VTSTech-NLTK Script v0.43

VTSTech-NLTK.py

#NLTK Script v0.2 2020-03-11 9:25:03 PM
#Written by VTSTech (veritas@vts-tech.org)
#Various functions inspired by code from sentdex/pythonprogramming.net
#https://pythonprogramming.net/tokenizing-words-sentences-nltk-tutorial/

import sys, nltk, os, string
from nltk import pos_tag
from nltk.tokenize import sent_tokenize, word_tokenize, SpaceTokenizer, PunktSentenceTokenizer
from nltk.stem import PorterStemmer, WordNetLemmatizer
from nltk.corpus import wordnet, state_union

synonyms = []
antonyms = []
train_text = state_union.raw("1999-Clinton.txt")
custom_sent_tokenizer = PunktSentenceTokenizer(train_text)

def banner():
				print("NLTK Script v0.2 03-11-2020\nWritten by VTSTech (veritas@vts-tech.org)\n")
				print("Usage:", os.path.basename(__file__),"mode \"word or sentence\"\n")
def spc_tok():
				#print("[+] SpaceTokenizer imported.")
				print("[+] Target:", sys.argv[2])
				print("[+] Output:",end='')
				print(SpaceTokenizer().tokenize(sys.argv[2]))
				print("[+] Complete.")        
def syn_ant():
	      #print("[+] wordnet imported.")
	      for syn in wordnet.synsets(sys.argv[2]):
	          for l in syn.lemmas():
	              synonyms.append(l.name())
	          if l.antonyms():
	              antonyms.append(l.antonyms()[0].name())
	      print("[+] Target:", sys.argv[2])
	      target = wordnet.synsets(sys.argv[2])
	      if (len(target) >= 1): print("[+] Defined:", target[0].definition())
	      print("[+] Output:")
	      if (len(set(synonyms))>0):
	      	print("Syn:", set(synonyms))
	      else:
	      	print("Syn: Failed to find synonym!")
	      if (len(set(antonyms))>0):
	      	print("Ant:", set(antonyms))
	      else:
	      	print("Ant: Failed to find antonym!")
	      print("[+] Complete.")
def stem():
        ps = PorterStemmer()
        #print("[+] PorterStemmer imported.")
        print("[+] Target:",sys.argv[2])
        print("[+] Output: ", end='')
        words = SpaceTokenizer().tokenize(sys.argv[2])
        for w in words:
            print(ps.stem(w))
        print("[+] Complete.")
def lemma():
		    lemmatizer = WordNetLemmatizer()
		    #print("[+] WordNetLemmatizer imported.")
		    #pos=a,s,v,r
		    print("[+] Target:",sys.argv[2])
		    print("[+] Output: ",end='')
		    if (len(sys.argv) == 4):
		    	#print("DEBUG:", sys.argv[3])
		    	print(lemmatizer.lemmatize(sys.argv[2], pos=sys.argv[3]))
		    else:
		        print(lemmatizer.lemmatize(sys.argv[2]))
		    print("[+] Complete.")        
def postag():
				#print("[+] pos_tag, SpaceTokenizer imported.")
				print("[+] Target:", sys.argv[2])
				print("[+] Output:", end='')
				print(pos_tag(SpaceTokenizer().tokenize(sys.argv[2])))
				print("[+] Complete.")
def nltk_download():
				print("[+] NLTK Downloader launching...\n")
				nltk.download()
				print("[+] Complete.")
def ner():
			  tokenized = custom_sent_tokenizer.tokenize(sys.argv[2])
			  try:
			      for i in tokenized:
			          words = nltk.word_tokenize(i)
			          tagged = nltk.pos_tag(words)
			          namedEnt = nltk.ne_chunk(tagged, binary=True)
			          print("[+] Target:", sys.argv[2])
			          print("[+] Output:", end='')
			          print(namedEnt)
			  except Exception as e:
			      print(str(e))
			  print("[+] Complete.")
###
def main():
				if (len(sys.argv) == 2) and ("nltk_download" in sys.argv[1]):
				        banner()
				        nltk_download()
				elif (len(sys.argv) <= 2) and ("VTSTech-NLTK.py" in sys.argv[0]):
				        banner()
				        print("Modes:\n\nspc_tok\nsyn_ant\nstem\nlemma\npos_tag\nner\nnltk_download")
				else:
				        banner()
				        if ("spc_tok" in sys.argv[1]): # expects "a complete sentence."
				            spc_tok()
				        if ("syn_ant" in sys.argv[1]): # expects word
				            syn_ant()
				        if ("stem" in sys.argv[1]):    # expects word
				            stem()       
				        if ("lemma" in sys.argv[1]):   # expects word
				            lemma()                   
				        if ("pos_tag" in sys.argv[1]): # expects "a complete sentence."
				            postag()
				        if ("ner" in sys.argv[1]):     # expects "a complete sentence."
				            ner()		            
###
main()