Skip to content

Support 'is_json_object()' function for Flink #592

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

Open
liushengxuan wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Support 'is_json_object()' function for Flink #592

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
57 changes: 57 additions & 0 deletions bolt/functions/prestosql/SIMDJsonFunctions.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,23 @@ struct SIMDIsJsonScalarFunction {
}
};

template <typename T>
struct SIMDIsJsonObjectFunction {
VELOX_DEFINE_FUNCTION_TYPES(T);

FOLLY_ALWAYS_INLINE static void call(
bool& result,
const arg_type<Json>& json) {
ParserContext ctx(json.data(), json.size());
try {
ctx.parseDocument();
result = (ctx.jsonDoc.type() == simdjson::ondemand::json_type::object);
} catch (const simdjson::simdjson_error&) {
result = false;
}
}
};

template <typename T>
struct SonicIsJsonScalarFunction {
BOLT_DEFINE_FUNCTION_TYPES(T);
Expand All @@ -105,6 +122,23 @@ struct SonicIsJsonScalarFunction {
}
};

template <typename T>
struct SonicIsJsonObjectFunction {
VELOX_DEFINE_FUNCTION_TYPES(T);

FOLLY_ALWAYS_INLINE static void call(
bool& result,
const arg_type<Json>& json) {
sonic_json::Document jsonDoc;
jsonDoc.Parse(json.data(), json.size());
if (jsonDoc.HasParseError()) {
result = false;
return;
}
result = jsonDoc.IsObject();
}
};

template <typename T>
class WrapperIsJsonScalarFunction {
public:
Expand All @@ -128,6 +162,29 @@ class WrapperIsJsonScalarFunction {
bool useSonic = true;
};

template <typename T>
class WrapperIsJsonObjectFunction {
public:
VELOX_DEFINE_FUNCTION_TYPES(T);

FOLLY_ALWAYS_INLINE void initialize(
const std::vector<TypePtr>& /*inputTypes*/,
const core::QueryConfig& config,
const arg_type<Json>* /*json*/) {
useSonic = config.enableSonicIsJsonScalar();
}

FOLLY_ALWAYS_INLINE void call(bool& result, const arg_type<Json>& json) {
if (useSonic) {
SonicIsJsonObjectFunction<T>::call(result, json);
} else {
SIMDIsJsonObjectFunction<T>::call(result, json);
}
}

bool useSonic = true;
};

template <typename T>
struct SIMDJsonArrayContainsFunction {
BOLT_DEFINE_FUNCTION_TYPES(T);
Expand Down
5 changes: 5 additions & 0 deletions bolt/functions/prestosql/registration/JsonFunctionsRegistration.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,11 @@ void registerJsonFunctions(const std::string& prefix) {
registerFunction<WrapperIsJsonScalarFunction, bool, Varchar>(
{prefix + "is_json_scalar"});

registerFunction<WrapperIsJsonObjectFunction, bool, Json>(
{prefix + "is_json_object"});
registerFunction<WrapperIsJsonObjectFunction, bool, Varchar>(
{prefix + "is_json_object"});

registerFunction<WrapperJsonExtractScalarFunction, Varchar, Json, Varchar>(
{prefix + "json_extract_scalar"});
registerFunction<WrapperJsonExtractScalarFunction, Varchar, Varchar, Varchar>(
Expand Down
32 changes: 32 additions & 0 deletions bolt/functions/prestosql/tests/JsonFunctionsTest.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,16 @@ class JsonFunctionsTest : public functions::test::FunctionBaseTest {
return jsonResult;
}

std::optional<bool> isJsonObject(std::optional<std::string> json) {
auto [jsonVector, varcharVector] = makeVectors(json);
auto jsonResult =
evaluateOnce<bool>("is_json_object(c0)", makeRowVector({jsonVector}));
auto varcharResult = evaluateOnce<bool>(
"is_json_object(c0)", makeRowVector({varcharVector}));
EXPECT_EQ(jsonResult, varcharResult);
return jsonResult;
}

std::optional<int64_t> jsonArrayLength(std::optional<std::string> json) {
auto [jsonVector, varcharVector] = makeVectors(json);
auto jsonResult = evaluateOnce<int64_t>(
Expand Down Expand Up @@ -314,6 +324,13 @@ TEST_F(JsonFunctionsTest, isJsonScalarSignatures) {
ASSERT_EQ(1, signatures.count("(varchar) -> boolean"));
}

TEST_F(JsonFunctionsTest, isJsonObjectSignatures) {
auto signatures = getSignatureStrings("is_json_object");
ASSERT_EQ(2, signatures.size());
ASSERT_EQ(1, signatures.count("(json) -> boolean"));
ASSERT_EQ(1, signatures.count("(varchar) -> boolean"));
}

TEST_F(JsonFunctionsTest, jsonArrayLengthSignatures) {
auto signatures = getSignatureStrings("json_array_length");
ASSERT_EQ(2, signatures.size());
Expand Down Expand Up @@ -370,6 +387,21 @@ TEST_F(JsonFunctionsTest, isJsonScalar) {
EXPECT_EQ(isJsonScalar(R"({"k1":""})"), false);
}

TEST_F(JsonFunctionsTest, isJsonObject) {
EXPECT_EQ(isJsonObject(R"({"k1":"v1"})"), true);
EXPECT_EQ(isJsonObject(R"({"k1":[0,1,2]})"), true);
EXPECT_EQ(isJsonObject(R"({})"), true);

EXPECT_EQ(isJsonObject(R"(1)"), false);
EXPECT_EQ(isJsonObject(R"("hello")"), false);
EXPECT_EQ(isJsonObject(R"(true)"), false);
EXPECT_EQ(isJsonObject(R"(null)"), false);
EXPECT_EQ(isJsonObject(R"([1,2])"), false);

EXPECT_EQ(isJsonObject(R"(not_json)"), false);
EXPECT_EQ(isJsonObject(R"()"), false);
}

TEST_F(JsonFunctionsTest, jsonArrayLength) {
EXPECT_EQ(jsonArrayLength(R"([])"), 0);
EXPECT_EQ(jsonArrayLength(R"([1])"), 1);
Expand Down
Loading