You're probably sorting them by ascii string-comparison ('.' < '5', etc.), when you'd rather that they sort numerically. Try converting them to tuples of ints, then sorting:
def ipPortToTuple(string):
"""
'12.34.5.678:910' -> (12,34,5,678,910)
"""
ip,port = string.strip().split(':')
return tuple(int(i) for i in ip.split('.')) + (port,)
with open('myfile.txt') as f:
nonemptyLines = (line for line in f if line.strip()!='')
sorted(nonemptyLines, key=ipPortToTuple)
edit: The ValueError you are getting is because your text files are not entirely in the #.#.#.#:# format as you imply. (There may be comments or blank lines, though in this case the error would hint that there is a line with more than one ':'.) You can use debugging techniques to home in on your issue, by catching the exception and emitting useful debugging data:
def tryParseLines(lines):
for line in lines:
try:
yield ipPortToTuple(line.strip())
except Exception:
if __debug__:
print('line {} did not match #.#.#.#:# format'.format(repr(line)))
with open('myfile.txt') as f:
sorted(tryParseLines(f))
I was a bit sloppy in the above, in that it still lets some invalid IP addresses through (e.g. #.#.#.#.#, or 257.-1.#.#). Below is a more thorough solution, which allows you do things like compare IP addresses with the < operators, also making sorting work naturally:
#!/usr/bin/python3
import functools
import re
@functools.total_ordering
class Ipv4Port(object):
regex = re.compile(r'(\d{1,3})\.(\d{1,3})\.(\d{1,3})\.(\d{1,3}):(\d{1,5})')
def __init__(self, ipv4:(int,int,int,int), port:int):
try:
assert type(ipv4)==tuple and len(ipv4)==4, 'ipv4 not 4-length tuple'
assert all(0<=x<256 for x in ipv4), 'ipv4 numbers not in valid range (0<=n<256)'
assert type(port)==int, 'port must be integer'
except AssertionError as ex:
print('Invalid IPv4 input: ipv4={}, port={}'.format(repr(ipv4),repr(port)))
raise ex
self.ipv4 = ipv4
self.port = port
self._tuple = ipv4+(port,)
@classmethod
def fromString(cls, string:'12.34.5.678:910'):
try:
a,b,c,d,port = cls.regex.match(string.strip()).groups()
ip = tuple(int(x) for x in (a,b,c,d))
return cls(ip, int(port))
except Exception as ex:
args = list(ex.args) if ex.args else ['']
args[0] += "\n...indicating ipv4 string {} doesn't match #.#.#.#:# format\n\n".format(repr(string))
ex.args = tuple(args)
raise ex
def __lt__(self, other):
return self._tuple < other._tuple
def __eq__(self, other):
return self._tuple == other._tuple
def __repr__(self):
#return 'Ipv4Port(ipv4={ipv4}, port={port})'.format(**self.__dict__)
return "Ipv4Port.fromString('{}.{}.{}.{}:{}')".format(*self._tuple)
and then:
def tryParseLines(lines):
for line in lines:
line = line.strip()
if line != '':
try:
yield Ipv4Port.fromString(line)
except AssertionError as ex:
raise ex
except Exception as ex:
if __debug__:
print(ex)
raise ex
Demo:
>>> lines = '222.111.22.44:214 \n222.1.1.1:234\n 23.1.35.6:199'.splitlines()
>>> sorted(tryParseLines(lines))
[Ipv4Port.fromString('23.1.35.6:199'), Ipv4Port.fromString('222.1.1.1:234'), Ipv4Port.fromString('222.111.22.44:214')]
Changing the values to be for example 264... or ...-35... will result in the appropriate errors.