Feat: add initial support for Mindmap (#10310)

### What problem does this PR solve?

Add initial support for Mindmap.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
This commit is contained in:
Yongteng Lei
2025-09-26 19:45:01 +08:00
committed by GitHub
parent 76b1ee2a00
commit 4c0a89f262
8 changed files with 182 additions and 63 deletions

View File

@ -298,21 +298,23 @@ class TaskService(CommonService):
((prog == -1) | (prog > cls.model.progress))
)
).execute()
return
else:
with DB.lock("update_progress", -1):
if info["progress_msg"]:
progress_msg = trim_header_by_lines(task.progress_msg + "\n" + info["progress_msg"], 3000)
cls.model.update(progress_msg=progress_msg).where(cls.model.id == id).execute()
if "progress" in info:
prog = info["progress"]
cls.model.update(progress=prog).where(
(cls.model.id == id) &
(
(cls.model.progress != -1) &
((prog == -1) | (prog > cls.model.progress))
)
).execute()
with DB.lock("update_progress", -1):
if info["progress_msg"]:
progress_msg = trim_header_by_lines(task.progress_msg + "\n" + info["progress_msg"], 3000)
cls.model.update(progress_msg=progress_msg).where(cls.model.id == id).execute()
if "progress" in info:
prog = info["progress"]
cls.model.update(progress=prog).where(
(cls.model.id == id) &
(
(cls.model.progress != -1) &
((prog == -1) | (prog > cls.model.progress))
)
).execute()
process_duration = (datetime.now() - task.begin_at).total_seconds()
cls.model.update(process_duration=process_duration).where(cls.model.id == id).execute()
def queue_tasks(doc: dict, bucket: str, name: str, priority: int):
@ -336,7 +338,14 @@ def queue_tasks(doc: dict, bucket: str, name: str, priority: int):
- Previous task chunks may be reused if available
"""
def new_task():
return {"id": get_uuid(), "doc_id": doc["id"], "progress": 0.0, "from_page": 0, "to_page": 100000000}
return {
"id": get_uuid(),
"doc_id": doc["id"],
"progress": 0.0,
"from_page": 0,
"to_page": 100000000,
"begin_at": datetime.now(),
}
parse_task_array = []
@ -487,6 +496,7 @@ def queue_dataflow(tenant_id:str, flow_id:str, task_id:str, doc_id:str=CANVAS_DE
to_page=100000000,
task_type="dataflow" if not rerun else "dataflow_rerun",
priority=priority,
begin_at=datetime.now(),
)
if doc_id not in [CANVAS_DEBUG_DOC_ID, GRAPH_RAPTOR_FAKE_DOC_ID]:
TaskService.model.delete().where(TaskService.model.doc_id == doc_id).execute()