/**
 * Extract the CLI invocations a command template tells the agent to run —
 * from the template's OWN text, never hand-written.
 *
 * [[dogfood-the-command-not-the-cli]] (#63): a hand-typed argv is a path no user
 * takes. The flag surface a template actually exercises is only knowable by
 * reading the template, and it lives in THREE forms, all of them "the template's
 * own text":
 *
 *   1. literal in the call        `--apply`, `--json`
 *   2. an `if` assignment         `… then RAW_FLAG="--raw"; fi`
 *   3. ONLY in a trailing comment `GLOBAL_FLAG=""   # --global`
 *
 * Form 3 is the class that can die silently. The variable is empty on the
 * default path, so a template run without the user flag proves nothing about
 * whether the CLI still accepts it — exactly the shape of M-BUG-45, where
 * `--stale-after` reached the CLI malformed and the command reported success.
 * An extractor that reads only forms 1 and 2 is green on its own defect.
 */

import { readFile, readdir } from 'node:fs/promises';
import { resolve, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';

const __dirname = dirname(fileURLToPath(import.meta.url));
export const COMMANDS_DIR = resolve(__dirname, '..', '..', 'commands');

/** `node ${CLAUDE_PLUGIN_ROOT}/scanners/<name>.mjs` — the only anchored form. */
const INVOCATION = /node\s+\$\{CLAUDE_PLUGIN_ROOT\}\/scanners\/([A-Za-z0-9._-]+\.mjs)/;

/** A bare `--flag` token. Stops at `=` so `--flag=value` still yields `--flag`. */
const FLAG_TOKEN = /(^|[\s"'])(--[a-z][a-z0-9-]*)(?=[\s"'=]|$)/g;

/** `$VAR` or `"$VAR"` or `${VAR}` in an argv position. */
const VAR_TOKEN = /\$\{?([A-Z_][A-Z0-9_]*)\}?/g;

/**
 * Join shell line-continuations so a multi-line invocation is one logical line.
 * Returns `[{ text, line }]` where `line` is the 1-based line the call STARTS on.
 */
function logicalLines(content) {
  const raw = content.split('\n');
  const out = [];
  let buffer = null;

  raw.forEach((text, i) => {
    const continues = /\\\s*$/.test(text);
    const body = text.replace(/\\\s*$/, '');
    if (buffer) {
      buffer.text += ' ' + body.trim();
      if (!continues) { out.push(buffer); buffer = null; }
      return;
    }
    if (continues) { buffer = { text: body, line: i + 1 }; return; }
    out.push({ text, line: i + 1 });
  });

  if (buffer) out.push(buffer);
  return out;
}

/**
 * Every flag a shell variable can carry, resolved from the template itself.
 * Returns `Map<varName, string[]>`.
 *
 * Both `VAR="--flag"` (any position, so the `if … then VAR="--raw"; fi` idiom is
 * covered) and the comment form are read. The comment form is read from the
 * WHOLE trailing comment, so `# e.g. SCOPE_FLAG="--full-machine" or
 * SCOPE_FLAG="--global"` yields both candidates: a template that documents two
 * possible values promises the CLI accepts both.
 */
export function resolveFlagVariables(content) {
  const vars = new Map();
  const add = (name, flag) => {
    if (!vars.has(name)) vars.set(name, []);
    if (!vars.get(name).includes(flag)) vars.get(name).push(flag);
  };

  for (const { text } of logicalLines(content)) {
    // Form 2 — assignment to a literal flag, anywhere on the line.
    for (const m of text.matchAll(/\b([A-Z_][A-Z0-9_]*)=["'](--[a-z][a-z0-9-]*)["']/g)) {
      add(m[1], m[2]);
    }
    // Form 3 — an empty assignment whose real value lives in the comment.
    const commented = text.match(/\b([A-Z_][A-Z0-9_]*)=["']{2}\s*#(.*)$/);
    if (commented) {
      for (const f of commented[2].matchAll(/(--[a-z][a-z0-9-]*)/g)) add(commented[1], f[1]);
    }
  }

  return vars;
}

/**
 * All invocations in one template.
 * `[{ cli, flags: string[], line, source: Map<flag, 'literal'|'$VAR'> }]`
 */
export function extractInvocations(content) {
  const vars = resolveFlagVariables(content);
  const found = [];

  for (const { text, line } of logicalLines(content)) {
    const call = text.match(INVOCATION);
    if (!call) continue;

    // Only the part AFTER the script path is argv.
    const argv = text.slice(text.indexOf(call[0]) + call[0].length);
    const flags = [];
    const source = new Map();
    const push = (flag, from) => {
      if (!flags.includes(flag)) { flags.push(flag); source.set(flag, from); }
    };

    for (const m of argv.matchAll(FLAG_TOKEN)) push(m[2], 'literal');
    for (const m of argv.matchAll(VAR_TOKEN)) {
      for (const flag of vars.get(m[1]) ?? []) push(flag, `$${m[1]}`);
    }

    found.push({ cli: call[1], flags, line, source });
  }

  return found;
}

/** Every command template, as `[{ file, content }]`, sorted. */
export async function commandTemplates() {
  const entries = (await readdir(COMMANDS_DIR)).filter((e) => e.endsWith('.md')).sort();
  return Promise.all(
    entries.map(async (file) => ({
      file,
      content: await readFile(resolve(COMMANDS_DIR, file), 'utf-8'),
    })),
  );
}

/**
 * The whole command layer's contract with the CLI layer:
 * `[{ file, line, cli, flags, source }]`, one entry per invocation.
 */
export async function allInvocations() {
  const out = [];
  for (const { file, content } of await commandTemplates()) {
    for (const inv of extractInvocations(content)) out.push({ file, ...inv });
  }
  return out;
}