If it won't be simple, it simply won't be. [Hire me, source code] by Miki Tebeka, CEO, 353Solutions

Thursday, September 14, 2006


cut is a nice littiel utility that cuts a line to several fields and displays only some of them. It's main drawback is that cut splits to fields according to fixed separator, there are times when you want to split accoring to a regular expression - enters ecut.

ecut let's you split fields by regular expression (defaulting to \s+), it also handles Python's array indexing so that you can write someting like:

ls -l | tail +2 | ecut -f -2 | sort -r | head -1

(which is a weird way of finding the last time someting was modified in the current directory :)

ecut code is simple:

#!/usr/bin/env python
'''cut with regular expressions'''

__author__ = "Miki Tebeka "
__license__ = "BSD"
__version__ = "0.2.0"

from sys import stdin
import re
from optparse import OptionParser

progname = "ecut" # Program name
is_range = re.compile("\d+-\d+").match

class FatalError(SystemExit):
def __init__(self, message):
error_message = "%s: error: %s" % (progname, message)
SystemExit.__init__(self, error_message)

parser = OptionParser("usage: %prog [OPTIONS] [FILE]",
version="%%prog %s" % __version__)
default_delimiter = r"\s+"
parser.add_option("-d", "--delimiter", dest="delim",
help="delimiter to use (defaults to '%s')" % default_delimiter)
parser.add_option("-f", "--fields", dest="fields", default=[],
help="comma seperated list of fields to print", metavar="LIST")
parser.add_option("--output-delimiter", dest="out_delim", default=" ",
help="output delimiter", metavar="STRING")
parser.add_option("-s", "--only-delimited", dest="only_delim", default=0,
help="do not print lines not containing delimiters",

opts, args = parser.parse_args()
if not opts.fields:
raise FatalError("no fields given")

# Compile the delimiter
split = re.compile(opts.delim).split
except re.error, e:
raise FatalError("bad regular expression (%s)" % e.args[0])

if not args:
infiles = ["-"]
infiles = args

# Prase fields, we substract 1 since f1 is the 1'st field
fields = []
for field in opts.fields.split(","):
if not is_range(field):
fs = field.split("-")
if len(fs) != 2:
raise ValueError
if fs[0] and fs[1]:
fields.append((int(fs[0]) - 1, int(fs[1]) - 1)) # Full range
elif not fs[0]:
fields.append((0, int(fs[1]) - 1)) # 0-M
else: # M-end
fields.append((int(fs[0]) - 1, -1))
except ValueError:
raise FatalError("bad field: %s" % field)

inttype = type(1) # Ingeter type

# Process input files
for file in infiles:
if file == "-":
info = stdin
info = open(file)
except IOError, e:
raise FatalError("can't open %s - %s" % (file, e.strerror))

for line in info:
out = []
fs = filter(lambda x: x, split(line))
max = len(fs) - 1

if opts.only_delim and (len(fs) == 1):

for field in fields:
if (type(field) == inttype): # Simple field
if field <= max:
else: # Range
start = field[0]
if field[1] == -1:
end = max
end = min(field[2], max)
for i in range(start, end + 1):
print opts.out_delim.join(out)

No comments:

Blog Archive