lib/_data_ingestion: split parsing and seeding steps

bin/jadb.dart

@@ -4,9 +4,7 @@ import 'dart:io';
 
 import 'package:args/args.dart';
 import 'package:args/command_runner.dart';
-import 'package:jadb/_data_ingestion/jmdict/parser.dart';
-import 'package:jadb/_data_ingestion/kanjidic/parser.dart';
-import 'package:jadb/_data_ingestion/radkfile/parser.dart';
+import 'package:jadb/_data_ingestion/seed_database.dart';
 import 'package:jadb/search.dart';
 import 'package:sqflite_common_ffi/sqflite_ffi.dart';
 import 'package:sqlite3/open.dart';
@@ -58,9 +56,13 @@ class CreateDb extends Command {
       ),
     );
 
-    await addDataFromJMdict(db);
-    await addDataFromRADKFILE(db);
-    await addDataFromKANJIDIC(db);
+    seedData(db).then((_) {
+      print("Database created successfully");
+    }).catchError((error) {
+      print("Error creating database: $error");
+    }).whenComplete(() {
+      db.close();
+    });
   }
 }
 

lib/_data_ingestion/jmdict/seed_data.dart

@@ -1,80 +1,9 @@
 import 'dart:collection';
-import 'dart:io';
 
 import 'package:collection/collection.dart';
+import 'package:jadb/_data_ingestion/jmdict/objects.dart';
 import 'package:jadb/util/romaji_transliteration.dart';
 import 'package:sqflite_common/sqlite_api.dart';
-import 'package:xml/xml.dart';
-
-import 'objects.dart';
-
-/// parse priority values from r_ele and k_ele xml elements
-///
-/// source: http://www.edrdg.org/jmwsgi/edhelp.py?sid=#kw_freq
-List<int?> getPriorityValues(XmlElement e, String prefix) {
-  int? news, ichi, spec, gai, nf;
-  for (final pri in e.findElements('${prefix}_pri')) {
-    final txt = pri.innerText;
-    if (txt.startsWith('news'))
-      news = int.parse(txt.substring(4));
-    else if (txt.startsWith('ichi'))
-      ichi = int.parse(txt.substring(4));
-    else if (txt.startsWith('spec'))
-      spec = int.parse(txt.substring(4));
-    else if (txt.startsWith('gai'))
-      gai = int.parse(txt.substring(3));
-    else if (txt.startsWith('nf')) nf = int.parse(txt.substring(2));
-  }
-  return [news, ichi, spec, gai, nf];
-}
-
-// source: www.edrdg.org/jmwsgi/edhelp.py?sid=#syn_xref
-XRefParts parseXrefParts(String s) {
-  final parts = s.split('・');
-  late final XRefParts result;
-  switch (parts.length) {
-    case 1:
-      result = parts[0].contains(kanaRegex)
-          ? XRefParts(readingRef: parts[0])
-          : XRefParts(kanjiRef: parts[0]);
-      break;
-
-    case 2:
-      if (int.tryParse(parts[1]) != null) {
-        if (parts[0].contains(kanaRegex)) {
-          result = XRefParts(
-            readingRef: parts[0],
-            senseOrderNum: int.parse(parts[1]),
-          );
-        } else {
-          result = XRefParts(
-            kanjiRef: parts[0],
-            senseOrderNum: int.parse(parts[1]),
-          );
-        }
-      } else {
-        result = XRefParts(
-          kanjiRef: parts[0],
-          readingRef: parts[1],
-        );
-      }
-      break;
-
-    case 3:
-      result = XRefParts(
-        kanjiRef: parts[0],
-        readingRef: parts[1],
-        senseOrderNum: int.parse(parts[2]),
-      );
-      break;
-
-    default:
-      result = XRefParts();
-      break;
-  }
-
-  return result;
-}
 
 class ResolvedXref {
   Entry entry;
@@ -139,138 +68,7 @@ ResolvedXref resolveXref(
   }
 }
 
-List<Entry> parseXML(XmlElement root) {
-  final List<Entry> entries = [];
-
-  int senseId = 0;
-
-  for (final entry in root.childElements) {
-    final entryId = int.parse(entry.findElements('ent_seq').first.innerText);
-
-    final List<KanjiElement> kanjiEls = [];
-    final List<ReadingElement> readingEls = [];
-    final List<Sense> senses = [];
-
-    for (final (kanjiNum, k_ele) in entry.findElements('k_ele').indexed) {
-      final ke_pri = getPriorityValues(k_ele, 'ke');
-      kanjiEls.add(
-        KanjiElement(
-          orderNum: kanjiNum + 1,
-          info: k_ele
-              .findElements('ke_inf')
-              .map((e) => e.innerText.substring(1, e.innerText.length - 1))
-              .toList(),
-          reading: k_ele.findElements('keb').first.innerText,
-          news: ke_pri[0],
-          ichi: ke_pri[1],
-          spec: ke_pri[2],
-          gai: ke_pri[3],
-          nf: ke_pri[4],
-        ),
-      );
-    }
-
-    for (final (orderNum, r_ele) in entry.findElements('r_ele').indexed) {
-      final re_pri = getPriorityValues(r_ele, 're');
-      final readingDoesNotMatchKanji =
-          r_ele.findElements('re_nokanji').isNotEmpty;
-      readingEls.add(
-        ReadingElement(
-          orderNum: orderNum + 1,
-          readingDoesNotMatchKanji: readingDoesNotMatchKanji,
-          info: r_ele
-              .findElements('re_inf')
-              .map((e) => e.innerText.substring(1, e.innerText.length - 1))
-              .toList(),
-          restrictions:
-              r_ele.findElements('re_restr').map((e) => e.innerText).toList(),
-          reading: r_ele.findElements('reb').first.innerText,
-          news: re_pri[0],
-          ichi: re_pri[1],
-          spec: re_pri[2],
-          gai: re_pri[3],
-          nf: re_pri[4],
-        ),
-      );
-    }
-
-    for (final (orderNum, sense) in entry.findElements('sense').indexed) {
-      senseId++;
-      final result = Sense(
-        id: senseId,
-        orderNum: orderNum + 1,
-        restrictedToKanji:
-            sense.findElements('stagk').map((e) => e.innerText).toList(),
-        restrictedToReading:
-            sense.findElements('stagr').map((e) => e.innerText).toList(),
-        pos: sense
-            .findElements('pos')
-            .map((e) => e.innerText.substring(1, e.innerText.length - 1))
-            .toList(),
-        misc: sense
-            .findElements('misc')
-            .map((e) => e.innerText.substring(1, e.innerText.length - 1))
-            .toList(),
-        dialects: sense
-            .findElements('dial')
-            .map((e) => e.innerText.substring(1, e.innerText.length - 1))
-            .toList(),
-        info: sense.findElements('s_inf').map((e) => e.innerText).toList(),
-        languageSource: sense
-            .findElements('lsource')
-            .map(
-              (e) => LanguageSource(
-                language: e.getAttribute('xml:lang') ?? 'eng',
-                fullyDescribesSense: e.getAttribute('ls_type') == 'part',
-                constructedFromSmallerWords: e.getAttribute('ls_wasei') == 'y',
-              ),
-            )
-            .toList(),
-        glossary: sense
-            .findElements('gloss')
-            .map(
-              (e) => Glossary(
-                language: e.getAttribute('xml:lang') ?? 'eng',
-                phrase: e.innerText,
-                type: e.getAttribute('g_type'),
-              ),
-            )
-            .toList(),
-        antonyms: sense
-            .findElements('ant')
-            .map((e) => parseXrefParts(e.innerText))
-            .toList(),
-        seeAlso: sense
-            .findElements('xref')
-            .map((e) => parseXrefParts(e.innerText))
-            .toList(),
-      );
-
-      if (result.isEmpty) {
-        print(
-          'WARNING: Sense $senseId for entry $entryId is empty, '
-          'kanji: ${kanjiEls.map((e) => e.reading).join(', ')}, '
-          'reading: ${readingEls.map((e) => e.reading).join(', ')}',
-        );
-      } else {
-        senses.add(result);
-      }
-    }
-
-    entries.add(
-      Entry(
-        id: entryId,
-        kanji: kanjiEls,
-        readings: readingEls,
-        senses: senses,
-      ),
-    );
-  }
-
-  return entries;
-}
-
-Future<void> insertIntoDB(List<Entry> entries, Database db) async {
+Future<void> seedJMDictData(List<Entry> entries, Database db) async {
   print('  [JMdict] Batch 1 - Kanji and readings');
   Batch b = db.batch();
   for (final e in entries) {
@@ -471,17 +269,3 @@ Future<void> insertIntoDB(List<Entry> entries, Database db) async {
 
   await b.commit();
 }
-
-Future<void> addDataFromJMdict(Database db) async {
-  print('[JMdict] Reading file content...');
-  String rawXML = File('data/tmp/JMdict.xml').readAsStringSync();
-
-  print('[JMdict] Parsing XML tags...');
-  XmlElement root = XmlDocument.parse(rawXML).getElement('JMdict')!;
-
-  print('[JMdict] Parsing XML content...');
-  final entries = parseXML(root);
-
-  print('[JMdict] Writing to database...');
-  await insertIntoDB(entries, db);
-}

lib/_data_ingestion/jmdict/xml_parser.dart

@@ -0,0 +1,201 @@
+import 'package:jadb/_data_ingestion/jmdict/objects.dart';
+import 'package:xml/xml.dart';
+
+/// parse priority values from r_ele and k_ele xml elements
+///
+/// source: http://www.edrdg.org/jmwsgi/edhelp.py?sid=#kw_freq
+List<int?> getPriorityValues(XmlElement e, String prefix) {
+  int? news, ichi, spec, gai, nf;
+  for (final pri in e.findElements('${prefix}_pri')) {
+    final txt = pri.innerText;
+    if (txt.startsWith('news'))
+      news = int.parse(txt.substring(4));
+    else if (txt.startsWith('ichi'))
+      ichi = int.parse(txt.substring(4));
+    else if (txt.startsWith('spec'))
+      spec = int.parse(txt.substring(4));
+    else if (txt.startsWith('gai'))
+      gai = int.parse(txt.substring(3));
+    else if (txt.startsWith('nf')) nf = int.parse(txt.substring(2));
+  }
+  return [news, ichi, spec, gai, nf];
+}
+
+// source: www.edrdg.org/jmwsgi/edhelp.py?sid=#syn_xref
+XRefParts parseXrefParts(String s) {
+  final parts = s.split('・');
+  late final XRefParts result;
+  switch (parts.length) {
+    case 1:
+      result = parts[0].contains(kanaRegex)
+          ? XRefParts(readingRef: parts[0])
+          : XRefParts(kanjiRef: parts[0]);
+      break;
+
+    case 2:
+      if (int.tryParse(parts[1]) != null) {
+        if (parts[0].contains(kanaRegex)) {
+          result = XRefParts(
+            readingRef: parts[0],
+            senseOrderNum: int.parse(parts[1]),
+          );
+        } else {
+          result = XRefParts(
+            kanjiRef: parts[0],
+            senseOrderNum: int.parse(parts[1]),
+          );
+        }
+      } else {
+        result = XRefParts(
+          kanjiRef: parts[0],
+          readingRef: parts[1],
+        );
+      }
+      break;
+
+    case 3:
+      result = XRefParts(
+        kanjiRef: parts[0],
+        readingRef: parts[1],
+        senseOrderNum: int.parse(parts[2]),
+      );
+      break;
+
+    default:
+      result = XRefParts();
+      break;
+  }
+
+  return result;
+}
+
+List<Entry> parseJMDictData(XmlElement root) {
+  final List<Entry> entries = [];
+
+  int senseId = 0;
+
+  for (final entry in root.childElements) {
+    final entryId = int.parse(entry.findElements('ent_seq').first.innerText);
+
+    final List<KanjiElement> kanjiEls = [];
+    final List<ReadingElement> readingEls = [];
+    final List<Sense> senses = [];
+
+    for (final (kanjiNum, k_ele) in entry.findElements('k_ele').indexed) {
+      final ke_pri = getPriorityValues(k_ele, 'ke');
+      kanjiEls.add(
+        KanjiElement(
+          orderNum: kanjiNum + 1,
+          info: k_ele
+              .findElements('ke_inf')
+              .map((e) => e.innerText.substring(1, e.innerText.length - 1))
+              .toList(),
+          reading: k_ele.findElements('keb').first.innerText,
+          news: ke_pri[0],
+          ichi: ke_pri[1],
+          spec: ke_pri[2],
+          gai: ke_pri[3],
+          nf: ke_pri[4],
+        ),
+      );
+    }
+
+    for (final (orderNum, r_ele) in entry.findElements('r_ele').indexed) {
+      final re_pri = getPriorityValues(r_ele, 're');
+      final readingDoesNotMatchKanji =
+          r_ele.findElements('re_nokanji').isNotEmpty;
+      readingEls.add(
+        ReadingElement(
+          orderNum: orderNum + 1,
+          readingDoesNotMatchKanji: readingDoesNotMatchKanji,
+          info: r_ele
+              .findElements('re_inf')
+              .map((e) => e.innerText.substring(1, e.innerText.length - 1))
+              .toList(),
+          restrictions:
+              r_ele.findElements('re_restr').map((e) => e.innerText).toList(),
+          reading: r_ele.findElements('reb').first.innerText,
+          news: re_pri[0],
+          ichi: re_pri[1],
+          spec: re_pri[2],
+          gai: re_pri[3],
+          nf: re_pri[4],
+        ),
+      );
+    }
+
+    for (final (orderNum, sense) in entry.findElements('sense').indexed) {
+      senseId++;
+      final result = Sense(
+        id: senseId,
+        orderNum: orderNum + 1,
+        restrictedToKanji:
+            sense.findElements('stagk').map((e) => e.innerText).toList(),
+        restrictedToReading:
+            sense.findElements('stagr').map((e) => e.innerText).toList(),
+        pos: sense
+            .findElements('pos')
+            .map((e) => e.innerText.substring(1, e.innerText.length - 1))
+            .toList(),
+        misc: sense
+            .findElements('misc')
+            .map((e) => e.innerText.substring(1, e.innerText.length - 1))
+            .toList(),
+        dialects: sense
+            .findElements('dial')
+            .map((e) => e.innerText.substring(1, e.innerText.length - 1))
+            .toList(),
+        info: sense.findElements('s_inf').map((e) => e.innerText).toList(),
+        languageSource: sense
+            .findElements('lsource')
+            .map(
+              (e) => LanguageSource(
+                language: e.getAttribute('xml:lang') ?? 'eng',
+                fullyDescribesSense: e.getAttribute('ls_type') == 'part',
+                constructedFromSmallerWords: e.getAttribute('ls_wasei') == 'y',
+              ),
+            )
+            .toList(),
+        glossary: sense
+            .findElements('gloss')
+            .map(
+              (e) => Glossary(
+                language: e.getAttribute('xml:lang') ?? 'eng',
+                phrase: e.innerText,
+                type: e.getAttribute('g_type'),
+              ),
+            )
+            .toList(),
+        antonyms: sense
+            .findElements('ant')
+            .map((e) => parseXrefParts(e.innerText))
+            .toList(),
+        seeAlso: sense
+            .findElements('xref')
+            .map((e) => parseXrefParts(e.innerText))
+            .toList(),
+      );
+
+      if (result.isEmpty) {
+        print(
+          'WARNING: Sense $senseId for entry $entryId is empty, '
+          'kanji: ${kanjiEls.map((e) => e.reading).join(', ')}, '
+          'reading: ${readingEls.map((e) => e.reading).join(', ')}',
+        );
+      } else {
+        senses.add(result);
+      }
+    }
+
+    entries.add(
+      Entry(
+        id: entryId,
+        kanji: kanjiEls,
+        readings: readingEls,
+        senses: senses,
+      ),
+    );
+  }
+
+  return entries;
+}

lib/_data_ingestion/kanjidic/seed_data.dart

@@ -0,0 +1,74 @@
+import 'package:sqflite_common/sqlite_api.dart';
+
+import 'objects.dart';
+
+Future<void> seedKANJIDICData(List<Character> characters, Database db) async {
+  final b = db.batch();
+  for (final c in characters) {
+    // if (c.dictionaryReferences.any((e) =>
+    //     c.dictionaryReferences
+    //         .where((e2) => e.kanji == e2.kanji && e.type == e2.type)
+    //         .length >
+    //     1)) {
+    //       print(c.dictionaryReferences.map((e) => e.sqlValue).toList());
+    //     }
+    b.insert(TableNames.character, c.sqlValue);
+    for (final n in c.radicalName) {
+      b.insert(TableNames.radicalName, {'kanji': c.literal, 'name': n});
+    }
+    for (final cp in c.codepoints) {
+      b.insert(TableNames.codepoint, cp.sqlValue);
+    }
+    for (final r in c.radicals) {
+      b.insert(TableNames.radical, r.sqlValue);
+    }
+    for (final sm in c.strokeMiscounts) {
+      b.insert(
+        TableNames.strokeMiscount,
+        {
+          'kanji': c.literal,
+          'strokeCount': sm,
+        },
+      );
+    }
+    for (final v in c.variants) {
+      b.insert(TableNames.variant, v.sqlValue);
+    }
+    for (final dr in c.dictionaryReferences) {
+      // There are duplicate entries here
+      b.insert(
+        TableNames.dictionaryReference,
+        dr.sqlValue,
+        conflictAlgorithm: ConflictAlgorithm.ignore,
+      );
+    }
+    for (final drm in c.dictionaryReferencesMoro) {
+      b.insert(TableNames.dictionaryReferenceMoro, drm.sqlValue);
+    }
+    for (final q in c.querycodes) {
+      b.insert(TableNames.queryCode, q.sqlValue);
+    }
+    for (final r in c.readings) {
+      b.insert(TableNames.reading, r.sqlValue);
+    }
+    for (final k in c.kunyomi) {
+      b.insert(TableNames.kunyomi, k.sqlValue);
+    }
+    for (final o in c.onyomi) {
+      b.insert(TableNames.onyomi, o.sqlValue);
+    }
+    for (final m in c.meanings) {
+      b.insert(TableNames.meaning, m.sqlValue);
+    }
+    for (final n in c.nanori) {
+      b.insert(
+        TableNames.nanori,
+        {
+          'kanji': c.literal,
+          'nanori': n,
+        },
+      );
+    }
+  }
+  b.commit();
+}

lib/_data_ingestion/kanjidic/xml_parser.dart

@@ -1,12 +1,7 @@
-import 'dart:io';
-
-import 'package:sqflite_common/sqlite_api.dart';
+import 'package:jadb/_data_ingestion/kanjidic/objects.dart';
 import 'package:xml/xml.dart';
-import 'package:collection/collection.dart';
 
-import 'objects.dart';
-
-List<Character> transformXML(XmlElement root) {
+List<Character> parseKANJIDICData(XmlElement root) {
   final List<Character> result = [];
   for (final c in root.findElements('character')) {
     final kanji = c.findElements('literal').first.innerText;
@@ -170,88 +165,3 @@ List<Character> transformXML(XmlElement root) {
   }
   return result;
 }
-
-Future<void> insertIntoDB(List<Character> characters, Database db) async {
-  final b = db.batch();
-  for (final c in characters) {
-    // if (c.dictionaryReferences.any((e) =>
-    //     c.dictionaryReferences
-    //         .where((e2) => e.kanji == e2.kanji && e.type == e2.type)
-    //         .length >
-    //     1)) {
-    //       print(c.dictionaryReferences.map((e) => e.sqlValue).toList());
-    //     }
-    b.insert(TableNames.character, c.sqlValue);
-    for (final n in c.radicalName) {
-      b.insert(TableNames.radicalName, {'kanji': c.literal, 'name': n});
-    }
-    for (final cp in c.codepoints) {
-      b.insert(TableNames.codepoint, cp.sqlValue);
-    }
-    for (final r in c.radicals) {
-      b.insert(TableNames.radical, r.sqlValue);
-    }
-    for (final sm in c.strokeMiscounts) {
-      b.insert(
-        TableNames.strokeMiscount,
-        {
-          'kanji': c.literal,
-          'strokeCount': sm,
-        },
-      );
-    }
-    for (final v in c.variants) {
-      b.insert(TableNames.variant, v.sqlValue);
-    }
-    for (final dr in c.dictionaryReferences) {
-      // There are duplicate entries here
-      b.insert(
-        TableNames.dictionaryReference,
-        dr.sqlValue,
-        conflictAlgorithm: ConflictAlgorithm.ignore,
-      );
-    }
-    for (final drm in c.dictionaryReferencesMoro) {
-      b.insert(TableNames.dictionaryReferenceMoro, drm.sqlValue);
-    }
-    for (final q in c.querycodes) {
-      b.insert(TableNames.queryCode, q.sqlValue);
-    }
-    for (final r in c.readings) {
-      b.insert(TableNames.reading, r.sqlValue);
-    }
-    for (final k in c.kunyomi) {
-      b.insert(TableNames.kunyomi, k.sqlValue);
-    }
-    for (final o in c.onyomi) {
-      b.insert(TableNames.onyomi, o.sqlValue);
-    }
-    for (final m in c.meanings) {
-      b.insert(TableNames.meaning, m.sqlValue);
-    }
-    for (final n in c.nanori) {
-      b.insert(
-        TableNames.nanori,
-        {
-          'kanji': c.literal,
-          'nanori': n,
-        },
-      );
-    }
-  }
-  b.commit();
-}
-
-Future<void> addDataFromKANJIDIC(Database db) async {
-  print('[KANJIDIC2] Reading file...');
-  String rawXML = File('data/tmp/kanjidic2.xml').readAsStringSync();
-
-  print('[KANJIDIC2] Parsing XML...');
-  XmlElement root = XmlDocument.parse(rawXML).getElement('kanjidic2')!;
-
-  print('[KANJIDIC2] Transforming data...');
-  final entries = transformXML(root);
-
-  print('[KANJIDIC2] Writing to database...');
-  await insertIntoDB(entries, db);
-}

lib/_data_ingestion/radkfile/parser.dart

@@ -1,32 +1,10 @@
 import 'dart:io';
 
-import 'package:sqflite_common/sqlite_api.dart';
-
-Future<void> addDataFromRADKFILE(Database db) async {
+Iterable<String> parseRADKFILEBlocks(File radkfile) {
   final String content = File('data/tmp/radkfile_utf8').readAsStringSync();
+
   final Iterable<String> blocks =
       content.replaceAll(RegExp(r'^#.*$'), '').split(r'$').skip(2);
 
-  print('[RADKFILE] Writing to database...');
-  final b = db.batch();
-
-  for (final block in blocks) {
-    final String radical = block[1];
-    final List<String> kanjiList = block
-        .replaceFirst(RegExp(r'.*\n'), '')
-        .split('')
-      ..removeWhere((e) => e == '' || e == '\n');
-
-    for (final kanji in kanjiList.toSet()) {
-      b.insert(
-        'RADKFILE',
-        {
-          'radical': radical,
-          'kanji': kanji,
-        },
-      );
-    }
-  }
-
-  b.commit();
+  return blocks;
 }

lib/_data_ingestion/radkfile/seed_data.dart

@@ -0,0 +1,28 @@
+import 'package:sqflite_common/sqlite_api.dart';
+
+Future<void> seedRADKFILEData(
+  Iterable<String> blocks,
+  Database db,
+) async {
+  final b = db.batch();
+
+  for (final block in blocks) {
+    final String radical = block[1];
+    final List<String> kanjiList = block
+        .replaceFirst(RegExp(r'.*\n'), '')
+        .split('')
+      ..removeWhere((e) => e == '' || e == '\n');
+
+    for (final kanji in kanjiList.toSet()) {
+      b.insert(
+        'RADKFILE',
+        {
+          'radical': radical,
+          'kanji': kanji,
+        },
+      );
+    }
+  }
+
+  b.commit();
+}

lib/_data_ingestion/seed_database.dart

@@ -0,0 +1,55 @@
+import 'dart:io';
+
+import 'package:jadb/_data_ingestion/jmdict/seed_data.dart';
+import 'package:jadb/_data_ingestion/jmdict/xml_parser.dart';
+import 'package:jadb/_data_ingestion/kanjidic/seed_data.dart';
+import 'package:jadb/_data_ingestion/kanjidic/xml_parser.dart';
+import 'package:jadb/_data_ingestion/radkfile/parser.dart';
+import 'package:jadb/_data_ingestion/radkfile/seed_data.dart';
+import 'package:sqflite_common/sqlite_api.dart';
+import 'package:xml/xml.dart';
+
+Future<void> seedData(Database db) async {
+  await parseAndSeedDataFromJMdict(db);
+  await parseAndSeedDataFromRADKFILE(db);
+  await parseAndSeedDataFromKANJIDIC(db);
+}
+
+Future<void> parseAndSeedDataFromJMdict(Database db) async {
+  print('[JMdict] Reading file content...');
+  String rawXML = File('data/tmp/JMdict.xml').readAsStringSync();
+
+  print('[JMdict] Parsing XML tags...');
+  XmlElement root = XmlDocument.parse(rawXML).getElement('JMdict')!;
+
+  print('[JMdict] Parsing XML content...');
+  final entries = parseJMDictData(root);
+
+  print('[JMdict] Writing to database...');
+  await seedJMDictData(entries, db);
+}
+
+Future<void> parseAndSeedDataFromKANJIDIC(Database db) async {
+  print('[KANJIDIC2] Reading file...');
+  String rawXML = File('data/tmp/kanjidic2.xml').readAsStringSync();
+
+  print('[KANJIDIC2] Parsing XML...');
+  XmlElement root = XmlDocument.parse(rawXML).getElement('kanjidic2')!;
+
+  print('[KANJIDIC2] Parsing XML content...');
+  final entries = parseKANJIDICData(root);
+
+  print('[KANJIDIC2] Writing to database...');
+  await seedKANJIDICData(entries, db);
+}
+
+Future<void> parseAndSeedDataFromRADKFILE(Database db) async {
+  print('[RADKFILE] Reading file...');
+  File raw = File('data/tmp/RADKFILE');
+
+  print('[RADKFILE] Parsing content...');
+  final blocks = parseRADKFILEBlocks(raw);
+
+  print('[RADKFILE] Writing to database...');
+  seedRADKFILEData(blocks, db);
+}