mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-05 15:20:30 +08:00
## 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.
54 lines
1.9 KiB
Go
54 lines
1.9 KiB
Go
//
|
|
// Copyright 2026 The InfiniFlow Authors. All Rights Reserved.
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
//
|
|
|
|
package indexdoc
|
|
|
|
// AddPositions adds position fields to a chunk map.
|
|
// Input positions is a flat []float64 grouped as [pn, left, right, top, bottom]
|
|
// every 5 elements. pn is ALREADY 1-indexed — the 0→1 conversion happens
|
|
// once, at the parser boundary (normalizePDFPageNumber for the DeepDoc PDF
|
|
// path; TCADP writes 1-indexed directly). This function is a passthrough: it
|
|
// must NOT add +1, otherwise the PDF path (which already normalized) would
|
|
// double-increment page numbers.
|
|
//
|
|
// Mirrors Python: rag.nlp.add_positions() (Python adds +1 because its
|
|
// callers feed 0-indexed values; the Go pipeline normalizes earlier).
|
|
func AddPositions(chunk map[string]any, positions []float64) {
|
|
if len(positions) == 0 || len(positions)%5 != 0 {
|
|
return
|
|
}
|
|
n := len(positions) / 5
|
|
pageNumInt := make([]int, 0, n)
|
|
topInt := make([]int, 0, n)
|
|
positionInt := make([][]int, 0, n)
|
|
|
|
for i := 0; i < len(positions); i += 5 {
|
|
pn := int(positions[i]) // already 1-indexed
|
|
left := int(positions[i+1])
|
|
right := int(positions[i+2])
|
|
top := int(positions[i+3])
|
|
bottom := int(positions[i+4])
|
|
|
|
pageNumInt = append(pageNumInt, pn)
|
|
topInt = append(topInt, top)
|
|
positionInt = append(positionInt, []int{pn, left, right, top, bottom})
|
|
}
|
|
|
|
chunk["page_num_int"] = pageNumInt
|
|
chunk["top_int"] = topInt
|
|
chunk["position_int"] = positionInt
|
|
}
|