feat(annotation): 优化文本标注分段功能实现

- 新增 getEditorTaskSegmentsUsingGet 接口用于获取任务分段信息 - 移除 SegmentInfo 中的 text、start、end 字段，精简数据结构 - 添加 EditorTaskSegmentsResponse 类型定义用于分段摘要响应 - 实现服务端 get_task_segments 方法，支持分段信息查询 - 重构前端组件缓存机制，使用 segmentSummaryFileRef 管理分段状态 - 优化分段构建逻辑，提取 _build_segment_contexts 公共方法 - 调整后端 _build_text_task 方法中的分段处理流程 - 更新 API 类型定义，统一 RequestParams 和 RequestPayload 类型
2026-02-04 16:59:04 +08:00
parent 394e2bda18
commit cda22a720c
5 changed files with 250 additions and 108 deletions
--- a/frontend/src/pages/DataAnnotation/Annotate/LabelStudioTextEditor.tsx
+++ b/frontend/src/pages/DataAnnotation/Annotate/LabelStudioTextEditor.tsx
@@ -6,6 +6,7 @@ import { useNavigate, useParams } from "react-router";
 import {
  getEditorProjectInfoUsingGet,
  getEditorTaskUsingGet,
+  getEditorTaskSegmentsUsingGet,
  listEditorTasksUsingGet,
  upsertEditorAnnotationUsingPut,
 } from "../annotation.api";
@@ -38,9 +39,6 @@ type LsfMessage = {

 type SegmentInfo = {
  idx: number;
-  text: string;
-  start: number;
-  end: number;
  hasAnnotation: boolean;
  lineIndex: number;
  chunkIndex: number;
@@ -66,10 +64,16 @@ type EditorTaskPayload = {
 type EditorTaskResponse = {
  task?: EditorTaskPayload;
  segmented?: boolean;
-  segments?: SegmentInfo[];
+  totalSegments?: number;
  currentSegmentIndex?: number;
 };

+type EditorTaskSegmentsResponse = {
+  segmented?: boolean;
+  segments?: SegmentInfo[];
+  totalSegments?: number;
+};
+
 type EditorTaskListResponse = {
  content?: EditorTaskListItem[];
  totalElements?: number;
@@ -288,6 +292,7 @@ export default function LabelStudioTextEditor() {
  const segmentStatsCacheRef = useRef<Record<string, SegmentStats>>({});
  const segmentStatsSeqRef = useRef(0);
  const segmentStatsLoadingRef = useRef<Set<string>>(new Set());
+  const segmentSummaryFileRef = useRef<string>("");

  const [loadingProject, setLoadingProject] = useState(true);
  const [loadingTasks, setLoadingTasks] = useState(false);
@@ -358,9 +363,7 @@ export default function LabelStudioTextEditor() {
    if (segmentStatsCacheRef.current[fileId] || segmentStatsLoadingRef.current.has(fileId)) return;
    segmentStatsLoadingRef.current.add(fileId);
    try {
-      const resp = (await getEditorTaskUsingGet(projectId, fileId, {
-        segmentIndex: 0,
-      })) as ApiResponse<EditorTaskResponse>;
+      const resp = (await getEditorTaskSegmentsUsingGet(projectId, fileId)) as ApiResponse<EditorTaskSegmentsResponse>;
      if (segmentStatsSeqRef.current !== seq) return;
      const data = resp?.data;
      if (!data?.segmented) return;
@@ -591,20 +594,38 @@ export default function LabelStudioTextEditor() {
      if (seq !== initSeqRef.current) return;

      // 更新分段状态
-      const segmentIndex = data?.segmented
+      const isSegmented = !!data?.segmented;
+      const segmentIndex = isSegmented
        ? resolveSegmentIndex(data.currentSegmentIndex) ?? 0
        : undefined;
-      if (data?.segmented) {
-        const stats = buildSegmentStats(data.segments);
+      if (isSegmented) {
+        let nextSegments: SegmentInfo[] = [];
+        if (segmentSummaryFileRef.current === fileId && segments.length > 0) {
+          nextSegments = segments;
+        } else {
+          try {
+            const segmentResp = (await getEditorTaskSegmentsUsingGet(projectId, fileId)) as ApiResponse<EditorTaskSegmentsResponse>;
+            if (seq !== initSeqRef.current) return;
+            const segmentData = segmentResp?.data;
+            if (segmentData?.segmented) {
+              nextSegments = Array.isArray(segmentData.segments) ? segmentData.segments : [];
+            }
+          } catch (e) {
+            console.error(e);
+          }
+        }
+        const stats = buildSegmentStats(nextSegments);
        setSegmented(true);
-        setSegments(data.segments || []);
+        setSegments(nextSegments);
        setCurrentSegmentIndex(segmentIndex ?? 0);
        updateSegmentStatsCache(fileId, stats);
+        segmentSummaryFileRef.current = fileId;
      } else {
        setSegmented(false);
        setSegments([]);
        setCurrentSegmentIndex(0);
        updateSegmentStatsCache(fileId, null);
+        segmentSummaryFileRef.current = fileId;
      }

      const taskData = {
@@ -664,7 +685,7 @@ export default function LabelStudioTextEditor() {
    } finally {
      if (seq === initSeqRef.current) setLoadingTaskDetail(false);
    }
-  }, [iframeReady, message, postToIframe, project, projectId, updateSegmentStatsCache]);
+  }, [iframeReady, message, postToIframe, project, projectId, segments, updateSegmentStatsCache]);

  const advanceAfterSave = useCallback(async (fileId: string, segmentIndex?: number) => {
    if (!fileId) return;
@@ -979,6 +1000,7 @@ export default function LabelStudioTextEditor() {
    setSegmented(false);
    setSegments([]);
    setCurrentSegmentIndex(0);
+    segmentSummaryFileRef.current = "";
    savedSnapshotsRef.current = {};
    segmentStatsSeqRef.current += 1;
    segmentStatsCacheRef.current = {};
--- a/frontend/src/pages/DataAnnotation/annotation.api.ts
+++ b/frontend/src/pages/DataAnnotation/annotation.api.ts
@@ -1,20 +1,23 @@
 import { get, post, put, del, download } from "@/utils/request";

-// 导出格式类型
-export type ExportFormat = "json" | "jsonl" | "csv" | "coco" | "yolo";
-
-// 标注任务管理相关接口
-export function queryAnnotationTasksUsingGet(params?: any) {
-  return get("/api/annotation/project", params);
-}
-
-export function createAnnotationTaskUsingPost(data: any) {
-  return post("/api/annotation/project", data);
-}
-
-export function syncAnnotationTaskUsingPost(data: any) {
-  return post(`/api/annotation/task/sync`, data);
-}
+// 导出格式类型
+export type ExportFormat = "json" | "jsonl" | "csv" | "coco" | "yolo";
+
+type RequestParams = Record<string, unknown>;
+type RequestPayload = Record<string, unknown>;
+
+// 标注任务管理相关接口
+export function queryAnnotationTasksUsingGet(params?: RequestParams) {
+  return get("/api/annotation/project", params);
+}
+
+export function createAnnotationTaskUsingPost(data: RequestPayload) {
+  return post("/api/annotation/project", data);
+}
+
+export function syncAnnotationTaskUsingPost(data: RequestPayload) {
+  return post(`/api/annotation/task/sync`, data);
+}

 export function deleteAnnotationTaskByIdUsingDelete(mappingId: string) {
  // Backend expects mapping UUID as path parameter
@@ -25,9 +28,9 @@ export function getAnnotationTaskByIdUsingGet(taskId: string) {
  return get(`/api/annotation/project/${taskId}`);
 }

-export function updateAnnotationTaskByIdUsingPut(taskId: string, data: any) {
-  return put(`/api/annotation/project/${taskId}`, data);
-}
+export function updateAnnotationTaskByIdUsingPut(taskId: string, data: RequestPayload) {
+  return put(`/api/annotation/project/${taskId}`, data);
+}

 // 标签配置管理
 export function getTagConfigUsingGet() {
@@ -35,20 +38,20 @@ export function getTagConfigUsingGet() {
 }

 // 标注模板管理
-export function queryAnnotationTemplatesUsingGet(params?: any) {
-  return get("/api/annotation/template", params);
-}
+export function queryAnnotationTemplatesUsingGet(params?: RequestParams) {
+  return get("/api/annotation/template", params);
+}
+
+export function createAnnotationTemplateUsingPost(data: RequestPayload) {
+  return post("/api/annotation/template", data);
+}

-export function createAnnotationTemplateUsingPost(data: any) {
-  return post("/api/annotation/template", data);
-}
-
-export function updateAnnotationTemplateByIdUsingPut(
-  templateId: string | number,
-  data: any
-) {
-  return put(`/api/annotation/template/${templateId}`, data);
-}
+export function updateAnnotationTemplateByIdUsingPut(
+  templateId: string | number,
+  data: RequestPayload
+) {
+  return put(`/api/annotation/template/${templateId}`, data);
+}

 export function deleteAnnotationTemplateByIdUsingDelete(
  templateId: string | number
@@ -65,27 +68,31 @@ export function getEditorProjectInfoUsingGet(projectId: string) {
  return get(`/api/annotation/editor/projects/${projectId}`);
 }

-export function listEditorTasksUsingGet(projectId: string, params?: any) {
-  return get(`/api/annotation/editor/projects/${projectId}/tasks`, params);
-}
+export function listEditorTasksUsingGet(projectId: string, params?: RequestParams) {
+  return get(`/api/annotation/editor/projects/${projectId}/tasks`, params);
+}

-export function getEditorTaskUsingGet(
-  projectId: string,
-  fileId: string,
-  params?: { segmentIndex?: number }
-) {
-  return get(`/api/annotation/editor/projects/${projectId}/tasks/${fileId}`, params);
-}
+export function getEditorTaskUsingGet(
+  projectId: string,
+  fileId: string,
+  params?: { segmentIndex?: number }
+) {
+  return get(`/api/annotation/editor/projects/${projectId}/tasks/${fileId}`, params);
+}
+
+export function getEditorTaskSegmentsUsingGet(projectId: string, fileId: string) {
+  return get(`/api/annotation/editor/projects/${projectId}/tasks/${fileId}/segments`);
+}

 export function upsertEditorAnnotationUsingPut(
-  projectId: string,
-  fileId: string,
-  data: {
-    annotation: any;
-    expectedUpdatedAt?: string;
-    segmentIndex?: number;
-  }
-) {
+  projectId: string,
+  fileId: string,
+  data: {
+    annotation: Record<string, unknown>;
+    expectedUpdatedAt?: string;
+    segmentIndex?: number;
+  }
+) {
  return put(`/api/annotation/editor/projects/${projectId}/tasks/${fileId}/annotation`, data);
 }