收口 MinerU OCR 任务链与上下文

2026-06-01 10:30:42 +08:00
parent 1481de2018
commit 610b23d3a5
13 changed files with 710 additions and 55 deletions
@@ -1039,6 +1039,169 @@ export const createResourceTabRuntime = (dependencies = {}) => {
    return payload.job || null;
  };

+  const localOcrTaskState = {
+    rootUri: '',
+    jobsBySource: new Map(),
+    drawerOpen: false,
+    eventSource: null,
+  };
+
+  const localOcrJobKey = (job) => String(job?.sourceRootRelativePath || job?.jobId || '').trim();
+
+  const updateLocalOcrTaskState = (job) => {
+    const key = localOcrJobKey(job);
+    if (!key) return;
+    localOcrTaskState.jobsBySource.set(key, job);
+    renderLocalOcrTaskDock();
+  };
+
+  const statusTextForLocalOcrJob = (job) => {
+    const status = String(job?.status || '').trim();
+    if (job?.stageLabel) return String(job.stageLabel);
+    return status === 'done' ? '已识别'
+      : status === 'failed' ? '识别失败'
+        : status === 'stale' ? '来源已变化'
+          : status === 'running' ? '处理中'
+            : status || '未知';
+  };
+
+  const ensureLocalOcrTaskDock = () => {
+    let dock = document.querySelector('[data-testid="mnote-local-ocr-task-dock"]');
+    if (dock instanceof HTMLElement) return dock;
+    dock = document.createElement('section');
+    dock.className = 'mnote-local-ocr-task-dock';
+    dock.setAttribute('data-testid', 'mnote-local-ocr-task-dock');
+    dock.innerHTML = '<button type="button" class="mnote-local-ocr-task-button" data-testid="mnote-local-ocr-task-toggle" aria-expanded="false">OCR 0</button><div class="mnote-local-ocr-task-drawer" data-testid="mnote-local-ocr-task-drawer" hidden><div class="mnote-local-ocr-task-head"><strong>OCR 任务</strong></div><div class="mnote-local-ocr-task-list" data-testid="mnote-local-ocr-task-list"></div></div>';
+    document.body.appendChild(dock);
+    const toggle = dock.querySelector('[data-testid="mnote-local-ocr-task-toggle"]');
+    if (toggle instanceof HTMLButtonElement) {
+      toggle.addEventListener('click', () => {
+        localOcrTaskState.drawerOpen = !localOcrTaskState.drawerOpen;
+        renderLocalOcrTaskDock();
+      });
+    }
+    dock.addEventListener('click', (event) => {
+      const openButton = event.target instanceof Element ? event.target.closest('[data-mnote-local-ocr-task-open]') : null;
+      if (openButton instanceof HTMLElement) {
+        const sourcePath = openButton.getAttribute('data-mnote-local-ocr-task-open') || '';
+        const job = localOcrTaskState.jobsBySource.get(sourcePath) || null;
+        if (job) {
+          void openResourceInActiveTab({
+            kind: 'markdown',
+            title: String(job.ocrRootRelativePath || '').split('/').filter(Boolean).pop() || 'OCR',
+            path: job.ocrRootRelativePath,
+            objectIdentity: `local-ocr:${job.ocrRootRelativePath}`,
+            assetId: `local-ocr:${job.ocrRootRelativePath}`,
+            documentId: job.ownerDocumentId || currentWebShellDocumentId() || '',
+            ownerDocumentId: job.ownerDocumentId || currentWebShellDocumentId() || '',
+            workspaceId: currentWebShellWorkspaceId() || '',
+            sourceKind: 'local_folder',
+            rootUri: localOcrTaskState.rootUri || '',
+            resourceKind: 'markdown',
+          }).catch((error) => console.warn('mnote local OCR 任务打开失败', error));
+        }
+      }
+      const retryButton = event.target instanceof Element ? event.target.closest('[data-mnote-local-ocr-task-retry]') : null;
+      if (retryButton instanceof HTMLElement) {
+        const sourcePath = retryButton.getAttribute('data-mnote-local-ocr-task-retry') || '';
+        const job = localOcrTaskState.jobsBySource.get(sourcePath) || null;
+        if (job) {
+          const entry = {
+            sourceKind: 'local_folder',
+            rootUri: localOcrTaskState.rootUri,
+            path: sourcePath,
+            kind: sourcePath.toLowerCase().endsWith('.pdf') ? 'pdf' : 'image',
+            title: sourcePath.split('/').filter(Boolean).pop() || sourcePath,
+            documentId: job.ownerDocumentId || currentWebShellDocumentId() || '',
+            ownerDocumentId: job.ownerDocumentId || currentWebShellDocumentId() || '',
+            workspaceId: currentWebShellWorkspaceId() || '',
+            localOcrJob: job,
+          };
+          void createLocalOcrJob(entry).catch((error) => console.warn('mnote local OCR 任务重试失败', error));
+        }
+      }
+    });
+    return dock;
+  };
+
+  const renderLocalOcrTaskDock = () => {
+    const dock = ensureLocalOcrTaskDock();
+    const jobs = Array.from(localOcrTaskState.jobsBySource.values())
+      .sort((left, right) => Number(right.updatedAtMs || 0) - Number(left.updatedAtMs || 0));
+    const runningCount = jobs.filter((job) => !['done', 'failed', 'stale'].includes(String(job?.status || ''))).length;
+    const toggle = dock.querySelector('[data-testid="mnote-local-ocr-task-toggle"]');
+    if (toggle instanceof HTMLButtonElement) {
+      toggle.textContent = runningCount > 0 ? `OCR ${runningCount} 处理中` : `OCR ${jobs.length}`;
+      toggle.setAttribute('aria-expanded', localOcrTaskState.drawerOpen ? 'true' : 'false');
+    }
+    const drawer = dock.querySelector('[data-testid="mnote-local-ocr-task-drawer"]');
+    if (drawer instanceof HTMLElement) drawer.hidden = !localOcrTaskState.drawerOpen;
+    const list = dock.querySelector('[data-testid="mnote-local-ocr-task-list"]');
+    if (!(list instanceof HTMLElement)) return;
+    list.replaceChildren();
+    if (!jobs.length) {
+      const empty = document.createElement('div');
+      empty.className = 'mnote-local-ocr-task-empty';
+      empty.textContent = '暂无 OCR 任务';
+      list.appendChild(empty);
+      return;
+    }
+    jobs.forEach((job) => {
+      const row = document.createElement('div');
+      row.className = 'mnote-local-ocr-task-row';
+      row.setAttribute('data-mnote-local-ocr-task-row', String(job.sourceRootRelativePath || ''));
+      row.setAttribute('data-mnote-local-ocr-task-status', String(job.status || ''));
+      const title = String(job.sourceRootRelativePath || '').split('/').filter(Boolean).pop() || 'OCR';
+      row.innerHTML = '<div class="mnote-local-ocr-task-main"><strong></strong><span></span></div><div class="mnote-local-ocr-task-actions"><button type="button" data-mnote-local-ocr-task-open>打开 OCR</button><button type="button" data-mnote-local-ocr-task-retry>重试</button></div>';
+      row.querySelector('strong').textContent = title;
+      row.querySelector('span').textContent = statusTextForLocalOcrJob(job);
+      const open = row.querySelector('[data-mnote-local-ocr-task-open]');
+      if (open instanceof HTMLButtonElement) {
+        open.setAttribute('data-mnote-local-ocr-task-open', String(job.sourceRootRelativePath || ''));
+        open.disabled = !job.ocrRootRelativePath;
+      }
+      const retry = row.querySelector('[data-mnote-local-ocr-task-retry]');
+      if (retry instanceof HTMLButtonElement) {
+        retry.setAttribute('data-mnote-local-ocr-task-retry', String(job.sourceRootRelativePath || ''));
+        retry.hidden = !['failed', 'stale'].includes(String(job.status || ''));
+      }
+      list.appendChild(row);
+    });
+  };
+
+  const loadLocalOcrJobs = async (rootUri) => {
+    const normalizedRoot = String(rootUri || '').trim();
+    if (!normalizedRoot) return;
+    localOcrTaskState.rootUri = normalizedRoot;
+    const url = new URL('/api/local-folder/ocr/jobs', window.location.origin);
+    url.searchParams.set('rootUri', normalizedRoot);
+    const response = await fetch(url.toString(), { cache: 'no-store', headers: { accept: 'application/json' } });
+    const payload = await response.json().catch(() => null);
+    if (!response.ok || !payload || payload.ok !== true) return;
+    (Array.isArray(payload.jobs) ? payload.jobs : []).forEach(updateLocalOcrTaskState);
+    renderLocalOcrTaskDock();
+  };
+
+  const ensureLocalOcrTaskEvents = (rootUri) => {
+    const normalizedRoot = String(rootUri || '').trim();
+    if (!normalizedRoot || typeof window.EventSource !== 'function') return;
+    if (localOcrTaskState.eventSource && localOcrTaskState.rootUri === normalizedRoot) return;
+    if (localOcrTaskState.eventSource) {
+      try { localOcrTaskState.eventSource.close(); } catch (_) {}
+      localOcrTaskState.eventSource = null;
+    }
+    localOcrTaskState.rootUri = normalizedRoot;
+    const url = new URL('/api/local-folder/events', window.location.origin);
+    url.searchParams.set('rootUri', normalizedRoot);
+    const eventSource = new EventSource(url.toString());
+    localOcrTaskState.eventSource = eventSource;
+    eventSource.addEventListener('local_ocr.job.updated', (event) => {
+      let payload = null;
+      try { payload = JSON.parse(event.data || '{}'); } catch (_) {}
+      if (payload?.job) updateLocalOcrTaskState(payload.job);
+    });
+  };
+
  const openLocalOcrSidecar = async (entry, job) => {
    const target = job || entry?.localOcrJob || null;
    const ocrPath = String(target?.ocrRootRelativePath || '').trim();
@@ -1108,6 +1271,7 @@ export const createResourceTabRuntime = (dependencies = {}) => {
    }
    const job = payload.job || null;
    setLocalOcrStatus(entry, String(job?.status || 'done'), job?.stale ? 'OCR 需更新' : 'OCR 已完成', job);
+    if (job) updateLocalOcrTaskState(job);
    return job;
  };

@@ -1146,9 +1310,13 @@ export const createResourceTabRuntime = (dependencies = {}) => {
      });
    }
    setLocalOcrStatus(entry, 'idle', 'OCR 未生成', null);
+    ensureLocalOcrTaskDock();
+    ensureLocalOcrTaskEvents(entry.rootUri);
+    void loadLocalOcrJobs(entry.rootUri).catch(() => undefined);
    void readLocalOcrStatus(entry).then((job) => {
      if (!job) return;
      setLocalOcrStatus(entry, job.stale ? 'stale' : String(job.status || 'done'), job.stale ? 'OCR 需更新' : 'OCR 已完成', job);
+      updateLocalOcrTaskState(job);
    }).catch(() => undefined);
  };