update

mr/python/reducer.py

@@ -1,38 +1,31 @@
-#!/usr/bin/env python
+from operator import itemgetter
-from operator import itemgetter
+import sys
-import sys
+
-
+# Lista do przechowywania wyników
-current_word = None
+results = []
-current_count = 0
+
-word = None
+# input comes from STDIN
-
+for line in sys.stdin:
-# input comes from STDIN
+    # remove leading and trailing whitespace
-for line in sys.stdin:
+    line = line.strip()
-    # remove leading and trailing whitespace
+
-    line = line.strip()
+    # parse the input we got from mapper.py
-
+    word, count = line.split('\t', 1)
-    # parse the input we got from mapper.py
+
-    word, count = line.split('\t', 1)
+    # convert count (currently a string) to int
-
+    try:
-    # convert count (currently a string) to int
+        count = int(count)
-    try:
+    except ValueError:
-        count = int(count)
+        # count was not a number, so silently
-    except ValueError:
+        # ignore/discard this line
-        # count was not a number, so silently
+        continue
-        # ignore/discard this line
+
-        continue
+    # Dodaj słowo i jego długość do listy wyników
-
+    results.append((word, len(word), count))
-    # this IF-switch only works because Hadoop sorts map output
+
-    # by key (here: word) before it is passed to the reducer
+# Posortuj wyniki po długości słowa
-    if current_word == word:
+results.sort(key=lambda x: x[1])
-        current_count += count
+
-    else:
+# Wypisz posortowane wyniki
-        if current_word:
+for result in results:
-            # write result to STDOUT
+    print('%s\t%s' % (result[0], result[2]))
-            print('%s\t%s' % (current_word, current_count))
-        current_count = count
-        current_word = word
-
-# do not forget to output the last word if needed!
-if current_word == word:
-    print('%s\t%s' % (current_word, current_count))