Go: support ids filter in list datasets API (#17705)

This commit is contained in:
euvre
2026-08-03 13:54:44 +08:00
committed by GitHub
parent 75586c0be1
commit 04918f88bf
7 changed files with 364 additions and 7 deletions

View File

@@ -173,7 +173,7 @@ func (dao *KnowledgebaseDAO) Count(ctx context.Context, db *gorm.DB, filters map
// GetByTenantIDs retrieves knowledge bases by tenant IDs with pagination
// This matches the Python get_by_tenant_ids method
func (dao *KnowledgebaseDAO) GetByTenantIDs(ctx context.Context, db *gorm.DB, tenantIDs []string, userID string, pageNumber, itemsPerPage int, orderby string, desc bool, keywords, parserID, id, name string) ([]*entity.KnowledgebaseListItem, int64, error) {
func (dao *KnowledgebaseDAO) GetByTenantIDs(ctx context.Context, db *gorm.DB, tenantIDs []string, userID string, pageNumber, itemsPerPage int, orderby string, desc bool, keywords, parserID, id, name string, ids []string) ([]*entity.KnowledgebaseListItem, int64, error) {
var kbs []*entity.KnowledgebaseListItem
var total int64
@@ -193,6 +193,10 @@ func (dao *KnowledgebaseDAO) GetByTenantIDs(ctx context.Context, db *gorm.DB, te
query = query.Where("knowledgebase.id = ?", id)
}
if len(ids) > 0 {
query = query.Where("knowledgebase.id IN ?", ids)
}
if name != "" {
query = query.Where("knowledgebase.name = ?", name)
}
@@ -318,6 +322,21 @@ func (dao *KnowledgebaseDAO) Accessible(ctx context.Context, db *gorm.DB, datase
return count > 0
}
// GetAccessibleIDs returns the subset of ids that are visible to the user:
// team-permission KBs owned by any joined tenant, plus the user's own KBs.
// This matches the Python get_accessible_ids method.
func (dao *KnowledgebaseDAO) GetAccessibleIDs(ctx context.Context, db *gorm.DB, joinedTenantIDs []string, userID string, ids []string) ([]string, error) {
accessibleIDs := make([]string, 0, len(ids))
err := db.WithContext(ctx).Model(&entity.Knowledgebase{}).
Where("id IN ? AND ((tenant_id IN ? AND permission = ?) OR tenant_id = ?) AND status = ?",
ids, joinedTenantIDs, string(entity.TenantPermissionTeam), userID, string(entity.StatusValid)).
Pluck("id", &accessibleIDs).Error
if err != nil {
return nil, err
}
return accessibleIDs, nil
}
// Accessible4Deletion checks if a knowledge base can be deleted by a user
// This matches the Python accessible4deletion method
func (dao *KnowledgebaseDAO) Accessible4Deletion(ctx context.Context, db *gorm.DB, kbID, userID string) bool {

View File

@@ -168,6 +168,39 @@ func (h *DatasetsHandler) ListDatasets(c *gin.Context) {
}
}
// Mirror pydantic's ListDatasetReq.ids: each occurrence is comma-split,
// every value must be a valid UUID, and duplicates are rejected.
var ids []string
if rawIDs, exists := c.Request.URL.Query()["ids"]; exists {
seen := make(map[string]int)
for _, item := range rawIDs {
for _, value := range strings.Split(item, ",") {
if value == "" {
continue
}
normalizedID, err := dataset.NormalizeDatasetID(strings.TrimSpace(value))
if err != nil {
common.ResponseWithCodeData(c, common.CodeArgumentError, nil, err.Error())
return
}
seen[normalizedID]++
ids = append(ids, normalizedID)
}
}
duplicates := make([]string, 0, len(ids))
reported := make(map[string]bool)
for _, normalizedID := range ids {
if seen[normalizedID] > 1 && !reported[normalizedID] {
reported[normalizedID] = true
duplicates = append(duplicates, normalizedID)
}
}
if len(duplicates) > 0 {
common.ResponseWithCodeData(c, common.CodeArgumentError, nil, fmt.Sprintf("Duplicate ids: '%s'", strings.Join(duplicates, ", ")))
return
}
}
ctx := c.Request.Context()
data, total, code, err := h.datasetsService.ListDatasets(
ctx,
@@ -181,6 +214,7 @@ func (h *DatasetsHandler) ListDatasets(c *gin.Context) {
ownerIDs,
parserID,
user.ID,
ids,
)
if err != nil {
common.ErrorWithCode(c, code, err.Error())
@@ -326,7 +360,7 @@ func pythonJSONTypeName(v interface{}) string {
// ListDatasetReq (BaseListReq + include_parsing_status/ext; `type` is handled
// before validation in the Python endpoint).
var listDatasetsAllowedParams = map[string]bool{
"id": true, "name": true, "page": true, "page_size": true,
"id": true, "ids": true, "name": true, "page": true, "page_size": true,
"orderby": true, "desc": true, "include_parsing_status": true,
"ext": true, "type": true,
}

View File

@@ -0,0 +1,147 @@
package handler
import (
"encoding/json"
"fmt"
"net/http"
"net/http/httptest"
"net/url"
"testing"
"github.com/gin-gonic/gin"
"github.com/glebarez/sqlite"
"gorm.io/gorm"
"ragflow/internal/common"
"ragflow/internal/dao"
"ragflow/internal/entity"
dataset "ragflow/internal/service/dataset"
)
const (
listDatasetsTestKBID = "123e4567e89b12d3a456426614174000"
listDatasetsTestKBIDDashed = "123e4567-e89b-12d3-a456-426614174000"
)
func setupListDatasetsTestDB(t *testing.T) *gorm.DB {
t.Helper()
db, err := gorm.Open(sqlite.Open("file:"+url.QueryEscape(t.Name())+"?mode=memory&cache=shared"), &gorm.Config{
TranslateError: true,
})
if err != nil {
t.Fatalf("failed to open sqlite: %v", err)
}
if err := db.AutoMigrate(&entity.Knowledgebase{}, &entity.User{}, &entity.UserTenant{}, &entity.Tenant{}); err != nil {
t.Fatalf("failed to migrate test schema: %v", err)
}
origDB := dao.DB
dao.DB = db
t.Cleanup(func() { dao.DB = origDB })
return db
}
func insertListDatasetsTestKB(t *testing.T, id, tenantID, name string) {
t.Helper()
status := string(entity.StatusValid)
kb := &entity.Knowledgebase{
ID: id,
TenantID: tenantID,
Name: name,
EmbdID: "BAAI/bge-large-zh-v1.5@Builtin",
CreatedBy: tenantID,
Permission: string(entity.TenantPermissionMe),
ParserID: string(entity.ParserTypeNaive),
ParserConfig: entity.JSONMap{"chunk_token_num": float64(128)},
Status: &status,
}
if err := dao.DB.Create(kb).Error; err != nil {
t.Fatalf("insert test kb: %v", err)
}
}
func newListDatasetsTestRouter() *gin.Engine {
gin.SetMode(gin.TestMode)
h := NewDatasetsHandler(dataset.NewDatasetService(), nil)
r := gin.New()
r.GET("/api/v1/datasets", func(c *gin.Context) {
c.Set("user", &entity.User{ID: "user-1"})
h.ListDatasets(c)
})
return r
}
type listDatasetsTestResponse struct {
Code int `json:"code"`
Data []map[string]interface{} `json:"data"`
Message string `json:"message"`
TotalDatasets int64 `json:"total_datasets"`
}
func getListDatasets(t *testing.T, r *gin.Engine, rawQuery string) listDatasetsTestResponse {
t.Helper()
resp := httptest.NewRecorder()
req := httptest.NewRequest(http.MethodGet, "/api/v1/datasets?"+rawQuery, nil)
r.ServeHTTP(resp, req)
if resp.Code != http.StatusOK {
t.Fatalf("status=%d body=%s", resp.Code, resp.Body.String())
}
var body listDatasetsTestResponse
if err := json.Unmarshal(resp.Body.Bytes(), &body); err != nil {
t.Fatalf("unmarshal response: %v body=%s", err, resp.Body.String())
}
return body
}
func TestDatasetsHandlerListDatasetsFiltersByIDs(t *testing.T) {
setupListDatasetsTestDB(t)
insertListDatasetsTestKB(t, listDatasetsTestKBID, "user-1", "Alpha")
body := getListDatasets(t, newListDatasetsTestRouter(),
fmt.Sprintf("ids=%s&page_size=1", listDatasetsTestKBIDDashed))
if body.Code != int(common.CodeSuccess) {
t.Fatalf("code=%d message=%q", body.Code, body.Message)
}
if body.TotalDatasets != 1 || len(body.Data) != 1 {
t.Fatalf("expected exactly one dataset, got total=%d len=%d", body.TotalDatasets, len(body.Data))
}
if body.Data[0]["id"] != listDatasetsTestKBID {
t.Fatalf("expected dataset id %q, got %#v", listDatasetsTestKBID, body.Data[0]["id"])
}
}
func TestDatasetsHandlerListDatasetsRejectsInvalidIDInIDs(t *testing.T) {
setupListDatasetsTestDB(t)
body := getListDatasets(t, newListDatasetsTestRouter(), "ids=not-a-uuid")
if body.Code != int(common.CodeArgumentError) {
t.Fatalf("code=%d want=%d", body.Code, common.CodeArgumentError)
}
if body.Message != "Invalid UUID format" {
t.Fatalf("message=%q want=%q", body.Message, "Invalid UUID format")
}
}
func TestDatasetsHandlerListDatasetsRejectsDuplicateIDs(t *testing.T) {
setupListDatasetsTestDB(t)
rawQuery := fmt.Sprintf("ids=%s,%s", listDatasetsTestKBIDDashed, listDatasetsTestKBIDDashed)
body := getListDatasets(t, newListDatasetsTestRouter(), rawQuery)
if body.Code != int(common.CodeArgumentError) {
t.Fatalf("code=%d want=%d", body.Code, common.CodeArgumentError)
}
expected := fmt.Sprintf("Duplicate ids: '%s'", listDatasetsTestKBID)
if body.Message != expected {
t.Fatalf("message=%q want=%q", body.Message, expected)
}
}

View File

@@ -35,7 +35,7 @@ import (
// by the MCP server handler.
type MCPRetrievalService interface {
SearchDatasets(req *service.SearchDatasetsRequest, userID string) (*service.SearchDatasetsResponse, error)
ListDatasets(id, name string, page, pageSize int, orderby string, desc bool, keywords string, ownerIDs []string, parserID, userID string) ([]map[string]interface{}, int64, common.ErrorCode, error)
ListDatasets(id, name string, page, pageSize int, orderby string, desc bool, keywords string, ownerIDs []string, parserID, userID string, ids []string) ([]map[string]interface{}, int64, common.ErrorCode, error)
}
// MCPServerHandler handles MCP protocol requests (JSON-RPC over HTTP).
@@ -118,7 +118,7 @@ func (h *MCPServerHandler) HandleMCP(c *gin.Context) {
func MCPListDatasets(ctx context.Context, ds *dataset.DatasetService, userID string, page, pageSize int, orderby string, desc bool) ([]map[string]interface{}, int64, error) {
data, total, _, err := ds.ListDatasets(ctx,
"", "", page, pageSize, orderby, desc,
"", nil, "", userID,
"", nil, "", userID, nil,
)
return data, total, err
}
@@ -154,7 +154,7 @@ func MCPRetrieval(ctx context.Context, ds *dataset.DatasetService, userID string
for {
data, _, _, err := ds.ListDatasets(ctx,
"", "", page, maxPageSize, "create_time", true,
"", nil, "", userID,
"", nil, "", userID, nil,
)
if err != nil {
return "", fmt.Errorf("cannot resolve accessible datasets: %w", err)

View File

@@ -328,8 +328,11 @@ func (d *DatasetService) deleteDataset(tenantID string, kb *entity.Knowledgebase
})
}
func (d *DatasetService) ListDatasets(ctx context.Context, id, name string, page, pageSize int, orderby string, desc bool, keywords string, ownerIDs []string, parserID, userID string) ([]map[string]interface{}, int64, common.ErrorCode, error) {
func (d *DatasetService) ListDatasets(ctx context.Context, id, name string, page, pageSize int, orderby string, desc bool, keywords string, ownerIDs []string, parserID, userID string, ids []string) ([]map[string]interface{}, int64, common.ErrorCode, error) {
id = strings.TrimSpace(id)
if id != "" && len(ids) > 0 {
return nil, 0, common.CodeDataError, fmt.Errorf("Should not provide both 'id':%s and 'ids'%s", id, pythonStringListRepr(ids))
}
if id != "" {
normalizedID, err := normalizeDatasetID(id)
if err != nil {
@@ -380,6 +383,7 @@ func (d *DatasetService) ListDatasets(ctx context.Context, id, name string, page
}
}
queryUserID := userID
var joinedTenantIDs []string
if len(tenantIDs) > 0 {
joinedTenants, err := d.tenantDAO.GetJoinedTenantsByUserID(ctx, dao.DB, userID)
if err != nil {
@@ -391,6 +395,7 @@ func (d *DatasetService) ListDatasets(ctx context.Context, id, name string, page
continue
}
allowedTenantIDs[joinedTenant.TenantID] = struct{}{}
joinedTenantIDs = append(joinedTenantIDs, joinedTenant.TenantID)
}
filteredTenantIDs := tenantIDs[:0]
queryUserID = ""
@@ -414,10 +419,33 @@ func (d *DatasetService) ListDatasets(ctx context.Context, id, name string, page
continue
}
tenantIDs = append(tenantIDs, joinedTenant.TenantID)
joinedTenantIDs = append(joinedTenantIDs, joinedTenant.TenantID)
}
}
kbs, total, err := d.kbDAO.GetByTenantIDs(ctx, dao.DB, tenantIDs, queryUserID, page, pageSize, orderby, desc, keywords, parserID, id, name)
// Mirror Python: ids are checked for accessibility against the joined
// tenants (not the owner-filtered tenant list) before filtering.
if len(ids) > 0 {
accessibleIDs, err := d.kbDAO.GetAccessibleIDs(ctx, dao.DB, joinedTenantIDs, userID, ids)
if err != nil {
return nil, 0, common.CodeServerError, errors.New("database operation failed")
}
accessible := make(map[string]struct{}, len(accessibleIDs))
for _, accessibleID := range accessibleIDs {
accessible[accessibleID] = struct{}{}
}
deniedIDs := make([]string, 0, len(ids))
for _, datasetID := range ids {
if _, ok := accessible[datasetID]; !ok {
deniedIDs = append(deniedIDs, datasetID)
}
}
if len(deniedIDs) > 0 {
return nil, 0, common.CodeDataError, fmt.Errorf("User '%s' lacks permission for datasets: '%s'", userID, strings.Join(deniedIDs, ", "))
}
}
kbs, total, err := d.kbDAO.GetByTenantIDs(ctx, dao.DB, tenantIDs, queryUserID, page, pageSize, orderby, desc, keywords, parserID, id, name, ids)
if err != nil {
return nil, 0, common.CodeServerError, errors.New("database operation failed")
}

View File

@@ -180,6 +180,16 @@ func normalizeDatasetID(id string) (string, error) {
return strings.ReplaceAll(parsedUUID.String(), "-", ""), nil
}
// pythonStringListRepr renders a string slice the way Python prints a list of
// strings, e.g. ['a', 'b'], for error messages that mirror the Python API.
func pythonStringListRepr(items []string) string {
quoted := make([]string, 0, len(items))
for _, item := range items {
quoted = append(quoted, "'"+item+"'")
}
return "[" + strings.Join(quoted, ", ") + "]"
}
func canvasAccessibleForUser(ctx context.Context, userID, canvasID string) (bool, error) {
tenantIDs, _ := dao.NewUserTenantDAO().GetTenantIDsByUserID(ctx, dao.DB, userID)
return dao.NewUserCanvasDAO().Accessible(ctx, dao.DB, canvasID, userID, tenantIDs), nil

View File

@@ -0,0 +1,119 @@
package dataset
import (
"strings"
"testing"
"ragflow/internal/common"
"ragflow/internal/dao"
"ragflow/internal/entity"
)
func testDatasetListService(t *testing.T) *DatasetService {
t.Helper()
return &DatasetService{
kbDAO: dao.NewKnowledgebaseDAO(),
documentDAO: dao.NewDocumentDAO(),
tenantDAO: dao.NewTenantDAO(),
}
}
func TestDatasetServiceListDatasetsFiltersByIDs(t *testing.T) {
db := setupDatasetUpdateTestDB(t)
pushServiceDB(t, db)
insertDatasetUpdateKB(t, "kb-1", "tenant-1", "Alpha")
insertDatasetUpdateKB(t, "kb-2", "tenant-1", "Beta")
ctx := t.Context()
data, total, code, err := testDatasetListService(t).ListDatasets(ctx,
"", "", 1, 30, "create_time", true,
"", nil, "", "tenant-1", []string{"kb-1"},
)
if err != nil {
t.Fatalf("ListDatasets failed: %v", err)
}
if code != common.CodeSuccess {
t.Fatalf("expected success code, got %d", code)
}
if total != 1 || len(data) != 1 {
t.Fatalf("expected exactly one dataset, got total=%d len=%d", total, len(data))
}
if data[0]["id"] != "kb-1" {
t.Fatalf("expected kb-1, got %#v", data[0]["id"])
}
}
func TestDatasetServiceListDatasetsIDsAccessibleViaTeamTenant(t *testing.T) {
db := setupDatasetUpdateTestDB(t)
pushServiceDB(t, db)
insertDatasetUpdateKB(t, "kb-team", "owner-1", "Shared")
if err := dao.DB.Create(&entity.Tenant{ID: "owner-1", Name: sptr("owner"), Status: sptr("1")}).Error; err != nil {
t.Fatalf("insert owner tenant: %v", err)
}
insertDatasetUpdateTeamMember(t, "user-1", "owner-1")
if err := dao.DB.Model(&entity.Knowledgebase{}).
Where("id = ?", "kb-team").
Update("permission", string(entity.TenantPermissionTeam)).Error; err != nil {
t.Fatalf("update kb permission: %v", err)
}
ctx := t.Context()
data, total, code, err := testDatasetListService(t).ListDatasets(ctx,
"", "", 1, 30, "create_time", true,
"", nil, "", "user-1", []string{"kb-team"},
)
if err != nil {
t.Fatalf("ListDatasets failed: %v", err)
}
if code != common.CodeSuccess {
t.Fatalf("expected success code, got %d", code)
}
if total != 1 || len(data) != 1 || data[0]["id"] != "kb-team" {
t.Fatalf("expected the shared dataset, got total=%d data=%#v", total, data)
}
}
func TestDatasetServiceListDatasetsRejectsIDAndIDsTogether(t *testing.T) {
db := setupDatasetUpdateTestDB(t)
pushServiceDB(t, db)
insertDatasetUpdateKB(t, "kb-1", "tenant-1", "Alpha")
ctx := t.Context()
_, _, code, err := testDatasetListService(t).ListDatasets(ctx,
"kb-1", "", 1, 30, "create_time", true,
"", nil, "", "tenant-1", []string{"kb-1"},
)
if err == nil {
t.Fatal("expected id/ids conflict error")
}
if code != common.CodeDataError {
t.Fatalf("expected data error code, got %d", code)
}
expected := "Should not provide both 'id':kb-1 and 'ids'['kb-1']"
if err.Error() != expected {
t.Fatalf("unexpected error: %v", err)
}
}
func TestDatasetServiceListDatasetsRejectsDeniedIDs(t *testing.T) {
db := setupDatasetUpdateTestDB(t)
pushServiceDB(t, db)
insertDatasetUpdateKB(t, "kb-private", "owner-1", "Private")
ctx := t.Context()
_, _, code, err := testDatasetListService(t).ListDatasets(ctx,
"", "", 1, 30, "create_time", true,
"", nil, "", "user-1", []string{"kb-private"},
)
if err == nil {
t.Fatal("expected permission error")
}
if code != common.CodeDataError {
t.Fatalf("expected data error code, got %d", code)
}
expected := "User 'user-1' lacks permission for datasets: 'kb-private'"
if !strings.Contains(err.Error(), expected) {
t.Fatalf("unexpected error: %v", err)
}
}