mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-06 07:34:04 +08:00
b59d6e8ba1
## Summary Extract the pipeline-output → search-engine index document mapping helpers out of the `task` package into a dedicated, dependency-light leaf package `internal/ingestion/task/indexdoc`. These functions are pure transforms (they only depend on `common`/`utility`) and are not task-orchestration concerns: - `NormalizeChunks`, `DeepCopyChunks` (was unexported `deepCopyChunks`), `toChunkMaps` → `indexdoc/normalize.go` - `ProcessChunksForPipeline`, `RenameTextToContentWithWeight`, `GetEmbeddingTokenConsumption`, `cleanupConsumedChunkFields`, `mergeChunkMetadata`, `processChunkPositions`, `AggregateTableDocMetadata`, `resolveTableColumnConfig` → `indexdoc/process.go` - `AddPositions` → `indexdoc/position.go` - `EmbeddingTokenConsumptionKey` constant → `indexdoc/constants.go` (task/constants.go keeps only `GRAPH_RAPTOR_FAKE_DOC_ID`) Call sites in `pipeline_executor.go` and `golden_compare.go` now reference the `indexdoc` package; package-task tests qualify the moved symbols. ## Why The `task` package had grown into a "orchestration + pure mapping + debug" mix. Splitting the pure mapping helpers into a leaf package sharpens package boundaries, removes a misleading top-level `ingestion/chunk` candidate (there are already `parser/chunk` and `service/chunk`), and lets the golden tool / future reuse pull in the mapping logic without dragging in `task`'s `dao`/`engine`/`service` dependency graph (Go subpackage import does not pull in the parent). ## Test plan - `build.sh --test ./internal/ingestion/task/...` — **green** (task 4.7s, indexdoc 0.007s), matching the pre-change baseline. - `gofmt` clean; `build.sh` builds both `ragflow-cli` and `ragflow_server` successfully. - Integration/E2E tiers are delegated to CI (need real MySQL/MinIO/ES services). Note: `pipeline_e2e_test.go` has a **pre-existing** compile error (`server.ElasticsearchConfig` / `server.InfinityConfig` are now defined under `internal/server/config/`, not re-exported by `internal/server`). This is unrelated to this change — the diff to that file is only the added `indexdoc` import and the qualified `EmbeddingTokenConsumptionKey` reference.
80 lines
2.2 KiB
Go
80 lines
2.2 KiB
Go
package task
|
|
|
|
import (
|
|
"testing"
|
|
"time"
|
|
|
|
indexdoc "ragflow/internal/ingestion/task/indexdoc"
|
|
)
|
|
|
|
func TestProcessPipelineOutputForGolden_Markdown(t *testing.T) {
|
|
input := map[string]any{
|
|
"markdown": "# Title\n\nContent",
|
|
}
|
|
|
|
result, err := ProcessPipelineOutputForGolden(input, "doc-1", "kb-1", "sample.md")
|
|
if err != nil {
|
|
t.Fatalf("ProcessPipelineOutputForGolden: %v", err)
|
|
}
|
|
|
|
if len(result.NormalizedChunks) != 1 {
|
|
t.Fatalf("normalized len = %d, want 1", len(result.NormalizedChunks))
|
|
}
|
|
if got := result.NormalizedChunks[0]["text"]; got != "# Title\n\nContent" {
|
|
t.Fatalf("normalized text = %v, want markdown string", got)
|
|
}
|
|
if len(result.ProcessedChunks) != 1 {
|
|
t.Fatalf("processed len = %d, want 1", len(result.ProcessedChunks))
|
|
}
|
|
if got := result.ProcessedChunks[0]["content_with_weight"]; got != "# Title\n\nContent" {
|
|
t.Fatalf("content_with_weight = %v, want markdown string", got)
|
|
}
|
|
if _, exists := result.ProcessedChunks[0]["text"]; exists {
|
|
t.Fatal("processed chunk should not keep text key")
|
|
}
|
|
}
|
|
|
|
func TestProcessChunksForPipeline_StableFields(t *testing.T) {
|
|
now := time.Date(2026, 7, 3, 20, 0, 0, 0, time.FixedZone("CST", 8*3600))
|
|
chunks := []map[string]any{
|
|
{
|
|
"text": "hello",
|
|
"questions": "Q1\nQ2",
|
|
"keywords": "kw1,kw2",
|
|
"summary": "sum",
|
|
"metadata": map[string]any{"author": "Alice"},
|
|
},
|
|
}
|
|
|
|
meta, err := indexdoc.ProcessChunksForPipeline(chunks, "doc-1", "kb-1", "sample.md", now)
|
|
if err != nil {
|
|
t.Fatalf("ProcessChunksForPipeline: %v", err)
|
|
}
|
|
|
|
chunk := chunks[0]
|
|
if chunk["doc_id"] != "doc-1" {
|
|
t.Fatalf("doc_id = %v", chunk["doc_id"])
|
|
}
|
|
if chunk["docnm_kwd"] != "sample.md" {
|
|
t.Fatalf("docnm_kwd = %v", chunk["docnm_kwd"])
|
|
}
|
|
if chunk["content_with_weight"] != "hello" {
|
|
t.Fatalf("content_with_weight = %v", chunk["content_with_weight"])
|
|
}
|
|
if _, ok := chunk["id"].(string); !ok {
|
|
t.Fatalf("id should be string, got %T", chunk["id"])
|
|
}
|
|
if _, exists := chunk["questions"]; exists {
|
|
t.Fatal("questions should be removed")
|
|
}
|
|
if _, exists := chunk["keywords"]; exists {
|
|
t.Fatal("keywords should be removed")
|
|
}
|
|
if _, exists := chunk["summary"]; exists {
|
|
t.Fatal("summary should be removed")
|
|
}
|
|
if meta["author"] != "Alice" {
|
|
t.Fatalf("metadata merge failed: %v", meta)
|
|
}
|
|
}
|