vvellanki commented on a change in pull request #11287:
URL: https://github.com/apache/arrow/pull/11287#discussion_r756700195
##########
File path: cpp/src/gandiva/precompiled/string_ops_test.cc
##########
@@ -2129,4 +2129,78 @@ TEST(TestStringOps, TestFromHex) {
::testing::HasSubstr("Error parsing hex string, one or more bytes are
not valid."));
ctx.Reset();
}
+TEST(TestStringOps, TestInstr) {
+ std::string s1 = "hello world!";
+ auto s1_len = static_cast<int32_t>(s1.size());
+ std::string s2 = "world";
+ auto s2_len = static_cast<int32_t>(s2.size());
+
+ auto result = instr_utf8(s1.c_str(), s1_len, s2.c_str(), s2_len);
+ EXPECT_EQ(result, 7);
+
+ s1 = "apple banana mango";
+ s1_len = static_cast<int32_t>(s1.size());
+ s2 = "apple";
+ s2_len = static_cast<int32_t>(s2.size());
+
+ result = instr_utf8(s1.c_str(), s1_len, s2.c_str(), s2_len);
+ EXPECT_EQ(result, 1);
+
+ s1 = "";
+ s1_len = static_cast<int32_t>(s1.size());
+ s2 = "mango";
+ s2_len = static_cast<int32_t>(s2.size());
+
+ result = instr_utf8(s1.c_str(), s1_len, s2.c_str(), s2_len);
+ EXPECT_EQ(result, 0);
+
+ s1 = "open the door";
+ s1_len = static_cast<int32_t>(s1.size());
+ s2 = "";
+ s2_len = static_cast<int32_t>(s2.size());
+
+ result = instr_utf8(s1.c_str(), s1_len, s2.c_str(), s2_len);
+ EXPECT_EQ(result, 1);
+
+ s1 = "";
+ s1_len = static_cast<int32_t>(s1.size());
+ s2 = "";
+ s2_len = static_cast<int32_t>(s2.size());
+
+ result = instr_utf8(s1.c_str(), s1_len, s2.c_str(), s2_len);
+ EXPECT_EQ(result, 1);
+
+ s1 = "hi john";
+ s1_len = static_cast<int32_t>(s1.size());
+ s2 = "johny";
+ s2_len = static_cast<int32_t>(s2.size());
+
+ result = instr_utf8(s1.c_str(), s1_len, s2.c_str(), s2_len);
Review comment:
We should have more negative tests with the following:
- The substring's first 2 chars only match. The 3rd char doesn't match
- Test cases with this matching substring at the beginning of string, middle
of the string and end of string
##########
File path: cpp/src/gandiva/precompiled/string_ops_test.cc
##########
@@ -2129,4 +2129,78 @@ TEST(TestStringOps, TestFromHex) {
::testing::HasSubstr("Error parsing hex string, one or more bytes are
not valid."));
ctx.Reset();
}
+TEST(TestStringOps, TestInstr) {
+ std::string s1 = "hello world!";
+ auto s1_len = static_cast<int32_t>(s1.size());
+ std::string s2 = "world";
+ auto s2_len = static_cast<int32_t>(s2.size());
+
+ auto result = instr_utf8(s1.c_str(), s1_len, s2.c_str(), s2_len);
+ EXPECT_EQ(result, 7);
+
+ s1 = "apple banana mango";
+ s1_len = static_cast<int32_t>(s1.size());
+ s2 = "apple";
+ s2_len = static_cast<int32_t>(s2.size());
+
+ result = instr_utf8(s1.c_str(), s1_len, s2.c_str(), s2_len);
+ EXPECT_EQ(result, 1);
+
+ s1 = "";
+ s1_len = static_cast<int32_t>(s1.size());
+ s2 = "mango";
+ s2_len = static_cast<int32_t>(s2.size());
+
+ result = instr_utf8(s1.c_str(), s1_len, s2.c_str(), s2_len);
+ EXPECT_EQ(result, 0);
+
+ s1 = "open the door";
+ s1_len = static_cast<int32_t>(s1.size());
+ s2 = "";
+ s2_len = static_cast<int32_t>(s2.size());
+
+ result = instr_utf8(s1.c_str(), s1_len, s2.c_str(), s2_len);
+ EXPECT_EQ(result, 1);
+
+ s1 = "";
+ s1_len = static_cast<int32_t>(s1.size());
+ s2 = "";
+ s2_len = static_cast<int32_t>(s2.size());
+
+ result = instr_utf8(s1.c_str(), s1_len, s2.c_str(), s2_len);
+ EXPECT_EQ(result, 1);
+
+ s1 = "hi john";
+ s1_len = static_cast<int32_t>(s1.size());
+ s2 = "johny";
+ s2_len = static_cast<int32_t>(s2.size());
+
+ result = instr_utf8(s1.c_str(), s1_len, s2.c_str(), s2_len);
Review comment:
Did this test pass with this version of the code? If so, the code has
another bug around the length
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
