revert update
This commit is contained in:
s1201683 2024-04-05 15:41:07 +02:00
parent 9e58d37a8c
commit 20cbaa1fa7

View File

@ -1,10 +1,8 @@
#!/usr/bin/env python
from operator import itemgetter from operator import itemgetter
import sys import sys
current_word = None # Lista do przechowywania wyników
current_count = 0 results = []
word = None
# input comes from STDIN # input comes from STDIN
for line in sys.stdin: for line in sys.stdin:
@ -22,18 +20,12 @@ for line in sys.stdin:
# ignore/discard this line # ignore/discard this line
continue continue
# this IF-switch only works because Hadoop sorts map output # Dodaj słowo i jego długość do listy wyników
# by key (here: word) before it is passed to the reducer results.append((word, len(word), count))
if current_word == word:
current_count += count
else:
if current_word:
# write result to STDOUT
print('%s\t%s' % (current_word, current_count))
current_count = count
current_word = word
# do not forget to output the last word if needed! # Posortuj wyniki po długości słowa
if current_word == word: results.sort(key=lambda x: x[1])
print('%s\t%s' % (current_word, current_count))
# Wypisz posortowane wyniki
for result in results:
print('%s\t%s' % (result[0], result[2]))