halkyon/halkyon_learn_curator/bin/curate.dart

import 'dart:convert';
import 'dart:io';

import 'package:args/args.dart';
import 'package:halkyon_learn_curator/src/sources/jlpt.dart';
import 'package:halkyon_learn_curator/src/sources/jmdict.dart';
import 'package:halkyon_learn_curator/src/sources/jmdict_xml.dart';
import 'package:halkyon_learn_curator/src/sources/kanjidic.dart';
import 'package:halkyon_learn_curator/src/sources/kanjivg.dart';
import 'package:halkyon_learn_curator/src/update.dart';

/// Turns a dictionary download into a dictionary file for the server's
/// `dictionaries` folder, or KanjiVG into the app's stroke files
/// (README.md):
///
///     dart run halkyon_learn_curator:curate jmdict \
///       --input JMdict_e_examp.gz --jlpt original_data \
///       --output jmdict-en.jsonl.gz
///     dart run halkyon_learn_curator:curate kanjidic \
///       --input kanjidic2.xml.gz --jlpt kanji.json \
///       --output kanjidic-en.jsonl.gz
///     dart run halkyon_learn_curator:curate kanjivg \
///       --input kanjivg-20260714.xml.gz \
///       --output ../halkyon_learn_flutter/assets/kanjivg
///
/// Or brings a server's dictionaries up to date from EDRDG's files of the
/// day, once or every so many days:
///
///     dart run halkyon_learn_curator:curate update \
///       --into ../halkyon_learn_server/dictionaries [--every 7]
Future<void> main(List<String> args) async {
  final parser = ArgParser()
    ..addOption(
      'input',
      abbr: 'i',
      help: 'The source file, unpacked or gzipped (.gz).',
    )
    ..addOption(
      'jlpt',
      help:
          "jmdict: yomitan-jlpt-vocab's original_data folder (n1.csv … "
          "n5.csv); kanjidic: kanji-data's kanji.json.",
    )
    ..addFlag(
      'examples',
      help:
          "The input is JMdict's examples edition (EDRDG's "
          "JMdict_e_examp.gz, jmdict-simplified's jmdict-examples-eng-*.json): "
          'credit Tatoeba for its sentences. On by default for a file named '
          'so.',
      defaultsTo: null,
    )
    ..addOption(
      'output',
      abbr: 'o',
      help:
          'The dictionary file to write, gzipped when it ends in .gz; for '
          'kanjivg the folder to write the stroke files into.',
    )
    ..addOption('into', help: 'update: the folder of the dictionary files.')
    ..addOption(
      'data',
      help: "update: the curator's data folder (the JLPT lists).",
      defaultsTo: 'data',
    )
    ..addOption(
      'every',
      help:
          'update: keep running, and update once the files are this many '
          'days old.',
    );
  final ArgResults options;
  try {
    options = parser.parse(args);
  } on FormatException catch (error) {
    _fail('${error.message}\n${parser.usage}');
  }
  final [source, ...] = options.rest.isEmpty ? [''] : options.rest;
  if (source == 'update') {
    final into = options.option('into');
    final every = options.option('every');
    final days = every == null ? null : int.tryParse(every);
    if (into == null || (every != null && (days == null || days < 1))) {
      _fail(
        'Usage: curate update --into <folder> [--data <folder>] '
        '[--every <days>]\n${parser.usage}',
      );
    }
    await _update(Directory(into), Directory(options.option('data')!), days);
    return;
  }
  final input = options.option('input');
  final output = options.option('output');
  if (!['jmdict', 'kanjidic', 'kanjivg'].contains(source) ||
      input == null ||
      output == null) {
    _fail(
      'Usage: curate jmdict|kanjidic|kanjivg --input <file> [--jlpt <path>] '
      '--output <path>\n${parser.usage}',
    );
  }
  final read = File(input).openRead();
  final text = (input.endsWith('.gz') ? read.transform(gzip.decoder) : read)
      .transform(utf8.decoder);
  final jlptPath = options.option('jlpt');

  if (source == 'kanjivg') {
    final strokes = kanjivgStrokes(await text.join());
    final folder = await Directory(output).create(recursive: true);
    final files = strokeFiles(strokes);
    for (final MapEntry(key: name, value: characters) in files.entries) {
      await File('${folder.path}/$name.json.gz')
          .writeAsBytes(gzip.encode(utf8.encode(jsonEncode(characters))));
    }
    stdout.writeln(
      'Wrote the strokes of ${strokes.length} characters to '
      '${files.length} files in $output.',
    );
    return;
  }

  final Stream<String> lines;
  final int withLevel;
  if (source == 'kanjidic') {
    final jlpt = jlptPath == null
        ? const <String, int>{}
        : await readKanjiJlpt(File(jlptPath));
    lines = Stream.fromIterable(
      kanjidicDictionary(await text.join(), jlpt: jlpt),
    );
    withLevel = jlpt.length;
  } else {
    final jlpt = jlptPath == null
        ? const <String, JlptLevel>{}
        : await readJlptLevels(Directory(jlptPath));
    final name = File(input).uri.pathSegments.last;
    final examples = options.wasParsed('examples')
        ? options.flag('examples')
        : name.contains('examp');
    // jmdict-simplified's JSON (`jmdict-eng-….json`), else EDRDG's XML.
    lines = name.contains('.json')
        ? jmdictDictionary(text, jlpt: jlpt, examples: examples)
        : jmdictXmlDictionary(text, jlpt: jlpt, examples: examples);
    withLevel = jlpt.length;
  }
  var entries = -1;
  final bytes = lines
      .map((line) {
        entries++;
        return line;
      })
      .transform(utf8.encoder);
  await (output.endsWith('.gz') ? bytes.transform(gzip.encoder) : bytes).pipe(
    File(output).openWrite(),
  );
  stdout.writeln(
    'Wrote $entries entries to $output'
    '${withLevel == 0 ? '' : ' ($withLevel with a JLPT level)'}.',
  );
}

/// Updates the dictionaries in [into]; with [every], keeps running and
/// updates them whenever they are that many days old (as the files' dates
/// say, so a restart doesn't download them again), trying again after six
/// hours when an update fails.
Future<void> _update(Directory into, Directory data, int? every) async {
  void say(String message) =>
      stdout.writeln('${DateTime.now().toUtc().toIso8601String()} $message');
  Future<bool> once() async {
    try {
      final written = await updateDictionaries(into: into, data: data);
      say(
        'Updated ${[for (final file in written) file.uri.pathSegments.last].join(', ')}.',
      );
      return true;
    } on Object catch (error) {
      say('Updating the dictionaries failed: $error');
      return false;
    }
  }

  if (every == null) {
    if (!await once()) {
      exit(1);
    }
    return;
  }
  for (;;) {
    final due = lastUpdated(into)?.add(Duration(days: every));
    final now = DateTime.now();
    if (due == null || !now.isBefore(due)) {
      if (!await once()) {
        await Future<void>.delayed(const Duration(hours: 6));
      }
      continue;
    }
    say('Up to date; the next update ${due.toUtc().toIso8601String()}.');
    await Future<void>.delayed(due.difference(now));
  }
}

Never _fail(String message) {
  stderr.writeln(message);
  exit(64);
}