2003-05-05 13:52:39 +02:00
#
# Some simple test of load data
#
2003-05-21 20:39:58 +02:00
--disable_warnings
2005-03-16 10:13:35 +01:00
drop table if exists t1, t2;
2003-05-21 20:39:58 +02:00
--enable_warnings
2003-05-05 13:52:39 +02:00
create table t1 (a date, b date, c date not null, d date);
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/loaddata1.dat' into table t1 fields terminated by ',';
load data infile '../../std_data/loaddata1.dat' into table t1 fields terminated by ',' IGNORE 2 LINES;
2003-05-05 13:52:39 +02:00
SELECT * from t1;
2003-05-26 10:47:03 +02:00
truncate table t1;
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/loaddata1.dat' into table t1 fields terminated by ',' LINES STARTING BY ',' (b,c,d);
2003-05-26 10:47:03 +02:00
SELECT * from t1;
2003-05-05 13:52:39 +02:00
drop table t1;
2003-05-26 10:47:03 +02:00
2003-08-22 03:07:40 +02:00
create table t1 (a text, b text);
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/loaddata2.dat' into table t1 fields terminated by ',' enclosed by '''';
2003-08-22 03:07:40 +02:00
select concat('|',a,'|'), concat('|',b,'|') from t1;
drop table t1;
2003-12-14 05:39:52 +01:00
create table t1 (a int, b char(10));
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/loaddata3.dat' into table t1 fields terminated by '' enclosed by '' ignore 1 lines;
2003-12-14 05:39:52 +01:00
select * from t1;
truncate table t1;
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/loaddata4.dat' into table t1 fields terminated by '' enclosed by '' lines terminated by '' ignore 1 lines;
2003-12-14 05:39:52 +01:00
# The empty line last comes from the end line field in the file
select * from t1;
drop table t1;
2005-09-22 09:46:01 +02:00
#
# Bug #12053 LOAD DATA INFILE ignores NO_AUTO_VALUE_ON_ZERO setting
#
SET @OLD_SQL_MODE=@@SQL_MODE, @@SQL_MODE=NO_AUTO_VALUE_ON_ZERO;
create table t1(id integer not null auto_increment primary key);
insert into t1 values(0);
disable_query_log;
2006-01-24 08:30:54 +01:00
eval SELECT * INTO OUTFILE '$MYSQLTEST_VARDIR/tmp/t1' from t1;
2005-09-22 09:46:01 +02:00
delete from t1;
2006-01-24 08:30:54 +01:00
eval load data infile '$MYSQLTEST_VARDIR/tmp/t1' into table t1;
2005-09-22 09:46:01 +02:00
enable_query_log;
select * from t1;
2007-08-28 15:32:44 +02:00
remove_file $MYSQLTEST_VARDIR/tmp/t1;
2005-09-22 09:46:01 +02:00
disable_query_log;
2006-01-24 08:30:54 +01:00
eval SELECT * INTO OUTFILE '$MYSQLTEST_VARDIR/tmp/t1'
2005-09-22 09:46:01 +02:00
FIELDS TERMINATED BY '' OPTIONALLY ENCLOSED BY '' LINES TERMINATED BY '\r\n'
FROM t1;
delete from t1;
2006-01-24 08:30:54 +01:00
eval load data infile '$MYSQLTEST_VARDIR/tmp/t1' into table t1
2005-09-22 09:46:01 +02:00
FIELDS TERMINATED BY '' OPTIONALLY ENCLOSED BY '' LINES TERMINATED BY '\r\n';
enable_query_log;
select * from t1;
2007-08-28 15:32:44 +02:00
remove_file $MYSQLTEST_VARDIR/tmp/t1;
2005-09-22 09:46:01 +02:00
SET @@SQL_MODE=@OLD_SQL_MODE;
2005-09-23 14:37:22 +02:00
drop table t1;
2005-09-22 09:46:01 +02:00
2005-06-23 01:14:14 +02:00
#
# Bug #11203: LOAD DATA does not accept same characters for ESCAPED and
# ENCLOSED
#
create table t1 (a varchar(20), b varchar(20));
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/loaddata_dq.dat' into table t1 fields terminated by ',' enclosed by '"' escaped by '"' (a,b);
2005-06-23 01:14:14 +02:00
select * from t1;
drop table t1;
2005-10-22 02:57:51 +02:00
Fixed bug #29294.
The `SELECT 'r' INTO OUTFILE ... FIELDS ENCLOSED BY 'r' ' statement
encoded the 'r' string to a 4 byte string of value x'725c7272'
(sequence of 4 characters: r\rr).
The LOAD DATA statement decoded this string to a 1 byte string of
value x'0d' (ASCII Carriage Return character) instead of the original
'r' character.
The same error also happened with the FIELDS ENCLOSED BY clause
followed by special characters: 'n', 't', 'r', 'b', '0', 'Z' and 'N'.
NOTE 1: This is a result of the undocumented feature: the LOAD DATA INFILE
recognises 2-byte input sequences like \n, \t, \r and \Z in addition
to documented 2-byte sequences: \0 and \N. This feature should be
documented (here backspace character is a default ESCAPED BY character,
in the real-life example it may be any ESCAPED BY character).
NOTE 2, changed behaviour:
Now the `SELECT INTO OUTFILE' statement with the `FIELDS ENCLOSED BY'
clause followed by one of: 'n', 't', 'r', 'b', '0', 'Z' or 'N' characters
encodes this special character itself by doubling it ('r' --> 'rr'),
not by prepending it with an escape character.
2007-07-03 16:37:46 +02:00
#
# Bug #29294 SELECT INTO OUTFILE/LOAD DATA INFILE with special
# characters in the FIELDS ENCLOSED BY clause
#
CREATE TABLE t1 (
id INT AUTO_INCREMENT PRIMARY KEY,
c1 VARCHAR(255)
);
CREATE TABLE t2 (
id INT,
c2 VARCHAR(255)
);
INSERT INTO t1 (c1) VALUES
('r'), ('rr'), ('rrr'), ('rrrr'),
('.r'), ('.rr'), ('.rrr'), ('.rrrr'),
('r.'), ('rr.'), ('rrr.'), ('rrrr.'),
2007-07-03 18:45:20 +02:00
('.r.'), ('.rr.'), ('.rrr.'), ('.rrrr.');
Fixed bug #29294.
The `SELECT 'r' INTO OUTFILE ... FIELDS ENCLOSED BY 'r' ' statement
encoded the 'r' string to a 4 byte string of value x'725c7272'
(sequence of 4 characters: r\rr).
The LOAD DATA statement decoded this string to a 1 byte string of
value x'0d' (ASCII Carriage Return character) instead of the original
'r' character.
The same error also happened with the FIELDS ENCLOSED BY clause
followed by special characters: 'n', 't', 'r', 'b', '0', 'Z' and 'N'.
NOTE 1: This is a result of the undocumented feature: the LOAD DATA INFILE
recognises 2-byte input sequences like \n, \t, \r and \Z in addition
to documented 2-byte sequences: \0 and \N. This feature should be
documented (here backspace character is a default ESCAPED BY character,
in the real-life example it may be any ESCAPED BY character).
NOTE 2, changed behaviour:
Now the `SELECT INTO OUTFILE' statement with the `FIELDS ENCLOSED BY'
clause followed by one of: 'n', 't', 'r', 'b', '0', 'Z' or 'N' characters
encodes this special character itself by doubling it ('r' --> 'rr'),
not by prepending it with an escape character.
2007-07-03 16:37:46 +02:00
SELECT * FROM t1;
2007-07-04 00:15:37 +02:00
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
eval SELECT * INTO OUTFILE '$MYSQLTEST_VARDIR/tmp/t1' FIELDS ENCLOSED BY 'r' FROM t1;
2007-08-28 15:32:44 +02:00
cat_file $MYSQLTEST_VARDIR/tmp/t1;
Fixed bug #29294.
The `SELECT 'r' INTO OUTFILE ... FIELDS ENCLOSED BY 'r' ' statement
encoded the 'r' string to a 4 byte string of value x'725c7272'
(sequence of 4 characters: r\rr).
The LOAD DATA statement decoded this string to a 1 byte string of
value x'0d' (ASCII Carriage Return character) instead of the original
'r' character.
The same error also happened with the FIELDS ENCLOSED BY clause
followed by special characters: 'n', 't', 'r', 'b', '0', 'Z' and 'N'.
NOTE 1: This is a result of the undocumented feature: the LOAD DATA INFILE
recognises 2-byte input sequences like \n, \t, \r and \Z in addition
to documented 2-byte sequences: \0 and \N. This feature should be
documented (here backspace character is a default ESCAPED BY character,
in the real-life example it may be any ESCAPED BY character).
NOTE 2, changed behaviour:
Now the `SELECT INTO OUTFILE' statement with the `FIELDS ENCLOSED BY'
clause followed by one of: 'n', 't', 'r', 'b', '0', 'Z' or 'N' characters
encodes this special character itself by doubling it ('r' --> 'rr'),
not by prepending it with an escape character.
2007-07-03 16:37:46 +02:00
2007-07-04 00:15:37 +02:00
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
eval LOAD DATA INFILE '$MYSQLTEST_VARDIR/tmp/t1' INTO TABLE t2 FIELDS ENCLOSED BY 'r';
Fixed bug #29294.
The `SELECT 'r' INTO OUTFILE ... FIELDS ENCLOSED BY 'r' ' statement
encoded the 'r' string to a 4 byte string of value x'725c7272'
(sequence of 4 characters: r\rr).
The LOAD DATA statement decoded this string to a 1 byte string of
value x'0d' (ASCII Carriage Return character) instead of the original
'r' character.
The same error also happened with the FIELDS ENCLOSED BY clause
followed by special characters: 'n', 't', 'r', 'b', '0', 'Z' and 'N'.
NOTE 1: This is a result of the undocumented feature: the LOAD DATA INFILE
recognises 2-byte input sequences like \n, \t, \r and \Z in addition
to documented 2-byte sequences: \0 and \N. This feature should be
documented (here backspace character is a default ESCAPED BY character,
in the real-life example it may be any ESCAPED BY character).
NOTE 2, changed behaviour:
Now the `SELECT INTO OUTFILE' statement with the `FIELDS ENCLOSED BY'
clause followed by one of: 'n', 't', 'r', 'b', '0', 'Z' or 'N' characters
encodes this special character itself by doubling it ('r' --> 'rr'),
not by prepending it with an escape character.
2007-07-03 16:37:46 +02:00
SELECT t1.id, c1, c2 FROM t1 LEFT JOIN t2 ON t1.id=t2.id WHERE c1 != c2;
SELECT t1.id, c1, c2 FROM t1 RIGHT JOIN t2 ON t1.id=t2.id WHERE c1 != c2;
2007-08-28 15:32:44 +02:00
remove_file $MYSQLTEST_VARDIR/tmp/t1;
Fixed bug #29294.
The `SELECT 'r' INTO OUTFILE ... FIELDS ENCLOSED BY 'r' ' statement
encoded the 'r' string to a 4 byte string of value x'725c7272'
(sequence of 4 characters: r\rr).
The LOAD DATA statement decoded this string to a 1 byte string of
value x'0d' (ASCII Carriage Return character) instead of the original
'r' character.
The same error also happened with the FIELDS ENCLOSED BY clause
followed by special characters: 'n', 't', 'r', 'b', '0', 'Z' and 'N'.
NOTE 1: This is a result of the undocumented feature: the LOAD DATA INFILE
recognises 2-byte input sequences like \n, \t, \r and \Z in addition
to documented 2-byte sequences: \0 and \N. This feature should be
documented (here backspace character is a default ESCAPED BY character,
in the real-life example it may be any ESCAPED BY character).
NOTE 2, changed behaviour:
Now the `SELECT INTO OUTFILE' statement with the `FIELDS ENCLOSED BY'
clause followed by one of: 'n', 't', 'r', 'b', '0', 'Z' or 'N' characters
encodes this special character itself by doubling it ('r' --> 'rr'),
not by prepending it with an escape character.
2007-07-03 16:37:46 +02:00
DROP TABLE t1,t2;
2005-07-28 02:22:47 +02:00
# End of 4.1 tests
2005-07-28 16:09:54 +02:00
2005-03-16 02:32:47 +01:00
#
# Let us test extended LOAD DATA features
#
create table t1 (a int default 100, b int, c varchar(60));
# we can do something like this
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/rpl_loaddata.dat' into table t1 (a, @b) set b=@b+10, c=concat("b=",@b);
2005-03-16 02:32:47 +01:00
select * from t1;
truncate table t1;
# we can use filled fields in expressions
# we also assigning NULL value to field with non-NULL default here
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/rpl_loaddata.dat' into table t1 (a, @b) set c= if(a is null,"oops",a);
2005-03-16 02:32:47 +01:00
select * from t1;
truncate table t1;
# we even can use variables in set clause, and missed columns will be set
# with default values
set @c:=123;
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/rpl_loaddata.dat' into table t1 (@a, b) set c= if(@a is null,@c,b);
2005-03-16 02:32:47 +01:00
select * from t1;
# let us test side-effect of such load
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/rpl_loaddata.dat' into table t1 (@a, @b);
2005-03-16 02:32:47 +01:00
select * from t1;
select @a, @b;
truncate table t1;
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.
2006-06-04 17:52:22 +02:00
# Reading of all columns with set
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/rpl_loaddata.dat' into table t1 set c=b;
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.
2006-06-04 17:52:22 +02:00
select * from t1;
truncate table t1;
2005-03-16 02:32:47 +01:00
# now going to test fixed field-row file format
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/loaddata5.dat' into table t1 fields terminated by '' enclosed by '' (a, b) set c="Wow";
2005-03-16 02:32:47 +01:00
select * from t1;
truncate table t1;
# this also should work
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/loaddata5.dat' into table t1 fields terminated by '' enclosed by '' (a, b) set c=concat(a,"+",b,"+",@c,"+",b,"+",if(c is null,"NIL",c));
2005-03-16 02:32:47 +01:00
select * from t1;
# and this should bark
--error 1409
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/loaddata5.dat' into table t1 fields terminated by '' enclosed by '' (a, @b);
2005-03-16 10:13:35 +01:00
# Now let us test LOAD DATA with subselect
create table t2 (num int primary key, str varchar(10));
insert into t2 values (10,'Ten'), (15,'Fifteen');
truncate table t1;
2007-12-12 18:19:24 +01:00
load data infile '../../std_data/rpl_loaddata.dat' into table t1 (@dummy,@n) set a= @n, c= (select str from t2 where num=@n);
2005-03-16 10:13:35 +01:00
select * from t1;
2007-02-14 14:44:34 +01:00
#
# Bug#18628 mysql-test-run: security problem
#
# It should not be possible to load from a file outside of vardir
2010-05-03 18:14:39 +02:00
## The following lines were disabled because of patch for
## bug 50373. MYSQLTEST_VARDIR doesn't rewrite symlinks
## to real paths, but this is done for secure_file_priv.
## Because of this the result can't be replaced if the
## test suite runs with the --mem option which creates
## symlinks to the ramdisk.
#--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
#show variables like "secure_file_pri%";
#--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
#select @@secure_file_priv;
2007-02-14 14:44:34 +01:00
--error 1238
set @@secure_file_priv= 0;
# Test "load data"
truncate table t1;
--replace_result $MYSQL_TEST_DIR MYSQL_TEST_DIR
2008-07-04 11:33:34 +02:00
--error ER_OPTION_PREVENTS_STATEMENT, ER_TEXTFILE_NOT_READABLE
2007-03-16 19:56:16 +01:00
eval load data infile '$MYSQL_TEST_DIR/t/loaddata.test' into table t1;
2007-02-14 14:44:34 +01:00
select * from t1;
# Test "load_file" returns NULL
--replace_result $MYSQL_TEST_DIR MYSQL_TEST_DIR
2007-03-16 19:56:16 +01:00
eval select load_file("$MYSQL_TEST_DIR/t/loaddata.test");
2007-02-14 14:44:34 +01:00
2005-03-16 10:13:35 +01:00
# cleanup
drop table t1, t2;
2005-10-26 23:11:08 +02:00
2007-04-06 22:13:27 +02:00
#
# Bug#27586: Wrong autoinc value assigned by LOAD DATA in the
# NO_AUTO_VALUE_ON_ZERO mode
#
create table t1(f1 int);
insert into t1 values(1),(null);
create table t2(f2 int auto_increment primary key);
disable_query_log;
eval select * into outfile '$MYSQLTEST_VARDIR/tmp/t1' from t1;
SET @OLD_SQL_MODE=@@SQL_MODE, @@SQL_MODE=NO_AUTO_VALUE_ON_ZERO;
eval load data infile '$MYSQLTEST_VARDIR/tmp/t1' into table t2;
enable_query_log;
select * from t2;
2007-08-28 15:32:44 +02:00
remove_file $MYSQLTEST_VARDIR/tmp/t1;
2007-04-06 22:13:27 +02:00
SET @@SQL_MODE=@OLD_SQL_MODE;
drop table t1,t2;
2007-05-08 22:23:16 +02:00
#
# Bug#27670: LOAD DATA does not set CURRENT_TIMESTAMP default value for a
# TIMESTAMP field when no value has been provided.
#
create table t1(f1 int, f2 timestamp not null default current_timestamp);
create table t2(f1 int);
insert into t2 values(1),(2);
disable_query_log;
eval select * into outfile '$MYSQLTEST_VARDIR/tmp/t2' from t2;
eval load data infile '$MYSQLTEST_VARDIR/tmp/t2' into table t1;
enable_query_log;
2007-05-09 12:46:11 +02:00
select f1 from t1 where f2 <> '0000-00-00 00:00:00' order by f1;
2007-08-28 15:32:44 +02:00
remove_file $MYSQLTEST_VARDIR/tmp/t2;
2007-05-08 22:23:16 +02:00
delete from t1;
disable_query_log;
eval SELECT * INTO OUTFILE '$MYSQLTEST_VARDIR/tmp/t2'
FIELDS TERMINATED BY '' OPTIONALLY ENCLOSED BY '' LINES TERMINATED BY '\r\n'
FROM t2;
eval load data infile '$MYSQLTEST_VARDIR/tmp/t2' into table t1
FIELDS TERMINATED BY '' OPTIONALLY ENCLOSED BY '' LINES TERMINATED BY '\r\n';
enable_query_log;
2007-05-09 12:46:11 +02:00
select f1 from t1 where f2 <> '0000-00-00 00:00:00' order by f1;
2007-08-28 15:32:44 +02:00
remove_file $MYSQLTEST_VARDIR/tmp/t2;
2007-05-08 22:23:16 +02:00
drop table t1,t2;
2007-07-06 00:43:23 +02:00
#
# Bug#29442: SELECT INTO OUTFILE FIELDS ENCLOSED BY digit, minus sign etc
# corrupts non-string fields containing this character.
#
CREATE TABLE t1 (c1 INT, c2 TIMESTAMP, c3 REAL, c4 DOUBLE);
INSERT INTO t1 (c1, c2, c3, c4) VALUES (10, '1970-02-01 01:02:03', 1.1E-100, 1.1E+100);
SELECT * FROM t1;
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
eval SELECT * INTO OUTFILE '$MYSQLTEST_VARDIR/tmp/t1' FIELDS ENCLOSED BY '-' FROM t1;
2007-08-28 15:32:44 +02:00
cat_file $MYSQLTEST_VARDIR/tmp/t1;
echo EOF;
2007-07-06 00:43:23 +02:00
TRUNCATE t1;
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
eval LOAD DATA INFILE '$MYSQLTEST_VARDIR/tmp/t1' INTO TABLE t1 FIELDS ENCLOSED BY '-';
SELECT * FROM t1;
2007-08-28 15:32:44 +02:00
remove_file $MYSQLTEST_VARDIR/tmp/t1;
2007-07-06 00:43:23 +02:00
DROP TABLE t1;
2008-03-28 16:59:13 +01:00
###########################################################################
--echo
--echo # --
--echo # -- Bug#35469: server crash with LOAD DATA INFILE to a VIEW.
--echo # --
--echo
--disable_warnings
DROP TABLE IF EXISTS t1;
DROP VIEW IF EXISTS v1;
DROP VIEW IF EXISTS v2;
DROP VIEW IF EXISTS v3;
--enable_warnings
--echo
CREATE TABLE t1(c1 INT, c2 VARCHAR(255));
--echo
CREATE VIEW v1 AS SELECT * FROM t1;
CREATE VIEW v2 AS SELECT 1 + 2 AS c0, c1, c2 FROM t1;
CREATE VIEW v3 AS SELECT 1 AS d1, 2 AS d2;
--echo
2008-04-03 21:40:10 +02:00
LOAD DATA INFILE '../../std_data/bug35469.dat' INTO TABLE v1
2008-03-28 16:59:13 +01:00
FIELDS ESCAPED BY '\\'
TERMINATED BY ','
ENCLOSED BY '"'
LINES TERMINATED BY '\n' (c1, c2);
--echo
SELECT * FROM t1;
--echo
SELECT * FROM v1;
--echo
DELETE FROM t1;
--echo
2008-04-03 21:40:10 +02:00
LOAD DATA INFILE '../../std_data/bug35469.dat' INTO TABLE v2
2008-03-28 16:59:13 +01:00
FIELDS ESCAPED BY '\\'
TERMINATED BY ','
ENCLOSED BY '"'
LINES TERMINATED BY '\n' (c1, c2);
--echo
SELECT * FROM t1;
--echo
SELECT * FROM v2;
--echo
DELETE FROM t1;
--echo
--error ER_LOAD_DATA_INVALID_COLUMN
2008-04-03 21:40:10 +02:00
LOAD DATA INFILE '../../std_data/bug35469.dat' INTO TABLE v2
2008-03-28 16:59:13 +01:00
FIELDS ESCAPED BY '\\'
TERMINATED BY ','
ENCLOSED BY '"'
LINES TERMINATED BY '\n' (c0, c2);
--echo
--error ER_NON_UPDATABLE_TABLE
2008-04-03 21:40:10 +02:00
LOAD DATA INFILE '../../std_data/bug35469.dat' INTO TABLE v3
2008-03-28 16:59:13 +01:00
FIELDS ESCAPED BY '\\'
TERMINATED BY ','
ENCLOSED BY '"'
LINES TERMINATED BY '\n' (d1, d2);
--echo
DROP TABLE t1;
DROP VIEW v1;
DROP VIEW v2;
DROP VIEW v3;
--echo
--echo # -- End of Bug#35469.
2008-09-17 08:34:00 +02:00
2008-03-28 16:59:13 +01:00
###########################################################################
2008-09-17 08:34:00 +02:00
#
# Bug#37114: sql_mode NO_BACKSLASH_ESCAPES does not work properly with
# LOAD DATA INFILE
#
# - For each plain "SELECT id,...", the 1st pair ("before" SELECT...OUTFILE,
# LOAD...INFILE) and the 2nd pair of lines ("after") in the result should
# look the same, otherwise we broke the dumpe/restore cycle!
#
# - the \r is always { '\\', 'r' } in memory, but on-disk format changes
#
# - the \t is { '\t' } or { '\\', 't' } in memory depending on whether \
# is magic (that is, NO_BACKSLASH_ESCAPES is not set) at INSERT-time.
# on-disk format varies.
#
# - while INFILE/OUTFILE behaviour changes according to NO_BACKSLASH_ESCAPES,
# we can override these defaults using ESCAPED BY '...'
# 1: NO_BACKSLASH_ESCAPES default, \ on-disk: \,t,x,\r
# 2: NO_BACKSLASH_ESCAPES override, \\ on-disk: \,\,t,x,\,\,r
# 3: !NO_BACKSLASH_ESCAPES default, \\ on-disk: tab,\,\,r
# 3: !NO_BACKSLASH_ESCAPES override, \ on-disk: tab,\,r
--echo Bug#37114
SET SESSION character_set_client=latin1;
SET SESSION character_set_server=latin1;
SET SESSION character_set_connection=latin1;
SET @OLD_SQL_MODE=@@SESSION.SQL_MODE;
# 0. test LOAD DATA INFILE first; if that works, all issues in
# SELECT INTO OUTFILE / LOAD DATA INFILE cycles below are
# arguably in the saving.
--echo test LOAD DATA INFILE
--let $file=$MYSQLTEST_VARDIR/tmp/bug37114.txt
--let $file2=$MYSQLTEST_VARDIR/tmp/bug37114_out.txt
2008-09-18 11:24:50 +02:00
SET sql_mode = '';
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
--eval SELECT '1 \\\\aa\n' INTO DUMPFILE '$file'
2008-09-17 08:34:00 +02:00
CREATE TABLE t1 (id INT, val1 CHAR(3)) ENGINE=MyISAM;
SET sql_mode = 'NO_BACKSLASH_ESCAPES';
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
2008-09-18 11:24:50 +02:00
--eval LOAD DATA INFILE '$file' REPLACE INTO TABLE t1 FIELDS TERMINATED BY ' '
2008-09-17 08:34:00 +02:00
SELECT * FROM t1;
# show we can write this with OUTFILE, forcing the parameters for now
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
--eval SELECT * INTO OUTFILE '$file2' FIELDS ESCAPED BY '' TERMINATED BY ' ' FROM t1
--diff_files $file $file2
--remove_file $file2
# now show the OUTFILE defaults are correct with NO_BACKSLASH_ESCAPES
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
--eval SELECT * INTO OUTFILE '$file2' FIELDS TERMINATED BY ' ' FROM t1
--diff_files $file $file2
--remove_file $file2
INSERT INTO t1 (id, val1) VALUES (1, '\aa');
SELECT * FROM t1;
SET sql_mode='';
INSERT INTO t1 (id, val1) VALUES (1, '\aa');
SELECT * FROM t1;
DROP TABLE t1;
--remove_file $file
--echo test SELECT INTO OUTFILE
CREATE TABLE t1 (id INT PRIMARY KEY, val1 CHAR(4));
CREATE TABLE t2 LIKE t1;
# 1. with NO_BACKSLASH_ESCAPES on
SET sql_mode = '';
INSERT INTO t1 (id, val1) VALUES (5, '\ttab');
INSERT INTO t1 (id, val1) VALUES (4, '\\r');
SET sql_mode = 'NO_BACKSLASH_ESCAPES';
INSERT INTO t1 (id, val1) VALUES (3, '\tx');
--echo 1.1 NO_BACKSLASH_ESCAPES, use defaults for ESCAPED BY
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
--eval SELECT * INTO OUTFILE '$file' FIELDS TERMINATED BY ' ' FROM t1 ORDER BY id
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
--eval LOAD DATA INFILE '$file' INTO TABLE t2 FIELDS TERMINATED BY ' '
SELECT 'before' AS t, id, val1, hex(val1) FROM t1 UNION
SELECT 'after' AS t, id, val1, hex(val1) FROM t2 ORDER BY id,t DESC;
TRUNCATE t2;
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
eval SELECT LOAD_FILE("$file");
--remove_file $file
--echo 1.2 NO_BACKSLASH_ESCAPES, override defaults for ESCAPED BY
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
--eval SELECT * INTO OUTFILE '$file' FIELDS ESCAPED BY '\' TERMINATED BY ' ' FROM t1 ORDER BY id
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
--eval LOAD DATA INFILE '$file' INTO TABLE t2 FIELDS ESCAPED BY '\' TERMINATED BY ' '
SELECT 'before' AS t, id, val1, hex(val1) FROM t1 UNION
SELECT 'after' AS t, id, val1, hex(val1) FROM t2 ORDER BY id,t DESC;
TRUNCATE t2;
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
eval SELECT LOAD_FILE("$file");
--remove_file $file
# 2. with NO_BACKSLASH_ESCAPES off
SET sql_mode = '';
--echo 2.1 !NO_BACKSLASH_ESCAPES, use defaults for ESCAPED BY
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
--eval SELECT * INTO OUTFILE '$file' FIELDS TERMINATED BY ' ' FROM t1 ORDER BY id
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
--eval LOAD DATA INFILE '$file' INTO TABLE t2 FIELDS TERMINATED BY ' '
SELECT 'before' AS t, id, val1, hex(val1) FROM t1 UNION
SELECT 'after' AS t, id, val1, hex(val1) FROM t2 ORDER BY id,t DESC;
TRUNCATE t2;
SET sql_mode = 'NO_BACKSLASH_ESCAPES';
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
eval SELECT LOAD_FILE("$file");
--remove_file $file
SET sql_mode = '';
--echo 2.2 !NO_BACKSLASH_ESCAPES, override defaults for ESCAPED BY
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
--eval SELECT * INTO OUTFILE '$file' FIELDS ESCAPED BY '' TERMINATED BY ' ' FROM t1 ORDER BY id
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
--eval LOAD DATA INFILE '$file' INTO TABLE t2 FIELDS ESCAPED BY '' TERMINATED BY ' '
SELECT 'before' AS t, id, val1, hex(val1) FROM t1 UNION
SELECT 'after' AS t, id, val1, hex(val1) FROM t2 ORDER BY id,t DESC;
TRUNCATE t2;
SET sql_mode = 'NO_BACKSLASH_ESCAPES';
--replace_result $MYSQLTEST_VARDIR MYSQLTEST_VARDIR
eval SELECT LOAD_FILE("$file");
--remove_file $file
# clean up
set session sql_mode=@OLD_SQL_MODE;
DROP TABLE t1,t2;
2010-03-30 14:03:50 +02:00
--echo #
--echo # Bug #51893: crash with certain characters given to load_file
--echo # function on windows
--echo #
select load_file(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
2008-09-17 08:34:00 +02:00
--echo End of 5.0 tests
2008-09-17 14:54:50 +02:00
2006-01-18 09:55:38 +01:00
#
# Bug#12448 LOAD DATA / SELECT INTO OUTFILE
# doesn't work with multibyte path name
#
CREATE TABLE t1 (a int);
INSERT INTO t1 VALUES (1);
SET NAMES latin1;
SET character_set_filesystem=filename;
select @@character_set_filesystem;
SELECT * INTO OUTFILE 't-1' FROM t1;
DELETE FROM t1;
LOAD DATA INFILE 't-1' INTO TABLE t1;
SELECT * FROM t1;
DELETE FROM t1;
SET character_set_filesystem=latin1;
select @@character_set_filesystem;
LOAD DATA INFILE 't@002d1' INTO TABLE t1;
SELECT * FROM t1;
DROP TABLE t1;
2007-12-12 18:19:24 +01:00
let $MYSQLD_DATADIR= `select @@datadir`;
remove_file $MYSQLD_DATADIR/test/t@002d1;
2006-01-18 09:55:38 +01:00
SET character_set_filesystem=default;
select @@character_set_filesystem;
2008-09-17 14:54:50 +02:00
2010-03-23 16:07:00 +01:00
--echo #
--echo # Bug #51850: crash/memory overlap when using load data infile and set
--echo # col equal to itself!
--echo #
CREATE TABLE t1(col0 LONGBLOB);
SELECT 'test' INTO OUTFILE 't1.txt';
LOAD DATA INFILE 't1.txt' IGNORE INTO TABLE t1 SET col0=col0;
SELECT * FROM t1;
DROP TABLE t1;
let $MYSQLD_DATADIR= `select @@datadir`;
remove_file $MYSQLD_DATADIR/test/t1.txt;
2008-09-17 14:54:50 +02:00
2010-04-07 17:17:56 +02:00
--echo #
--echo # Bug #52512 : Assertion `! is_set()' in
--echo # Diagnostics_area::set_ok_status on LOAD DATA
--echo #
connect (con1,localhost,root,,test);
CREATE TABLE t1 (id INT NOT NULL);
--send LOAD DATA LOCAL INFILE 'tb.txt' INTO TABLE t1
# please keep this is a spearate test file : it's important to have no
# commands after this one
connection default;
dirty_close con1;
connect (con1,localhost,root,,test);
DROP TABLE t1;
connection default;
disconnect con1;
2010-07-14 13:54:51 +02:00
--echo #
--echo # Bug #51876 : crash/memory underrun when loading data with ucs2
--echo # and reverse() function
--echo #
--echo # Problem # 1 (original report): wrong parsing of ucs2 data
SELECT '00' UNION SELECT '10' INTO OUTFILE 'tmpp.txt';
CREATE TABLE t1(a INT);
LOAD DATA INFILE 'tmpp.txt' INTO TABLE t1 CHARACTER SET ucs2
(@b) SET a=REVERSE(@b);
--echo # should return 2 zeroes (as the value is truncated)
SELECT * FROM t1;
DROP TABLE t1;
let $MYSQLD_DATADIR= `select @@datadir`;
remove_file $MYSQLD_DATADIR/test/tmpp.txt;
--echo # Problem # 2 : if you write and read ucs2 data to a file they're lost
SELECT '00' UNION SELECT '10' INTO OUTFILE 'tmpp2.txt' CHARACTER SET ucs2;
CREATE TABLE t1(a INT);
LOAD DATA INFILE 'tmpp2.txt' INTO TABLE t1 CHARACTER SET ucs2
(@b) SET a=REVERSE(@b);
--echo # should return 0 and 1 (10 reversed)
SELECT * FROM t1;
DROP TABLE t1;
let $MYSQLD_DATADIR= `select @@datadir`;
remove_file $MYSQLD_DATADIR/test/tmpp2.txt;
2008-09-17 14:54:50 +02:00
--echo End of 5.1 tests
