voyage/lib/parsers/arg-parser.mjs

// lib/parsers/arg-parser.mjs
// Parse $ARGUMENTS strings for the seven voyage commands.
//
// Each command has its own valid-flag set; passing flags from another command
// produces an `unknown_flags` array but does not error — the caller decides.
//
// The commands hand $ARGUMENTS to the CLI as stdin text through a quoted
// heredoc (`--stdin`), never as shell words, so nothing in the arguments is
// expanded: no `~`, no `$VAR` or `$HOME`, no glob, no command substitution,
// and `;` is an ordinary character. Write a path out in full; `~/x` stays the
// three characters `~/x`. Quoting is the parser's own (see `tokenize`).

import { readFileSync } from 'node:fs';
import { isMain } from '../util/is-main.mjs';

const FLAG_SCHEMA = {
  trekbrief: {
    boolean: ['--quick', '--fg'],
    valued: ['--profile', '--approve'],
    aliases: {},
  },
  trekresearch: {
    boolean: ['--quick', '--local', '--external', '--fg'],
    valued: ['--project', '--profile'],
    aliases: {},
  },
  trekplan: {
    boolean: ['--quick', '--fg'],
    valued: ['--project', '--brief', '--export', '--decompose', '--profile'],
    multi: ['--research'],
    aliases: {},
  },
  trekexecute: {
    boolean: ['--resume', '--dry-run', '--validate', '--fg'],
    valued: ['--project', '--step', '--session', '--profile'],
    aliases: {},
  },
  trekreview: {
    boolean: ['--quick', '--fg', '--dry-run', '--validate', '--workflow'],
    valued: ['--project', '--since', '--profile'],
    aliases: {},
  },
  trekcontinue: {
    boolean: ['--help', '--cleanup', '--confirm', '--dry-run'],
    valued: ['--profile'],
    aliases: {},
  },
  trekendsession: {
    boolean: ['--help'],
    valued: [],
    aliases: {},
  },
};

/**
 * @param {string} argString  Raw $ARGUMENTS as the command sees it.
 * @param {keyof FLAG_SCHEMA} command
 * @returns {{
 *   command: string,
 *   flags: Record<string, true | string | string[]>,
 *   positional: string[],
 *   unknown: string[],
 *   errors: Array<{code: string, message: string}>,
 *   tail: string,
 * }}
 *   `tail` is the raw text after the first token, trimmed, with one balanced
 *   quote pair around the whole of it removed ('' when there is none): a
 *   label read whole, with its own spaces and apostrophes.
 */
export function parseArgs(argString, command) {
  const tail = tailOf(argString);
  const schema = FLAG_SCHEMA[command];
  if (!schema) {
    return {
      command,
      flags: {},
      positional: [],
      unknown: [],
      errors: [{ code: 'ARG_UNKNOWN_COMMAND', message: `Unknown command: ${command}` }],
      tail,
    };
  }

  const tokens = tokenize(argString).map((t) => t.value);
  const flags = {};
  const positional = [];
  const unknown = [];
  const errors = [];

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

    if (!tok.startsWith('--')) {
      positional.push(tok);
      continue;
    }

    if (schema.boolean.includes(tok)) {
      flags[tok] = true;
      continue;
    }

    if (schema.valued.includes(tok)) {
      const next = tokens[i + 1];
      if (next === undefined || next.startsWith('--')) {
        errors.push({ code: 'ARG_MISSING_VALUE', message: `Flag ${tok} requires a value` });
      } else {
        flags[tok] = next;
        i++;
      }
      continue;
    }

    if (schema.multi && schema.multi.includes(tok)) {
      const collected = [];
      while (i + 1 < tokens.length && !tokens[i + 1].startsWith('--')) {
        collected.push(tokens[i + 1]);
        i++;
      }
      if (collected.length === 0) {
        errors.push({ code: 'ARG_MISSING_VALUE', message: `Flag ${tok} requires at least one value` });
      } else {
        flags[tok] = collected;
      }
      continue;
    }

    unknown.push(tok);
  }

  return { command, flags, positional, unknown, errors, tail };
}

const isSpace = (c) => /\s/.test(c);

/**
 * Split argument text into words. Words are separated by whitespace. A word
 * that starts with `'` or `"` opens a quote. Its closing quote is the next
 * same-kind quote that ends a word (followed by whitespace or the end of the
 * text), whatever stands before it: a letter, whitespace or a line break. A
 * same-kind quote that starts a word (whitespace before it, a non-whitespace
 * character after it) stops the search: then there is no pair. Any other
 * same-kind quote (inside a word) is skipped. A pair groups the words between
 * the quotes into one value and is removed. A quote with no partner is a
 * literal character (`user's` stays `user's`). Examples: `"my dir "` is one
 * value, `my dir `; `'Fix the user's login'` is one value,
 * `Fix the user's login`; `"my dir"/x --since "HEAD~1"` gives the literal
 * words `"my` and `dir"/x`, then `--since` and `HEAD~1`. Nothing is expanded:
 * the function only slices the string.
 *
 * @param {string} text
 * @returns {Array<{ value: string, start: number, end: number }>}
 *   `start` / `end` are offsets into `text` (end exclusive), quotes included.
 */
export function tokenize(text) {
  if (typeof text !== 'string') return [];
  const out = [];
  const n = text.length;
  let i = 0;
  while (i < n) {
    while (i < n && isSpace(text[i])) i++;
    if (i >= n) break;
    const start = i;
    const q = text[i];
    if (q === '"' || q === "'") {
      let j = text.indexOf(q, i + 1);
      while (j !== -1 && j + 1 < n && !isSpace(text[j + 1])) {
        if (isSpace(text[j - 1])) { j = -1; break; }
        j = text.indexOf(q, j + 1);
      }
      if (j !== -1) {
        out.push({ value: text.slice(i + 1, j), start, end: j + 1 });
        i = j + 1;
        continue;
      }
    }
    while (i < n && !isSpace(text[i])) i++;
    out.push({ value: text.slice(start, i), start, end: i });
  }
  return out;
}

// The raw text after the first token, trimmed; one balanced quote pair that
// encloses the whole of it is removed. '' when there is no second token.
function tailOf(text) {
  const tokens = tokenize(text);
  if (tokens.length === 0) return '';
  const rest = text.slice(tokens[0].end).trim();
  const inner = tokenize(rest);
  if (inner.length === 1 && inner[0].start === 0 && inner[0].end === rest.length
      && (rest[0] === '"' || rest[0] === "'") && inner[0].value.length === rest.length - 2) {
    return inner[0].value;
  }
  return rest;
}

export { FLAG_SCHEMA };

// Flags a command cannot run without, and its usage line. The CLI below emits
// the error, so the command prose relays code output instead of composing the
// message (a model does not always repeat prose word for word — proevesett
// case review-requires-project failed 2 of 10 on backticks around the flag).
const REQUIRED = {
  trekreview: {
    flags: [['--project', '<dir>']],
    usage: 'Usage: /trekreview --project <dir> [--since <ref>] [--quick] [--validate] [--dry-run]',
  },
};

// CLI: node lib/parsers/arg-parser.mjs --command <command> --stdin <<'VOYAGE_ARGS_EOF_7F3C9E'
//      $ARGUMENTS
//      VOYAGE_ARGS_EOF_7F3C9E
//   reads the whole stdin as the argument text (one trailing newline
//   removed). The quoted heredoc keeps the shell from expanding anything; the
//   Bash guard (hooks/scripts/pre-bash-executor.mjs, args-heredoc-closed-early)
//   refuses a command in which that heredoc would close early.
// CLI: node lib/parsers/arg-parser.mjs --command <command> -- <word>...
//   the older argv form, kept: the words after `--` are the arguments.
//   stdout: the parse result as JSON (with `tail`). exit 0, or exit 1 with
//   each error as "Error: <message>" plus the usage line on stderr.
if (isMain(import.meta.url)) {
  const argv = process.argv.slice(2);
  const ci = argv.indexOf('--command');
  const command = ci >= 0 ? argv[ci + 1] : undefined;
  const dd = argv.indexOf('--');
  // `--stdin` counts only before `--`: after it, it is an argument word.
  const options = dd >= 0 ? argv.slice(0, dd) : argv;
  let r;
  if (options.includes('--stdin')) {
    let text = '';
    let readError = null;
    try {
      text = readFileSync(0, 'utf8');
    } catch (e) {
      readError = e;
    }
    r = parseArgs(text.replace(/\r?\n$/, ''), command);
    if (readError) {
      r.errors.push({ code: 'ARG_STDIN_UNREADABLE', message: `could not read the arguments from stdin (${readError.code || readError.message})` });
    }
  } else {
    const rest = dd >= 0 ? argv.slice(dd + 1) : [];
    r = parseArgs(rest.map((t) => (/\s/.test(t) ? `"${t}"` : t)).join(' '), command);
  }
  const req = REQUIRED[command];
  if (req) {
    for (const [flag, metavar] of req.flags) {
      if (!(flag in r.flags)) {
        r.errors.push({ code: 'ARG_REQUIRED_MISSING', message: `${flag} ${metavar} is required.` });
      }
    }
  }
  process.stdout.write(JSON.stringify(r) + '\n');
  if (r.errors.length > 0) {
    for (const e of r.errors) process.stderr.write(`Error: ${e.message}\n`);
    if (req) process.stderr.write(`${req.usage}\n`);
    process.exit(1);
  }
  process.exit(0);
}