def get_query():
'''
get_query()
This is a helper function to input the requested query.
'''
global Q
print "Audio input or text..???? 1 for audio and 2 for text "
x = raw_input()
x = int(x)
if (x == 1):
s = audio_to_text()
else:
s = raw_input("Enter Query: Ctrl+C to exit\n")
f = open('temp_porter.txt', "w")
f.write(s + "\n")
f.close()
lis = porter.inputs(['temp_porter.txt'])
lis = lis[0]
Q = ""
lis = auto_correct(nltk.word_tokenize(lis))
if (lis == -1):
return -1
else:
return lis
def fileread():
'''
fileread() function read all the files in the corpus and index them into the dictionary.
This function uses the porter algorithm and is generating a list of tokens for each document using the nltk.word_tokenize() function in the "punkt" library.
'''
filename = []
global doc_to_int
lis_of_docs = os.listdir("docs/")
len_of_corpus = 1 #actual size = 50
#import codecs
#f = codecs.open('C:\Python26\text.txt', 'r', 'utf-8-sig')
for i in lis_of_docs:
filename.append("docs/" + str(i))
doc_to_int.update({int(len_of_corpus): str(i)})
len_of_corpus += 1
#filename=['1.txt','2.txt']
lis = porter.inputs(filename)
tokens = []
n = 1
#n=len(lis)
for l in lis:
tokens.append([n] + nltk.word_tokenize(l))
n += 1
#print(len(tokens))
global NO_OF_DOC
NO_OF_DOC = len(tokens)
for t in tokens:
index(t)
print("Done indexing\n")
fo = open('big.txt', "w")
def get_query():
'''
get_query()
This is a helper function to input the requested query.
'''
global Q
s=input("Enter Query: Ctrl+C to exit\n")
f=open('temp_porter.txt',"w")
f.write(s+"\n")
f.close()
lis=porter.inputs(['temp_porter.txt'])
lis=lis[0]
Q=""
lis=auto_correct(nltk.word_tokenize(lis))
if(lis == -1):
return -1
else:
return lis
def fileread():
'''
fileread() function read all the files in the corpus and index them into the dictionary.
This function uses the porter algorithm and is generating a list of tokens for each document using the nltk.word_tokenize() function in the "punkt" library.
'''
filename=[]
len_of_corpus=51 #actual size = 50
for i in range(1,len_of_corpus):
filename.append(str(i)+".txt")
#filename=['1.txt','2.txt']
lis = porter.inputs(filename)
tokens=[]
n=1
#n=len(lis)
for l in lis:
tokens.append([n]+nltk.word_tokenize(l))
n+=1
#print(len(tokens))
global NO_OF_DOC
NO_OF_DOC= len(tokens)
for t in tokens:
index(t)
print("Done indexing\n")
fo=open('big.txt',"w")