// injection-lexicon.mjs — Prompt-injection pattern tables, built from vendored commons.
//
// v8 Phase 5 step 4, third consumer swap. The four arrays were 83 regex
// literals in injection-patterns.mjs; they are now built once, here, from
// `lexicon/injection-lexicon.json` in the vendored llm-security-commons
// subtree. Verified before the swap by a differential over all 83 positions —
// regex source, flags, label and `aliases.llm_security` — against the live
// source tables at commons v0.3.0: zero divergences, in order.
//
// The lexicon keys each family by `source_export`, which is the name of the
// constant it was extracted from, so the mapping from family to published
// table is data rather than a convention this file restates.
//
// Two things about this swap differ from the first two (codepoints, owasp-map)
// and are deliberate:
//
//   1. FAILURE IS LOUD. Those two degrade a normalization step and a report
//      label respectively, and their empty state is legitimately reachable, so
//      they fail silently by design. An empty injection table is different in
//      kind: `scanForInjection` would return `found: false` for every input
//      and every gate built on it — the UserPromptSubmit scan, the MCP output
//      scan, the pre-compact scan — would report success without running.
//      That is the v7.8.2 defect class, and this plugin has been bitten by it
//      four times in one release. So an unresolvable commons writes one line
//      to stderr. It still does not throw: hooks run per-tool-call, and a
//      module-load throw breaks the tool call rather than degrading the scan.
//      The warning fires only for the DEFAULT root — an explicit
//      `commonsRoot` is a test or a dev checkout deliberately pointing
//      elsewhere, and warning there would train the reader to ignore the line.
//
//   2. ENTRIES ARE COMPILED DEFENSIVELY. commons is vendored data, not code.
//      `new RegExp(source, flags)` throws on an uncompilable pattern or an
//      unknown flag, and it would throw at module load — inside a hook. A
//      malformed entry is therefore dropped rather than published, the same
//      call owasp-map.mjs makes for a non-array value.
//
// Array order is preserved and never sorted: it decides both dedup precedence
// in `scanForInjection` and the order findings reach report output.
//
// Zero external dependencies — Node.js builtins only.

import { loadArtifact } from './commons-loader.mjs';

/**
 * The `source_export` names this module publishes.
 *
 * A family the lexicon adds under any other name is ignored rather than
 * turned into a table no consumer reads — the same call codepoints.mjs makes
 * for `cyrillic_confusables`.
 */
const PUBLISHED_EXPORTS = Object.freeze([
  'CRITICAL_PATTERNS',
  'HIGH_PATTERNS',
  'MEDIUM_PATTERNS',
  'HYBRID_PATTERNS',
]);

/**
 * Compile one lexicon entry into the `{ pattern, label }` shape the consumers
 * expect, or return null if the entry cannot be trusted.
 */
function compileEntry(entry) {
  if (entry === null || typeof entry !== 'object') return null;
  if (typeof entry.pattern !== 'string' || typeof entry.label !== 'string') return null;
  // Absent `flags` means no flags — the lexicon's dialect note is explicit
  // that flags are declared per pattern and never inlined as `(?i)`.
  const flags = entry.flags ?? '';
  if (typeof flags !== 'string') return null;
  try {
    return Object.freeze({ pattern: new RegExp(entry.pattern, flags), label: entry.label });
  } catch {
    return null; // uncompilable source or unknown flag — drop, do not throw
  }
}

/**
 * Build the four injection tables from a commons root.
 *
 * @param {object} [opts]
 * @param {string} [opts.commonsRoot] - explicit commons root (tests, dev checkout).
 *   Suppresses the unresolvable-commons warning, which is meant for the
 *   default root only.
 * @returns {{
 *   CRITICAL_PATTERNS: ReadonlyArray<{pattern: RegExp, label: string}>,
 *   HIGH_PATTERNS: ReadonlyArray<{pattern: RegExp, label: string}>,
 *   MEDIUM_PATTERNS: ReadonlyArray<{pattern: RegExp, label: string}>,
 *   HYBRID_PATTERNS: ReadonlyArray<{pattern: RegExp, label: string}>,
 * }} Every key is always present, so a lost commons yields empty tables
 *   rather than undefined ones a consumer would iterate and throw on.
 */
export function buildInjectionTables(opts = {}) {
  const artifact = loadArtifact('lexicon/injection-lexicon', {
    fallback: null,
    commonsRoot: opts.commonsRoot,
  });

  if (artifact === null && opts.commonsRoot === undefined) {
    // See note 1 above: silent is the one thing this failure must not be.
    process.stderr.write(
      '[llm-security] injection lexicon unresolvable at scanners/commons/lexicon/injection-lexicon.json — '
      + 'prompt-injection detection is DISABLED for this process. Reinstall the plugin or re-vendor the commons subtree.\n',
    );
  }

  const tables = {};
  for (const name of PUBLISHED_EXPORTS) tables[name] = [];

  for (const family of artifact?.families ?? []) {
    const name = family?.source_export;
    if (!PUBLISHED_EXPORTS.includes(name)) continue;
    if (!Array.isArray(family.patterns)) continue;
    for (const entry of family.patterns) {
      const compiled = compileEntry(entry);
      if (compiled !== null) tables[name].push(compiled);
    }
  }

  for (const name of PUBLISHED_EXPORTS) Object.freeze(tables[name]);
  return tables;
}

const _tables = buildInjectionTables();

/** Direct injection attempts — blocked, not warned about. */
export const CRITICAL_PATTERNS = _tables.CRITICAL_PATTERNS;

/** Subtle manipulation: reframing, oversight evasion, HITL traps, HTML obfuscation. */
export const HIGH_PATTERNS = _tables.HIGH_PATTERNS;

/** Obfuscation and indirect manipulation — lower confidence, advisory. */
export const MEDIUM_PATTERNS = _tables.MEDIUM_PATTERNS;

/** Cross-domain injection: P2SQL, recursive injection, XSS in agent context. Reported as HIGH. */
export const HYBRID_PATTERNS = _tables.HYBRID_PATTERNS;