lib/util: add several utils from jptools

lib/_data_ingestion/jmdict/parser.dart

@@ -2,7 +2,7 @@ import 'dart:collection';
 import 'dart:io';
 
 import 'package:collection/collection.dart';
-import 'package:jadb/romaji_transliteration.dart';
+import 'package:jadb/util/romaji_transliteration.dart';
 import 'package:sqflite_common/sqlite_api.dart';
 import 'package:xml/xml.dart';
 

lib/util/datetime_extensions.dart

@@ -0,0 +1,303 @@
+import 'dart:core';
+
+// Run in console on http://www.kumamotokokufu-h.ed.jp/kumamoto/bungaku/nengoui.html
+// Array.from(document.querySelectorAll('table')[1].querySelectorAll('tr')).slice(1).map(row => `DateTime(${row.children[3 + (row.children.length == 7)].innerHTML.replace(/～.*/, '')}, ${row.children[4 + (row.children.length == 7)].innerHTML.replace('/', ', ')}): '${row.children[2 + (row.children.length == 7)].innerHTML}'`).join('\n')
+
+const Map<(int, int, int), String> periodsBeforeNanbokuchou = {
+  (645, 6, 19): '大化',
+  (650, 2, 15): '白雉',
+  (686, 7, 20): '朱鳥',
+  (701, 3, 21): '大宝',
+  (704, 5, 10): '慶雲',
+  (708, 1, 11): '和銅',
+  (715, 9, 2): '霊亀',
+  (717, 11, 17): '養老',
+  (724, 2, 4): '神亀',
+  (729, 8, 5): '天平',
+  (749, 4, 14): '天平感宝',
+  (749, 7, 2): '天平勝宝',
+  (757, 8, 18): '天平宝字',
+  (765, 1, 7): '天平神護',
+  (767, 8, 16): '神護景雲',
+  (770, 10, 1): '宝亀',
+  (781, 1, 1): '天応',
+  (782, 8, 19): '延暦',
+  (806, 5, 18): '大同',
+  (810, 9, 19): '弘仁',
+  (824, 1, 5): '天長',
+  (834, 1, 3): '承和',
+  (848, 6, 13): '嘉祥',
+  (851, 4, 28): '仁寿',
+  (854, 11, 30): '斎衡',
+  (857, 2, 21): '天安',
+  (859, 4, 15): '貞観',
+  (877, 4, 16): '元慶',
+  (885, 2, 21): '仁和',
+  (889, 4, 27): '寛平',
+  (898, 4, 26): '昌泰',
+  (901, 7, 15): '延喜',
+  (923, 4, 11): '延長',
+  (931, 4, 26): '承平',
+  (938, 5, 22): '天慶',
+  (947, 4, 22): '天暦',
+  (957, 10, 27): '天徳',
+  (961, 2, 16): '応和',
+  (964, 7, 10): '康保',
+  (968, 8, 13): '安和',
+  (970, 3, 25): '天禄',
+  (973, 12, 20): '天延',
+  (976, 7, 13): '貞元',
+  (978, 11, 29): '天元',
+  (983, 4, 15): '永観',
+  (985, 4, 27): '寛和',
+  (987, 4, 5): '永延',
+  (989, 8, 8): '永祚',
+  (990, 11, 7): '正暦',
+  (995, 2, 22): '長徳',
+  (999, 1, 13): '長保',
+  (1004, 7, 20): '寛弘',
+  (1012, 12, 25): '長和',
+  (1017, 4, 23): '寛仁',
+  (1021, 2, 2): '治安',
+  (1024, 7, 13): '万寿',
+  (1028, 7, 25): '長元',
+  (1037, 4, 21): '長暦',
+  (1040, 11, 10): '長久',
+  (1044, 11, 24): '寛徳',
+  (1046, 4, 14): '永承',
+  (1053, 1, 11): '天喜',
+  (1058, 8, 29): '康平',
+  (1065, 8, 2): '治暦',
+  (1069, 4, 13): '延久',
+  (1074, 8, 23): '承保',
+  (1077, 11, 17): '承暦',
+  (1081, 2, 10): '永保',
+  (1084, 2, 7): '応徳',
+  (1087, 4, 7): '寛治',
+  (1094, 12, 15): '嘉保',
+  (1096, 12, 17): '永長',
+  (1097, 11, 21): '承徳',
+  (1099, 8, 28): '康和',
+  (1104, 2, 10): '長治',
+  (1106, 4, 9): '嘉承',
+  (1108, 8, 3): '天仁',
+  (1110, 7, 13): '天永',
+  (1113, 7, 13): '永久',
+  (1118, 4, 3): '元永',
+  (1120, 4, 10): '保安',
+  (1124, 4, 3): '天治',
+  (1126, 1, 22): '大治',
+  (1131, 1, 29): '天承',
+  (1132, 8, 11): '長承',
+  (1135, 4, 27): '保延',
+  (1141, 7, 10): '永治',
+  (1142, 4, 28): '康治',
+  (1144, 2, 23): '天養',
+  (1145, 7, 22): '久安',
+  (1151, 1, 26): '仁平',
+  (1154, 10, 28): '久寿',
+  (1156, 4, 27): '保元',
+  (1159, 4, 20): '平治',
+  (1160, 1, 10): '永暦',
+  (1161, 9, 4): '応保',
+  (1163, 3, 29): '長寛',
+  (1165, 6, 5): '永万',
+  (1166, 8, 27): '仁安',
+  (1169, 4, 8): '嘉応',
+  (1171, 4, 21): '承安',
+  (1175, 7, 28): '安元',
+  (1177, 8, 4): '治承',
+  (1181, 7, 14): '養和',
+  (1182, 5, 27): '寿永',
+  (1184, 4, 16): '元暦',
+  (1185, 8, 14): '文治',
+  (1190, 4, 11): '建久',
+  (1199, 4, 27): '正治',
+  (1201, 2, 13): '建仁',
+  (1204, 2, 20): '元久',
+  (1206, 4, 27): '建永',
+  (1207, 10, 25): '承元',
+  (1211, 3, 9): '建暦',
+  (1213, 12, 6): '建保',
+  (1219, 4, 12): '承久',
+  (1222, 4, 13): '貞応',
+  (1224, 11, 20): '元仁',
+  (1225, 4, 20): '嘉禄',
+  (1227, 12, 10): '安貞',
+  (1229, 3, 5): '寛喜',
+  (1232, 4, 2): '貞永',
+  (1233, 4, 15): '天福',
+  (1234, 11, 5): '文暦',
+  (1235, 9, 19): '嘉禎',
+  (1238, 11, 23): '暦仁',
+  (1239, 2, 7): '延応',
+  (1240, 7, 16): '仁治',
+  (1243, 2, 26): '寛元',
+  (1247, 2, 28): '宝治',
+  (1249, 3, 18): '建長',
+  (1256, 10, 5): '康元',
+  (1257, 3, 14): '正嘉',
+  (1259, 3, 26): '正元',
+  (1260, 4, 13): '文応',
+  (1261, 2, 20): '弘長',
+  (1264, 2, 28): '文永',
+  (1275, 4, 25): '建治',
+  (1278, 2, 29): '弘安',
+  (1288, 4, 28): '正応',
+  (1293, 8, 5): '永仁',
+  (1299, 4, 25): '正安',
+  (1302, 11, 21): '乾元',
+  (1303, 8, 5): '嘉元',
+  (1306, 12, 14): '徳治',
+  (1308, 10, 9): '延慶',
+  (1311, 4, 28): '応長',
+  (1312, 3, 20): '正和',
+  (1317, 2, 3): '文保',
+  (1319, 4, 28): '元応',
+  (1321, 2, 23): '元亨',
+  (1324, 12, 9): '正中',
+  (1326, 4, 26): '嘉暦',
+};
+
+const Map<(int, int, int), String> periodsNanbokuchouNorth = {
+  (1329, 8, 29): '元徳',
+  (1332, 4, 28): '正慶',
+  (1334, 1, 29): '建武',
+  (1338, 8, 28): '暦応',
+  (1342, 4, 27): '康永',
+  (1345, 10, 21): '貞和',
+  (1350, 2, 27): '観応',
+  (1352, 9, 27): '文和',
+  (1356, 3, 28): '延文',
+  (1361, 3, 29): '康安',
+  (1362, 9, 23): '貞治',
+  (1368, 2, 18): '応安',
+  (1375, 2, 27): '永和',
+  (1379, 3, 22): '康暦',
+  (1381, 2, 24): '永徳',
+  (1384, 2, 27): '至徳',
+  (1387, 8, 23): '嘉慶',
+  (1389, 2, 9): '康応',
+  (1390, 3, 26): '明徳',
+};
+
+const Map<(int, int, int), String> periodsNanbokuchouSouth = {
+  (1329, 8, 29): '元徳',
+  (1331, 8, 9): '元弘',
+  (1334, 1, 29): '建武',
+  (1336, 2, 29): '延元',
+  (1340, 4, 28): '興国',
+  (1346, 12, 8): '正平',
+  (1370, 7, 24): '建徳',
+  (1372, 4, 4): '文中',
+  (1375, 5, 27): '天授',
+  (1381, 2, 10): '弘和',
+  (1384, 4, 28): '元中',
+};
+
+const Map<(int, int, int), String> periodsAfterNanbokuchou = {
+  // (1392, ): '室町時代',
+  (1394, 7, 5): '応永',
+  (1428, 4, 27): '正長',
+  (1429, 9, 5): '永享',
+  (1441, 2, 17): '嘉吉',
+  (1444, 2, 5): '文安',
+  (1449, 7, 28): '宝徳',
+  (1452, 7, 25): '享徳',
+  (1455, 7, 25): '康正',
+  (1457, 9, 28): '長禄',
+  (1460, 12, 21): '寛正',
+  (1466, 2, 28): '文正',
+  (1467, 3, 5): '応仁',
+  (1469, 4, 28): '文明',
+  (1487, 7, 20): '長享',
+  (1489, 8, 21): '延徳',
+  (1492, 7, 19): '明応',
+  (1501, 2, 29): '文亀',
+  (1504, 2, 30): '永正',
+  (1521, 8, 23): '大永',
+  (1528, 8, 20): '享禄',
+  (1532, 7, 29): '天文',
+  (1555, 10, 23): '弘治',
+  (1558, 2, 28): '永禄',
+  (1570, 4, 23): '元亀',
+  (1573, 7, 28): '天正',
+  (1592, 12, 8): '文禄',
+  (1596, 10, 27): '慶長',
+  (1615, 7, 13): '元和',
+  (1624, 2, 30): '寛永',
+  (1644, 12, 16): '正保',
+  (1648, 2, 15): '慶安',
+  (1652, 9, 18): '承応',
+  (1655, 4, 13): '明暦',
+  (1658, 7, 23): '万治',
+  (1661, 4, 25): '寛文',
+  (1673, 9, 21): '延宝',
+  (1681, 9, 29): '天和',
+  (1684, 2, 21): '貞享',
+  (1688, 9, 30): '元禄',
+  (1704, 3, 13): '宝永',
+  (1711, 4, 25): '正徳',
+  (1716, 6, 22): '享保',
+  (1736, 4, 28): '元文',
+  (1741, 2, 27): '寛保',
+  (1744, 2, 21): '延享',
+  (1748, 7, 12): '寛延',
+  (1751, 10, 27): '宝暦',
+  (1764, 6, 2): '明和',
+  (1772, 11, 16): '安永',
+  (1781, 4, 2): '天明',
+  (1789, 1, 25): '寛政',
+  (1801, 2, 5): '享和',
+  (1804, 2, 11): '文化',
+  (1818, 4, 22): '文政',
+  (1830, 12, 10): '天保',
+  (1844, 12, 2): '弘化',
+  (1848, 2, 28): '嘉永',
+  (1854, 11, 27): '安政',
+  (1860, 3, 18): '万延',
+  (1861, 2, 19): '文久',
+  (1864, 2, 20): '元治',
+  (1865, 4, 7): '慶応',
+  (1868, 9, 8): '明治',
+  (1912, 7, 30): '大正',
+  (1926, 12, 25): '昭和',
+  (1989, 1, 8): '平成',
+  (2019, 5, 1): '令和',
+};
+
+extension on DateTime {
+  /// Note: In the years between 1336 and 1392, Japan was split in two
+  /// because of an ongoing conflict. As a result, Japan has two timelines
+  /// during these years. Unless you turn off [nanbokuchouPeriodUsesNorth],
+  /// function will give you the timeline from the northern part of Japan
+  /// as a default.
+  ///
+  /// See more info here:
+  /// - https://en.wikipedia.org/wiki/Nanboku-ch%C5%8D_period
+  /// - http://www.kumamotokokufu-h.ed.jp/kumamoto/bungaku/nengoui.html
+  String? japaneseEra({bool nanbokuchouPeriodUsesNorth = true}) {
+    throw UnimplementedError('This function is not implemented yet.');
+
+    if (this.year < 645) {
+      return null;
+    }
+
+    if (this.year < periodsNanbokuchouNorth.keys.first.$1) {
+      // TODO: find first where year <= this.year and jump one period back.
+    }
+  }
+
+  String get japaneseWeekdayPrefix => [
+  	    '月',
+  	    '火',
+  	    '水',
+  	    '木',
+  	    '金',
+  	    '土',
+  	    '日',
+  	  ][weekday - 1];
+
+  /// Returns the date in Japanese format.
+  String japaneseDate({bool showWeekday = false}) => '$month月$day日' + (showWeekday ? '（$japaneseWeekdayPrefix）' : '');
+}

lib/util/number_transliteration.dart

@@ -0,0 +1,58 @@
+const Map<int, String> numberToKanjiMap = {
+  0: '冷',
+  1: '一',
+  2: '二',
+  3: '三',
+  4: '四',
+  5: '五',
+  6: '六',
+  7: '七',
+  8: '八',
+  9: '九',
+  10: '十',
+  100: '百',
+  1000: '千',
+  10000: '万',
+  100000000: '億',
+  1000000000000: '兆',
+};
+
+const Map<int, String> extendedNumberToKanjiMap = {
+  16: '京',
+  20: '垓',
+  24: '𥝱',
+  28: '穣',
+  32: '溝',
+  36: '澗',
+  40: '正',
+  44: '載',
+  48: '極',
+};
+
+const Map<int, String> numberToFormalKanjiMap = {
+  0: '冷',
+  1: '壱',
+  2: '弐',
+  3: '参',
+  4: '肆',
+  5: '伍',
+  6: '陸',
+  7: '漆',
+  8: '捌',
+  9: '玖',
+  10: '拾',
+  100: '陌',
+  1000: '阡',
+  10000: '萬',
+};
+
+const String yenSymbol = '円';
+const String formalYenSymbol = '圓';
+
+String numberToKanji(int number, {bool formal = false}) {
+  throw UnimplementedError();
+}
+
+int kanjiToNumber(String kanji) {
+  throw UnimplementedError();
+}

lib/util/text_filtering.dart

@@ -0,0 +1,28 @@
+/// The string version of a regex that will match any Unified CJK Character.
+/// This includes the ranges (), ()
+///
+/// See https://www.regular-expressions.info/unicode.html
+///
+/// Remember to turn on the unicode flag when making a new RegExp.
+const String rawKanjiRegex = r'\p{Script=Hani}';
+
+/// The string version of a regex that will match any katakana.
+/// This includes the ranges (), ()
+///
+/// See https://www.regular-expressions.info/unicode.html
+///
+/// Remember to turn on the unicode flag when making a new RegExp.
+const String rawKatakanaRegex = r'\p{Script=Katakana}';
+
+/// The string version of a regex that will match any hiragana.
+/// This includes the ranges (), ()
+///
+/// See https://www.regular-expressions.info/unicode.html
+///
+/// Remember to turn on the unicode flag when making a new RegExp.
+const String rawHiraganaRegex = r'\p{Script=Hiragana}';
+
+
+final RegExp kanjiRegex = RegExp(rawKanjiRegex, unicode: true);
+final RegExp katakanaRegex = RegExp(rawKatakanaRegex, unicode: true);
+final RegExp hiraganaRegex = RegExp(rawHiraganaRegex, unicode: true);

test/jouyou_kanji_test.dart

@@ -1,5 +1,5 @@
 import 'package:collection/collection.dart';
-import 'package:jadb/jouyou_kanji.dart';
+import 'package:jadb/util/jouyou_kanji.dart';
 import 'package:test/test.dart';
 
 void main() {

test/search/kanji_search_test.dart

@@ -1,4 +1,4 @@
-import 'package:jadb/jouyou_kanji.dart';
+import 'package:jadb/util/jouyou_kanji.dart';
 import 'package:test/test.dart';
 
 import 'setup_database_connection.dart';

test/util/romaji_transliteration_test.dart

@@ -1,4 +1,4 @@
-import 'package:jadb/romaji_transliteration.dart';
+import 'package:jadb/util/romaji_transliteration.dart';
 import 'package:test/test.dart';
 
 void main() {