From 1ab4d1f0f8b08d82d5739e6bc80464b447b77967 Mon Sep 17 00:00:00 2001 From: suguanYang Date: Thu, 7 May 2026 19:44:12 +0800 Subject: [PATCH] fix: restore worker ci checks --- apps/worker/app/core/tasks/kb_tasks.py | 3 --- apps/worker/app/services/document_parser/doc_parser.py | 1 - apps/worker/app/services/document_parser/md_parser.py | 1 - .../shared/services/retrieval/publication_service.py | 6 +++--- packages/shared-python/shared/utils/text_utils.py | 1 + 5 files changed, 4 insertions(+), 8 deletions(-) diff --git a/apps/worker/app/core/tasks/kb_tasks.py b/apps/worker/app/core/tasks/kb_tasks.py index 59c0ed233..edcadc241 100644 --- a/apps/worker/app/core/tasks/kb_tasks.py +++ b/apps/worker/app/core/tasks/kb_tasks.py @@ -688,10 +688,7 @@ def _parse(job_id: str, user_id: str | None): # 1.5. Garbage Collection: Remove redundant local media files try: - from shared.core.database_sync import get_sync_db_context from shared.services.retrieval.publication_service import RetrievalPublicationService - from shared.models.database.job import Job - from sqlalchemy import select with get_sync_db_context() as db: job_record = db.execute(select(Job).where(Job.job_id == job_id)).scalar_one_or_none() diff --git a/apps/worker/app/services/document_parser/doc_parser.py b/apps/worker/app/services/document_parser/doc_parser.py index 4d456131b..5aa877bf1 100755 --- a/apps/worker/app/services/document_parser/doc_parser.py +++ b/apps/worker/app/services/document_parser/doc_parser.py @@ -1,5 +1,4 @@ # pyright: reportArgumentType=false, reportAttributeAccessIssue=false, reportCallIssue=false, reportGeneralTypeIssues=false -import hashlib import io import json import os diff --git a/apps/worker/app/services/document_parser/md_parser.py b/apps/worker/app/services/document_parser/md_parser.py index 404d7b0cb..33f2d484f 100755 --- a/apps/worker/app/services/document_parser/md_parser.py +++ b/apps/worker/app/services/document_parser/md_parser.py @@ -1,5 +1,4 @@ # pyright: reportArgumentType=false, reportAssignmentType=false, reportOptionalIterable=false, reportOptionalMemberAccess=false, reportOptionalOperand=false, reportOptionalSubscript=false -import hashlib import json import os import re diff --git a/packages/shared-python/shared/services/retrieval/publication_service.py b/packages/shared-python/shared/services/retrieval/publication_service.py index aa2d3f675..3c547c0eb 100644 --- a/packages/shared-python/shared/services/retrieval/publication_service.py +++ b/packages/shared-python/shared/services/retrieval/publication_service.py @@ -14,7 +14,7 @@ from uuid import uuid4 from loguru import logger -from sqlalchemy import delete, func, select +from sqlalchemy import delete, select from sqlalchemy.orm import Session from shared.models.database.document import Document, DocumentChunk, DocumentSection @@ -201,7 +201,7 @@ def publish_document_state( job_id: str, job_result_id: str, chunks: List[Dict[str, Any]], - ) -> Optional[Dict[str, str]]: + ) -> Optional[Dict[str, Any]]: job = db.execute(select(Job).where(Job.job_id == job_id)).scalar_one_or_none() if not job: logger.warning(f"Job not found for document publication: {job_id}") @@ -221,7 +221,7 @@ def _publish_document_state_for_job( job: Job, job_result_id: str, chunks: List[Dict[str, Any]], - ) -> Optional[Dict[str, str]]: + ) -> Optional[Dict[str, Any]]: job_metadata = job.job_metadata or {} namespace = job_metadata.get("namespace") or "default" diff --git a/packages/shared-python/shared/utils/text_utils.py b/packages/shared-python/shared/utils/text_utils.py index adbd292fc..4423b67f2 100644 --- a/packages/shared-python/shared/utils/text_utils.py +++ b/packages/shared-python/shared/utils/text_utils.py @@ -20,6 +20,7 @@ class _JiebaModule(Protocol): def lcut(self, sentence: str) -> list[str]: ... + def cut(self, sentence: str) -> list[str]: ... warnings.filterwarnings(