Skip to content

branch-3.0: [feat](load) stream load supports loading JSON compressed format #48990 #49044

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
dataroaring merged 1 commit into from
Mar 17, 2025
Merged

branch-3.0: [feat](load) stream load supports loading JSON compressed format #48990 #49044

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
4 changes: 0 additions & 4 deletions be/src/http/action/stream_load.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -251,10 +251,6 @@ Status StreamLoadAction::_on_header(HttpRequest* http_req, std::shared_ptr<Strea
}

// get format of this put
if (!http_req->header(HTTP_COMPRESS_TYPE).empty() &&
iequal(http_req->header(HTTP_FORMAT_KEY), "JSON")) {
return Status::NotSupported("compress data of JSON format is not supported.");
}
std::string format_str = http_req->header(HTTP_FORMAT_KEY);
if (iequal(format_str, BeConsts::CSV_WITH_NAMES) ||
iequal(format_str, BeConsts::CSV_WITH_NAMES_AND_TYPES)) {
Expand Down
24 changes: 24 additions & 0 deletions be/src/util/load_util.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,30 @@ void LoadUtil::parse_format(const std::string& format_str, const std::string& co
} else if (iequal(format_str, "JSON")) {
if (compress_type_str.empty()) {
*format_type = TFileFormatType::FORMAT_JSON;
} else if (iequal(compress_type_str, "GZ")) {
*format_type = TFileFormatType::FORMAT_JSON;
*compress_type = TFileCompressType::GZ;
} else if (iequal(compress_type_str, "LZO")) {
*format_type = TFileFormatType::FORMAT_JSON;
*compress_type = TFileCompressType::LZO;
} else if (iequal(compress_type_str, "BZ2")) {
*format_type = TFileFormatType::FORMAT_JSON;
*compress_type = TFileCompressType::BZ2;
} else if (iequal(compress_type_str, "LZ4")) {
*format_type = TFileFormatType::FORMAT_JSON;
*compress_type = TFileCompressType::LZ4FRAME;
} else if (iequal(compress_type_str, "LZ4_BLOCK")) {
*format_type = TFileFormatType::FORMAT_JSON;
*compress_type = TFileCompressType::LZ4BLOCK;
} else if (iequal(compress_type_str, "LZOP")) {
*format_type = TFileFormatType::FORMAT_JSON;
*compress_type = TFileCompressType::LZO;
} else if (iequal(compress_type_str, "SNAPPY_BLOCK")) {
*format_type = TFileFormatType::FORMAT_JSON;
*compress_type = TFileCompressType::SNAPPYBLOCK;
} else if (iequal(compress_type_str, "DEFLATE")) {
*format_type = TFileFormatType::FORMAT_JSON;
*compress_type = TFileCompressType::DEFLATE;
}
} else if (iequal(format_str, "PARQUET")) {
*format_type = TFileFormatType::FORMAT_PARQUET;
Expand Down
64 changes: 64 additions & 0 deletions be/test/util/load_util_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,6 +119,70 @@ TEST_F(LoadUtilTest, ParseTest) {
TFileFormatType::type format_type;
TFileCompressType::type compress_type;
LoadUtil::parse_format("JSON", "GZ", &format_type, &compress_type);
EXPECT_EQ(TFileFormatType::FORMAT_JSON, format_type);
EXPECT_EQ(TFileCompressType::GZ, compress_type);
}
{
// JSON, LZO
TFileFormatType::type format_type;
TFileCompressType::type compress_type;
LoadUtil::parse_format("JSON", "LZOP", &format_type, &compress_type);
EXPECT_EQ(TFileFormatType::FORMAT_JSON, format_type);
EXPECT_EQ(TFileCompressType::LZO, compress_type);
}
{
// JSON, BZ2
TFileFormatType::type format_type;
TFileCompressType::type compress_type;
LoadUtil::parse_format("JSON", "BZ2", &format_type, &compress_type);
EXPECT_EQ(TFileFormatType::FORMAT_JSON, format_type);
EXPECT_EQ(TFileCompressType::BZ2, compress_type);
}
{
// JSON, LZ4
TFileFormatType::type format_type;
TFileCompressType::type compress_type;
LoadUtil::parse_format("JSON", "LZ4", &format_type, &compress_type);
EXPECT_EQ(TFileFormatType::FORMAT_JSON, format_type);
EXPECT_EQ(TFileCompressType::LZ4FRAME, compress_type);
}
{
// JSON, LZ4_BLOCK
TFileFormatType::type format_type;
TFileCompressType::type compress_type;
LoadUtil::parse_format("JSON", "LZ4_BLOCK", &format_type, &compress_type);
EXPECT_EQ(TFileFormatType::FORMAT_JSON, format_type);
EXPECT_EQ(TFileCompressType::LZ4BLOCK, compress_type);
}
{
// JSON, LZOP
TFileFormatType::type format_type;
TFileCompressType::type compress_type;
LoadUtil::parse_format("JSON", "LZOP", &format_type, &compress_type);
EXPECT_EQ(TFileFormatType::FORMAT_JSON, format_type);
EXPECT_EQ(TFileCompressType::LZO, compress_type);
}
{
// JSON, SNAPPY_BLOCK
TFileFormatType::type format_type;
TFileCompressType::type compress_type;
LoadUtil::parse_format("JSON", "SNAPPY_BLOCK", &format_type, &compress_type);
EXPECT_EQ(TFileFormatType::FORMAT_JSON, format_type);
EXPECT_EQ(TFileCompressType::SNAPPYBLOCK, compress_type);
}
{
// JSON, DEFLATE
TFileFormatType::type format_type;
TFileCompressType::type compress_type;
LoadUtil::parse_format("JSON", "DEFLATE", &format_type, &compress_type);
EXPECT_EQ(TFileFormatType::FORMAT_JSON, format_type);
EXPECT_EQ(TFileCompressType::DEFLATE, compress_type);
}
{
// JSON, unkonw
TFileFormatType::type format_type;
TFileCompressType::type compress_type;
LoadUtil::parse_format("JSON", "UNKNOWN", &format_type, &compress_type);
EXPECT_EQ(TFileFormatType::FORMAT_UNKNOWN, format_type);
EXPECT_EQ(TFileCompressType::PLAIN, compress_type);
}
Expand Down
Loading
Loading