/**
 * subtraction-prefilter — deterministic candidate generator for the v5.13
 * subtraction lens (`/config-audit optimize --subtract`, BP-SUB-001).
 *
 * Every other command in this plugin asks an ADDITION question — what could you
 * add, what would fit a better mechanism, how expensive is what you have. This
 * module asks the inverse: **what is no longer earning its always-loaded rent?**
 *
 * It is the mirror image of `lens-prefilter` in one important way. That module
 * is recall-first, because a false candidate only costs the judge a moment's
 * thought. Here a false candidate is a proposal to DELETE something, so the
 * polarity flips: precision-first, and a hard deterministic floor
 * (`floor-exclusion`) that the judge is not allowed to override.
 *
 * ## Granularity: leaf blocks
 *
 * The one design choice the hand-built fasit deliberately left open. A block is
 * one markdown *leaf*: a list item including its wrapped continuation lines, or
 * a paragraph. Headings, table rows and fenced code are structural, never
 * candidates.
 *
 * Both halves of that choice are load-bearing, and the fasit tests both:
 *   - It must SPLIT. A numbered list whose steps 2–3 are local facts and whose
 *     steps 1 and 4 are filler is a mixed block; section granularity would have
 *     to keep or drop all four.
 *   - It must NOT split further. A bullet's load-bearing literal often sits on a
 *     wrapped continuation line ("…— `coord-send` er mekanismen"). A
 *     line-granular mechanism severs the first line from the fact that protects
 *     it and proposes a floor block for deletion — the exact failure the gate
 *     exists to prevent.
 *
 * ## Two independent guarantees, not one
 *
 * A load-bearing block fails to become a candidate for either of two reasons,
 * and both are needed:
 *   1. it is *declarative* — "Language: Norwegian for dialogue" states a fact
 *      about the human and corrects no behaviour, so no detector fires; or
 *   2. `floor-exclusion` vetoes it for carrying an underivable local literal.
 * Group 1 never reaches the veto at all, which is why the contract is asserted
 * on the candidate list rather than on either mechanism alone.
 *
 * Norwegian and English are both first-class: the config this was designed
 * against is Norwegian prose carrying English identifiers.
 *
 * Zero external dependencies. Pure: input text → candidate array.
 */

import { floorMarker } from './floor-exclusion.mjs';

/**
 * The subtraction detector, kept in its OWN table. `LENS_DETECTORS` drives the
 * plain `optimize` payload's register block, and the subtraction axis must not
 * fire on a plain run — it asks a different question and the operator has to
 * opt into it with `--subtract`.
 */
export const SUBTRACT_DETECTORS = Object.freeze([
  { lensCheck: 'compensatory-instruction', registerId: 'BP-SUB-001', mechanism: 'deletion' },
]);

/**
 * Absolute / insistent phrasing. An instruction that has to shout is usually
 * correcting behaviour rather than stating a fact.
 */
/**
 * Word boundaries that understand æ/ø/å.
 *
 * JavaScript's `\b` is ASCII-only, so `/\bunngå\b/` never matches "unngå " —
 * the trailing "å" is not a word character, so there is no boundary after it.
 * Every Norwegian keyword ending in æ/ø/å was silently dead until the dogfood
 * run surfaced it. Do not reintroduce `\b` around this vocabulary.
 */
const LB = '(?<![\\wæøåÆØÅ])';
const RB = '(?![\\wæøåÆØÅ])';

const ABSOLUTE_RE = new RegExp(
  LB +
    '(?:never|always|avoid|don\'t|do not|must not|ensure|remember to|make sure|' +
    'aldri|alltid|unngå|husk|sørg for|ikke)' +
    RB,
  'i',
);

/**
 * Imperative verbs — the grammatical signature of telling the model how to
 * behave. Matched anywhere in the block, since Norwegian list prose puts them
 * after a colon ("…oppgaver: forstå problemet, vurder alternativer").
 *
 * Word boundaries matter more than the list length: `\bdocument\b` must not
 * match "documentation", or the declarative language-preference fact — a floor
 * block with no local literal to veto it — would become a deletion candidate.
 */
const IMPERATIVE_RE = new RegExp(
  LB +
    '(?:' +
    // English
    'think|write|test|commit|use|read|check|ask|verify|stop|start|summarize|' +
    'wait|match|change|fix|present|identify|keep|prefer|declare|refactor|' +
    'document|explain|split|review|' +
    // Norwegian
    'tenk|skriv|test|commit|bruk|les|sjekk|spør|verifiser|dokumenter|stopp|' +
    'start|oppsummer|vent|gjør|match|endre|fiks|presenter|identifiser|forstå|' +
    'vurder|hold|siter|jobb|gjett|push|del|sett|forklar|utfør|følg' +
    ')' +
    RB,
  'i',
);

/**
 * Minimum words for a block whose ONLY signal is an absolute marker. A bare
 * "Haiku: aldri." is a declarative policy fact wearing the word "aldri", not an
 * instruction about how to behave — the same reason "Tone: direct and technical"
 * never fires. Blocks carrying a real imperative verb are exempt from the floor,
 * so "Test inkrementelt" still surfaces at two words.
 */
const ABSOLUTE_ONLY_MIN_WORDS = 6;

const HEADING_RE = /^\s*#{1,6}\s/;
const TABLE_RE = /^\s*\|/;
const FENCE_RE = /^\s*(?:```|~~~)/;
const LIST_ITEM_RE = /^\s*(?:[-*+]\s+|\d+[.)]\s+)/;
const ORDERED_ITEM_RE = /^\s*\d+[.)]\s+/;
const CONTINUATION_RE = /^\s+\S/;
/** A paragraph that introduces the list beneath it ("…tre lag med hver sin ene jobb:"). */
const STEM_RE = /:\s*$/;

/**
 * Split markdown into leaf blocks.
 *
 * @param {string} text
 * @returns {Array<{startLine:number, endLine:number, text:string, type:string}>}
 *   `type` is one of paragraph | list-item | heading | table | code.
 */
export function splitLeafBlocks(text) {
  const lines = String(text == null ? '' : text).split('\n');
  const blocks = [];
  let current = null;
  let inFence = false;

  const flush = () => {
    if (current) blocks.push(current);
    current = null;
  };
  const indentOf = (line) => (line.match(/^\s*/) || [''])[0].length;
  const open = (type, i, line) => {
    current = { startLine: i + 1, endLine: i + 1, text: line, type, indent: indentOf(line) };
  };

  for (let i = 0; i < lines.length; i++) {
    const line = lines[i];

    if (FENCE_RE.test(line)) {
      flush();
      inFence = !inFence;
      blocks.push({ startLine: i + 1, endLine: i + 1, text: line, type: 'code' });
      continue;
    }
    if (inFence) {
      blocks.push({ startLine: i + 1, endLine: i + 1, text: line, type: 'code' });
      continue;
    }
    if (line.trim() === '') {
      flush();
      continue;
    }
    if (HEADING_RE.test(line)) {
      flush();
      blocks.push({ startLine: i + 1, endLine: i + 1, text: line, type: 'heading' });
      continue;
    }
    if (TABLE_RE.test(line)) {
      flush();
      blocks.push({ startLine: i + 1, endLine: i + 1, text: line, type: 'table' });
      continue;
    }
    if (LIST_ITEM_RE.test(line)) {
      // Structural exception 1: a paragraph ending in ':' is this list's stem —
      // it introduces the items rather than standing alone, so it merges with
      // them. Deleting a stem without its list is meaningless, and a stem often
      // carries no literal of its own to protect it.
      //
      // A list item can be a stem too ("5. …alltid eksplisitt:" over its
      // sub-bullets) — but only when the following item is nested deeper, or
      // sibling bullets would glue together.
      const isStem =
        current &&
        STEM_RE.test(current.text) &&
        (current.type === 'paragraph' || indentOf(line) > current.indent);
      if (isStem) {
        current.type = 'list-item';
        if (current.ordered === undefined) current.ordered = ORDERED_ITEM_RE.test(line);
        current.endLine = i + 1;
        current.text += '\n' + line;
        current.stemMerged = true;
        current.stemIndent = indentOf(line);
        continue;
      }
      if (current && current.stemMerged && current.endLine === i && indentOf(line) >= current.stemIndent) {
        // Subsequent items of the same stemmed list join it too.
        current.endLine = i + 1;
        current.text += '\n' + line;
        continue;
      }
      // Otherwise a new list item always ends the previous block, even mid-list.
      flush();
      open('list-item', i, line);
      current.ordered = ORDERED_ITEM_RE.test(line);
      continue;
    }
    if (current && CONTINUATION_RE.test(line)) {
      // Indented wrap — belongs to the block it continues.
      current.endLine = i + 1;
      current.text += '\n' + line;
      continue;
    }
    if (current && current.type === 'paragraph') {
      current.endLine = i + 1;
      current.text += '\n' + line;
      continue;
    }
    flush();
    open('paragraph', i, line);
  }
  flush();

  return blocks.sort((a, b) => a.startLine - b.startLine);
}

/** Blocks that can carry a deletable instruction at all. */
const isProse = (block) => block.type === 'paragraph' || block.type === 'list-item';

const wordCount = (s) => s.trim().split(/\s+/).filter(Boolean).length;

/**
 * Does the block instruct behaviour at all? A declarative fact does not, however
 * absolute its wording: "Haiku: aldri." and "Tone: direct and technical" both
 * state a decision rather than correcting how the model works.
 */
function correctsBehaviour(text) {
  if (IMPERATIVE_RE.test(text)) return true;
  return ABSOLUTE_RE.test(text) && wordCount(text) >= ABSOLUTE_ONLY_MIN_WORDS;
}

/**
 * Structural exception 2: an ordered list is a CONTRACT. Numbered steps are a
 * sequence whose items reference each other, so a floor marker on any step
 * floors the whole run — deleting step 2 of a five-step session protocol is not
 * the same kind of act as deleting one bullet from a list of platitudes.
 *
 * Unordered lists deliberately do NOT inherit. B-32a and B-32b are opposite
 * calls inside one bullet list, and "the container decides" is precisely the
 * reasoning the fasit exists to refute.
 *
 * @returns {Set<number>} startLine of every block floored by inheritance
 */
function orderedContractFloor(blocks, floored) {
  const inherited = new Set();
  let run = [];
  const closeRun = () => {
    if (run.length > 1 && run.some((b) => floored.has(b.startLine))) {
      for (const b of run) inherited.add(b.startLine);
    }
    run = [];
  };
  for (const block of blocks) {
    const contiguous = run.length > 0 && block.startLine === run[run.length - 1].endLine + 1;
    if (block.ordered && (run.length === 0 || contiguous)) {
      run.push(block);
    } else {
      closeRun();
      if (block.ordered) run.push(block);
    }
  }
  closeRun();
  return inherited;
}

/**
 * Compensatory-phrasing candidates that survived floor-exclusion.
 *
 * @param {string} text
 * @returns {Array<{lensCheck:string, registerId:string, mechanism:string,
 *   line:number, startLine:number, endLine:number, lineCount:number, text:string}>}
 */
export function subtractionCandidates(text) {
  const detector = SUBTRACT_DETECTORS[0];
  const out = [];
  const blocks = splitLeafBlocks(text).filter(isProse);

  // 1. The blocking floor veto, evaluated over the WHOLE leaf block — so a
  //    literal on a wrapped continuation line still protects its opening line.
  const floored = new Set();
  for (const block of blocks) {
    if (floorMarker(block.text)) floored.add(block.startLine);
  }
  // 2. …then propagated across ordered-list contracts.
  const inherited = orderedContractFloor(blocks, floored);

  for (const block of blocks) {
    // 3. Does it correct behaviour at all? A declarative local fact does not.
    if (!correctsBehaviour(block.text)) continue;
    if (floored.has(block.startLine) || inherited.has(block.startLine)) continue;

    out.push({
      lensCheck: detector.lensCheck,
      registerId: detector.registerId,
      mechanism: detector.mechanism,
      line: block.startLine,
      startLine: block.startLine,
      endLine: block.endLine,
      lineCount: block.endLine - block.startLine + 1,
      text: block.text.trim(),
    });
  }

  return out;
}

/**
 * Diagnostics for the floor gate: every prose block that fired the detector but
 * was vetoed, with the marker that saved it. Not user-facing — this is how a
 * later narrowing of the veto can be checked against the fasit.
 *
 * @param {string} text
 * @returns {Array<{startLine:number, endLine:number, marker:string, why:string}>}
 */
export function floorExcluded(text) {
  const blocks = splitLeafBlocks(text).filter(isProse);
  const floored = new Set();
  for (const block of blocks) {
    if (floorMarker(block.text)) floored.add(block.startLine);
  }
  const inherited = orderedContractFloor(blocks, floored);

  const out = [];
  for (const block of blocks) {
    if (!correctsBehaviour(block.text)) continue;
    const marker = floorMarker(block.text);
    if (marker) {
      out.push({ startLine: block.startLine, endLine: block.endLine, marker: marker.name, why: marker.why });
    } else if (inherited.has(block.startLine)) {
      out.push({
        startLine: block.startLine,
        endLine: block.endLine,
        marker: 'ordered-contract',
        why: 'is a step of an ordered list whose sibling carries a local fact',
      });
    }
  }
  return out;
}