From 3f29cd23f18500a850d2bc53612d30b98b40175a Mon Sep 17 00:00:00 2001
From: Christian-Bermejo <Christian_Bermejo@trendmicro.com>
Date: Thu, 18 Jun 2026 00:03:55 +0800
Subject: [PATCH] Parse large CSVs off the main thread (PapaParse worker)

parseCSV ran Papa.parse synchronously, so a big paste/upload froze the UI while
parsing. Enable worker:true above a 512KB threshold so large inputs parse on a
background thread; small inputs keep the synchronous main-thread path (the
worker's serialization overhead makes it slower for them).

PapaParse falls back to synchronous parsing when no Worker global exists
(verified in Node), so the existing tests and any non-browser use are unaffected.
The Promise contract and the normalize/enrich post-processing are unchanged.

Adds a >512KB parse test (30k rows) exercising the worker path. 41 tests green.
---
 studio/src/lib/csv.js      |  7 +++++++
 studio/src/lib/csv.test.js | 11 +++++++++++
 2 files changed, 18 insertions(+)

diff --git a/studio/src/lib/csv.js b/studio/src/lib/csv.js
index 55ddfb8..fc49527 100644
--- a/studio/src/lib/csv.js
+++ b/studio/src/lib/csv.js
@@ -48,11 +48,18 @@ export function normalize(row) {
   };
 }
 
+// Above this size, parse on a background worker so a big paste/upload doesn't
+// freeze the UI. Small inputs parse on the main thread — the worker's
+// serialization overhead makes it slower for them, and PapaParse falls back to
+// synchronous parsing anyway when no Worker global exists (e.g. in tests).
+const WORKER_THRESHOLD_BYTES = 512 * 1024;
+
 export function parseCSV(text) {
   return new Promise((resolve, reject) => {
     Papa.parse(text, {
       header: true,
       skipEmptyLines: true,
+      worker: text.length > WORKER_THRESHOLD_BYTES,
       complete: (res) => {
         const rows = (res.data || [])
           .map(normalize)
diff --git a/studio/src/lib/csv.test.js b/studio/src/lib/csv.test.js
index 4c072bd..92a47f1 100644
--- a/studio/src/lib/csv.test.js
+++ b/studio/src/lib/csv.test.js
@@ -84,4 +84,15 @@ describe("parseCSV", () => {
     const rows = await parseCSV(csv);
     expect(rows[0].uid).toBe("999");
   });
+
+  it("parses a large input (past the worker threshold) correctly", async () => {
+    const lines = ["text,likeCount"];
+    for (let i = 0; i < 30000; i++) lines.push(`tweet number ${i},${i}`);
+    const csv = lines.join("\n");
+    expect(csv.length).toBeGreaterThan(512 * 1024); // exercises worker:true path
+    const rows = await parseCSV(csv);
+    expect(rows).toHaveLength(30000);
+    expect(rows[0].text).toBe("tweet number 0");
+    expect(rows[29999].likes).toBe(29999);
+  });
 });