|
| 1 | +#!/usr/bin/env python3 |
| 2 | + |
| 3 | +from collections import Counter |
| 4 | +import argparse |
| 5 | +import re |
| 6 | +from itertools import islice |
| 7 | +import operator |
| 8 | + |
| 9 | +parser = argparse.ArgumentParser() |
| 10 | +parser.add_argument('--numWords',type=int,default=10) |
| 11 | +parser.add_argument('--maxTuples',type=int,default=4) |
| 12 | +parser.add_argument('--minWordLength',type=int,default=5) |
| 13 | +parser.add_argument('file',type=str) |
| 14 | +args = parser.parse_args() |
| 15 | + |
| 16 | +# Inspired by http://stackoverflow.com/questions/6822725 |
| 17 | +def window(seq, n): |
| 18 | + it = iter(seq) |
| 19 | + result = tuple(islice(it, n)) |
| 20 | + if len(result) == n: |
| 21 | + yield result |
| 22 | + for elem in it: |
| 23 | + result = result[1:] + (elem,) |
| 24 | + containsShortWord = False |
| 25 | + for i in result: |
| 26 | + if len(i) < args.minWordLength: |
| 27 | + containsShortWord = True |
| 28 | + break |
| 29 | + if not containsShortWord: |
| 30 | + yield result |
| 31 | + |
| 32 | +with open(args.file,'r') as f: |
| 33 | + content = f.read().replace('\n',' ') |
| 34 | + words = re.findall(r'\S+', content) |
| 35 | + for i in range(1,args.maxTuples+1): |
| 36 | + print("\n=== Sliding Window: {} ===".format(i)) |
| 37 | + for tup in Counter(window(words,i)).most_common(args.numWords): |
| 38 | + print(" {}: '{}'".format(tup[1]," ".join(tup[0]))) |
0 commit comments