Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

vreplication: Move to use collations package #13566

Merged
merged 2 commits into from
Jul 20, 2023
Merged

vreplication: Move to use collations package #13566

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f2152d9
vreplication: Move to use collations package
dbussink Jul 20, 2023
5310f10
Remove GKB test
dbussink Jul 20, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 0 additions & 31 deletions go/mysql/constants.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,10 +20,6 @@ import (
"strconv"
"strings"

"golang.org/x/text/encoding"
"golang.org/x/text/encoding/charmap"
"golang.org/x/text/encoding/simplifiedchinese"

"vitess.io/vitess/go/mysql/binlog"
)

Expand Down Expand Up @@ -660,33 +656,6 @@ const (
SSQueryInterrupted = "70100"
)

// CharacterSetEncoding maps a charset name to a golang encoder.
// golang does not support encoders for all MySQL charsets.
// A charset not in this map is unsupported.
// A trivial encoding (e.g. utf8) has a `nil` encoder
var CharacterSetEncoding = map[string]encoding.Encoding{
"cp850": charmap.CodePage850,
"koi8r": charmap.KOI8R,
"latin1": charmap.Windows1252,
"latin2": charmap.ISO8859_2,
"ascii": nil,
"hebrew": charmap.ISO8859_8,
"greek": charmap.ISO8859_7,
"cp1250": charmap.Windows1250,
"gbk": simplifiedchinese.GBK,
"latin5": charmap.ISO8859_9,
"utf8": nil,
"utf8mb3": nil,
"cp866": charmap.CodePage866,
"cp852": charmap.CodePage852,
"latin7": charmap.ISO8859_13,
"utf8mb4": nil,
"cp1251": charmap.Windows1251,
"cp1256": charmap.Windows1256,
"cp1257": charmap.Windows1257,
"binary": nil,
}

// IsNum returns true if a MySQL type is a numeric value.
// It is the same as IS_NUM defined in mysql.h.
func IsNum(typ uint8) bool {
Expand Down
25 changes: 0 additions & 25 deletions go/test/endtoend/onlineddl/vrepl_suite/testdata/gbk-charset/create.sql
View file
Open in desktop

This file was deleted.

Empty file removed go/test/endtoend/onlineddl/vrepl_suite/testdata/gbk-charset/extra_args
View file
Open in desktop
Empty file.
24 changes: 16 additions & 8 deletions go/vt/vttablet/onlineddl/vrepl.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,8 @@ import (
"strconv"
"strings"

"vitess.io/vitess/go/mysql"
"vitess.io/vitess/go/mysql/collations"
"vitess.io/vitess/go/mysql/collations/charset"
"vitess.io/vitess/go/sqltypes"
"vitess.io/vitess/go/textutil"
"vitess.io/vitess/go/vt/binlog/binlogplayer"
Expand Down Expand Up @@ -497,20 +498,19 @@ func (v *VRepl) generateFilterQuery(ctx context.Context) error {
case sourceCol.Type == vrepl.StringColumnType:
// Check source and target charset/encoding. If needed, create
// a binlogdatapb.CharsetConversion entry (later written to vreplication)
fromEncoding, ok := mysql.CharacterSetEncoding[sourceCol.Charset]
if !ok {
fromCollation := collations.Local().DefaultCollationForCharset(sourceCol.Charset)
if fromCollation == nil {
return vterrors.Errorf(vtrpcpb.Code_INVALID_ARGUMENT, "Character set %s not supported for column %s", sourceCol.Charset, sourceCol.Name)
}
toEncoding, ok := mysql.CharacterSetEncoding[targetCol.Charset]
toCollation := collations.Local().DefaultCollationForCharset(targetCol.Charset)
// Let's see if target col is at all textual
if targetCol.Type == vrepl.StringColumnType && !ok {
if targetCol.Type == vrepl.StringColumnType && toCollation == nil {
return vterrors.Errorf(vtrpcpb.Code_INVALID_ARGUMENT, "Character set %s not supported for column %s", targetCol.Charset, targetCol.Name)
}
if fromEncoding == nil && toEncoding == nil && targetCol.Type != vrepl.JSONColumnType {
// Both source and target have trivial charsets

if trivialCharset(fromCollation) && trivialCharset(toCollation) && targetCol.Type != vrepl.JSONColumnType {
sb.WriteString(escapeName(name))
} else {
// encoding can be nil for trivial charsets, like utf8, ascii, binary, etc.
v.convertCharset[targetName] = &binlogdatapb.CharsetConversion{
FromCharset: sourceCol.Charset,
ToCharset: targetCol.Charset,
Expand All @@ -533,6 +533,14 @@ func (v *VRepl) generateFilterQuery(ctx context.Context) error {
return nil
}

func trivialCharset(c collations.Collation) bool {
if c == nil {
return true
}
utf8mb4Charset := charset.Charset_utf8mb4{}
return utf8mb4Charset.IsSuperset(c.Charset()) || c.ID() == collations.CollationBinaryID
}

func (v *VRepl) analyzeBinlogSource(ctx context.Context) {
bls := &binlogdatapb.BinlogSource{
Keyspace: v.keyspace,
Expand Down
20 changes: 7 additions & 13 deletions go/vt/vttablet/tabletmanager/vreplication/replicator_plan.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,12 +22,12 @@ import (
"sort"
"strings"

"vitess.io/vitess/go/mysql/collations/charset"
"vitess.io/vitess/go/vt/vttablet"

"google.golang.org/protobuf/proto"

"vitess.io/vitess/go/bytes2"
"vitess.io/vitess/go/mysql"
"vitess.io/vitess/go/mysql/collations"
vjson "vitess.io/vitess/go/mysql/json"
"vitess.io/vitess/go/sqltypes"
Expand Down Expand Up @@ -317,21 +317,15 @@ func (tp *TablePlan) isOutsidePKRange(bindvars map[string]*querypb.BindVariable,
func (tp *TablePlan) bindFieldVal(field *querypb.Field, val *sqltypes.Value) (*querypb.BindVariable, error) {
if conversion, ok := tp.ConvertCharset[field.Name]; ok && !val.IsNull() {
// Non-null string value, for which we have a charset conversion instruction
valString := val.ToString()
fromEncoding, encodingOK := mysql.CharacterSetEncoding[conversion.FromCharset]
if !encodingOK {
fromCollation := collations.Local().DefaultCollationForCharset(conversion.FromCharset)
if fromCollation == nil {
return nil, vterrors.Errorf(vtrpcpb.Code_INVALID_ARGUMENT, "Character set %s not supported for column %s", conversion.FromCharset, field.Name)
}
if fromEncoding != nil {
// As reminder, encoding can be nil for trivial charsets, like utf8 or ascii.
// encoding will be non-nil for charsets like latin1, gbk, etc.
var err error
valString, err = fromEncoding.NewDecoder().String(valString)
if err != nil {
return nil, err
}
out, err := charset.Convert(nil, charset.Charset_utf8mb4{}, val.Raw(), fromCollation.Charset())
if err != nil {
return nil, err
}
return sqltypes.StringBindVariable(valString), nil
return sqltypes.StringBindVariable(string(out)), nil
}
if tp.ConvertIntToEnum[field.Name] && !val.IsNull() {
// An integer converted to an enum. We must write the textual value of the int. i.e. 0 turns to '0'
Expand Down