Merge pull request #3237 from robertcv/fixes/file_strip_columns

[FIX] io: Handle mismatched number of header/data values

Orange/data/io.py

@@ -618,15 +618,25 @@ def data_table(cls, data, headers=None):
         # Determine maximum row length
         rowlen = max(map(len, (names, types, flags)))
 
+        strip = False
+
         def _equal_length(lst):
-            lst.extend(['']*(rowlen - len(lst)))
+            nonlocal strip
+            if len(lst) > rowlen > 0:
+                lst = lst[:rowlen]
+                strip = True
+            elif len(lst) < rowlen:
+                lst.extend(['']*(rowlen - len(lst)))
             return lst
 
         # Ensure all data is of equal width in a column-contiguous array
         data = [_equal_length([s.strip() for s in row])
                 for row in data if any(row)]
         data = np.array(data, dtype=object, order='F')
 
+        if strip:
+            warnings.warn("Columns with no headers were removed.")
+
         # Data may actually be longer than headers were
         try:
             rowlen = data.shape[1]

Orange/tests/test_io.py

@@ -5,6 +5,7 @@
 import os
 import tempfile
 import shutil
+import io
 
 from Orange.data import ContinuousVariable
 from Orange.data.io import FileFormat, TabReader, CSVReader, PickleReader, \
@@ -104,6 +105,20 @@ def test_open_bad_pickle(self):
         with unittest.mock.patch("pickle.load", return_value=None):
             self.assertRaises(TypeError, reader.read, "foo")
 
+    def test_empty_columns(self):
+        """Can't read files with more columns then headers. GH-1417"""
+        samplefile = """\
+        a, b
+        1, 0,
+        1, 2,
+        """
+        c = io.StringIO(samplefile)
+        with self.assertWarns(UserWarning) as cm:
+            table = CSVReader(c).read()
+        self.assertEqual(len(table.domain.attributes), 2)
+        self.assertEqual(cm.warning.args[0],
+                         "Columns with no headers were removed.")
+
 
 class TestIo(unittest.TestCase):
     def test_sanitize_variable_deprecated_params(self):