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

schemadiff: assume default collation for textual column when collation is undefined #16000

Merged
merged 4 commits into from
May 25, 2024
Merged

schemadiff: assume default collation for textual column when collation is undefined #16000

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
38bc519
schemadiff: normalize missing column collation
shlomi-noach May 22, 2024
e1c2b97
defer restoring original collation
shlomi-noach May 22, 2024
333c7f8
more tests: compare column with just charset vs column with just coll…
shlomi-noach May 23, 2024
58983d3
revised comments
shlomi-noach May 24, 2024
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
23 changes: 22 additions & 1 deletion go/vt/schemadiff/column.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,7 +104,17 @@ func (c *ColumnDefinitionEntity) ColumnDiff(
) (*ModifyColumnDiff, error) {
if c.IsTextual() || other.IsTextual() {
// We will now denormalize the columns charset & collate as needed (if empty, populate from table.)

// This column definition
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this the full comment? 🙂 I'm assuming it should be ~

// This column definition is using the implied / default collation for the character set
// so we need to determine the default/actual collation used for the specified character set
// based on the MySQL version being used.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I've updated this and other comments.

if c.columnDefinition.Type.Charset.Name != "" && c.columnDefinition.Type.Options.Collate == "" {
collation := env.CollationEnv().DefaultCollationForCharset(c.columnDefinition.Type.Charset.Name)
if collation == collations.Unknown {
return nil, &UnknownColumnCharsetCollationError{Column: c.columnDefinition.Name.String(), Charset: t1cc.charset}
}
defer func() {
c.columnDefinition.Type.Options.Collate = ""
}()
c.columnDefinition.Type.Options.Collate = env.CollationEnv().LookupName(collation)
}
if c.columnDefinition.Type.Charset.Name == "" && c.columnDefinition.Type.Options.Collate != "" {
// Column has explicit collation but no charset. We can infer the charset from the collation.
collationID := env.CollationEnv().LookupByName(c.columnDefinition.Type.Options.Collate)
Expand Down Expand Up @@ -137,6 +147,17 @@ func (c *ColumnDefinitionEntity) ColumnDiff(
c.columnDefinition.Type.Options.Collate = env.CollationEnv().LookupName(collation)
}
}
// other column definition
Copy link
Contributor

@mattlord mattlord May 23, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ah, I see. So "this" and "other" are the two things being diffed. The other related comments are still worthwhile though IMO.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I've updated this and other comments.

if other.columnDefinition.Type.Charset.Name != "" && other.columnDefinition.Type.Options.Collate == "" {
collation := env.CollationEnv().DefaultCollationForCharset(other.columnDefinition.Type.Charset.Name)
if collation == collations.Unknown {
return nil, &UnknownColumnCharsetCollationError{Column: other.columnDefinition.Name.String(), Charset: t2cc.charset}
}
defer func() {
other.columnDefinition.Type.Options.Collate = ""
}()
other.columnDefinition.Type.Options.Collate = env.CollationEnv().LookupName(collation)
}
if other.columnDefinition.Type.Charset.Name == "" && other.columnDefinition.Type.Options.Collate != "" {
// Column has explicit collation but no charset. We can infer the charset from the collation.
collationID := env.CollationEnv().LookupByName(other.columnDefinition.Type.Options.Collate)
Expand Down
35 changes: 35 additions & 0 deletions go/vt/schemadiff/table_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1896,6 +1896,36 @@ func TestCreateTableDiff(t *testing.T) {
from: "create table t (id int primary key, v varchar(64) character set utf8mb3 collate utf8mb3_bin)",
to: "create table t (id int primary key, v varchar(64) collate utf8mb3_bin)",
},
{
name: "ignore identical implicit ascii charset",
from: "create table t (id int primary key, v varchar(64) character set ascii collate ascii_general_ci)",
to: "create table t (id int primary key, v varchar(64) collate ascii_general_ci)",
},
{
name: "ignore identical implicit collation",
from: "create table t (id int primary key, v varchar(64) character set utf8mb3 collate utf8mb3_general_ci)",
to: "create table t (id int primary key, v varchar(64) character set utf8mb3)",
},
{
name: "ignore identical implicit collation, reverse",
from: "create table t (id int primary key, v varchar(64) character set utf8mb3)",
to: "create table t (id int primary key, v varchar(64) character set utf8mb3 collate utf8mb3_general_ci)",
},
{
name: "implicit charset and implciit collation",
from: "create table t (id int primary key, v varchar(64) character set utf8mb3)",
to: "create table t (id int primary key, v varchar(64) collate utf8mb3_general_ci)",
},
{
name: "ignore identical implicit ascii collation",
from: "create table t (id int primary key, v varchar(64) character set ascii collate ascii_general_ci)",
to: "create table t (id int primary key, v varchar(64) character set ascii)",
},
{
name: "implicit charset and implciit collation, ascii",
from: "create table t (id int primary key, v varchar(64) collate ascii_general_ci)",
to: "create table t (id int primary key, v varchar(64) character set ascii)",
},
{
name: "normalized unsigned attribute",
from: "create table t1 (id int primary key)",
Expand Down Expand Up @@ -2925,6 +2955,11 @@ func TestNormalize(t *testing.T) {
from: "create table t (id int primary key, v varchar(255) charset utf8mb4 collate utf8mb4_german2_ci)",
to: "CREATE TABLE `t` (\n\t`id` int,\n\t`v` varchar(255) COLLATE utf8mb4_german2_ci,\n\tPRIMARY KEY (`id`)\n)",
},
{
name: "ascii charset and collation",
from: "create table t (id int primary key, v varchar(255) charset ascii collate ascii_general_ci) charset utf8mb3 collate utf8_general_ci",
to: "CREATE TABLE `t` (\n\t`id` int,\n\t`v` varchar(255) CHARACTER SET ascii COLLATE ascii_general_ci,\n\tPRIMARY KEY (`id`)\n) CHARSET utf8mb3,\n COLLATE utf8mb3_general_ci",
},
{
name: "correct case table options for engine",
from: "create table t (id int signed primary key) engine innodb",
Expand Down
Loading