This is my code snippet for where the traceback call shows an error:
def categorize(title):
with conn:
cur= conn.cursor()
title_str= str(title)
title_words= re.split('; |, |\*|\n',title_str)
key_list= list(dictionary.keys())
flag2= 1
for word in title_words:
title_letters= list(word)
flag1= 1
for key in key_list:
if key==title_letters[0]:
flag1= 0
break
if flag1== 0:
start=dictionary.get(title_letters[0])
end= next_val(title_letters[0])
for i in xrange (start,end):
if word==transfer_bag_of_words[i]:
flag2= 0
break
if flag2== 0:
cur.execute("select Id from articles where title=title")
row_id= cur.fetchone()
value= (row_id,'1')
s= str(value)
f.write(s)
f.write("\n")
break
return
def next_val(text):
for i,v in enumerate(keyList):
if text=='t':
return len(transfer_bag_of_words)
elif v==text:
return dictionary[keyList[i+1]]
This is the traceback call:
Traceback (most recent call last):
File "categorize_words.py", line 93, in <module>
query_database()
File "categorize_words.py", line 45, in query_database
categorize(row)
File "categorize_words.py", line 67, in categorize
for i in xrange (start,end):
TypeError: an integer is required
I have not given the whole code here. But I will explain what I am trying to do. I am trying to import a particular field from a sqlite database and checking if a single word of the field matches with a particular bag of words I already have in my program. I have sorted the bag of words aphabetically and assigned every starting of a new letter to it's index using python dictionary. This I have done so that everytime I check a word of the field being present in the bag of words, I do not have to loop through the entire bag of words. Rather I can just start looping from the index of the first letter of the word.
I have checked that the return type of get() in dictionary is int and the function nextVal also should return an int since both len() and dictionary[keylist[i+1]] are int types.
Please help.
EDIT
This is my entire code:
import sqlite3 as sql
import re
conn= sql.connect('football_corpus/corpus2.db')
transfer_bag_of_words=['transfer','Transfer','transfers','Transfers','deal','signs','contract','rejects','bid','rumours','swap','moves',
'negotiation','negotiations','fee','subject','signings','agreement','personal','terms','pens','agent','in','for',
'joins','sell','buy','confirms','confirm','confirmed','signing','renew','joined','hunt','excited','move','sign',
'loan','loaned','loans','switch','complete','offer','offered','interest','price','tag','miss','signed','sniffing',
'remain','plug','pull','race','targeting','targets','target','eye','sale','clause','rejected',
'interested']
dictionary={}
dictionary['a']=0;
keyList=[]
f= open('/home/surya/Twitter/corpus-builder/transfer.txt','w')
def map_letter_to_pos():
pos=0
transfer_bag_of_words.sort()
for word in transfer_bag_of_words:
flag=1
letters= list(word)
key_list= list(dictionary.keys())
for key in key_list:
if key==letters[0]:
flag=0
break
if flag==1:
dictionary[letters[0]]=pos
pos+=1
else:
pos+=1
keyList= sorted(dictionary.keys())
def query_database():
with conn:
cur= conn.cursor()
cur.execute("select title from articles")
row_titles= cur.fetchall()
for row in row_titles:
categorize(row)
def categorize(title):
with conn:
cur= conn.cursor()
title_str= str(title)
title_words= re.split('; |, |\*|\n',title_str)
key_list= list(dictionary.keys())
flag2= 1
for word in title_words:
title_letters= list(word)
flag1= 1
for key in key_list:
if key==title_letters[0]:
flag1= 0
break
if flag1== 0:
start=dictionary.get(title_letters[0])
end= next_val(title_letters[0])
for i in xrange (start,end):
if word==transfer_bag_of_words[i]:
flag2= 0
break
if flag2== 0:
cur.execute("select Id from articles where title=title")
row_id= cur.fetchone()
value= (row_id,'1')
s= str(value)
f.write(s)
f.write("\n")
break
return
def next_val(text):
for i,v in enumerate(keyList):
if text=='t':
return len(transfer_bag_of_words)
elif v==text:
return dictionary[keyList[i+1]]
if __name__=='__main__':
map_letter_to_pos()
query_database()
And this is the downloadable link to the database file http://wikisend.com/download/702374/corpus2.db