Return 1 if empty string is given as substring (apache#69)

rui-mo · Mar 15, 2022 · 950cd80 · 950cd80
1 parent 3e6b037
commit 950cd80
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 4 deletions.
diff --git a/cpp/src/gandiva/precompiled/string_ops.cc b/cpp/src/gandiva/precompiled/string_ops.cc
@@ -1807,9 +1807,9 @@ gdv_int32 locate_utf8_utf8_int32(gdv_int64 context, const char* sub_str,
     gdv_fn_context_set_error_msg(context, "Start position must be greater than 0");
     return 0;
   }
-
-  if (str_len == 0 || sub_str_len == 0) {
-    return 0;
+  // TO align with vanilla spark.
+  if (sub_str_len == 0) {
+    return 1;
   }
 
   gdv_int32 byte_pos = utf8_byte_pos(context, str, str_len, start_pos - 1);

diff --git a/cpp/src/gandiva/precompiled/string_ops_test.cc b/cpp/src/gandiva/precompiled/string_ops_test.cc
@@ -1539,7 +1539,11 @@ TEST(TestStringOps, TestLocate) {
   EXPECT_FALSE(ctx.has_error());
 
   pos = locate_utf8_utf8_int32(ctx_ptr, "", 0, "str", 3, 1);
-  EXPECT_EQ(pos, 0);
+  EXPECT_EQ(pos, 1);
+  EXPECT_FALSE(ctx.has_error());
+
+  pos = locate_utf8_utf8_int32(ctx_ptr, "", 0, "", 0, 1);
+  EXPECT_EQ(pos, 1);
   EXPECT_FALSE(ctx.has_error());
 
   pos = locate_utf8_utf8_int32(ctx_ptr, "bar", 3, "barbar", 6, 0);