@rubytech/create-maxy 1.0.759 → 1.0.760

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

@@ -0,0 +1,503 @@
+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";
+
+let workDir: string;
+
+beforeEach(() => {
+  workDir = mkdtempSync(join(tmpdir(), "whatsapp-export-parser-"));
+});
+
+afterEach(() => {
+  rmSync(workDir, { recursive: true, force: true });
+});
+
+function writeChat(name: string, content: string | Buffer): string {
+  const filePath = join(workDir, name);
+  writeFileSync(filePath, content);
+  return filePath;
+}
+
+describe("parseExport — happy path", () => {
+  it("parses two single-line messages and emits ISO 8601 timestamps with the supplied timezone", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      [
+        "[14/03/26, 10:15:23] Joel: Hello",
+        "[14/03/26, 10:16:01] Sarah: Hi back",
+        "",
+      ].join("\n"),
+    );
+
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+
+    expect(result.parsedLines).toHaveLength(2);
+    expect(result.parsedLines[0]).toMatchObject({
+      senderName: "Joel",
+      body: "Hello",
+      sequenceIndex: 0,
+    });
+    expect(result.parsedLines[1]).toMatchObject({
+      senderName: "Sarah",
+      body: "Hi back",
+      sequenceIndex: 1,
+    });
+    // ISO 8601 with timezone offset.
+    expect(result.parsedLines[0].dateSent).toMatch(/^2026-03-14T10:15:23(\.\d+)?[+-]\d{2}:\d{2}$/);
+    expect(result.counters.parsed).toBe(2);
+    expect(result.counters.systemSkipped).toBe(0);
+    expect(result.counters.mediaSkipped).toBe(0);
+    expect(result.counters.parseErrors).toBe(0);
+  });
+
+  it("emits archiveSourceFile = sha256 of the raw file bytes (with whatsapp-export: prefix)", () => {
+    const content = "[14/03/26, 10:15:23] Joel: Hello\n";
+    const filePath = writeChat("_chat.txt", content);
+
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+
+    // Pre-computed sha256 of the literal content above.
+    // Compute deterministically rather than hard-coding so the assert reflects the spec, not a magic string.
+    const { createHash } = require("node:crypto") as typeof import("node:crypto");
+    const expected = createHash("sha256").update(content).digest("hex");
+    expect(result.archiveSourceFile).toBe(`whatsapp-export:${expected}`);
+  });
+
+  it("derives conversationId = whatsapp-export:<sha256>:<accountId>", () => {
+    const filePath = writeChat("_chat.txt", "[14/03/26, 10:15:23] Joel: Hello\n");
+    const result = parseExport({
+      filePath,
+      accountId: "acct-abc",
+      timezone: "Europe/London",
+    });
+    expect(result.conversationId).toMatch(/^whatsapp-export:[a-f0-9]{64}:acct-abc$/);
+  });
+
+  it("parsing the same file twice returns identical output (idempotent)", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      "[14/03/26, 10:15:23] Joel: Hello\n[14/03/26, 10:16:01] Sarah: Hi\n",
+    );
+    const a = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+    const b = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+    expect(a).toEqual(b);
+  });
+});
+
+describe("parseExport — multi-line bodies", () => {
+  it("accumulates continuation lines into the previous message's body, joined with \\n", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      [
+        "[14/03/26, 10:15:23] Joel: Quick question about the deck —",
+        "do you have the v3 PDF anywhere?",
+        "I checked Drive and only see v2.",
+        "[14/03/26, 10:16:01] Sarah: Sec, will dig it out",
+        "",
+      ].join("\n"),
+    );
+
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+
+    expect(result.parsedLines).toHaveLength(2);
+    expect(result.parsedLines[0].body).toBe(
+      "Quick question about the deck —\ndo you have the v3 PDF anywhere?\nI checked Drive and only see v2.",
+    );
+    expect(result.parsedLines[1].body).toBe("Sec, will dig it out");
+  });
+});
+
+describe("parseExport — system messages skipped with counter", () => {
+  it("skips end-to-end-encrypted header and group-event lines, increments systemSkipped", () => {
+    // Real WhatsApp exports emit system events WITHOUT a `: ` separator:
+    // the sender's name flows straight into the verb phrase. Body-level
+    // events (`You deleted this message.`) keep the colon and are caught by
+    // a separate body-level filter.
+    const filePath = writeChat(
+      "_chat.txt",
+      [
+        "[14/03/26, 09:00:00] Messages and calls are end-to-end encrypted. No one outside of this chat, not even WhatsApp, can read or listen to them.",
+        "[14/03/26, 10:00:00] Joel created group \"Q3 planning\"",
+        "[14/03/26, 10:00:01] Joel added Sarah",
+        "[14/03/26, 10:15:23] Joel: Hello",
+        "[14/03/26, 11:00:00] Sarah left",
+        "[14/03/26, 11:01:00] Sarah's security code changed.",
+        "",
+      ].join("\n"),
+    );
+
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+
+    expect(result.parsedLines).toHaveLength(1);
+    expect(result.parsedLines[0].body).toBe("Hello");
+    expect(result.counters.systemSkipped).toBeGreaterThanOrEqual(5);
+  });
+
+  it("skips 'You deleted this message.' and 'This message was deleted.'", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      [
+        "[14/03/26, 10:15:23] Joel: You deleted this message.",
+        "[14/03/26, 10:16:01] Sarah: This message was deleted.",
+        "[14/03/26, 10:17:01] Joel: Real message",
+        "",
+      ].join("\n"),
+    );
+
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+
+    expect(result.parsedLines).toHaveLength(1);
+    expect(result.parsedLines[0].body).toBe("Real message");
+    expect(result.counters.systemSkipped).toBe(2);
+  });
+});
+
+describe("parseExport — media-only lines skipped", () => {
+  it("skips <Media omitted>, IMG-/VID-/PTT-/AUD-/STK- attachments, and PDF attachments", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      [
+        "[14/03/26, 10:00:00] Joel: <Media omitted>",
+        "[14/03/26, 10:01:00] Joel: IMG-20260314-WA0001.jpg (file attached)",
+        "[14/03/26, 10:02:00] Joel: VID-20260314-WA0002.mp4 (file attached)",
+        "[14/03/26, 10:03:00] Joel: PTT-20260314-WA0003.opus (file attached)",
+        "[14/03/26, 10:04:00] Joel: AUD-20260314-WA0004.opus (file attached)",
+        "[14/03/26, 10:05:00] Joel: STK-20260314-WA0005.webp (file attached)",
+        "[14/03/26, 10:06:00] Joel: deck-v3.pdf (file attached)",
+        "[14/03/26, 10:07:00] Joel: contract.docx (file attached)",
+        "[14/03/26, 10:15:23] Joel: Hello",
+        "",
+      ].join("\n"),
+    );
+
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+
+    expect(result.parsedLines).toHaveLength(1);
+    expect(result.parsedLines[0].body).toBe("Hello");
+    expect(result.counters.mediaSkipped).toBe(8);
+  });
+
+  it("keeps mixed messages where the body has text plus a media reference", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      [
+        "[14/03/26, 10:01:00] Joel: see attached IMG-20260314-WA0001.jpg",
+        "",
+      ].join("\n"),
+    );
+
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+
+    expect(result.parsedLines).toHaveLength(1);
+    expect(result.parsedLines[0].body).toBe("see attached IMG-20260314-WA0001.jpg");
+    expect(result.counters.mediaSkipped).toBe(0);
+  });
+});
+
+describe("parseExport — empty body skipped with counter", () => {
+  it("treats an empty body (timestamp + sender + colon + nothing) as a system skip", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      [
+        "[14/03/26, 10:15:23] Joel: ",
+        "[14/03/26, 10:16:01] Sarah: Hi",
+        "",
+      ].join("\n"),
+    );
+
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+
+    expect(result.parsedLines).toHaveLength(1);
+    expect(result.parsedLines[0].senderName).toBe("Sarah");
+    expect(result.counters.systemSkipped).toBe(1);
+  });
+});
+
+describe("parseExport — encoding + line ending invariants", () => {
+  it("strips a leading UTF-8 BOM (U+FEFF) before parsing the first line", () => {
+    const bom = Buffer.from([0xef, 0xbb, 0xbf]);
+    const body = Buffer.from("[14/03/26, 10:15:23] Joel: Hello\n", "utf8");
+    const filePath = writeChat("_chat.txt", Buffer.concat([bom, body]));
+
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+
+    expect(result.parsedLines).toHaveLength(1);
+    expect(result.parsedLines[0].senderName).toBe("Joel");
+  });
+
+  it("normalises CRLF line endings to LF before tokenisation", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      "[14/03/26, 10:15:23] Joel: Hello\r\n[14/03/26, 10:16:01] Sarah: Hi\r\n",
+    );
+
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+
+    expect(result.parsedLines).toHaveLength(2);
+    expect(result.parsedLines[0].body).toBe("Hello");
+    expect(result.parsedLines[1].body).toBe("Hi");
+  });
+});
+
+describe("parseExport — sender containing a colon (splits on the FIRST ': ')", () => {
+  it("preserves the colon inside the sender display name", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      "[14/03/26, 10:15:23] Joel: Work: today's update — see deck\n",
+    );
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+    expect(result.parsedLines).toHaveLength(1);
+    expect(result.parsedLines[0].senderName).toBe("Joel");
+    expect(result.parsedLines[0].body).toBe("Work: today's update — see deck");
+  });
+});
+
+describe("parseExport — forwarded messages preserve LRM character", () => {
+  it("keeps the U+200E LEFT-TO-RIGHT MARK in the body verbatim", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      "[14/03/26, 10:15:23] Joel: ‎Forwarded\nForwarded body\n",
+    );
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+    expect(result.parsedLines).toHaveLength(1);
+    expect(result.parsedLines[0].body).toContain("‎");
+  });
+});
+
+describe("parseExport — older exports with HH:MM (no seconds)", () => {
+  it("treats missing seconds as 0", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      "[14/03/26, 10:15] Joel: Hello\n",
+    );
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+    expect(result.parsedLines).toHaveLength(1);
+    expect(result.parsedLines[0].dateSent).toMatch(/^2026-03-14T10:15:00(\.\d+)?[+-]\d{2}:\d{2}$/);
+  });
+});
+
+describe("parseExport — date format toggle", () => {
+  it("defaults to DD/MM/YY", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      "[14/03/26, 10:15:23] Joel: Hello\n",
+    );
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+    expect(result.parsedLines[0].dateSent).toMatch(/^2026-03-14T/);
+  });
+
+  it("accepts dateFormat='MM/DD/YY' and parses the alternate ordering", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      "[03/14/26, 10:15:23] Joel: Hello\n",
+    );
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "America/New_York",
+      dateFormat: "MM/DD/YY",
+    });
+    expect(result.parsedLines[0].dateSent).toMatch(/^2026-03-14T/);
+  });
+
+  it("rejects out-of-range components (month/day) instead of silently rolling over", () => {
+    // 14/03/26 parsed as MM/DD/YY would have month=14 → Date.UTC silently
+    // rolls to year+1 / February. The range check turns it back into a
+    // non-match so the parser falls into "zero parsed lines" rather than
+    // emitting wrong timestamps.
+    const filePath = writeChat(
+      "_chat.txt",
+      "[14/03/26, 10:15:23] Joel: Hello\n",
+    );
+    expect(() =>
+      parseExport({
+        filePath,
+        accountId: "acct-123",
+        timezone: "Europe/London",
+        dateFormat: "MM/DD/YY",
+      }),
+    ).toThrow(/zero parsed lines/i);
+  });
+});
+
+describe("parseExport — LOUD-FAIL scenarios", () => {
+  it("throws when the file is empty", () => {
+    const filePath = writeChat("_chat.txt", "");
+    expect(() =>
+      parseExport({
+        filePath,
+        accountId: "acct-123",
+        timezone: "Europe/London",
+      }),
+    ).toThrow(/empty|zero parsed lines|not.*_chat\.txt/i);
+  });
+
+  it("throws when no lines parse (file isn't a _chat.txt)", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      "this is some random text\nwith no timestamp prefixes\nat all.\n",
+    );
+    expect(() =>
+      parseExport({
+        filePath,
+        accountId: "acct-123",
+        timezone: "Europe/London",
+      }),
+    ).toThrow(/zero parsed lines|not.*_chat\.txt/i);
+  });
+
+  it("throws when a timestamp prefix matches but the body parse fails (no ': ' separator)", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      [
+        "[14/03/26, 10:15:23] Joel: Hello",
+        "[14/03/26, 10:16:01] BrokenLineWithoutColonSeparator",
+        "[14/03/26, 10:17:01] Sarah: Hi",
+        "",
+      ].join("\n"),
+    );
+
+    expect(() =>
+      parseExport({
+        filePath,
+        accountId: "acct-123",
+        timezone: "Europe/London",
+      }),
+    ).toThrow(/parse-error.*line=2|line 2|malformed/i);
+  });
+
+  it("throws when accountId is missing or empty", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      "[14/03/26, 10:15:23] Joel: Hello\n",
+    );
+    expect(() =>
+      parseExport({
+        filePath,
+        accountId: "",
+        timezone: "Europe/London",
+      }),
+    ).toThrow(/accountId/i);
+  });
+
+  it("throws when timezone is missing or empty", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      "[14/03/26, 10:15:23] Joel: Hello\n",
+    );
+    expect(() =>
+      parseExport({
+        filePath,
+        accountId: "acct-123",
+        timezone: "",
+      }),
+    ).toThrow(/timezone/i);
+  });
+});
+
+describe("parseExport — sequenceIndex monotonicity", () => {
+  it("assigns sequenceIndex by parsed-message order, starting at 0", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      [
+        "[14/03/26, 10:15:23] Joel: A",
+        "[14/03/26, 10:15:24] Joel: <Media omitted>",
+        "[14/03/26, 10:15:25] Sarah: B",
+        "[14/03/26, 10:15:26] Sarah: C",
+        "",
+      ].join("\n"),
+    );
+
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+
+    expect(result.parsedLines.map((p) => p.sequenceIndex)).toEqual([0, 1, 2]);
+    expect(result.parsedLines.map((p) => p.body)).toEqual(["A", "B", "C"]);
+    expect(result.counters.mediaSkipped).toBe(1);
+  });
+});
+
+describe("parseExport — phone-number senders", () => {
+  it("accepts phone-number-style senderNames verbatim (no normalisation)", () => {
+    const filePath = writeChat(
+      "_chat.txt",
+      "[14/03/26, 10:15:23] +44 7700 900123: Hello\n",
+    );
+    const result = parseExport({
+      filePath,
+      accountId: "acct-123",
+      timezone: "Europe/London",
+    });
+    expect(result.parsedLines).toHaveLength(1);
+    expect(result.parsedLines[0].senderName).toBe("+44 7700 900123");
+  });
+});

package/payload/platform/plugins/whatsapp-import/lib/src/index.ts

@@ -0,0 +1,7 @@
+export { parseExport } from "./parse-export.js";
+export type {
+  ParseExportInput,
+  ParseExportResult,
+  ParseExportCounters,
+  ParsedLine,
+} from "./parse-export.js";