lexer

gistfile1.py

import shlex
import re
from cStringIO import StringIO

c1 = 'jobname|1d|4:30'
c2 = 'jobname | 1d | 4:30'

def tokenize(t):
    if re.match('(\d+)d', t):      return 'DAY'
    if re.match('(\d+)h', t):      return 'HOUR'
    if re.match('(\d+)m', t):      return 'MIN'
    if re.match('(\d+)s', t):      return 'SEC'
    if re.match('(\d+):(\d+)', t): return 'TIME'
    if re.match('\w+', t):         return 'JOB'
    return 'UNKNOWN'

for job in [c1, c2]:
    lex = shlex.shlex(StringIO(job))
    lex.whitespace += '|'
    lex.whitespace_split = True

    while 1:
        token = lex.get_token()
        if token == '': break
        print token
        print tokenize(token)