Poor mans csv readers

gistfile1.py

import re

from pprint import pprint
 
def option1(fn):
    '''the screwy quoting break the csv module, so we just have to do it ourselves'''
    
    data = []
    with open(fn, mode='r') as fh:
        for r in fh:
            if r:
                data.append(r.strip().split(','))
    return data

'''generators are just like functions, except they return piece by piece'''
'''this is really useful in processing files'''
'''so let's do this again, using a generator to slice through the file'''

def gen_option2(fn):
    '''generator for option 2'''
    with open(fn, mode='r') as fh:
        for r in fh:
            if r:
                yield [i.strip('[\'\"]') for i in r.strip().split(',')]
    
def option2(fn):
    '''this option uses a generator to make things a bit cleaner'''
    data = []
    for row in gen_option2(fn):
        data.append(row)
    return data

'''ok, now let's really clean up the data'''
'''this option uses a helper function cleaner(item) that cleans item'''
'''the cleaner function takes in a string and:
    1.  changes blanks to a Nonetype
    2.  changes strings that are floats, like "1.23" into actual floats, e.g. 1.23
    3.  changes ints into ints, so if 1.0 == 1, it returns just int(1)
    4.  removes extra spaces from strings

'''

def gen_option3(fn):
    '''generator for option 3'''
    '''just like option 2, but uses cleaner on each (i)'''
    with open(fn, mode='r') as fh:
        for r in fh:
            if r:
                yield [cleaner(i) for i in r.strip().split(',')]


def cleaner(i):
    '''this is the cleaner function described above'''
    i = i.strip('[\'\"]')
    if not i:
        return None
    try:
        i = float(i)
        if int(i) == i:
            i = int(i)
    except ValueError:
        # ok we have a string
        # let's get rid of excess spaces
        i = re.sub('\s+',' ',i)
    return i

def option3(fn):
    '''ok, let's extend the generator and add in a cleaner function'''
    '''to pretty things up some more'''
    data = []
    for row in gen_option3(fn):
        data.append(row)
    return data
    
def main():
    x = option3('FILE2.COMPAS')
    x = option3('file1.REAL')
    pprint(x)
    print(x[0][0])
    
if __name__ == '__main__':
 
    main()