update

mr/python/reducer.py

@@ -1,10 +1,8 @@
-#!/usr/bin/env python
 from operator import itemgetter
 import sys
 
-current_word = None
-current_count = 0
-word = None
+# Lista do przechowywania wyników
+results = []
 
 # input comes from STDIN
 for line in sys.stdin:
@@ -22,17 +20,12 @@ for line in sys.stdin:
         # ignore/discard this line
         continue
 
-    # this IF-switch only works because Hadoop sorts map output
-    # by key (here: word) before it is passed to the reducer
-    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
+    # Dodaj słowo i jego długość do listy wyników
+    results.append((word, len(word), count))
 
-# do not forget to output the last word if needed!
-if current_word == word:
-    print('%s\t%s' % (current_word, current_count))
+# Posortuj wyniki po długości słowa
+results.sort(key=lambda x: x[1])
+
+# Wypisz posortowane wyniki
+for result in results:
+    print('%s\t%s' % (result[0], result[2]))