-
Notifications
You must be signed in to change notification settings - Fork 63
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.
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
Modify interface and implementation of BulkInsertWithAssigningIDs #53
base: epic-assigning-ids
Are you sure you want to change the base?
Changes from all commits
e44a1e5
3903de2
d96d08e
59174e7
b4155aa
88dc325
aad2d27
8c21b86
4484575
9eeb267
241f2ad
798a708
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -32,65 +32,81 @@ func BulkInsert(db *gorm.DB, objects []interface{}, chunkSize int, excludeColumn | |
return nil | ||
} | ||
|
||
// BulkInsertWithAssigningIDs executes the query to insert multiple records at once. | ||
// it will scan the result of `returning id` or `returning *` to [returnedValue] after every insert. | ||
// it's necessary to set "gorm:insert_option"="returning id" in *gorm.DB | ||
// | ||
// [returnedValue] slice of primary_key or model, must be a *[]uint(for integer), *[]string(for uuid), *[]struct(for `returning *`) | ||
// BulkInsertWithReturningValues executes the query to insert multiple records at once. | ||
// This will scan the returned values into `returnedVals`. | ||
// | ||
// [objects] must be a slice of struct. | ||
// | ||
// [returnedVals] must be a point to a slice of struct. Values returned from `RETURNING` clause will be assigned. | ||
// | ||
// [chunkSize] is a number of variables embedded in query. To prevent the error which occurs embedding a large number of variables at once | ||
// and exceeds the limit of prepared statement. Larger size normally leads to better performance, in most cases 2000 to 3000 is reasonable. | ||
// | ||
// [excludeColumns] is column names to exclude from insert. | ||
func BulkInsertWithAssigningIDs(db *gorm.DB, returnedValue interface{}, objects []interface{}, chunkSize int, excludeColumns ...string) error { | ||
typ := reflect.TypeOf(returnedValue) | ||
if typ.Kind() != reflect.Ptr || typ.Elem().Kind() != reflect.Slice { | ||
return errors.New("returningId must be a slice ptr") | ||
func BulkInsertWithReturningValues(db *gorm.DB, objects []interface{}, returnedVals interface{}, chunkSize int, excludeColumns ...string) error { | ||
bombsimon marked this conversation as resolved.
Show resolved
Hide resolved
|
||
typ := reflect.TypeOf(returnedVals) | ||
if typ.Kind() != reflect.Ptr || typ.Elem().Kind() != reflect.Slice || typ.Elem().Elem().Kind() != reflect.Struct { | ||
return errors.New("returnedVals must be a pointer to a slice of struct") | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. we can also accept *[]uint i think, it will be more useful. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I'm not a fan of accepting a different type in a single method, rather I'd like to have a dedicated method if we accept a slice. The reason why I changed not to accept slice is, func BulkInsertWithReturningIDs(db *gorm.DB, objects []interface{}, ids interface{}, chunkSize int, excludeColumns ...string) error
// Or we should rename to use "PK" instead of "ID"? But PK is not always a single column🤔
func BulkInsertWithReturningPKs(db *gorm.DB, objects []interface{}, pks interface{}, chunkSize int, excludeColumns ...string) error What do you think? There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. how about
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Hmm, I feel There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. good idea |
||
} | ||
refDst := reflect.Indirect(reflect.ValueOf(returnedVals)) | ||
|
||
allIds := reflect.Indirect(reflect.ValueOf(returnedValue)) | ||
typ = allIds.Type() | ||
|
||
// Deference value of slice | ||
valueTyp := typ.Elem() | ||
for valueTyp.Kind() == reflect.Ptr { | ||
valueTyp = valueTyp.Elem() | ||
// set insert_option | ||
fields := (&gorm.Scope{Value: returnedVals}).Fields() | ||
returningCols := make([]string, len(fields)) | ||
for i, f := range fields { | ||
returningCols[i] = f.DBName | ||
} | ||
db = db.Set("gorm:insert_option", fmt.Sprintf("RETURNING %s", strings.Join(returningCols, ", "))) | ||
|
||
// Split records with specified size not to exceed Database parameter limit | ||
for _, objSet := range splitObjects(objects, chunkSize) { | ||
returnValueSlice := reflect.New(typ) | ||
var scanReturningId func(*gorm.DB) error | ||
switch valueTyp.Kind() { | ||
case reflect.Struct: | ||
// If user want to scan `returning *` with returnedValue=[]struct{...} | ||
scanReturningId = func(db *gorm.DB) error { | ||
return db.Scan(returnValueSlice.Interface()).Error | ||
} | ||
default: | ||
// If user want to scan primary key `returning pk` with returnedValue=[]struct{...} | ||
pk := db.NewScope(objects[0]).PrimaryKey() | ||
scanReturningId = func(db *gorm.DB) error { | ||
return db.Pluck(pk, returnValueSlice.Interface()).Error | ||
} | ||
if err := insertObjSet(db, objSet, excludeColumns...); err != nil { | ||
return err | ||
} | ||
|
||
if err := insertObjSetWithCallback(db, objSet, scanReturningId, excludeColumns...); err != nil { | ||
scanned := reflect.New(refDst.Type()) | ||
if err := db.Scan(scanned.Interface()).Error; err != nil { | ||
return err | ||
} | ||
|
||
allIds.Set(reflect.AppendSlice(allIds, returnValueSlice.Elem())) | ||
refDst.Set(reflect.AppendSlice(refDst, scanned.Elem())) | ||
} | ||
return nil | ||
} | ||
|
||
func insertObjSet(db *gorm.DB, objects []interface{}, excludeColumns ...string) error { | ||
return insertObjSetWithCallback(db, objects, nil, excludeColumns...) | ||
// BulkInsertWithReturningIDs executes the query to insert multiple records at once. | ||
// This will scan the returned id into `returnedIDs`. If the target table does not have "id" column, please use BulkInsertWithReturningValues instead. | ||
// | ||
// [objects] must be a slice of struct. | ||
// | ||
// [returnedVals] must be a point to a slice. Values returned from `RETURNING` clause will be assigned. | ||
// | ||
// [chunkSize] is a number of variables embedded in query. To prevent the error which occurs embedding a large number of variables at once | ||
// and exceeds the limit of prepared statement. Larger size normally leads to better performance, in most cases 2000 to 3000 is reasonable. | ||
// | ||
// [excludeColumns] is column names to exclude from insert. | ||
func BulkInsertWithReturningIDs(db *gorm.DB, objects []interface{}, returnedIDs interface{}, chunkSize int, excludeColumns ...string) error { | ||
typ := reflect.TypeOf(returnedIDs) | ||
if typ.Kind() != reflect.Ptr || typ.Elem().Kind() != reflect.Slice { | ||
return errors.New("returnedVals must be a pointer to a slice") | ||
} | ||
refDst := reflect.Indirect(reflect.ValueOf(returnedIDs)) | ||
|
||
db = db.Set("gorm:insert_option", "RETURNING id") | ||
|
||
// Split records with specified size not to exceed Database parameter limit | ||
for _, objSet := range splitObjects(objects, chunkSize) { | ||
if err := insertObjSet(db, objSet, excludeColumns...); err != nil { | ||
return err | ||
} | ||
ids := reflect.New(refDst.Type()) | ||
if err := db.Pluck("ID", ids.Interface()).Error; err != nil { | ||
return err | ||
} | ||
refDst.Set(reflect.AppendSlice(refDst, ids.Elem())) | ||
} | ||
return nil | ||
} | ||
|
||
func insertObjSetWithCallback(db *gorm.DB, objects []interface{}, postInsert func(*gorm.DB) error, excludeColumns ...string) error { | ||
func insertObjSet(db *gorm.DB, objects []interface{}, excludeColumns ...string) error { | ||
if len(objects) == 0 { | ||
return nil | ||
} | ||
|
@@ -156,18 +172,10 @@ func insertObjSetWithCallback(db *gorm.DB, objects []interface{}, postInsert fun | |
insertOption, | ||
)) | ||
|
||
db = db.Raw(mainScope.SQL, mainScope.SQLVars...) | ||
|
||
*db = *db.Raw(mainScope.SQL, mainScope.SQLVars...) | ||
if err := db.Error; err != nil { | ||
return err | ||
} | ||
|
||
if postInsert != nil { | ||
if err := postInsert(db); err != nil { | ||
return err | ||
} | ||
} | ||
|
||
return nil | ||
} | ||
|
||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -26,6 +26,77 @@ type fakeTable struct { | |
UpdatedAt time.Time | ||
} | ||
|
||
func TestBulkInsertWithReturningValues(t *testing.T) { | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Still think this test case should be simplified without column options and fields not needed. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. You mean, we don't need There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. It's a super nit but I just mean the test is copied when testing custom field tags so this test is also using the field tag type Table struct {
ID uint `gorm:"primary_key;auto_increment"`
ColumnOne string
ColumnTwo string
} And then just refer to the default column names |
||
type Table struct { | ||
ID uint `gorm:"primary_key;auto_increment"` | ||
RegularColumn string | ||
Custom string `gorm:"column:ThisIsCamelCase"` | ||
} | ||
|
||
db, mock, err := sqlmock.New() | ||
require.NoError(t, err) | ||
defer db.Close() | ||
|
||
gdb, err := gorm.Open("mysql", db) | ||
require.NoError(t, err) | ||
|
||
mock.ExpectQuery( | ||
"INSERT INTO `tables` \\(`ThisIsCamelCase`, `regular_column`\\)", | ||
Comment on lines
+43
to
+44
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I'd like to test with actual DBs using Docker containers as a follow-up task. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Personally I don't think that's necessary since this supports multiple dialects so it would require multiple containers. Also the only goal for this project is to generate SQL, not handle or parse the dialect nor handle connections. An example directory with a docker-compose file starting the DBMs to use as integration test might make sense but I don't think the unit tests should rely on that. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I have been testing manually to see if it works in various cases like ID is int or string, and composite PK, and so on. But when I make a change like this, I feel it's inconvenient without automated tests.
Can I ask why we should not use DBMs for unit tests? With docker-compose, we can easily test with DBs, and since there are only two public methods, I don't feel integration tests are necessary. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I'm just used to unit tests being small and quick, testing the implementation but not the dependencies. But it's easy enough to use Docker for unit tests as well so if you feel it makes sense go for it! Are you planning on testing all DBMs that Gorm support or only a subset? There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more.
I'm planning to test with MySQL and PostgreSQL since most of the users likely to use, I guess. |
||
).WithArgs( | ||
"first custom", "first regular", | ||
"second custom", "second regular", | ||
).WillReturnRows( | ||
sqlmock.NewRows([]string{"id", "ThisIsCamelCase", "regular_column"}). | ||
AddRow(1, "first custom", "first regular"). | ||
AddRow(2, "second custom", "second regular"), | ||
) | ||
|
||
var returnedVals []Table | ||
obj := []interface{}{ | ||
Table{ | ||
RegularColumn: "first regular", | ||
Custom: "first custom", | ||
}, | ||
Table{ | ||
RegularColumn: "second regular", | ||
Custom: "second custom", | ||
}, | ||
} | ||
|
||
err = BulkInsertWithReturningValues(gdb, obj, &returnedVals, 1000) | ||
require.NoError(t, err) | ||
|
||
expected := []Table{ | ||
{ID: 1, RegularColumn: "first regular", Custom: "first custom"}, | ||
{ID: 2, RegularColumn: "second regular", Custom: "second custom"}, | ||
} | ||
assert.Equal(t, expected, returnedVals) | ||
} | ||
|
||
func TestBulkInsertWithReturningValues_InvalidTypeOfReturnedVals(t *testing.T) { | ||
db, _, err := sqlmock.New() | ||
require.NoError(t, err) | ||
defer db.Close() | ||
|
||
gdb, err := gorm.Open("mysql", db) | ||
require.NoError(t, err) | ||
|
||
tests := []struct { | ||
name string | ||
vals interface{} | ||
}{ | ||
{name: "not a pointer", vals: []struct{ Name string }{{Name: "1"}}}, | ||
{name: "element is not a slice", vals: &struct{ Name string }{Name: "1"}}, | ||
{name: "slice element is not a struct", vals: &[]string{"1"}}, | ||
} | ||
for _, tt := range tests { | ||
t.Run(tt.name, func(t *testing.T) { | ||
err := BulkInsertWithReturningValues(gdb, []interface{}{}, tt.vals, 1000) | ||
assert.EqualError(t, err, "returnedVals must be a pointer to a slice of struct") | ||
}) | ||
} | ||
} | ||
|
||
func Test_extractMapValue(t *testing.T) { | ||
collectKeys := func(val map[string]interface{}) []string { | ||
keys := make([]string, 0, len(val)) | ||
|
@@ -113,59 +184,6 @@ func Test_insertObject(t *testing.T) { | |
require.NoError(t, err) | ||
} | ||
|
||
func Test_insertObjSetWithCallback(t *testing.T) { | ||
type Table struct { | ||
ID uint `gorm:"primary_key;auto_increment"` | ||
RegularColumn string | ||
Custom string `gorm:"column:ThisIsCamelCase"` | ||
} | ||
|
||
db, mock, err := sqlmock.New() | ||
require.NoError(t, err) | ||
|
||
defer db.Close() | ||
|
||
gdb, err := gorm.Open("mysql", db) | ||
require.NoError(t, err) | ||
|
||
mock.ExpectQuery( | ||
"INSERT INTO `tables` \\(`ThisIsCamelCase`, `regular_column`\\)", | ||
).WithArgs( | ||
"first custom", "first regular", | ||
"second custom", "second regular", | ||
).WillReturnRows( | ||
sqlmock.NewRows([]string{"id"}).AddRow(1).AddRow(2), | ||
) | ||
|
||
returningIdScope := func(db *gorm.DB) *gorm.DB { | ||
return db.Set("gorm:insert_option", "returning id") | ||
} | ||
|
||
err = insertObjSetWithCallback(gdb.Scopes(returningIdScope), []interface{}{ | ||
Table{ | ||
RegularColumn: "first regular", | ||
Custom: "first custom", | ||
}, | ||
Table{ | ||
RegularColumn: "second regular", | ||
Custom: "second custom", | ||
}, | ||
}, func(db *gorm.DB) error { | ||
var ids []uint | ||
if err := db.Pluck("id", &ids).Error; err != nil { | ||
return err | ||
} | ||
require.Len(t, ids, 2, "must return 2 ids") | ||
return nil | ||
}) | ||
|
||
if err != nil { | ||
t.Fatal(err) | ||
} | ||
|
||
require.NoError(t, err) | ||
} | ||
|
||
func Test_fieldIsAutoIncrement(t *testing.T) { | ||
type explicitSetTable struct { | ||
ID int `gorm:"column:id;auto_increment"` | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
if i only need
ID
, i would definescan it from result then
it's odd...
its nessessary to support *[]uint or *[]string, i suggest.