test: add test for split_whitespace

scikit-hep · Aug 7, 2023 · 461eb83 · 461eb83
1 parent d930260
commit 461eb83
Showing 1 changed file with 39 additions and 0 deletions.
diff --git a/tests/test_2616_use_pyarrow_for_strings.py b/tests/test_2616_use_pyarrow_for_strings.py
@@ -531,3 +531,42 @@ def test_slice():
  [],
  ["→δε←".encode()[1:], "ζz zζ".encode()[1:], b"abc"[1:]],
  ]
+
+
+def test_split_whitespace():
+ assert ak.str.split_whitespace(string_padded, max_splits=1).tolist() == [
+ [["", "αβγ "], ["", " "]],
+ [],
+ [["", "→δε← "], ["", "ζz zζ "], ["", "abc "]],
+ ]
+ assert ak.str.split_whitespace(
+ string_padded, max_splits=1, reverse=True
+ ).tolist() == [
+ [[" αβγ", ""], [" ", ""]],
+ [],
+ [[" →δε←", ""], [" ζz zζ", ""], [" abc", ""]],
+ ]
+ assert ak.str.split_whitespace(string_padded, max_splits=None).tolist() == [
+ [["", "αβγ", "", ""], ["", "", ""]],
+ [],
+ [["", "→δε←", "", ""], ["", "ζz", "zζ", "", ""], ["", "abc", "", ""]],
+ ]
+
+ # Bytestrings
+ assert ak.str.split_whitespace(bytestring_padded, max_splits=1).tolist() == [
+ [["", "αβγ "], ["", ""]],
+ [],
+ [["", "→δε← "], ["", "ζz zζ "], ["", "abc "]],
+ ]
+ assert ak.str.split_whitespace(
+ bytestring_padded, max_splits=1, reverse=True
+ ).tolist() == [
+ [[" αβγ", ""], ["", ""]],
+ [],
+ [[" →δε←", ""], [" ζz zζ", ""], [" abc", ""]],
+ ]
+ assert ak.str.split_whitespace(bytestring_padded, max_splits=None).tolist() == [
+ [["", "αβγ", ""], ["", ""]],
+ [],
+ [["", "→δε←", ""], ["", "ζz", "zζ", ""], ["", "abc", ""]],
+ ]