Fixed testing for most problems.

1 files changed, 31 insertions, 3 deletions

diff --git a/python/problems/lists_and_for/every_third/common.py b/python/problems/lists_and_for/every_third/common.py
index 9c27446..6f42663 100644
--- a/python/problems/lists_and_for/every_third/common.py
+++ b/python/problems/lists_and_for/every_third/common.py
@@ -26,12 +26,40 @@ hint_type = {
 }
 
 def test(python, code):
-    test_in = [1]
+    in_out = [
+        ([], []),
+        ([0], []),
+        ([0, 1], []),
+        ([0, 1, 2], [2]),
+        ([1, 2, 3, 4, 5, 5, 4, 3, 2, 1], [3, 5, 2]),
+        ([42, 5, 4, -7, 2, 12, -3, -4, 11, 42, 2], [4, 12, 11]),
+        (list(range(15)), [2, 5, 8, 11, 14])
+    ]
+
+    test_in = [t[0] for t in in_out]
+    test_out = [t[1] for t in in_out]
+
     n_correct = 0
+    tin = None
+    for xs_i, xs in enumerate(test_in):
+        # change code to contain new xs instead of the one
+        # given by user
+        tcode = re.sub(r'^xs\s*=\s*\[.*?\]',
+                       'xs = ' + str(xs),
+                       code,
+                       flags = re.DOTALL | re.MULTILINE)
 
+        # use python session to call tcode
+        answers = python(code=tcode, inputs=[(None, None)], timeout=1.0)
+        output = answers[0][1]
+
+        if str(test_out[xs_i]) in output:
+            n_correct += 1
+        else:
+            tin = test_in[xs_i]
+            tout = test_out[xs_i]
     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)}})