WIP: Show progress

bears/codeclone_detection/ClangSimilarityBear.py

@@ -82,9 +82,18 @@ def run(self,
         # thus we do parallel execution within this bear.
         pool = multiprocessing.Pool(get_cpu_count())
 
-        differences = pool.map(
-            get_difference,
-            [(f1, f2, count_matrices)
-             for f1, f2 in combinations(count_matrices, 2)])
+        differences = []
+        function_count = len(count_matrices)
+        # Thats n over 2, hardcoded to simplify calculation
+        combination_length = function_count * (function_count-1) / 2
+        function_combinations = [(f1, f2, count_matrices)
+                                 for f1, f2 in combinations(count_matrices, 2)]
+
+        for i, elem in enumerate(pool.imap_unordered(get_difference,
+                                                     function_combinations,
+                                                     chunksize=100)):
+            if i % 1000 == 0:
+                self.debug("{:2.4f}%".format(100*i/combination_length))
+            differences.append(elem)
 
         return [HiddenResult(self.__class__.__name__, differences)]

bears/codeclone_detection/CloneDetectionRoutines.py

@@ -32,8 +32,12 @@ def get_count_matrices(count_vector_creator, filenames):
                                  objects with variable names as key as content.
     """
     result = {}
+    i = 0
+    maxlen = len(filenames)
 
     for filename in filenames:
+        i += 1
+        print("{:2.4f}%".format(100*(i/maxlen)))
         count_dict = count_vector_creator.get_vectors_for_file(filename)
         for function in count_dict:
             if not exclude_function(count_dict[function]):