mariadb/sql/item_sum.h
unknown 01d03e7b4b This changeset is largely a handler cleanup changeset (WL#3281), but includes fixes and cleanups that was found necessary while testing the handler changes
Changes that requires code changes in other code of other storage engines.
(Note that all changes are very straightforward and one should find all issues
by compiling a --debug build and fixing all compiler errors and all
asserts in field.cc while running the test suite),

- New optional handler function introduced: reset()
  This is called after every DML statement to make it easy for a handler to
  statement specific cleanups.
  (The only case it's not called is if force the file to be closed)

- handler::extra(HA_EXTRA_RESET) is removed. Code that was there before
  should be moved to handler::reset()

- table->read_set contains a bitmap over all columns that are needed
  in the query.  read_row() and similar functions only needs to read these
  columns
- table->write_set contains a bitmap over all columns that will be updated
  in the query. write_row() and update_row() only needs to update these
  columns.
  The above bitmaps should now be up to date in all context
  (including ALTER TABLE, filesort()).

  The handler is informed of any changes to the bitmap after
  fix_fields() by calling the virtual function
  handler::column_bitmaps_signal(). If the handler does caching of
  these bitmaps (instead of using table->read_set, table->write_set),
  it should redo the caching in this code. as the signal() may be sent
  several times, it's probably best to set a variable in the signal
  and redo the caching on read_row() / write_row() if the variable was
  set.

- Removed the read_set and write_set bitmap objects from the handler class

- Removed all column bit handling functions from the handler class.
  (Now one instead uses the normal bitmap functions in my_bitmap.c instead
  of handler dedicated bitmap functions)

- field->query_id is removed. One should instead instead check
  table->read_set and table->write_set if a field is used in the query.

- handler::extra(HA_EXTRA_RETRIVE_ALL_COLS) and
  handler::extra(HA_EXTRA_RETRIEVE_PRIMARY_KEY) are removed. One should now
  instead use table->read_set to check for which columns to retrieve.

- If a handler needs to call Field->val() or Field->store() on columns
  that are not used in the query, one should install a temporary
  all-columns-used map while doing so. For this, we provide the following
  functions:

  my_bitmap_map *old_map= dbug_tmp_use_all_columns(table, table->read_set);
  field->val();
  dbug_tmp_restore_column_map(table->read_set, old_map);

  and similar for the write map:

  my_bitmap_map *old_map= dbug_tmp_use_all_columns(table, table->write_set);
  field->val();
  dbug_tmp_restore_column_map(table->write_set, old_map);

  If this is not done, you will sooner or later hit a DBUG_ASSERT
  in the field store() / val() functions.
  (For not DBUG binaries, the dbug_tmp_restore_column_map() and
  dbug_tmp_restore_column_map() are inline dummy functions and should
  be optimized away be the compiler).

- If one needs to temporary set the column map for all binaries (and not
  just to avoid the DBUG_ASSERT() in the Field::store() / Field::val()
  methods) one should use the functions tmp_use_all_columns() and
  tmp_restore_column_map() instead of the above dbug_ variants.

- All 'status' fields in the handler base class (like records,
  data_file_length etc) are now stored in a 'stats' struct. This makes
  it easier to know what status variables are provided by the base
  handler.  This requires some trivial variable names in the extra()
  function.

- New virtual function handler::records().  This is called to optimize
  COUNT(*) if (handler::table_flags() & HA_HAS_RECORDS()) is true.
  (stats.records is not supposed to be an exact value. It's only has to
  be 'reasonable enough' for the optimizer to be able to choose a good
  optimization path).

- Non virtual handler::init() function added for caching of virtual
  constants from engine.

- Removed has_transactions() virtual method. Now one should instead return
  HA_NO_TRANSACTIONS in table_flags() if the table handler DOES NOT support
  transactions.

- The 'xxxx_create_handler()' function now has a MEM_ROOT_root argument
  that is to be used with 'new handler_name()' to allocate the handler
  in the right area.  The xxxx_create_handler() function is also
  responsible for any initialization of the object before returning.

  For example, one should change:

  static handler *myisam_create_handler(TABLE_SHARE *table)
  {
    return new ha_myisam(table);
  }

  ->

  static handler *myisam_create_handler(TABLE_SHARE *table, MEM_ROOT *mem_root)
  {
    return new (mem_root) ha_myisam(table);
  }

- New optional virtual function: use_hidden_primary_key().
  This is called in case of an update/delete when
  (table_flags() and HA_PRIMARY_KEY_REQUIRED_FOR_DELETE) is defined
  but we don't have a primary key. This allows the handler to take precisions
  in remembering any hidden primary key to able to update/delete any
  found row. The default handler marks all columns to be read.

- handler::table_flags() now returns a ulonglong (to allow for more flags).

- New/changed table_flags()
  - HA_HAS_RECORDS	    Set if ::records() is supported
  - HA_NO_TRANSACTIONS	    Set if engine doesn't support transactions
  - HA_PRIMARY_KEY_REQUIRED_FOR_DELETE
                            Set if we should mark all primary key columns for
			    read when reading rows as part of a DELETE
			    statement. If there is no primary key,
			    all columns are marked for read.
  - HA_PARTIAL_COLUMN_READ  Set if engine will not read all columns in some
			    cases (based on table->read_set)
 - HA_PRIMARY_KEY_ALLOW_RANDOM_ACCESS
   			    Renamed to HA_PRIMARY_KEY_REQUIRED_FOR_POSITION.
 - HA_DUPP_POS              Renamed to HA_DUPLICATE_POS
 - HA_REQUIRES_KEY_COLUMNS_FOR_DELETE
			    Set this if we should mark ALL key columns for
			    read when when reading rows as part of a DELETE
			    statement. In case of an update we will mark
			    all keys for read for which key part changed
			    value.
  - HA_STATS_RECORDS_IS_EXACT
			     Set this if stats.records is exact.
			     (This saves us some extra records() calls
			     when optimizing COUNT(*))
			    

- Removed table_flags()
  - HA_NOT_EXACT_COUNT     Now one should instead use HA_HAS_RECORDS if
			   handler::records() gives an exact count() and
			   HA_STATS_RECORDS_IS_EXACT if stats.records is exact.
  - HA_READ_RND_SAME	   Removed (no one supported this one)

- Removed not needed functions ha_retrieve_all_cols() and ha_retrieve_all_pk()

- Renamed handler::dupp_pos to handler::dup_pos

- Removed not used variable handler::sortkey


Upper level handler changes:

- ha_reset() now does some overall checks and calls ::reset()
- ha_table_flags() added. This is a cached version of table_flags(). The
  cache is updated on engine creation time and updated on open.


MySQL level changes (not obvious from the above):

- DBUG_ASSERT() added to check that column usage matches what is set
  in the column usage bit maps. (This found a LOT of bugs in current
  column marking code).

- In 5.1 before, all used columns was marked in read_set and only updated
  columns was marked in write_set. Now we only mark columns for which we
  need a value in read_set.

- Column bitmaps are created in open_binary_frm() and open_table_from_share().
  (Before this was in table.cc)

- handler::table_flags() calls are replaced with handler::ha_table_flags()

- For calling field->val() you must have the corresponding bit set in
  table->read_set. For calling field->store() you must have the
  corresponding bit set in table->write_set. (There are asserts in
  all store()/val() functions to catch wrong usage)

- thd->set_query_id is renamed to thd->mark_used_columns and instead
  of setting this to an integer value, this has now the values:
  MARK_COLUMNS_NONE, MARK_COLUMNS_READ, MARK_COLUMNS_WRITE
  Changed also all variables named 'set_query_id' to mark_used_columns.

- In filesort() we now inform the handler of exactly which columns are needed
  doing the sort and choosing the rows.

- The TABLE_SHARE object has a 'all_set' column bitmap one can use
  when one needs a column bitmap with all columns set.
  (This is used for table->use_all_columns() and other places)

- The TABLE object has 3 column bitmaps:
  - def_read_set     Default bitmap for columns to be read
  - def_write_set    Default bitmap for columns to be written
  - tmp_set          Can be used as a temporary bitmap when needed.
  The table object has also two pointer to bitmaps read_set and write_set
  that the handler should use to find out which columns are used in which way.

- count() optimization now calls handler::records() instead of using
  handler->stats.records (if (table_flags() & HA_HAS_RECORDS) is true).

- Added extra argument to Item::walk() to indicate if we should also
  traverse sub queries.

- Added TABLE parameter to cp_buffer_from_ref()

- Don't close tables created with CREATE ... SELECT but keep them in
  the table cache. (Faster usage of newly created tables).


New interfaces:

- table->clear_column_bitmaps() to initialize the bitmaps for tables
  at start of new statements.

- table->column_bitmaps_set() to set up new column bitmaps and signal
  the handler about this.

- table->column_bitmaps_set_no_signal() for some few cases where we need
  to setup new column bitmaps but don't signal the handler (as the handler
  has already been signaled about these before). Used for the momement
  only in opt_range.cc when doing ROR scans.

- table->use_all_columns() to install a bitmap where all columns are marked
  as use in the read and the write set.

- table->default_column_bitmaps() to install the normal read and write
  column bitmaps, but not signaling the handler about this.
  This is mainly used when creating TABLE instances.

- table->mark_columns_needed_for_delete(),
  table->mark_columns_needed_for_delete() and
  table->mark_columns_needed_for_insert() to allow us to put additional
  columns in column usage maps if handler so requires.
  (The handler indicates what it neads in handler->table_flags())

- table->prepare_for_position() to allow us to tell handler that it
  needs to read primary key parts to be able to store them in
  future table->position() calls.
  (This replaces the table->file->ha_retrieve_all_pk function)

- table->mark_auto_increment_column() to tell handler are going to update
  columns part of any auto_increment key.

- table->mark_columns_used_by_index() to mark all columns that is part of
  an index.  It will also send extra(HA_EXTRA_KEYREAD) to handler to allow
  it to quickly know that it only needs to read colums that are part
  of the key.  (The handler can also use the column map for detecting this,
  but simpler/faster handler can just monitor the extra() call).

- table->mark_columns_used_by_index_no_reset() to in addition to other columns,
  also mark all columns that is used by the given key.

- table->restore_column_maps_after_mark_index() to restore to default
  column maps after a call to table->mark_columns_used_by_index().

- New item function register_field_in_read_map(), for marking used columns
  in table->read_map. Used by filesort() to mark all used columns

- Maintain in TABLE->merge_keys set of all keys that are used in query.
  (Simplices some optimization loops)

- Maintain Field->part_of_key_not_clustered which is like Field->part_of_key
  but the field in the clustered key is not assumed to be part of all index.
  (used in opt_range.cc for faster loops)

-  dbug_tmp_use_all_columns(), dbug_tmp_restore_column_map()
   tmp_use_all_columns() and tmp_restore_column_map() functions to temporally
   mark all columns as usable.  The 'dbug_' version is primarily intended
   inside a handler when it wants to just call Field:store() & Field::val()
   functions, but don't need the column maps set for any other usage.
   (ie:: bitmap_is_set() is never called)

- We can't use compare_records() to skip updates for handlers that returns
  a partial column set and the read_set doesn't cover all columns in the
  write set. The reason for this is that if we have a column marked only for
  write we can't in the MySQL level know if the value changed or not.
  The reason this worked before was that MySQL marked all to be written
  columns as also to be read. The new 'optimal' bitmaps exposed this 'hidden
  bug'.

- open_table_from_share() does not anymore setup temporary MEM_ROOT
  object as a thread specific variable for the handler. Instead we
  send the to-be-used MEMROOT to get_new_handler().
  (Simpler, faster code)



Bugs fixed:

- Column marking was not done correctly in a lot of cases.
  (ALTER TABLE, when using triggers, auto_increment fields etc)
  (Could potentially result in wrong values inserted in table handlers
  relying on that the old column maps or field->set_query_id was correct)
  Especially when it comes to triggers, there may be cases where the
  old code would cause lost/wrong values for NDB and/or InnoDB tables.

- Split thd->options flag OPTION_STATUS_NO_TRANS_UPDATE to two flags:
  OPTION_STATUS_NO_TRANS_UPDATE and OPTION_KEEP_LOG.
  This allowed me to remove some wrong warnings about:
  "Some non-transactional changed tables couldn't be rolled back"

- Fixed handling of INSERT .. SELECT and CREATE ... SELECT that wrongly reset
  (thd->options & OPTION_STATUS_NO_TRANS_UPDATE) which caused us to loose
  some warnings about
  "Some non-transactional changed tables couldn't be rolled back")

- Fixed use of uninitialized memory in ha_ndbcluster.cc::delete_table()
  which could cause delete_table to report random failures.

- Fixed core dumps for some tests when running with --debug

- Added missing FN_LIBCHAR in mysql_rm_tmp_tables()
  (This has probably caused us to not properly remove temporary files after
  crash)

- slow_logs was not properly initialized, which could maybe cause
  extra/lost entries in slow log.

- If we get an duplicate row on insert, change column map to read and
  write all columns while retrying the operation. This is required by
  the definition of REPLACE and also ensures that fields that are only
  part of UPDATE are properly handled.  This fixed a bug in NDB and
  REPLACE where REPLACE wrongly copied some column values from the replaced
  row.

- For table handler that doesn't support NULL in keys, we would give an error
  when creating a primary key with NULL fields, even after the fields has been
  automaticly converted to NOT NULL.

- Creating a primary key on a SPATIAL key, would fail if field was not
  declared as NOT NULL.


Cleanups:

- Removed not used condition argument to setup_tables

- Removed not needed item function reset_query_id_processor().

- Field->add_index is removed. Now this is instead maintained in
  (field->flags & FIELD_IN_ADD_INDEX)

- Field->fieldnr is removed (use field->field_index instead)

- New argument to filesort() to indicate that it should return a set of
  row pointers (not used columns). This allowed me to remove some references
  to sql_command in filesort and should also enable us to return column
  results in some cases where we couldn't before.

- Changed column bitmap handling in opt_range.cc to be aligned with TABLE
  bitmap, which allowed me to use bitmap functions instead of looping over
  all fields to create some needed bitmaps. (Faster and smaller code)

- Broke up found too long lines

- Moved some variable declaration at start of function for better code
  readability.

- Removed some not used arguments from functions.
  (setup_fields(), mysql_prepare_insert_check_table())

- setup_fields() now takes an enum instead of an int for marking columns
   usage.

- For internal temporary tables, use handler::write_row(),
  handler::delete_row() and handler::update_row() instead of
  handler::ha_xxxx() for faster execution.

- Changed some constants to enum's and define's.

- Using separate column read and write sets allows for easier checking
  of timestamp field was set by statement.

- Remove calls to free_io_cache() as this is now done automaticly in ha_reset()

- Don't build table->normalized_path as this is now identical to table->path
  (after bar's fixes to convert filenames)

- Fixed some missed DBUG_PRINT(.."%lx") to use "0x%lx" to make it easier to
  do comparision with the 'convert-dbug-for-diff' tool.


Things left to do in 5.1:

- We wrongly log failed CREATE TABLE ... SELECT in some cases when using
  row based logging (as shown by testcase binlog_row_mix_innodb_myisam.result)
  Mats has promised to look into this.

- Test that my fix for CREATE TABLE ... SELECT is indeed correct.
  (I added several test cases for this, but in this case it's better that
  someone else also tests this throughly).
  Lars has promosed to do this.


BitKeeper/etc/ignore:
  added mysys/test_bitmap
include/base64.h:
  Removed my_global.h, as this must be included first in any program
include/heap.h:
  Added heap_reset() (Required by new handler interface)
include/my_base.h:
  Removed HA_EXTRA_RESET. MySQL will now call ::reset() instead of ::extra(HA_EXTRA_RESET).
  HA_EXTRA_RETRIVE_ALL_COLS and HA_EXTRA_RETRIVE_PRIMARY key are deleted as the column bitmaps makes these unnecessary
include/my_bitmap.h:
  Remove my_pthread.h (should be included at upper level)
  Introduced my_bitmap_map typedef to make it the bitmap handling more like a black box
  Added bitmap_is_overlapping(), bitmap_test_and_clear(), bitmap_copy() and bitmap_cmp()
  Made bitmap_set_bit(), bitmap_flip_bit(), bitmap_clear_bit() return void
include/myisam.h:
  Added mi_reset() (Required by new handler interface)
include/myisammrg.h:
  Added myrg_reset() (Required by new handler interface)
include/mysql_com.h:
  Added flag FIELD_IN_ADD_INDEX to be able to remove Field->add_index
mysql-test/extra/binlog_tests/mix_innodb_myisam_binlog.test:
  Added testing of CREATE ... SELECT in a mixed environment
  (This found some bugs that Mats is going to fix shortly)
mysql-test/install_test_db.sh:
  Simplify ldata usage
  Added --tmpdir=. option to mysqld bootstrap (Removed some warnings when TMPDIR was wrongly set)
mysql-test/mysql-test-run.pl:
  Added --tmpdir=. to bootstrap
mysql-test/mysql-test-run.sh:
  Use copy instead of INSTALL_DB for master and slave databases.
  (Speeds up startup time a lot!)
  Remove snapshot directories at startup (removes some strange warnings)
mysql-test/r/binlog_row_mix_innodb_myisam.result:
  Added testing of CREATE ... SELECT in a mixed environment
  (This found some bugs that Mats is going to fix shortly)
mysql-test/r/binlog_stm_mix_innodb_myisam.result:
  Added testing of CREATE ... SELECT in a mixed environment
mysql-test/r/create.result:
  Some extra tests of warnings and number of tables opened by CREATE ... SELECT
mysql-test/r/federated.result:
  Drop some left over tables
  Added testing of multiple table update and multiple table delete (with and without keys)
mysql-test/r/func_gconcat.result:
  Enable some disabled tests (converted them slightly to be predictable)
mysql-test/r/func_time.result:
  Added drop of test function
mysql-test/r/innodb_mysql.result:
  Added tests for CREATE ... SELECT
mysql-test/r/insert.result:
  More tests
  Added testing of duplicate columns in insert
mysql-test/r/loaddata.result:
  Added testing LOAD DATA ... SET ...
mysql-test/r/multi_update.result:
  Test multi updates and deletes using primary key and without
mysql-test/r/ndb_index_unique.result:
  Better error message
mysql-test/r/ndb_replace.result:
  New correct result after fixing REPLACE handling with NDB
mysql-test/r/rpl_ddl.result:
  Now we don't get these (wrong) warnings anymore
mysql-test/r/view_grant.result:
  Drop used views
mysql-test/t/create.test:
  Some extra tests of warnings and number of tables opened by CREATE ... SELECT
mysql-test/t/federated.test:
  Drop some left over tables
  Added testing of multiple table update and multiple table delete (with and without keys)
mysql-test/t/func_gconcat.test:
  Enable some disabled tests (converted them slightly to be predictable)
mysql-test/t/func_time.test:
  Added drop of test function
mysql-test/t/innodb_mysql.test:
  Added tests for CREATE ... SELECT
mysql-test/t/insert.test:
  More tests
  Added testing of duplicate columns in insert
mysql-test/t/loaddata.test:
  Added testing LOAD DATA ... SET ...
mysql-test/t/multi_update.test:
  Test multi updates and deletes using primary key and without
mysql-test/t/view_grant.test:
  Drop used views
mysql-test/valgrind.supp:
  Added supression of not needed warnings when printing stack trace
mysys/base64.c:
  Include my_global.h first
mysys/my_bitmap.c:
  Added bitmap_is_overlapping(), bitmap_test_and_clear() and bitmap_copy()
  Changed logic of bitmap handling to be a bit more efficent (Did this together with Mikael Ronström)
  Now the 'extra, not used bits' in the bitmap are assumed to have a 'random value' and the bitmap functions are free to change them whenever needed.
  Changed how mutex is allocated to make 'bitmap_free()' function simpler.
mysys/thr_lock.c:
  Added 0x before thread pointers (for easier comparison of DBUG traces)
sql/event.cc:
  Ensure 'use_all_columns()' is used for event tables
  Don't print warning that event table is damaged if it doesn't exists.
sql/field.cc:
  Added ASSERT_COLUMN_MARKED_FOR_WRITE in all store() methods and ASSERT_COLUMN_MARKED_FOR_READ in all val() methods to catch wrong setting if table->read_set and table->write_set
  (Rest of changes are only indentation cleanups)
sql/field.h:
  Removed Field->query_id (replaced by table->read_set and table->write_set)
  Removed Field->fieldnr (use Field->field_index instead)
  Removed Field->add_index (Use Field->flags instead)
  Add Field->part_of_key_not_clustered (for usage in opt_range.cc)
sql/filesort.cc:
  Added paramater sort_postion to filesort() to force sorting by position instead of storing all fields in the result set.
  This allowed me to remove checking of sql_command.
  Create a temporary column bitmap for fields that are used by the sorting process.
  Use column bitmaps instead of query_id
sql/ha_berkeley.cc:
  Update to 'newer' table handler interface
sql/ha_berkeley.h:
  Update to 'newer' table handler interface
sql/ha_federated.cc:
  Update to 'newer' table handler interface
  Only read columns that are needed from remote server.
  In case of eq ranges, don't generate two conditions in the WHERE clause
  (this can still be optimized, but would require a bigger code change)
  Use 'simpler to use' XXXX_LEN' macros
  A bit simpler logic in ::write_row() when creating statements.
  In update, only include test of fields actually read.
  (This greatly simplifies the queries sent by the federated engine)
  Similar changes done for delete_row()
sql/ha_federated.h:
  Update to 'newer' table handler interface
  Changed XXX_LEN macros to use sizeof(...)-1, to simplify usage in ha_federated.cc
  Added HA_PRIMARY_KEY_REQUIRED_FOR_DELETE to tell MySQL to read all primary key columns in case of DELETE
sql/ha_heap.cc:
  Update to 'newer' table handler interface
sql/ha_heap.h:
  Update to 'newer' table handler interface
sql/ha_innodb.cc:
  Update to 'newer' table handler interface
  - Update innobase_create_handler() to new interface
  - Removed HA_NOT_EXACT_COUNT (not needed)
  - Renamed HA_PRIMARY_KEY_ALLOW_RANDOM_ACCESS to HA_PRIMARY_KEY_REQUIRED_FOR_POSITION.
  - Prefixed base status variables with 'stats'
  - Use table column bitmaps instead of ha_get_bit_in_read_set()
  - Added ::reset(), with code from ::extra(HA_EXTRA_RESET)
  - Removed HA_EXTRA_RETRIVE_ALL_COLS and HA_EXTRA_RETRIEVE_PRIMARY_KEY as
    the table->read_set and table->write_set bitmaps now are accurate
sql/ha_innodb.h:
  Update to 'newer' table handler interface
  - table_flags are now ulonglong
  - Added reset() method
  - Removed not needed ha_retrieve_all_cols() and ha_retrieve_all_pk() columns.
  - Made build_template() a class function to be able to easier access class variables
sql/ha_myisam.cc:
  Update to 'newer' table handler interface
sql/ha_myisam.h:
  Update to 'newer' table handler interface
sql/ha_myisammrg.cc:
  Update to 'newer' table handler interface
sql/ha_myisammrg.h:
  Update to 'newer' table handler interface
sql/ha_ndbcluster.cc:
  Update to 'newer' table handler interface
  Fixed use_blob_value() to be accurate
  In ::complemented_read() we have to check both the read and write bitmap as the old code did mark all changed columns also in the read map
  Correct dumping of field data with DBUG_DUMP
  Prefix addresses in DBUG_PRINT with 0x
  Fixed usage of not initialized memory
  Update to use field->flags & FIELD_IN_ADD_INDEX instead of field->add_index.
sql/ha_ndbcluster.h:
  Update to 'newer' table handler interface
sql/ha_ndbcluster_binlog.cc:
  Mark usage of all columns in ndbcluster binlog tables
  false -> FALSE, true -> TRUE
  Use table->s->all_set instead of creating a temporary bitmap.
sql/ha_partition.cc:
  Update to 'newer' table handler interface
  Added memroot to initialise_partitions() and related functions to get faster memory allocation.
  partition_create_handler() is now responsible for initialisation of the partition object
  Some trivial optimizations and indentation fixes
  Ensure that table_flags() are up to date
  Removed documentation for removed HA_EXTRA flags
  Fixed 'strange' usage of m_file[i] in new_handlers_from_part_info()that worked in current code 'by chance'
sql/ha_partition.h:
  Update to 'newer' table handler interface
sql/handler.cc:
  create_xxx handler now takes MEMROOT as an argument to simplify memory allocation.
  Much simpler get_new_handler()
  (Initialization of the object is now handled by the create method for the engine)
  Moved all allocation of bitmap handling to the TABLE object (in table.cc)
  Added column_bitmaps_signal() to signal column usage changes.
  Changed binlog_log_row() to use the exiusting all_set bitmap in the table object.
  Added ha_reset() function to test that the file object is ok at end of statement and call handler::reset()
  Added use_hidden_primary_key() to signal handler that we we are going to read and update + delete the row and the handler should thus remember the position for the row
sql/handler.h:
  Added HA_NO_TRANSACTIONS, HA_PARTIAL_COLUMN_READ, HA_REQUIRES_KEY_COLUMNS_FOR_DELETE,HA_PRIMARY_KEY_REQUIRED_FOR_DELETE and HA_HAS_RECORDS
  Removed HA_NOT_EXACT_COUNT, HA_READ_RND_SAME
  HA_DUPP_POS -> HA_DUPLICATE_POS
  HA_NOT_EXACT_COUNT replaced by HA_STATS_RECORDS_IS_EXACT, HA_HAS_RECORDS and records()
  HA_PRIMARY_KEY_ALLOW_RANDOM_ACCESS renamed to HA_PRIMARY_KEY_REQUIRED_FOR_POSITION
  Added future row type 'ROW_TYPE_PAGES'
  Added MEM_ROOT to handlerton 'create' function
  Added ha_statistics, a structure for all status variable in the base handler class.
  Moved all status variables in the handler class into a stats structs to improve readability.
  ha_table_flags() is now a cached (not virtual) version of table_flags()
  reset() doesn't anymore call extra(HA_EXTRA_RESET) but is a function of it's own.
  Renamed dupp_ref to dup_ref
  Renamed not used handler::sortkey
  Moved read_set and write_set to TABLE structure
  handler::init() function added for cacheing of virtual constants from engine.
sql/item.cc:
  Added register_field_in_read_map() for marking used columns in expression.
  This is used by filesort() for creating an optimal column bitmap while retrieving columns for sorting.
  Initalize value.cs_info.character_set_client to fix core dump bug with --debug
  set_query_id -> mark_used_columns
  Mark used columns in read_set OR write_set.
sql/item.h:
  Removed reset_query_id_processor() as it's not needed anymore.
  Added register_field_in_read_map()
  Added extra argument to Item::walk() to indicate if we should also
  traverse sub queries.
sql/item_cmpfunc.cc:
  Temporary mark used columns to be read/writable
  Update Item::walk to new interface
sql/item_cmpfunc.h:
  Added extra argument to Item::walk() to indicate if we should also traverse sub queries.
sql/item_func.cc:
  Update Item::walk() to new interface
  table_flags() -> ha_table_flags()
sql/item_func.h:
  Update Item::walk() to new interface
sql/item_row.cc:
  Update Item::walk() to new interface
sql/item_row.h:
  Update Item::walk() to new interface
sql/item_strfunc.h:
  Update Item::walk() to new interface
sql/item_subselect.cc:
  Added Item_subselect::walk()
  (It was a bug it was missing before. Not sure what kind of bugs this could have caused)
sql/item_subselect.h:
  Update Item::walk() to new interface
sql/item_sum.cc:
  Update Item::walk() to new interface
  Updates for new handler interace
sql/item_sum.h:
  Update Item::walk() to new interface
sql/key.cc:
  Updates for new handler interace
sql/log.cc:
  Mark all columns used for log tables
  Split options flag
  Ensured that second argument to trans_register_ha is a bool
sql/log_event.cc:
  Fixed comments to be withing 79 characters
  Use OPTION_KEEP_LOG instead of OPTION_STATUS_NO_TRANS_UPDATE to remove wrong warnings
  Updates for new handler interface
  Use 0x%lx instead of %p (portability problem)
sql/mysql_priv.h:
  Added OPTION_KEEP_LOG to indicate that we should replicate the binlog even on rollback
  Removed not used 'conds' argument to setup_tables
sql/mysqld.cc:
  Indentation fixes and removed old comment
sql/opt_range.cc:
  Update to new handler and bitmap interface.
  Fixed calls to cp_buffer_from_ref() and walk() (new argument).
  Create new temporary bitmaps for ror scans.
  (Needed because of handler changes and to get more accurate column bitmaps than before)
  Remove not needed file->ha_reset() call before file->close().
  Some trivial optimization and indentation fixes.
  Use Field->part_of_key_not_clustered() to check if field is part of a key, instead of looping over all key parts.
  
  Added flag 'in_ror_merged_scan' to allow ::get_next() to know that we need a special column bitmap to only fetch pointer to record.
  This is needed because ror scan uses the same TABLE object but different file objects, which creates problem for the column bitmap handling.
  (This is a temporary solution. A better one would be to allocate an own TABLE object for ROR scans)
  
  Optimized bitmap handling in ror scans:
  - Start bitmap at position 0, not 1
  - Use same bitmap size as in TABLE
  - Use table->read_set and table->write_set to create column bitmaps instead of looping over all fields in table
sql/opt_range.h:
  Added 'in_ror_merged_scan' to indicate if we are doing a ROR scan
  Added temporary column bitmaps used in ROR scans
sql/opt_sum.cc:
  Added get_ext_record_count() which is used in COUNT() optimization if handler has HA_HAS_RECORDS
  Note that we don't call this if handler has HA_STATS_RECORDS_IS_EXACT set.
sql/protocol.cc:
  We need to mark columns as readable in ::store() as we sometimes return default value for fields to the user
sql/records.cc:
  Updates for new handler interface
sql/set_var.cc:
  Handle splitting OPTION_STATUS_NO_TRANS_UPDATE to two flags
sql/share/errmsg.txt:
  Fixed wrong
sql/sp.cc:
  Mark that we are using all columns for the proc table
  Update call to setup_tables() to use new prototype
sql/sp_head.cc:
  Removed QQ comment
sql/spatial.cc:
  Removed wrong QQ comment
sql/sql_acl.cc:
  Mark that we need all columns for acl tables
  Supply memroot to some 'new' calls.
  Indentation fixes
sql/sql_base.cc:
  set_query_id removed
  Ensure we call ha_reset() at end of each statement
  Mark read columns in read_set and changed columns in write_set (Before all columns was marked in read set)
  Fixed marking of some columns that was not proplerly marked before
  Maintain in TABLE->merge_keys set of all keys that are used in some way
  Removed not used 'conds' argument from setup_tables()
  Remove not used setting of 'dupp_field' in insert_fields()
  Added missing FN_LIBCHAR in mysql_rm_tmp_tables()
  (This has probably caused us to not properly remove temporary files after crash)
sql/sql_bitmap.h:
  Added is_overlapping()
sql/sql_class.cc:
  Slow_logs was not properly initialized, which could maybe cause extra/lost entries in slow log.
  set_query_id -> mark_used_columns
  Simpler variable usage in pack_row()  (cleanup)
  Moved some variable declartion at start of function for better code readability
sql/sql_class.h:
  Added enum_mark_columns
  Updated comments
  Renamed dupp_field -> dup_field
  Added virtual function 'can_rollback_data()' to select_insert() to be used in CREATE ... SELECT to optimize use of OPTION_STATUS_NO_TRANS_UPDATE.
  (This fixes a bug in CREATE ... SELECT where we did give wrong warnings when using non transacational tables)
sql/sql_delete.cc:
  Updates to new handler interface
  Call table->mark_columns_needed_for_delete() to allow us to put additional columns in column usage maps if handler so requires.
  Call table->prepare_for_position() to tell handler that we are going to call ha_position().
  Removed call to free_io_cache(). (io_cache is now removed in ha_reset()).
  Fixed calls to setup_tables()
sql/sql_do.cc:
  Update call to setup_fields()
sql/sql_handler.cc:
  Tell handler tables to always read all columns.
  Use temporary column map when storing value in field for later index usage
sql/sql_help.cc:
  Makr all used fields to be read
  Update call to setup_fields()
sql/sql_insert.cc:
  Tell handler we are going to update the auto_increment column
  dupp_field -> dup_field
  Set column usage bits for timestamp field.
  Call table->mark_columns_needed_for_insert() and table->mark_auto_increment_column()
  Removed not used argument from mysql_prepare_insert_check_table().
  
  If we get an duplicate row on insert, change column map to read and write all columns while retrying the operatation.
  This is required by the definition of REPLACE and also ensures that fields that are only part of UPDATE are properly handled.
  This fixed a bug in NDB and REPLACE where REPLACE wrongly copied some column values from the replaced row.
  
  Setup new bitmaps for delayed insert rows
  Remove reseting of next_number_fields as it will be reset on next call to handler_insert()
  
  Fixed usage of thd->options and OPTION_STATUS_NO_TRANS_UPDATE.
  The issue was that one should not to reset this flag as it may be set by a previous statement.
  The way it was now used caused us to loose some warnings and get other wrong warnings when using non transactional tables mixed with transactional.
  I fixed it by introducing 'select_insert::can_rollback_data' to inform send_error() that the given statement can be rolled back (which in case of CREATE TABLE can always be done)
  Don't close tables created with CREATE ... SELECT but keep them in the table cache.
  
  Moved out MY_HOOKS from inside function (better readability)
sql/sql_load.cc:
  Update to use new handler and column marking interface
  Update using setup_tables()
sql/sql_olap.cc:
  Update calls to setup_tables
  Use enums instead of constants to setup_fields()
sql/sql_parse.cc:
  Handle OPTION_KEEP_LOG:
  - Set it on CREATE TEMPORARY TABLE / DROP TABLE
  - Reset it when OPTION_STATUS_NO_TRANS_UPDATE is reset
  - Don't set it for CREATE ... SELECT (this is handled in select_create class)
  Remove reseting of OPTION_STATUS_NO_TRANS_UPDATE in begin_trans() as this should already be reset.
  If in autocommit mode, reset OPTION_KEEP_LOG and OPTION_STATUS_NO_TRANS_UPDATE to not give warnings in future commands
sql/sql_partition.cc:
  Update walk() usage
  Trivial indentation fixes
sql/sql_plugin.cc:
  Mark all columns as used for plugins
sql/sql_prepare.cc:
  Added assert to find out hidden bugs in character_set_client (got an error in debug binary when this not set correctly)
  Updates for new handler interface
  Update calls to setup_fields()
sql/sql_repl.cc:
  Indentation fixes
sql/sql_select.cc:
  Update call to setup_tables() and setup_fields()
  Remove some old disabled code
  Update to new hadler interface
  Indentation cleanups
  Added column bitmaps for temporary tables.
  Remove updating of the removed slots in the Field class
  Added TABLE argument to cp_buffer_from_ref() (To be able to install temporary column maps)
  For internal temporary tables, use handler::write_row(), handler::delete_row() and handler::update_row() instead of handler::ha_xxxx() for faster execution.
sql/sql_select.h:
  Indentaition fixes.
  Install temporary column usage maps when needed
  Added TABLE element to cp_buffer_from_ref()
sql/sql_show.cc:
  Update to new handler interface
  Mark all columns used for internal tables.
  Style fixes.
  Added support for 'future' ROW_TYPE_PAGES.
  Don't allocate TMP_TABLE_PARAM with calloc. The 'init()' function will initialize the structure properly.
sql/sql_table.cc:
  Update to new handler interface
  Simple my_snprintf -> strmake()
  Changed some constants to defines
  Don't test for NULL in primary key (as we a couple of line above force the PRIMARY KEY to be NOT NULL)
  Change field->add_index to use field->flags & FIELD_IN_ADD_INDEX
  Mark all columns as used for ALTER TABLE
  Style fixes
  Update call to filesort()
sql/sql_trigger.h:
  Added friend functions to be able to test if triggers exists for table we are going to insert/update or delete in.
sql/sql_udf.cc:
  Mark all columns as used for udf system table.
sql/sql_union.cc:
  Update call to walk()
  Update to new handler interface
sql/sql_update.cc:
  Remove query_id argument from compare_record()
  Use column bitmaps instead of query_id.
  We can't use compare_records() to skip updates for handlers that returns a partial column set and the read_set doesn't cover all columns in the write set, because compare_record() can't in this case know if a not read column changed value.
  Update call to setup_fields()
  Using separate column read and write sets allows for easier checking of timestamp field was set by statement.
  Removed call to free_io_cache() as this is now done in ha_reset()
  Call table->mark_columns_needed_for_update() and table->prepare_for_position()
  Style fixes
sql/sql_view.cc:
  Style fixes
sql/table.cc:
  Remove implicitely include 'errno.h'
  Remove code for building normalized path, as this is now identical to 'path'
  Remove field->fieldnr
  Added update of field->part_of_key_not_clustered()
  Create column bitmaps in TABLE and TABLE_SHARE
  Don't setup a temporary MEM_ROOT object as a thread specific variable for the handler. Instead we send the to-be-used MEMROOT to get_new_handler()
  Update to new handler interface
  Update call to walk()
  Added new functions:
  - st_table::clear_column_bitmaps()
  - st_table::prepare_for_position()
  - st_table::mark_columns_used_by_index()
  - st_table::restore_column_maps_after_mark_index()
  - st_table::mark_columns_used_by_index_no_reset()
  - st_table::mark_auto_increment_column()
  - st_table::mark_columns_needed_for_delete()
  - st_table::mark_columns_needed_for_update()
  - st_table::mark_columns_needed_for_insert()
sql/table.h:
  Moved column usage bitmaps from handler to TABLE
  Added to TABLE_SHARE all_set and column_bitmap_size
  Added to TABLE merge_keys, bitmap_init_values, def_read_set, def_write_set, tmp_set, read_set and write_set.
  Declared all new table column bitmap functions
  Added TABLE functions column_bitmaps_set(), column_bitmaps_set_no_signal(), use_all_columns() and default_column_bitmaps()
  Added functions: tmp_use_all_columns() and tmp_restore_column_map() to temporarly switch column bitmaps
  Added functions: dbug_tmp_use_all_columns() and dbug_tmp_restore_column_map() to temporarly switch column bitmaps to avoid asserts in Field::store() and Field::val().
sql/tztime.cc:
  Mark all columns as used for timezone tables
storage/archive/ha_archive.cc:
  Update to new handler interface
storage/archive/ha_archive.h:
  Update to new handler interface
storage/blackhole/ha_blackhole.cc:
  Update to new handler interface
storage/blackhole/ha_blackhole.h:
  Update to new handler interface
  removed not needed flag HA_DUPP_POS
storage/csv/ha_tina.cc:
  Update to new handler interface
storage/csv/ha_tina.h:
  Update to new handler interface
storage/example/ha_example.cc:
  Update to new handler interface
storage/example/ha_example.h:
  Update to new handler interface
storage/heap/hp_extra.c:
  Added heap_reset() (Required by new handler interface)
storage/heap/hp_test2.c:
  Use heap_reset()
storage/myisam/ft_boolean_search.c:
  Fixed compiler warning
storage/myisam/mi_extra.c:
  Added mi_reset() (Required by new handler interface)
storage/myisam/mi_search.c:
  Fixed DBUG_PRINT messages to use 0x%lx instead of %lx
storage/myisam/mi_test2.c:
  Use mi_reset()
storage/myisam/myisampack.c:
  Use mi_reset()
storage/myisammrg/myrg_extra.c:
  Added myrg_reset() (Required by new handler interface)
unittest/mysys/base64.t.c:
  Include my_global.h
  Don't include implictely include file 'stdlib.h'
2006-06-04 18:52:22 +03:00

1161 lines
39 KiB
C++

/* Copyright (C) 2000 MySQL AB & MySQL Finland AB & TCX DataKonsult AB
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; either version 2 of the License, or
(at your option) any later version.
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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */
/* classes for sum functions */
#ifdef USE_PRAGMA_INTERFACE
#pragma interface /* gcc class implementation */
#endif
#include <my_tree.h>
/*
Class Item_sum is the base class used for special expressions that SQL calls
'set functions'. These expressions are formed with the help of aggregate
functions such as SUM, MAX, GROUP_CONCAT etc.
GENERAL NOTES
A set function cannot be used in certain positions where expressions are
accepted. There are some quite explicable restrictions for the usage of
set functions.
In the query:
SELECT AVG(b) FROM t1 WHERE SUM(b) > 20 GROUP by a
the usage of the set function AVG(b) is legal, while the usage of SUM(b)
is illegal. A WHERE condition must contain expressions that can be
evaluated for each row of the table. Yet the expression SUM(b) can be
evaluated only for each group of rows with the same value of column a.
In the query:
SELECT AVG(b) FROM t1 WHERE c > 30 GROUP BY a HAVING SUM(b) > 20
both set function expressions AVG(b) and SUM(b) are legal.
We can say that in a query without nested selects an occurrence of a
set function in an expression of the SELECT list or/and in the HAVING
clause is legal, while in the WHERE clause it's illegal.
The general rule to detect whether a set function is legal in a query with
nested subqueries is much more complicated.
Consider the the following query:
SELECT t1.a FROM t1 GROUP BY t1.a
HAVING t1.a > ALL (SELECT t2.c FROM t2 WHERE SUM(t1.b) < t2.c).
The set function SUM(b) is used here in the WHERE clause of the subquery.
Nevertheless it is legal since it is under the HAVING clause of the query
to which this function relates. The expression SUM(t1.b) is evaluated
for each group defined in the main query, not for groups of the subquery.
The problem of finding the query where to aggregate a particular
set function is not so simple as it seems to be.
In the query:
SELECT t1.a FROM t1 GROUP BY t1.a
HAVING t1.a > ALL(SELECT t2.c FROM t2 GROUP BY t2.c
HAVING SUM(t1.a) < t2.c)
the set function can be evaluated for both outer and inner selects.
If we evaluate SUM(t1.a) for the outer query then we get the value of t1.a
multiplied by the cardinality of a group in table t1. In this case
in each correlated subquery SUM(t1.a) is used as a constant. But we also
can evaluate SUM(t1.a) for the inner query. In this case t1.a will be a
constant for each correlated subquery and summation is performed
for each group of table t2.
(Here it makes sense to remind that the query
SELECT c FROM t GROUP BY a HAVING SUM(1) < a
is quite legal in our SQL).
So depending on what query we assign the set function to we
can get different result sets.
The general rule to detect the query where a set function is to be
evaluated can be formulated as follows.
Consider a set function S(E) where E is an expression with occurrences
of column references C1, ..., CN. Resolve these column references against
subqueries that contain the set function S(E). Let Q be the innermost
subquery of those subqueries. (It should be noted here that S(E)
in no way can be evaluated in the subquery embedding the subquery Q,
otherwise S(E) would refer to at least one unbound column reference)
If S(E) is used in a construct of Q where set functions are allowed then
we evaluate S(E) in Q.
Otherwise we look for a innermost subquery containing S(E) of those where
usage of S(E) is allowed.
Let's demonstrate how this rule is applied to the following queries.
1. SELECT t1.a FROM t1 GROUP BY t1.a
HAVING t1.a > ALL(SELECT t2.b FROM t2 GROUP BY t2.b
HAVING t2.b > ALL(SELECT t3.c FROM t3 GROUP BY t3.c
HAVING SUM(t1.a+t2.b) < t3.c))
For this query the set function SUM(t1.a+t2.b) depends on t1.a and t2.b
with t1.a defined in the outermost query, and t2.b defined for its
subquery. The set function is in the HAVING clause of the subquery and can
be evaluated in this subquery.
2. SELECT t1.a FROM t1 GROUP BY t1.a
HAVING t1.a > ALL(SELECT t2.b FROM t2
WHERE t2.b > ALL (SELECT t3.c FROM t3 GROUP BY t3.c
HAVING SUM(t1.a+t2.b) < t3.c))
Here the set function SUM(t1.a+t2.b)is in the WHERE clause of the second
subquery - the most upper subquery where t1.a and t2.b are defined.
If we evaluate the function in this subquery we violate the context rules.
So we evaluate the function in the third subquery (over table t3) where it
is used under the HAVING clause.
3. SELECT t1.a FROM t1 GROUP BY t1.a
HAVING t1.a > ALL(SELECT t2.b FROM t2
WHERE t2.b > ALL (SELECT t3.c FROM t3
WHERE SUM(t1.a+t2.b) < t3.c))
In this query evaluation of SUM(t1.a+t2.b) is not legal neither in the second
nor in the third subqueries. So this query is invalid.
Mostly set functions cannot be nested. In the query
SELECT t1.a from t1 GROUP BY t1.a HAVING AVG(SUM(t1.b)) > 20
the expression SUM(b) is not acceptable, though it is under a HAVING clause.
Yet it is acceptable in the query:
SELECT t.1 FROM t1 GROUP BY t1.a HAVING SUM(t1.b) > 20.
An argument of a set function does not have to be a reference to a table
column as we saw it in examples above. This can be a more complex expression
SELECT t1.a FROM t1 GROUP BY t1.a HAVING SUM(t1.b+1) > 20.
The expression SUM(t1.b+1) has a very clear semantics in this context:
we sum up the values of t1.b+1 where t1.b varies for all values within a
group of rows that contain the same t1.a value.
A set function for an outer query yields a constant within a subquery. So
the semantics of the query
SELECT t1.a FROM t1 GROUP BY t1.a
HAVING t1.a IN (SELECT t2.c FROM t2 GROUP BY t2.c
HAVING AVG(t2.c+SUM(t1.b)) > 20)
is still clear. For a group of the rows with the same t1.a values we
calculate the value of SUM(t1.b). This value 's' is substituted in the
the subquery:
SELECT t2.c FROM t2 GROUP BY t2.c HAVING AVG(t2.c+s)
than returns some result set.
By the same reason the following query with a subquery
SELECT t1.a FROM t1 GROUP BY t1.a
HAVING t1.a IN (SELECT t2.c FROM t2 GROUP BY t2.c
HAVING AVG(SUM(t1.b)) > 20)
is also acceptable.
IMPLEMENTATION NOTES
Three methods were added to the class to check the constraints specified
in the previous section. These methods utilize several new members.
The field 'nest_level' contains the number of the level for the subquery
containing the set function. The main SELECT is of level 0, its subqueries
are of levels 1, the subqueries of the latter are of level 2 and so on.
The field 'aggr_level' is to contain the nest level of the subquery
where the set function is aggregated.
The field 'max_arg_level' is for the maximun of the nest levels of the
unbound column references occurred in the set function. A column reference
is unbound within a set function if it is not bound by any subquery
used as a subexpression in this function. A column reference is bound by
a subquery if it is a reference to the column by which the aggregation
of some set function that is used in the subquery is calculated.
For the set function used in the query
SELECT t1.a FROM t1 GROUP BY t1.a
HAVING t1.a > ALL(SELECT t2.b FROM t2 GROUP BY t2.b
HAVING t2.b > ALL(SELECT t3.c FROM t3 GROUP BY t3.c
HAVING SUM(t1.a+t2.b) < t3.c))
the value of max_arg_level is equal to 1 since t1.a is bound in the main
query, and t2.b is bound by the first subquery whose nest level is 1.
Obviously a set function cannot be aggregated in the subquery whose
nest level is less than max_arg_level. (Yet it can be aggregated in the
subqueries whose nest level is greater than max_arg_level.)
In the query
SELECT t.a FROM t1 HAVING AVG(t1.a+(SELECT MIN(t2.c) FROM t2))
the value of the max_arg_level for the AVG set function is 0 since
the reference t2.c is bound in the subquery.
The field 'max_sum_func_level' is to contain the maximum of the
nest levels of the set functions that are used as subexpressions of
the arguments of the given set function, but not aggregated in any
subquery within this set function. A nested set function s1 can be
used within set function s0 only if s1.max_sum_func_level <
s0.max_sum_func_level. Set function s1 is considered as nested
for set function s0 if s1 is not calculated in any subquery
within s0.
A set function that is used as a subexpression in an argument of another
set function refers to the latter via the field 'in_sum_func'.
The condition imposed on the usage of set functions are checked when
we traverse query subexpressions with the help of the recursive method
fix_fields. When we apply this method to an object of the class
Item_sum, first, on the descent, we call the method init_sum_func_check
that initialize members used at checking. Then, on the ascent, we
call the method check_sum_func that validates the set function usage
and reports an error if it is illegal.
The method register_sum_func serves to link the items for the set functions
that are aggregated in the embedding (sub)queries. Circular chains of such
functions are attached to the corresponding st_select_lex structures
through the field inner_sum_func_list.
Exploiting the fact that the members mentioned above are used in one
recursive function we could have allocated them on the thread stack.
Yet we don't do it now.
We assume that the nesting level of subquries does not exceed 127.
TODO: to catch queries where the limit is exceeded to make the
code clean here.
*/
class Item_sum :public Item_result_field
{
public:
enum Sumfunctype
{ COUNT_FUNC, COUNT_DISTINCT_FUNC, SUM_FUNC, SUM_DISTINCT_FUNC, AVG_FUNC,
AVG_DISTINCT_FUNC, MIN_FUNC, MAX_FUNC, UNIQUE_USERS_FUNC, STD_FUNC,
VARIANCE_FUNC, SUM_BIT_FUNC, UDF_SUM_FUNC, GROUP_CONCAT_FUNC
};
Item **args, *tmp_args[2];
Item **ref_by; /* pointer to a ref to the object used to register it */
Item_sum *next; /* next in the circular chain of registered objects */
uint arg_count;
Item_sum *in_sum_func; /* embedding set function if any */
int8 nest_level; /* number of the nesting level of the set function */
int8 aggr_level; /* nesting level of the aggregating subquery */
int8 max_arg_level; /* max level of unbound column references */
int8 max_sum_func_level;/* max level of aggregation for embedded functions */
bool quick_group; /* If incremental update of fields */
void mark_as_sum_func();
Item_sum() :arg_count(0), quick_group(1)
{
mark_as_sum_func();
}
Item_sum(Item *a)
:args(tmp_args), arg_count(1), quick_group(1)
{
args[0]=a;
mark_as_sum_func();
}
Item_sum( Item *a, Item *b )
:args(tmp_args), arg_count(2), quick_group(1)
{
args[0]=a; args[1]=b;
mark_as_sum_func();
}
Item_sum(List<Item> &list);
//Copy constructor, need to perform subselects with temporary tables
Item_sum(THD *thd, Item_sum *item);
enum Type type() const { return SUM_FUNC_ITEM; }
virtual enum Sumfunctype sum_func () const=0;
inline bool reset() { clear(); return add(); };
virtual void clear()= 0;
virtual bool add()=0;
/*
Called when new group is started and results are being saved in
a temporary table. Similar to reset(), but must also store value in
result_field. Like reset() it is supposed to reset start value to
default.
This set of methods (reult_field(), reset_field, update_field()) of
Item_sum is used only if quick_group is not null. Otherwise
copy_or_same() is used to obtain a copy of this item.
*/
virtual void reset_field()=0;
/*
Called for each new value in the group, when temporary table is in use.
Similar to add(), but uses temporary table field to obtain current value,
Updated value is then saved in the field.
*/
virtual void update_field()=0;
virtual bool keep_field_type(void) const { return 0; }
virtual void fix_length_and_dec() { maybe_null=1; null_value=1; }
/*
This method is used for debug purposes to print the name of an
item to the debug log. The second use of this method is as
a helper function of print(), where it is applicable.
To suit both goals it should return a meaningful,
distinguishable and sintactically correct string. This method
should not be used for runtime type identification, use enum
{Sum}Functype and Item_func::functype()/Item_sum::sum_func()
instead.
NOTE: for Items inherited from Item_sum, func_name() return part of
function name till first argument (including '(') to make difference in
names for functions with 'distinct' clause and without 'distinct' and
also to make printing of items inherited from Item_sum uniform.
*/
virtual const char *func_name() const= 0;
virtual Item *result_item(Field *field)
{ return new Item_field(field); }
table_map used_tables() const { return ~(table_map) 0; } /* Not used */
bool const_item() const { return 0; }
bool is_null() { return null_value; }
void update_used_tables() { }
void make_field(Send_field *field);
void print(String *str);
void fix_num_length_and_dec();
void no_rows_in_result() { reset(); }
virtual bool setup(THD *thd) {return 0;}
virtual void make_unique() {}
Item *get_tmp_table_item(THD *thd);
virtual Field *create_tmp_field(bool group, TABLE *table,
uint convert_blob_length);
bool walk(Item_processor processor, bool walk_subquery, byte *argument);
bool init_sum_func_check(THD *thd);
bool check_sum_func(THD *thd, Item **ref);
bool register_sum_func(THD *thd, Item **ref);
};
class Item_sum_num :public Item_sum
{
public:
Item_sum_num() :Item_sum() {}
Item_sum_num(Item *item_par) :Item_sum(item_par) {}
Item_sum_num(Item *a, Item* b) :Item_sum(a,b) {}
Item_sum_num(List<Item> &list) :Item_sum(list) {}
Item_sum_num(THD *thd, Item_sum_num *item) :Item_sum(thd, item) {}
bool fix_fields(THD *, Item **);
longlong val_int()
{
DBUG_ASSERT(fixed == 1);
return (longlong) rint(val_real()); /* Real as default */
}
String *val_str(String*str);
my_decimal *val_decimal(my_decimal *);
void reset_field();
};
class Item_sum_int :public Item_sum_num
{
public:
Item_sum_int(Item *item_par) :Item_sum_num(item_par) {}
Item_sum_int(List<Item> &list) :Item_sum_num(list) {}
Item_sum_int(THD *thd, Item_sum_int *item) :Item_sum_num(thd, item) {}
double val_real() { DBUG_ASSERT(fixed == 1); return (double) val_int(); }
String *val_str(String*str);
my_decimal *val_decimal(my_decimal *);
enum Item_result result_type () const { return INT_RESULT; }
void fix_length_and_dec()
{ decimals=0; max_length=21; maybe_null=null_value=0; }
};
class Item_sum_sum :public Item_sum_num
{
protected:
Item_result hybrid_type;
double sum;
my_decimal dec_buffs[2];
uint curr_dec_buff;
void fix_length_and_dec();
public:
Item_sum_sum(Item *item_par) :Item_sum_num(item_par) {}
Item_sum_sum(THD *thd, Item_sum_sum *item);
enum Sumfunctype sum_func () const {return SUM_FUNC;}
void clear();
bool add();
double val_real();
longlong val_int();
String *val_str(String*str);
my_decimal *val_decimal(my_decimal *);
enum Item_result result_type () const { return hybrid_type; }
void reset_field();
void update_field();
void no_rows_in_result() {}
const char *func_name() const { return "sum("; }
Item *copy_or_same(THD* thd);
};
/* Common class for SUM(DISTINCT), AVG(DISTINCT) */
class Unique;
class Item_sum_distinct :public Item_sum_num
{
protected:
/* storage for the summation result */
ulonglong count;
Hybrid_type val;
/* storage for unique elements */
Unique *tree;
TABLE *table;
enum enum_field_types table_field_type;
uint tree_key_length;
protected:
Item_sum_distinct(THD *thd, Item_sum_distinct *item);
public:
Item_sum_distinct(Item *item_par);
~Item_sum_distinct();
bool setup(THD *thd);
void clear();
void cleanup();
bool add();
double val_real();
my_decimal *val_decimal(my_decimal *);
longlong val_int();
String *val_str(String *str);
/* XXX: does it need make_unique? */
enum Sumfunctype sum_func () const { return SUM_DISTINCT_FUNC; }
void reset_field() {} // not used
void update_field() {} // not used
virtual void no_rows_in_result() {}
void fix_length_and_dec();
enum Item_result result_type () const { return val.traits->type(); }
virtual void calculate_val_and_count();
virtual bool unique_walk_function(void *elem);
};
/*
Item_sum_sum_distinct - implementation of SUM(DISTINCT expr).
See also: MySQL manual, chapter 'Adding New Functions To MySQL'
and comments in item_sum.cc.
*/
class Item_sum_sum_distinct :public Item_sum_distinct
{
private:
Item_sum_sum_distinct(THD *thd, Item_sum_sum_distinct *item)
:Item_sum_distinct(thd, item) {}
public:
Item_sum_sum_distinct(Item *item_arg) :Item_sum_distinct(item_arg) {}
enum Sumfunctype sum_func () const { return SUM_DISTINCT_FUNC; }
const char *func_name() const { return "sum(distinct "; }
Item *copy_or_same(THD* thd) { return new Item_sum_sum_distinct(thd, this); }
};
/* Item_sum_avg_distinct - SELECT AVG(DISTINCT expr) FROM ... */
class Item_sum_avg_distinct: public Item_sum_distinct
{
private:
Item_sum_avg_distinct(THD *thd, Item_sum_avg_distinct *original)
:Item_sum_distinct(thd, original) {}
public:
uint prec_increment;
Item_sum_avg_distinct(Item *item_arg) : Item_sum_distinct(item_arg) {}
void fix_length_and_dec();
virtual void calculate_val_and_count();
enum Sumfunctype sum_func () const { return AVG_DISTINCT_FUNC; }
const char *func_name() const { return "avg(distinct "; }
Item *copy_or_same(THD* thd) { return new Item_sum_avg_distinct(thd, this); }
};
class Item_sum_count :public Item_sum_int
{
longlong count;
table_map used_table_cache;
public:
Item_sum_count(Item *item_par)
:Item_sum_int(item_par),count(0),used_table_cache(~(table_map) 0)
{}
Item_sum_count(THD *thd, Item_sum_count *item)
:Item_sum_int(thd, item), count(item->count),
used_table_cache(item->used_table_cache)
{}
table_map used_tables() const { return used_table_cache; }
bool const_item() const { return !used_table_cache; }
enum Sumfunctype sum_func () const { return COUNT_FUNC; }
void clear();
void no_rows_in_result() { count=0; }
bool add();
void make_const(longlong count_arg) { count=count_arg; used_table_cache=0; }
longlong val_int();
void reset_field();
void cleanup();
void update_field();
const char *func_name() const { return "count("; }
Item *copy_or_same(THD* thd);
};
class TMP_TABLE_PARAM;
class Item_sum_count_distinct :public Item_sum_int
{
TABLE *table;
uint32 *field_lengths;
TMP_TABLE_PARAM *tmp_table_param;
bool force_copy_fields;
/*
If there are no blobs, we can use a tree, which
is faster than heap table. In that case, we still use the table
to help get things set up, but we insert nothing in it
*/
Unique *tree;
/*
Following is 0 normal object and pointer to original one for copy
(to correctly free resources)
*/
Item_sum_count_distinct *original;
uint tree_key_length;
bool always_null; // Set to 1 if the result is always NULL
friend int composite_key_cmp(void* arg, byte* key1, byte* key2);
friend int simple_str_key_cmp(void* arg, byte* key1, byte* key2);
public:
Item_sum_count_distinct(List<Item> &list)
:Item_sum_int(list), table(0), field_lengths(0), tmp_table_param(0),
force_copy_fields(0), tree(0), original(0), always_null(FALSE)
{ quick_group= 0; }
Item_sum_count_distinct(THD *thd, Item_sum_count_distinct *item)
:Item_sum_int(thd, item), table(item->table),
field_lengths(item->field_lengths),
tmp_table_param(item->tmp_table_param),
force_copy_fields(0), tree(item->tree), original(item),
tree_key_length(item->tree_key_length),
always_null(item->always_null)
{}
~Item_sum_count_distinct();
void cleanup();
enum Sumfunctype sum_func () const { return COUNT_DISTINCT_FUNC; }
void clear();
bool add();
longlong val_int();
void reset_field() { return ;} // Never called
void update_field() { return ; } // Never called
const char *func_name() const { return "count(distinct "; }
bool setup(THD *thd);
void make_unique();
Item *copy_or_same(THD* thd);
void no_rows_in_result() {}
};
/* Item to get the value of a stored sum function */
class Item_sum_avg;
class Item_avg_field :public Item_result_field
{
public:
Field *field;
Item_result hybrid_type;
uint f_precision, f_scale, dec_bin_size;
uint prec_increment;
Item_avg_field(Item_result res_type, Item_sum_avg *item);
enum Type type() const { return FIELD_AVG_ITEM; }
double val_real();
longlong val_int();
my_decimal *val_decimal(my_decimal *);
bool is_null() { (void) val_int(); return null_value; }
String *val_str(String*);
enum_field_types field_type() const
{
return hybrid_type == DECIMAL_RESULT ?
MYSQL_TYPE_NEWDECIMAL : MYSQL_TYPE_DOUBLE;
}
void fix_length_and_dec() {}
enum Item_result result_type () const { return hybrid_type; }
};
class Item_sum_avg :public Item_sum_sum
{
public:
ulonglong count;
uint prec_increment;
uint f_precision, f_scale, dec_bin_size;
Item_sum_avg(Item *item_par) :Item_sum_sum(item_par), count(0) {}
Item_sum_avg(THD *thd, Item_sum_avg *item)
:Item_sum_sum(thd, item), count(item->count),
prec_increment(item->prec_increment) {}
void fix_length_and_dec();
enum Sumfunctype sum_func () const {return AVG_FUNC;}
void clear();
bool add();
double val_real();
// In SPs we might force the "wrong" type with select into a declare variable
longlong val_int() { return (longlong) rint(val_real()); }
my_decimal *val_decimal(my_decimal *);
String *val_str(String *str);
void reset_field();
void update_field();
Item *result_item(Field *field)
{ return new Item_avg_field(hybrid_type, this); }
void no_rows_in_result() {}
const char *func_name() const { return "avg("; }
Item *copy_or_same(THD* thd);
Field *create_tmp_field(bool group, TABLE *table, uint convert_blob_length);
};
class Item_sum_variance;
class Item_variance_field :public Item_result_field
{
public:
Field *field;
Item_result hybrid_type;
uint f_precision0, f_scale0;
uint f_precision1, f_scale1;
uint dec_bin_size0, dec_bin_size1;
uint sample;
uint prec_increment;
Item_variance_field(Item_sum_variance *item);
enum Type type() const {return FIELD_VARIANCE_ITEM; }
double val_real();
longlong val_int()
{ /* can't be fix_fields()ed */ return (longlong) rint(val_real()); }
String *val_str(String*);
my_decimal *val_decimal(my_decimal *);
bool is_null() { (void) val_int(); return null_value; }
enum_field_types field_type() const
{
return hybrid_type == DECIMAL_RESULT ?
MYSQL_TYPE_NEWDECIMAL : MYSQL_TYPE_DOUBLE;
}
void fix_length_and_dec() {}
enum Item_result result_type () const { return hybrid_type; }
};
/*
variance(a) =
= sum (ai - avg(a))^2 / count(a) )
= sum (ai^2 - 2*ai*avg(a) + avg(a)^2) / count(a)
= (sum(ai^2) - sum(2*ai*avg(a)) + sum(avg(a)^2))/count(a) =
= (sum(ai^2) - 2*avg(a)*sum(a) + count(a)*avg(a)^2)/count(a) =
= (sum(ai^2) - 2*sum(a)*sum(a)/count(a) + count(a)*sum(a)^2/count(a)^2 )/count(a) =
= (sum(ai^2) - 2*sum(a)^2/count(a) + sum(a)^2/count(a) )/count(a) =
= (sum(ai^2) - sum(a)^2/count(a))/count(a)
*/
class Item_sum_variance : public Item_sum_num
{
void fix_length_and_dec();
public:
Item_result hybrid_type;
double sum, sum_sqr;
my_decimal dec_sum[2], dec_sqr[2];
int cur_dec;
ulonglong count;
uint f_precision0, f_scale0;
uint f_precision1, f_scale1;
uint dec_bin_size0, dec_bin_size1;
uint sample;
uint prec_increment;
Item_sum_variance(Item *item_par, uint sample_arg) :Item_sum_num(item_par),
hybrid_type(REAL_RESULT), cur_dec(0), count(0), sample(sample_arg)
{}
Item_sum_variance(THD *thd, Item_sum_variance *item);
enum Sumfunctype sum_func () const { return VARIANCE_FUNC; }
void clear();
bool add();
double val_real();
my_decimal *val_decimal(my_decimal *);
void reset_field();
void update_field();
Item *result_item(Field *field)
{ return new Item_variance_field(this); }
void no_rows_in_result() {}
const char *func_name() const
{ return sample ? "var_samp(" : "variance("; }
Item *copy_or_same(THD* thd);
Field *create_tmp_field(bool group, TABLE *table, uint convert_blob_length);
enum Item_result result_type () const { return hybrid_type; }
};
class Item_sum_std;
class Item_std_field :public Item_variance_field
{
public:
Item_std_field(Item_sum_std *item);
enum Type type() const { return FIELD_STD_ITEM; }
double val_real();
my_decimal *val_decimal(my_decimal *);
enum Item_result result_type () const { return REAL_RESULT; }
enum_field_types field_type() const { return MYSQL_TYPE_DOUBLE;}
};
/*
standard_deviation(a) = sqrt(variance(a))
*/
class Item_sum_std :public Item_sum_variance
{
public:
Item_sum_std(Item *item_par, uint sample_arg)
:Item_sum_variance(item_par, sample_arg) {}
Item_sum_std(THD *thd, Item_sum_std *item)
:Item_sum_variance(thd, item)
{}
enum Sumfunctype sum_func () const { return STD_FUNC; }
double val_real();
Item *result_item(Field *field)
{ return new Item_std_field(this); }
const char *func_name() const { return "std("; }
Item *copy_or_same(THD* thd);
enum Item_result result_type () const { return REAL_RESULT; }
enum_field_types field_type() const { return MYSQL_TYPE_DOUBLE;}
};
// This class is a string or number function depending on num_func
class Item_sum_hybrid :public Item_sum
{
protected:
String value,tmp_value;
double sum;
longlong sum_int;
my_decimal sum_dec;
Item_result hybrid_type;
enum_field_types hybrid_field_type;
int cmp_sign;
table_map used_table_cache;
bool was_values; // Set if we have found at least one row (for max/min only)
public:
Item_sum_hybrid(Item *item_par,int sign)
:Item_sum(item_par), sum(0.0), sum_int(0),
hybrid_type(INT_RESULT), hybrid_field_type(FIELD_TYPE_LONGLONG),
cmp_sign(sign), used_table_cache(~(table_map) 0),
was_values(TRUE)
{ collation.set(&my_charset_bin); }
Item_sum_hybrid(THD *thd, Item_sum_hybrid *item);
bool fix_fields(THD *, Item **);
table_map used_tables() const { return used_table_cache; }
bool const_item() const { return !used_table_cache; }
void clear();
double val_real();
longlong val_int();
my_decimal *val_decimal(my_decimal *);
void reset_field();
String *val_str(String *);
void make_const() { used_table_cache=0; }
bool keep_field_type(void) const { return 1; }
enum Item_result result_type () const { return hybrid_type; }
enum enum_field_types field_type() const { return hybrid_field_type; }
void update_field();
void min_max_update_str_field();
void min_max_update_real_field();
void min_max_update_int_field();
void min_max_update_decimal_field();
void cleanup();
bool any_value() { return was_values; }
void no_rows_in_result();
Field *create_tmp_field(bool group, TABLE *table,
uint convert_blob_length);
};
class Item_sum_min :public Item_sum_hybrid
{
public:
Item_sum_min(Item *item_par) :Item_sum_hybrid(item_par,1) {}
Item_sum_min(THD *thd, Item_sum_min *item) :Item_sum_hybrid(thd, item) {}
enum Sumfunctype sum_func () const {return MIN_FUNC;}
bool add();
const char *func_name() const { return "min("; }
Item *copy_or_same(THD* thd);
};
class Item_sum_max :public Item_sum_hybrid
{
public:
Item_sum_max(Item *item_par) :Item_sum_hybrid(item_par,-1) {}
Item_sum_max(THD *thd, Item_sum_max *item) :Item_sum_hybrid(thd, item) {}
enum Sumfunctype sum_func () const {return MAX_FUNC;}
bool add();
const char *func_name() const { return "max("; }
Item *copy_or_same(THD* thd);
};
class Item_sum_bit :public Item_sum_int
{
protected:
ulonglong reset_bits,bits;
public:
Item_sum_bit(Item *item_par,ulonglong reset_arg)
:Item_sum_int(item_par),reset_bits(reset_arg),bits(reset_arg) {}
Item_sum_bit(THD *thd, Item_sum_bit *item):
Item_sum_int(thd, item), reset_bits(item->reset_bits), bits(item->bits) {}
enum Sumfunctype sum_func () const {return SUM_BIT_FUNC;}
void clear();
longlong val_int();
void reset_field();
void update_field();
void fix_length_and_dec()
{ decimals= 0; max_length=21; unsigned_flag= 1; maybe_null= null_value= 0; }
};
class Item_sum_or :public Item_sum_bit
{
public:
Item_sum_or(Item *item_par) :Item_sum_bit(item_par,LL(0)) {}
Item_sum_or(THD *thd, Item_sum_or *item) :Item_sum_bit(thd, item) {}
bool add();
const char *func_name() const { return "bit_or("; }
Item *copy_or_same(THD* thd);
};
class Item_sum_and :public Item_sum_bit
{
public:
Item_sum_and(Item *item_par) :Item_sum_bit(item_par, ULONGLONG_MAX) {}
Item_sum_and(THD *thd, Item_sum_and *item) :Item_sum_bit(thd, item) {}
bool add();
const char *func_name() const { return "bit_and("; }
Item *copy_or_same(THD* thd);
};
class Item_sum_xor :public Item_sum_bit
{
public:
Item_sum_xor(Item *item_par) :Item_sum_bit(item_par,LL(0)) {}
Item_sum_xor(THD *thd, Item_sum_xor *item) :Item_sum_bit(thd, item) {}
bool add();
const char *func_name() const { return "bit_xor("; }
Item *copy_or_same(THD* thd);
};
/*
User defined aggregates
*/
#ifdef HAVE_DLOPEN
class Item_udf_sum : public Item_sum
{
protected:
udf_handler udf;
public:
Item_udf_sum(udf_func *udf_arg)
:Item_sum(), udf(udf_arg)
{ quick_group=0; }
Item_udf_sum(udf_func *udf_arg, List<Item> &list)
:Item_sum(list), udf(udf_arg)
{ quick_group=0;}
Item_udf_sum(THD *thd, Item_udf_sum *item)
:Item_sum(thd, item), udf(item->udf)
{ udf.not_original= TRUE; }
const char *func_name() const { return udf.name(); }
bool fix_fields(THD *thd, Item **ref)
{
DBUG_ASSERT(fixed == 0);
fixed= 1;
return udf.fix_fields(thd, this, this->arg_count, this->args);
}
enum Sumfunctype sum_func () const { return UDF_SUM_FUNC; }
virtual bool have_field_update(void) const { return 0; }
void clear();
bool add();
void reset_field() {};
void update_field() {};
void cleanup();
void print(String *str);
};
class Item_sum_udf_float :public Item_udf_sum
{
public:
Item_sum_udf_float(udf_func *udf_arg)
:Item_udf_sum(udf_arg) {}
Item_sum_udf_float(udf_func *udf_arg, List<Item> &list)
:Item_udf_sum(udf_arg, list) {}
Item_sum_udf_float(THD *thd, Item_sum_udf_float *item)
:Item_udf_sum(thd, item) {}
longlong val_int()
{
DBUG_ASSERT(fixed == 1);
return (longlong) rint(Item_sum_udf_float::val_real());
}
double val_real();
String *val_str(String*str);
my_decimal *val_decimal(my_decimal *);
void fix_length_and_dec() { fix_num_length_and_dec(); }
Item *copy_or_same(THD* thd);
};
class Item_sum_udf_int :public Item_udf_sum
{
public:
Item_sum_udf_int(udf_func *udf_arg)
:Item_udf_sum(udf_arg) {}
Item_sum_udf_int(udf_func *udf_arg, List<Item> &list)
:Item_udf_sum(udf_arg, list) {}
Item_sum_udf_int(THD *thd, Item_sum_udf_int *item)
:Item_udf_sum(thd, item) {}
longlong val_int();
double val_real()
{ DBUG_ASSERT(fixed == 1); return (double) Item_sum_udf_int::val_int(); }
String *val_str(String*str);
my_decimal *val_decimal(my_decimal *);
enum Item_result result_type () const { return INT_RESULT; }
void fix_length_and_dec() { decimals=0; max_length=21; }
Item *copy_or_same(THD* thd);
};
class Item_sum_udf_str :public Item_udf_sum
{
public:
Item_sum_udf_str(udf_func *udf_arg)
:Item_udf_sum(udf_arg) {}
Item_sum_udf_str(udf_func *udf_arg, List<Item> &list)
:Item_udf_sum(udf_arg,list) {}
Item_sum_udf_str(THD *thd, Item_sum_udf_str *item)
:Item_udf_sum(thd, item) {}
String *val_str(String *);
double val_real()
{
int err_not_used;
char *end_not_used;
String *res;
res=val_str(&str_value);
return res ? my_strntod(res->charset(),(char*) res->ptr(),res->length(),
&end_not_used, &err_not_used) : 0.0;
}
longlong val_int()
{
int err_not_used;
char *end;
String *res;
CHARSET_INFO *cs;
if (!(res= val_str(&str_value)))
return 0; /* Null value */
cs= res->charset();
end= (char*) res->ptr()+res->length();
return cs->cset->strtoll10(cs, res->ptr(), &end, &err_not_used);
}
my_decimal *val_decimal(my_decimal *dec);
enum Item_result result_type () const { return STRING_RESULT; }
void fix_length_and_dec();
Item *copy_or_same(THD* thd);
};
class Item_sum_udf_decimal :public Item_udf_sum
{
public:
Item_sum_udf_decimal(udf_func *udf_arg)
:Item_udf_sum(udf_arg) {}
Item_sum_udf_decimal(udf_func *udf_arg, List<Item> &list)
:Item_udf_sum(udf_arg, list) {}
Item_sum_udf_decimal(THD *thd, Item_sum_udf_decimal *item)
:Item_udf_sum(thd, item) {}
String *val_str(String *);
double val_real();
longlong val_int();
my_decimal *val_decimal(my_decimal *);
enum Item_result result_type () const { return DECIMAL_RESULT; }
void fix_length_and_dec() { fix_num_length_and_dec(); }
Item *copy_or_same(THD* thd);
};
#else /* Dummy functions to get sql_yacc.cc compiled */
class Item_sum_udf_float :public Item_sum_num
{
public:
Item_sum_udf_float(udf_func *udf_arg)
:Item_sum_num() {}
Item_sum_udf_float(udf_func *udf_arg, List<Item> &list) :Item_sum_num() {}
Item_sum_udf_float(THD *thd, Item_sum_udf_float *item)
:Item_sum_num(thd, item) {}
enum Sumfunctype sum_func () const { return UDF_SUM_FUNC; }
double val_real() { DBUG_ASSERT(fixed == 1); return 0.0; }
void clear() {}
bool add() { return 0; }
void update_field() {}
};
class Item_sum_udf_int :public Item_sum_num
{
public:
Item_sum_udf_int(udf_func *udf_arg)
:Item_sum_num() {}
Item_sum_udf_int(udf_func *udf_arg, List<Item> &list) :Item_sum_num() {}
Item_sum_udf_int(THD *thd, Item_sum_udf_int *item)
:Item_sum_num(thd, item) {}
enum Sumfunctype sum_func () const { return UDF_SUM_FUNC; }
longlong val_int() { DBUG_ASSERT(fixed == 1); return 0; }
double val_real() { DBUG_ASSERT(fixed == 1); return 0; }
void clear() {}
bool add() { return 0; }
void update_field() {}
};
class Item_sum_udf_decimal :public Item_sum_num
{
public:
Item_sum_udf_decimal(udf_func *udf_arg)
:Item_sum_num() {}
Item_sum_udf_decimal(udf_func *udf_arg, List<Item> &list)
:Item_sum_num() {}
Item_sum_udf_decimal(THD *thd, Item_sum_udf_float *item)
:Item_sum_num(thd, item) {}
enum Sumfunctype sum_func () const { return UDF_SUM_FUNC; }
double val_real() { DBUG_ASSERT(fixed == 1); return 0.0; }
my_decimal *val_decimal(my_decimal *) { DBUG_ASSERT(fixed == 1); return 0; }
void clear() {}
bool add() { return 0; }
void update_field() {}
};
class Item_sum_udf_str :public Item_sum_num
{
public:
Item_sum_udf_str(udf_func *udf_arg)
:Item_sum_num() {}
Item_sum_udf_str(udf_func *udf_arg, List<Item> &list)
:Item_sum_num() {}
Item_sum_udf_str(THD *thd, Item_sum_udf_str *item)
:Item_sum_num(thd, item) {}
String *val_str(String *)
{ DBUG_ASSERT(fixed == 1); null_value=1; return 0; }
double val_real() { DBUG_ASSERT(fixed == 1); null_value=1; return 0.0; }
longlong val_int() { DBUG_ASSERT(fixed == 1); null_value=1; return 0; }
enum Item_result result_type () const { return STRING_RESULT; }
void fix_length_and_dec() { maybe_null=1; max_length=0; }
enum Sumfunctype sum_func () const { return UDF_SUM_FUNC; }
void clear() {}
bool add() { return 0; }
void update_field() {}
};
#endif /* HAVE_DLOPEN */
class MYSQL_ERROR;
class Item_func_group_concat : public Item_sum
{
TMP_TABLE_PARAM *tmp_table_param;
MYSQL_ERROR *warning;
String result;
String *separator;
TREE tree_base;
TREE *tree;
TABLE *table;
ORDER **order;
Name_resolution_context *context;
uint arg_count_order; // total count of ORDER BY items
uint arg_count_field; // count of arguments
uint count_cut_values;
bool distinct;
bool warning_for_row;
bool always_null;
bool force_copy_fields;
bool no_appended;
/*
Following is 0 normal object and pointer to original one for copy
(to correctly free resources)
*/
Item_func_group_concat *original;
friend int group_concat_key_cmp_with_distinct(void* arg, byte* key1,
byte* key2);
friend int group_concat_key_cmp_with_order(void* arg, byte* key1,
byte* key2);
friend int group_concat_key_cmp_with_distinct_and_order(void* arg,
byte* key1,
byte* key2);
friend int dump_leaf_key(byte* key,
element_count count __attribute__((unused)),
Item_func_group_concat *group_concat_item);
public:
Item_func_group_concat(Name_resolution_context *context_arg,
bool is_distinct, List<Item> *is_select,
SQL_LIST *is_order, String *is_separator);
Item_func_group_concat(THD *thd, Item_func_group_concat *item);
~Item_func_group_concat() {}
void cleanup();
enum Sumfunctype sum_func () const {return GROUP_CONCAT_FUNC;}
const char *func_name() const { return "group_concat"; }
virtual Item_result result_type () const { return STRING_RESULT; }
enum_field_types field_type() const
{
if (max_length/collation.collation->mbmaxlen > CONVERT_IF_BIGGER_TO_BLOB )
return FIELD_TYPE_BLOB;
else
return MYSQL_TYPE_VARCHAR;
}
void clear();
bool add();
void reset_field() { DBUG_ASSERT(0); } // not used
void update_field() { DBUG_ASSERT(0); } // not used
bool fix_fields(THD *,Item **);
bool setup(THD *thd);
void make_unique();
double val_real()
{
String *res; res=val_str(&str_value);
return res ? my_atof(res->c_ptr()) : 0.0;
}
longlong val_int()
{
String *res;
char *end_ptr;
int error;
if (!(res= val_str(&str_value)))
return (longlong) 0;
end_ptr= (char*) res->ptr()+ res->length();
return my_strtoll10(res->ptr(), &end_ptr, &error);
}
my_decimal *val_decimal(my_decimal *decimal_value)
{
return val_decimal_from_string(decimal_value);
}
String* val_str(String* str);
Item *copy_or_same(THD* thd);
void no_rows_in_result() {}
void print(String *str);
virtual bool change_context_processor(byte *cntx)
{ context= (Name_resolution_context *)cntx; return FALSE; }
};