Created
February 4, 2013 01:38
-
-
Save RWJMurphy/4704584 to your computer and use it in GitHub Desktop.
Like sort(1), only in Python, and capable of sorting by line length.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import argparse | |
import os | |
import random | |
import re | |
import string | |
import sys | |
def number_or_zero(x): | |
try: | |
return float(x) | |
except ValueError: | |
return 0.0 | |
# reduce(lambda arg, func: func(arg), [arg] + funcs) | |
def apply_funcs(funcs, arg): | |
result = arg | |
for func in funcs: | |
result = func(result) | |
return result | |
def main(args): | |
status = os.EX_OK | |
lines = [] | |
reverse = args.reverse | |
for input_file in args.FILE: | |
if input_file == "-": | |
input_file = sys.stdin | |
else: | |
input_file = open(input_file, 'r') | |
lines.extend(line.rstrip('\n') for line in input_file) | |
prefilters = [] | |
if args.ignore_leading_blanks: | |
prefilters.append(lambda x: x.lstrip()) | |
if args.dictionary_order: | |
prefilters.append(lambda x: re.sub( | |
'[^' + string.letters + string.whitespace + string.digits + ']+', | |
'', | |
x | |
)) | |
if args.ignore_case: | |
prefilters.append(lambda x: x.upper()) | |
if args.ignore_nonprinting: | |
prefilters.append(lambda x: re.sub( | |
'[^' + string.printable + ']+', | |
'', | |
x | |
)) | |
comparison = lambda x: x | |
if args.length: | |
comparison = lambda x: len(x) | |
elif args.numeric_sort: | |
comparison = lambda x: number_or_zero(x) | |
if args.random_sort: | |
random.shuffle(lines) | |
else: | |
lines.sort(key=lambda line: comparison(apply_funcs(prefilters, line)), reverse=reverse) | |
print("\n".join(lines)) | |
return status | |
if __name__ == "__main__": | |
exit_code = os.EX_OK | |
parser = argparse.ArgumentParser( | |
description="Sort lines of text", | |
usage="%(prog)s [OPTION]... [FILE]..." | |
) | |
comparison_args = parser.add_mutually_exclusive_group() | |
comparison_args.add_argument('-l', '--length', help="compare by the length of each line ", action="store_true") | |
comparison_args.add_argument('-n', '--numeric-sort', help="compare according to string numerical value", action="store_true") | |
comparison_args.add_argument('-R', '--random-sort', help="shuffle the input, rather than sorting", action="store_true") | |
parser.add_argument('-b', '--ignore-leading-blanks', help="ignore leading blanks", action="store_true") | |
parser.add_argument('-d', '--dictionary-order', help="consider only blanks and alphanumeric characters", action="store_true") | |
parser.add_argument('-f', '--ignore-case', help="fold lower case to upper case characters", action="store_true") | |
parser.add_argument('-r', '--reverse', help="reverse the result of comparisons", action="store_true") | |
parser.add_argument('-i', '--ignore-nonprinting', help="consider only printable characters", action="store_true") | |
parser.add_argument('-V', '--version', action='version', version='%(prog)s 0.2') | |
parser.add_argument('FILE', nargs="*", default=['-'], help="The files to be sorted. If unsupplied, or '-', reads from standard input.") | |
args = parser.parse_args() | |
try: | |
exit_code = main(args) | |
except KeyboardInterrupt: | |
pass | |
sys.exit(exit_code) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment