database/mariadb-columnstore-engine
1
0
Fork 0
mirror of https://github.com/mariadb-corporation/mariadb-columnstore-engine.git synced 2025-04-20 09:07:44 +03:00
Code
mariadb-columnstore-engine/utils/funcexp/func_decode_oracle.cpp
Alexander Barkov 9608533d92 MCOL-4734 Compilation failure: MariaDB-10.6 + ColumnStore-develop 
mcsconfig.h and my_config.h have the following
pre-processor definitions:

1. Conflicting definitions coming from the standard cmake definitions:
- PACKAGE
- PACKAGE_BUGREPORT
- PACKAGE_NAME
- PACKAGE_STRING
- PACKAGE_TARNAME
- PACKAGE_VERSION
- VERSION

2. Conflicting definitions of other kinds:
- HAVE_STRTOLL - this is a dirt in MariaDB headers.
  Should be fixed in the server code. my_config.h erroneously
  performs "#define HAVE_STRTOLL" instead of "#define HAVE_STRTOLL 1".
  in some cases. The former is not CMake compatible style. The latter is.

3. Non-conflicting definitions:
  Otherwise, mcsconfig.h and my_config.h should be mutually compatible,
  because both are generated by cmake on the same host machine. So
  they should have exactly equal definitions like "HAVE_XXX", "SIZEOF_XXX", etc.

Observations:
- It's OK to include both mcsconfig.h and my_config.h providing that we
  suppress duplicate definition of the above conflicting types #1 and #2.
- There is no a need to suppress duplicate definitions mentioned in #3,
  as they are compatible!
- my_sys.h and m_ctype.h must always follow a CMake configuation header,
  either my_config.h or mcsconfig.h (or both).
  They must never be included without any preceeding configuration header.

This change make sure that we resolve conflicts by:
- either disallowing inclusion of mcsconfig.h and my_config.h
  at the same time
- or by hiding conflicting definitions #1 and #2
  (with their later restoring).
- also, by making sure that my_sys.h and m_ctype.h always follow
  a CMake configuration file.

Details:
- idb_mysql.h can now only be included only after my_config.h
  An attempt to use idb_mysql.h with mcsconfig.h instead of
  my_config.h is caught by the "#error" preprocessor directive.

- mariadb_my_sys.h can now be only included after mcsconfig.h.
  An attempt to use mariadb_my_sys.h without mcscofig.h
  (e.g. with my_config.h) is also caught by "#error".

- collation.h now can now be included in two ways.
  It now has the following effective structure:

    #if defined(PREFER_MY_CONFIG_H) && defined(MY_CONFIG_H)
    //  Remember current conflicting definitions on the preprocessor stack
    //  Undefine current conflicting definitions
    #endif
    #include "mcsconfig.h"
    #include "m_ctype.h"
    #if defined(PREFER_MY_CONFIG_H) && defined(MY_CONFIG_H)
    #    Restore conflicting definitions from the preprocessor stack
    #endif

  and can be included as follows:

  a. using only mcsconfig.h as a configuration header:

    // my_config.h must not be included so far
    #include "collation.h"

  b. using my_config.h as the first included configuration file:

    #define PREFER_MY_CONFIG_H // Force conflict resolution
    #include "my_config.h"     // can be included directly or indirectly
    ...
    #include "collation.h"

Other changes:

- Adding helper header files
     utils/common/mcsconfig_conflicting_defs_remember.h
     utils/common/mcsconfig_conflicting_defs_restore.h
     utils/common/mcsconfig_conflicting_defs_undef.h
  to perform conflict resolution easier.

- Removing `#include "collation.h"` from a number of files,
  as it's automatically included from rowgroup.h.

- Removing redundant `#include "utils_utf8.h"`.
  This change is not directly related to the problem being fixed,
  but it's nice to remove redundant directives for both collation.h
  and utils_utf8.h from all the files that do not really need them.
  (this change could probably have gone as a separate commit)

- Changing my_init() to MY_INIT(argv[0]) in the MCS services sources.
  After the fix of the complitation failure it appeared that ColumnStore
  services compiled with the debug build crash due to recent changes in
  safemalloc. The crash happened in strcmp() with `my_progname` as an argument
  (where my_progname is a mysys global variable). This problem should
  probably be fixed on the server side as well to avoid passing NULL.
  But, the majority of MariaDB executable programs also use MY_INIT(argv[0])
  rather than my_init(). So let's make MCS do like the other programs do.
2021-05-25 12:34:36 +04:00

584 lines
16 KiB
C++
Raw Blame History

/* Copyright (C) 2021 MariaDB Corporation
This program is free software; you can redistribute it and/or
modify it under the terms of the GNU General Public License
as published by the Free Software Foundation; version 2 of
the License.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
MA 02110-1301, USA. */
#include <string>
//#define NDEBUG
#include <cassert>
using namespace std;
#include "functor_all.h"
#include "functioncolumn.h"
#include "predicateoperator.h"
using namespace execplan;
#include "rowgroup.h"
using namespace rowgroup;
#include "errorcodes.h"
#include "idberrorinfo.h"
#include "errorids.h"
using namespace logging;
using namespace funcexp;
namespace
{
using namespace funcexp;
inline uint64_t simple_case_cmp(Row& row,
FunctionParm& parm,
bool& isNull,
CalpontSystemCatalog::ColType& operationColType)
{
uint64_t i = 0; // index to the parm list
uint64_t n = 0; // remove expression from count of expression_i + result_i
uint64_t hasElse = (parm.size() - 1) % 2; // if 1, then ELSE exist
uint64_t whereCount = hasElse ? (parm.size() - 2) / 2 : (parm.size() - 1) / 2;
bool foundIt = false;
switch (operationColType.colDataType)
{
case execplan::CalpontSystemCatalog::TINYINT:
case execplan::CalpontSystemCatalog::SMALLINT:
case execplan::CalpontSystemCatalog::MEDINT:
case execplan::CalpontSystemCatalog::INT:
case execplan::CalpontSystemCatalog::BIGINT:
case execplan::CalpontSystemCatalog::DATE:
{
int64_t ev = parm[n]->data()->getIntVal(row, isNull);
if (isNull)
break;
for (i = 1; i <= whereCount; i++)
{
if (ev == parm[i]->data()->getIntVal(row, isNull) && !isNull)
{
foundIt = true;
break;
}
else
isNull = false;
}
break;
}
case execplan::CalpontSystemCatalog::DATETIME:
{
int64_t ev = parm[n]->data()->getDatetimeIntVal(row, isNull);
if (isNull)
break;
for (i = 1; i <= whereCount; i++)
{
if (ev == parm[i]->data()->getDatetimeIntVal(row, isNull) && !isNull)
{
foundIt = true;
break;
}
else
isNull = false;
}
break;
}
case execplan::CalpontSystemCatalog::TIMESTAMP:
{
int64_t ev = parm[n]->data()->getTimestampIntVal(row, isNull);
if (isNull)
break;
for (i = 1; i <= whereCount; i++)
{
if (ev == parm[i]->data()->getTimestampIntVal(row, isNull) && !isNull)
{
foundIt = true;
break;
}
else
isNull = false;
}
break;
}
case execplan::CalpontSystemCatalog::TIME:
{
int64_t ev = parm[n]->data()->getTimeIntVal(row, isNull);
if (isNull)
break;
for (i = 1; i <= whereCount; i++)
{
if (ev == parm[i]->data()->getTimeIntVal(row, isNull) && !isNull)
{
foundIt = true;
break;
}
else
isNull = false;
}
break;
}
case execplan::CalpontSystemCatalog::UBIGINT:
case execplan::CalpontSystemCatalog::UINT:
case execplan::CalpontSystemCatalog::UMEDINT:
case execplan::CalpontSystemCatalog::UTINYINT:
case execplan::CalpontSystemCatalog::USMALLINT:
{
uint64_t ev = parm[n]->data()->getUintVal(row, isNull);
if (isNull)
break;
for (i = 1; i <= whereCount; i++)
{
if (ev == parm[i]->data()->getUintVal(row, isNull) && !isNull)
{
foundIt = true;
break;
}
else
isNull = false;
}
break;
}
case execplan::CalpontSystemCatalog::CHAR:
case execplan::CalpontSystemCatalog::TEXT:
case execplan::CalpontSystemCatalog::VARCHAR:
{
const string& ev = parm[n]->data()->getStrVal(row, isNull);
if (isNull)
break;
CHARSET_INFO* cs = parm[n]->data()->resultType().getCharset();
for (i = 1; i <= whereCount; i++)
{
//BUG 5362
const string& p1 = parm[i]->data()->getStrVal(row, isNull);
if (isNull)
break;
if (cs->strnncoll(ev.c_str(), ev.length(), p1.c_str(), p1.length()) == 0)
{
foundIt = true;
break;
}
}
break;
}
case execplan::CalpontSystemCatalog::DECIMAL:
case execplan::CalpontSystemCatalog::UDECIMAL:
{
IDB_Decimal ev = parm[n]->data()->getDecimalVal(row, isNull);
if (isNull)
break;
for (i = 1; i <= whereCount; i++)
{
if (ev == parm[i]->data()->getDecimalVal(row, isNull) && !isNull)
{
foundIt = true;
break;
}
else
isNull = false;
}
break;
}
case execplan::CalpontSystemCatalog::DOUBLE:
case execplan::CalpontSystemCatalog::UDOUBLE:
{
double ev = parm[n]->data()->getDoubleVal(row, isNull);
if (isNull)
break;
for (i = 1; i <= whereCount; i++)
{
if (ev == parm[i]->data()->getDoubleVal(row, isNull) && !isNull)
{
foundIt = true;
break;
}
else
isNull = false;
}
break;
}
case execplan::CalpontSystemCatalog::FLOAT:
case execplan::CalpontSystemCatalog::UFLOAT:
{
float ev = parm[n]->data()->getFloatVal(row, isNull);
if (isNull)
break;
for (i = 1; i <= whereCount; i++)
{
if (ev == parm[i]->data()->getFloatVal(row, isNull) && !isNull)
{
foundIt = true;
break;
}
else
isNull = false;
}
break;
}
case execplan::CalpontSystemCatalog::LONGDOUBLE:
{
long double ev = parm[n]->data()->getLongDoubleVal(row, isNull);
if (isNull)
break;
for (i = 1; i <= whereCount; i++)
{
if (ev == parm[i]->data()->getLongDoubleVal(row, isNull) && !isNull)
{
foundIt = true;
break;
}
else
isNull = false;
}
break;
}
default:
{
std::ostringstream oss;
oss << "case: datatype of " << execplan::colDataTypeToString(operationColType.colDataType);
throw logging::IDBExcept(oss.str(), ERR_DATATYPE_NOT_SUPPORT);
}
}
if (!foundIt && !hasElse)
isNull = true;
else if (!foundIt && hasElse && !isNull)
{
i = parm.size() - 1;
}
else if (isNull && hasElse)
// BUG 5110. Only way we can exit above with isNull == true is when ev is NULL
// if so and we have else condition we need to use it by setting i = else
{
i = parm.size() - 1;
isNull = false;
}
if (foundIt)
{
i += whereCount;
}
return i;
}
CalpontSystemCatalog::ColType caseOperationType(FunctionParm& fp,
CalpontSystemCatalog::ColType& resultType,
bool simpleCase)
{
uint64_t simple = simpleCase ? 1 : 0;
bool hasElse = (((fp.size()-simple) % 2) != 0); // if 1, then ELSE exist
uint64_t parmCount = hasElse ? (fp.size() - 2) : (fp.size() - 1);
uint64_t whereCount = hasElse ? (fp.size() - 2 + simple) / 2 : (fp.size() - 1) / 2 + simple;
bool allStringO = true;
bool allStringR = true;
FunctionParm::size_type l = fp.size() - 1; // last fp index
idbassert(fp[l]->data());
CalpontSystemCatalog::ColType oct = fp[l]->data()->resultType();
CalpontSystemCatalog::ColType rct = resultType;
bool operation = true;
for (uint64_t i = 0; i <= parmCount; i++)
{
// for SimpleCase, we return the type of the case expression,
// which will always be in position 0.
if (i == 0 && simpleCase)
{
if (fp[i]->data()->resultType().colDataType != CalpontSystemCatalog::CHAR &&
fp[i]->data()->resultType().colDataType != CalpontSystemCatalog::TEXT &&
fp[i]->data()->resultType().colDataType != CalpontSystemCatalog::VARCHAR)
{
PredicateOperator op;
op.setOpType(oct, fp[i]->data()->resultType());
allStringO = false;
oct = op.operationType();
}
i += 1;
}
// operation or result type
operation = ((i > 0+simple) && (i <= whereCount));
if (fp[i]->data()->resultType().colDataType != CalpontSystemCatalog::CHAR &&
fp[i]->data()->resultType().colDataType != CalpontSystemCatalog::TEXT &&
fp[i]->data()->resultType().colDataType != CalpontSystemCatalog::VARCHAR)
{
// this is not a string column
PredicateOperator op;
if (operation)
{
if (!simpleCase)
{
op.setOpType(oct, fp[i]->data()->resultType());
allStringO = false;
oct = op.operationType();
}
}
// If any parm is of string type, the result type should be string. (same as if)
else if (rct.colDataType != CalpontSystemCatalog::CHAR &&
rct.colDataType != CalpontSystemCatalog::TEXT &&
rct.colDataType != CalpontSystemCatalog::VARCHAR)
{
op.setOpType(rct, fp[i]->data()->resultType());
allStringR = false;
rct = op.operationType();
}
}
else
{
// this is a string
// If any parm is of string type, the result type should be string. (same as if)
allStringR = true;
}
}
if (allStringO)
{
oct.colDataType = CalpontSystemCatalog::VARCHAR;
oct.colWidth = 255;
}
if (allStringR)
{
rct.colDataType = CalpontSystemCatalog::VARCHAR;
rct.colWidth = 255;
}
if (rct.scale != 0 && rct.colDataType == CalpontSystemCatalog::BIGINT)
rct.colDataType = CalpontSystemCatalog::DECIMAL;
if (oct.scale != 0 && oct.colDataType == CalpontSystemCatalog::BIGINT)
oct.colDataType = CalpontSystemCatalog::DECIMAL;
resultType = rct;
return oct;
}
}
namespace funcexp
{
// simple CASE:
// SELECT CASE ("expression")
// WHEN "condition1" THEN "result1"
// WHEN "condition2" THEN "result2"
// ...
// [ELSE "resultN"]
// END
//
// simple CASE parm order:
// expression condition1 condition2 ... result1 result2 ... [resultN]
//
// Note that this order changed in 10.2.14, see MCOL-1341
CalpontSystemCatalog::ColType Func_decode_oracle::operationType(FunctionParm& fp, CalpontSystemCatalog::ColType& resultType)
{
return caseOperationType(fp, resultType, true);
}
bool Func_decode_oracle::getBoolVal(Row& row,
FunctionParm& parm,
bool& isNull,
CalpontSystemCatalog::ColType& operationColType)
{
uint64_t i = simple_case_cmp(row, parm, isNull, operationColType);
if (isNull)
return false;
ParseTree* lop = parm[i]->left();
ParseTree* rop = parm[i]->right();
if (lop && rop)
{
return (reinterpret_cast<Operator*>(parm[i]->data()))->getBoolVal(row, isNull, lop, rop);
}
return parm[i]->data()->getBoolVal(row, isNull);
}
int64_t Func_decode_oracle::getIntVal(Row& row,
FunctionParm& parm,
bool& isNull,
CalpontSystemCatalog::ColType& operationColType)
{
uint64_t i = simple_case_cmp(row, parm, isNull, operationColType);
if (isNull)
return joblist::BIGINTNULL;
return parm[i]->data()->getIntVal(row, isNull);
}
string Func_decode_oracle::getStrVal(Row& row,
FunctionParm& parm,
bool& isNull,
CalpontSystemCatalog::ColType& operationColType)
{
uint64_t i = simple_case_cmp(row, parm, isNull, operationColType);
if (isNull)
return string("");
return parm[i]->data()->getStrVal(row, isNull);
}
IDB_Decimal Func_decode_oracle::getDecimalVal(Row& row,
FunctionParm& parm,
bool& isNull,
CalpontSystemCatalog::ColType& operationColType)
{
uint64_t i = simple_case_cmp(row, parm, isNull, operationColType);
if (isNull)
return IDB_Decimal(); // need a null value for IDB_Decimal??
return parm[i]->data()->getDecimalVal(row, isNull);
}
double Func_decode_oracle::getDoubleVal(Row& row,
FunctionParm& parm,
bool& isNull,
CalpontSystemCatalog::ColType& operationColType)
{
uint64_t i = simple_case_cmp(row, parm, isNull, operationColType);
if (isNull)
return doubleNullVal();
return parm[i]->data()->getDoubleVal(row, isNull);
}
long double Func_decode_oracle::getLongDoubleVal(Row& row,
FunctionParm& parm,
bool& isNull,
CalpontSystemCatalog::ColType& operationColType)
{
uint64_t i = simple_case_cmp(row, parm, isNull, operationColType);
if (isNull)
return doubleNullVal();
return parm[i]->data()->getLongDoubleVal(row, isNull);
}
int32_t Func_decode_oracle::getDateIntVal(rowgroup::Row& row,
FunctionParm& parm,
bool& isNull,
execplan::CalpontSystemCatalog::ColType& op_ct)
{
uint64_t i = simple_case_cmp(row, parm, isNull, op_ct);
if (isNull)
return joblist::DATENULL;
return parm[i]->data()->getDateIntVal(row, isNull);
}
int64_t Func_decode_oracle::getDatetimeIntVal(rowgroup::Row& row,
FunctionParm& parm,
bool& isNull,
execplan::CalpontSystemCatalog::ColType& op_ct)
{
uint64_t i = simple_case_cmp(row, parm, isNull, op_ct);
if (isNull)
return joblist::DATETIMENULL;
return parm[i]->data()->getDatetimeIntVal(row, isNull);
}
int64_t Func_decode_oracle::getTimestampIntVal(rowgroup::Row& row,
FunctionParm& parm,
bool& isNull,
execplan::CalpontSystemCatalog::ColType& op_ct)
{
uint64_t i = simple_case_cmp(row, parm, isNull, op_ct);
if (isNull)
return joblist::TIMESTAMPNULL;
return parm[i]->data()->getTimestampIntVal(row, isNull);
}
int64_t Func_decode_oracle::getTimeIntVal(rowgroup::Row& row,
FunctionParm& parm,
bool& isNull,
execplan::CalpontSystemCatalog::ColType& op_ct)
{
uint64_t i = simple_case_cmp(row, parm, isNull, op_ct);
if (isNull)
return joblist::TIMENULL;
return parm[i]->data()->getTimeIntVal(row, isNull);
}
}
View Git Blame Copy Permalink