mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-01 21:37:33 +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.
86 lines
2.9 KiB
Go
86 lines
2.9 KiB
Go
package parser
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"image"
|
|
"reflect"
|
|
"testing"
|
|
|
|
deepdocpdf "ragflow/internal/deepdoc/parser/pdf"
|
|
deepdoctype "ragflow/internal/deepdoc/parser/pdf/type"
|
|
)
|
|
|
|
// noopDocAnalyzer is a DocAnalyzer that reports unhealthy and returns empty
|
|
// results, forcing the parser onto the charsToBoxes path. It lets the parser
|
|
// package exercise the deepdoc parser without the real DeepDoc models.
|
|
type noopDocAnalyzer struct{}
|
|
|
|
func (noopDocAnalyzer) DLA(context.Context, image.Image) ([]deepdoctype.DLARegion, error) {
|
|
return nil, nil
|
|
}
|
|
func (noopDocAnalyzer) TSR(context.Context, image.Image) ([]deepdoctype.TSRCell, error) {
|
|
return nil, nil
|
|
}
|
|
func (noopDocAnalyzer) OCRDetect(context.Context, image.Image) ([]deepdoctype.OCRBox, error) {
|
|
return nil, nil
|
|
}
|
|
func (noopDocAnalyzer) OCRRecognize(context.Context, image.Image) ([]deepdoctype.OCRText, error) {
|
|
return nil, nil
|
|
}
|
|
func (noopDocAnalyzer) Health() bool { return false }
|
|
|
|
// TestPDFParser_PagesEndToEnd_FromConfigureFromSetup verifies the full path
|
|
// from a filetype setup map (as delivered by the pipeline override_params)
|
|
// through ConfigureFromSetup -> PDFParser.Pages -> deepdoc ParserConfig.Pages
|
|
// -> resolvePagesToProcess, asserting only the configured page ranges are
|
|
// parsed.
|
|
//
|
|
// This ties together step 2 (ConfigureFromSetup + cfg.Pages plumbing) and
|
|
// step 1 (deepdoc page filtering) at the PDFParser level.
|
|
func TestPDFParser_PagesEndToEnd_FromConfigureFromSetup(t *testing.T) {
|
|
// Build a 10-page mock engine where page N carries the text "pN".
|
|
chars := make(map[int][]deepdoctype.TextChar, 10)
|
|
for i := 0; i < 10; i++ {
|
|
chars[i] = []deepdoctype.TextChar{
|
|
{Text: fmt.Sprintf("p%d", i), X0: 10, X1: 50, Top: 10, Bottom: 30, PageNumber: i},
|
|
}
|
|
}
|
|
eng := &deepdocpdf.MockEngine{NumPages: 10, Chars: chars, RenderW: 100, RenderH: 100}
|
|
|
|
// 1. ConfigureFromSetup reads "pages" exactly as the pipeline would pass
|
|
// it (JSON-decoded []any of []any of float64).
|
|
p := &PDFParser{}
|
|
p.ConfigureFromSetup(map[string]any{
|
|
"pages": []any{
|
|
[]any{float64(1), float64(3)},
|
|
[]any{float64(8), float64(10)},
|
|
},
|
|
})
|
|
wantPages := [][]int{{1, 3}, {8, 10}}
|
|
if !reflect.DeepEqual(p.Pages, wantPages) {
|
|
t.Fatalf("PDFParser.Pages = %v, want %v", p.Pages, wantPages)
|
|
}
|
|
|
|
// 2. Build the deepdoc config the same way ParseWithResult does
|
|
// (cfg.Pages = p.Pages) and run the parser.
|
|
cfg := deepdoctype.DefaultParserConfig()
|
|
cfg.Pages = p.Pages
|
|
docParser := deepdocpdf.NewParser(cfg)
|
|
|
|
result, err := docParser.ParseRaw(context.Background(), eng, noopDocAnalyzer{})
|
|
if err != nil {
|
|
t.Fatalf("ParseRaw: %v", err)
|
|
}
|
|
|
|
// 3. [1,3] -> 0-based 0..2 ; [8,10] -> 7..9
|
|
gotPages := make(map[int]struct{}, len(result.PageHeight))
|
|
for k := range result.PageHeight {
|
|
gotPages[k] = struct{}{}
|
|
}
|
|
want := map[int]struct{}{0: {}, 1: {}, 2: {}, 7: {}, 8: {}, 9: {}}
|
|
if !reflect.DeepEqual(gotPages, want) {
|
|
t.Errorf("PageHeight keys = %v, want %v", gotPages, want)
|
|
}
|
|
}
|