From 097d6f2e444c40ec7b1172dd9158a0ca24b5b1df Mon Sep 17 00:00:00 2001
From: David Wendt <45795991+davidwendt@users.noreply.github.com>
Date: Fri, 21 Apr 2023 20:11:14 -0400
Subject: [PATCH] Fix slice_strings to return empty strings for stop < start
 indices (#13178)

Fixes bug where `stop` value is less than `start` value in calls to `cudf::strings::slice_strings` should result in an empty string. Optimization in #13057 introduced this bug. Additional gtest was added to check for this condition.

Close #13173

Authors:
  - David Wendt (https://github.com/davidwendt)

Approvers:
  - Jason Lowe (https://github.com/jlowe)
  - Nghia Truong (https://github.com/ttnghia)
  - MithunR (https://github.com/mythrocks)

URL: https://github.com/rapidsai/cudf/pull/13178
---
 cpp/src/strings/slice.cu          |  2 +-
 cpp/tests/strings/slice_tests.cpp | 18 ++++++++++++++++++
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/cpp/src/strings/slice.cu b/cpp/src/strings/slice.cu
index fbe54c01bba..a3182577c34 100644
--- a/cpp/src/strings/slice.cu
+++ b/cpp/src/strings/slice.cu
@@ -59,7 +59,7 @@ struct substring_from_fn {
 
     auto const stop = stops[idx];
     auto const end  = (((stop < 0) || (stop > length)) ? length : stop);
-    return d_str.substr(start, end - start);
+    return start < end ? d_str.substr(start, end - start) : string_view{};
   }
 
   substring_from_fn(column_device_view const& d_column, IndexIterator starts, IndexIterator stops)
diff --git a/cpp/tests/strings/slice_tests.cpp b/cpp/tests/strings/slice_tests.cpp
index 8e0c3b325b2..ca73e1791d6 100644
--- a/cpp/tests/strings/slice_tests.cpp
+++ b/cpp/tests/strings/slice_tests.cpp
@@ -93,6 +93,24 @@ TEST_P(Parameters, Substring_From)
   CUDF_TEST_EXPECT_COLUMNS_EQUAL(*results, expected);
 }
 
+TEST_P(Parameters, SubstringStopZero)
+{
+  cudf::size_type start = GetParam();
+  cudf::test::strings_column_wrapper input({"abc", "défgh", "", "XYZ"});
+  auto view = cudf::strings_column_view(input);
+
+  auto results = cudf::strings::slice_strings(view, start, 0);
+  cudf::test::strings_column_wrapper expected({"", "", "", ""});
+  CUDF_TEST_EXPECT_COLUMNS_EQUAL(*results, expected);
+
+  auto starts =
+    cudf::test::fixed_width_column_wrapper<cudf::size_type>({start, start, start, start});
+  auto stops = cudf::test::fixed_width_column_wrapper<cudf::size_type>({0, 0, 0, 0});
+
+  results = cudf::strings::slice_strings(view, starts, stops);
+  CUDF_TEST_EXPECT_COLUMNS_EQUAL(*results, expected);
+}
+
 TEST_P(Parameters, AllEmpty)
 {
   std::vector<std::string> h_strings{"", "", "", ""};