Develop Reference

Python 3.6 script surprisingly slow on Windows 10 but not on Ubuntu 17.10

I recently had to write a challenge for a company that was to merge 3 CSV files into one based on the first attribute of each (the attributes were repeating in all files).
I wrote the code and sent it to them, but they said it took 2 minutes to run. That was funny because it ran for 10 seconds on my machine. My machine had the same processor, 16GB of RAM, and had an SSD as well. Very similar environments.
I tried optimising it and resubmitted it. This time they said they ran it on an Ubuntu machine and got 11 seconds, while the code ran for 100 seconds on the Windows 10 still.
Another peculiar thing was that when I tried profiling it with the Profile module, it went on forever, had to terminate after 450 seconds. I moved to cProfiler and it recorded it for 7 seconds.
EDIT: The exact formulation of the problem is
Write a console program to merge the files provided in a timely and
efficient manner. File paths should be supplied as arguments so that
the program can be evaluated on different data sets. The merged file
should be saved as CSV; use the id column as the unique key for
merging; the program should do any necessary data cleaning and error
checking.
Feel free to use any language you’re comfortable with – only
restriction is no external libraries as this defeats the purpose of
the test. If the language provides CSV parsing libraries (like
Python), please avoid using them as well as this is a part of the
test.
Without further ado here's the code:
#!/usr/bin/python3
import sys
from multiprocessing import Pool
HEADERS = ['id']
def csv_tuple_quotes_valid(a_tuple):
"""
checks if a quotes in each attribute of a entry (i.e. a tuple) agree with the csv format
returns True or False
"""
for attribute in a_tuple:
in_quotes = False
attr_len = len(attribute)
skip_next = False
for i in range(0, attr_len):
if not skip_next and attribute[i] == '\"':
if i < attr_len - 1 and attribute[i + 1] == '\"':
skip_next = True
continue
elif i == 0 or i == attr_len - 1:
in_quotes = not in_quotes
else:
return False
else:
skip_next = False
if in_quotes:
return False
return True
def check_and_parse_potential_tuple(to_parse):
"""
receives a string and returns an array of the attributes of the csv line
if the string was not a valid csv line, then returns False
"""
a_tuple = []
attribute_start_index = 0
to_parse_len = len(to_parse)
in_quotes = False
i = 0
#iterate through the string (line from the csv)
while i < to_parse_len:
current_char = to_parse[i]
#this works the following way: if we meet a quote ("), it must be in one
#of five cases: "" | ", | ," | "\0 | (start_of_string)"
#in case we are inside a quoted attribute (i.e. "123"), then commas are ignored
#the following code also extracts the tuples' attributes
if current_char == '\"':
if i == 0 or (to_parse[i - 1] == ',' and not in_quotes): # (start_of_string)" and ," case
#not including the quote in the next attr
attribute_start_index = i + 1
#starting a quoted attr
in_quotes = True
elif i + 1 < to_parse_len:
if to_parse[i + 1] == '\"': # "" case
i += 1 #skip the next " because it is part of a ""
elif to_parse[i + 1] == ',' and in_quotes: # ", case
a_tuple.append(to_parse[attribute_start_index:i].strip())
#not including the quote and comma in the next attr
attribute_start_index = i + 2
in_quotes = False #the quoted attr has ended
#skip the next comma - we know what it is for
i += 1
else:
#since we cannot have a random " in the middle of an attr
return False
elif i == to_parse_len - 1: # "\0 case
a_tuple.append(to_parse[attribute_start_index:i].strip())
#reached end of line, so no more attr's to extract
attribute_start_index = to_parse_len
in_quotes = False
else:
return False
elif current_char == ',':
if not in_quotes:
a_tuple.append(to_parse[attribute_start_index:i].strip())
attribute_start_index = i + 1
i += 1
#in case the last attr was left empty or unquoted
if attribute_start_index < to_parse_len or (not in_quotes and to_parse[-1] == ','):
a_tuple.append(to_parse[attribute_start_index:])
#line ended while parsing; i.e. a quote was openned but not closed
if in_quotes:
return False
return a_tuple
def parse_tuple(to_parse, no_of_headers):
"""
parses a string and returns an array with no_of_headers number of headers
raises an error if the string was not a valid CSV line
"""
#get rid of the newline at the end of every line
to_parse = to_parse.strip()
# return to_parse.split(',') #if we assume the data is in a valid format
#the following checking of the format of the data increases the execution
#time by a factor of 2; if the data is know to be valid, uncomment 3 lines above here
#if there are more commas than fields, then we must take into consideration
#how the quotes parse and then extract the attributes
if to_parse.count(',') + 1 > no_of_headers:
result = check_and_parse_potential_tuple(to_parse)
if result:
a_tuple = result
else:
raise TypeError('Error while parsing CSV line %s. The quotes do not parse' % to_parse)
else:
a_tuple = to_parse.split(',')
if not csv_tuple_quotes_valid(a_tuple):
raise TypeError('Error while parsing CSV line %s. The quotes do not parse' % to_parse)
#if the format is correct but more data fields were provided
#the following works faster than an if statement that checks the length of a_tuple
try:
a_tuple[no_of_headers - 1]
except IndexError:
raise TypeError('Error while parsing CSV line %s. Unknown reason' % to_parse)
#this replaces the use my own hashtables to store the duplicated values for the attributes
for i in range(1, no_of_headers):
a_tuple[i] = sys.intern(a_tuple[i])
return a_tuple
def read_file(path, file_number):
"""
reads the csv file and returns (dict, int)
the dict is the mapping of id's to attributes
the integer is the number of attributes (headers) for the csv file
"""
global HEADERS
try:
file = open(path, 'r');
except FileNotFoundError as e:
print("error in %s:\n%s\nexiting...")
exit(1)
main_table = {}
headers = file.readline().strip().split(',')
no_of_headers = len(headers)
HEADERS.extend(headers[1:]) #keep the headers from the file
lines = file.readlines()
file.close()
args = []
for line in lines:
args.append((line, no_of_headers))
#pool is a pool of worker processes parsing the lines in parallel
with Pool() as workers:
try:
all_tuples = workers.starmap(parse_tuple, args, 1000)
except TypeError as e:
print('Error in file %s:\n%s\nexiting thread...' % (path, e.args))
exit(1)
for a_tuple in all_tuples:
#add quotes to key if needed
key = a_tuple[0] if a_tuple[0][0] == '\"' else ('\"%s\"' % a_tuple[0])
main_table[key] = a_tuple[1:]
return (main_table, no_of_headers)
def merge_files():
"""
produces a file called merged.csv
"""
global HEADERS
no_of_files = len(sys.argv) - 1
processed_files = [None] * no_of_files
for i in range(0, no_of_files):
processed_files[i] = read_file(sys.argv[i + 1], i)
out_file = open('merged.csv', 'w+')
merged_str = ','.join(HEADERS)
all_keys = {}
#this is to ensure that we include all keys in the final file.
#even those that are missing from some files and present in others
for processed_file in processed_files:
all_keys.update(processed_file[0])
for key in all_keys:
merged_str += '\n%s' % key
for i in range(0, no_of_files):
(main_table, no_of_headers) = processed_files[i]
try:
for attr in main_table[key]:
merged_str += ',%s' % attr
except KeyError:
print('NOTE: no values found for id %s in file \"%s\"' % (key, sys.argv[i + 1]))
merged_str += ',' * (no_of_headers - 1)
out_file.write(merged_str)
out_file.close()
if __name__ == '__main__':
# merge_files()
import cProfile
cProfile.run('merge_files()')
# import time
# start = time.time()
# print(time.time() - start);
Here is the profiler report I got on my Windows.
EDIT: The rest of the csv data provided is here. Pastebin was taking too long to process the files, so...
It might not be the best code and I know that, but my question is what slows down Windows so much that doesn't slow down an Ubuntu? The merge_files() function takes the longest, with 94 seconds just for itself, not including the calls to other functions. And there doesn't seem to be anything too obvious to me for why it is so slow.
Thanks
EDIT: Note: We both used the same dataset to run the code with.

It turns out that Windows and Linux handle very long strings differently. When I moved the out_file.write(merged_str) inside the outer for loop (for key in all_keys:) and stopped appending to merged_str, it ran for 11 seconds as expected. I don't have enough knowledge on either of the OS's memory management systems to be able to give a prediction on why it is so different.
But I would say that the way that the second one (the Windows one) is the more fail-safe method because it is unreasonable to keep a 30 MB string in memory. It just turns out that Linux sees that and doesn't always try to keep the string in cache, or to rebuild it every time.
Funny enough, initially I did run it a few times on my Linux machine with these same writing strategies, and the one with the large string seemed to go faster, so I stuck with it. I guess you never know.
Here's the modified code
for key in all_keys:
merged_str = '%s' % key
for i in range(0, no_of_files):
(main_table, no_of_headers) = processed_files[i]
try:
for attr in main_table[key]:
merged_str += ',%s' % attr
except KeyError:
print('NOTE: no values found for id %s in file \"%s\"' % (key, sys.argv[i + 1]))
merged_str += ',' * (no_of_headers - 1)
out_file.write(merged_str + '\n')
out_file.close()

When I run your solution on Ubuntu 16.04 with the three given files, it seems to take ~8 seconds to complete. The only modification I made was to uncomment the timing code at the bottom and use it.
$ python3 dimitar_merge.py file1.csv file2.csv file3.csv
NOTE: no values found for id "aaa5d09b-684b-47d6-8829-3dbefd608b5e" in file "file2.csv"
NOTE: no values found for id "38f79a49-4357-4d5a-90a5-18052ef03882" in file "file2.csv"
NOTE: no values found for id "766590d9-4f5b-4745-885b-83894553394b" in file "file2.csv"
8.039648056030273
$ python3 dimitar_merge.py file1.csv file2.csv file3.csv
NOTE: no values found for id "38f79a49-4357-4d5a-90a5-18052ef03882" in file "file2.csv"
NOTE: no values found for id "766590d9-4f5b-4745-885b-83894553394b" in file "file2.csv"
NOTE: no values found for id "aaa5d09b-684b-47d6-8829-3dbefd608b5e" in file "file2.csv"
7.78482985496521
I rewrote my first attempt without using csv from the standard library and am now getting times of ~4.3 seconds.
$ python3 lettuce_merge.py file1.csv file2.csv file3.csv
4.332579612731934
$ python3 lettuce_merge.py file1.csv file2.csv file3.csv
4.305467367172241
$ python3 lettuce_merge.py file1.csv file2.csv file3.csv
4.27345871925354
This is my solution code (lettuce_merge.py):
from collections import defaultdict
def split_row(csv_row):
return [col.strip('"') for col in csv_row.rstrip().split(',')]
def merge_csv_files(files):
file_headers = []
merged_headers = []
for i, file in enumerate(files):
current_header = split_row(next(file))
unique_key, *current_header = current_header
if i == 0:
merged_headers.append(unique_key)
merged_headers.extend(current_header)
file_headers.append(current_header)
result = defaultdict(lambda: [''] * (len(merged_headers) - 1))
for file_header, file in zip(file_headers, files):
for line in file:
key, *values = split_row(line)
for col_name, col_value in zip(file_header, values):
result[key][merged_headers.index(col_name) - 1] = col_value
file.close()
quotes = '"{}"'.format
with open('lettuce_merged.csv', 'w') as f:
f.write(','.join(quotes(a) for a in merged_headers) + '\n')
for key, values in result.items():
f.write(','.join(quotes(b) for b in [key] + values) + '\n')
if __name__ == '__main__':
from argparse import ArgumentParser, FileType
from time import time
parser = ArgumentParser()
parser.add_argument('files', nargs='*', type=FileType('r'))
args = parser.parse_args()
start_time = time()
merge_csv_files(args.files)
print(time() - start_time)
I'm sure this code could be optimized even further but sometimes just seeing another way to solve a problem can help spark new ideas.

opening shelf file / dbm file returns error dbmError created file using dbm.open and shelve.Shelf.open

python 3.4.2, on Linux
I'm pretty new to this language but I'm coding this project. It started as a simple program that displayed a dictionary . Well I'm trying to expand on it based on tutorials that i am reading. I came to one about shelving and being able to preserve info in a save file in a format much like a dictionary. So far i have a program that takes input and updates the dictionary based on the input. It's very basic but it works on a simple level but naturally I would want to save what I entered. Following is the code so far.
the updateSaveP1() function is what is giving me trouble. Although not coded like this currently, i would ultimately like the function to take 2 arguments, one to name the key in the shelf file, and one to reference the target dictionary/ list etc. Currently its not even saving to the file.
the loadINV() function is a place holder and doent work as coded currently. i need to figure out the dbm problem first as i get the same dbmError with the load function too.
I originally just .opened the file. found documentation here at Stack that i should open it with either so that it creates the right file. I have tried both to no avail.
NOTICE**** this code will create an empty file on your system at the working directory of python named savedata.db
Much Thanks and appreciation for any help.
`import pygame, math, sys, os, pprint, shelve, dbm,
SAVE_LOCATION = os.path.join(os.getcwd() + '/savedata')
SAVE_FILE_LIST = os.listdir(os.getcwd())
SOURCE = os.path.dirname('inventory.py')
YES = ["y","Y"]
NO = ["n","N"]
playerStash = {"rope": 77,
"giant's toe" : 1,
"gold" : 420}
'''def loadINV():
fileTOload = dbm.open('savedata.db', 'w')
print('opened savedata file')
#for eachLine in fileTOload:
playerStash.update(str(fileTOload.read())
)
print('updated dict')
fileTOload.close()'''
def checkSavesFile():
while True:
if os.path.exists(SAVE_LOCATION):
print('Save file found')
break
elif os.path.exists(SAVE_LOCATION + '.db'):
print('.db Save file found')
loadINV()
break
else:
updateSaveP1()
print('New Save Created')
break
def updateSaveP1():
with dbm.open('savedata', 'c') as save:
save['player1'] = str(playerStash)
save.close()
#print(SAVE_LOCATION) #debugging - file name format verification
#pprint.pprint(SAVE_FILE_LIST) debugging will pretty print list of files
checkSavesFile() # runs the save file check
def askAboutInv(player):
while True:
print("What item would you like to add? \n\
(leave blank and press enter to quit)")
name = input() # Reads input and checks for duplicates or non entries
if name == '':
break # Stop loop
elif name in playerStash.keys():
# the check to see if input was in dictionary
dict_quant = int(playerStash.get(name, 0))
# "dict_quant" represents the value in dictionary as an integer
dict_item = str(playerStash.get(name, 0))
# "dict_item represents the value in dictionary as a string
addedItem = dict_quant + 1
#handles adding the value of the input
print("You have " + dict_item + " already, \n\
would you like to add more Y/N?")
# prints " You have "dictionary number" already"
answer = input()
# checks for input if you want to add more to inventory
if answer in YES: #checks to see if y or Y is entered
playerStash[name] = addedItem
# adds +1 to the quantity of "name" per the dict_quant variable
print("you have " + str(addedItem) + " now")
# prints " you have "new dictionary number" now"
if answer in NO: #checks to see if n or N was entered
print("Nothing added") #prints
break #ends loop
else: #if none others statements are true
if name not in playerStash.keys():
#if "name" / input is not in the dictionary
playerStash[name] = playerStash.setdefault(name, 1)
# add the item to the dictionary with a value of 1
print('Inventory updated.')
# prints
updateSaveP1()
def inventoryDisp(player):# displays dictionary pointing towards argument
print("Inventory")
item_total = 0
for eachOne in playerStash.items():
print(eachOne) # looks at and prints each item/ key in dictionary
for i, q in playerStash.items():
item_total = item_total + q #adds all the quantities / values up
print("Total number of items: " + str(item_total))
# prints total number of items in inventory
def updatedInv(player): #same as above just reads "updated inventory"
print("Updated Inventory")
item_total = 0
for eachOne in playerStash.items():
print(eachOne)
for i, q in playerStash.items():
item_total = item_total + q
print("Total number of items: " + str(item_total))
inventoryDisp(playerStash)
askAboutInv(playerStash)
updateSaveP1()
updatedInv(playerStash)`
Update*****
after changing this:
`def updateSaveP1():
with dbm.open('savedata', 'c') as save:
save['player1'] = str(playerStash)
save.close()`
to this:
`def updateSaveP1():
save = openShelf()
#save = shelve.Shelf(dbm.open('savedata', 'c')) #old code
save['player1'] = str(playerStash)
print(save['player1'])
save.close()`
it would seem that the dictionary does get saved. now the loadINV function is giving me trouble. This:
def loadINV():
fileTOload = dbm.open('savedata.db', 'w')
print('opened savedata file')
#for eachLine in fileTOload:
playerStash.update(str(fileTOload.read())
)
print('updated dict')
fileTOload.close()
is now this:
def loadINV():
file = openShelf()
print('opened savedata file')
playerStash.update(file['player1'])
print('updated dict')
fileTOload.close()
but the .update() method returns this error: which i can't seem to find any info.
Traceback (most recent call last):
File "/home/pi/inventoryShelve.py", line 58, in <module>
checkSavesFile() # runs the save file check
File "/home/pi/inventoryShelve.py", line 40, in checkSavesFile
loadINV()
File "/home/pi/inventoryShelve.py", line 25, in loadINV
playerStash.update(file['player1'])
ValueError: dictionary update sequence element #0 has length 1; 2 is required

Turned out I was saving (into the shelf) the data for the inventory dictionary as something other than a dict:
def updateSaveP1():
save = openShelf()
save['player1'] = str(playerStash)
#print(save['player1'])
save.close()
became
def updateSaveP1():
save = openShelf()
save['player1'] = dict(playerStash)
#print(save['player1'])
save.close()

unknown error in jython when use startswith()

I'm using python to analyze some records bib and ris files. I made two functions for each type. The first function is the one you see below:
def limpiarlineasris(self, data):
cont = data
dic = cont.splitlines()
cont = ""
con = []
i = 0
for a in dic:
if len(a) != 0:
con.append(a)
for a in con:
cont = cont + a + "\n"
return cont
That works well and I can compile without problem. The problem arises when I write the second function see below:
def limpiarlineasbib(self, data):
cont = data
dic = cont.splitlines()
cont = ""
con = []
separador = "°-°-°"
for a in dic:
if len(a)!= 0:
if a.startswith('#'):
con.append(separador)
else:
con.append(a)
for a in con:
cont = cont + a + "\n"
return cont
When building the first function no problem. But when I compile the second compiler shows me an error but does not tell me exactly what or where it is because I am using plyjy a jar to create Jython objects, and the console only shows me an exception Plyjy without the line where it occurs. I'm using Netbeans to compile

Python: For loop only loops over the first part of a txt file

Recently I had to make a script for my internship to check if a subnet occurs in a bunch of router/switch configs.
I've made a script that generates the output. Now I need a second script (I couldn't get it to work into one), that reads the output, if the subnet occurs write it to aanwezig.txt, if not write to nietAanwezig.txt.
A lot of other answers helped me to make this script and it works but it only executes for the first 48 IPs and there are over 2000...
The code of checkOutput.py:
def main():
file = open('../iprangesclean.txt', 'rb')
aanwezig = open('../aanwezig.txt', 'w')
nietAanwezig = open('../nietAanwezig.txt', 'w')
output = open('output.txt', 'rb')
for line in file:
originalLine = line
line.rstrip()
line = line.replace(' ', '')
line = line.replace('\n', '')
line = line.replace('\r', '')
one,two,three,four = line.split('.')
# 3Byte IP:
ipaddr = str(one) + "." + str(two) + "." + str(three)
counter = 1
found = 0
for lijn in output:
if re.search("\b{0}\b".format(ipaddr),lijn) and found == 0:
found = 1
else:
found = 2
print counter
counter= counter + 1
if found == 1:
aanwezig.write(originalLine)
print "Written to aanwezig"
elif found == 2:
nietAanwezig.write(originalLine)
print "Written to nietAanwezig"
found = 0
file.close()
aanwezig.close()
nietAanwezig.close()
main()
The format of iprangesclean.txt is like following:
10.35.6.0/24
10.132.42.0/24
10.143.26.0/24
10.143.30.0/24
10.143.31.0/24
10.143.32.0/24
10.35.7.0/24
10.143.35.0/24
10.143.44.0/24
10.143.96.0/24
10.142.224.0/24
10.142.185.0/24
10.142.32.0/24
10.142.208.0/24
10.142.70.0/24
and so on...
Part of output.txt (I can't give you everything because it has user information):
*name of device*.txt:logging 10.138.200.100
*name of device*.txt:access-list 37 permit 10.138.200.96 0.0.0.31
*name of device*.txt:access-list 38 permit 10.138.200.100
*name of device*.txt:snmp-server host 10.138.200.100 *someword*
*name of device*.txt:logging 10.138.200.100

Try this change:
for lijn in output:
found = 0 # put this here
if re.search("\b{0}\b".format(ipaddr),lijn) and found == 0:
found = 1
else:
found = 2
print counter
counter= counter + 1
"""Indent one level so it us in the for statement"""
if found == 1:
aanwezig.write(originalLine)
print "Written to aanwezig"
elif found == 2:
nietAanwezig.write(originalLine)
print "Written to nietAanwezig"
If I understand the problem correctly, this should guide you to the right direction. The if statement is currently not executed in the for statement. If this does solve your problem, then you don't need the found variable either. You can just have something like:
for counter, lijn in enumerate(output, 1):
if re.search("\b{0}\b".format(ipaddr),lijn):
aanwezig.write(originalLine)
print "Written to aanwezig"
else:
nietAanwezig.write(originalLine)
print "Written to nietAanwezig"
print counter
Please let me know if I have misunderstood the question.
Note I haven't tested the code above, try them out as a starting point.

Userfriendly way of handling config files in python?

I want to write a program that sends an e-mail to one or more specified recipients when a certain event occurs. For this I need the user to write the parameters for the mail server into a config. Possible values are for example: serveradress, ports, ssl(true/false) and a list of desired recipients.
Whats the user-friendliest/best-practice way to do this?
I could of course use a python file with the correct parameters and the user has to fill it out, but I wouldn't consider this user friendly. I also read about the 'config' module in python, but it seems to me that it's made for creating config files on its own, and not to have users fill the files out themselves.

Are you saying that the fact that the config file would need to be valid Python makes it unfriendly? It seems like having lines in a file like:
server = 'mail.domain.com'
port = 25
...etc would be intuitive enough while still being valid Python. If you don't want the user to have to know that they have to quote strings, though, you might go the YAML route. I use YAML pretty much exclusively for config files and find it very intuitive, and it would also be intuitive for an end user I think (though it requires a third-party module - PyYAML):
server: mail.domain.com
port: 25
Having pyyaml load it is simple:
>>> import yaml
>>> yaml.load("""a: 1
... b: foo
... """)
{'a': 1, 'b': 'foo'}
With a file it's easy too.
>>> with open('myconfig.yaml', 'r') as cfile:
... config = yaml.load(cfile)
...
config now contains all of the parameters.

I doesn't matter technically proficient your users are; you can count on them to screw up editing a text file. (They'll save it in the wrong place. They'll use MS Word to edit a text file. They'll make typos.) I suggest making a gui that validates the input and creates the configuration file in the correct format and location. A simple gui created in Tkinter would probably fit your needs.

I've been using ConfigParser. It's designed to read .ini style files that have:
[section]
option = value
It's quite easy to use and the documentation is pretty easy to read. Basically you just load the whole file into a ConfigParser object:
import ConfigParser
config = ConfigParser.ConfigParser()
config.read('configfile.txt')
Then you can make sure the users haven't messed anything up by checking the options. I do so with a list:
OPTIONS =
['section,option,defaultvalue',
.
.
.
]
for opt in OPTIONS:
section,option,defaultval = opt.split(',')
if not config.has_option(section,option):
print "Missing option %s in section %s" % (option,section)
Getting the values out is easy too.
val = config.get('section','option')
And I also wrote a function that creates a sample config file using that OPTIONS list.
new_config = ConfigParser.ConfigParser()
for opt in OPTIONS:
section,option,defaultval = opt.split(',')
if not new_config.has_section(section):
new_config.add_section(section)
new_config.set(section, option, defaultval)
with open("sample_configfile.txt", 'wb') as newconfigfile:
new_config.write(newconfigfile)
print "Generated file: sample_configfile.txt"

What are the drawbacks of such a solution:
ch = 'serveradress = %s\nport = %s\nssl = %s'
a = raw_input("Enter the server's address : ")
b = 'a'
bla = "\nEnter the port : "
while not all(x.isdigit() for x in b):
b = raw_input(bla)
bla = "Take care: you must enter digits exclusively\n"\
+" Re-enter the port (digits only) : "
c = ''
bla = "\nChoose the ssl option (t or f) : "
while c not in ('t','f'):
c = raw_input(bla)
bla = "Take care: you must type f or t exclusively\n"\
+" Re-choose the ssl option : "
with open('configfile.txt','w') as f:
f.write(ch % (a,b,c))
.
PS
I've read in the jonesy's post that the value in a config file may have to be quoted. If so, and you want the user not to have to write him/her-self the quotes, you simply add
a = a.join('""')
b = b.join('""')
c = c.join('""')
.
EDIT
ch = 'serveradress = %s\nport = %s\nssl = %s'
d = {0:('',
"Enter the server's address : "),
1:("Take care: you must enter digits exclusively",
"Enter the port : "),
2:("Take care: you must type f or t exclusively",
"Choose the ssl option (t or f) : ") }
def func(i,x):
if x is None:
return False
if i==0:
return True
elif i==1:
try:
ess = int(x)
return True
except:
return False
elif i==2:
if x in ('t','f'):
return True
else:
return False
li = len(d)*[None]
L = range(len(d))
while True:
for n in sorted(L):
bla = d[n][1]
val = None
while not func(n,val):
val = raw_input(bla)
bla = '\n '.join(d[n])
li[n] = val.join('""')
decision = ''
disp = "\n====== If you choose to process, =============="\
+"\n the content of the file will be :\n\n" \
+ ch % tuple(li) \
+ "\n==============================================="\
+ "\n\nDo you want to process (type y) or to correct (type c) : "
while decision not in ('y','c'):
decision = raw_input(disp)
disp = "Do you want to process (type y) or to correct (type c) ? : "
if decision=='y':
break
else:
diag = False
while not diag:
vi = '\nWhat lines do you want to correct ?\n'\
+'\n'.join(str(j)+' - '+line for j,line in enumerate((ch % tuple(li)).splitlines()))\
+'\nType numbers of lines belonging to range(0,'+str(len(d))+') separated by spaces) :\n'
to_modify = raw_input(vi)
try:
diag = all(int(entry) in xrange(len(d)) for entry in to_modify.split())
L = [int(entry) for entry in to_modify.split()]
except:
diag = False
with open('configfile.txt','w') as f:
f.write(ch % tuple(li))
print '-*- Recording of the config file : done -*-'