ahmed mohammedandClaude Opus 4.7
4b5c19b5d2
- lib/plan-file.ts: BOM-aware decode for UTF-8, UTF-16LE/BE (with and without BOM) and UTF-32, with a NUL-density fallback for BOM-less UTF-16. The browser had a two-byte FF FE sniff only, so a UTF-16BE or BOM-less plan arrived as NUL-filled junk and the digest blamed the export. - digestPlan now quotes fast-xml-parser's first line instead of a fixed sentence, so a truncated file, a stray entity and a wrong file stay distinguishable. - plan-file.ts holds the decode so the XML parser stays out of the client bundle. - tests: 6 encodings round-trip through decodePlan into a digest; a truncated plan's message is asserted to carry a reason; e2e drops a real UTF-16LE file. 36 unit, 23 e2e. - history.spec picked the rail's first row, which is now one of the new failing-input rows; it selects the newest finished run instead. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
26 lines
1.3 KiB
TypeScript
26 lines
1.3 KiB
TypeScript
"use client";
|
|
// SSMS saves .sqlplan as UTF-16LE with a BOM; other tools write UTF-8 (sometimes with a BOM), and a few write
|
|
// UTF-16BE or BOM-less UTF-16. File.text() assumes UTF-8, which turns a UTF-16 plan into NUL-filled junk that
|
|
// fails to parse with a message blaming the user's export. BOM first, then a NUL-density guess.
|
|
export function decodePlan(buf: Uint8Array): string {
|
|
const enc = utfEncoding(buf);
|
|
return new TextDecoder(enc).decode(buf).replace(/^\uFEFF/, "");
|
|
}
|
|
|
|
function utfEncoding(buf: Uint8Array): "utf-8" | "utf-16le" | "utf-16be" | "utf-32le" | "utf-32be" {
|
|
const b = (i: number) => buf[i] ?? 0;
|
|
if (b(0) === 0xff && b(1) === 0xfe && b(2) === 0 && b(3) === 0) return "utf-32le";
|
|
if (b(0) === 0 && b(1) === 0 && b(2) === 0xfe && b(3) === 0xff) return "utf-32be";
|
|
if (b(0) === 0xff && b(1) === 0xfe) return "utf-16le";
|
|
if (b(0) === 0xfe && b(1) === 0xff) return "utf-16be";
|
|
// BOM-less UTF-16 of ASCII XML: in the first 200 bytes roughly every other byte is 0x00.
|
|
const n = Math.min(buf.length - (buf.length % 2), 200);
|
|
if (n < 40) return "utf-8";
|
|
let even = 0, odd = 0;
|
|
for (let i = 0; i < n; i += 2) { if (b(i) === 0) even++; if (b(i + 1) === 0) odd++; }
|
|
if (odd > n / 6) return "utf-16le";
|
|
if (even > n / 6) return "utf-16be";
|
|
return "utf-8";
|
|
}
|
|
|