Merge branch 'master' into latin1-utf8mb4

addresses #290

Note: there is currently no issue backfilling the ghost table when the
characterset changes, likely because it's a insert-into-select-from and
it all occurs within mysql.

However, when applying DML events (UPDATE, DELETE, etc) the values are
sprintf'd into a prepared statement and due to the possibility of
migrating text column data containing invalid characters in the
destination charset, a conversion step is often necessary.

For example, when migrating a table/column from latin1 to utf8mb4, the
latin1 column may contain characters that are invalid single-byte utf8
characters. Characters in the \x80-\xFF range are most common. When
written to utf8mb4 column without conversion, they fail as they do not
exist in the utf8 codepage.

Converting these texts/characters to the destination charset using
convert(? using {charset}) will convert appropriately and the
update/replace will succeed.

I only point out the "Note:" above because there are two tests added
for this: latin1text-to-utf8mb4 and latin1text-to-ut8mb4-insert

The former is a test that fails prior to this commit. The latter is a
test that succeeds prior to this comment. Both are affected by the code
in this commit.

convert text to original charset, then destination

converting text first to the original charset and then to the
destination charset produces the most consistent results, as inserting
the binary into a utf8-charset column may encounter an error if there is
no prior context of latin1 encoding.

mysql> select hex(convert(char(189) using utf8mb4));
+---------------------------------------+
| hex(convert(char(189) using utf8mb4)) |
+---------------------------------------+
|                                       |
+---------------------------------------+
1 row in set, 1 warning (0.00 sec)

mysql> select hex(convert(convert(char(189) using latin1) using utf8mb4));
+-------------------------------------------------------------+
| hex(convert(convert(char(189) using latin1) using utf8mb4)) |
+-------------------------------------------------------------+
| C2BD                                                        |
+-------------------------------------------------------------+
1 row in set (0.00 sec)

as seen in this failure on 5.5.62

 Error 1300: Invalid utf8mb4 character string: 'BD'; query=
			replace /* gh-ost `test`.`_gh_ost_test_gho` */ into
				`test`.`_gh_ost_test_gho`
					(`id`, `t`)
				values
					(?, convert(? using utf8mb4))

go/logic/inspect.go

@@ -191,6 +191,9 @@ func (this *Inspector) inspectOriginalAndGhostTables() (err error) {
 			this.migrationContext.MappedSharedColumns.SetEnumToTextConversion(column.Name)
 			this.migrationContext.MappedSharedColumns.SetEnumValues(column.Name, column.EnumValues)
 		}
+		if column.Name == mappedColumn.Name && column.Charset != mappedColumn.Charset {
+			this.migrationContext.MappedSharedColumns.SetCharsetConversion(column.Name, column.Charset, mappedColumn.Charset)
+		}
 	}
 
 	for _, column := range this.migrationContext.UniqueKey.Columns.Columns() {

go/sql/builder.go

@@ -42,6 +42,8 @@ func buildColumnsPreparedValues(columns *ColumnList) []string {
 			token = fmt.Sprintf("ELT(?, %s)", column.EnumValues)
 		} else if column.Type == JSONColumnType {
 			token = "convert(? using utf8mb4)"
+		} else if column.charsetConversion != nil {
+			token = fmt.Sprintf("convert(convert(? using %s) using %s)", column.charsetConversion.FromCharset, column.charsetConversion.ToCharset)
 		} else {
 			token = "?"
 		}
@@ -114,6 +116,8 @@ func BuildSetPreparedClause(columns *ColumnList) (result string, err error) {
 			setToken = fmt.Sprintf("%s=ELT(?, %s)", EscapeName(column.Name), column.EnumValues)
 		} else if column.Type == JSONColumnType {
 			setToken = fmt.Sprintf("%s=convert(? using utf8mb4)", EscapeName(column.Name))
+		} else if column.charsetConversion != nil {
+			setToken = fmt.Sprintf("%s=convert(convert(? using %s) using %s)", EscapeName(column.Name), column.charsetConversion.FromCharset, column.charsetConversion.ToCharset)
 		} else {
 			setToken = fmt.Sprintf("%s=?", EscapeName(column.Name))
 		}

go/sql/types.go

@@ -32,6 +32,11 @@ type TimezoneConversion struct {
 	ToTimezone string
 }
 
+type CharsetConversion struct {
+	ToCharset   string
+	FromCharset string
+}
+
 type Column struct {
 	Name                 string
 	IsUnsigned           bool
@@ -40,6 +45,7 @@ type Column struct {
 	EnumValues           string
 	timezoneConversion   *TimezoneConversion
 	enumToTextConversion bool
+	charsetConversion    *CharsetConversion
 	// add Octet length for binary type, fix bytes with suffix "00" get clipped in mysql binlog.
 	// https://github.com/github/gh-ost/issues/909
 	BinaryOctetLength uint
@@ -211,6 +217,14 @@ func (this *ColumnList) SetEnumValues(columnName string, enumValues string) {
 	this.GetColumn(columnName).EnumValues = enumValues
 }
 
+func (this *ColumnList) SetCharsetConversion(columnName string, fromCharset string, toCharset string) {
+	this.GetColumn(columnName).charsetConversion = &CharsetConversion{FromCharset: fromCharset, ToCharset: toCharset}
+}
+
+func (this *ColumnList) IsCharsetConversion(columnName string) bool {
+	return this.GetColumn(columnName).charsetConversion != nil
+}
+
 func (this *ColumnList) String() string {
 	return strings.Join(this.Names(), ",")
 }

localtests/convert-utf8mb4/create.sql

@@ -7,7 +7,7 @@ create table gh_ost_test (
   primary key(id)
 ) auto_increment=1;
 
-insert into gh_ost_test values (null, 'átesting');
+insert into gh_ost_test values (null, 'átesting', '', '');
 
 
 insert into gh_ost_test values (null, 'Hello world, Καλημέρα κόσμε, コンニチハ', 'átesting0', 'initial');

localtests/latin1text-to-utf8mb4/create.sql

@@ -0,0 +1,24 @@
+drop table if exists gh_ost_test;
+create table gh_ost_test (
+  id int auto_increment,
+  t text charset latin1 collate latin1_swedish_ci,
+  primary key(id)
+) auto_increment=1 charset latin1 collate latin1_swedish_ci;
+
+insert into gh_ost_test values (null, char(189));
+
+drop event if exists gh_ost_test;
+delimiter ;;
+create event gh_ost_test
+  on schedule every 1 second
+  starts current_timestamp
+  ends current_timestamp + interval 60 second
+  on completion not preserve
+  enable
+  do
+begin
+  insert into gh_ost_test values (null, md5(rand()));
+  insert into gh_ost_test values (null, char(189));
+  update gh_ost_test set t=char(190) order by id desc limit 1;
+  delete from gh_ost_test where t=char(190);
+end ;;

localtests/latin1text-to-utf8mb4/extra_args

@@ -0,0 +1 @@
+--alter "convert to character set utf8mb4 collate utf8mb4_unicode_ci"

localtests/latin1text-to-utf8mb4/ignored_versions

@@ -0,0 +1 @@
+(5.5)