This is an automated email from the ASF dual-hosted git repository.
kou pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow.git
The following commit(s) were added to refs/heads/main by this push:
new c13f3bc96c GH-19667: [C++][Gandiva] Use arrow::Result<std::string> for
RegexUtil::SqlLikePatternToPcre (#49879)
c13f3bc96c is described below
commit c13f3bc96c5d9985e49ef31cc0c232e1ffec379a
Author: Aaditya Srinivasan <[email protected]>
AuthorDate: Fri May 1 17:25:52 2026 +0530
GH-19667: [C++][Gandiva] Use arrow::Result<std::string> for
RegexUtil::SqlLikePatternToPcre (#49879)
### Rationale for this change
Replace the `Status` + out-parameter pattern in
`RegexUtil::SqlLikePatternToPcre` with `arrow::Result<std::string>`, aligning
with modern Arrow API practices.
### What changes are included in this PR?
* Updated `RegexUtil::SqlLikePatternToPcre` to return
`arrow::Result<std::string>` instead of using an out-parameter
* Updated call sites in `regex_functions_holder.cc` to use
`ARROW_ASSIGN_OR_RAISE`
* Updated tests in `regex_functions_holder_test.cc` to use
`ASSERT_OK_AND_ASSIGN`
* Removed `GANDIVA_EXPORT` from the inline wrapper to avoid Windows
`dllimport` issues
* Simplified control flow in `regex_functions_holder.cc`
### Are these changes tested?
* Rebuilt with `ninja gandiva`
* Ran Gandiva tests successfully
### Are there any user-facing changes?
Yes.
* GitHub Issue: #19667
Authored-by: Aaditya Srinivasan <[email protected]>
Signed-off-by: Sutou Kouhei <[email protected]>
---
cpp/src/gandiva/regex_functions_holder.cc | 13 ++++++-------
cpp/src/gandiva/regex_functions_holder_test.cc | 5 ++---
cpp/src/gandiva/regex_util.cc | 10 +++++-----
cpp/src/gandiva/regex_util.h | 12 ++++++------
4 files changed, 19 insertions(+), 21 deletions(-)
diff --git a/cpp/src/gandiva/regex_functions_holder.cc
b/cpp/src/gandiva/regex_functions_holder.cc
index 1c9e44d61b..6c0c3d40f1 100644
--- a/cpp/src/gandiva/regex_functions_holder.cc
+++ b/cpp/src/gandiva/regex_functions_holder.cc
@@ -128,8 +128,7 @@ Result<std::shared_ptr<LikeHolder>> LikeHolder::Make(const
FunctionNode& node) {
}
Result<std::shared_ptr<LikeHolder>> LikeHolder::Make(const std::string&
sql_pattern) {
- std::string pcre_pattern;
- ARROW_RETURN_NOT_OK(RegexUtil::SqlLikePatternToPcre(sql_pattern,
pcre_pattern));
+ ARROW_ASSIGN_OR_RAISE(auto pcre_pattern,
RegexUtil::SqlLikePatternToPcre(sql_pattern));
RE2::Options regex_op;
regex_op.set_dot_nl(true); // set dotall mode for the regex.
@@ -148,11 +147,12 @@ Result<std::shared_ptr<LikeHolder>>
LikeHolder::Make(const std::string& sql_patt
Status::Invalid("The length of escape char ", escape_char,
" in 'like' function is greater than 1"));
std::string pcre_pattern;
+
if (escape_char.length() == 1) {
- ARROW_RETURN_NOT_OK(
- RegexUtil::SqlLikePatternToPcre(sql_pattern, escape_char.at(0),
pcre_pattern));
+ ARROW_ASSIGN_OR_RAISE(
+ pcre_pattern, RegexUtil::SqlLikePatternToPcre(sql_pattern,
escape_char.at(0)));
} else {
- ARROW_RETURN_NOT_OK(RegexUtil::SqlLikePatternToPcre(sql_pattern,
pcre_pattern));
+ ARROW_ASSIGN_OR_RAISE(pcre_pattern,
RegexUtil::SqlLikePatternToPcre(sql_pattern));
}
auto lholder = std::shared_ptr<LikeHolder>(new LikeHolder(pcre_pattern,
regex_op));
@@ -165,8 +165,7 @@ Result<std::shared_ptr<LikeHolder>> LikeHolder::Make(const
std::string& sql_patt
Result<std::shared_ptr<LikeHolder>> LikeHolder::Make(const std::string&
sql_pattern,
RE2::Options regex_op) {
- std::string pcre_pattern;
- ARROW_RETURN_NOT_OK(RegexUtil::SqlLikePatternToPcre(sql_pattern,
pcre_pattern));
+ ARROW_ASSIGN_OR_RAISE(auto pcre_pattern,
RegexUtil::SqlLikePatternToPcre(sql_pattern));
auto lholder = std::shared_ptr<LikeHolder>(new LikeHolder(pcre_pattern,
regex_op));
diff --git a/cpp/src/gandiva/regex_functions_holder_test.cc
b/cpp/src/gandiva/regex_functions_holder_test.cc
index d0cef50687..4d7b0fd319 100644
--- a/cpp/src/gandiva/regex_functions_holder_test.cc
+++ b/cpp/src/gandiva/regex_functions_holder_test.cc
@@ -88,9 +88,8 @@ TEST_F(TestLikeHolder, TestPcreSpecialWithNewLine) {
}
TEST_F(TestLikeHolder, TestRegexEscape) {
- std::string res;
- ARROW_EXPECT_OK(RegexUtil::SqlLikePatternToPcre("#%hello#_abc_def##", '#',
res));
-
+ ASSERT_OK_AND_ASSIGN(auto res,
+ RegexUtil::SqlLikePatternToPcre("#%hello#_abc_def##",
'#'));
EXPECT_EQ(res, "%hello_abc.def#");
}
diff --git a/cpp/src/gandiva/regex_util.cc b/cpp/src/gandiva/regex_util.cc
index abdd579d1f..5d68cefef8 100644
--- a/cpp/src/gandiva/regex_util.cc
+++ b/cpp/src/gandiva/regex_util.cc
@@ -22,11 +22,11 @@ namespace gandiva {
const std::set<char> RegexUtil::pcre_regex_specials_ = {
'[', ']', '(', ')', '|', '^', '-', '+', '*', '?', '{', '}', '$', '\\',
'.'};
-Status RegexUtil::SqlLikePatternToPcre(const std::string& sql_pattern, char
escape_char,
- std::string& pcre_pattern) {
- /// Characters that are considered special by pcre regex. These needs to be
+arrow::Result<std::string> RegexUtil::SqlLikePatternToPcre(const std::string&
sql_pattern,
+ char escape_char) {
+ /// Characters that are considered special by pcre regex. These need to be
/// escaped with '\\'.
- pcre_pattern.clear();
+ std::string pcre_pattern;
for (size_t idx = 0; idx < sql_pattern.size(); ++idx) {
auto cur = sql_pattern.at(idx);
@@ -57,7 +57,7 @@ Status RegexUtil::SqlLikePatternToPcre(const std::string&
sql_pattern, char esca
pcre_pattern += cur;
}
}
- return Status::OK();
+ return pcre_pattern;
}
} // namespace gandiva
diff --git a/cpp/src/gandiva/regex_util.h b/cpp/src/gandiva/regex_util.h
index cf0002b8cd..baaf8212bd 100644
--- a/cpp/src/gandiva/regex_util.h
+++ b/cpp/src/gandiva/regex_util.h
@@ -27,15 +27,15 @@
namespace gandiva {
/// \brief Utility class for converting sql patterns to pcre patterns.
-class GANDIVA_EXPORT RegexUtil {
+class RegexUtil {
public:
// Convert an sql pattern to a pcre pattern
- static Status SqlLikePatternToPcre(const std::string& like_pattern, char
escape_char,
- std::string& pcre_pattern);
+ static GANDIVA_EXPORT arrow::Result<std::string> SqlLikePatternToPcre(
+ const std::string& like_pattern, char escape_char);
- static Status SqlLikePatternToPcre(const std::string& like_pattern,
- std::string& pcre_pattern) {
- return SqlLikePatternToPcre(like_pattern, 0 /*escape_char*/, pcre_pattern);
+ static arrow::Result<std::string> SqlLikePatternToPcre(
+ const std::string& like_pattern) {
+ return SqlLikePatternToPcre(like_pattern, '\0' /*escape_char*/);
}
private:
