#!/usr/bin/env node
/**
 * `npm run check:claims` — a mechanical gate on the SHIPPED OUTPUT.
 *
 * Pouya's ruling, 2026-08-29, and the reasoning is the point:
 *
 *   "Your recurring failure this project is a specific shape: you write a rule
 *    into a header comment, then breach it in the file below, in the same
 *    change set. Q53's sweep, Q54's gate four times, the D13 'cannot' phrasing
 *    fifty lines under your own warning about it. That is not a discipline
 *    problem — prose in a comment does not govern the writing that follows it.
 *    The pattern that actually worked was mechanical: deleting the `class` prop
 *    so passing one is a build error. Nobody has breached that since."
 *
 * So this is not documentation. It is a build error.
 *
 * SCOPE — `dist/**\/*.html` AND NOTHING ELSE. Not `AGENTS.md`, not `docs/`, not
 * `src/`. D19 bounds review to what ships, and §4's Forbidden table says in as
 * many words that it "governs published pages… It is not a word filter over the
 * repository's own documentation." A register that records a forbidden phrase in
 * order to forbid it must not be failed by its own quotation of it.
 *
 * `<style>` BLOCKS AND NON-JSON-LD `<script>` BLOCKS ARE STRIPPED FIRST, and
 * that is load-bearing rather than tidy. Measured against the step-4 build
 * before this file existed: a bare case-insensitive sweep for `leading` returned
 * **26 hits, 25 of them `var(--leading-body)`** inside Astro's inlined critical
 * CSS. A check that cries wolf on every page on its first run is a check
 * somebody deletes in week two. JSON-LD is deliberately NOT stripped — a claim
 * in a `<script type="application/ld+json">` is still a claim, and docs/04 says
 * so: "Marking an unheld credential as held in structured data is a
 * misrepresentation that happens to be machine-readable."
 *
 * EVERY PATTERN CARRIES ITS `incident`, PRINTED ON FAILURE. Pouya's
 * instruction: "so nobody deletes one for being noisy." A pattern whose cost is
 * visible and whose reason is not gets deleted; this prints the reason at the
 * moment the cost is felt.
 *
 * AND IT SELF-TESTS BEFORE IT SWEEPS. See `FIXTURES` below. A regex that has
 * quietly stopped matching passes a clean sweep forever, which is the exact
 * shape of AGENTS.md Q22 — a documented control that no longer existed.
 */

import { readdirSync, readFileSync, statSync } from 'node:fs';
import { join, relative, resolve } from 'node:path';

const ROOT = resolve(import.meta.dirname, '..');
const DIST = resolve(ROOT, process.argv[2] ?? 'dist');

/* Sources whose mtime, if newer than the newest built page, means this sweep
   would be reading yesterday's output. `docs/` is absent on purpose: it directs
   copy but does not produce it, so a spec edit does not stale the build. */
const SOURCE_DIRS = ['src', 'public'];
const SOURCE_FILES = ['astro.config.mjs', 'package.json'];

/**
 * The patterns.
 *
 * `re` is matched against the page's text with `<style>` and non-JSON-LD
 * `<script>` removed. All are global and case-insensitive.
 *
 * WORD BOUNDARIES ARE NOT DECORATION ON ANY OF THESE. `\bleading\b` does not
 * match "pleadings" and `\blicensed\b` does not match "licensing" — both are
 * words this site publishes, and both were live false positives when the
 * patterns were first drafted. Loosening a boundary here re-creates the noise
 * this file was built to avoid.
 */
const PATTERNS = [
  {
    id: 'licensure-of-pouya',
    rule: 'D13 / §4 Forbidden — the site asserts the JD and nothing further.',
    incident:
      '§4 opened with "Pouya is a licensed legal professional", then "a legal ' +
      'professional", then an assertion that LSO marketing rules apply — three ' +
      'progressively weaker forms of the same unverified claim, each surviving a ' +
      'sweep meant to remove it, in the section written to stop exactly that. ' +
      '§4 does not establish licence status either way.',
    re: /\blawyer\b|\bcalled to the bar\b|\blicensed\b|\bpost-nominal\b/gi,
    note: '"licensing" and "licence" are NOT matched — /practice/technology/ ships "IP and licensing".',
  },
  {
    id: 'acting-for-a-party',
    rule: '§4 Forbidden — implication is the risk, not just the word.',
    incident:
      '§4 bars "acts for clients", "represents parties", "my clients", ' +
      '"my litigation practice". The site sells neutrality; a partisan verb ' +
      'undercuts the central claim before it reaches the licensure question. ' +
      'Settlement counsel was struck from three specs for the same reason (Q42).',
    re: /\bmy litigation practice\b|\bmy law practice\b|\bmy clients?\b|\bacts for\b|\bI act for\b|\brepresents?\b/gi,
    note:
      '"I do not act for a party" is the APPROVED sentence (/mediation/) and does ' +
      'not match. THE SINGULAR WAS ADDED 2026-08-29: the pattern read ' +
      '`my clients` and `/med-arb/` was shipping "The neutral who heard my ' +
      'client in caucus" in its FAQ — the possessive belonged to the counsel ' +
      'voicing the objection, not to Pouya, but the gate cannot tell and the ' +
      'phrase is forbidden in his voice, so the copy changed to "our client" ' +
      'and the pattern widened. Same shape as the capacity-phrasing hole: a ' +
      'pattern narrow enough to miss the real form of the breach.',
  },
  {
    id: 'capacity-phrasing',
    rule: 'docs/03 — when a fact is [unestablished], write around the capacity question.',
    incident:
      'Attempt 1 "I do not give legal advice" was flagged as an ELECTION ' +
      '(entitlement withheld by choice). Attempt 2 "I cannot give legal advice" ' +
      'was flagged as a DENIAL of capacity. Both audits were right: they are ' +
      'opposite answers to a question §4 holds neither side of. The shipped ' +
      'sentence makes no capacity claim at all.',
    re: /\b(cannot|can ?not|can't|do(es)? not|don't|will not|won't|unable to|not (qualified|permitted|able) to)\s+(give|provide|offer)\s+legal advice\b|\bI\s+(?:cannot|can ?not|can't|do not|don't|will not|won't)\b[^.<]{0,25}\badvis(?:e|ing)\b/gi,
    note:
      'THE SECOND ALTERNATIVE WAS ADDED 2026-08-29 BECAUSE THE FIRST MISSED A REAL ' +
      'BREACH. `/practice/cross-cultural/` shipped "What I do not do is advise on the ' +
      'law of another country" — the election form, narrowed by jurisdiction, which ' +
      'makes it worse rather than better: naming only foreign law invites the reader ' +
      'to supply the domestic half. `claims-auditor` caught it and noted, correctly, ' +
      'that this pattern could not, because it required the literal object "legal ' +
      'advice". The verb list is deliberately tight — give / provide / offer / advise ' +
      '/ render — and the window is 25 characters, so the six approved first-person ' +
      'negations this site ships ("I do not act for a party", "I do not run a case", ' +
      '"I will not run a process", "I do not carry a number across the hall", "I will ' +
      'not convert a mediation", "If I cannot decide a remaining issue") all stay ' +
      'silent. Every one of them is in the mustNotMatch fixtures below.',
  },
  {
    id: 'designation-name',
    rule: "ADRIO's own form is Chartered Med-Arbitrator.",
    incident:
      '"Chartered Mediator-Arbitrator" is not the name of anything ADRIC or ' +
      'ADRIO confers. docs/03 §About names the correct form and the source is ' +
      'docs/reference/adrio-designations.md. A designation stated in a form its ' +
      'own institution does not use reads as a designation not held.',
    re: /Chartered Mediator[- ]Arbitrator/gi,
  },
  {
    id: 'rule-set-name',
    rule: 'ADRIC publishes the ADRIC National Mediation Rules.',
    incident:
      '`docs/01` §/mediation/ said "Model Mediation Rules", which is not the ' +
      'name of anything ADRIC publishes — "Model" belongs to the Model Dispute ' +
      'Resolution Clause INSIDE the rules. Caught at build step 4 only because ' +
      'the rules were fetched rather than named from recall (R14).',
    re: /Model Mediation Rules/gi,
  },
  {
    id: 'counts-and-tenure',
    rule: '§4 Forbidden — no count of matters, hours mediated, or years in practice.',
    incident:
      'The site this replaces carried "Since 2009", "sixteen years", London and ' +
      'New York offices and a company number, all artefacts of a purchased ' +
      'template and all false. §4: the practice is new, and small true numbers ' +
      'do not persuade a sophisticated GC — they invite scrutiny.',
    re: /\b\d[\d,]*\s*\+?\s*(matters|mediations|arbitrations|appointments|awards)\b|\b\d[\d,]*\s+years\s+in\b|\bsince\s+(19|20)\d{2}\b|\b(ten|eleven|twelve|thirteen|fourteen|fifteen|sixteen|seventeen|eighteen|nineteen|twenty|thirty|forty)[\s-]years\b/gi,
  },
  {
    id: 'superlatives',
    rule: '§4 Forbidden — unverifiable as written, and they read as insecure.',
    incident:
      'The reason §4 gives is editorial before it is regulatory: this audience ' +
      'discounts everything after a superlative. AND THE FALSE POSITIVES ARE ' +
      'REAL AND KNOWN — "pleadings" contains "leading" and every inlined ' +
      'stylesheet contains var(--leading-body). Both are handled, by the word ' +
      'boundary and by the <style> strip. Do not loosen the boundary and do not ' +
      'delete this pattern because it once matched a token name.',
    re: /\bleading\b|\bpremier\b|\btop[- ]rated\b|\bbest\b|\bworld[- ]class\b|\bunrivalled\b|\bunparalleled\b/gi,
  },

  /* --- Beyond Pouya's minimum list, 2026-08-29. Each names a real incident in
     this repository and each has near-zero false-positive surface on this
     site's vocabulary. Strike any of the three and the rest still stand. --- */
  {
    id: 'fabricated-founder',
    rule: '§4 Forbidden — the fictitious founder from the template.',
    incident:
      'The site this replaces carried a founder who does not exist, a ' +
      'testimonial attributed to a person who does not exist, invented matter ' +
      'values and fabricated office locations. This register exists because of ' +
      'that, and this is the one pattern whose match would be unambiguous.',
    re: /\bS\.?\s?M\.?\s+Lawrence\b|\b07452218\b/gi,
  },
  {
    id: 'q-arb-as-a-stage',
    rule: '§4 — Q.Arb is HELD. It must never read as a stage, a pathway, or pending.',
    incident:
      'THIS PATTERN WAS INVERTED ON 2026-08-29 AND ITS PREDECESSOR IS GONE. It ' +
      'used to bar Q.Arb reading as HELD, because §4 recorded it as "commenced ' +
      'August 2026"; Pouya ruled it held (obtained July 2026, date NOT ' +
      'published), so every stage word now understates a real credential. The ' +
      'site carried the struck forms on six surfaces — an h1 reading "Available ' +
      'now, and open about the stage", a whole /arbitration/ section headed ' +
      '"Where I am in the arc", /about/\'s arc section, the footer strip, and ' +
      'both JSON-LD nodes. Publish "Q.Arb (ADRIC / ADRIO)" and nothing more.',
    /* ~50 characters either side, per Pouya's specification. The window stops at
       the next TAG boundary so it cannot leap a paragraph. It stopped at a
       sentence boundary too (`[^.<]`) until the fixture below proved that too
       tight: "Qualified Arbitrator. Newly commenced" splits the anchor from the
       stage word across a full stop, 22 characters apart, and that is precisely
       the copy this pattern exists for. The self-test caught the regression.

       ⚠️ THE ANCHOR MATCHES THE EXPANSION TOO, and it did not on the first
       draft. Tested against the nine strings this change set removed: it caught
       seven and MISSED "Qualified Arbitrator. Newly commenced — not held, and
       not nearing completion." — /about/'s own arc body, which never wrote the
       abbreviation. An abbreviation-only anchor cannot see copy that spells the
       designation out, and prose is exactly where it gets spelled out.

       KNOWN LIMIT, stated rather than papered over: this cannot catch a stage
       expressed without naming the designation at all. The h1 it replaced —
       "Available now, and open about the stage" — matches nothing here and no
       regex over shipped HTML would catch it without firing on ordinary copy.
       That one is `claims-auditor`'s. */
    /* WHAT EACH ALTERNATIVE IS FOR, because none is obvious from the regex:
       (1) stage word after the designation, (2) before it, (3) an acquisition
       DATE near it — §4 records July 2026 and bars publishing it, and docs/03
       cited this script as enforcing that before it did (the Q22 shape) —
       (4) "once/when I hold it", which must take the designation as its object
       or it fires on "when I hold a preliminary conference".

       THE ANCHOR MATCHES THE EXPANSION because `docs/03` authorises "Qualified
       Arbitrator" as publishable prose, and prose is where it gets spelled out.

       KNOWN LIMIT, stated rather than papered over: this cannot catch a stage
       expressed without naming the designation. The h1 it replaced — "Available
       now, and open about the stage" — matches nothing here, and no regex over
       shipped HTML would catch it without firing on ordinary copy. That one is
       `claims-auditor`'s. */
    re: /(?:Q\.?\s?Arb|Qualified Arbitrator)\b[^<\uE000]{0,50}?\b(commenc\w*|in progress|pathway|not yet|not held|nearing completion|pending|working toward|under ?way)\b|\b(commenc\w*|in progress|pathway|not yet|not held|nearing completion|pending|working toward|under ?way)\b[^<\uE000]{0,50}?\b(?:Q\.?\s?Arb|Qualified Arbitrator)\b|(?:Q\.?\s?Arb|Qualified Arbitrator)\b[^<\uE000]{0,50}?\b(?:January|February|March|April|May|June|July|August|September|October|November|December)\s+20\d\d\b|\b(?:January|February|March|April|May|June|July|August|September|October|November|December)\s+20\d\d\b[^<\uE000]{0,50}?\b(?:Q\.?\s?Arb|Qualified Arbitrator)\b|\b(?:once|when)\s+(?:I|he)\s+(?:holds?|obtains?|receives?|completes?)\s+(?:it\b|the\s+)?(?:Q\.?\s?Arb|designation)\b/gi,
  },
  {
    id: 'c-med-arb-struck',
    rule: 'C.Med-Arb is out entirely — it appears on no page (Pouya, 2026-08-29).',
    incident:
      'It was the strategy brief\'s "explicit long-term professional narrative" ' +
      'and it shipped on /, /about/, /arbitration/ and /med-arb/ as the endpoint ' +
      'of a credentialing arc. Pouya dispensed with it: he holds Q.Med and ' +
      'Q.Arb, which is what med-arb requires. THE DESIGNATION IS STILL REAL and ' +
      'stays in AGENTS.md §11 as a definition — this bars naming it in shipped ' +
      'output, not knowing what it is. Barred in every spelling both ' +
      'institutions use, because the reinstatement risk is a well-meaning ' +
      'implementer reading the brief, not a typo.',
    /* ⚠️ THE LEADING \b AND THE MANDATORY DOT ARE BOTH LOAD-BEARING, and this
       pattern shipped without them for one run. `C\.?\s?Med-Arb` matched
       "ADRIC Med-Arb Rules" as "C Med-Arb" — the C of ADRIC, a space, then the
       real rule-set name — and failed the build on approved copy on /med-arb/.
       The abbreviation always carries the dot; "C Med-Arb" is not a form either
       institution uses. The fixture below pins it. */
    re: /\bC\.\s?Med-Arb(?:itrat(?:or|ion))?s?\b|\bChartered Med-Arb(?:itrat(?:or|ion))?s?\b/gi,
  },
  {
    id: 'struck-universal-q39',
    rule: 'Q39 — the class statement about arbitral gating was FALSE and was published once.',
    incident:
      '§4 carried "Anyone may be appointed an arbitrator in Ontario. Nothing in ' +
      'law gates the role behind a designation." Pouya checked the ' +
      'counter-example and confirmed it: "My assertion was FALSE as a ' +
      'universal." Ontario family arbitrators must complete prescribed ' +
      'training. The scoped replacement is COMMERCIAL arbitration and it is ' +
      "Pouya's attributed position, not a verified fact. Swept four times; " +
      'reached a public page once.',
    re: /anyone (may|can) be appointed an arbitrator|nothing in law gates|no (licence|license|designation) is (required|needed) to (be appointed|arbitrate|act as an arbitrator)/gi,
  },
];

/**
 * THE INSTRUMENT CHECK, and it runs before every sweep.
 *
 * `mustMatch` — a pattern that has stopped firing passes a clean sweep forever
 * and looks identical to a clean site. `mustNotMatch` — the known-legitimate
 * strings this site actually publishes; if one of them starts failing, the
 * pattern got looser, not the copy worse.
 *
 * CLAUDE.md, five times over: "a measurement is a claim about your instrument
 * until you check the instrument."
 */
const FIXTURES = {
  mustMatch: {
    'licensure-of-pouya': [
      'He is a lawyer.',
      'called to the bar',
      'a licensed neutral',
    ],
    'acting-for-a-party': [
      'my litigation practice',
      'acts for clients',
      'I act for the claimant',
      'represents parties',
      'my clients',
      /* The singular, which the pattern missed until 2026-08-29. */
      'the neutral who heard my client in caucus',
    ],
    'capacity-phrasing': [
      'I cannot give legal advice',
      'I do not give legal advice',
      "I can't provide legal advice",
      /* The real breach the first form of this pattern could not catch. */
      'What I do not do is advise on the law of another country',
      'I do not advise on foreign law',
    ],
    'designation-name': ['Chartered Mediator-Arbitrator'],
    'rule-set-name': ['the Model Mediation Rules'],
    'counts-and-tenure': [
      '40 matters',
      '120 mediations',
      '16 years in ADR',
      'Since 2009',
      'sixteen years',
    ],
    superlatives: [
      'a leading neutral',
      'premier',
      'top-rated',
      'the best mediator',
    ],
    'fabricated-founder': ['S. M. Lawrence', 'Co. № 07452218'],
    'q-arb-as-a-stage': [
      'The Q.Arb pathway commenced in August 2026',
      'Q.Arb is in progress',
      'Q.Arb — not yet held',
      'once I hold Q.Arb',
      'my Q.Arb pathway',
      /* The expansion, which the first draft of this pattern missed. */
      'Qualified Arbitrator. Newly commenced — not held, and not nearing completion.',
      /* The acquisition date, which no stage word caught. */
      'Q.Arb, obtained July 2026',
      'Q.Arb (ADRIC / ADRIO), held since July 2026',
      /* The `rule` line above named these and the regex never matched them —
         a documented control not covering what it is cited for (Q22's shape). */
      'Q.Arb is pending',
      'Q.Arb — the designation I am working toward',
      'the Q.Arb process is under way',
    ],
    'c-med-arb-struck': [
      'C.Med-Arb is the endpoint',
      'Chartered Med-Arbitrator',
      'the ADRIC Chartered Med-Arb designation',
      /* The blend §11's own expansion invites, which the trailing \b in the
         first draft made invisible: `C\.Med-Arb\b` cannot match when the next
         character is a word char. */
      'the C.Med-Arbitrator designation',
      'Chartered Med-Arbitration',
      /* Plurals: the trailing \b survived the first repair and blocked these. */
      'Chartered Med-Arbitrators',
      'C.Med-Arbitrators',
      'C.Med-Arbitration',
    ],
    'struck-universal-q39': [
      'Anyone may be appointed an arbitrator in Ontario',
      'nothing in law gates the role',
    ],
  },
  /* Every one of these is real published or spec-approved copy on this site. */
  mustNotMatch: [
    'I act as a neutral. I do not act for a party in a matter I take, and each party should have their own legal advice.',
    'I run a process, I do not run a case for anybody in it.',
    'I will not run a process whose shape nobody agreed to in advance.',
    'I do not carry a number across the hall that I was not given to carry.',
    'I will not convert a mediation into an arbitration on the day.',
    'Commercial matters. I do not accept family arbitration.',
    /* An OFFERING statement, not a capacity claim. The capacity pattern carried
       `offer` for one pass and fired on this. */
    'I do not offer family arbitration.',
    /* Counsel's voice in /med-arb/'s FAQ, after the possessive was changed. */
    'The neutral who heard our client in caucus then decides the case.',
    /* Undertaking (c) — the nearest miss on the widened capacity pattern. */
    'If I cannot decide a remaining issue without relying on something said to me in confidence, I say so and step out of the arbitral phase rather than decide on it.',
    'Pleadings, disclosure, witnesses, experts, oral argument.',
    /* Wrapped, because the wrapper IS what is being tested. The first draft of
       this fixture was the bare declaration and the self-test failed on it —
       correctly: an unwrapped token name is not something the strip can reach,
       so the fixture was asserting the wrong thing. 25 of the 26 real hits were
       inside <style>. */
    '<style>.hero-lede{line-height:var(--leading-body);color:var(--text-secondary)}</style>',
    'Software contracts, SLA and MSA breakdowns, data residency and processing, AI vendor diligence, IP and licensing.',
    /* The approved replacements for the two negatives struck on 2026-08-29,
       which were 'The Q.Arb pathway commenced in August 2026; C.Med-Arb is
       the endpoint.' and a bare 'Chartered Med-Arbitrator'. Both are now
       breaches, and both moved to mustMatch. */
    'Q.Med (ADRIC / ADRIO) · Q.Arb (ADRIC / ADRIO)',
    /* The expansion in approved use — §11 definitional, no stage word. */
    'Q.Arb stands for Qualified Arbitrator, an ADRIC and ADRIO designation.',
    /* `once` and `when` were BARE stage words for one run, and all four of these
       compliant sentences failed the build. They now require a hold-verb. */
    'I hold Q.Med and Q.Arb, and I say so when a party asks',
    'Q.Arb (ADRIC / ADRIO), which is what parties look at when they appoint',
    'Once appointed, I hold Q.Arb and act as sole arbitrator',
    'Q.Arb, and when the parties agree the process runs on that basis',
    /* `hold` is a common verb on an arbitration page with a different object;
       the repair narrowed `once|when` rather than closing it, and this shipped
       past it for one run. The hold-verb must now take the designation. */
    'I hold Q.Arb, and when I hold a preliminary conference the parties attend',
    'I hold the Q.Med and Q.Arb designations through the ADR Institute of Canada and the ADR Institute of Ontario.',
    /* The false positive the first form of `c-med-arb-struck` produced. */
    'The ADR Institute of Canada publishes ADRIC Med-Arb Rules, developed by a task force.',
    'The ADRIC National Mediation Rules.',
    'adopted a new edition effective 1 March 2025',
    'Commercial arbitration in Ontario. I do not accept family arbitration.',
    'Published as typical, not as a guarantee.',
    'Liens, delay and change-order claims, scheduling, subcontract and deficiency disputes.',
  ],
};

/* --- machinery ----------------------------------------------------------- */

/* `relative()` escapes the root with `../../..` when the optional path argument
   points outside the repo (which only a test run does). Show the plain absolute
   path in that case — an unreadable path in a failure report is one more thing
   between a reader and the match. */
function rel(p) {
  const r = relative(ROOT, p);
  return r && !r.startsWith('..') ? r : p;
}

function walk(dir) {
  const out = [];
  for (const entry of readdirSync(dir, { withFileTypes: true })) {
    const full = join(dir, entry.name);
    if (entry.isDirectory()) out.push(...walk(full));
    else if (entry.name.endsWith('.html')) out.push(full);
  }
  return out;
}

function newestMtime(paths) {
  let newest = 0;
  let which = null;
  const visit = (p) => {
    const s = statSync(p);
    if (s.isDirectory()) {
      for (const e of readdirSync(p)) visit(join(p, e));
    } else if (s.mtimeMs > newest) {
      newest = s.mtimeMs;
      which = p;
    }
  };
  for (const p of paths) visit(p);
  return { newest, which };
}

/**
 * Strip what is not published prose or published data.
 *
 * `<style>` goes because Astro inlines critical CSS into every page and the
 * token names collide with the superlative pattern. Non-JSON-LD `<script>` goes
 * because a third-party analytics snippet is somebody else's vocabulary — there
 * is none today (D15's Plausible is one line and not yet added) and there will
 * be. `ld+json` STAYS: it is claim-bearing.
 *
 * Attributes are NOT stripped, deliberately. `<title>`, `<meta name=
 * "description">`, `og:*` and image `alt` text are published copy and are among
 * the places a claim is least likely to be re-read.
 */
function publishedText(html) {
  return (
    html
      .replace(/<style\b[^>]*>[\s\S]*?<\/style>/gi, ' ')
      .replace(
        /<script\b(?![^>]*application\/ld\+json)[^>]*>[\s\S]*?<\/script>/gi,
        ' ',
      )
      /* Smart punctuation, so `can’t` is matched by a pattern written `can't`.
       Astro emits whatever the source used and the source uses curly quotes. */
      .replace(/[‘’]/g, "'")
      .replace(/[“”]/g, '"')
      .replace(/&#(?:39|x27);/gi, "'")
      .replace(/&amp;/gi, '&')
      .replace(/&nbsp;|&#160;/gi, ' ')
  );
}

/**
 * THE SECOND VIEW, AND IT EXISTS BECAUSE `<strong>` DEFEATED THE GATE.
 *
 * `publishedText` leaves tags in place, and several patterns use `[^<]` as a
 * window boundary so they cannot leap a paragraph. That boundary also stops
 * them crossing INLINE markup: `<strong>Q.Arb</strong> — the pathway commenced
 * in August 2026` matched nothing, and this site sets `<strong>` in prose on
 * `/arbitration/` and `/`. Found by `adversarial-reviewer` 2026-08-30.
 *
 * So every page is scanned TWICE — once as published, once with inline tags
 * collapsed to a single space. Block-level tags collapse to a full stop
 * instead, which preserves the "do not leap a paragraph" property that made the
 * `[^.<]` window worth having in the first place. Matches are deduplicated by
 * the matched text, so a hit visible in both views is reported once.
 */
const BLOCK_TAGS =
  /<\/?(?:p|div|section|article|header|footer|nav|main|aside|h[1-6]|li|ul|ol|dl|dt|dd|table|tr|td|th|blockquote|figure|figcaption|br|hr)\b[^>]*>/gi;

/**
 * ⚠️ THE BLOCK BOUNDARY IS A SENTINEL (`\uE000`), NOT A FULL STOP, AND THAT IS
 * WHAT LETS ONE REGEX SERVE BOTH VIEWS.
 *
 * First attempt substituted `' . '` and the windows were written `[^<]` — but
 * collapsed text contains no `<` at all, so the window was bounded by nothing
 * and leapt three block boundaries to join an `<h2>Q.Arb</h2>` to a paragraph
 * reading "took effect on 1 March 2025" — approved copy that ships. Measured by
 * `adversarial-reviewer`.
 *
 * Writing the windows `[^.<]` instead would fix that and reintroduce the defect
 * the collapsed view exists for: a real sentence period inside one paragraph
 * ("Qualified Arbitrator. Newly commenced") must still be crossable.
 *
 * A sentinel separates the two jobs. `[^<\uE000]` is bounded by `<` in the
 * published view and by `\uE000` in the collapsed one; neither character occurs
 * in the other view, and a full stop bounds neither. Every window in PATTERNS
 * uses that class.
 */
const BLOCK_BOUNDARY = '\uE000'; // Private Use Area: never occurs in real content,
// and unlike \u0000 it is not a control character, which `no-control-regex` bars.

function collapsedText(html) {
  return publishedText(html)
    .replace(BLOCK_TAGS, BLOCK_BOUNDARY)
    .replace(/<[^>]+>/g, ' ')
    .replace(/[ \t]+/g, ' ');
}

function contextAt(text, index, length) {
  const from = Math.max(0, index - 55);
  const to = Math.min(text.length, index + length + 55);
  const snip = text.slice(from, to).replace(/\s+/g, ' ');
  return `${from > 0 ? '…' : ''}${snip}${to < text.length ? '…' : ''}`;
}

function lineOf(text, index) {
  let line = 1;
  for (let i = 0; i < index; i++) if (text.charCodeAt(i) === 10) line++;
  return line;
}

function scan(text, re) {
  const hits = [];
  re.lastIndex = 0;
  let m;
  while ((m = re.exec(text)) !== null) {
    hits.push({ match: m[0], index: m.index });
    if (m[0].length === 0) re.lastIndex++;
  }
  return hits;
}

function selfTest() {
  const failures = [];
  for (const p of PATTERNS) {
    for (const positive of FIXTURES.mustMatch[p.id] ?? []) {
      if (scan(positive, p.re).length === 0) {
        failures.push(
          `${p.id}: STOPPED MATCHING its own fixture — ${JSON.stringify(positive)}`,
        );
      }
    }
    if (!(p.id in FIXTURES.mustMatch)) {
      failures.push(
        `${p.id}: has no fixture. Every pattern proves it still fires.`,
      );
    }
    for (const negative of FIXTURES.mustNotMatch) {
      /* ⚠️ BOTH VIEWS. This read `publishedText` only, which left the entire
         false-positive surface of `collapsedText` untested — and that is
         exactly where the loosening happened: the collapsed view leapt three
         block boundaries onto approved copy and the instrument check could not
         see it. Found by `adversarial-reviewer`. */
      const hits = [
        ...scan(publishedText(negative), p.re),
        ...scan(collapsedText(negative), p.re),
      ];
      if (hits.length > 0) {
        failures.push(
          `${p.id}: matched APPROVED copy — ${JSON.stringify(hits[0].match)} in ${JSON.stringify(negative)}`,
        );
      }
    }
  }
  return failures;
}

/* --- run ----------------------------------------------------------------- */

let failed = false;

console.log(
  'check:claims — AGENTS.md §4 Forbidden, enforced on shipped output',
);
console.log(`  target: ${rel(DIST)}/**/*.html\n`);

// 1. The instrument, before the measurement.
const selfTestFailures = selfTest();
if (selfTestFailures.length > 0) {
  console.error(
    'SELF-TEST FAILED — the patterns cannot be trusted, so nothing was swept.\n',
  );
  for (const f of selfTestFailures) console.error(`  ${f}`);
  console.error(
    '\nA pattern that no longer fires passes a clean sweep forever.',
  );
  process.exit(2);
}
console.log(
  `  self-test: ${PATTERNS.length} patterns fire on their fixtures and stay silent on ${FIXTURES.mustNotMatch.length} approved strings`,
);

// 2. The target has to exist and have content in it. An empty sweep is not a
//    pass — CLAUDE.md: "a command that did not run is not evidence of absence."
let pages;
try {
  pages = walk(DIST);
} catch (err) {
  console.error(`\nFAILED: cannot read ${DIST} — ${err.message}`);
  console.error(
    'Run `npm run build` first. This checks the built output, not the source.',
  );
  process.exit(2);
}
if (pages.length === 0) {
  console.error(`\nFAILED: no HTML under ${DIST}. Nothing was checked.`);
  console.error(
    'An empty sweep reads exactly like a clean one. Run `npm run build`.',
  );
  process.exit(2);
}

// 3. Staleness. A pass against yesterday's dist is the same false negative in
//    slower motion.
const newestPage = newestMtime(pages);
const newestSource = newestMtime([
  ...SOURCE_DIRS.map((d) => join(ROOT, d)),
  ...SOURCE_FILES.map((f) => join(ROOT, f)),
]);
if (newestSource.newest > newestPage.newest) {
  console.error(`\nFAILED: ${rel(DIST)} is older than the source.`);
  console.error(`  newest source: ${rel(newestSource.which)}`);
  console.error(`  newest page:   ${rel(newestPage.which)}`);
  console.error(
    '\nThis would have checked a build that does not include your change.',
  );
  console.error('Run `npm run build`, then this again.');
  process.exit(2);
}

console.log(`  pages:     ${pages.length}\n`);

for (const p of PATTERNS) {
  const hits = [];
  for (const page of pages) {
    const raw = readFileSync(page, 'utf8');
    /* ⚠️ DEDUPE BY OCCURRENCE COUNT, NEVER BY TEXT. The first version keyed a
       Set on the matched string, so `He is a lawyer.` twice on one page was
       reported ONCE and the count said 1 — the check truncating its own
       output, which is the one thing CLAUDE.md says a check must never do.
       Measured by `adversarial-reviewer` on a two-line fixture.

       The published view is authoritative; the collapsed view only ever ADDS
       occurrences the tags hid, so a collapsed hit counts only where it exceeds
       what the published view already found for that same text. */
    const counted = new Map();
    const bump = (key) => {
      const n = (counted.get(key) ?? 0) + 1;
      counted.set(key, n);
      return n;
    };
    const publishedCounts = new Map();
    for (const [viewIndex, text] of [
      publishedText(raw),
      collapsedText(raw),
    ].entries()) {
      for (const hit of scan(text, p.re)) {
        const key = hit.match.replace(/\s+/g, ' ').trim().toLowerCase();
        if (viewIndex === 0) {
          publishedCounts.set(key, (publishedCounts.get(key) ?? 0) + 1);
        } else if (bump(key) <= (publishedCounts.get(key) ?? 0)) {
          continue;
        }
        hits.push({
          page: rel(page),
          line: lineOf(text, hit.index),
          match: hit.match,
          context: contextAt(text, hit.index, hit.match.length),
        });
      }
    }
  }

  if (hits.length === 0) {
    console.log(`  ok    ${p.id}`);
    continue;
  }

  failed = true;
  console.error(
    `\n  FAIL  ${p.id} — ${hits.length} match${hits.length === 1 ? '' : 'es'}`,
  );
  console.error(`        rule:     ${p.rule}`);
  console.error(`        incident: ${p.incident}`);
  if (p.note) console.error(`        note:     ${p.note}`);
  console.error('');
  for (const hit of hits) {
    console.error(
      `        ${hit.page}:${hit.line}  ${JSON.stringify(hit.match)}`,
    );
    console.error(`          ${hit.context}`);
  }
}

if (failed) {
  console.error('\n' + '-'.repeat(72));
  console.error(
    'A match is not yet a finding — read the context printed above before acting.',
  );
  console.error(
    'This site has had a superlative sweep hit "pleadings" and a case-insensitive',
  );
  console.error(
    'sweep for LSO hit "I aLSO practise". Read what matched, then either fix the',
  );
  console.error(
    'copy or change this file DELIBERATELY, with an AGENTS.md Change Log entry.',
  );
  console.error('Do not delete a pattern to make a build pass.');
  process.exit(1);
}

console.log(
  '\nClean. Every pattern ran and every pattern is still firing on its fixture.',
);