@rubytech/create-realagent 1.0.828 → 1.0.830

package/payload/platform/plugins/whatsapp-import/lib/src/__tests__/parse-export-lrm.test.ts

@@ -1,83 +0,0 @@
-import { describe, it, expect, beforeEach, afterEach } from "vitest";
-import { mkdtempSync, rmSync, writeFileSync } from "node:fs";
-import { tmpdir } from "node:os";
-import { join } from "node:path";
-import { parseExport } from "../parse-export.js";
-
-// Task 887 — bidi-strip regression. Some WhatsApp exports prefix every
-// timestamp header with U+200E (LEFT-TO-RIGHT MARK) or U+200F (RTL MARK).
-// Pre-fix `decodeAndNormalise` left those bytes in place; the timestamp
-// regex (`^\[(\d{2})\/...`) failed; the LRM-prefixed line was glued onto
-// the previous body as a continuation; the next clean header parsed its
-// senderName off the polluted body — leaking 23 :Person nodes per import
-// in the Adam Mackay archive. The fix strips U+200E/U+200F before
-// tokenisation; this test reproduces the failure shape.
-
-let workDir: string;
-
-beforeEach(() => {
-  workDir = mkdtempSync(join(tmpdir(), "whatsapp-export-lrm-"));
-});
-
-afterEach(() => {
-  rmSync(workDir, { recursive: true, force: true });
-});
-
-function writeChat(name: string, content: string): string {
-  const filePath = join(workDir, name);
-  writeFileSync(filePath, content);
-  return filePath;
-}
-
-describe("parseExport — bidi-strip (Task 887)", () => {
-  it("strips U+200E from timestamp headers and parses each row independently", () => {
-    const LRM = "‎";
-    const filePath = writeChat(
-      "_chat.txt",
-      [
-        `${LRM}[04/02/26, 11:52:16] Adam Mackay: hi`,
-        `${LRM}[04/02/26, 11:52:30] Joel Smalley: hey`,
-        "",
-      ].join("\n"),
-    );
-
-    const result = parseExport({
-      filePath,
-      accountId: "acct-887",
-      timezone: "Europe/London",
-    });
-
-    expect(result.parsedLines).toHaveLength(2);
-    expect(result.parsedLines.map((l) => l.senderName).sort()).toEqual([
-      "Adam Mackay",
-      "Joel Smalley",
-    ]);
-    for (const line of result.parsedLines) {
-      expect(line.senderName).not.toContain("\n");
-      expect(line.senderName).not.toContain("[");
-      expect(line.senderName).not.toContain(LRM);
-    }
-  });
-
-  it("strips U+200F (RLM) on the timestamp line", () => {
-    const RLM = "‏";
-    const filePath = writeChat(
-      "_chat.txt",
-      [
-        `${RLM}[14/03/26, 10:15:23] Joel: Hello`,
-        `${RLM}[14/03/26, 10:16:01] Sarah: Hi back`,
-        "",
-      ].join("\n"),
-    );
-
-    const result = parseExport({
-      filePath,
-      accountId: "acct-887",
-      timezone: "Europe/London",
-    });
-
-    expect(result.parsedLines).toHaveLength(2);
-    expect(result.parsedLines[0].senderName).toBe("Joel");
-    expect(result.parsedLines[1].senderName).toBe("Sarah");
-  });
-});