ekuster/visualizador_instanciados
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Inicia integrar Anzograph

Browse Source
This commit is contained in:
Oxy8
2026-02-13 16:39:41 -03:00
parent f3db6af958
commit 343055b7dd
13 changed files with 666 additions and 20472 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@@ -1,2 +1,4 @@
.direnv/ .direnv/
.envrc .envrc
.env
data/

2
Dockerfile
View File

@@ -15,4 +15,4 @@ COPY . .
EXPOSE 5173 EXPOSE 5173
# Compute layout, then start the dev server with --host for external access # Compute layout, then start the dev server with --host for external access
CMD ["sh", "-c", "npm run layout && npm run dev -- --host"] CMD ["sh", "-c", "npm run dev -- --host"]

18
docker-compose.yml
View File

@@ -1,9 +1,23 @@
services: services:
app: app:
build: . build: .
depends_on:
- anzograph
ports: ports:
- "5173:5173" - "5173:5173"
env_file:
- .env
command: sh -c "npm run layout && npm run dev -- --host" command: sh -c "npm run layout && npm run dev -- --host"
volumes: volumes:
- .:/app - .:/app:Z
- /app/node_modules # Prevents local node_modules from overwriting the container's - /app/node_modules
anzograph:
image: cambridgesemantics/anzograph:latest
container_name: anzograph
ports:
- "8080:8080"
- "8443:8443"
volumes:
- ./data:/opt/shared-files:Z

2
package.json
View File

@@ -7,7 +7,7 @@
"dev": "vite", "dev": "vite",
"build": "vite build", "build": "vite build",
"preview": "vite preview", "preview": "vite preview",
"layout": "npx tsx scripts/generate_tree.ts && npx tsx scripts/compute_layout.ts" "layout": "npx tsx scripts/fetch_from_db.ts && npx tsx scripts/compute_layout.ts"
}, },
"dependencies": { "dependencies": {
"@webgpu/types": "^0.1.69", "@webgpu/types": "^0.1.69",

10000
public/node_positions.csv
View File

File diff suppressed because it is too large Load Diff

35
public/primary_edges.csv
View File

@@ -1,36 +1 @@
source,target source,target
1,0
2,0
3,0
4,0
5,1
6,1
7,1
8,1
9,2
10,3
11,3
12,4
13,4
14,5
15,5
16,5
17,6
18,7
19,8
20,8
21,8
22,8
23,9
24,9
25,10
26,11
27,11
28,11
29,12
30,12
31,12
32,12
33,13
34,13
35,13
1 source target
1 0
2 0
3 0
4 0
5 1
6 1
7 1
8 1
9 2
10 3
11 3
12 4
13 4
14 5
15 5
16 5
17 6
18 7
19 8
20 8
21 8
22 8
23 9
24 9
25 10
26 11
27 11
28 11
29 12
30 12
31 12
32 12
33 13
34 13
35 13

9964
public/secondary_edges.csv
View File

File diff suppressed because it is too large Load Diff

1
public/uri_map.csv Normal file
View File

@@ -0,0 +1 @@
id,uri,label,isPrimary
1 id uri label isPrimary

659
scripts/compute_layout.ts
View File

@@ -1,12 +1,17 @@
#!/usr/bin/env npx tsx #!/usr/bin/env npx tsx
/** /**
* Two-Phase Tree Layout * Graph Layout
* *
* Phase 1: Position a primary skeleton (nodes from primary_edges.csv) * Computes a 2D layout for a general graph (not necessarily a tree).
* with generous spacing, then force-simulate the skeleton. *
* Phase 2: Fill in remaining subtrees (secondary_edges.csv) within sectors. * - Primary nodes (from primary_edges.csv) are placed first in a radial layout
* - Remaining nodes are placed near their connected primary neighbors
* - Barnes-Hut force simulation relaxes the layout
* *
* Usage: npm run layout-only (after generating tree) * Reads: primary_edges.csv, secondary_edges.csv
* Writes: node_positions.csv
*
* Usage: npx tsx scripts/compute_layout.ts
*/ */
import { writeFileSync, readFileSync, existsSync } from "fs"; import { writeFileSync, readFileSync, existsSync } from "fs";
@@ -20,28 +25,21 @@ const PUBLIC_DIR = join(__dirname, "..", "public");
// Configuration // Configuration
// ══════════════════════════════════════════════════════════ // ══════════════════════════════════════════════════════════
const ENABLE_FORCE_SIM = true; // Set to false to skip force simulation const ITERATIONS = 200; // Force iterations
const ITERATIONS = 100; // Force iterations const REPULSION_K = 200; // Repulsion strength
const REPULSION_K = 80; // Repulsion strength const EDGE_LENGTH = 80; // Desired edge rest length
const EDGE_LENGTH = 120; // Desired edge rest length const ATTRACTION_K = 0.005; // Spring stiffness for edges
const ATTRACTION_K = 0.0002; // Spring stiffness for edges const INITIAL_MAX_DISP = 20; // Starting max displacement
const INITIAL_MAX_DISP = 15; // Starting max displacement const COOLING = 0.995; // Cooling per iteration
const COOLING = 0.998; // Cooling per iteration
const MIN_DIST = 0.5; const MIN_DIST = 0.5;
const PRINT_EVERY = 10; // Print progress every N iterations const PRINT_EVERY = 20; // Print progress every N iterations
const BH_THETA = 0.8; // Barnes-Hut opening angle
// Scale radius so the tree is nicely spread
const RADIUS_PER_DEPTH = EDGE_LENGTH * 1.2;
// How many times longer skeleton edges are vs. normal edges
const LONG_EDGE_MULTIPLIER = 39.0;
const SKELETON_STEP = RADIUS_PER_DEPTH * LONG_EDGE_MULTIPLIER;
// Primary node radial placement
const PRIMARY_RADIUS = 300; // Radius for primary node ring
// ══════════════════════════════════════════════════════════ // ══════════════════════════════════════════════════════════
// Read tree data from CSVs // Read edge data from CSVs
// ══════════════════════════════════════════════════════════ // ══════════════════════════════════════════════════════════
const primaryPath = join(PUBLIC_DIR, "primary_edges.csv"); const primaryPath = join(PUBLIC_DIR, "primary_edges.csv");
@@ -51,16 +49,14 @@ if (!existsSync(primaryPath) || !existsSync(secondaryPath)) {
console.error(`Error: Missing input files!`); console.error(`Error: Missing input files!`);
console.error(` Expected: ${primaryPath}`); console.error(` Expected: ${primaryPath}`);
console.error(` Expected: ${secondaryPath}`); console.error(` Expected: ${secondaryPath}`);
console.error(` Run 'npx tsx scripts/generate_tree.ts' first.`); console.error(` Run 'npx tsx scripts/fetch_from_db.ts' first.`);
process.exit(1); process.exit(1);
} }
// ── Helper to parse CSV edge list ──
function parseEdges(path: string): Array<[number, number]> { function parseEdges(path: string): Array<[number, number]> {
const content = readFileSync(path, "utf-8"); const content = readFileSync(path, "utf-8");
const lines = content.trim().split("\n"); const lines = content.trim().split("\n");
const edges: Array<[number, number]> = []; const edges: Array<[number, number]> = [];
// Skip header "source,target"
for (let i = 1; i < lines.length; i++) { for (let i = 1; i < lines.length; i++) {
const line = lines[i].trim(); const line = lines[i].trim();
if (!line) continue; if (!line) continue;
@@ -76,409 +72,171 @@ const primaryEdges = parseEdges(primaryPath);
const secondaryEdges = parseEdges(secondaryPath); const secondaryEdges = parseEdges(secondaryPath);
const allEdges = [...primaryEdges, ...secondaryEdges]; const allEdges = [...primaryEdges, ...secondaryEdges];
// ── Reconstruct tree connectivity ── // ══════════════════════════════════════════════════════════
// Build adjacency
// ══════════════════════════════════════════════════════════
const childrenOf = new Map<number, number[]>();
const parentOf = new Map<number, number>();
const allNodes = new Set<number>(); const allNodes = new Set<number>();
const primaryNodes = new Set<number>(); // Nodes involved in primary edges const primaryNodes = new Set<number>();
const neighbors = new Map<number, Set<number>>();
// Process primary edges first (to classify primary nodes) function addNeighbor(a: number, b: number) {
for (const [child, parent] of primaryEdges) { if (!neighbors.has(a)) neighbors.set(a, new Set());
allNodes.add(child); neighbors.get(a)!.add(b);
allNodes.add(parent); if (!neighbors.has(b)) neighbors.set(b, new Set());
primaryNodes.add(child); neighbors.get(b)!.add(a);
primaryNodes.add(parent);
parentOf.set(child, parent);
if (!childrenOf.has(parent)) childrenOf.set(parent, []);
childrenOf.get(parent)!.push(child);
} }
// Process secondary edges for (const [src, dst] of primaryEdges) {
for (const [child, parent] of secondaryEdges) { allNodes.add(src);
allNodes.add(child); allNodes.add(dst);
allNodes.add(parent); primaryNodes.add(src);
primaryNodes.add(dst);
addNeighbor(src, dst);
}
parentOf.set(child, parent); for (const [src, dst] of secondaryEdges) {
if (!childrenOf.has(parent)) childrenOf.set(parent, []); allNodes.add(src);
childrenOf.get(parent)!.push(child); allNodes.add(dst);
addNeighbor(src, dst);
} }
const N = allNodes.size; const N = allNodes.size;
const nodeIds = Array.from(allNodes).sort((a, b) => a - b); const nodeIds = Array.from(allNodes).sort((a, b) => a - b);
// Find root (node with no parent)
// Assuming single root for now. If multiple, pick smallest ID or error.
let root = -1;
for (const node of allNodes) {
if (!parentOf.has(node)) {
root = node;
break;
}
}
if (primaryNodes.size === 0 && N > 0) {
// Edge case: no primary edges?
root = nodeIds[0];
primaryNodes.add(root);
}
console.log(
`Read tree: ${N} nodes, ${allEdges.length} edges (P=${primaryEdges.length}, S=${secondaryEdges.length}), root=${root}`
);
// ══════════════════════════════════════════════════════════
// Compute full-tree subtree sizes
// ══════════════════════════════════════════════════════════
const subtreeSize = new Map<number, number>();
for (const id of nodeIds) subtreeSize.set(id, 1);
{
// Post-order traversal to sum subtree sizes
// Or iterative with two stacks
const stack: Array<{ id: number; phase: "enter" | "exit" }> = [
{ id: root, phase: "enter" },
];
while (stack.length > 0) {
const { id, phase } = stack.pop()!;
if (phase === "enter") {
stack.push({ id, phase: "exit" });
const kids = childrenOf.get(id);
if (kids) for (const kid of kids) stack.push({ id: kid, phase: "enter" });
} else {
const kids = childrenOf.get(id);
if (kids) {
let sum = 0;
for (const kid of kids) sum += subtreeSize.get(kid)!;
subtreeSize.set(id, 1 + sum);
}
}
}
}
// ══════════════════════════════════════════════════════════
// Skeleton = primary nodes
// ══════════════════════════════════════════════════════════
const skeleton = primaryNodes;
console.log(`Skeleton: ${skeleton.size} nodes, ${primaryEdges.length} edges`);
// ══════════════════════════════════════════════════════════
// Position arrays & per-node tracking
// ══════════════════════════════════════════════════════════
// We use dense arrays logic, but node IDs might be sparse if loaded from file.
// However, generate_tree produced sequential IDs starting at 0.
// Let's assume dense 0..N-1 for array indexing, mapped via nodeIds if needed.
// Actually, let's keep it simple: assume maxId < 2*N or use Maps for positions?
// The current code uses Float64Array(N) and assumes `nodeIds[i]` corresponds to index `i`?
// No, the previous code pushed `nodeIds` as `0..N-1`.
// Here, `nodeIds` IS verified to be `0..N-1` because generate_tree did `nextId++`.
// So `nodeIds[i] === i`. We can directly use `x[i]`.
// But if input file has gaps, we'd need a map. To be safe, let's build an `idToIdx` map.
const maxId = Math.max(...nodeIds);
const mapSize = maxId + 1; // Or just use `N` if we remap. Let's remap.
const idToIdx = new Map<number, number>(); const idToIdx = new Map<number, number>();
nodeIds.forEach((id, idx) => idToIdx.set(id, idx)); nodeIds.forEach((id, idx) => idToIdx.set(id, idx));
console.log(
`Read graph: ${N} nodes, ${allEdges.length} edges (P=${primaryEdges.length}, S=${secondaryEdges.length})`
);
console.log(`Primary nodes: ${primaryNodes.size}`);
// ══════════════════════════════════════════════════════════
// Initial placement
// ══════════════════════════════════════════════════════════
const x = new Float64Array(N); const x = new Float64Array(N);
const y = new Float64Array(N); const y = new Float64Array(N);
const nodeRadius = new Float64Array(N); // distance from origin
const sectorStart = new Float64Array(N); // Step 1: Place primary nodes in a radial layout
const sectorEnd = new Float64Array(N); const primaryArr = Array.from(primaryNodes).sort((a, b) => a - b);
const positioned = new Set<number>(); const angleStep = (2 * Math.PI) / Math.max(1, primaryArr.length);
const radius = PRIMARY_RADIUS * Math.max(1, Math.sqrt(primaryArr.length / 10));
for (let i = 0; i < primaryArr.length; i++) {
const idx = idToIdx.get(primaryArr[i])!;
const angle = i * angleStep;
x[idx] = radius * Math.cos(angle);
y[idx] = radius * Math.sin(angle);
}
console.log(`Placed ${primaryArr.length} primary nodes in radial layout (r=${radius.toFixed(0)})`);
// Step 2: Place remaining nodes near their connected neighbors
// BFS from already-placed nodes
const placed = new Set<number>(primaryNodes);
const queue: number[] = [...primaryArr];
let head = 0;
while (head < queue.length) {
const nodeId = queue[head++];
const nodeNeighbors = neighbors.get(nodeId);
if (!nodeNeighbors) continue;
for (const nbId of nodeNeighbors) {
if (placed.has(nbId)) continue;
placed.add(nbId);
// Place near this neighbor with some jitter
const parentIdx = idToIdx.get(nodeId)!;
const childIdx = idToIdx.get(nbId)!;
const jitterAngle = Math.random() * 2 * Math.PI;
const jitterDist = EDGE_LENGTH * (0.5 + Math.random() * 0.5);
x[childIdx] = x[parentIdx] + jitterDist * Math.cos(jitterAngle);
y[childIdx] = y[parentIdx] + jitterDist * Math.sin(jitterAngle);
queue.push(nbId);
}
}
// Handle disconnected nodes (place randomly)
for (const id of nodeIds) {
if (!placed.has(id)) {
const idx = idToIdx.get(id)!;
const angle = Math.random() * 2 * Math.PI;
const r = radius * (1 + Math.random());
x[idx] = r * Math.cos(angle);
y[idx] = r * Math.sin(angle);
placed.add(id);
}
}
console.log(`Initial placement complete: ${placed.size} nodes`);
// ══════════════════════════════════════════════════════════ // ══════════════════════════════════════════════════════════
// Phase 1: Layout skeleton with long edges // Force-directed layout with Barnes-Hut
// ══════════════════════════════════════════════════════════ // ══════════════════════════════════════════════════════════
const rootIdx = idToIdx.get(root)!; console.log(`Running force simulation (${ITERATIONS} iterations, ${N} nodes, ${allEdges.length} edges)...`);
x[rootIdx] = 0;
y[rootIdx] = 0;
nodeRadius[rootIdx] = 0;
sectorStart[rootIdx] = 0;
sectorEnd[rootIdx] = 2 * Math.PI;
positioned.add(root);
{ const t0 = performance.now();
const queue: number[] = [root]; let maxDisp = INITIAL_MAX_DISP;
let head = 0;
while (head < queue.length) { for (let iter = 0; iter < ITERATIONS; iter++) {
const parentId = queue[head++]; const bhRoot = buildBHTree(x, y, N);
const parentIdx = idToIdx.get(parentId)!; const fx = new Float64Array(N);
const kids = childrenOf.get(parentId); const fy = new Float64Array(N);
if (!kids || kids.length === 0) continue;
const aStart = sectorStart[parentIdx]; // 1. Repulsion via Barnes-Hut
const aEnd = sectorEnd[parentIdx]; for (let i = 0; i < N; i++) {
const totalWeight = kids.reduce((s, k) => s + subtreeSize.get(k)!, 0); calcBHForce(bhRoot, x[i], y[i], fx, fy, i, BH_THETA, x, y);
}
// Sort children by subtree size // 2. Edge attraction (spring force)
const sortedKids = [...kids].sort( for (const [aId, bId] of allEdges) {
(a, b) => subtreeSize.get(b)! - subtreeSize.get(a)! const a = idToIdx.get(aId)!;
const b = idToIdx.get(bId)!;
const dx = x[b] - x[a];
const dy = y[b] - y[a];
const d = Math.sqrt(dx * dx + dy * dy) || MIN_DIST;
const displacement = d - EDGE_LENGTH;
const f = ATTRACTION_K * displacement;
const ux = dx / d;
const uy = dy / d;
fx[a] += ux * f;
fy[a] += uy * f;
fx[b] -= ux * f;
fy[b] -= uy * f;
}
// 3. Apply forces with displacement capping
let totalForce = 0;
for (let i = 0; i < N; i++) {
const mag = Math.sqrt(fx[i] * fx[i] + fy[i] * fy[i]);
totalForce += mag;
if (mag > 0) {
const cap = Math.min(maxDisp, mag) / mag;
x[i] += fx[i] * cap;
y[i] += fy[i] * cap;
}
}
maxDisp *= COOLING;
if ((iter + 1) % PRINT_EVERY === 0 || iter === 0) {
console.log(
` iter ${iter + 1}/${ITERATIONS} max_disp=${maxDisp.toFixed(2)} avg_force=${(totalForce / N).toFixed(2)}`
); );
let angle = aStart;
for (const kid of sortedKids) {
const kidIdx = idToIdx.get(kid)!;
const w = subtreeSize.get(kid)!;
const sector = (w / totalWeight) * (aEnd - aStart);
sectorStart[kidIdx] = angle;
sectorEnd[kidIdx] = angle + sector;
// Only position skeleton children now
if (skeleton.has(kid)) {
const midAngle = angle + sector / 2;
const r = nodeRadius[parentIdx] + SKELETON_STEP;
nodeRadius[kidIdx] = r;
x[kidIdx] = r * Math.cos(midAngle);
y[kidIdx] = r * Math.sin(midAngle);
positioned.add(kid);
queue.push(kid); // continue BFS within skeleton
}
angle += sector;
}
}
}
console.log(`Phase 1: Positioned ${positioned.size} skeleton nodes`);
// ══════════════════════════════════════════════════════════
// Force simulation on skeleton only
// ══════════════════════════════════════════════════════════
if (ENABLE_FORCE_SIM && skeleton.size > 1) {
const skeletonArr = Array.from(skeleton);
const skeletonIndices = skeletonArr.map(id => idToIdx.get(id)!);
console.log(
`Force sim on skeleton (${skeletonArr.length} nodes, ${primaryEdges.length} edges)...`
);
const t0 = performance.now();
let maxDisp = INITIAL_MAX_DISP;
for (let iter = 0; iter < ITERATIONS; iter++) {
const fx = new Float64Array(N);
const fy = new Float64Array(N);
// 1. Pairwise repulsion
for (let i = 0; i < skeletonIndices.length; i++) {
const u = skeletonIndices[i];
for (let j = i + 1; j < skeletonIndices.length; j++) {
const v = skeletonIndices[j];
const dx = x[u] - x[v];
const dy = y[u] - y[v];
const d2 = dx * dx + dy * dy;
const d = Math.sqrt(d2) || MIN_DIST;
const f = REPULSION_K / (d2 + MIN_DIST);
fx[u] += (dx / d) * f;
fy[u] += (dy / d) * f;
fx[v] -= (dx / d) * f;
fy[v] -= (dy / d) * f;
}
}
// 2. Edge attraction
for (const [aId, bId] of primaryEdges) {
const a = idToIdx.get(aId)!;
const b = idToIdx.get(bId)!;
const dx = x[b] - x[a];
const dy = y[b] - y[a];
const d = Math.sqrt(dx * dx + dy * dy) || MIN_DIST;
const displacement = d - SKELETON_STEP;
const f = (ATTRACTION_K / LONG_EDGE_MULTIPLIER) * displacement;
const ux = dx / d, uy = dy / d;
fx[a] += ux * f;
fy[a] += uy * f;
fx[b] -= ux * f;
fy[b] -= uy * f;
}
// 3. Apply forces (skip root)
for (const idx of skeletonIndices) {
if (nodeIds[idx] === root) continue;
const mag = Math.sqrt(fx[idx] * fx[idx] + fy[idx] * fy[idx]);
if (mag > 0) {
const cap = Math.min(maxDisp, mag) / mag;
x[idx] += fx[idx] * cap;
y[idx] += fy[idx] * cap;
}
}
maxDisp *= COOLING;
if ((iter + 1) % PRINT_EVERY === 0) {
let totalForce = 0;
for (const idx of skeletonIndices) {
totalForce += Math.sqrt(fx[idx] * fx[idx] + fy[idx] * fy[idx]);
}
console.log(
` iter ${iter + 1}/${ITERATIONS} max_disp=${maxDisp.toFixed(2)} avg_force=${(totalForce / skeletonIndices.length).toFixed(2)}`
);
}
}
const elapsed = performance.now() - t0;
console.log(`Skeleton force sim done in ${(elapsed / 1000).toFixed(1)}s`);
}
// ══════════════════════════════════════════════════════════
// Phase 2: Fill subtrees
// ══════════════════════════════════════════════════════════
{
const queue: number[] = Array.from(positioned);
let head = 0;
while (head < queue.length) {
const parentId = queue[head++];
const parentIdx = idToIdx.get(parentId)!;
const kids = childrenOf.get(parentId);
if (!kids) continue;
const unpositionedKids = kids.filter(k => !positioned.has(k));
if (unpositionedKids.length === 0) continue;
unpositionedKids.sort((a, b) => subtreeSize.get(b)! - subtreeSize.get(a)!);
const px = x[parentIdx];
const py = y[parentIdx];
// Determine available angular sector
// If parent is SKELETON, we reset to full 360 (local root behavior).
// If parent is NORMAL, we strictly use the sector allocated to it by its parent.
const isSkeleton = skeleton.has(parentId);
let currentAngle = isSkeleton ? 0 : sectorStart[parentIdx];
const endAngle = isSkeleton ? 2 * Math.PI : sectorEnd[parentIdx];
const totalSpan = endAngle - currentAngle;
const totalWeight = unpositionedKids.reduce((s, k) => s + subtreeSize.get(k)!, 0);
for (const kid of unpositionedKids) {
const kidIdx = idToIdx.get(kid)!;
const w = subtreeSize.get(kid)!;
// Allocate a portion of the available sector based on subtree weight
const span = (w / totalWeight) * totalSpan;
// Track the sector for this child so ITS children are constrained
sectorStart[kidIdx] = currentAngle;
sectorEnd[kidIdx] = currentAngle + span;
const midAngle = currentAngle + span / 2;
const r = RADIUS_PER_DEPTH;
x[kidIdx] = px + r * Math.cos(midAngle);
y[kidIdx] = py + r * Math.sin(midAngle);
positioned.add(kid);
queue.push(kid);
currentAngle += span;
}
}
}
console.log(`Phase 2: Positioned ${positioned.size} total nodes (of ${N})`);
// ══════════════════════════════════════════════════════════
// Phase 3: Final Relaxation (Force Sim on ALL nodes)
// ══════════════════════════════════════════════════════════
{
console.log(`Phase 3: Final relaxation on ${N} nodes...`);
const FINAL_ITERATIONS = 50;
const FINAL_MAX_DISP = 5.0;
const BH_THETA = 0.5;
// We use slightly weaker forces for final polish
// Keep repulsion same but limit displacement strongly
// Use Barnes-Hut for performance with 10k nodes
for (let iter = 0; iter < FINAL_ITERATIONS; iter++) {
const rootBH = buildBHTree(nodeIds, x, y);
const fx = new Float64Array(N);
const fy = new Float64Array(N);
// 1. Repulsion via Barnes-Hut
for (let i = 0; i < N; i++) {
calcBHForce(rootBH, x[i], y[i], fx, fy, i, BH_THETA);
}
// 2. Attraction edges
// Only attract if displacement > rest length?
// Standard spring: f = k * (d - L)
// L = EDGE_LENGTH for normal, SKELETON_STEP for skeleton?
// We can just use standard EDGE_LENGTH as "rest" for everyone to pull tight?
// Or respect hierarchy?
// With 10k nodes, we just want to relax overlaps.
for (const [uId, vId] of allEdges) {
const u = idToIdx.get(uId)!;
const v = idToIdx.get(vId)!;
const dx = x[v] - x[u];
const dy = y[v] - y[u];
const d = Math.sqrt(dx * dx + dy * dy) || MIN_DIST;
// Identifying if edge is skeletal?
// If u and v both skeleton, use longer length.
// Else normal length.
let restLen = EDGE_LENGTH;
let k = ATTRACTION_K;
if (primaryNodes.has(uId) && primaryNodes.has(vId)) {
restLen = SKELETON_STEP;
k = ATTRACTION_K / LONG_EDGE_MULTIPLIER;
}
const displacement = d - restLen;
const f = k * displacement;
const ux = dx / d, uy = dy / d;
fx[u] += ux * f;
fy[u] += uy * f;
fx[v] -= ux * f;
fy[v] -= uy * f;
}
// 3. Apply forces
let totalDisp = 0;
let maxD = 0;
const currentLimit = FINAL_MAX_DISP * (1 - iter / FINAL_ITERATIONS); // Cool down
for (let i = 0; i < N; i++) {
if (nodeIds[i] === root) continue; // Pin root
const dx = fx[i];
const dy = fy[i];
const dist = Math.sqrt(dx * dx + dy * dy);
if (dist > 0) {
const limit = Math.min(currentLimit, dist);
const scale = limit / dist;
x[i] += dx * scale;
y[i] += dy * scale;
totalDisp += limit;
maxD = Math.max(maxD, limit);
}
}
if (iter % 10 === 0) {
console.log(` Phase 3 iter ${iter}: max movement ${maxD.toFixed(3)}`);
}
} }
} }
const elapsed = performance.now() - t0;
console.log(`Force simulation done in ${(elapsed / 1000).toFixed(1)}s`);
// ══════════════════════════════════════════════════════════ // ══════════════════════════════════════════════════════════
// Write output // Write output
// ══════════════════════════════════════════════════════════ // ══════════════════════════════════════════════════════════
// Write node positions
const outLines: string[] = ["vertex,x,y"]; const outLines: string[] = ["vertex,x,y"];
for (let i = 0; i < N; i++) { for (let i = 0; i < N; i++) {
outLines.push(`${nodeIds[i]},${x[i]},${y[i]}`); outLines.push(`${nodeIds[i]},${x[i]},${y[i]}`);
@@ -487,9 +245,6 @@ for (let i = 0; i < N; i++) {
const outPath = join(PUBLIC_DIR, "node_positions.csv"); const outPath = join(PUBLIC_DIR, "node_positions.csv");
writeFileSync(outPath, outLines.join("\n") + "\n"); writeFileSync(outPath, outLines.join("\n") + "\n");
console.log(`Wrote ${N} positions to ${outPath}`); console.log(`Wrote ${N} positions to ${outPath}`);
// Edges are provided via primary_edges.csv and secondary_edges.csv generated by generate_tree.ts
// We do not write a consolidated edges.csv anymore.
console.log(`Layout complete.`); console.log(`Layout complete.`);
// ══════════════════════════════════════════════════════════ // ══════════════════════════════════════════════════════════
@@ -498,79 +253,61 @@ console.log(`Layout complete.`);
interface BHNode { interface BHNode {
mass: number; mass: number;
x: number; cx: number;
y: number; cy: number;
minX: number; minX: number;
maxX: number; maxX: number;
minY: number; minY: number;
maxY: number; maxY: number;
children?: BHNode[]; // NW, NE, SW, SE children?: BHNode[];
pointIdx?: number; // Leaf node index pointIdx?: number;
} }
function buildBHTree(indices: number[], x: Float64Array, y: Float64Array): BHNode { function buildBHTree(x: Float64Array, y: Float64Array, n: number): BHNode {
// Determine bounds
let minX = Infinity, maxX = -Infinity, minY = Infinity, maxY = -Infinity; let minX = Infinity, maxX = -Infinity, minY = Infinity, maxY = -Infinity;
for (let i = 0; i < x.length; i++) { for (let i = 0; i < n; i++) {
if (x[i] < minX) minX = x[i]; if (x[i] < minX) minX = x[i];
if (x[i] > maxX) maxX = x[i]; if (x[i] > maxX) maxX = x[i];
if (y[i] < minY) minY = y[i]; if (y[i] < minY) minY = y[i];
if (y[i] > maxY) maxY = y[i]; if (y[i] > maxY) maxY = y[i];
} }
// Square bounds for quadtree
const cx = (minX + maxX) / 2; const cx = (minX + maxX) / 2;
const cy = (minY + maxY) / 2; const cy = (minY + maxY) / 2;
const halfDim = Math.max(maxX - minX, maxY - minY) / 2 + 0.01; const halfDim = Math.max(maxX - minX, maxY - minY) / 2 + 0.01;
const root: BHNode = { const root: BHNode = {
mass: 0, x: 0, y: 0, mass: 0, cx: 0, cy: 0,
minX: cx - halfDim, maxX: cx + halfDim, minX: cx - halfDim, maxX: cx + halfDim,
minY: cy - halfDim, maxY: cy + halfDim minY: cy - halfDim, maxY: cy + halfDim,
}; };
for (let i = 0; i < x.length; i++) { for (let i = 0; i < n; i++) {
insertBH(root, i, x[i], y[i]); insertBH(root, i, x[i], y[i], x, y);
} }
calcBHMass(root); calcBHMass(root, x, y);
return root; return root;
} }
function insertBH(node: BHNode, idx: number, px: number, py: number) { function insertBH(node: BHNode, idx: number, px: number, py: number, x: Float64Array, y: Float64Array) {
if (!node.children && node.pointIdx === undefined) { if (!node.children && node.pointIdx === undefined) {
// Empty leaf -> Put point here
node.pointIdx = idx; node.pointIdx = idx;
return; return;
} }
if (!node.children && node.pointIdx !== undefined) { if (!node.children && node.pointIdx !== undefined) {
// Occupied leaf -> Subdivide
const oldIdx = node.pointIdx; const oldIdx = node.pointIdx;
node.pointIdx = undefined; node.pointIdx = undefined;
subdivideBH(node); subdivideBH(node);
// Re-insert old point and new point insertBH(node, oldIdx, x[oldIdx], y[oldIdx], x, y);
// Note: oldIdx needs x,y. But we don't pass array. Wait, BHTree function scope?
// We need explicit x,y access. But passing array everywhere is ugly.
// Hack: The recursive function needs access to global x/y or passed in values.
// But here we are inserting one by one.
// Wait, to re-insert oldIdx, WE NEED ITS COORDS.
// This simple 'insertBH' signature is insufficient unless we capture x/y closure or pass them.
// Let's assume x, y are available globally or we redesign.
// Since this script is top-level, x and y are available in scope!
// But `insertBH` is defined outside main scope if hoisted? No, it's inside module.
// If defined as function `function insertBH`, it captures module scope `x`, `y`?
// `x` and `y` are const Float64Array defined at line ~120.
// So yes, they are captured!
insertBH(node, oldIdx, x[oldIdx], y[oldIdx]);
// Then fall through to insert new point
} }
if (node.children) { if (node.children) {
const mx = (node.minX + node.maxX) / 2; const mx = (node.minX + node.maxX) / 2;
const my = (node.minY + node.maxY) / 2; const my = (node.minY + node.maxY) / 2;
let q = 0; let q = 0;
if (px > mx) q += 1; // East if (px > mx) q += 1;
if (py > my) q += 2; // South if (py > my) q += 2;
insertBH(node.children[q], idx, px, py); insertBH(node.children[q], idx, px, py, x, y);
} }
} }
@@ -578,62 +315,62 @@ function subdivideBH(node: BHNode) {
const mx = (node.minX + node.maxX) / 2; const mx = (node.minX + node.maxX) / 2;
const my = (node.minY + node.maxY) / 2; const my = (node.minY + node.maxY) / 2;
node.children = [ node.children = [
{ mass: 0, x: 0, y: 0, minX: node.minX, maxX: mx, minY: node.minY, maxY: my }, // NW { mass: 0, cx: 0, cy: 0, minX: node.minX, maxX: mx, minY: node.minY, maxY: my },
{ mass: 0, x: 0, y: 0, minX: mx, maxX: node.maxX, minY: node.minY, maxY: my }, // NE { mass: 0, cx: 0, cy: 0, minX: mx, maxX: node.maxX, minY: node.minY, maxY: my },
{ mass: 0, x: 0, y: 0, minX: node.minX, maxX: mx, minY: my, maxY: node.maxY }, // SW { mass: 0, cx: 0, cy: 0, minX: node.minX, maxX: mx, minY: my, maxY: node.maxY },
{ mass: 0, x: 0, y: 0, minX: mx, maxX: node.maxX, minY: my, maxY: node.maxY } // SE { mass: 0, cx: 0, cy: 0, minX: mx, maxX: node.maxX, minY: my, maxY: node.maxY },
]; ];
} }
function calcBHMass(node: BHNode) { function calcBHMass(node: BHNode, x: Float64Array, y: Float64Array) {
if (node.pointIdx !== undefined) { if (node.pointIdx !== undefined) {
node.mass = 1; node.mass = 1;
node.x = x[node.pointIdx]; node.cx = x[node.pointIdx];
node.y = y[node.pointIdx]; node.cy = y[node.pointIdx];
return; return;
} }
if (node.children) { if (node.children) {
let m = 0, cx = 0, cy = 0; let m = 0, sx = 0, sy = 0;
for (const c of node.children) { for (const c of node.children) {
calcBHMass(c); calcBHMass(c, x, y);
m += c.mass; m += c.mass;
cx += c.x * c.mass; sx += c.cx * c.mass;
cy += c.y * c.mass; sy += c.cy * c.mass;
} }
node.mass = m; node.mass = m;
if (m > 0) { if (m > 0) {
node.x = cx / m; node.cx = sx / m;
node.y = cy / m; node.cy = sy / m;
} else { } else {
// Center of box if empty node.cx = (node.minX + node.maxX) / 2;
node.x = (node.minX + node.maxX) / 2; node.cy = (node.minY + node.maxY) / 2;
node.y = (node.minY + node.maxY) / 2;
} }
} }
} }
function calcBHForce(node: BHNode, px: number, py: number, fx: Float64Array, fy: Float64Array, idx: number, theta: number) { function calcBHForce(
const dx = px - node.x; node: BHNode,
const dy = py - node.y; px: number, py: number,
fx: Float64Array, fy: Float64Array,
idx: number, theta: number,
x: Float64Array, y: Float64Array,
) {
const dx = px - node.cx;
const dy = py - node.cy;
const d2 = dx * dx + dy * dy; const d2 = dx * dx + dy * dy;
const dist = Math.sqrt(d2); const dist = Math.sqrt(d2);
const width = node.maxX - node.minX; const width = node.maxX - node.minX;
if (width / dist < theta || !node.children) { if (width / dist < theta || !node.children) {
// Treat as single body if (node.mass > 0 && node.pointIdx !== idx) {
if (node.mass > 0 && (node.pointIdx !== idx)) {
// Apply repulsion
// F = K * mass / dist^2
// Direction: from node to p
const dEff = Math.max(dist, MIN_DIST); const dEff = Math.max(dist, MIN_DIST);
const f = (REPULSION_K * node.mass) / (dEff * dEff); // d^2 repulsion const f = (REPULSION_K * node.mass) / (dEff * dEff);
fx[idx] += (dx / dEff) * f; fx[idx] += (dx / dEff) * f;
fy[idx] += (dy / dEff) * f; fy[idx] += (dy / dEff) * f;
} }
} else { } else {
// Recurse
for (const c of node.children) { for (const c of node.children) {
calcBHForce(c, px, py, fx, fy, idx, theta); calcBHForce(c, px, py, fx, fy, idx, theta, x, y);
} }
} }
} }

390
scripts/fetch_from_db.ts Normal file
View File

@@ -0,0 +1,390 @@
#!/usr/bin/env npx tsx
/**
* Fetch RDF Data from AnzoGraph DB
*
* 1. Query the first 1000 distinct subject URIs
* 2. Fetch all triples where those URIs appear as subject or object
* 3. Identify primary nodes (objects of rdf:type)
* 4. Write primary_edges.csv, secondary_edges.csv, and uri_map.csv
*
* Usage: npx tsx scripts/fetch_from_db.ts [--host http://localhost:8080]
*/
import { writeFileSync } from "fs";
import { join, dirname } from "path";
import { fileURLToPath } from "url";
const __dirname = dirname(fileURLToPath(import.meta.url));
const PUBLIC_DIR = join(__dirname, "..", "public");
// ══════════════════════════════════════════════════════════
// Configuration
// ══════════════════════════════════════════════════════════
const RDF_TYPE = "http://www.w3.org/1999/02/22-rdf-syntax-ns#type";
const BATCH_SIZE = 100; // URIs per VALUES batch query
const MAX_RETRIES = 30; // Wait up to ~120s for AnzoGraph to start
const RETRY_DELAY_MS = 4000;
// Path to TTL file inside the AnzoGraph container (mapped via docker-compose volume)
const DATA_FILE = process.env.SPARQL_DATA_FILE || "file:///opt/shared-files/vkg-materialized.ttl";
// Parse --host flag, default to http://localhost:8080
function getEndpoint(): string {
const hostIdx = process.argv.indexOf("--host");
if (hostIdx !== -1 && process.argv[hostIdx + 1]) {
return process.argv[hostIdx + 1];
}
// Inside Docker, use service name; otherwise localhost
return process.env.SPARQL_HOST || "http://localhost:8080";
}
const SPARQL_ENDPOINT = `${getEndpoint()}/sparql`;
// Auth credentials (AnzoGraph defaults)
const SPARQL_USER = process.env.SPARQL_USER || "admin";
const SPARQL_PASS = process.env.SPARQL_PASS || "Passw0rd1";
const AUTH_HEADER = "Basic " + Buffer.from(`${SPARQL_USER}:${SPARQL_PASS}`).toString("base64");
// ══════════════════════════════════════════════════════════
// SPARQL helpers
// ══════════════════════════════════════════════════════════
interface SparqlBinding {
[key: string]: { type: string; value: string };
}
function sleep(ms: number): Promise<void> {
return new Promise((resolve) => setTimeout(resolve, ms));
}
async function sparqlQuery(query: string, retries = 5): Promise<SparqlBinding[]> {
for (let attempt = 1; attempt <= retries; attempt++) {
const controller = new AbortController();
const timeout = setTimeout(() => controller.abort(), 300_000); // 5 min timeout
try {
const t0 = performance.now();
const response = await fetch(SPARQL_ENDPOINT, {
method: "POST",
headers: {
"Content-Type": "application/x-www-form-urlencoded",
"Accept": "application/sparql-results+json",
"Authorization": AUTH_HEADER,
},
body: "query=" + encodeURIComponent(query),
signal: controller.signal,
});
const t1 = performance.now();
console.log(` [sparql] response status=${response.status} in ${((t1 - t0) / 1000).toFixed(1)}s`);
if (!response.ok) {
const text = await response.text();
throw new Error(`SPARQL query failed (${response.status}): ${text}`);
}
const text = await response.text();
const t2 = performance.now();
console.log(` [sparql] body read (${(text.length / 1024).toFixed(0)} KB) in ${((t2 - t1) / 1000).toFixed(1)}s`);
const json = JSON.parse(text);
return json.results.bindings;
} catch (err: any) {
clearTimeout(timeout);
const msg = err instanceof Error ? err.message : String(err);
const isTransient = msg.includes("fetch failed") || msg.includes("Timeout") || msg.includes("ABORT") || msg.includes("abort");
if (isTransient && attempt < retries) {
console.log(` [sparql] transient error (attempt ${attempt}/${retries}): ${msg.substring(0, 100)}`);
console.log(` [sparql] retrying in 10s (AnzoGraph may still be indexing after LOAD)...`);
await sleep(10_000);
continue;
}
throw err;
} finally {
clearTimeout(timeout);
}
}
throw new Error("sparqlQuery: should not reach here");
}
async function waitForAnzoGraph(): Promise<void> {
console.log(`Waiting for AnzoGraph at ${SPARQL_ENDPOINT}...`);
for (let attempt = 1; attempt <= MAX_RETRIES; attempt++) {
try {
const response = await fetch(SPARQL_ENDPOINT, {
method: "POST",
headers: {
"Content-Type": "application/x-www-form-urlencoded",
"Accept": "application/sparql-results+json",
"Authorization": AUTH_HEADER,
},
body: "query=" + encodeURIComponent("ASK WHERE { ?s ?p ?o }"),
});
const text = await response.text();
// Verify it's actual JSON (not a plain-text error from a half-started engine)
JSON.parse(text);
console.log(` AnzoGraph is ready (attempt ${attempt})`);
return;
} catch (err: any) {
const msg = err instanceof Error ? err.message : String(err);
console.log(` Attempt ${attempt}/${MAX_RETRIES}: ${msg.substring(0, 100)}`);
if (attempt < MAX_RETRIES) {
await sleep(RETRY_DELAY_MS);
}
}
}
throw new Error(`AnzoGraph not available after ${MAX_RETRIES} attempts`);
}
async function sparqlUpdate(update: string): Promise<string> {
const response = await fetch(SPARQL_ENDPOINT, {
method: "POST",
headers: {
"Content-Type": "application/sparql-update",
"Accept": "application/json",
"Authorization": AUTH_HEADER,
},
body: update,
});
const text = await response.text();
if (!response.ok) {
throw new Error(`SPARQL update failed (${response.status}): ${text}`);
}
return text;
}
async function loadData(): Promise<void> {
console.log(`Loading data from ${DATA_FILE}...`);
const t0 = performance.now();
const result = await sparqlUpdate(`LOAD <${DATA_FILE}>`);
const elapsed = ((performance.now() - t0) / 1000).toFixed(1);
console.log(` Load complete in ${elapsed}s: ${result.substring(0, 200)}`);
}
// ══════════════════════════════════════════════════════════
// Step 1: Fetch seed URIs
// ══════════════════════════════════════════════════════════
async function fetchSeedURIs(): Promise<string[]> {
console.log("Querying first 1000 distinct subject URIs...");
const t0 = performance.now();
const query = `
SELECT DISTINCT ?s
WHERE { ?s ?p ?o }
LIMIT 1000
`;
const bindings = await sparqlQuery(query);
const elapsed = ((performance.now() - t0) / 1000).toFixed(1);
const uris = bindings.map((b) => b.s.value);
console.log(` Got ${uris.length} seed URIs in ${elapsed}s`);
return uris;
}
// ══════════════════════════════════════════════════════════
// Step 2: Fetch all triples involving seed URIs
// ══════════════════════════════════════════════════════════
interface Triple {
s: string;
p: string;
o: string;
oType: string; // "uri" or "literal"
}
async function fetchTriples(seedURIs: string[]): Promise<Triple[]> {
console.log(`Fetching triples for ${seedURIs.length} seed URIs (batch size: ${BATCH_SIZE})...`);
const allTriples: Triple[] = [];
for (let i = 0; i < seedURIs.length; i += BATCH_SIZE) {
const batch = seedURIs.slice(i, i + BATCH_SIZE);
const valuesClause = batch.map((u) => `<${u}>`).join(" ");
const query = `
SELECT ?s ?p ?o
WHERE {
VALUES ?uri { ${valuesClause} }
{
?uri ?p ?o .
BIND(?uri AS ?s)
}
UNION
{
?s ?p ?uri .
BIND(?uri AS ?o)
}
}
`;
const bindings = await sparqlQuery(query);
for (const b of bindings) {
allTriples.push({
s: b.s.value,
p: b.p.value,
o: b.o.value,
oType: b.o.type,
});
}
const progress = Math.min(i + BATCH_SIZE, seedURIs.length);
process.stdout.write(`\r Fetched triples: batch ${Math.ceil(progress / BATCH_SIZE)}/${Math.ceil(seedURIs.length / BATCH_SIZE)} (${allTriples.length} triples so far)`);
}
console.log(`\n Total triples: ${allTriples.length}`);
return allTriples;
}
// ══════════════════════════════════════════════════════════
// Step 3: Build graph data
// ══════════════════════════════════════════════════════════
interface GraphData {
nodeURIs: string[]; // All unique URIs (subjects & objects that are URIs)
uriToId: Map<string, number>;
primaryNodeIds: Set<number>; // Nodes that are objects of rdf:type
edges: Array<[number, number]>; // [source, target] as numeric IDs
primaryEdges: Array<[number, number]>;
secondaryEdges: Array<[number, number]>;
}
function buildGraphData(triples: Triple[]): GraphData {
console.log("Building graph data...");
// Collect all unique URI nodes (skip literal objects)
const uriSet = new Set<string>();
for (const t of triples) {
uriSet.add(t.s);
if (t.oType === "uri") {
uriSet.add(t.o);
}
}
// Assign numeric IDs
const nodeURIs = Array.from(uriSet).sort();
const uriToId = new Map<string, number>();
nodeURIs.forEach((uri, idx) => uriToId.set(uri, idx));
// Identify primary nodes: objects of rdf:type triples
const primaryNodeIds = new Set<number>();
for (const t of triples) {
if (t.p === RDF_TYPE && t.oType === "uri") {
const objId = uriToId.get(t.o);
if (objId !== undefined) {
primaryNodeIds.add(objId);
}
}
}
// Build edges (only between URI nodes, skip literal objects)
const edgeSet = new Set<string>();
const edges: Array<[number, number]> = [];
for (const t of triples) {
if (t.oType !== "uri") continue;
const srcId = uriToId.get(t.s);
const dstId = uriToId.get(t.o);
if (srcId === undefined || dstId === undefined) continue;
if (srcId === dstId) continue; // Skip self-loops
const key = `${srcId},${dstId}`;
if (edgeSet.has(key)) continue; // Deduplicate
edgeSet.add(key);
edges.push([srcId, dstId]);
}
// Classify edges into primary (touches a primary node) and secondary
const primaryEdges: Array<[number, number]> = [];
const secondaryEdges: Array<[number, number]> = [];
for (const [src, dst] of edges) {
if (primaryNodeIds.has(src) || primaryNodeIds.has(dst)) {
primaryEdges.push([src, dst]);
} else {
secondaryEdges.push([src, dst]);
}
}
console.log(` Nodes: ${nodeURIs.length}`);
console.log(` Primary nodes (rdf:type objects): ${primaryNodeIds.size}`);
console.log(` Edges: ${edges.length} (primary: ${primaryEdges.length}, secondary: ${secondaryEdges.length})`);
return { nodeURIs, uriToId, primaryNodeIds, edges, primaryEdges, secondaryEdges };
}
// ══════════════════════════════════════════════════════════
// Step 4: Write CSV files
// ══════════════════════════════════════════════════════════
function extractLabel(uri: string): string {
// Extract local name: after # or last /
const hashIdx = uri.lastIndexOf("#");
if (hashIdx !== -1) return uri.substring(hashIdx + 1);
const slashIdx = uri.lastIndexOf("/");
if (slashIdx !== -1) return uri.substring(slashIdx + 1);
return uri;
}
function writeCSVs(data: GraphData): void {
// Write primary_edges.csv
const pLines = ["source,target"];
for (const [src, dst] of data.primaryEdges) {
pLines.push(`${src},${dst}`);
}
const pPath = join(PUBLIC_DIR, "primary_edges.csv");
writeFileSync(pPath, pLines.join("\n") + "\n");
console.log(`Wrote ${data.primaryEdges.length} primary edges to ${pPath}`);
// Write secondary_edges.csv
const sLines = ["source,target"];
for (const [src, dst] of data.secondaryEdges) {
sLines.push(`${src},${dst}`);
}
const sPath = join(PUBLIC_DIR, "secondary_edges.csv");
writeFileSync(sPath, sLines.join("\n") + "\n");
console.log(`Wrote ${data.secondaryEdges.length} secondary edges to ${sPath}`);
// Write uri_map.csv (id,uri,label,isPrimary)
const uLines = ["id,uri,label,isPrimary"];
for (let i = 0; i < data.nodeURIs.length; i++) {
const uri = data.nodeURIs[i];
const label = extractLabel(uri);
const isPrimary = data.primaryNodeIds.has(i) ? "1" : "0";
// Escape commas in URIs by quoting
const safeUri = uri.includes(",") ? `"${uri}"` : uri;
const safeLabel = label.includes(",") ? `"${label}"` : label;
uLines.push(`${i},${safeUri},${safeLabel},${isPrimary}`);
}
const uPath = join(PUBLIC_DIR, "uri_map.csv");
writeFileSync(uPath, uLines.join("\n") + "\n");
console.log(`Wrote ${data.nodeURIs.length} URI mappings to ${uPath}`);
}
// ══════════════════════════════════════════════════════════
// Main
// ══════════════════════════════════════════════════════════
async function main() {
console.log(`SPARQL endpoint: ${SPARQL_ENDPOINT}`);
const t0 = performance.now();
await waitForAnzoGraph();
await loadData();
// Smoke test: simplest possible query to verify connectivity
console.log("Smoke test: SELECT ?s ?p ?o LIMIT 3...");
const smokeT0 = performance.now();
const smokeResult = await sparqlQuery("SELECT ?s ?p ?o WHERE { ?s ?p ?o } LIMIT 3");
const smokeElapsed = ((performance.now() - smokeT0) / 1000).toFixed(1);
console.log(` Smoke test OK: ${smokeResult.length} results in ${smokeElapsed}s`);
if (smokeResult.length > 0) {
console.log(` First triple: ${smokeResult[0].s.value} ${smokeResult[0].p.value} ${smokeResult[0].o.value}`);
}
const seedURIs = await fetchSeedURIs();
const triples = await fetchTriples(seedURIs);
const graphData = buildGraphData(triples);
writeCSVs(graphData);
const elapsed = ((performance.now() - t0) / 1000).toFixed(1);
console.log(`\nDone in ${elapsed}s`);
}
main().catch((err) => {
console.error("Fatal error:", err);
process.exit(1);
});

2
scripts/generate_tree.ts
View File

@@ -20,7 +20,7 @@ const PUBLIC_DIR = join(__dirname, "..", "public");
const TARGET_NODES = 10000; // Approximate number of nodes to generate const TARGET_NODES = 10000; // Approximate number of nodes to generate
const MAX_CHILDREN = 4; // Each node gets 1..MAX_CHILDREN children const MAX_CHILDREN = 4; // Each node gets 1..MAX_CHILDREN children
const PRIMARY_DEPTH = 3; // Nodes at depth ≤ this form the primary skeleton const PRIMARY_DEPTH = 4; // Nodes at depth ≤ this form the primary skeleton
// ══════════════════════════════════════════════════════════ // ══════════════════════════════════════════════════════════
// Tree data types // Tree data types

47
src/App.tsx
View File

@@ -6,6 +6,7 @@ export default function App() {
const rendererRef = useRef<Renderer | null>(null); const rendererRef = useRef<Renderer | null>(null);
const [status, setStatus] = useState("Loading node positions…"); const [status, setStatus] = useState("Loading node positions…");
const [nodeCount, setNodeCount] = useState(0); const [nodeCount, setNodeCount] = useState(0);
const uriMapRef = useRef<Map<number, { uri: string; label: string; isPrimary: boolean }>>(new Map());
const [stats, setStats] = useState({ const [stats, setStats] = useState({
fps: 0, fps: 0,
drawn: 0, drawn: 0,
@@ -14,7 +15,7 @@ export default function App() {
ptSize: 0, ptSize: 0,
}); });
const [error, setError] = useState(""); const [error, setError] = useState("");
const [hoveredNode, setHoveredNode] = useState<{ x: number; y: number; screenX: number; screenY: number } | null>(null); const [hoveredNode, setHoveredNode] = useState<{ x: number; y: number; screenX: number; screenY: number; index?: number } | null>(null);
const [selectedNodes, setSelectedNodes] = useState<Set<number>>(new Set()); const [selectedNodes, setSelectedNodes] = useState<Set<number>>(new Set());
// Store mouse position in a ref so it can be accessed in render loop without re-renders // Store mouse position in a ref so it can be accessed in render loop without re-renders
@@ -39,19 +40,21 @@ export default function App() {
(async () => { (async () => {
try { try {
setStatus("Fetching data files…"); setStatus("Fetching data files…");
const [nodesResponse, primaryEdgesResponse, secondaryEdgesResponse] = await Promise.all([ const [nodesResponse, primaryEdgesResponse, secondaryEdgesResponse, uriMapResponse] = await Promise.all([
fetch("/node_positions.csv"), fetch("/node_positions.csv"),
fetch("/primary_edges.csv"), fetch("/primary_edges.csv"),
fetch("/secondary_edges.csv"), fetch("/secondary_edges.csv"),
fetch("/uri_map.csv"),
]); ]);
if (!nodesResponse.ok) throw new Error(`Failed to fetch nodes: ${nodesResponse.status}`); if (!nodesResponse.ok) throw new Error(`Failed to fetch nodes: ${nodesResponse.status}`);
if (!primaryEdgesResponse.ok) throw new Error(`Failed to fetch primary edges: ${primaryEdgesResponse.status}`); if (!primaryEdgesResponse.ok) throw new Error(`Failed to fetch primary edges: ${primaryEdgesResponse.status}`);
if (!secondaryEdgesResponse.ok) throw new Error(`Failed to fetch secondary edges: ${secondaryEdgesResponse.status}`); if (!secondaryEdgesResponse.ok) throw new Error(`Failed to fetch secondary edges: ${secondaryEdgesResponse.status}`);
const [nodesText, primaryEdgesText, secondaryEdgesText] = await Promise.all([ const [nodesText, primaryEdgesText, secondaryEdgesText, uriMapText] = await Promise.all([
nodesResponse.text(), nodesResponse.text(),
primaryEdgesResponse.text(), primaryEdgesResponse.text(),
secondaryEdgesResponse.text(), secondaryEdgesResponse.text(),
uriMapResponse.ok ? uriMapResponse.text() : Promise.resolve(""),
]); ]);
if (cancelled) return; if (cancelled) return;
@@ -90,6 +93,21 @@ export default function App() {
edgeData[idx++] = parseInt(parts[1], 10); edgeData[idx++] = parseInt(parts[1], 10);
} }
// Parse URI map if available
if (uriMapText) {
const uriLines = uriMapText.split("\n").slice(1).filter(l => l.trim().length > 0);
for (const line of uriLines) {
const parts = line.split(",");
if (parts.length >= 4) {
const id = parseInt(parts[0], 10);
const uri = parts[1];
const label = parts[2];
const isPrimary = parts[3].trim() === "1";
uriMapRef.current.set(id, { uri, label, isPrimary });
}
}
}
if (cancelled) return; if (cancelled) return;
setStatus("Building spatial index…"); setStatus("Building spatial index…");
@@ -182,9 +200,9 @@ export default function App() {
frameCount++; frameCount++;
// Find hovered node using quadtree // Find hovered node using quadtree
const node = renderer.findNodeAt(mousePos.current.x, mousePos.current.y); const nodeResult = renderer.findNodeIndexAt(mousePos.current.x, mousePos.current.y);
if (node) { if (nodeResult) {
setHoveredNode({ ...node, screenX: mousePos.current.x, screenY: mousePos.current.y }); setHoveredNode({ x: nodeResult.x, y: nodeResult.y, screenX: mousePos.current.x, screenY: mousePos.current.y, index: nodeResult.index });
} else { } else {
setHoveredNode(null); setHoveredNode(null);
} }
@@ -331,7 +349,22 @@ export default function App() {
boxShadow: "0 2px 8px rgba(0,0,0,0.5)", boxShadow: "0 2px 8px rgba(0,0,0,0.5)",
}} }}
> >
({hoveredNode.x.toFixed(2)}, {hoveredNode.y.toFixed(2)}) {(() => {
if (hoveredNode.index !== undefined && rendererRef.current) {
const vertexId = rendererRef.current.getVertexId(hoveredNode.index);
const info = vertexId !== undefined ? uriMapRef.current.get(vertexId) : undefined;
if (info) {
return (
<>
<div style={{ fontWeight: "bold", marginBottom: 2 }}>{info.label}</div>
<div style={{ fontSize: "10px", color: "#8cf", wordBreak: "break-all", maxWidth: 400 }}>{info.uri}</div>
{info.isPrimary && <div style={{ color: "#ff0", fontSize: "10px", marginTop: 2 }}>⭐ Primary (rdf:type)</div>}
</>
);
}
}
return <>({hoveredNode.x.toFixed(2)}, {hoveredNode.y.toFixed(2)})</>;
})()}
</div> </div>
)} )}
</> </>

16
src/renderer.ts
View File

@@ -83,6 +83,7 @@ export class Renderer {
private nodeCount = 0; private nodeCount = 0;
private edgeCount = 0; private edgeCount = 0;
private neighborMap: Map<number, number[]> = new Map(); private neighborMap: Map<number, number[]> = new Map();
private sortedToVertexId: Uint32Array = new Uint32Array(0);
private leafEdgeStarts: Uint32Array = new Uint32Array(0); private leafEdgeStarts: Uint32Array = new Uint32Array(0);
private leafEdgeCounts: Uint32Array = new Uint32Array(0); private leafEdgeCounts: Uint32Array = new Uint32Array(0);
private maxPtSize = 256; private maxPtSize = 256;
@@ -213,6 +214,12 @@ export class Renderer {
gl.bufferData(gl.ARRAY_BUFFER, sorted, gl.STATIC_DRAW); gl.bufferData(gl.ARRAY_BUFFER, sorted, gl.STATIC_DRAW);
gl.bindVertexArray(null); gl.bindVertexArray(null);
// Build sorted index → vertex ID mapping for hover lookups
this.sortedToVertexId = new Uint32Array(count);
for (let i = 0; i < count; i++) {
this.sortedToVertexId[i] = vertexIds[order[i]];
}
// Build vertex ID → original input index mapping // Build vertex ID → original input index mapping
const vertexIdToOriginal = new Map<number, number>(); const vertexIdToOriginal = new Map<number, number>();
for (let i = 0; i < count; i++) { for (let i = 0; i < count; i++) {
@@ -331,6 +338,15 @@ export class Renderer {
return this.nodeCount; return this.nodeCount;
} }
/**
* Get the original vertex ID for a given sorted index.
* Useful for looking up URI labels from the URI map.
*/
getVertexId(sortedIndex: number): number | undefined {
if (sortedIndex < 0 || sortedIndex >= this.sortedToVertexId.length) return undefined;
return this.sortedToVertexId[sortedIndex];
}
/** /**
* Convert screen coordinates (CSS pixels) to world coordinates. * Convert screen coordinates (CSS pixels) to world coordinates.
*/ */