Files
ragflow/internal/ingestion/task/position.go

54 lines
1.9 KiB
Go
Raw Normal View History

//
// 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 task
// AddPositions adds position fields to a chunk map.
// Input positions is a flat []float64 grouped as [pn, left, right, top, bottom]
fix: Go ingestion migration batch 5 (Parser 1.1/1.7/2.11, Chunker 1.7/1.8/2.6/2.7, Tokenizer 6x fixes) (#17419) ## Summary Continuation of the Python→Go ingestion pipeline migration (File → Parser → Chunker → Extractor → Tokenizer). Fixes cover Parser, Chunker, and Tokenizer gaps identified. Fix page number (0-indexed and 1-index mixed before fix; use 1-indexed after fix) and chunk order issues. ### Parser - **Slides TCADP (1.7):** `pptx_tcadp.go` + TCADP branch in `pptx_parser.go`/`ppt_parser.go` — PowerPoint files now support `parse_method="tcadp"` via the TCADP cloud service, matching the spreadsheet-family TCADP pattern. PPT containers pass `"PPT"` as fileType (not hardcoded `"PPTX"`). - **Audio default output_format (2.11):** `defaultSetups()` audio default changed from `"text"` to `"json"`, aligning with Python `parser.py:232` and `AllowedOutputFormat["audio"]={"json"}`. - **PDF VLM enhancement (1.1):** `maybeDispatchPDFVisionEnhancement` in `pdf_vision_dispatch.go` enriches image/table items with IMAGE2TEXT model descriptions after PDF parsing, mirroring Python `enhance_media_sections_with_vision`. Semaphore fix: acquire before goroutine start to prevent unbounded goroutine creation. - **json family (2.3):** reclassified as Keep Go — `json_parser.go` is a functional enhancement, not a parity gap. - **page number:** changed from "mixed use of 1-indexed & 0-indexed" to "1-indexed" ### Chunker - **BULLET_PATTERN fallback (1.7):** 4th-level fallback in `resolveTitleLevels` (`title.go`) detects bullet/numbered-list patterns (Chinese legal, numbering, English) when outline + regex levels produce only bodyLevel. Guarded by `allBodyLevel` to never override existing structure. - **Tag/One chunker fields (1.8):** `tag.go` sets `TopInt` from source row index; `one.go` preserves `Positions`/`PDFPositions` from source items. TSV multi-line RowNum fix: tracks `contentStart` for correct row attribution. - **Overlapped_percent normalization (2.6):** `NormalizeOverlappedPercent` in `schema/chunker.go` mirrors Python `common/float_utils.py:50-58` — accepts `[0,1)` fraction or `[0,90]` percent, normalizes to canonical `[0,90]`. - **Paragraph splitting (2.7):** aligned to Python flow `naive_merge` — `CRLF` normalization, `splitKeepingDelimiter` preserves sentence delimiters, single-section merge with token-budget-governed chunking. - **chunk order:** sort by reading order ### Tokenizer - **Phantom chunk filtering (Omission 2):** `isPhantomChunk` + filter loop in `chunksFromTokenizerUpstream` skips zero-value ChunkDocs. - **Batch size env var (Omission 3):** `embeddingBatchSize()` reads `TOKENIZER_EMBEDDING_BATCH_SIZE`, defaults to 16. - **Summary empty check (Diff 5):** `TrimSpace(s) != ""` → `s != ""`, matching Python truthy check. - **chunk_order_int all paths (Diff 8):** set unconditionally before full_text/embedding branching. - **Timeout default (Diff 10):** `600s` → `60s`, matching Python `@timeout(60)`. - **Small maxTokens truncation (Diff 14):** `truncateForEmbedding` returns `""` when `maxTokens <= 10`, matching Python. ### Code review fixes - Semaphore acquire moved before goroutine in `pdf_vision_dispatch.go` (concurrency control) - Context propagation in `pptx_tcadp.go` (cancellation support) - Test resolver leak fix in `media_dispatch_test.go` (defer restore) - Migration history comments removed per AGENTS.md ## Test plan ``` bash build.sh --test ./internal/parser/parser/... ./internal/ingestion/component/... ``` ## Notes - Migration diff tracking: `docs/migration_python_go_diff.md` - Remaining gaps: Extractor component only (21 items)
2026-07-28 11:12:52 +08:00
// 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.
//
fix: Go ingestion migration batch 5 (Parser 1.1/1.7/2.11, Chunker 1.7/1.8/2.6/2.7, Tokenizer 6x fixes) (#17419) ## Summary Continuation of the Python→Go ingestion pipeline migration (File → Parser → Chunker → Extractor → Tokenizer). Fixes cover Parser, Chunker, and Tokenizer gaps identified. Fix page number (0-indexed and 1-index mixed before fix; use 1-indexed after fix) and chunk order issues. ### Parser - **Slides TCADP (1.7):** `pptx_tcadp.go` + TCADP branch in `pptx_parser.go`/`ppt_parser.go` — PowerPoint files now support `parse_method="tcadp"` via the TCADP cloud service, matching the spreadsheet-family TCADP pattern. PPT containers pass `"PPT"` as fileType (not hardcoded `"PPTX"`). - **Audio default output_format (2.11):** `defaultSetups()` audio default changed from `"text"` to `"json"`, aligning with Python `parser.py:232` and `AllowedOutputFormat["audio"]={"json"}`. - **PDF VLM enhancement (1.1):** `maybeDispatchPDFVisionEnhancement` in `pdf_vision_dispatch.go` enriches image/table items with IMAGE2TEXT model descriptions after PDF parsing, mirroring Python `enhance_media_sections_with_vision`. Semaphore fix: acquire before goroutine start to prevent unbounded goroutine creation. - **json family (2.3):** reclassified as Keep Go — `json_parser.go` is a functional enhancement, not a parity gap. - **page number:** changed from "mixed use of 1-indexed & 0-indexed" to "1-indexed" ### Chunker - **BULLET_PATTERN fallback (1.7):** 4th-level fallback in `resolveTitleLevels` (`title.go`) detects bullet/numbered-list patterns (Chinese legal, numbering, English) when outline + regex levels produce only bodyLevel. Guarded by `allBodyLevel` to never override existing structure. - **Tag/One chunker fields (1.8):** `tag.go` sets `TopInt` from source row index; `one.go` preserves `Positions`/`PDFPositions` from source items. TSV multi-line RowNum fix: tracks `contentStart` for correct row attribution. - **Overlapped_percent normalization (2.6):** `NormalizeOverlappedPercent` in `schema/chunker.go` mirrors Python `common/float_utils.py:50-58` — accepts `[0,1)` fraction or `[0,90]` percent, normalizes to canonical `[0,90]`. - **Paragraph splitting (2.7):** aligned to Python flow `naive_merge` — `CRLF` normalization, `splitKeepingDelimiter` preserves sentence delimiters, single-section merge with token-budget-governed chunking. - **chunk order:** sort by reading order ### Tokenizer - **Phantom chunk filtering (Omission 2):** `isPhantomChunk` + filter loop in `chunksFromTokenizerUpstream` skips zero-value ChunkDocs. - **Batch size env var (Omission 3):** `embeddingBatchSize()` reads `TOKENIZER_EMBEDDING_BATCH_SIZE`, defaults to 16. - **Summary empty check (Diff 5):** `TrimSpace(s) != ""` → `s != ""`, matching Python truthy check. - **chunk_order_int all paths (Diff 8):** set unconditionally before full_text/embedding branching. - **Timeout default (Diff 10):** `600s` → `60s`, matching Python `@timeout(60)`. - **Small maxTokens truncation (Diff 14):** `truncateForEmbedding` returns `""` when `maxTokens <= 10`, matching Python. ### Code review fixes - Semaphore acquire moved before goroutine in `pdf_vision_dispatch.go` (concurrency control) - Context propagation in `pptx_tcadp.go` (cancellation support) - Test resolver leak fix in `media_dispatch_test.go` (defer restore) - Migration history comments removed per AGENTS.md ## Test plan ``` bash build.sh --test ./internal/parser/parser/... ./internal/ingestion/component/... ``` ## Notes - Migration diff tracking: `docs/migration_python_go_diff.md` - Remaining gaps: Extractor component only (21 items)
2026-07-28 11:12:52 +08:00
// 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 {
fix: Go ingestion migration batch 5 (Parser 1.1/1.7/2.11, Chunker 1.7/1.8/2.6/2.7, Tokenizer 6x fixes) (#17419) ## Summary Continuation of the Python→Go ingestion pipeline migration (File → Parser → Chunker → Extractor → Tokenizer). Fixes cover Parser, Chunker, and Tokenizer gaps identified. Fix page number (0-indexed and 1-index mixed before fix; use 1-indexed after fix) and chunk order issues. ### Parser - **Slides TCADP (1.7):** `pptx_tcadp.go` + TCADP branch in `pptx_parser.go`/`ppt_parser.go` — PowerPoint files now support `parse_method="tcadp"` via the TCADP cloud service, matching the spreadsheet-family TCADP pattern. PPT containers pass `"PPT"` as fileType (not hardcoded `"PPTX"`). - **Audio default output_format (2.11):** `defaultSetups()` audio default changed from `"text"` to `"json"`, aligning with Python `parser.py:232` and `AllowedOutputFormat["audio"]={"json"}`. - **PDF VLM enhancement (1.1):** `maybeDispatchPDFVisionEnhancement` in `pdf_vision_dispatch.go` enriches image/table items with IMAGE2TEXT model descriptions after PDF parsing, mirroring Python `enhance_media_sections_with_vision`. Semaphore fix: acquire before goroutine start to prevent unbounded goroutine creation. - **json family (2.3):** reclassified as Keep Go — `json_parser.go` is a functional enhancement, not a parity gap. - **page number:** changed from "mixed use of 1-indexed & 0-indexed" to "1-indexed" ### Chunker - **BULLET_PATTERN fallback (1.7):** 4th-level fallback in `resolveTitleLevels` (`title.go`) detects bullet/numbered-list patterns (Chinese legal, numbering, English) when outline + regex levels produce only bodyLevel. Guarded by `allBodyLevel` to never override existing structure. - **Tag/One chunker fields (1.8):** `tag.go` sets `TopInt` from source row index; `one.go` preserves `Positions`/`PDFPositions` from source items. TSV multi-line RowNum fix: tracks `contentStart` for correct row attribution. - **Overlapped_percent normalization (2.6):** `NormalizeOverlappedPercent` in `schema/chunker.go` mirrors Python `common/float_utils.py:50-58` — accepts `[0,1)` fraction or `[0,90]` percent, normalizes to canonical `[0,90]`. - **Paragraph splitting (2.7):** aligned to Python flow `naive_merge` — `CRLF` normalization, `splitKeepingDelimiter` preserves sentence delimiters, single-section merge with token-budget-governed chunking. - **chunk order:** sort by reading order ### Tokenizer - **Phantom chunk filtering (Omission 2):** `isPhantomChunk` + filter loop in `chunksFromTokenizerUpstream` skips zero-value ChunkDocs. - **Batch size env var (Omission 3):** `embeddingBatchSize()` reads `TOKENIZER_EMBEDDING_BATCH_SIZE`, defaults to 16. - **Summary empty check (Diff 5):** `TrimSpace(s) != ""` → `s != ""`, matching Python truthy check. - **chunk_order_int all paths (Diff 8):** set unconditionally before full_text/embedding branching. - **Timeout default (Diff 10):** `600s` → `60s`, matching Python `@timeout(60)`. - **Small maxTokens truncation (Diff 14):** `truncateForEmbedding` returns `""` when `maxTokens <= 10`, matching Python. ### Code review fixes - Semaphore acquire moved before goroutine in `pdf_vision_dispatch.go` (concurrency control) - Context propagation in `pptx_tcadp.go` (cancellation support) - Test resolver leak fix in `media_dispatch_test.go` (defer restore) - Migration history comments removed per AGENTS.md ## Test plan ``` bash build.sh --test ./internal/parser/parser/... ./internal/ingestion/component/... ``` ## Notes - Migration diff tracking: `docs/migration_python_go_diff.md` - Remaining gaps: Extractor component only (21 items)
2026-07-28 11:12:52 +08:00
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
}