Skip to content

FixBug: Load data Is error in json load #3702

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
morningman merged 1 commit into from
May 28, 2020
Merged

FixBug: Load data Is error in json load #3702

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
12 changes: 4 additions & 8 deletions be/src/exec/json_scanner.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -267,15 +267,11 @@ size_t JsonReader::get_data_by_jsonpath(const std::vector<SlotDescriptor*>& slot
}

// if jsonValues is null, because not match in jsondata.
rapidjson::Value* json_values = JsonFunctions::get_json_object_from_parsed_json(path.GetString(), &_json_doc, _json_doc.GetAllocator());
rapidjson::Value* json_values = JsonFunctions::get_json_array_from_parsed_json(path.GetString(), &_json_doc, _json_doc.GetAllocator());
if (json_values == nullptr) {
return -1;
}
if (json_values->IsArray()) {
max_lines = std::max(max_lines, (size_t)json_values->Size());
} else {
max_lines = std::max(max_lines, (size_t)1);
}
max_lines = std::max(max_lines, (size_t)json_values->Size());
_jmap.emplace(slot_descs[i]->col_name(), json_values);
}

Expand Down Expand Up @@ -376,7 +372,7 @@ Status JsonReader::set_tuple_value(rapidjson::Value& objectValue, Tuple* tuple,
/**
* handle input a simple json
* For example:
* case 1. {"RECORDS": [{"colunm1":"value1", "colunm2":10}, {"colunm1":"value2", "colunm2":30}]}
* case 1. [{"colunm1":"value1", "colunm2":10}, {"colunm1":"value2", "colunm2":30}]
* case 2. {"colunm1":"value1", "colunm2":10}
*/
Status JsonReader::handle_simple_json(Tuple* tuple, const std::vector<SlotDescriptor*>& slot_descs, MemPool* tuple_pool, bool* eof) {
Expand Down Expand Up @@ -497,7 +493,7 @@ Status JsonReader::handle_flat_array_complex_json(Tuple* tuple, const std::vecto
}

// if jsonValues is null, because not match in jsondata.
rapidjson::Value* json_values = JsonFunctions::get_json_object_from_parsed_json(path.GetString(), &objectValue, _json_doc.GetAllocator());
rapidjson::Value* json_values = JsonFunctions::get_json_array_from_parsed_json(path.GetString(), &objectValue, _json_doc.GetAllocator());
if (json_values == nullptr) {
if (slot_descs[i]->is_nullable()) {
tuple->set_null(slot_descs[i]->null_indicator_offset());
Expand Down
9 changes: 8 additions & 1 deletion be/src/exprs/json_functions.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -263,7 +263,7 @@ rapidjson::Value* JsonFunctions::get_json_object(
}


rapidjson::Value* JsonFunctions::get_json_object_from_parsed_json (
rapidjson::Value* JsonFunctions::get_json_array_from_parsed_json (
const std::string& path_string,
rapidjson::Value* document,
rapidjson::Document::AllocatorType& mem_allocator) {
Expand Down Expand Up @@ -293,6 +293,13 @@ rapidjson::Value* JsonFunctions::get_json_object_from_parsed_json (
rapidjson::Value* root = match_value(parsed_paths, document, mem_allocator, true);
if (root == document) {// not found
return nullptr;
} else if (!root->IsArray()) {
rapidjson::Value* array_obj = nullptr;
array_obj = static_cast<rapidjson::Value*>(
mem_allocator.Malloc(sizeof(rapidjson::Value)));
array_obj->SetArray();
array_obj->PushBack(*root, mem_allocator);
return array_obj;
}
return root;
}
Expand Down
3 changes: 2 additions & 1 deletion be/src/exprs/json_functions.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,8 +72,9 @@ class JsonFunctions {

/**
* The `document` parameter must be has parsed.
* return Value Is Array object
Copy link
Contributor

@morningman morningman May 27, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

better to change its name to get_json_array_from_parsed_json() to make it more explict.

And in src//exec/json_scanner.cpp line 270, you can this method, but judge the return value as either array or non-array? the else should not happen?

Copy link
Contributor Author

@worker24h worker24h May 27, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The method MUST return ArrayObject.
else if (!root->IsArray()) is true, then I warp a ArrayObject in root outside.
else case MUST be ArrayObject

Copy link
Contributor Author

@worker24h worker24h May 27, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The method name changed to get_json_objects_from_parsed_json ??

*/
static rapidjson::Value* get_json_object_from_parsed_json(
static rapidjson::Value* get_json_array_from_parsed_json(
const std::string& path_string,
rapidjson::Value* document,
rapidjson::Document::AllocatorType& mem_allocator);
Expand Down
10 changes: 5 additions & 5 deletions be/test/exprs/json_function_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -194,13 +194,13 @@ TEST_F(JsonFunctionTest, json_path1)
ASSERT_TRUE(false);
}
rapidjson::Value* res3;
res3 = JsonFunctions::get_json_object_from_parsed_json("$.[*].keyname.ip", &jsonDoc, jsonDoc.GetAllocator());
res3 = JsonFunctions::get_json_array_from_parsed_json("$.[*].keyname.ip", &jsonDoc, jsonDoc.GetAllocator());
ASSERT_TRUE(res3->IsArray());
for (int i = 0; i < res3->Size(); i++) {
std::cout<< (*res3)[i].GetString() << std::endl;
}

res3 = JsonFunctions::get_json_object_from_parsed_json("$.[*].k1", &jsonDoc, jsonDoc.GetAllocator());
res3 = JsonFunctions::get_json_array_from_parsed_json("$.[*].k1", &jsonDoc, jsonDoc.GetAllocator());
ASSERT_TRUE(res3->IsArray());
for (int i = 0; i < res3->Size(); i++) {
std::cout<< (*res3)[i].GetString() << std::endl;
Expand All @@ -216,7 +216,7 @@ TEST_F(JsonFunctionTest, json_path_get_nullobject)
ASSERT_TRUE(false);
}

rapidjson::Value* res3 = JsonFunctions::get_json_object_from_parsed_json("$.[*].b", &jsonDoc, jsonDoc.GetAllocator());
rapidjson::Value* res3 = JsonFunctions::get_json_array_from_parsed_json("$.[*].b", &jsonDoc, jsonDoc.GetAllocator());
ASSERT_TRUE(res3->IsArray());
ASSERT_EQ(res3->Size(), 3);
for (int i = 0; i < res3->Size(); i++) {
Expand All @@ -239,7 +239,7 @@ TEST_F(JsonFunctionTest, json_path_test)
ASSERT_TRUE(false);
}

rapidjson::Value* res3 = JsonFunctions::get_json_object_from_parsed_json("$.[*].a", &jsonDoc, jsonDoc.GetAllocator());
rapidjson::Value* res3 = JsonFunctions::get_json_array_from_parsed_json("$.[*].a", &jsonDoc, jsonDoc.GetAllocator());
ASSERT_TRUE(res3->IsArray());
ASSERT_EQ(res3->Size(), 2);
for (int i = 0; i < res3->Size(); i++) {
Expand All @@ -258,7 +258,7 @@ TEST_F(JsonFunctionTest, json_path_test)
ASSERT_TRUE(false);
}

rapidjson::Value* res3 = JsonFunctions::get_json_object_from_parsed_json("$.a", &jsonDoc, jsonDoc.GetAllocator());
rapidjson::Value* res3 = JsonFunctions::get_json_array_from_parsed_json("$.a", &jsonDoc, jsonDoc.GetAllocator());
ASSERT_TRUE(res3->IsArray());
ASSERT_EQ(res3->Size(), 2);
for (int i = 0; i < res3->Size(); i++) {
Expand Down