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

### 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>

api/db/db_models.py

@@ -55,7 +55,7 @@ from api.utils.configs import deserialize_b64, serialize_b64
 
 from common.time_utils import current_timestamp, timestamp_to_date, date_string_to_timestamp
 from common.decorator import singleton
-from common.constants import ParserType
+from common.constants import ParserType, MAXIMUM_TASK_PAGE_NUMBER
 from common import settings
 
 
@@ -945,7 +945,7 @@ class Task(DataBaseModel):
     id = CharField(max_length=32, primary_key=True)
     doc_id = CharField(max_length=32, null=False, index=True)
     from_page = IntegerField(default=0)
-    to_page = IntegerField(default=100000000)
+    to_page = IntegerField(default=MAXIMUM_TASK_PAGE_NUMBER)
     task_type = CharField(max_length=32, null=False, default="")
     priority = IntegerField(default=0)
 

api/db/services/document_service.py

@@ -35,7 +35,7 @@ from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db.services.doc_metadata_service import DocMetadataService
 from common.misc_utils import get_uuid
 from common.time_utils import current_timestamp, get_format_time
-from common.constants import LLMType, ParserType, StatusEnum, TaskStatus, SVR_CONSUMER_GROUP_NAME
+from common.constants import LLMType, ParserType, StatusEnum, TaskStatus, SVR_CONSUMER_GROUP_NAME, MAXIMUM_PAGE_NUMBER, MAXIMUM_TASK_PAGE_NUMBER
 from rag.nlp import rag_tokenizer, search
 from rag.utils.redis_conn import REDIS_CONN
 from common.doc_store.doc_store_base import OrderByExpr
@@ -1000,8 +1000,8 @@ def queue_raptor_o_graphrag_tasks(sample_doc, ty, priority, fake_doc_id="", doc_
         return {
             "id": get_uuid(),
             "doc_id": fake_doc_id,
-            "from_page": 100000000,
-            "to_page": 100000000,
+            "from_page": MAXIMUM_TASK_PAGE_NUMBER,
+            "to_page": MAXIMUM_TASK_PAGE_NUMBER,
             "task_type": ty,
             "progress_msg": datetime.now().strftime("%H:%M:%S") + " created task " + ty,
             "begin_at": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
@@ -1069,7 +1069,7 @@ def doc_upload_and_parse(conversation_id, file_objs, user_id):
     for d, blob in files:
         doc_nm[d["id"]] = d["name"]
     for d, blob in files:
-        kwargs = {"callback": dummy, "parser_config": parser_config, "from_page": 0, "to_page": 100000, "tenant_id": kb.tenant_id, "lang": kb.language}
+        kwargs = {"callback": dummy, "parser_config": parser_config, "from_page": 0, "to_page": MAXIMUM_PAGE_NUMBER, "tenant_id": kb.tenant_id, "lang": kb.language}
         threads.append(exe.submit(FACTORY.get(d["parser_id"], naive).chunk, d["name"], blob, **kwargs))
 
     for (docinfo, _), th in zip(files, threads):

api/db/services/file_service.py

@@ -36,7 +36,7 @@ from api.db.services.document_service import DocumentService
 from api.db.services.file2document_service import File2DocumentService
 from common.misc_utils import get_uuid
 from common.ssrf_guard import assert_url_is_safe
-from common.constants import TaskStatus, FileSource, ParserType
+from common.constants import TaskStatus, FileSource, ParserType, MAXIMUM_PAGE_NUMBER
 from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db.services.task_service import TaskService
 from api.utils.file_utils import filename_type, read_potential_broken_pdf, thumbnail_img, sanitize_path
@@ -553,7 +553,7 @@ class FileService(CommonService):
 
         FACTORY = {ParserType.PRESENTATION.value: presentation, ParserType.PICTURE.value: picture, ParserType.AUDIO.value: audio, ParserType.EMAIL.value: email}
         parser_config = {"chunk_token_num": 16096, "delimiter": "\n!?;。；！？", "layout_recognize": layout_recognize or "Plain Text"}
-        kwargs = {"lang": "English", "callback": dummy, "parser_config": parser_config, "from_page": 0, "to_page": 100000, "tenant_id": current_user.id if current_user else tenant_id}
+        kwargs = {"lang": "English", "callback": dummy, "parser_config": parser_config, "from_page": 0, "to_page": MAXIMUM_PAGE_NUMBER, "tenant_id": current_user.id if current_user else tenant_id}
         file_type = filename_type(filename)
         if img_base64 and file_type == FileType.VISUAL.value:
             return GptV4.image2base64(blob)

api/db/services/task_service.py

@@ -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"),