diff --git a/innobase/include/rem0rec.h b/innobase/include/rem0rec.h index 1d15b8d1c77..69b397c9682 100644 --- a/innobase/include/rem0rec.h +++ b/innobase/include/rem0rec.h @@ -312,6 +312,15 @@ rec_offs_nth_extern( const ulint* offsets,/* in: array returned by rec_get_offsets() */ ulint n); /* in: nth field */ /********************************************************** +Returns nonzero if the SQL NULL bit is set in nth field of rec. */ +UNIV_INLINE +ulint +rec_offs_nth_sql_null( +/*==================*/ + /* out: nonzero if SQL NULL */ + const ulint* offsets,/* in: array returned by rec_get_offsets() */ + ulint n); /* in: nth field */ +/********************************************************** Gets the physical size of a field. */ UNIV_INLINE ulint diff --git a/innobase/include/rem0rec.ic b/innobase/include/rem0rec.ic index e2dceb6bae5..9c24f385f4f 100644 --- a/innobase/include/rem0rec.ic +++ b/innobase/include/rem0rec.ic @@ -954,6 +954,22 @@ rec_offs_nth_extern( & REC_OFFS_EXTERNAL)); } +/********************************************************** +Returns nonzero if the SQL NULL bit is set in nth field of rec. */ +UNIV_INLINE +ulint +rec_offs_nth_sql_null( +/*==================*/ + /* out: nonzero if SQL NULL */ + const ulint* offsets,/* in: array returned by rec_get_offsets() */ + ulint n) /* in: nth field */ +{ + ut_ad(rec_offs_validate(NULL, NULL, offsets)); + ut_ad(n < rec_offs_n_fields(offsets)); + return(UNIV_UNLIKELY(rec_offs_base(offsets)[1 + n] + & REC_OFFS_SQL_NULL)); +} + /********************************************************** Gets the physical size of a field. */ UNIV_INLINE diff --git a/innobase/row/row0upd.c b/innobase/row/row0upd.c index 4f44dbeae67..ff1ad1dfd05 100644 --- a/innobase/row/row0upd.c +++ b/innobase/row/row0upd.c @@ -395,6 +395,18 @@ row_upd_changes_field_size_or_external( old_len = rec_offs_nth_size(offsets, upd_field->field_no); + if (rec_offs_comp(offsets) + && rec_offs_nth_sql_null(offsets, upd_field->field_no)) { + /* Note that in the compact table format, for a + variable length field, an SQL NULL will use zero + bytes in the offset array at the start of the physical + record, but a zero-length value (empty string) will + use one byte! Thus, we cannot use update-in-place + if we update an SQL NULL varchar to an empty string! */ + + old_len = UNIV_SQL_NULL; + } + if (old_len != new_len) { return(TRUE); diff --git a/mysql-test/r/innodb.result b/mysql-test/r/innodb.result index a66259ff5f4..dc4893c3bfa 100644 --- a/mysql-test/r/innodb.result +++ b/mysql-test/r/innodb.result @@ -2663,3 +2663,112 @@ rollback; rollback; drop table t1; drop function f1; +create table t1 ( +a int, b char(10), c char(10), filler char(10), primary key(a, b(2)), unique key (a, c(2)) +) character set utf8 engine = innodb; +create table t2 ( +a int, b char(10), c char(10), filler char(10), primary key(a, b(2)), unique key (a, c(2)) +) character set ucs2 engine = innodb; +insert into t1 values (1,'abcdefg','abcdefg','one'); +insert into t1 values (2,'ijkilmn','ijkilmn','two'); +insert into t1 values (3,'qrstuvw','qrstuvw','three'); +insert into t1 values (4,_utf8 0xe880bd,_utf8 0xe880bd,'four'); +insert into t1 values (4,_utf8 0x5b,_utf8 0x5b,'five'); +insert into t1 values (4,_utf8 0xe880bde880bd,_utf8 0xe880bde880bd,'six'); +insert into t1 values (4,_utf8 0xe880bdD0B1e880bd,_utf8 0xe880bdD0B1e880bd,'seven'); +insert into t1 values (4,_utf8 0xD0B1,_utf8 0xD0B1,'eight'); +insert into t2 values (1,'abcdefg','abcdefg','one'); +insert into t2 values (2,'ijkilmn','ijkilmn','two'); +insert into t2 values (3,'qrstuvw','qrstuvw','three'); +insert into t2 values (4,_ucs2 0x00e400,_ucs2 0x00e400,'four'); +insert into t2 values (4,_ucs2 0x00640065,_ucs2 0x00640065,'five'); +insert into t2 values (4,_ucs2 0x00e400e50068,_ucs2 0x00e400e50068,'six'); +insert into t2 values (4,_ucs2 0x01fc,_ucs2 0x01fc,'seven'); +insert into t2 values (4,_ucs2 0x0120,_ucs2 0x0120,'eight'); +insert into t2 values (4,_ucs2 0x0563,_ucs2 0x0563,'ten'); +insert into t2 values (4,_ucs2 0x05630563,_ucs2 0x05630563,'eleven'); +insert into t2 values (4,_ucs2 0x0563001fc0563,_ucs2 0x0563001fc0563,'point'); +insert into t2 values (4,_ucs2 0x05612020,_ucs2 0x05612020,'taken'); +drop table t1; +drop table t2; +create table t1 ( +a int, b varchar(10), c varchar(10), filler varchar(10), primary key(a, b(2)), unique key (a, c(2)) +) character set utf8 engine = innodb; +create table t2 ( +a int, b varchar(10), c varchar(10), filler varchar(10), primary key(a, b(2)), unique key (a, c(2)) +) character set ucs2 engine = innodb; +insert into t1 values (1,'abcdefg','abcdefg','one'); +insert into t1 values (2,'ijkilmn','ijkilmn','two'); +insert into t1 values (3,'qrstuvw','qrstuvw','three'); +insert into t1 values (4,_utf8 0xe880bd,_utf8 0xe880bd,'four'); +insert into t1 values (4,_utf8 0x5b,_utf8 0x5b,'five'); +insert into t1 values (4,_utf8 0xe880bde880bd,_utf8 0xe880bde880bd,'six'); +insert into t1 values (4,_utf8 0xe880bdD0B1e880bd,_utf8 0xe880bdD0B1e880bd,'seven'); +insert into t1 values (4,_utf8 0xD0B1,_utf8 0xD0B1,'eight'); +insert into t2 values (1,'abcdefg','abcdefg','one'); +insert into t2 values (2,'ijkilmn','ijkilmn','two'); +insert into t2 values (3,'qrstuvw','qrstuvw','three'); +insert into t2 values (4,_ucs2 0x00e400,_ucs2 0x00e400,'four'); +insert into t2 values (4,_ucs2 0x00640065,_ucs2 0x00640065,'five'); +insert into t2 values (4,_ucs2 0x00e400e50068,_ucs2 0x00e400e50068,'six'); +insert into t2 values (4,_ucs2 0x01fc,_ucs2 0x01fc,'seven'); +insert into t2 values (4,_ucs2 0x0120,_ucs2 0x0120,'eight'); +insert into t2 values (4,_ucs2 0x0563,_ucs2 0x0563,'ten'); +insert into t2 values (4,_ucs2 0x05630563,_ucs2 0x05630563,'eleven'); +insert into t2 values (4,_ucs2 0x0563001fc0563,_ucs2 0x0563001fc0563,'point'); +insert into t2 values (4,_ucs2 0x05612020,_ucs2 0x05612020,'taken'); +drop table t1; +drop table t2; +create table t1 ( +a int, b text(10), c text(10), filler text(10), primary key(a, b(2)), unique key (a, c(2)) +) character set utf8 engine = innodb; +create table t2 ( +a int, b text(10), c text(10), filler text(10), primary key(a, b(2)), unique key (a, c(2)) +) character set ucs2 engine = innodb; +insert into t1 values (1,'abcdefg','abcdefg','one'); +insert into t1 values (2,'ijkilmn','ijkilmn','two'); +insert into t1 values (3,'qrstuvw','qrstuvw','three'); +insert into t1 values (4,_utf8 0xe880bd,_utf8 0xe880bd,'four'); +insert into t1 values (4,_utf8 0x5b,_utf8 0x5b,'five'); +insert into t1 values (4,_utf8 0xe880bde880bd,_utf8 0xe880bde880bd,'six'); +insert into t1 values (4,_utf8 0xe880bdD0B1e880bd,_utf8 0xe880bdD0B1e880bd,'seven'); +insert into t1 values (4,_utf8 0xD0B1,_utf8 0xD0B1,'eight'); +insert into t2 values (1,'abcdefg','abcdefg','one'); +insert into t2 values (2,'ijkilmn','ijkilmn','two'); +insert into t2 values (3,'qrstuvw','qrstuvw','three'); +insert into t2 values (4,_ucs2 0x00e400,_ucs2 0x00e400,'four'); +insert into t2 values (4,_ucs2 0x00640065,_ucs2 0x00640065,'five'); +insert into t2 values (4,_ucs2 0x00e400e50068,_ucs2 0x00e400e50068,'six'); +insert into t2 values (4,_ucs2 0x01fc,_ucs2 0x01fc,'seven'); +insert into t2 values (4,_ucs2 0x0120,_ucs2 0x0120,'eight'); +insert into t2 values (4,_ucs2 0x0563,_ucs2 0x0563,'ten'); +insert into t2 values (4,_ucs2 0x05630563,_ucs2 0x05630563,'eleven'); +insert into t2 values (4,_ucs2 0x0563001fc0563,_ucs2 0x0563001fc0563,'point'); +insert into t2 values (4,_ucs2 0x05612020,_ucs2 0x05612020,'taken'); +drop table t1; +drop table t2; +create table t1 ( +a int, b blob(10), c blob(10), filler blob(10), primary key(a, b(2)), unique key (a, c(2)) +) character set utf8 engine = innodb; +create table t2 ( +a int, b blob(10), c blob(10), filler blob(10), primary key(a, b(2)), unique key (a, c(2)) +) character set ucs2 engine = innodb; +insert into t1 values (1,'abcdefg','abcdefg','one'); +insert into t1 values (2,'ijkilmn','ijkilmn','two'); +insert into t1 values (3,'qrstuvw','qrstuvw','three'); +insert into t1 values (4,_utf8 0xe880bd,_utf8 0xe880bd,'four'); +insert into t1 values (4,_utf8 0x5b,_utf8 0x5b,'five'); +insert into t1 values (4,_utf8 0xD0B1,_utf8 0xD0B1,'eight'); +insert into t2 values (1,'abcdefg','abcdefg','one'); +insert into t2 values (2,'ijkilmn','ijkilmn','two'); +insert into t2 values (3,'qrstuvw','qrstuvw','three'); +insert into t2 values (4,_ucs2 0x00e400,_ucs2 0x00e400,'four'); +insert into t2 values (4,_ucs2 0x00640065,_ucs2 0x00640065,'five'); +insert into t2 values (4,_ucs2 0x00e400e50068,_ucs2 0x00e400e50068,'six'); +insert into t2 values (4,_ucs2 0x01fc,_ucs2 0x01fc,'seven'); +insert into t2 values (4,_ucs2 0x0120,_ucs2 0x0120,'eight'); +insert into t2 values (4,_ucs2 0x0563,_ucs2 0x0563,'ten'); +insert into t2 values (4,_ucs2 0x05612020,_ucs2 0x05612020,'taken'); +drop table t1; +drop table t2; +commit; diff --git a/mysql-test/t/innodb.test b/mysql-test/t/innodb.test index 5a45b3524ac..cf0e08e2e66 100644 --- a/mysql-test/t/innodb.test +++ b/mysql-test/t/innodb.test @@ -1635,3 +1635,119 @@ drop function f1; disconnect a; disconnect b; +# +# BUG 14056 Column prefix index on UTF-8 primary key column causes: Can't find record.. +# + +create table t1 ( + a int, b char(10), c char(10), filler char(10), primary key(a, b(2)), unique key (a, c(2)) +) character set utf8 engine = innodb; +create table t2 ( + a int, b char(10), c char(10), filler char(10), primary key(a, b(2)), unique key (a, c(2)) +) character set ucs2 engine = innodb; +insert into t1 values (1,'abcdefg','abcdefg','one'); +insert into t1 values (2,'ijkilmn','ijkilmn','two'); +insert into t1 values (3,'qrstuvw','qrstuvw','three'); +insert into t1 values (4,_utf8 0xe880bd,_utf8 0xe880bd,'four'); +insert into t1 values (4,_utf8 0x5b,_utf8 0x5b,'five'); +insert into t1 values (4,_utf8 0xe880bde880bd,_utf8 0xe880bde880bd,'six'); +insert into t1 values (4,_utf8 0xe880bdD0B1e880bd,_utf8 0xe880bdD0B1e880bd,'seven'); +insert into t1 values (4,_utf8 0xD0B1,_utf8 0xD0B1,'eight'); +insert into t2 values (1,'abcdefg','abcdefg','one'); +insert into t2 values (2,'ijkilmn','ijkilmn','two'); +insert into t2 values (3,'qrstuvw','qrstuvw','three'); +insert into t2 values (4,_ucs2 0x00e400,_ucs2 0x00e400,'four'); +insert into t2 values (4,_ucs2 0x00640065,_ucs2 0x00640065,'five'); +insert into t2 values (4,_ucs2 0x00e400e50068,_ucs2 0x00e400e50068,'six'); +insert into t2 values (4,_ucs2 0x01fc,_ucs2 0x01fc,'seven'); +insert into t2 values (4,_ucs2 0x0120,_ucs2 0x0120,'eight'); +insert into t2 values (4,_ucs2 0x0563,_ucs2 0x0563,'ten'); +insert into t2 values (4,_ucs2 0x05630563,_ucs2 0x05630563,'eleven'); +insert into t2 values (4,_ucs2 0x0563001fc0563,_ucs2 0x0563001fc0563,'point'); +insert into t2 values (4,_ucs2 0x05612020,_ucs2 0x05612020,'taken'); +drop table t1; +drop table t2; + +create table t1 ( + a int, b varchar(10), c varchar(10), filler varchar(10), primary key(a, b(2)), unique key (a, c(2)) +) character set utf8 engine = innodb; +create table t2 ( + a int, b varchar(10), c varchar(10), filler varchar(10), primary key(a, b(2)), unique key (a, c(2)) +) character set ucs2 engine = innodb; +insert into t1 values (1,'abcdefg','abcdefg','one'); +insert into t1 values (2,'ijkilmn','ijkilmn','two'); +insert into t1 values (3,'qrstuvw','qrstuvw','three'); +insert into t1 values (4,_utf8 0xe880bd,_utf8 0xe880bd,'four'); +insert into t1 values (4,_utf8 0x5b,_utf8 0x5b,'five'); +insert into t1 values (4,_utf8 0xe880bde880bd,_utf8 0xe880bde880bd,'six'); +insert into t1 values (4,_utf8 0xe880bdD0B1e880bd,_utf8 0xe880bdD0B1e880bd,'seven'); +insert into t1 values (4,_utf8 0xD0B1,_utf8 0xD0B1,'eight'); +insert into t2 values (1,'abcdefg','abcdefg','one'); +insert into t2 values (2,'ijkilmn','ijkilmn','two'); +insert into t2 values (3,'qrstuvw','qrstuvw','three'); +insert into t2 values (4,_ucs2 0x00e400,_ucs2 0x00e400,'four'); +insert into t2 values (4,_ucs2 0x00640065,_ucs2 0x00640065,'five'); +insert into t2 values (4,_ucs2 0x00e400e50068,_ucs2 0x00e400e50068,'six'); +insert into t2 values (4,_ucs2 0x01fc,_ucs2 0x01fc,'seven'); +insert into t2 values (4,_ucs2 0x0120,_ucs2 0x0120,'eight'); +insert into t2 values (4,_ucs2 0x0563,_ucs2 0x0563,'ten'); +insert into t2 values (4,_ucs2 0x05630563,_ucs2 0x05630563,'eleven'); +insert into t2 values (4,_ucs2 0x0563001fc0563,_ucs2 0x0563001fc0563,'point'); +insert into t2 values (4,_ucs2 0x05612020,_ucs2 0x05612020,'taken'); +drop table t1; +drop table t2; + +create table t1 ( + a int, b text(10), c text(10), filler text(10), primary key(a, b(2)), unique key (a, c(2)) +) character set utf8 engine = innodb; +create table t2 ( + a int, b text(10), c text(10), filler text(10), primary key(a, b(2)), unique key (a, c(2)) +) character set ucs2 engine = innodb; +insert into t1 values (1,'abcdefg','abcdefg','one'); +insert into t1 values (2,'ijkilmn','ijkilmn','two'); +insert into t1 values (3,'qrstuvw','qrstuvw','three'); +insert into t1 values (4,_utf8 0xe880bd,_utf8 0xe880bd,'four'); +insert into t1 values (4,_utf8 0x5b,_utf8 0x5b,'five'); +insert into t1 values (4,_utf8 0xe880bde880bd,_utf8 0xe880bde880bd,'six'); +insert into t1 values (4,_utf8 0xe880bdD0B1e880bd,_utf8 0xe880bdD0B1e880bd,'seven'); +insert into t1 values (4,_utf8 0xD0B1,_utf8 0xD0B1,'eight'); +insert into t2 values (1,'abcdefg','abcdefg','one'); +insert into t2 values (2,'ijkilmn','ijkilmn','two'); +insert into t2 values (3,'qrstuvw','qrstuvw','three'); +insert into t2 values (4,_ucs2 0x00e400,_ucs2 0x00e400,'four'); +insert into t2 values (4,_ucs2 0x00640065,_ucs2 0x00640065,'five'); +insert into t2 values (4,_ucs2 0x00e400e50068,_ucs2 0x00e400e50068,'six'); +insert into t2 values (4,_ucs2 0x01fc,_ucs2 0x01fc,'seven'); +insert into t2 values (4,_ucs2 0x0120,_ucs2 0x0120,'eight'); +insert into t2 values (4,_ucs2 0x0563,_ucs2 0x0563,'ten'); +insert into t2 values (4,_ucs2 0x05630563,_ucs2 0x05630563,'eleven'); +insert into t2 values (4,_ucs2 0x0563001fc0563,_ucs2 0x0563001fc0563,'point'); +insert into t2 values (4,_ucs2 0x05612020,_ucs2 0x05612020,'taken'); +drop table t1; +drop table t2; + +create table t1 ( + a int, b blob(10), c blob(10), filler blob(10), primary key(a, b(2)), unique key (a, c(2)) +) character set utf8 engine = innodb; +create table t2 ( + a int, b blob(10), c blob(10), filler blob(10), primary key(a, b(2)), unique key (a, c(2)) +) character set ucs2 engine = innodb; +insert into t1 values (1,'abcdefg','abcdefg','one'); +insert into t1 values (2,'ijkilmn','ijkilmn','two'); +insert into t1 values (3,'qrstuvw','qrstuvw','three'); +insert into t1 values (4,_utf8 0xe880bd,_utf8 0xe880bd,'four'); +insert into t1 values (4,_utf8 0x5b,_utf8 0x5b,'five'); +insert into t1 values (4,_utf8 0xD0B1,_utf8 0xD0B1,'eight'); +insert into t2 values (1,'abcdefg','abcdefg','one'); +insert into t2 values (2,'ijkilmn','ijkilmn','two'); +insert into t2 values (3,'qrstuvw','qrstuvw','three'); +insert into t2 values (4,_ucs2 0x00e400,_ucs2 0x00e400,'four'); +insert into t2 values (4,_ucs2 0x00640065,_ucs2 0x00640065,'five'); +insert into t2 values (4,_ucs2 0x00e400e50068,_ucs2 0x00e400e50068,'six'); +insert into t2 values (4,_ucs2 0x01fc,_ucs2 0x01fc,'seven'); +insert into t2 values (4,_ucs2 0x0120,_ucs2 0x0120,'eight'); +insert into t2 values (4,_ucs2 0x0563,_ucs2 0x0563,'ten'); +insert into t2 values (4,_ucs2 0x05612020,_ucs2 0x05612020,'taken'); +drop table t1; +drop table t2; +commit; diff --git a/sql/ha_innodb.cc b/sql/ha_innodb.cc index 455b54361f0..a7957ee3cbf 100644 --- a/sql/ha_innodb.cc +++ b/sql/ha_innodb.cc @@ -2872,6 +2872,9 @@ ha_innobase::store_key_val_for_row( ulint lenlen; ulint len; byte* data; + ulint key_len; + CHARSET_INFO* cs; + int error=0; if (is_null) { buff += key_part->length + 2; @@ -2890,8 +2893,20 @@ ha_innobase::store_key_val_for_row( /* In a column prefix index, we may need to truncate the stored value: */ - if (len > key_part->length) { - len = key_part->length; + cs = key_part->field->charset(); + + if (cs->mbmaxlen > 1 && key_part->length > 0) { + key_len = (ulint) cs->cset->well_formed_len(cs, + (const char *) data, + (const char *) data + key_part->length, + key_part->length / cs->mbmaxlen, + &error); + } else { + key_len = key_part->length; + } + + if (len > key_len) { + len = key_len; } /* The length in a key value is always stored in 2 @@ -2915,6 +2930,11 @@ ha_innobase::store_key_val_for_row( || mysql_type == FIELD_TYPE_BLOB || mysql_type == FIELD_TYPE_LONG_BLOB) { + CHARSET_INFO* cs; + ulint key_len; + ulint len; + int error=0; + ut_a(key_part->key_part_flag & HA_PART_KEY_SEG); if (is_null) { @@ -2935,8 +2955,21 @@ ha_innobase::store_key_val_for_row( indexes, and we may need to truncate the data to be stored in the key value: */ - if (blob_len > key_part->length) { - blob_len = key_part->length; + cs = key_part->field->charset(); + + if (cs->mbmaxlen > 1 && key_part->length > 0) { + key_len = (ulint) cs->cset->well_formed_len(cs, + (const char *) blob_data, + (const char *) blob_data + + key_part->length, + key_part->length / cs->mbmaxlen, + &error); + } else { + key_len = key_part->length; + } + + if (blob_len > key_len) { + blob_len = key_len; } /* MySQL reserves 2 bytes for the length and the @@ -2958,15 +2991,40 @@ ha_innobase::store_key_val_for_row( value we store may be also in a column prefix index. */ + CHARSET_INFO* cs; + ulint len; + const mysql_byte* src_start; + int error=0; + if (is_null) { buff += key_part->length; continue; } - memcpy(buff, record + key_part->offset, - key_part->length); - buff += key_part->length; + cs = key_part->field->charset(); + src_start = record + key_part->offset; + + if (key_part->length > 0 && cs->mbmaxlen > 1) { + len = (ulint) cs->cset->well_formed_len(cs, + src_start, + src_start + key_part->length, + key_part->length / cs->mbmaxlen, + &error); + } else { + len = key_part->length; + } + + memcpy(buff, src_start, len); + buff+=len; + + /* Pad the unused space with spaces */ + + if (len < key_part->length) { + len = key_part->length - len; + memset(buff, ' ', len); + buff+=len; + } } }