Skip to content

Commit

Permalink
Add test cases for groupby search (#672)
Browse files Browse the repository at this point in the history 
- add test cases for groupby search
- update case: different metrics type for BinFlat and BinIvfFlat index
- update case: create scalar index for all kinds of supported FieldType
- update case: json support multiple forms
- add case: change of vector's legal dim
- add case: search from growing segments

see also: #670

Signed-off-by: ThreadDao <[email protected]>
  • Loading branch information
@ThreadDao
ThreadDao authored Mar 18, 2024
1 parent 1a1a092 commit aa29152
Show file tree
Hide file tree
Showing 6 changed files with 645 additions and 105 deletions.
112 changes: 67 additions & 45 deletions test/common/utils.go
View file
Original file line number Diff line number Diff line change
Expand Up @@ -412,28 +412,42 @@ func GenArrayColumnData(start int, nb int, fieldName string, opts ...GenColumnDa
}
}

type JSONStruct struct {
Number int32 `json:"number" milvus:"name:number"`
String string `json:"string" milvus:"name:string"`
Bool bool `json:"bool" milvus:"name:bool"`
List []int64 `json:"list" milvus:"name:list"`
}

// GenDefaultJSONData gen default column with data
func GenDefaultJSONData(columnName string, start int, nb int) *entity.ColumnJSONBytes {
type JSONStruct struct {
Number int32 `json:"number" milvus:"name:number"`
String string `json:"string" milvus:"name:string"`
Bool bool `json:"bool" milvus:"name:bool"`
List []int64 `json:"list" milvus:"name:list"`
}
jsonValues := make([][]byte, 0, nb)
var m JSONStruct
var m interface{}
for i := start; i < start+nb; i++ {
if i%2 == 0 {
m = JSONStruct{
String: strconv.Itoa(i),
Bool: i%2 == 0,
if i < (start+nb)/2 {
if i%2 == 0 {
m = JSONStruct{
String: strconv.Itoa(i),
Bool: i%2 == 0,
}
} else {
m = JSONStruct{
Number: int32(i),
String: strconv.Itoa(i),
Bool: i%2 == 0,
List: []int64{int64(i), int64(i + 1)},
}
}
} else {
m = JSONStruct{
Number: int32(i),
String: strconv.Itoa(i),
Bool: i%2 == 0,
List: []int64{int64(i), int64(i + 1)},
switch i % 4 {
case 0:
m = i
case 1:
m = float32(i)
case 2:
m = strconv.Itoa(i)
case 3:
m = []int64{int64(i), int64(i + 1)}
}
}
bs, err := json.Marshal(&m)
Expand Down Expand Up @@ -668,12 +682,6 @@ func GenDefaultVarcharRows(start int, nb int, dim int64, enableDynamicField bool

func GenDefaultJSONRows(start int, nb int, dim int64, enableDynamicField bool) []interface{} {
rows := make([]interface{}, 0, nb)
type JSONStruct struct {
Number int32 `json:"number" milvus:"name:number"`
String string `json:"string" milvus:"name:string"`
Bool bool `json:"bool" milvus:"name:bool"`
List []int64 `json:"list" milvus:"name:list"`
}

// BaseRow generate insert rows
type BaseRow struct {
Expand Down Expand Up @@ -1030,26 +1038,37 @@ func MergeColumnsToDynamic(nb int, columns []entity.Column) *entity.ColumnJSONBy
// --- gen row data ---

// --- index utils ---
var SupportFloatMetricType = []entity.MetricType{
entity.L2,
entity.IP,
entity.COSINE,
}

var SupportBinFlatMetricType = []entity.MetricType{
entity.JACCARD,
entity.HAMMING,
entity.SUBSTRUCTURE,
entity.SUPERSTRUCTURE,
}

var SupportBinIvfFlatMetricType = []entity.MetricType{
entity.JACCARD,
entity.HAMMING,
}

// GenAllFloatIndex gen all float vector index
func GenAllFloatIndex(metricType entity.MetricType) []entity.Index {
func GenAllFloatIndex() []entity.Index {
nlist := 128
idxFlat, _ := entity.NewIndexFlat(metricType)
idxIvfFlat, _ := entity.NewIndexIvfFlat(metricType, nlist)
idxIvfSq8, _ := entity.NewIndexIvfSQ8(metricType, nlist)
idxIvfPq, _ := entity.NewIndexIvfPQ(metricType, nlist, 16, 8)
idxHnsw, _ := entity.NewIndexHNSW(metricType, 8, 96)
idxScann, _ := entity.NewIndexSCANN(metricType, 16, false)
idxDiskAnn, _ := entity.NewIndexDISKANN(metricType)

allFloatIndex := []entity.Index{
idxFlat,
idxIvfFlat,
idxIvfSq8,
idxIvfPq,
idxHnsw,
idxScann,
idxDiskAnn,
var allFloatIndex []entity.Index
for _, metricType := range SupportFloatMetricType {
idxFlat, _ := entity.NewIndexFlat(metricType)
idxIvfFlat, _ := entity.NewIndexIvfFlat(metricType, nlist)
idxIvfSq8, _ := entity.NewIndexIvfSQ8(metricType, nlist)
idxIvfPq, _ := entity.NewIndexIvfPQ(metricType, nlist, 16, 8)
idxHnsw, _ := entity.NewIndexHNSW(metricType, 8, 96)
idxScann, _ := entity.NewIndexSCANN(metricType, 16, false)
idxDiskAnn, _ := entity.NewIndexDISKANN(metricType)
allFloatIndex = append(allFloatIndex, idxFlat, idxIvfFlat, idxIvfSq8, idxIvfPq, idxHnsw, idxScann, idxDiskAnn)
}
return allFloatIndex
}
Expand Down Expand Up @@ -1084,22 +1103,25 @@ type InvalidExprStruct struct {
}

var InvalidExpressions = []InvalidExprStruct{
{Expr: "id in [0]", ErrNil: true, ErrMsg: "fieldName(id) not found"}, // not exist field but no error
{Expr: "int64 in not [0]", ErrNil: false, ErrMsg: "cannot parse expression"}, // wrong term expr keyword
{Expr: "int64 < floatVec", ErrNil: false, ErrMsg: "not supported"}, // unsupported compare field
{Expr: "floatVec in [0]", ErrNil: false, ErrMsg: "cannot be casted to FloatVector"}, // value and field type mismatch
{Expr: fmt.Sprintf("%s == 1", DefaultJSONFieldName), ErrNil: false, ErrMsg: "can not comparisons jsonField directly"},
{Expr: fmt.Sprintf("%s == 1", DefaultDynamicFieldName), ErrNil: false, ErrMsg: "can not comparisons jsonField directly"},
{Expr: "id in [0]", ErrNil: true, ErrMsg: "fieldName(id) not found"}, // not exist field but no error
{Expr: "int64 in not [0]", ErrNil: false, ErrMsg: "cannot parse expression"}, // wrong term expr keyword
{Expr: "int64 < floatVec", ErrNil: false, ErrMsg: "not supported"}, // unsupported compare field
{Expr: "floatVec in [0]", ErrNil: false, ErrMsg: "cannot be casted to FloatVector"}, // value and field type mismatch
{Expr: fmt.Sprintf("%s == 1", DefaultJSONFieldName), ErrNil: true, ErrMsg: ""}, // hist empty
{Expr: fmt.Sprintf("%s like 'a%%' ", DefaultJSONFieldName), ErrNil: true, ErrMsg: ""}, // hist empty
{Expr: fmt.Sprintf("%s > 1", DefaultDynamicFieldName), ErrNil: true, ErrMsg: ""}, // hits empty
{Expr: fmt.Sprintf("%s[\"dynamicList\"] == [2, 3]", DefaultDynamicFieldName), ErrNil: true, ErrMsg: ""},
{Expr: fmt.Sprintf("%s['a'] == [2, 3]", DefaultJSONFieldName), ErrNil: true, ErrMsg: ""}, // json field not exist
{Expr: fmt.Sprintf("%s['number'] == [2, 3]", DefaultJSONFieldName), ErrNil: true, ErrMsg: ""}, // field exist but type not match
{Expr: fmt.Sprintf("%s[0] == [2, 3]", DefaultJSONFieldName), ErrNil: true, ErrMsg: ""}, // field exist but type not match
{Expr: fmt.Sprintf("json_contains (%s['number'], 2)", DefaultJSONFieldName), ErrNil: true, ErrMsg: ""},
{Expr: fmt.Sprintf("json_contains (%s['list'], [2])", DefaultJSONFieldName), ErrNil: true, ErrMsg: ""},
{Expr: fmt.Sprintf("json_contains_all (%s['list'], 2)", DefaultJSONFieldName), ErrNil: false, ErrMsg: "contains_all operation element must be an array"},
{Expr: fmt.Sprintf("JSON_CONTAINS_ANY (%s['list'], 2)", DefaultJSONFieldName), ErrNil: false, ErrMsg: "contains_any operation element must be an array"},
{Expr: fmt.Sprintf("json_contains_aby (%s['list'], 2)", DefaultJSONFieldName), ErrNil: false, ErrMsg: "invalid expression: json_contains_aby"},
{Expr: fmt.Sprintf("json_contains_aby (%s['list'], 2)", DefaultJSONFieldName), ErrNil: false, ErrMsg: "invalid expression: json_contains_aby"},
{Expr: fmt.Sprintf("%s[-1] > %d", DefaultInt8ArrayField, TestCapacity), ErrNil: false, ErrMsg: "cannot parse expression"}, // array[-1] >
{Expr: fmt.Sprintf(fmt.Sprintf("%s[-1] > 1", DefaultJSONFieldName)), ErrNil: false, ErrMsg: "invalid expression"}, // json[-1] >
}

// --- search utils ---
41 changes: 38 additions & 3 deletions test/testcases/collection_test.go
View file
Original file line number Diff line number Diff line change
Expand Up @@ -372,19 +372,21 @@ func TestCreateCollectionDescription(t *testing.T) {
}

// test create collection with invalid dim
func TestCreateCollectionInvalidDim(t *testing.T) {
func TestCreateBinaryCollectionInvalidDim(t *testing.T) {
t.Parallel()
type invalidDimStruct struct {
dim string
errMsg string
}
invalidDims := []invalidDimStruct{
{dim: "10", errMsg: "should be multiple of 8"},
{dim: "0", errMsg: "should be in range 1 ~ 32768"},
{dim: "0", errMsg: "should be in range 2 ~ 32768"},
{dim: "1", errMsg: "should be in range 2 ~ 32768"},
{dim: "", errMsg: "invalid syntax"},
{dim: "中文", errMsg: "invalid syntax"},
{dim: "%$#", errMsg: "invalid syntax"},
{dim: fmt.Sprintf("%d", common.MaxDim+1), errMsg: "should be in range 1 ~ 32768"},
{dim: fmt.Sprintf("%d", common.MaxDim*9), errMsg: "binary vector dimension should be in range 2 ~ 262144"},
{dim: fmt.Sprintf("%d", common.MaxDim*8+1), errMsg: "binary vector dimension should be multiple of 8"},
}

// connect
Expand All @@ -405,6 +407,39 @@ func TestCreateCollectionInvalidDim(t *testing.T) {
}
}

func TestCreateFloatCollectionInvalidDim(t *testing.T) {
t.Parallel()
type invalidDimStruct struct {
dim string
errMsg string
}
invalidDims := []invalidDimStruct{
{dim: "0", errMsg: "should be in range 2 ~ 32768"},
{dim: "1", errMsg: "should be in range 2 ~ 32768"},
{dim: "", errMsg: "invalid syntax"},
{dim: "中文", errMsg: "invalid syntax"},
{dim: "%$#", errMsg: "invalid syntax"},
{dim: fmt.Sprintf("%d", common.MaxDim+1), errMsg: "float vector dimension should be in range 2 ~ 32768"},
}

// connect
ctx := createContext(t, time.Second*common.DefaultTimeout)
mc := createMilvusClient(ctx, t)

// create binary collection with autoID true
pkField := common.GenField("", entity.FieldTypeInt64, common.WithIsPrimaryKey(true), common.WithAutoID(true))
for _, invalidDim := range invalidDims {
collName := common.GenRandomString(6)
binaryFields := entity.NewField().
WithName(common.DefaultFloatVecFieldName).
WithDataType(entity.FieldTypeFloatVector).
WithTypeParams(entity.TypeParamDim, invalidDim.dim)
schema := common.GenSchema(collName, true, []*entity.Field{pkField, binaryFields})
errCreate := mc.CreateCollection(ctx, schema, common.DefaultShards)
common.CheckErr(t, errCreate, false, invalidDim.errMsg)
}
}

func TestCreateJsonCollection(t *testing.T) {
ctx := createContext(t, time.Second*common.DefaultTimeout)
mc := createMilvusClient(ctx, t)
Expand Down
Loading

0 comments on commit aa29152

Please sign in to comment.