feat(workspaces): reveal PDF citations at cited pages #685
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -28,6 +28,7 @@ import { | |
| ScrollPluginPackage, | ||
| ScrollStrategy, | ||
| useScroll, | ||
| useScrollCapability, | ||
| } from "@embedpdf/plugin-scroll/react"; | ||
| import { | ||
| SelectionPluginPackage, | ||
|
|
@@ -44,7 +45,10 @@ import { | |
| WorkspaceCaptureViewerFrame, | ||
| } from "#/features/workspaces/components/WorkspaceCaptureChrome"; | ||
| import { useFileItemToolbar } from "#/features/workspaces/components/WorkspaceItemToolbarSlot"; | ||
| import { | ||
| useWorkspacePaneHotkey, | ||
| useWorkspacePaneRuntime, | ||
| } from "#/features/workspaces/components/WorkspacePaneRuntime"; | ||
| import { WorkspacePdfAskSelectionMenu } from "#/features/workspaces/components/WorkspacePdfAskSelectionMenu"; | ||
| import { | ||
| WorkspacePdfCaptureInteractionMode, | ||
|
|
@@ -55,6 +59,7 @@ import { WorkspacePdfPageControl } from "#/features/workspaces/components/Worksp | |
| import { useWorkspaceViewCapabilities } from "#/features/workspaces/components/workspace-view-policy"; | ||
| import { createCaptureAttachmentFile } from "#/features/workspaces/components/workspace-region-capture"; | ||
| import { stageCaptureAttachmentToComposerWithFeedback } from "#/features/workspaces/composer/workspace-composer-actions"; | ||
| import { useWorkspacePdfPageRevealRequest } from "#/features/workspaces/locations/workspace-location-context"; | ||
| import type { WorkspaceItem } from "#/features/workspaces/model/types"; | ||
| import { getWorkspaceFileContentUrl } from "#/features/workspaces/model/workspace-file"; | ||
| import { | ||
|
|
@@ -102,11 +107,11 @@ type WorkspacePdfInteractions = { | |
|
|
||
| export default function WorkspacePdfViewer({ | ||
| item, | ||
| viewInstanceId, | ||
| workspaceId, | ||
| }: { | ||
| item: WorkspaceItem; | ||
| viewInstanceId: string; | ||
| workspaceId: string; | ||
| }) { | ||
| const fileUrl = getWorkspaceFileContentUrl(workspaceId, item.id); | ||
|
|
@@ -131,7 +136,7 @@ export default function WorkspacePdfViewer({ | |
| : undefined, | ||
| fileName: item.name, | ||
| fileUrl, | ||
| slotId: viewInstanceId, | ||
| }); | ||
|
|
||
| return ( | ||
|
|
@@ -155,6 +160,7 @@ export default function WorkspacePdfViewer({ | |
| itemId={item.id} | ||
| onCaptureModeExit={exitCapture} | ||
| onCaptureModeToggle={toggleCapture} | ||
| viewInstanceId={viewInstanceId} | ||
| workspaceId={workspaceId} | ||
| /> | ||
| ) : ( | ||
|
|
@@ -177,6 +183,7 @@ function WorkspacePdfDocumentLoader({ | |
| itemId, | ||
| onCaptureModeExit, | ||
| onCaptureModeToggle, | ||
| viewInstanceId, | ||
| workspaceId, | ||
| }: { | ||
| activeDocumentId: string | null; | ||
|
|
@@ -187,14 +194,19 @@ function WorkspacePdfDocumentLoader({ | |
| itemId: string; | ||
| onCaptureModeExit: () => void; | ||
| onCaptureModeToggle: () => void; | ||
| viewInstanceId: string; | ||
| workspaceId: string; | ||
| }) { | ||
| const { provides: documentManager } = useDocumentManagerCapability(); | ||
| const { provides: scrollCapability } = useScrollCapability(); | ||
| const paneRuntime = useWorkspacePaneRuntime(); | ||
| const { consume, request } = useWorkspacePdfPageRevealRequest(viewInstanceId); | ||
| const [openError, setOpenError] = useState<{ | ||
| documentId: string; | ||
| message: string; | ||
| } | null>(null); | ||
| const currentOpenError = openError?.documentId === documentId ? openError.message : null; | ||
| const isActive = paneRuntime?.isActive ?? true; | ||
|
Comment on lines
+197
to
+209
There was a problem hiding this comment. 🎯 Functional Correctness | 🟠 Major | 🏗️ Heavy lift 🧩 Analysis chain🏁 Script executed: #!/bin/bash
# Check whether `@embedpdf/plugin-scroll` exposes a synchronous "current layout/ready" query
# that can be checked immediately (avoiding reliance on a fresh onLayoutReady firing).
fd -HI 'plugin-scroll' node_modules/@embedpdf 2>/dev/null
rg -n 'isInitial|onLayoutReady|getState|totalPages' node_modules/@embedpdf/plugin-scroll/dist 2>/dev/null | head -50Repository: ThinkEx-OSS/thinkex Length of output: 157 🏁 Script executed: #!/bin/bash
set -euo pipefail
echo "Repo files of interest:"
git ls-files | rg '(^|/)WorkspacePdfViewer\.tsx$|WorkspaceStandardTabPanes|package\.json|yarn\.lock|pnpm-lock\.yaml|package-lock\.json'
echo
echo "Dependency versions:"
if [ -f package.json ]; then jq '.dependencies, .devDependencies' package.json | rg -n 'embedpdf|react-pdf|pdf|plugin-scroll' -C 2; fi
echo
echo "Inspect WorkspacePdfViewer outline and relevant sections:"
ast-grep outline src/features/workspaces/components/WorkspacePdfViewer.tsx 2>/dev/null || true
wc -l src/features/workspaces/components/WorkspacePdfViewer.tsx
sed -n '1,340p' src/features/workspaces/components/WorkspacePdfViewer.tsx
echo
echo "Inspect WorkspaceStandardTabPanes:"
fd -HI 'WorkspaceStandardTabPanes' . -x sh -c 'echo "FILE: $1"; wc -l "$1"; sed -n "1,220p" "$1"' sh {}
echo
echo "Search revealWorkspaceLocation and related types:"
rg -n "revealWorkspaceLocation|WorkspacePdfPage|useWorkspacePdfPageRevealRequest|onLayoutReady|viewInstanceId|handleScroll" src package.jsonRepository: ThinkEx-OSS/thinkex Length of output: 20236 🌐 Web query:
💡 Result: In the EmbedPDF viewer, the onLayoutReady event is part of the Scroll plugin and is used to perform actions—such as programmatic scrolling—once a document's layout has been fully initialized and is ready for interaction [1][2][3]. The isInitial property is a boolean flag included in the payload of the onLayoutReady event [1][4]. It serves to distinguish between different layout stages: - isInitial is true only on the first layout immediately following the initial document load [1][5]. - isInitial is false on subsequent layouts, such as when switching between tabs or re-rendering the layout [1][5]. Because documents load asynchronously, developers should use the onLayoutReady event rather than attempting to call navigation methods like scrollToPage immediately after initialization [2][6][3]. Checking that isInitial is true ensures that your logic (e.g., jumping to a specific page on load) only executes when the document is first ready [2][4][5]. This pattern was introduced as part of a update that removed the global initialPage configuration option in favor of more flexible, programmatic control [4][5]. Citations:
🏁 Script executed: #!/bin/bash
set -euo pipefail
echo "Inspect workspace navigation / revealWorkspaceLocation:"
wc -l src/features/workspaces/navigation/useWorkspaceNavigation.ts
sed -n '180,290p' src/features/workspaces/navigation/useWorkspaceNavigation.ts
echo
echo "Inspect workspace location context:"
wc -l src/features/workspaces/locations/workspace-location-context.tsx
sed -n '1,120p' src/features/workspaces/locations/workspace-location-context.tsx
echo
echo "Inspect workspace content around pdf viewer path:"
sed -n '380,530p' src/features/workspaces/components/WorkspaceContent.tsx
echo
echo "Search pdfPage references:"
rg -n "pdf-page|pdfPage|pdf-page|locationPage|pageNumber|revealWorkspaceLocation|matchingTab|activeItem" src -C 2Repository: ThinkEx-OSS/thinkex Length of output: 50375 🌐 Web query:
💡 Result: In the EmbedPDF viewer, the onLayoutReady event handler within the scroll plugin is used to handle scrolling after a document has loaded [1][2]. Because document loading is asynchronous, this event ensures that the document structure is calculated and the viewer is ready for interaction before attempting to navigate to a specific position [1][3]. The onLayoutReady event provides a payload containing documentId and isInitial properties [4][5]. The isInitial boolean is a key feature used to differentiate between the first layout following a document's initial load (where isInitial is true) and subsequent layout events, such as those triggered by switching tabs or document re-renders (where isInitial is false) [6][7]. This mechanism was introduced as part of a move to remove the global initialPage configuration option [6][7]. By checking if isInitial is true, developers can safely trigger actions—like scrolling to a specific page—only once during the initial load cycle [1][2]. Example usage in React: const unsubscribe = scrollCapability.onLayoutReady((event) => { if (event.documentId === documentId && event.isInitial) { scrollCapability.forDocument(documentId).scrollToPage({ pageNumber: initialPage, behavior: 'instant', }); } }); Citations:
🌐 Web query:
💡 Result: The terms onLayoutReady and isInitial refer to the API provided by the Citations:
🌐 Web query:
💡 Result: In the Citations:
Check EmbedPDF layout readiness synchronously before relying on For reused inactive PDF tabs, 🤖 Prompt for AI Agents |
||
|
|
||
| useEffect(() => { | ||
| if (!documentManager || documentManager.isDocumentOpen(documentId)) { | ||
|
|
@@ -240,6 +252,46 @@ function WorkspacePdfDocumentLoader({ | |
| }; | ||
| }, [documentId, documentManager, fileName, fileUrl]); | ||
|
|
||
| useEffect(() => { | ||
| if (!request) { | ||
| return; | ||
| } | ||
|
|
||
| if (currentOpenError || request.location.itemId !== documentId) { | ||
| consume(request); | ||
| return; | ||
| } | ||
|
|
||
| if (!isActive || activeDocumentId !== documentId || !scrollCapability) { | ||
| return; | ||
| } | ||
|
|
||
| let handled = false; | ||
|
|
||
| return scrollCapability.onLayoutReady((event) => { | ||
|
There was a problem hiding this comment.
When a citation targets a PDF that is already open and laid out, this effect subscribes to Useful? React with 👍 / 👎. |
||
| if (handled || event.documentId !== documentId) { | ||
| return; | ||
| } | ||
|
|
||
| handled = true; | ||
| if (request.location.pageNumber <= event.totalPages) { | ||
| scrollCapability.forDocument(documentId).scrollToPage({ | ||
| behavior: "instant", | ||
| pageNumber: request.location.pageNumber, | ||
| }); | ||
| } | ||
| consume(request); | ||
| }); | ||
| }, [ | ||
| activeDocumentId, | ||
| consume, | ||
|
Contributor
There was a problem hiding this comment. P3: The Prompt for AI agents |
||
| currentOpenError, | ||
| documentId, | ||
| isActive, | ||
| request, | ||
| scrollCapability, | ||
| ]); | ||
|
|
||
| if (currentOpenError) { | ||
| return ( | ||
| <WorkspacePdfLoadFailure fileName={fileName} fileUrl={fileUrl}> | ||
|
|
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
P2: Citations opened while the workspace is in split presentation will not reveal the page in the target pane: this line identifies the PDF viewer with
pane.id, but the navigation callback stores a workspace tab ID in the reveal request. The request consequently matches no mountedWorkspacePdfViewer. The navigation/reveal flow would need to resolve and return the actual rendered pane instance (or otherwise map the tab to that pane) for split/maximized presentations.Prompt for AI agents