BUG: Add warning if rows have more columns than expected

pandas/io/parsers.py

@@ -49,7 +49,7 @@
     pandas_dtype,
 )
 from pandas.core.dtypes.dtypes import CategoricalDtype
-from pandas.core.dtypes.missing import isna
+from pandas.core.dtypes.missing import isna, notna
 
 from pandas.core import algorithms
 from pandas.core.arrays import Categorical
@@ -2151,15 +2151,19 @@ def read(self, nrows=None):
 
             # columns as list
             alldata = [x[1] for x in data]
-
+            if len(names) != len(data) and notna(data[len(names) :]).any():
+                warnings.warn(
+                    "Expected {} columns instead of {}".format(len(names), len(data)),
+                    ParserWarning,
+                    stacklevel=2,
+                )
             data = {k: v for k, (i, v) in zip(names, data)}
 
             names, data = self._do_date_conversions(names, data)
             index, names = self._make_index(data, alldata, names)
 
         # maybe create a mi on the columns
         names = self._maybe_make_multi_index_columns(names, self.col_names)
-
         return index, names, data
 
     def _filter_usecols(self, names):
@@ -2508,6 +2512,13 @@ def read(self, rows=None):
             content = content[1:]
 
         alldata = self._rows_to_cols(content)
+        if len(columns) != len(alldata) and notna(alldata[len(columns) :]).any():
+            warnings.warn(
+                "Expected {} columns instead of {}".format(len(columns), len(alldata)),
+                ParserWarning,
+                stacklevel=2,
+            )
+
         data = self._exclude_implicit_index(alldata)
 
         columns = self._maybe_dedup_names(self.columns)

pandas/tests/io/parser/test_common.py

@@ -14,7 +14,7 @@
 import pytest
 
 from pandas._libs.tslib import Timestamp
-from pandas.errors import DtypeWarning, EmptyDataError, ParserError
+from pandas.errors import DtypeWarning, EmptyDataError, ParserError, ParserWarning
 import pandas.util._test_decorators as td
 
 from pandas import DataFrame, Index, MultiIndex, Series, compat, concat
@@ -2124,5 +2124,13 @@ def test_no_header_two_extra_columns(all_parsers):
     ref = DataFrame([["foo", "bar", "baz"]], columns=column_names)
     stream = StringIO("foo,bar,baz,bam,blah")
     parser = all_parsers
-    df = parser.read_csv(stream, header=None, names=column_names, index_col=False)
-    tm.assert_frame_equal(df, ref)
+    with tm.assert_produces_warning(ParserWarning):
+        df = parser.read_csv(stream, header=None, names=column_names, index_col=False)
+        tm.assert_frame_equal(df, ref)
+
+
+def test_first_row_length(all_parsers):
+    stream = StringIO("col1,col2,col3\n0,1,2,X\n4,5,6\n6,7,8")
+    parser = all_parsers
+    with tm.assert_produces_warning(ParserWarning):
+        parser.read_csv(stream, index_col=False)