fix: preserve U+FEFF at chunk boundaries (#1010)

src/apps/cli/package.json

@@ -41,7 +41,7 @@
     "dependencies": {
         "chokidar": "^4.0.0",
         "minimatch": "^10.2.5",
-        "octagonal-wheels": "^0.1.47",
+        "octagonal-wheels": "^0.1.50",
         "pouchdb-adapter-http": "^9.0.0",
         "pouchdb-adapter-leveldb": "^9.0.0",
         "pouchdb-core": "^9.0.0",

src/apps/webapp/package.json

@@ -12,7 +12,7 @@
         "preview": "vite preview"
     },
     "dependencies": {
-        "octagonal-wheels": "^0.1.47"
+        "octagonal-wheels": "^0.1.50"
     },
     "devDependencies": {
         "@playwright/test": "^1.58.2",

src/apps/webpeer/package.json

@@ -12,7 +12,7 @@
         "check": "svelte-check --tsconfig ./tsconfig.app.json && tsc -p tsconfig.node.json"
     },
     "dependencies": {
-        "octagonal-wheels": "^0.1.47"
+        "octagonal-wheels": "^0.1.50"
     },
     "devDependencies": {
         "eslint-plugin-svelte": "^3.19.0",

src/rabinKarpBom.unit.spec.ts

@@ -0,0 +1,18 @@
+import { splitPiecesRabinKarp } from "@lib/string_and_binary/chunks.ts";
+import { describe, expect, it } from "vitest";
+
+describe("Rabin-Karp text splitting", () => {
+    it("preserves U+FEFF at the beginning of an internal chunk", async () => {
+        const content = `${"a".repeat(1024)}\uFEFF${"b".repeat(1024)}`;
+        const createChunks = await splitPiecesRabinKarp(new Blob([content], { type: "text/plain" }), 1024, true, 1024);
+        const chunks: string[] = [];
+
+        for await (const chunk of createChunks()) {
+            chunks.push(chunk);
+        }
+
+        expect(chunks).toHaveLength(3);
+        expect(chunks[1].startsWith("\uFEFF")).toBe(true);
+        expect(chunks.join("")).toBe(content);
+    });
+});