This commit is contained in:
Alexey Milovidov 2018-01-14 03:12:23 +03:00
parent 610b64679f
commit ce5de79263
6 changed files with 76 additions and 27 deletions

2
contrib/librdkafka vendored

@ -1 +1 @@
Subproject commit 3401fa1e45605b5ae806f94905c92f5f546a607b Subproject commit c3d50eb613704fb9c8ab3bce95a88275cb5875b7

2
contrib/poco vendored

@ -1 +1 @@
Subproject commit bcf9ebad48b2162d25f5fc432b176d74a09f498d Subproject commit 81d4fdfcb887f89b0f7b1e9b503cbe63e6d8366b

View File

@ -16,6 +16,7 @@ namespace ErrorCodes
{ {
extern const int CANNOT_PARSE_INPUT_ASSERTION_FAILED; extern const int CANNOT_PARSE_INPUT_ASSERTION_FAILED;
extern const int CANNOT_PARSE_QUOTED_STRING; extern const int CANNOT_PARSE_QUOTED_STRING;
extern const int CANNOT_PARSE_NUMBER;
extern const int CANNOT_PARSE_DATE; extern const int CANNOT_PARSE_DATE;
extern const int CANNOT_PARSE_DATETIME; extern const int CANNOT_PARSE_DATETIME;
extern const int CANNOT_READ_ARRAY_FROM_TEXT; extern const int CANNOT_READ_ARRAY_FROM_TEXT;
@ -80,6 +81,7 @@ bool ValuesRowInputStream::read(MutableColumns & columns)
*/ */
if (e.code() == ErrorCodes::CANNOT_PARSE_INPUT_ASSERTION_FAILED if (e.code() == ErrorCodes::CANNOT_PARSE_INPUT_ASSERTION_FAILED
|| e.code() == ErrorCodes::CANNOT_PARSE_QUOTED_STRING || e.code() == ErrorCodes::CANNOT_PARSE_QUOTED_STRING
|| e.code() == ErrorCodes::CANNOT_PARSE_NUMBER
|| e.code() == ErrorCodes::CANNOT_PARSE_DATE || e.code() == ErrorCodes::CANNOT_PARSE_DATE
|| e.code() == ErrorCodes::CANNOT_PARSE_DATETIME || e.code() == ErrorCodes::CANNOT_PARSE_DATETIME
|| e.code() == ErrorCodes::CANNOT_READ_ARRAY_FROM_TEXT) || e.code() == ErrorCodes::CANNOT_READ_ARRAY_FROM_TEXT)

View File

@ -19,6 +19,7 @@ void registerFunctionsReinterpret(FunctionFactory & factory)
factory.registerFunction<FunctionReinterpretAsDate>(); factory.registerFunction<FunctionReinterpretAsDate>();
factory.registerFunction<FunctionReinterpretAsDateTime>(); factory.registerFunction<FunctionReinterpretAsDateTime>();
factory.registerFunction<FunctionReinterpretAsString>(); factory.registerFunction<FunctionReinterpretAsString>();
factory.registerFunction<FunctionReinterpretAsFixedString>();
} }
} }

View File

@ -46,13 +46,76 @@ public:
{ {
const IDataType & type = *arguments[0]; const IDataType & type = *arguments[0];
if (type.isValueUnambiguouslyRepresentedInFixedSizeContiguousMemoryRegion())
return std::make_shared<DataTypeFixedString>(type.getSizeOfValueInMemory());
if (type.isValueUnambiguouslyRepresentedInContiguousMemoryRegion()) if (type.isValueUnambiguouslyRepresentedInContiguousMemoryRegion())
return std::make_shared<DataTypeString>(); return std::make_shared<DataTypeString>();
throw Exception("Cannot reinterpret " + type.getName() + " as String because it is not contiguous in memory", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); throw Exception("Cannot reinterpret " + type.getName() + " as String because it is not contiguous in memory", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
} }
void executeToString(const IColumn & src, ColumnString & dst)
{
size_t rows = src.size();
ColumnString::Chars_t & data_to = dst.getChars();
ColumnString::Offsets & offsets_to = dst.getOffsets();
offsets_to.resize(rows);
ColumnString::Offset offset = 0;
for (size_t i = 0; i < rows; ++i)
{
StringRef data = src.getDataAt(i);
/// Cut trailing zero bytes.
while (data.size && data.data[data.size - 1] == 0)
--data.size;
data_to.resize(offset + data.size + 1);
memcpySmallAllowReadWriteOverflow15(&data_to[offset], data.data, data.size);
offset += data.size;
data_to[offset] = 0;
++offset;
offsets_to[i] = offset;
}
}
bool useDefaultImplementationForConstants() const override { return true; }
void executeImpl(Block & block, const ColumnNumbers & arguments, size_t result) override
{
const IColumn & src = *block.getByPosition(arguments[0]).column;
MutableColumnPtr dst = block.getByPosition(result).type->createColumn();
if (ColumnString * dst_concrete = typeid_cast<ColumnString *>(dst.get()))
executeToString(src, *dst_concrete);
else
throw Exception("Illegal column " + src.getName() + " of argument of function " + getName(), ErrorCodes::ILLEGAL_COLUMN);
block.getByPosition(result).column = std::move(dst);
}
};
template <typename Name>
class FunctionReinterpretAsFixedStringImpl : public IFunction
{
public:
static constexpr auto name = Name::name;
static FunctionPtr create(const Context &) { return std::make_shared<FunctionReinterpretAsFixedStringImpl>(); };
String getName() const override
{
return name;
}
size_t getNumberOfArguments() const override { return 1; }
DataTypePtr getReturnTypeImpl(const DataTypes & arguments) const override
{
const IDataType & type = *arguments[0];
if (type.isValueUnambiguouslyRepresentedInFixedSizeContiguousMemoryRegion())
return std::make_shared<DataTypeFixedString>(type.getSizeOfValueInMemory());
throw Exception("Cannot reinterpret " + type.getName() + " as FixedString because it is not fixed size and contiguous in memory", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
void executeToFixedString(const IColumn & src, ColumnFixedString & dst, size_t n) void executeToFixedString(const IColumn & src, ColumnFixedString & dst, size_t n)
{ {
size_t rows = src.size(); size_t rows = src.size();
@ -68,26 +131,6 @@ public:
} }
} }
void executeToString(const IColumn & src, ColumnString & dst)
{
size_t rows = src.size();
ColumnString::Chars_t & data_to = dst.getChars();
ColumnString::Offsets & offsets_to = dst.getOffsets();
offsets_to.resize(rows);
ColumnString::Offset offset = 0;
for (size_t i = 0; i < rows; ++i)
{
StringRef data = src.getDataAt(i);
data_to.resize(offset + data.size + 1);
memcpySmallAllowReadWriteOverflow15(&data_to[offset], data.data, data.size);
offset += data.size;
data_to[offset] = 0;
++offset;
offsets_to[i] = offset;
}
}
bool useDefaultImplementationForConstants() const override { return true; } bool useDefaultImplementationForConstants() const override { return true; }
void executeImpl(Block & block, const ColumnNumbers & arguments, size_t result) override void executeImpl(Block & block, const ColumnNumbers & arguments, size_t result) override
@ -97,8 +140,6 @@ public:
if (ColumnFixedString * dst_concrete = typeid_cast<ColumnFixedString *>(dst.get())) if (ColumnFixedString * dst_concrete = typeid_cast<ColumnFixedString *>(dst.get()))
executeToFixedString(src, *dst_concrete, dst_concrete->getN()); executeToFixedString(src, *dst_concrete, dst_concrete->getN());
else if (ColumnString * dst_concrete = typeid_cast<ColumnString *>(dst.get()))
executeToString(src, *dst_concrete);
else else
throw Exception("Illegal column " + src.getName() + " of argument of function " + getName(), ErrorCodes::ILLEGAL_COLUMN); throw Exception("Illegal column " + src.getName() + " of argument of function " + getName(), ErrorCodes::ILLEGAL_COLUMN);
@ -202,6 +243,7 @@ struct NameReinterpretAsFloat64 { static constexpr auto name = "reinterpretA
struct NameReinterpretAsDate { static constexpr auto name = "reinterpretAsDate"; }; struct NameReinterpretAsDate { static constexpr auto name = "reinterpretAsDate"; };
struct NameReinterpretAsDateTime { static constexpr auto name = "reinterpretAsDateTime"; }; struct NameReinterpretAsDateTime { static constexpr auto name = "reinterpretAsDateTime"; };
struct NameReinterpretAsString { static constexpr auto name = "reinterpretAsString"; }; struct NameReinterpretAsString { static constexpr auto name = "reinterpretAsString"; };
struct NameReinterpretAsFixedString { static constexpr auto name = "reinterpretAsFixedString"; };
using FunctionReinterpretAsUInt8 = FunctionReinterpretStringAs<DataTypeUInt8, NameReinterpretAsUInt8>; using FunctionReinterpretAsUInt8 = FunctionReinterpretStringAs<DataTypeUInt8, NameReinterpretAsUInt8>;
using FunctionReinterpretAsUInt16 = FunctionReinterpretStringAs<DataTypeUInt16, NameReinterpretAsUInt16>; using FunctionReinterpretAsUInt16 = FunctionReinterpretStringAs<DataTypeUInt16, NameReinterpretAsUInt16>;
@ -217,6 +259,7 @@ using FunctionReinterpretAsDate = FunctionReinterpretStringAs<DataTypeDate,
using FunctionReinterpretAsDateTime = FunctionReinterpretStringAs<DataTypeDateTime, NameReinterpretAsDateTime>; using FunctionReinterpretAsDateTime = FunctionReinterpretStringAs<DataTypeDateTime, NameReinterpretAsDateTime>;
using FunctionReinterpretAsString = FunctionReinterpretAsStringImpl<NameReinterpretAsString>; using FunctionReinterpretAsString = FunctionReinterpretAsStringImpl<NameReinterpretAsString>;
using FunctionReinterpretAsFixedString = FunctionReinterpretAsStringImpl<NameReinterpretAsFixedString>;
} }

View File

@ -718,8 +718,11 @@ void skipJSONFieldPlain(ReadBuffer & buf, const StringRef & name_of_filed)
NullSink sink; NullSink sink;
readJSONStringInto(sink, buf); readJSONStringInto(sink, buf);
} }
else if (isNumericASCII(*buf.position()) || *buf.position() == '-' || *buf.position() == '+') /// skip number else if (isNumericASCII(*buf.position()) || *buf.position() == '-' || *buf.position() == '+' || *buf.position() == '.') /// skip number
{ {
if (*buf.position() == '+')
++buf.position();
double v; double v;
if (!tryReadFloatText(v, buf)) if (!tryReadFloatText(v, buf))
throw Exception("Expected a number field for key '" + name_of_filed.toString() + "'", ErrorCodes::INCORRECT_DATA); throw Exception("Expected a number field for key '" + name_of_filed.toString() + "'", ErrorCodes::INCORRECT_DATA);