setop/sqlite-parquet-vtable
1
0
Fork 0
mirror of https://github.com/cldellow/sqlite-parquet-vtable.git synced 2025-09-16 22:49:59 +00:00
Code Releases Activity

More defensive, add caveats

Browse Source
This commit is contained in:
Colin Dellow
2018-03-03 20:26:41 -05:00
parent eb0b48f867
commit 18f07f4c43
2 changed files with 87 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

86
parquet/parquet_table.cc
View File

@@ -35,45 +35,65 @@ std::string ParquetTable::CreateStatement() {
text += col->name();
std::string type;
switch(col->physical_type()) {
case parquet::Type::BOOLEAN:
type = "TINYINT";
break;
case parquet::Type::INT32:
if(col->logical_type() == parquet::LogicalType::NONE) {
type = "INT";
} else if(col->logical_type() == parquet::LogicalType::INT_8) {
parquet::Type::type physical = col->physical_type();
parquet::LogicalType::type logical = col->logical_type();
// Be explicit about which types we understand so we don't mislead someone
// whose unsigned ints start getting interpreted as signed. (We could
// support this for UINT_8/16/32 -- and for UINT_64 we could throw if
// the high bit was set.)
if(logical == parquet::LogicalType::NONE ||
logical == parquet::LogicalType::UTF8 ||
logical == parquet::LogicalType::DATE ||
logical == parquet::LogicalType::TIME_MILLIS ||
logical == parquet::LogicalType::TIMESTAMP_MILLIS ||
logical == parquet::LogicalType::TIME_MICROS ||
logical == parquet::LogicalType::TIMESTAMP_MICROS ||
logical == parquet::LogicalType::INT_8 ||
logical == parquet::LogicalType::INT_16 ||
logical == parquet::LogicalType::INT_32 ||
logical == parquet::LogicalType::INT_64) {
switch(physical) {
case parquet::Type::BOOLEAN:
type = "TINYINT";
} else if(col->logical_type() == parquet::LogicalType::INT_16) {
type = "SMALLINT";
}
break;
case parquet::Type::INT96:
// INT96 is used for nanosecond precision on timestamps; we truncate
// to millisecond precision.
case parquet::Type::INT64:
type = "BIGINT";
break;
case parquet::Type::FLOAT:
type = "REAL";
break;
case parquet::Type::DOUBLE:
type = "DOUBLE";
break;
case parquet::Type::BYTE_ARRAY:
if(col->logical_type() == parquet::LogicalType::UTF8) {
type = "TEXT";
}
break;
case parquet::Type::FIXED_LEN_BYTE_ARRAY:
default:
break;
break;
case parquet::Type::INT32:
if(logical == parquet::LogicalType::NONE ||
logical == parquet::LogicalType::INT_32) {
type = "INT";
} else if(logical == parquet::LogicalType::INT_8) {
type = "TINYINT";
} else if(logical == parquet::LogicalType::INT_16) {
type = "SMALLINT";
}
break;
case parquet::Type::INT96:
// INT96 is used for nanosecond precision on timestamps; we truncate
// to millisecond precision.
case parquet::Type::INT64:
type = "BIGINT";
break;
case parquet::Type::FLOAT:
type = "REAL";
break;
case parquet::Type::DOUBLE:
type = "DOUBLE";
break;
case parquet::Type::BYTE_ARRAY:
if(logical == parquet::LogicalType::UTF8) {
type = "TEXT";
}
break;
case parquet::Type::FIXED_LEN_BYTE_ARRAY:
default:
break;
}
}
if(type.empty()) {
std::ostringstream ss;
ss << __FILE__ << ":" << __LINE__ << ": column " << i << " has unsupported type: " <<
parquet::TypeToString(col->physical_type()) << "/" << parquet::LogicalTypeToString(col->logical_type());
parquet::TypeToString(physical) << "/" << parquet::LogicalTypeToString(logical);
throw std::invalid_argument(ss.str());
}