Skip to content

fix(cpp): reject UTF-8 name collisions before CLI output #1002

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ColinLeeo merged 1 commit into from
Oct 10, 2026
Merged

fix(cpp): reject UTF-8 name collisions before CLI output #1002

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 6 additions & 8 deletions cpp/test/tools/command_e2e_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1815,9 +1815,9 @@ TEST(CliE2E, Utf8JsonKeyCollisionsFailWithoutPublishingOutput) {
args.insert(args.end() - 1, {"--start", "0", "-n", "0"});
}
std::ostringstream out, err;
EXPECT_EQ(tsfile_cli::run_cli(args, out, err), 3) << err.str();
EXPECT_EQ(tsfile_cli::run_cli(args, out, err), 2) << err.str();
EXPECT_TRUE(out.str().empty());
EXPECT_NE(err.str().find("duplicate NDJSON column name"),
EXPECT_NE(err.str().find("duplicate column name"),
std::string::npos);
EXPECT_TRUE(tsfile_cli::is_valid_utf8(err.str()));
}
Expand All @@ -1837,10 +1837,9 @@ TEST(CliE2E, Utf8JsonKeyCollisionsFailWithoutPublishingOutput) {
args.insert(args.end() - 1, "--force");
}
std::ostringstream out, err;
EXPECT_EQ(tsfile_cli::run_cli(args, out, err), 3) << err.str();
EXPECT_EQ(tsfile_cli::run_cli(args, out, err), 2) << err.str();
EXPECT_TRUE(out.str().empty());
EXPECT_NE(err.str().find("duplicate NDJSON column name"),
std::string::npos);
EXPECT_NE(err.str().find("duplicate column name"), std::string::npos);
std::ifstream target(output.c_str(), std::ios::binary);
if (existing) {
ASSERT_TRUE(target.is_open());
Expand Down Expand Up @@ -1897,10 +1896,9 @@ TEST(CliE2E, TableUtf8JsonKeyCollisionsFailInRowsAndStats) {
std::ostringstream out, err;
EXPECT_EQ(tsfile_cli::run_cli(
{command, "-t", table, "-f", "ndjson", path}, out, err),
3);
2);
EXPECT_TRUE(out.str().empty());
EXPECT_NE(err.str().find("duplicate NDJSON column name"),
std::string::npos);
EXPECT_NE(err.str().find("duplicate column name"), std::string::npos);
EXPECT_TRUE(tsfile_cli::is_valid_utf8(err.str()));
}
std::remove(path.c_str());
Expand Down
35 changes: 21 additions & 14 deletions cpp/test/tools/output_format_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -346,29 +346,36 @@ TEST(RowWriterTest, PreservesNonUtf8BlobBytesAsHex) {
}
}

TEST(RowWriterTest, RejectsJsonKeyCollisionsAfterUtf8Replacement) {
TEST(RowWriterTest, RejectsColumnCollisionsAfterUtf8Replacement) {
const std::vector<std::vector<std::string>> headers = {
{"bad\xff", "bad\xfe"},
{"bad\xff", "bad\xef\xbf\xbd"},
{"same", "same"},
};
for (const auto& header : headers) {
for (bool no_header : {false, true}) {
std::ostringstream out;
RowWriter writer(out, OutputFormat::kJson, header,
{common::INT64, common::INT64}, no_header);
EXPECT_FALSE(writer.write({"42", "7"}, {false, false}));
EXPECT_FALSE(writer.finish());
EXPECT_TRUE(out.str().empty());
for (OutputFormat format : {OutputFormat::kJson, OutputFormat::kCsv,
OutputFormat::kTable, OutputFormat::kTsv}) {
for (bool no_header : {false, true}) {
std::ostringstream out;
RowWriter writer(out, format, header,
{common::INT64, common::INT64}, no_header);
EXPECT_FALSE(writer.write({"42", "7"}, {false, false}));
EXPECT_FALSE(writer.finish());
EXPECT_TRUE(out.str().empty());
}
}
}
}

TEST(RowWriterTest, RejectsJsonKeyCollisionsWithoutRows) {
std::ostringstream out;
RowWriter writer(out, OutputFormat::kJson, {"bad\xff", "bad\xfe"},
{common::STRING, common::STRING}, false);
EXPECT_FALSE(writer.finish());
EXPECT_TRUE(out.str().empty());
TEST(RowWriterTest, RejectsColumnCollisionsWithoutRows) {
for (OutputFormat format : {OutputFormat::kJson, OutputFormat::kCsv,
OutputFormat::kTable, OutputFormat::kTsv}) {
std::ostringstream out;
RowWriter writer(out, format, {"bad\xff", "bad\xfe"},
{common::STRING, common::STRING}, false);
EXPECT_FALSE(writer.finish());
EXPECT_TRUE(out.str().empty());
}
}

TEST(RowWriterTest, CsvEscapesLeadingBackslashesOnlyInTextValues) {
Expand Down
Loading
Loading