mirror of
https://github.com/milvus-io/milvus.git
synced 2026-07-21 10:15:43 +00:00
fix: add utf8 check before bm25 functoin run (#44220)
relate: https://github.com/milvus-io/milvus/issues/44219 Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
This commit is contained in:
@@ -28,6 +28,7 @@ import (
|
||||
"github.com/milvus-io/milvus-proto/go-api/v2/milvuspb"
|
||||
"github.com/milvus-io/milvus-proto/go-api/v2/schemapb"
|
||||
"github.com/milvus-io/milvus/internal/util/analyzer"
|
||||
"github.com/milvus-io/milvus/pkg/v2/util/merr"
|
||||
"github.com/milvus-io/milvus/pkg/v2/util/typeutil"
|
||||
)
|
||||
|
||||
@@ -109,6 +110,9 @@ func (v *BM25FunctionRunner) run(data []string, dst []map[uint32]float32) error
|
||||
defer tokenizer.Destroy()
|
||||
|
||||
for i := 0; i < len(data); i++ {
|
||||
if !typeutil.IsUTF8(data[i]) {
|
||||
return merr.WrapErrParameterInvalidMsg("string data must be utf8 format: %v", data[i])
|
||||
}
|
||||
embeddingMap := map[uint32]float32{}
|
||||
tokenStream := tokenizer.NewTokenStream(data[i])
|
||||
defer tokenStream.Destroy()
|
||||
|
||||
@@ -26,6 +26,7 @@ import (
|
||||
"github.com/milvus-io/milvus-proto/go-api/v2/milvuspb"
|
||||
"github.com/milvus-io/milvus-proto/go-api/v2/schemapb"
|
||||
"github.com/milvus-io/milvus/internal/util/analyzer"
|
||||
"github.com/milvus-io/milvus/pkg/v2/util/merr"
|
||||
"github.com/milvus-io/milvus/pkg/v2/util/typeutil"
|
||||
)
|
||||
|
||||
@@ -153,6 +154,9 @@ func (v *MultiAnalyzerBM25FunctionRunner) run(text []string, analyzerName []stri
|
||||
}()
|
||||
|
||||
for i := 0; i < len(text); i++ {
|
||||
if !typeutil.IsUTF8(text[i]) {
|
||||
return merr.WrapErrParameterInvalidMsg("string data must be utf8 format: %v", text[i])
|
||||
}
|
||||
embeddingMap := map[uint32]float32{}
|
||||
|
||||
analyzer, err := v.getAnalyzer(analyzerName[i], cloneAnalyzers)
|
||||
|
||||
Reference in New Issue
Block a user