_data_ingestion: retrieve input paths from env

lib/_data_ingestion/seed_database.dart

@@ -23,8 +23,13 @@ Future<void> seedData(Database db) async {
 }
 
 Future<void> parseAndSeedDataFromJMdict(Database db) async {
+  final jmdictPath = Platform.environment['JMDICT_PATH'] ?? 'data/JMdict.xml';
+  if (!File(jmdictPath).existsSync()) {
+    throw Exception('JMdict file not found at $jmdictPath');
+  }
+
   print('[JMdict] Reading file content...');
-  final String rawXML = File('data/JMdict.xml').readAsStringSync();
+  final String rawXML = File(jmdictPath).readAsStringSync();
 
   print('[JMdict] Parsing XML tags...');
   final XmlElement root = XmlDocument.parse(rawXML).getElement('JMdict')!;
@@ -37,8 +42,14 @@ Future<void> parseAndSeedDataFromJMdict(Database db) async {
 }
 
 Future<void> parseAndSeedDataFromKANJIDIC(Database db) async {
+  final kanjidicPath =
+      Platform.environment['KANJIDIC_PATH'] ?? 'data/kanjidic2.xml';
+  if (!File(kanjidicPath).existsSync()) {
+    throw Exception('KANJIDIC file not found at $kanjidicPath');
+  }
+
   print('[KANJIDIC2] Reading file...');
-  final String rawXML = File('data/kanjidic2.xml').readAsStringSync();
+  final String rawXML = File(kanjidicPath).readAsStringSync();
 
   print('[KANJIDIC2] Parsing XML...');
   final XmlElement root = XmlDocument.parse(rawXML).getElement('kanjidic2')!;
@@ -51,8 +62,13 @@ Future<void> parseAndSeedDataFromKANJIDIC(Database db) async {
 }
 
 Future<void> parseAndSeedDataFromRADKFILE(Database db) async {
+  final radkfilePath = Platform.environment['RADKFILE_PATH'] ?? 'data/RADKFILE';
+  if (!File(radkfilePath).existsSync()) {
+    throw Exception('RADKFILE not found at $radkfilePath');
+  }
+
   print('[RADKFILE] Reading file...');
-  final File raw = File('data/RADKFILE');
+  final File raw = File(radkfilePath);
 
   print('[RADKFILE] Parsing content...');
   final blocks = parseRADKFILEBlocks(raw);
@@ -62,13 +78,19 @@ Future<void> parseAndSeedDataFromRADKFILE(Database db) async {
 }
 
 Future<void> parseAndSeedDataFromTanosJLPT(Database db) async {
+  final tanosJlptPath =
+      Platform.environment['TANOS_JLPT_PATH'] ?? 'data/tanos-jlpt';
+  if (!Directory(tanosJlptPath).existsSync()) {
+    throw Exception('TANOS-JLPT directory not found at $tanosJlptPath');
+  }
+
   print('[TANOS-JLPT] Reading files...');
   final Map<String, File> files = {
-    'N1': File('data/tanos-jlpt/n1.csv'),
-    'N2': File('data/tanos-jlpt/n2.csv'),
-    'N3': File('data/tanos-jlpt/n3.csv'),
-    'N4': File('data/tanos-jlpt/n4.csv'),
-    'N5': File('data/tanos-jlpt/n5.csv'),
+    'N1': File('$tanosJlptPath/n1.csv'),
+    'N2': File('$tanosJlptPath/n2.csv'),
+    'N3': File('$tanosJlptPath/n3.csv'),
+    'N4': File('$tanosJlptPath/n4.csv'),
+    'N5': File('$tanosJlptPath/n5.csv'),
   };
 
   print('[TANOS-JLPT] Parsing content...');

lib/cli/commands/create_tanos_jlpt_mappings.dart

@@ -42,12 +42,18 @@ class CreateTanosJlptMappings extends Command {
 
     final useOverrides = argResults!.flag('overrides');
 
+    final tanosJlptPath =
+        Platform.environment['TANOS_JLPT_PATH'] ?? 'data/tanos-jlpt';
+    if (!Directory(tanosJlptPath).existsSync()) {
+      throw Exception('TANOS-JLPT directory not found at $tanosJlptPath');
+    }
+
     final Map<String, File> files = {
-      'N1': File('data/tanos-jlpt/n1.csv'),
-      'N2': File('data/tanos-jlpt/n2.csv'),
-      'N3': File('data/tanos-jlpt/n3.csv'),
-      'N4': File('data/tanos-jlpt/n4.csv'),
-      'N5': File('data/tanos-jlpt/n5.csv'),
+      'N1': File('$tanosJlptPath/n1.csv'),
+      'N2': File('$tanosJlptPath/n2.csv'),
+      'N3': File('$tanosJlptPath/n3.csv'),
+      'N4': File('$tanosJlptPath/n4.csv'),
+      'N5': File('$tanosJlptPath/n5.csv'),
     };
 
     final rankedWords = await parseJLPTRankedWords(files);

nix/database.nix

@@ -20,18 +20,22 @@ stdenvNoCC.mkDerivation {
   ];
 
   env = {
+    JMDICT_PATH = "${jmdict}/JMdict.xml";
     JMDICT_VERSION = jmdict.version;
     JMDICT_DATE = jmdict.date;
     JMDICT_HASH = jmdict.hash;
 
+    KANJIDIC_PATH = "${kanjidic2}/kanjidic2.xml";
     KANJIDIC_VERSION = kanjidic2.version;
     KANJIDIC_DATE = kanjidic2.date;
     KANJIDIC_HASH = kanjidic2.hash;
 
+    RADKFILE_PATH = "${radkfile}/RADKFILE";
     RADKFILE_VERSION = radkfile.version;
     RADKFILE_DATE = radkfile.date;
     RADKFILE_HASH = radkfile.hash;
 
+    TANOS_JLPT_PATH = toString tanos-jlpt;
     TANOS_JLPT_VERSION = tanos-jlpt.version;
     TANOS_JLPT_DATE = tanos-jlpt.date;
     TANOS_JLPT_HASH = tanos-jlpt.hash;
@@ -40,12 +44,6 @@ stdenvNoCC.mkDerivation {
   buildPhase = ''
     runHook preBuild
 
-    mkdir -p data
-    ln -s '${jmdict}'/* data/
-    ln -s '${kanjidic2}'/* data/
-    ln -s '${radkfile}'/* data/
-    ln -s '${tanos-jlpt}' data/tanos-jlpt
-
     for migration in migrations/*.sql; do
       sqlite3 jadb.sqlite < "$migration"
     done