1
0
mirror of https://github.com/mariadb-corporation/mariadb-columnstore-engine.git synced 2025-04-23 07:05:36 +03:00
mariadb-columnstore-engine/utils/funcexp/func_substring_index.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

213 lines
6.0 KiB
C++

/* Copyright (C) 2014 InfiniDB, Inc.
Copyright (C) 2019 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. */
/****************************************************************************
* $Id: func_substring_index.cpp 2477 2011-04-01 16:07:35Z rdempsey $
*
*
****************************************************************************/
#include <string>
using namespace std;
#include "functor_str.h"
#include "functioncolumn.h"
using namespace execplan;
#include "rowgroup.h"
using namespace rowgroup;
#include "joblisttypes.h"
using namespace joblist;
namespace funcexp
{
CalpontSystemCatalog::ColType Func_substring_index::operationType(FunctionParm& fp, CalpontSystemCatalog::ColType& resultType)
{
// operation type is not used by this functor
return fp[0]->data()->resultType();
}
std::string Func_substring_index::getStrVal(rowgroup::Row& row,
FunctionParm& fp,
bool& isNull,
execplan::CalpontSystemCatalog::ColType& ct)
{
CHARSET_INFO* cs = ct.getCharset();
const string& str = fp[0]->data()->getStrVal(row, isNull);
if (isNull)
return "";
int64_t strLen = str.length();
const string& delimstr = fp[1]->data()->getStrVal(row, isNull);
if (isNull)
return "";
int64_t delimLen = delimstr.length();
int64_t count = fp[2]->data()->getIntVal(row, isNull);
if (isNull)
return "";
if (strLen == 0 || delimLen == 0 || count == 0)
return "";
if (count > strLen)
return str;
if ((count < 0) && ((count * -1) > strLen))
return str;
bool binaryCmp = (cs->state & MY_CS_BINSORT) || !cs->use_mb();
std::string value; // Only used if !use_mb()
if (!binaryCmp) // Charset supports multibyte characters
{
const char* src = str.c_str();
const char* srcEnd = src + strLen;
const char* srchEnd = srcEnd - delimLen + 1;
const char* delim = delimstr.c_str();
const char* delimEnd = delim + delimLen;
char* ptr = const_cast<char*>(src);
char *i,*j;
uint32_t l;
int32_t n = 0, c = count, pass;
// For count > 0, this loop goes once.
// For count < 0, it goes twice
for (pass = (count > 0 ? 1 : 0); pass<2; ++pass)
{
while (ptr < srchEnd)
{
bool found = false;
if (*ptr == *delim) // If the first byte matches, maybe we have a match
{
// Do a byte by byte compare of src at that spot against delim
i = ptr + 1;
j = const_cast<char*>(delim) + 1;
found = true;
while (j != delimEnd)
{
if (*i++ != *j++)
{
found = false;
break;
}
}
}
if (found)
{
if (pass==0)
++n;
else if (!--c)
break;
ptr += delimLen;
continue;
}
else
{
// move to the next character
if ((l = my_ismbchar(cs, ptr, srcEnd))) // returns the number of bytes in the leading char or zero if one byte
ptr += l;
else
++ptr;
}
}
if (pass == 0) /* count<0 */
{
c += n + 1;
if (c <= 0)
{
return str; // not found, return the original string
}
// Go back and do a second pass
ptr = const_cast<char*>(src);
}
else
{
if (c)
{
return str; // not found, return the original string
}
}
}
if ( count > 0) /* return left part */
{
std::string ret(src, ptr - src);
return ret;
}
else /* return right part */
{
ptr+= delimLen;
std::string ret(ptr, srcEnd - ptr);
return ret;
}
}
else
{
if (count > 0)
{
int pointer = 0;
int64_t end = strLen;
for ( int64_t i = 0 ; i < count ; i ++ )
{
string::size_type pos = str.find(delimstr, pointer);
if (pos != string::npos)
pointer = pos + 1;
end = pos;
}
value = str.substr(0, end);
}
else
{
count = -count;
int pointer = strLen;
int start = 0;
for ( int64_t i = 0 ; i < count ; i ++ )
{
string::size_type pos = str.rfind(delimstr, pointer);
if (pos != string::npos)
{
if ( count > strLen )
return "";
pointer = pos - 1;
start = pos + 1;
}
else
start = 0;
}
value = str.substr(start, strLen);
}
}
return value;
}
} // namespace funcexp
// vim:ts=4 sw=4: