// adversarial-scan.mjs — Layer B (G6 §8 / R6 punkt d): the PURE disposition core of
// the ingestion security gate. It is the ms-ai-architect-specific brain that decides,
// for each raw adversarial-content finding, whether it BLOCKs the write (hard-fail,
// never committed), WARNs (flag → same human-in-loop as a status-claim flag), or passes.
//
// Design:
//  - Detection (the injection lexicon, unicode charsets, base64/entropy) is the SHARED
//    llm-security asset — imported by the bridge (adversarial-detect.mjs), never copied
//    here (house policy: no drifting lexicon copies). This module receives already-detected
//    raw findings and is therefore pure + sync + trivially unit-testable.
//  - Disposition is PROVENANCE-TIERED (brief §5): source trust is a first-class input.
//    A payload in a low-trust surface (fenced code sample, localized string) is far more
//    likely a real attack → hard-fail; a payload-looking string in authored, en-locale
//    prose is more likely a legitimate doc artifact → WARN + human review, not a silent block.
//  - Orthogonal to the correctness judge: a factually-correct file that carries a payload
//    is still blocked. This gate answers "is this trying to inject / smuggle?", not "is
//    this claim true?".
//
// Never writes. Mirrors verify-out.mjs / transform.mjs: a pure classifier.

import { parseSourceHeader } from './kb-headers.mjs';

const FENCE_RE = /^\s*(```|~~~)/;

/**
 * Line spans (1-indexed, inclusive of both fence lines) of every fenced code block.
 * An unterminated fence treats the remainder of the file as code (fail-safe: we would
 * rather over-classify a region as low-trust code than let a smuggled payload ride in
 * an "open" fence and be treated as authored prose).
 * @param {string} content
 * @returns {Array<[number, number]>}
 */
export function findFencedCodeRanges(content) {
  const lines = String(content ?? '').split('\n');
  const ranges = [];
  let open = null;
  for (let i = 0; i < lines.length; i++) {
    if (FENCE_RE.test(lines[i])) {
      if (open === null) open = i + 1;
      else {
        ranges.push([open, i + 1]);
        open = null;
      }
    }
  }
  if (open !== null) ranges.push([open, lines.length]);
  return ranges;
}

/** Is a 1-indexed line inside any fenced code range? */
export function lineInCode(line, ranges) {
  return (ranges ?? []).some(([s, e]) => line >= s && line <= e);
}

/**
 * The Microsoft Learn locale segment of a Source URL, lowercased, or null.
 * e.g. https://learn.microsoft.com/nb-no/azure/x → "nb-no".
 * @param {string|null} sourceUrl
 * @returns {string|null}
 */
export function localeFromSource(sourceUrl) {
  if (!sourceUrl) return null;
  const m = String(sourceUrl).match(/learn\.microsoft\.com\/([a-z]{2}(?:-[a-z]{2,4})?)\//i);
  return m ? m[1].toLowerCase() : null;
}

/**
 * Provenance trust tier for a finding's line. Low-trust surfaces (adversary-reachable):
 * fenced code samples and localized (non-English) strings — the surfaces the threat
 * model (brief §3) calls community-contributable / machine-ingested. High-trust:
 * authored, English-locale prose.
 * @param {{line: number, ranges: Array<[number,number]>, sourceUrl: string|null}} args
 * @returns {'code-sample'|'localized'|'authored-doc'}
 */
export function provenanceTier({ line, ranges, sourceUrl }) {
  if (lineInCode(line, ranges)) return 'code-sample';
  const loc = localeFromSource(sourceUrl);
  if (loc && !loc.startsWith('en')) return 'localized';
  return 'authored-doc';
}

/** Low-trust tiers are the adversary-reachable surfaces. */
export function isLowTrust(tier) {
  return tier === 'code-sample' || tier === 'localized';
}

/** Invisible-carrier unicode subtypes — never legitimate in a KB reference file. */
const CARRIER_SUBTYPES = new Set(['zero-width', 'bidi', 'unicode-tag']);

/**
 * Disposition for a single finding given its provenance tier.
 *  block → hard-fail, never written / never committed.
 *  warn  → flag for human review (same human-in-loop as a status-claim flag).
 *  pass  → benign.
 *
 * Rationale (brief §5, §8):
 *  - Invisible unicode carriers (zero-width / bidi / unicode-tag) have NO legitimate
 *    reason to appear in authored Microsoft Learn content → block in any tier.
 *  - Encoded blobs (base64/hex): block on a low-trust surface (the "base64 inside a
 *    code sample" vector); WARN if they surface in authored prose (rarer, likelier FP).
 *  - Injection patterns are provenance-tiered: critical (spoofed <system>, override+
 *    identity) is unambiguous → block anywhere; high blocks on a low-trust surface but
 *    WARNs in authored prose (could be a doc literally discussing the pattern);
 *    medium/low → WARN.
 * @param {{class: string, subtype?: string, severity: string}} finding
 * @param {string} tier
 * @returns {'block'|'warn'|'pass'}
 */
export function disposition(finding, tier) {
  const cls = finding.class;
  const sev = finding.severity;
  if (cls === 'unicode') {
    return CARRIER_SUBTYPES.has(finding.subtype) ? 'block' : 'warn';
  }
  if (cls === 'encoded') {
    return isLowTrust(tier) ? 'block' : 'warn';
  }
  if (cls === 'injection') {
    if (sev === 'critical') return 'block';
    if (sev === 'high') return isLowTrust(tier) ? 'block' : 'warn';
    return 'warn';
  }
  // Unknown finding classes (e.g. read/scanner errors surfaced as findings) → block:
  // fail closed, never let an unclassifiable signal pass silently.
  return 'block';
}

const RANK = { block: 2, warn: 1, clean: 0 };

/**
 * Classify a batch of raw findings against the file content. Pure + sync.
 * @param {string} content — the full candidate file content (for code-fence + Source tiering)
 * @param {Array<object>} rawFindings — [{class, subtype?, severity, line, evidence}]
 * @param {{sourceUrl?: string}} [opts] — sourceUrl overrides the in-file **Source:** header
 * @returns {{disposition: 'block'|'warn'|'clean', findings: Array<object>}}
 */
export function classifyFindings(content, rawFindings, opts = {}) {
  const ranges = findFencedCodeRanges(content);
  const sourceUrl = opts.sourceUrl ?? parseSourceHeader(content) ?? null;
  const findings = (rawFindings ?? []).map((f) => {
    const tier = provenanceTier({ line: f.line, ranges, sourceUrl });
    return { ...f, tier, disposition: disposition(f, tier) };
  });
  let worst = 'clean';
  for (const f of findings) {
    if (RANK[f.disposition] > RANK[worst]) worst = f.disposition;
  }
  return { disposition: worst, findings };
}