fix(#2128): address shared-seam review regressions (#557, action-scan, comment-strip)

Final convergence review found the shared <tag> seam introduced 3 behavior
regressions; fixed all + locked with tests:

- #557 REGRESSION: stripTaggedBlocks's attribute-tolerance stripped `<details open>`
  (the ACTIVE-milestone marker) that the old `<details>`-only regex preserved. The
  seam now takes `allowAttributes` (default false) — details/decisions strip is
  attr-INTOLERANT (preserves `<details open>`); only `<task type="…">` opts in.
  Regression test added to roadmap-parser + markdown-sectionizer suites.
- verify.cts actionZones (negative-grep-echo security scan): reverted to a bounded
  to-first-close scan `<action>([\s\S]{0,20000}?)</action>` so a grep-echo trick
  can't hide behind an unterminated inner <action> (the seam's stop-at-next-open
  would drop it). ReDoS-safe via the cap.
- check-command-router HTML-comment strip: `(?:-->|$)` fallback wiped to EOF
  (fail-closed spurious gate block) — replaced with stop-at-next-open so an
  unclosed `<!--` leaves downstream tags intact.
- Updated the extractTaggedBlocks nested-tag tests to the new (stop-at-next-open)
  behavior: `<x><x>inner</x></x>` -> ['inner'].

All vectors still linear; every fix verified in-process.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Tom Boucher
2026-07-10 11:12:45 -04:00
parent 01b691fae8
commit 8e4ebb49e4
6 changed files with 91 additions and 34 deletions

View File

@@ -33,6 +33,7 @@ const {
collectSection,
iterateBullets,
extractTaggedBlocks,
stripTaggedBlocks,
replaceSection,
} = require('../gsd-core/bin/lib/markdown-sectionizer.cjs');
@@ -1015,15 +1016,14 @@ describe('stripFencedCode and tokenizeHeadings: backtick info string with backti
// ─── FIX 6: extractTaggedBlocks — nested tag behavior ─────────────────────────
describe('extractTaggedBlocks: nested same-name tag behavior (non-greedy limitation)', () => {
test('nested <x><x>…</x></x> closes at first </x> (non-greedy; nested tags not supported)', () => {
// Non-greedy match: <x>([\s\S]*?)</x> closes at the FIRST </x>.
// So <x><x>inner</x></x> → first block captures "<x>inner", second </x> is unmatched.
describe('extractTaggedBlocks: nested same-name tag behavior (#2128 stop-at-next-open)', () => {
test('nested <x><x>inner</x></x> extracts the well-formed inner block', () => {
// #2128: the ReDoS-safe body scan terminates at the NEXT opening <x>, so the
// unterminated outer <x> is skipped and the inner block is extracted.
const content = '<x><x>inner</x></x>';
const result = extractTaggedBlocks(content, 'x');
// The first match closes at the first </x>, capturing "<x>inner"
assert.equal(result.length, 1, 'non-greedy match produces exactly one result from nested input');
assert.equal(result[0], '<x>inner', 'inner capture is the content up to the first closing tag');
assert.equal(result.length, 1, 'exactly one result from nested input');
assert.equal(result[0], 'inner', 'the well-formed inner block is extracted; the unterminated outer is skipped');
});
test('back-to-back blocks (not nested) are both extracted', () => {
@@ -1033,6 +1033,24 @@ describe('extractTaggedBlocks: nested same-name tag behavior (non-greedy limitat
assert.equal(result[0], 'first');
assert.equal(result[1], 'second');
});
test('#2128: a document full of unclosed <x> openings stays linear and yields no match', () => {
const content = '<x>a\n'.repeat(50) + 'no closing tag';
assert.deepEqual(extractTaggedBlocks(content, 'x'), [], 'no </x> anywhere -> no blocks');
});
test('#557 / #2128: attr-intolerant by default preserves <details open>; opt-in matches <task type=…>', () => {
// stripTaggedBlocks(details) must PRESERVE <details open> (the active-milestone
// marker) and strip only bare <details>; extractTaggedBlocks(task, true) must
// match attributed tasks, and must NOT when allowAttributes is left false.
assert.equal(
stripTaggedBlocks('X<details>shipped</details>Y<details open>active</details>Z', 'details'),
'XY<details open>active</details>Z',
'#557: <details open> preserved; bare <details> stripped',
);
assert.deepEqual(extractTaggedBlocks('<task type="auto">body</task>', 'task', true), ['body'], 'attributed task matched with allowAttributes=true');
assert.deepEqual(extractTaggedBlocks('<task type="auto">body</task>', 'task'), [], 'attributed task NOT matched with allowAttributes=false');
});
});
// Parity guard removed in T5 (ADR-1372): uat-predicate now imports stripFencedCode