Move pdf-viewer-adapter-spike.tsx, scroll-job.ts (+test), highlight-styles.css and debug-textlayer.css into src/pdf/ (the adapter boundary). Rewrite the spike's @shared import to @citation-evidence/engine/shared and its ./types to ../types. Add src/css.d.ts so tsc accepts side-effect .css imports. Decisions: - adapter stays the explicitly-named PdfSpikeViewer spike; promotion to a production PDFViewerAdapter is registered as T06 follow-on work - viewer libs (pdfjs-dist, react, react-pdf-highlighter-plus) confined to src/pdf/ and exposed only via the evidence-anchor/pdf subpath; the root entrypoint stays pure. Boundary enforced by eslint no-restricted-imports. - ported unit suites (pdf-selector-math round-trip + scroll-job retry) serve as the inspectable harness for capture->selectors->resolve->scroll. Verified: pnpm test (30 passed), typecheck, lint all green. README layout updated. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
424 lines
14 KiB
TypeScript
424 lines
14 KiB
TypeScript
/**
|
||
* Throwaway PDF viewer adapter spike (CE-WP-0002-T02).
|
||
*
|
||
* Purpose: prove that `react-pdf-highlighter-plus` can implement the §5
|
||
* `DocumentViewerAdapter` contract end-to-end (select → save selectors →
|
||
* reload → resolve → scroll → render highlight) without leaking PDF.js
|
||
* types into `src/shared/` or `src/engine/`.
|
||
*
|
||
* This module is the only place in the codebase that imports
|
||
* `react-pdf-highlighter-plus`. The exported React component is consumed
|
||
* by `src/app/SpikeApp.tsx`.
|
||
*
|
||
* Replace before production. T03 (source ingest) + T04 (anchor resolution)
|
||
* will build the real PDFViewerAdapter on top of this lessons-learned.
|
||
*/
|
||
|
||
import {
|
||
createContext,
|
||
useCallback,
|
||
useContext,
|
||
useEffect,
|
||
useMemo,
|
||
useRef,
|
||
type ReactNode,
|
||
} from "react";
|
||
import {
|
||
PdfHighlighter,
|
||
PdfLoader,
|
||
TextHighlight,
|
||
MonitoredHighlightContainer,
|
||
useHighlightContainerContext,
|
||
type Highlight,
|
||
type PdfHighlighterUtils,
|
||
type PdfSelection,
|
||
type ScaledPosition,
|
||
} from "react-pdf-highlighter-plus";
|
||
// pdfjs-dist's own pdf_viewer.css is the authoritative source for
|
||
// text-layer positioning. The version bundled with
|
||
// react-pdf-highlighter-plus is a minimal *override* (missing
|
||
// `position: absolute`, `inset: 0`, and PDF.js 4.x's
|
||
// `--scale-factor` handling) — load the real one first, then the
|
||
// library's overrides on top.
|
||
import "pdfjs-dist/web/pdf_viewer.css";
|
||
import "react-pdf-highlighter-plus/style/style.css";
|
||
import "react-pdf-highlighter-plus/style/pdf_viewer.css";
|
||
import "./highlight-styles.css";
|
||
import "./debug-textlayer.css";
|
||
|
||
import type { NormalizedRect, Selector } from "@citation-evidence/engine/shared";
|
||
import type { AnchorResolution, PdfSelectionCapture, ResolvedAnchorTarget } from "../types";
|
||
import { findPdfRectSelector, selectorsFromPdfCapture, unionRect } from "./pdf-selector-math";
|
||
import { runScrollToHighlightJob } from "./scroll-job";
|
||
|
||
export { selectorsFromPdfCapture };
|
||
|
||
/**
|
||
* Inverse of `selectorsFromPdfCapture`: build a viewer-renderable
|
||
* `Highlight` from stored selectors. The spike's reload path leans on
|
||
* `PdfRectSelector` since it carries page + page-relative rects directly.
|
||
* T04 will own the production resolver and add the text-only paths.
|
||
*/
|
||
function highlightFromSelectors(
|
||
id: string,
|
||
text: string,
|
||
selectors: readonly Selector[],
|
||
): Highlight | null {
|
||
const rectSel = findPdfRectSelector(selectors);
|
||
if (!rectSel) return null;
|
||
const boundingRect = unionRect(rectSel.rects);
|
||
if (!boundingRect) return null;
|
||
const scaledRects = rectSel.rects.map((r) => toScaled(r, rectSel.page));
|
||
return {
|
||
id,
|
||
type: "text",
|
||
content: { text },
|
||
position: {
|
||
boundingRect: toScaled(boundingRect, rectSel.page),
|
||
rects: scaledRects,
|
||
} satisfies ScaledPosition,
|
||
};
|
||
}
|
||
|
||
/**
|
||
* Convert the adapter's `NormalizedRect` (page-relative 0..1) to the
|
||
* `Scaled` shape react-pdf-highlighter-plus expects (also normalized 0..1
|
||
* via width/height). We use a unit page-space of 1×1 — the library
|
||
* computes pixel coords from `pageNumber` and the renderer's actual page
|
||
* dimensions.
|
||
*/
|
||
function toScaled(r: NormalizedRect, page: number) {
|
||
return {
|
||
x1: r.x,
|
||
y1: r.y,
|
||
x2: r.x + r.width,
|
||
y2: r.y + r.height,
|
||
width: 1,
|
||
height: 1,
|
||
pageNumber: page,
|
||
};
|
||
}
|
||
|
||
/** PdfSelection → our domain-neutral `PdfSelectionCapture`. */
|
||
function captureFromPdfSelection(sel: PdfSelection): PdfSelectionCapture {
|
||
const page = sel.position.boundingRect.pageNumber;
|
||
const rects = sel.position.rects.map<NormalizedRect>((r) => ({
|
||
x: r.x1 / r.width,
|
||
y: r.y1 / r.height,
|
||
width: (r.x2 - r.x1) / r.width,
|
||
height: (r.y2 - r.y1) / r.height,
|
||
}));
|
||
const br = sel.position.boundingRect;
|
||
const boundingRect: NormalizedRect = {
|
||
x: br.x1 / br.width,
|
||
y: br.y1 / br.height,
|
||
width: (br.x2 - br.x1) / br.width,
|
||
height: (br.y2 - br.y1) / br.height,
|
||
};
|
||
return {
|
||
kind: "pdf",
|
||
text: sel.content.text ?? "",
|
||
page,
|
||
rects,
|
||
boundingRect,
|
||
};
|
||
}
|
||
|
||
const ActiveAnnotationContext = createContext<string | null | undefined>(
|
||
undefined,
|
||
);
|
||
const HighlightClickContext = createContext<((annotationId: string) => void) | undefined>(
|
||
undefined,
|
||
);
|
||
|
||
/**
|
||
* Stable highlight row — component type never changes so PdfHighlighter does
|
||
* not remount highlight layers on activation changes (which disturbs scroll).
|
||
* Active/focus styling reads from context instead.
|
||
*/
|
||
function SpikeHighlightContainer(): ReactNode {
|
||
const activeAnnotationId = useContext(ActiveAnnotationContext);
|
||
const onHighlightClicked = useContext(HighlightClickContext);
|
||
const { highlight, isScrolledTo } = useHighlightContainerContext();
|
||
const isActive = activeAnnotationId === highlight.id;
|
||
return (
|
||
<div
|
||
data-highlight-id={highlight.id}
|
||
data-ce-active={isActive ? "true" : "false"}
|
||
style={{ display: "contents" }}
|
||
onClickCapture={(e) => {
|
||
e.stopPropagation();
|
||
onHighlightClicked?.(highlight.id);
|
||
}}
|
||
>
|
||
<MonitoredHighlightContainer>
|
||
<TextHighlight highlight={highlight} isScrolledTo={isScrolledTo} />
|
||
</MonitoredHighlightContainer>
|
||
</div>
|
||
);
|
||
}
|
||
|
||
/**
|
||
* Resolve the rendered DOM rect for a highlight by data attribute, or
|
||
* `null` if the highlight isn't currently rendered (e.g. its page hasn't
|
||
* scrolled into view). Used by `app/forms/HighlightRectBridge` to feed
|
||
* the rect registry as kind="highlight".
|
||
*
|
||
* `display: contents` on the wrapper means it has no box of its own; we
|
||
* union the rects of its children. For TextHighlight that's typically
|
||
* one rect per line.
|
||
*/
|
||
export function getHighlightClientRects(annotationId: string): DOMRect | null {
|
||
if (typeof document === "undefined") return null;
|
||
const wrapper = document.querySelector(`[data-highlight-id="${CSS.escape(annotationId)}"]`);
|
||
if (!wrapper) return null;
|
||
const rects = wrapper.getClientRects();
|
||
if (rects.length === 0) return null;
|
||
let left = Infinity;
|
||
let top = Infinity;
|
||
let right = -Infinity;
|
||
let bottom = -Infinity;
|
||
for (const r of Array.from(rects)) {
|
||
left = Math.min(left, r.left);
|
||
top = Math.min(top, r.top);
|
||
right = Math.max(right, r.right);
|
||
bottom = Math.max(bottom, r.bottom);
|
||
}
|
||
if (!isFinite(left)) return null;
|
||
return new DOMRect(left, top, right - left, bottom - top);
|
||
}
|
||
|
||
export interface PdfSpikeViewerProps {
|
||
/** URL of the PDF to load (served by Vite dev server). */
|
||
readonly pdfUrl: string;
|
||
/** Previously-saved selector sets to restore on mount. */
|
||
readonly storedAnnotations: readonly StoredAnnotation[];
|
||
/** Called when the user produces a new selection. */
|
||
onSelectionCaptured(capture: PdfSelectionCapture, selectors: Selector[]): void;
|
||
/** Annotation id to scroll to and highlight on mount, if any. */
|
||
readonly scrollToAnnotationId?: string;
|
||
/**
|
||
* Bumps when the same annotation should be re-scrolled (e.g. repeat click).
|
||
* Format is opaque — typically `${annotationId}:${version}`.
|
||
*/
|
||
readonly scrollRequestKey?: string;
|
||
/**
|
||
* Annotation id currently focused. The matching highlight gets a
|
||
* thicker border (see highlight-styles.css). `null`/undefined means
|
||
* "no active highlight".
|
||
*/
|
||
readonly activeAnnotationId?: string | null;
|
||
/**
|
||
* Called when the user clicks an existing highlight in the page.
|
||
* The receiver typically activates the matching evidence item.
|
||
*/
|
||
onHighlightClicked?(annotationId: string): void;
|
||
/**
|
||
* When true, paint the PDF text-layer spans in light grey so it's
|
||
* obvious which glyphs have a selectable text overlay and which are
|
||
* image-only. Also logs every onSelection event to the console.
|
||
*/
|
||
readonly debugTextLayer?: boolean;
|
||
/**
|
||
* Hide specific PDF.js layers so you can see what sits underneath.
|
||
* Helps diagnose layer-stacking issues (e.g. "is the text layer
|
||
* covering the canvas content?").
|
||
*/
|
||
readonly hideCanvas?: boolean;
|
||
readonly hideTextLayer?: boolean;
|
||
readonly hideAnnotationLayer?: boolean;
|
||
readonly hideXfaLayer?: boolean;
|
||
}
|
||
|
||
/**
|
||
* Nudge the PDF scroll container so `highlight` sits vertically centred.
|
||
* Best-effort: depends on highlight layer DOM being present after scroll.
|
||
*/
|
||
function centerHighlightInViewer(
|
||
utils: PdfHighlighterUtils,
|
||
highlight: Highlight,
|
||
attempt = 0,
|
||
): void {
|
||
const viewer = utils.getViewer();
|
||
const container = viewer?.container as HTMLElement | undefined;
|
||
if (!container) return;
|
||
const rect = getHighlightClientRects(highlight.id);
|
||
if (!rect) {
|
||
if (attempt < 12) {
|
||
requestAnimationFrame(() =>
|
||
centerHighlightInViewer(utils, highlight, attempt + 1),
|
||
);
|
||
}
|
||
return;
|
||
}
|
||
const cRect = container.getBoundingClientRect();
|
||
const highlightCenterY = rect.top + rect.height / 2;
|
||
const containerCenterY = cRect.top + cRect.height / 2;
|
||
const delta = highlightCenterY - containerCenterY;
|
||
if (Math.abs(delta) < 4) return;
|
||
container.scrollTop += delta;
|
||
}
|
||
|
||
export interface StoredAnnotation {
|
||
readonly id: string;
|
||
readonly text: string;
|
||
readonly selectors: readonly Selector[];
|
||
}
|
||
|
||
/**
|
||
* The spike's React component. Renders a PDF and:
|
||
* - emits `onSelectionCaptured(capture, selectors)` on every fresh selection
|
||
* - reconstructs and renders `storedAnnotations` immediately on load
|
||
* - scrolls to `scrollToAnnotationId` if its highlight can be reconstructed
|
||
*/
|
||
export function PdfSpikeViewer(props: PdfSpikeViewerProps) {
|
||
const {
|
||
pdfUrl,
|
||
storedAnnotations,
|
||
onSelectionCaptured,
|
||
scrollToAnnotationId,
|
||
scrollRequestKey,
|
||
activeAnnotationId,
|
||
onHighlightClicked,
|
||
debugTextLayer,
|
||
hideCanvas,
|
||
hideTextLayer,
|
||
hideAnnotationLayer,
|
||
hideXfaLayer,
|
||
} = props;
|
||
const onHighlightClickedRef = useRef(onHighlightClicked);
|
||
onHighlightClickedRef.current = onHighlightClicked;
|
||
const handleHighlightClicked = useCallback((annotationId: string) => {
|
||
onHighlightClickedRef.current?.(annotationId);
|
||
}, []);
|
||
const pdfLoaderDocument = useMemo(
|
||
() => ({
|
||
url: pdfUrl,
|
||
// PdfLoader's effect depends on `document` by reference — must be
|
||
// stable across re-renders or the PDF reloads and scroll resets to top.
|
||
cMapUrl: "/cmaps/",
|
||
cMapPacked: true,
|
||
standardFontDataUrl: "/standard_fonts/",
|
||
}),
|
||
[pdfUrl],
|
||
);
|
||
const wrapperClasses = [
|
||
debugTextLayer ? "ce-debug-textlayer" : null,
|
||
hideCanvas ? "ce-hide-canvas" : null,
|
||
hideTextLayer ? "ce-hide-text-layer" : null,
|
||
hideAnnotationLayer ? "ce-hide-annotation-layer" : null,
|
||
hideXfaLayer ? "ce-hide-xfa-layer" : null,
|
||
]
|
||
.filter((c): c is string => c !== null)
|
||
.join(" ");
|
||
const utilsRef = useRef<PdfHighlighterUtils | null>(null);
|
||
const scrollStateRef = useRef({ lastCompletedKey: null as string | null });
|
||
|
||
const highlights = useMemo<Highlight[]>(() => {
|
||
const out: Highlight[] = [];
|
||
const skipped: { id: string; reason: string }[] = [];
|
||
for (const a of storedAnnotations) {
|
||
const h = highlightFromSelectors(a.id, a.text, a.selectors);
|
||
if (h) out.push(h);
|
||
else skipped.push({ id: a.id, reason: "no PdfRectSelector / empty boundingRect" });
|
||
}
|
||
if (debugTextLayer) {
|
||
console.log("[ce] viewer highlights", {
|
||
in: storedAnnotations.length,
|
||
rendered: out.length,
|
||
rendered_detail: out.map((h) => ({
|
||
id: h.id,
|
||
page: h.position.boundingRect.pageNumber,
|
||
bounding: h.position.boundingRect,
|
||
rectCount: h.position.rects.length,
|
||
})),
|
||
skipped,
|
||
});
|
||
}
|
||
return out;
|
||
}, [storedAnnotations, debugTextLayer]);
|
||
|
||
const highlightsRef = useRef(highlights);
|
||
highlightsRef.current = highlights;
|
||
|
||
const highlightsSignature = useMemo(
|
||
() => highlights.map((h) => h.id).join(","),
|
||
[highlights],
|
||
);
|
||
|
||
// Re-render highlight layers when focus moves so `data-ce-active` updates.
|
||
const highlightsForViewer = useMemo(
|
||
() => highlights,
|
||
[highlights, activeAnnotationId],
|
||
);
|
||
|
||
useEffect(() => {
|
||
const requestKey = scrollRequestKey ?? scrollToAnnotationId ?? null;
|
||
if (!requestKey || !scrollToAnnotationId) return;
|
||
if (scrollStateRef.current.lastCompletedKey === requestKey) return;
|
||
|
||
if (debugTextLayer) {
|
||
console.log("[ce] scrollToAnnotation requested", {
|
||
id: scrollToAnnotationId,
|
||
requestKey,
|
||
utilsAvailable: !!utilsRef.current,
|
||
targetFound: !!highlightsRef.current.find((h) => h.id === scrollToAnnotationId),
|
||
knownIds: highlightsRef.current.map((h) => h.id),
|
||
});
|
||
}
|
||
|
||
return runScrollToHighlightJob(
|
||
{ requestKey, annotationId: scrollToAnnotationId },
|
||
{
|
||
getUtils: () => utilsRef.current,
|
||
findHighlight: (id) => highlightsRef.current.find((h) => h.id === id),
|
||
scrollToHighlight: (utils, target) => utils.scrollToHighlight(target),
|
||
centerHighlight: (utils, target) => centerHighlightInViewer(utils, target),
|
||
scheduleFrame: (fn) => requestAnimationFrame(fn),
|
||
},
|
||
scrollStateRef.current,
|
||
);
|
||
}, [scrollToAnnotationId, scrollRequestKey, highlightsSignature, debugTextLayer]);
|
||
|
||
return (
|
||
<div
|
||
className={wrapperClasses.length > 0 ? wrapperClasses : undefined}
|
||
style={{ height: "100%" }}
|
||
>
|
||
<PdfLoader document={pdfLoaderDocument}>
|
||
{(pdfDocument) => (
|
||
<ActiveAnnotationContext.Provider value={activeAnnotationId}>
|
||
<HighlightClickContext.Provider value={handleHighlightClicked}>
|
||
<PdfHighlighter
|
||
pdfDocument={pdfDocument}
|
||
highlights={highlightsForViewer}
|
||
utilsRef={(u) => {
|
||
utilsRef.current = u;
|
||
}}
|
||
onSelection={(selection) => {
|
||
const capture = captureFromPdfSelection(selection);
|
||
const selectors = selectorsFromPdfCapture(capture);
|
||
if (debugTextLayer) {
|
||
console.log("[ce] onSelection", {
|
||
text: capture.text,
|
||
page: capture.page,
|
||
rects: capture.rects,
|
||
selectorTypes: selectors.map((s) => s.type),
|
||
raw: selection,
|
||
});
|
||
}
|
||
onSelectionCaptured(capture, selectors);
|
||
}}
|
||
>
|
||
<SpikeHighlightContainer />
|
||
</PdfHighlighter>
|
||
</HighlightClickContext.Provider>
|
||
</ActiveAnnotationContext.Provider>
|
||
)}
|
||
</PdfLoader>
|
||
</div>
|
||
);
|
||
}
|
||
|
||
// Re-export the §5 contract surface so callers see anchor as one entry point.
|
||
export type { AnchorResolution, ResolvedAnchorTarget, PdfSelectionCapture };
|