WIP: Changing Python parser behaviour, better tests

Author: AaronCritchley

pandas/io/parsers.py

@@ -1665,18 +1665,18 @@ def __init__(self, src, **kwds):
                 missing = [c for c in usecols if c not in self.orig_names]
                 raise ValueError(
                     "Usecols do not match columns, "
-                    "columns expected but not found: %s" % missing
+                    "columns expected but not found: {}".format(missing)
                 )
 
             if len(self.names) > len(usecols):
                 self.names = [n for i, n in enumerate(self.names)
                               if (i in usecols or n in usecols)]
 
             if len(self.names) < len(usecols):
-                missing = [c for c in usecols if c not in self.orig_names]
+                missing = [c for c in usecols if c not in self.names]
                 raise ValueError(
                     "Usecols do not match columns, "
-                    "columns expected but not found: %s" % missing
+                    "columns expected but not found: {}".format(missing)
                 )
 
         self._set_noconvert_columns()
@@ -2450,6 +2450,14 @@ def _handle_usecols(self, columns, usecols_key):
                     raise ValueError("If using multiple headers, usecols must "
                                      "be integers.")
                 col_indices = []
+
+                missing = [c for c in self.usecols if c not in usecols_key]
+                if len(missing) > 0:
+                    raise ValueError(
+                        "Usecols do not match columns, "
+                        "columns expected but not found: {}".format(missing)
+                    )
+
                 for col in self.usecols:
                     if isinstance(col, string_types):
                         col_indices.append(usecols_key.index(col))

pandas/tests/io/parser/usecols.py

@@ -480,10 +480,10 @@ def test_raise_on_usecols_names_mismatch(self):
         # GH 14671
         data = 'a,b,c,d\n1,2,3,4\n5,6,7,8'
 
-        if self.engine == 'c':
-            msg = "do not match columns, columns expected but not found"
-        else:
-            msg = 'is not in list'
+        msg = (
+            "Usecols do not match columns, "
+            "columns expected but not found: {}"
+        )
 
         usecols = ['a', 'b', 'c', 'd']
         df = self.read_csv(StringIO(data), usecols=usecols)
@@ -492,11 +492,11 @@ def test_raise_on_usecols_names_mismatch(self):
         tm.assert_frame_equal(df, expected)
 
         usecols = ['a', 'b', 'c', 'f']
-        with tm.assert_raises_regex(ValueError, msg):
+        with tm.assert_raises_regex(ValueError, msg.format(['f'])):
             self.read_csv(StringIO(data), usecols=usecols)
 
         usecols = ['a', 'b', 'f']
-        with tm.assert_raises_regex(ValueError, msg):
+        with tm.assert_raises_regex(ValueError, msg.format(['f'])):
             self.read_csv(StringIO(data), usecols=usecols)
 
         names = ['A', 'B', 'C', 'D']
@@ -520,9 +520,9 @@ def test_raise_on_usecols_names_mismatch(self):
         # tm.assert_frame_equal(df, expected)
 
         usecols = ['A', 'B', 'C', 'f']
-        with tm.assert_raises_regex(ValueError, msg):
+        with tm.assert_ra(ValueError, msg.format(['f'])):
             self.read_csv(StringIO(data), header=0, names=names,
                           usecols=usecols)
         usecols = ['A', 'B', 'f']
-        with tm.assert_raises_regex(ValueError, msg):
+        with tm.assert_raises_regex(ValueError, msg.format(['f'])):
             self.read_csv(StringIO(data), names=names, usecols=usecols)