
            #sentence_extraction, cleaning, dan tokenisasi_kalimat ada di file tokenization.py
            out = sentence_extraction(cleaning(l))
            for o in out:
                strtag = " ".join(tokenisasi_kalimat(o)).strip()
                result += [" ".join(mt.taggingStr(strtag))]
    except:
        return "Error Exception"
    return "\n".join(result)