Fixed testing for most problems.

1 files changed, 30 insertions, 3 deletions

diff --git a/python/problems/lists_and_for/calculator_polish/common.py b/python/problems/lists_and_for/calculator_polish/common.py
index d08f19c..7ea25ce 100644
--- a/python/problems/lists_and_for/calculator_polish/common.py
+++ b/python/problems/lists_and_for/calculator_polish/common.py
@@ -46,12 +46,39 @@ hint_type = {
 }
 
 def test(python, code):
-    test_in = [1]
+    in_out = [
+        (['6 3 +'], [9]),
+        (['6 3 -'], [3]),
+        (['6 3 /'], [2]),
+        (['7 3 /'], [2]),
+        (['6 3 *'], [18]),
+        (['6 3 %'], [0]),
+        (['1 2 +', '2 3 +', '1 2 3 4 5 * * * *'], [3, 5, 120]),
+        (['1 2 + 3 +'], [6]),
+        (['1 2 3 + +'], [6]),
+        (['1 2 + 3 4 + *'], [21]),
+        (['1 2 3 * 4 + +'], [11]),
+        (['3 5 + 2 * 10 2 1 - * -'], [6]),
+        (['11 22 33 * * 7 + 2 / 100 % 1 2 - -'], [97]),
+    ]
+
+    test_in = [(None, '\n'.join(s[0])+'\n') for s in in_out]
+    test_out = [s[1] for s in in_out]
+    # List of outputs: (expression result, stdout, stderr, exception).
+    answers = python(code=code, inputs=test_in, timeout=1.0)
+    outputs = [ans[1] for ans in answers]
+
     n_correct = 0
+    tin = None
+    for i, (output, correct) in enumerate(zip(outputs, test_out)):
+        if all(string_almost_equal(output, c, prec=2) for c in correct):
+            n_correct += 1
+        else:
+            tin = test_in[i][1]
+            tout = correct
 
     passed = n_correct == len(test_in)
-    tin = None
-    tout = None
+
     hints = [{'id': 'test_results', 'args': {'passed': n_correct, 'total': len(test_in)}}]
     if tin:
         hints.append({'id': 'problematic_test_case', 'args': {'testin': str(tin), 'testout': str(tout)}})