revert d881302e4e

revert update

mr/python/reducer.py

@@ -1,31 +1,38 @@
-from operator import itemgetter
-import sys
-
-# Lista do przechowywania wyników
-results = []
-
-# input comes from STDIN
-for line in sys.stdin:
-    # remove leading and trailing whitespace
-    line = line.strip()
-
-    # parse the input we got from mapper.py
-    word, count = line.split('\t', 1)
-
-    # convert count (currently a string) to int
-    try:
-        count = int(count)
-    except ValueError:
-        # count was not a number, so silently
-        # ignore/discard this line
-        continue
-
-    # Dodaj słowo i jego długość do listy wyników
-    results.append((word, len(word), 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]))
+#!/usr/bin/env python
+from operator import itemgetter
+import sys
+
+current_word = None
+current_count = 0
+word = None
+
+# input comes from STDIN
+for line in sys.stdin:
+    # remove leading and trailing whitespace
+    line = line.strip()
+
+    # parse the input we got from mapper.py
+    word, count = line.split('\t', 1)
+
+    # convert count (currently a string) to int
+    try:
+        count = int(count)
+    except ValueError:
+        # count was not a number, so silently
+        # 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
+
+# do not forget to output the last word if needed!
+if current_word == word:
+    print('%s\t%s' % (current_word, current_count))