mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-25 01:43:27 +08:00
## Summary Adds page-range parsing support to the Go-native pipeline path and introduces strict `parse_type` validation for both dataset and document update endpoints. ## What changed ### Pages range parsing - **`internal/utility/pdf_pages.go`** — `NormalizePDFPages`: normalizes raw page ranges (list of `[from,to]` 1-indexed inclusive ranges) into sorted, merged, deduplicated `[][]int`. Invalid ranges are dropped. - **`internal/ingestion/pipeline/pdf_pages.go`** — `NormalizeParserConfigPages`: walks any parser_config map and normalizes `"pages"` values under every component → filetype setup, so the persisted config always carries clean, merged ranges. - **`internal/deepdoc/parser/pdf/parser.go`** — integrates `resolvePagesToProcess` to filter parsed PDF pages by the configured ranges. - Pipeline integration (parser pages): `internal/parser/parser/pdf_parser_common.go`, `chunk_process.go`, plus associated e2e and unit tests. ### Parse type validation (shared logic) - **`internal/service/parser_mode.go`** (new) — `ValidateParseTypeMode`: shared function that validates `parse_type` (1=BuiltIn/parser_id, 2=Pipeline/pipeline_id) and ensures the corresponding field is present. Used by both dataset and document update endpoints. - **`internal/service/dataset/crud.go`** / `update.go` — replaces inline `isPipelineMode`/`isBuiltinMode` computation with the shared `service.ValidateParseTypeMode`. - **`internal/service/document/document_dataset_update.go`** — adds strict `parse_type` validation in `validateDatasetDocumentUpdate`, simplifies the reparse logic to a two-way switch (isBuiltin/isPipeline) now that parse_type is always valid. - **`internal/service/document/document.go`** — adds `ParseType` field to `UpdateDatasetDocumentRequest`. - **`internal/service/document/document_dataset_update.go`** — `updateDocumentParserConfig` fallback path when DSL loading fails. - **`internal/service/parser_mode_test.go`** (new) — test coverage for nil, invalid, and missing-field scenarios. ### Frontend - **`web/src/interfaces/request/document.ts`** — adds `parseType` to `IChangeParserRequestBody`. - **`web/src/hooks/use-document-request.ts`** — `useSetDocumentPipelineParser` sends `parse_type` in the PATCH payload. - **`web/src/pages/dataset/dataset/use-change-document-parser.ts`** — Go/Python branching for the document parser config dialog. - **`web/src/components/document-pipeline-dialog/use-document-pipeline-form.ts`** — `buildSubmitData` returns `parseType` (bugfix: was dropped from the return value). ### Test changes - **Removed**: 2 tests that verified the old "mutually exclusive" error (replaced by `ValidateParseTypeMode` coverage). - **Modified**: 6 tests across document and dataset packages to include `ParseType` in request structs. - **Added**: new e2e tests for pages parsing (`pages_e2e_test.go`, `pdf_parser_pages_e2e_test.go`) and unit tests for `NormalizePDFPages`, `NormalizeParserConfigPages`, `resolvePagesToProcess`. ## Backward compatibility - The `parse_type` field is **required** when `parser_id` or `pipeline_id` is sent. This changes the contract for both dataset and document PATCH endpoints, but aligns the Go backend with the existing frontend behavior (the frontend already sends `parse_type`). Callers that omit `parse_type` when updating parser/pipeline selections will receive a clear error message. - Existing callers that only update fields like `name`, `enabled`, or `meta_fields` are unaffected. - Test updates ensure all known call sites are compliant.
225 lines
6.8 KiB
Go
225 lines
6.8 KiB
Go
package dataset
|
|
|
|
import (
|
|
"strings"
|
|
"testing"
|
|
|
|
"ragflow/internal/common"
|
|
"ragflow/internal/dao"
|
|
"ragflow/internal/entity"
|
|
"ragflow/internal/service"
|
|
)
|
|
|
|
func insertCreateDatasetTenant(t *testing.T, tenantID string) {
|
|
t.Helper()
|
|
var existing entity.Tenant
|
|
if err := dao.DB.Where("id = ?", tenantID).First(&existing).Error; err != nil {
|
|
tn := &entity.Tenant{
|
|
ID: tenantID,
|
|
LLMID: "llm-default",
|
|
EmbdID: "embd-default",
|
|
TenantEmbdID: sptr("embd-1"),
|
|
ASRID: "asr-default",
|
|
Status: sptr("1"),
|
|
}
|
|
if err := dao.DB.Create(tn).Error; err != nil {
|
|
t.Fatalf("insert test tenant: %v", err)
|
|
}
|
|
}
|
|
}
|
|
|
|
func testDatasetCreateService(t *testing.T) *DatasetService {
|
|
t.Helper()
|
|
return &DatasetService{
|
|
kbDAO: dao.NewKnowledgebaseDAO(),
|
|
documentDAO: dao.NewDocumentDAO(),
|
|
connectorDAO: dao.NewConnectorDAO(),
|
|
tenantDAO: dao.NewTenantDAO(),
|
|
}
|
|
}
|
|
|
|
func TestCreateDataset_NoComponentParams(t *testing.T) {
|
|
db := setupServiceTestDB(t)
|
|
pushServiceDB(t, db)
|
|
insertCreateDatasetTenant(t, "tenant-1")
|
|
|
|
chunkMethod := "naive"
|
|
parseType := 1
|
|
result, code, err := testDatasetCreateService(t).CreateDataset(&service.CreateDatasetRequest{
|
|
Name: "ds-no-cp",
|
|
ParserID: &chunkMethod,
|
|
ParseType: &parseType,
|
|
}, "tenant-1")
|
|
if err != nil {
|
|
t.Fatalf("CreateDataset failed: %v", err)
|
|
}
|
|
if code != common.CodeSuccess {
|
|
t.Fatalf("expected success code, got %d", code)
|
|
}
|
|
if result["parser_id"] != strings.TrimSpace(chunkMethod) {
|
|
t.Fatalf("expected parser_id %q, got %#v", chunkMethod, result["parser_id"])
|
|
}
|
|
}
|
|
|
|
func TestCreateDataset_ComponentParamsPopulated(t *testing.T) {
|
|
db := setupServiceTestDB(t)
|
|
pushServiceDB(t, db)
|
|
insertCreateDatasetTenant(t, "tenant-1")
|
|
|
|
chunkMethod := "general"
|
|
parseType := 1
|
|
result, code, err := testDatasetCreateService(t).CreateDataset(&service.CreateDatasetRequest{
|
|
Name: "ds-with-cp",
|
|
ParserID: &chunkMethod,
|
|
ParseType: &parseType,
|
|
}, "tenant-1")
|
|
if err != nil {
|
|
t.Fatalf("CreateDataset failed: %v", err)
|
|
}
|
|
if code != common.CodeSuccess {
|
|
t.Fatalf("expected success code, got %d", code)
|
|
}
|
|
parserConfig, ok := result["parser_config"].(entity.JSONMap)
|
|
if !ok || len(parserConfig) == 0 {
|
|
t.Fatal("expected non-empty parser_config for general pipeline")
|
|
}
|
|
}
|
|
|
|
func TestCreateDataset_ParseTypeBuiltinClearsPipelineID(t *testing.T) {
|
|
db := setupServiceTestDB(t)
|
|
pushServiceDB(t, db)
|
|
insertCreateDatasetTenant(t, "tenant-1")
|
|
|
|
pipelineID := "0123456789abcdef0123456789abcdef"
|
|
parseTypeBuiltin := 1
|
|
chunkMethod := "naive"
|
|
result, code, err := testDatasetCreateService(t).CreateDataset(&service.CreateDatasetRequest{
|
|
Name: "ds-parse-builtin",
|
|
ParserID: &chunkMethod,
|
|
PipelineID: &pipelineID,
|
|
ParseType: &parseTypeBuiltin,
|
|
}, "tenant-1")
|
|
if err != nil {
|
|
t.Fatalf("CreateDataset failed: %v", err)
|
|
}
|
|
if code != common.CodeSuccess {
|
|
t.Fatalf("expected success code, got %d", code)
|
|
}
|
|
if result["parser_id"] != chunkMethod {
|
|
t.Fatalf("expected parser_id %q, got %#v", chunkMethod, result["parser_id"])
|
|
}
|
|
if v, ok := result["pipeline_id"]; ok && v != nil {
|
|
t.Fatalf("expected pipeline_id to be nil for BuiltIn mode, got %#v", v)
|
|
}
|
|
}
|
|
|
|
func TestCreateDataset_ParseTypePipelineIgnoresParserID(t *testing.T) {
|
|
t.Skip("requires canvas seed data in test DB")
|
|
db := setupServiceTestDB(t)
|
|
pushServiceDB(t, db)
|
|
insertCreateDatasetTenant(t, "tenant-1")
|
|
|
|
pipelineID := "0123456789abcdef0123456789abcdef"
|
|
parseTypePipeline := 2
|
|
chunkMethod := "naive"
|
|
result, code, err := testDatasetCreateService(t).CreateDataset(&service.CreateDatasetRequest{
|
|
Name: "ds-parse-pipeline",
|
|
ParserID: &chunkMethod,
|
|
PipelineID: &pipelineID,
|
|
ParseType: &parseTypePipeline,
|
|
}, "tenant-1")
|
|
if err != nil {
|
|
t.Fatalf("CreateDataset failed: %v", err)
|
|
}
|
|
if code != common.CodeSuccess {
|
|
t.Fatalf("expected success code, got %d", code)
|
|
}
|
|
if v, ok := result["parser_id"]; !ok || v == nil {
|
|
} else {
|
|
t.Fatalf("expected parser_id to be empty for Pipeline mode, got %#v", v)
|
|
}
|
|
}
|
|
|
|
func TestCreateDataset_ValidatesName(t *testing.T) {
|
|
db := setupServiceTestDB(t)
|
|
pushServiceDB(t, db)
|
|
insertCreateDatasetTenant(t, "tenant-1")
|
|
|
|
_, code, err := testDatasetCreateService(t).CreateDataset(&service.CreateDatasetRequest{Name: " "}, "tenant-1")
|
|
if err == nil {
|
|
t.Fatal("expected name validation error")
|
|
}
|
|
if code != common.CodeDataError {
|
|
t.Fatalf("expected data error code, got %d", code)
|
|
}
|
|
if err.Error() != "Dataset name can't be empty." {
|
|
t.Fatalf("unexpected error: %v", err)
|
|
}
|
|
}
|
|
|
|
func TestCreateDataset_RejectsDuplicateName(t *testing.T) {
|
|
db := setupServiceTestDB(t)
|
|
pushServiceDB(t, db)
|
|
insertCreateDatasetTenant(t, "tenant-1")
|
|
|
|
if err := db.Create(&entity.Knowledgebase{
|
|
ID: "kb-1",
|
|
TenantID: "tenant-1",
|
|
Name: "Existing",
|
|
ParserID: "naive",
|
|
CreatedBy: "tenant-1",
|
|
Status: sptr(string(entity.StatusValid)),
|
|
}).Error; err != nil {
|
|
t.Fatalf("failed to create existing kb: %v", err)
|
|
}
|
|
|
|
_, code, err := testDatasetCreateService(t).CreateDataset(&service.CreateDatasetRequest{Name: "Existing"}, "tenant-1")
|
|
if err == nil {
|
|
t.Fatal("expected duplicate name error")
|
|
}
|
|
if code != common.CodeDataError {
|
|
t.Fatalf("expected data error code, got %d", code)
|
|
}
|
|
if !strings.Contains(err.Error(), "already exists") {
|
|
t.Fatalf("unexpected error: %v", err)
|
|
}
|
|
}
|
|
|
|
func TestCreateDataset_RejectsInvalidEmbeddingModel(t *testing.T) {
|
|
cases := []struct {
|
|
name string
|
|
embeddingModel string
|
|
expectedMessage string
|
|
}{
|
|
{"empty", "", "Embedding model identifier must follow <model_name>@<provider> format"},
|
|
{"whitespace", " ", "Embedding model identifier must follow <model_name>@<provider> format"},
|
|
{"missing_at", "BAAI/bge-small-en-v1.5Builtin", "Embedding model identifier must follow <model_name>@<provider> format"},
|
|
{"empty_model_name", "@Builtin", "Both model_name and provider must be non-empty strings"},
|
|
{"empty_provider", "BAAI/bge-small-en-v1.5@", "Both model_name and provider must be non-empty strings"},
|
|
{"whitespace_model_name", " @Builtin", "Both model_name and provider must be non-empty strings"},
|
|
{"whitespace_provider", "BAAI/bge-small-en-v1.5@ ", "Both model_name and provider must be non-empty strings"},
|
|
}
|
|
|
|
for _, tc := range cases {
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
db := setupServiceTestDB(t)
|
|
pushServiceDB(t, db)
|
|
insertCreateDatasetTenant(t, "tenant-1")
|
|
|
|
_, code, err := testDatasetCreateService(t).CreateDataset(&service.CreateDatasetRequest{
|
|
Name: "ds-embd-" + tc.name,
|
|
EmbeddingModel: &tc.embeddingModel,
|
|
}, "tenant-1")
|
|
if err == nil {
|
|
t.Fatal("expected embedding model validation error")
|
|
}
|
|
if code != common.CodeDataError {
|
|
t.Fatalf("expected data error code, got %d", code)
|
|
}
|
|
if err.Error() != tc.expectedMessage {
|
|
t.Fatalf("unexpected error: got %q, want %q", err.Error(), tc.expectedMessage)
|
|
}
|
|
})
|
|
}
|
|
}
|