Created
June 30, 2018 00:56
-
-
Save sashiyama/a10da1bfb0846078d75b9250533c1632 to your computer and use it in GitHub Desktop.
wc.py
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
import sys | |
import re | |
def count_word(lines): | |
words = {} | |
sum = 0 | |
for line in lines: | |
line = re.sub(r'\r\n|\n|\.|,|-|\"|\'|\[|\]|_|\*|:|\;|\(|\)|\/|\&|!|\?', ' ', line).lower() | |
n = line.split() | |
sum += len(n) | |
for word in n: | |
if word in words: | |
words[word] += 1 | |
else: | |
words[word] = 1 | |
return sorted(words.items(), key = lambda w: w[1], reverse = True), sum | |
argc = len(sys.argv) | |
if argc == 1: | |
lines = sys.stdin.readlines() | |
wcs, sum = count_word(lines) | |
elif argc == 2: | |
try: | |
f = open(sys.argv[1], 'rU') | |
lines = f.readlines() | |
wcs, sum = count_word(lines) | |
f.close() | |
except IOError: | |
print("Error: open file", sys.stderr) | |
sys.exit(1) | |
else: | |
sys.exit('usage: wc [file]') | |
print('Number of words: {0}'.format(sum)) | |
print('Top 20 frequent words:') | |
for wc in wcs[:20]: | |
print(wc) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment