In [ ]:

    

import re
import nose
# %timeit


    

In [ ]:

    

from __future__ import print_function
# Before writing the parser, collect samples of
#  the interesting lines. For now just
from course import mail_sent, mail_delivered

print("I'm goint to parse the following line", mail_sent, sep="\n\n")


    

In [ ]:

    

# and %edit a simple
def test_sent():
    hour, host, to = parse_line(mail_sent)
    assert hour == '08:00:00'
    assert to == 'jon@doe.it'


    

In [ ]:

    

# Play with mail_sent and start using basic strings in ipython
mail_sent.split()


    

In [ ]:

    

# You can number fields with enumerate. 
# Remember that ipython puts the last returned value in `_`
# which is useful in interactive mode!
fields, counting = _, enumerate(_)
print(*counting, sep="\n")


    

In [ ]:

    

# Now we can pick fields singularly...
hour, host, dest = fields[2], fields[3], fields[6]


    

In [ ]:

    

# ... or with 
from operator import itemgetter
which_returns_a_function = itemgetter(2, 3, 6)
assert (hour, host, dest) == which_returns_a_function(fields)


    

In [ ]:

    

# %load ../scripts/03_parsing_test.py
""" Python for System Administrators

    Roberto Polli <rpolli@babel.it>

    This file shows how to parse a postfix maillog file.
     maillog traces every incoming and outgoing email using
     different line formats.
"""

#
# Before writing the parser we collect the
#  interesting lines to use as a sample
#  For now we're just interested in the following cases
#  1- a mail is sent
#  2- a mail is delivered
test_str_1 = 'Nov 31 08:00:00 test-fe1 postfix/smtp[16669]: 7CD8E730020: to=<jon@doe.it>, relay=examplemx2.doe.it[222.33.44.555]:25, delay=0.8, delays=0.17/0.01/0.43/0.19, dsn=2.0.0, status=sent(250 ok:  Message 2108406157 accepted)'
test_str_2 = 'Nov 31 08:00:00 test-fe1 postfix/smtp[16669]: 7CD8E730020: removed'


def test_sent():
    hour, host, destination = parse_line(test_str_1)
    assert hour == '08:00:00'
    assert host == 'test-fe1'
    assert destination == 'jon@doe.it'


def test_delivered():
    hour, host, destination = parse_line(test_str_2)
    assert hour == '08:00:00'
    assert host == 'test-fe1'
    assert destination is None


def parse_line(line):
    """ Complete the parse line function.

        Without watching the solution: ICAgIGltcG9ydCByZQogICAgXywgXywgaG91ciwgaG9zdCwgXywgXywgZGVzdCA9IGxpbmUuc3BsaXQoKVs6N10KICAgIHRyeToKICAgICAgICBkZXN0ID0gcmUuc3BsaXQocidbPD5dJywgZGVzdClbMV0KICAgIGV4Y2VwdDoKICAgICAgICBkZXN0ID0gTm9uZQogICAgcmV0dXJuIChob3VyLCBob3N0LCBkZXN0KQoK"""
    # Hint: "you can".split()
    # Hint: "<you can slice>"[1:-1] or use re.split
    raise NotImplementedError("Write me!")


    

In [ ]:

    

#
# Run test
#
test_sent()


    

In [ ]:

    

# Don't look at the solution ;)
%load course/parse_line.py


    

In [ ]:

    

# Python supports regular expressions via
import re

# We start showing a grep-reloaded function
def grep(expr, fpath):
    one = re.compile(expr) # ...has two lookup methods...
    assert ( one.match     # which searches from ^ the beginning
         and one.search )  # that searches $\pyver{anywhere}$

    with open(fpath) as fp:
        return [x for x in fp if one.search(x)]


    

In [ ]:

    

# The function seems to work as expected ;)
assert not grep(r'^localhost', '/etc/hosts')

# And some more tests
ret = grep('127.0.0.1', '/etc/hosts')
assert ret, "ret should not be empty"
print(*ret)


    

In [ ]:

    

from re import split # is a very nice function
import sys
from course import sh

# Let's gather some ping stats
if sys.platform.startswith('win'):
    cmd = "ping -n3 www.google.it"
else:
    cmd = "ping -c3 -w3 www.google.it"

# Split for both space and =
ping_output = [split("[ =]", x) for x in sh(cmd)]

print(*ping_output, sep="\n")


    

In [ ]:

    

# Splitting with re.findall

from re import findall  # can be misused too;

# eg for adding the ":" to a
mac = "00""24""e8""b4""33""20"

# ...using this
re_hex = "[0-9a-fA-F]{2}"
mac_address = ':'.join(findall(re_hex, mac))
print("The mac address is ", mac_address)

# Actually this does a bit of validation, requiring all chars to be in the 0-F range


    

In [ ]:

    

# Run the following cell many times. 
# Do you always get the same results?
test_all_regexps = ("..", "[a-fA-F0-9]{2}")
for re_s in test_all_regexps:
    %timeit ':'.join(findall(re_s, mac))


    

In [ ]:

    

# We can even compare compiled vs inline regexp
import re
from time import sleep
for re_s in test_all_regexps:
    re_c = re.compile(re_s)
    %timeit ':'.join(re_c.findall(mac))


    

In [ ]:

    

# Or find other methods:

# complex...
from re import sub as sed
%timeit sed(r'(..)', r'\1:', mac)


    

In [ ]:

    

# ...or simple
%timeit ':'.join([mac[i:i+2] for i in range(0,12,2)])
#Outside iPython check the timeit module

# Execise: which is the fastest method? Why?


    

In [ ]:

    

# Don't need to type this VSAN configuration script
#  which uses linux FC information from /sys filesystem
from glob import glob
fc_id_path = "/sys/class/fc_host/host*/port_name"
for x in glob(fc_id_path):
    # ...we boldly skip an explicit close()
    pwwn = open(x).read()  # 0x500143802427e66c
    pwwn = pwwn[2:]
    # ...and even use the slower but readable
    pwwn = re.findall(r'..', pwwn)
    print("member pwwn ", ':'.join(pwwn))


    

In [ ]:

    




    

In [ ]:

    

#
# Use this cell for Exercise II
#
test_delivered()