#!/usr/bin/env python2.7

"""
Example IDA Python script to get "names" (functions, variables, etc...) from string constants
using Natural Language Processing.
"""

from __future__ import print_function

import pprint
import idautils

import nltk
from nltk.tokenize import word_tokenize
from nltk.tag import pos_tag

def preprocess(sent):
  sent = nltk.word_tokenize(sent)
  sent = nltk.pos_tag(sent)
  return sent

strings = Strings()
strings.setup(strtypes=[0, 1])

s = "\n".join(map(str, list(strings)))
results = preprocess(s)
for value, type in results:
  if len(value) > 4 and (type == "NN" or type.startswith("VB")):
    print("Found", value, "type", type)