Add informative error message for sep in CSV writer(#7095)

Fixes: #7091 This PR introduces validation and throwing of informative error messages for the `sep` parameter in csv writer. Authors: - galipremsagar <[email protected]> Approvers: - Keith Kraus (@kkraus14) - Vukasin Milovanovic (@vuule) URL: #7095
rapidsai · Jan 7, 2021 · aa38f85 · aa38f85
1 parent ee65a47
commit aa38f85
Show file tree

Hide file tree

Showing 2 changed files with 28 additions and 3 deletions.
diff --git a/python/cudf/cudf/io/csv.py b/python/cudf/cudf/io/csv.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2018-2020, NVIDIA CORPORATION.
+# Copyright (c) 2018-2021, NVIDIA CORPORATION.
 
 from io import BytesIO, StringIO
 
@@ -119,6 +119,11 @@ def to_csv(
 ):
     """{docstring}"""
 
+    if not isinstance(sep, str):
+        raise TypeError(f'"sep" must be string, not {type(sep).__name__}')
+    elif len(sep) > 1:
+        raise TypeError('"sep" must be a 1-character string')
+
     return_as_string = False
     if path_or_buf is None:
         path_or_buf = StringIO()

diff --git a/python/cudf/cudf/tests/test_csv.py b/python/cudf/cudf/tests/test_csv.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2018-2020, NVIDIA CORPORATION.
+# Copyright (c) 2018-2021, NVIDIA CORPORATION.
 
 import csv
 import gzip
@@ -15,7 +15,7 @@
 
 import cudf
 from cudf import read_csv
-from cudf.tests.utils import assert_eq
+from cudf.tests.utils import assert_eq, assert_exceptions_equal
 
 
 def make_numeric_dataframe(nrows, dtype):
@@ -1935,3 +1935,23 @@ def test_na_filter_empty_fields():
         StringIO(buffer), keep_default_na=False, na_values=test_na
     )
     assert_eq(pdf, gdf)
+
+
+def test_csv_sep_error():
+    pdf = pd.DataFrame({"a": [1, 2, 3]})
+    gdf = cudf.DataFrame({"a": [1, 2, 3]})
+    assert_exceptions_equal(
+        lfunc=pdf.to_csv,
+        rfunc=gdf.to_csv,
+        lfunc_args_and_kwargs=([], {"sep": "abc"}),
+        rfunc_args_and_kwargs=([], {"sep": "abc"}),
+        expected_error_message='"sep" must be a 1-character string',
+    )
+
+    assert_exceptions_equal(
+        lfunc=pdf.to_csv,
+        rfunc=gdf.to_csv,
+        lfunc_args_and_kwargs=([], {"sep": 1}),
+        rfunc_args_and_kwargs=([], {"sep": 1}),
+        expected_error_message='"sep" must be string, not int',
+    )