zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-08-26 01:52:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: Remove hardcoded page limits causing parsing failures on large PDFs (>300 pages) (#14382)

Browse Source 
### What problem does this PR solve?

Fixes #14196

## Problem

When using DeepDOC to parse large PDFs (over 1000 pages), the parser
silently truncated processing at 300 pages due to a hardcoded default
`page_to=299` in `RAGFlowPdfParser.__images__()`. This caused:

- **Errors** on pages beyond the limit
- **Poor image quality** as the parser attempted to compensate with
missing page data
- **Inconsistent chunk splitting** between full PDF imports and partial
imports

Additionally, the codebase scattered magic numbers (`299`, `600`,
`10000`, `100000`, `100000000`, `10000000000`, `10**9`) across 22 files
as sentinel values for "parse all pages", making future maintenance
error-prone.

## Root Cause

```python
# deepdoc/parser/pdf_parser.py (before)
def __images__(self, fnm, zoomin=3, page_from=0, page_to=299, callback=None):
    # Only the first 300 pages were rendered; everything beyond was silently dropped
```

While most callers in `rag/app/*.py` correctly passed `to_page=100000`,
the base class `RAGFlowPdfParser.__call__()` and `parse_into_bboxes()`
invoked `__images__` **without** forwarding `page_from`/`page_to`,
falling back to the restrictive default of 299.

## Solution

### 1. Define constants in `common/constants.py`

```python
MAXIMUM_PAGE_NUMBER = 100000                        # Used by the parsing layer
MAXIMUM_TASK_PAGE_NUMBER = MAXIMUM_PAGE_NUMBER * 1000  # Used by the task/DB layer
```

### 2. Replace all hardcoded sentinel values

| Layer | Files Changed | Old Values | New Value |
|---|---|---|---|
| **Deepdoc parsers** | `pdf_parser.py`, `mineru_parser.py`,
`docling_parser.py`, `opendataloader_parser.py`, `paddleocr_parser.py`,
`docx_parser.py` | `299`, `600`, `10**9`, `100000000` |
`MAXIMUM_PAGE_NUMBER` |
| **Chunk parsers** | `naive.py`, `book.py`, `qa.py`, `one.py`,
`manual.py`, `paper.py`, `presentation.py`, `laws.py`, `resume.py`,
`email.py`, `table.py` | `100000`, `10000`, `10000000000` |
`MAXIMUM_PAGE_NUMBER` |
| **Task/DB layer** | `db_models.py`, `task_service.py`,
`document_service.py`, `file_service.py` | `100000000` |
`MAXIMUM_TASK_PAGE_NUMBER` |

### 3. Fix `parse_into_bboxes()` missing parameters

Added `from_page`/`to_page` parameters to `parse_into_bboxes()` so that
the `rag/flow/parser/parser.py` DeepDOC path no longer falls back to the
restrictive default.

## Files Changed (22)

- `common/constants.py`
- `deepdoc/parser/pdf_parser.py`
- `deepdoc/parser/mineru_parser.py`
- `deepdoc/parser/docling_parser.py`
- `deepdoc/parser/opendataloader_parser.py`
- `deepdoc/parser/paddleocr_parser.py`
- `deepdoc/parser/docx_parser.py`
- `rag/app/naive.py`
- `rag/app/book.py`
- `rag/app/qa.py`
- `rag/app/one.py`
- `rag/app/manual.py`
- `rag/app/paper.py`
- `rag/app/presentation.py`
- `rag/app/laws.py`
- `rag/app/resume.py`
- `rag/app/email.py`
- `rag/app/table.py`
- `api/db/db_models.py`
- `api/db/services/task_service.py`
- `api/db/services/document_service.py`
- `api/db/services/file_service.py`

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring

---------

Signed-off-by: noob <yixiao121314@outlook.com>
This commit is contained in:
euvre
2026-04-27 06:57:20 +00:00
committed by GitHub
parent c3eac4103a
commit 2846a93998
24 changed files with 99 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
api/db/services/task_service.py
View File

@@ -29,7 +29,7 @@ from api.db.services.common_service import CommonService
from api.db.services.document_service import DocumentService
from common.misc_utils import get_uuid
from common.time_utils import current_timestamp
from common.constants import StatusEnum, TaskStatus
from common.constants import StatusEnum, TaskStatus, MAXIMUM_PAGE_NUMBER, MAXIMUM_TASK_PAGE_NUMBER
from deepdoc.parser.excel_parser import RAGFlowExcelParser
from rag.utils.redis_conn import REDIS_CONN
from common import settings
@@ -379,7 +379,7 @@ def queue_tasks(doc: dict, bucket: str, name: str, priority: int):
"doc_id": doc["id"],
"progress": 0.0,
"from_page": 0,
"to_page": 100000000,
"to_page": MAXIMUM_TASK_PAGE_NUMBER,
"begin_at": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
}
@@ -395,8 +395,8 @@ def queue_tasks(doc: dict, bucket: str, name: str, priority: int):
if doc["parser_id"] == "paper":
page_size = doc["parser_config"].get("task_page_size") or 22
if doc["parser_id"] in ["one", "knowledge_graph"] or do_layout != "DeepDOC" or doc["parser_config"].get("toc_extraction", False):
page_size = 10 ** 9
page_ranges = doc["parser_config"].get("pages") or [(1, 10 ** 5)]
page_size = MAXIMUM_TASK_PAGE_NUMBER
page_ranges = doc["parser_config"].get("pages") or [(1, MAXIMUM_PAGE_NUMBER)]
for s, e in page_ranges:
s -= 1
s = max(0, s)
@@ -495,7 +495,7 @@ def reuse_prev_task_chunks(task: dict, prev_tasks: list[dict], chunking_config:
return 0
task["chunk_ids"] = prev_task["chunk_ids"]
task["progress"] = 1.0
if "from_page" in task and "to_page" in task and int(task['to_page']) - int(task['from_page']) >= 10 ** 6:
if "from_page" in task and "to_page" in task and (int(task['to_page']) - int(task['from_page']) >= 10 ** 6 or (int(task['from_page']) == MAXIMUM_TASK_PAGE_NUMBER and int(task['to_page']) == MAXIMUM_TASK_PAGE_NUMBER)):
task["progress_msg"] = f"Page({task['from_page']}~{task['to_page']}): "
else:
task["progress_msg"] = ""
@@ -530,7 +530,7 @@ def queue_dataflow(tenant_id:str, flow_id:str, task_id:str, doc_id:str=CANVAS_DE
id=task_id,
doc_id=doc_id,
from_page=0,
to_page=100000000,
to_page=MAXIMUM_TASK_PAGE_NUMBER,
task_type="dataflow" if not rerun else "dataflow_rerun",
priority=priority,
begin_at= datetime.now().strftime("%Y-%m-%d %H:%M:%S"),